A first connection is established between a client device and server. The client sends a user query (a first message) to the server and the server sends a first prompt based thereon to a LLM. In response, the LLM invokes a tool call for execution by the client device. The server transmits the tool call to the client device and the first connection is closed. The client executes the tool call. A second connection is established between the client device and server. The client device sends a second message to the server. The server determines that the second message includes a tool response in reply to the tool call and transmits a message including the tool response and at least a portion of stored conversation history to the LLM. The LLM sends an assistant message in reply and the server transmits a first assistant message to the client device.
(1) Downloadable software for use in e-commerce and the retail industry to allow users to perform business management and to automate business management tasks via a global computer network, namely, inventory management, order fulfillment and shipment tracking, customer tracking, creation of advertising content for third parties, fraud detection and prevention, creation of workflow templates, sales tracking, customer review tracking and management, and electronic messaging; Downloadable software for use in e-commerce and the retail industry to allow users to perform business management and to automate business management tasks via a global computer network, namely, managing the user's business contacts, business information and business relationships; Downloadable software for use in e-commerce and the retail industry to allow users to perform business management and to automate business management tasks via a global computer network, namely, online promotion, advertising and marketing, namely, for search engine and web site optimization, targeted and retargeting advertising, electronic messaging and text marketing; Downloadable software for use in e-commerce and the retail industry to allow users to perform business management and to automate business management tasks via a global computer network, namely, managing a loyalty program, rewards and offers to support retailers' sales; Downloadable software for use in e-commerce and the retail industry that uses artificial intelligence to understand general and pre-defined user queries and formulate responses (1) Providing online non-downloadable software for use in e-commerce and the retail industry to allow users to perform business management to automate business management tasks via a global computer network, namely, inventory management, order fulfillment and tracking, customer tracking, creation of advertising signage content for third parties, fraud detection and prevention, creation of workflow templates, sales tracking, customer review tracking and management, and electronic messaging; Providing online non-downloadable software for use in e-commerce and the retail industry to allow users to perform business management to automate business management tasks via a global computer network, namely, management of the user's business contacts, business information and business relationships; Providing online non-downloadable software for use in e-commerce and the retail industry to allow users to perform business management to automate business management tasks via a global computer network, namely, online promotion, advertising and marketing, namely, for search engine and web site optimization, targeted and retargeting advertising, electronic messaging and text marketing; Providing online non-downloadable software for use in e-commerce and the retail industry to allow users to perform business management to automate business management tasks via a global computer network, namely, managing a loyalty program, rewards and offers to support retailers' sales; Providing online non-downloadable software that uses artificial intelligence to understand general and pre-defined user queries and formulate responses
41 - Education, entertainment, sporting and cultural services
Goods & Services
Clothing, namely, T-shirts, hats, caps, windbreakers, racing
jerseys. Advertising services, namely, providing advertising space on
an automobile participating in automobile racing events and
exhibitions; promotional sponsorship of racing events;
online retail store services for sports equipment, clothing,
headwear, and toys; retail store services for sports
equipment, clothing, headwear, and toys. Entertainment services in the nature of professional
athletes competing in sports car races; entertainment
services in the nature of participating in professional
automobile races and automobile racing exhibitions;
provision of information regarding automobile racing via
website; providing sports information online; provision of
information relating to motor racing; entertainment in the
nature of organizing and hosting social entertainment events
in the field of automobile racing.
4.
Display screen with animated graphical user interface
A computer system maintains adaptation models (e.g., low-rank adaptation (LoRA) models), where each adaptation model includes a set of weights configured to modify parameters of a generative model (e.g., a large-language model) to cause the generative model to generate output (e.g., text) having a corresponding property. The computer system presents a set of manipulable user-interface controls that allow configuration of properties of model-generated output. Output of the generative model is modified using adaptation models that are selected based on a state of the user-interface controls as manipulated. A preview of generative model output may be provided that corresponds to the current state of the user-interface controls during presentation and manipulation thereof.
A large language model (LLM) may be used to classify an input into one of a plurality of categories. However, given the machine-learning operation of the LLM, the output of the LLM does not represent a definitive statement, but is based on probability computations of the machine learning model. Therefore, the classification performed by the LLM might not be correct. Classification into the wrong category by the LLM results in downstream technical problems. In some implementations, when an LLM generates a response that classifies an input, one or more probability values associated with a token that forms the basis of the response may be used to determine a confidence value. The confidence value is indicative of confidence in the classification performed by the LLM. An action may be taken based on the confidence value.
G06F 16/353 - ClusteringClassification into predefined classes
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
A system and method are provided for responding to unmatched queries. The method includes determining that a query compared to a knowledge store of query and response pairs is unmatched, determining a candidate response to the query, determining a confidence value associated with the candidate response, and responding to the query based on how the confidence value compares to a threshold value.
Described herein are systems and methods for generating and transmitting media data feeds location-based privacy settings. Embodiments generate, store, and reference location-based privacy settings that instruct the computing device to generate obfuscations in the media data. The obfuscations may include computer-generated or user gesture-generated obfuscation regions that instruct the computing device to apply the obfuscations to portions of the video feed. The computing device may be pre-configured to recognize certain objects or regions (or portions thereof) and remove, blur, or substitute them from the live video stream or 3D data according to privacy settings. The privacy settings may be relative to the location in which the user and computing device are situated. In operation, the computing device may determine the location and then apply the location-specific privacy settings to obfuscate a portion of the video feed while being generated and transmitted.
G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
G06F 3/04815 - Interaction with a metaphor-based environment or interaction object displayed as three-dimensional, e.g. changing the user viewpoint with respect to the environment or object
G06V 40/20 - Movements or behaviour, e.g. gesture recognition
10.
Computer System, Computer-Implemented Method, and Computer Readable Media for Managing Query Responses
A system and method are provided for responding to unmatched queries. The method includes determining that a query compared to a knowledge store of query and response pairs is unmatched, adding the query to a collection of unmatched queries, using the collection of unmatched queries to identify a group of aggregated unmatched queries, determining a representative query for the group of aggregated unmatched queries, and using the representative query to obtain a response to the representative query.
Methods and systems for the automatic deduplication of a set of data records corresponding to a plurality of unique items are described. An automated engine generates corresponding metadata for each data record in the set of data records. A graph network is generated based on the set of data records, including the generated metadata, where the graph network comprises a plurality of nodes and a plurality of edges connecting the nodes, each node corresponding to a respective data record of the set of data records and each edge representing a relationship between two associated nodes. A subset of nodes in the graph network is assigned to a respective item of the plurality of unique items and verified using an LLM. The graph network is updated, based on the verification. The disclosed methods and systems enable the effective deduplication of data records in a computationally efficient manner.
A system and method are provided for responding to unmatched queries. The method includes determining that a query compared to a knowledge store of query and response pairs is unmatched, determining a candidate response to the query, determining a confidence value associated with the candidate response, and responding to the query based on how the confidence value compares to a threshold value.
Methods and systems for implementing an action prediction framework associated with a user are described. An action prediction model generates a plurality of synthetic action sequences and corresponding synthetic end states for the user, based on a sequence of historical actions and corresponding historical end states. A plurality of pathways are projected through the plurality of synthetic action sequences, for assisting the user in arriving at a desired end state. During a training phase, a machine learning model is trained to learn a plurality of implicit features related to user behavior, for generating the synthetic action sequences and pathways. During an inference phase, the action prediction framework identifies waypoints associated with recommended user or system actions for assisting the user in reaching the end state more efficiently. The disclosed methods and systems may enable robust and efficient sequential action prediction while minimizing resource consumption associated with computationally expensive foundation models.
Methods and systems for implementing an action prediction framework associated with a user are described. An action prediction model generates a plurality of synthetic action sequences and corresponding synthetic end states for the user, based on a sequence of historical actions and corresponding historical end states. A plurality of pathways are projected through the plurality of synthetic action sequences, for assisting the user in arriving at a desired end state. During a training phase, a machine learning model is trained to learn a plurality of implicit features related to user behavior, for generating the synthetic action sequences and pathways. During an inference phase, the action prediction framework identifies waypoints associated with recommended user or system actions for assisting the user in reaching the end state more efficiently. The disclosed methods and systems may enable robust and efficient sequential action prediction while minimizing resource consumption associated with computationally expensive foundation models.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
(1) Downloadable computer application software for mobile devices for tracking deliveries and use as a digital wallet. (1) Providing temporary use of on-line non-downloadable software and applications for tracking deliveries and use as a digital wallet.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
(1) Downloadable computer application software for mobile devices for tracking deliveries and use as a digital wallet. (1) Providing temporary use of on-line non-downloadable software and applications for tracking deliveries and use as a digital wallet.
Artificial intelligence (AI) agents may produce errors from responses to their requests which they are not properly configured to handle. To address at least this technical problem, in some examples, the first AI agent may transmit a request to a first resource. The first AI agent may receive a response bundle responsive to the request from the first AI agent. The response bundle may include a response from the first resource to the request and an instruction for the first AI agent. The first AI agent may perform an operation responsive to the instruction. In some examples, the instruction may instruct the first AI agent to handle the response from the first resource in a way specified by the instruction.
A computer system and computer-implemented method, the method including receiving text input, the text input including feature inputs and prompt instructions; analyzing the text input to identify the feature inputs and the prompt instructions; and generating a prompt to be provided to a Large Language Model (LLM) based on a prompt template, the feature inputs, and the prompt instructions.
Methods and systems for identifying non-compliance of a user interface with a guideline are described. The methods and systems may include: detecting a trigger condition; prompting a large language model to identify an element of a user interface non-compliant with a guideline, wherein prompting includes providing an image showing at least a portion of the user interface to the large language model; receiving a first output of the large language model; identifying, based on the first output, the element that is non-compliant with the guideline; and presenting, on a display, an indication that the element is non-compliant. The guideline may include a semantic criterion paring a textual context with a visual condition.
G06V 10/766 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using regression, e.g. by projecting features on hyperplanes
G06F 9/451 - Execution arrangements for user interfaces
G06F 40/117 - TaggingMarking up Designating a blockSetting of attributes
21.
METHODS AND SYSTEMS FOR PROVIDING EXAMPLES TO A LARGE LANGUAGE MODEL
Methods and systems providing examples to a large language model (LLM) are described. A conversation history is maintained for an ongoing conversation between a client and the LLM. A current client message is received from the client. An input is provided to the LLM to instruct the LLM to generate an output in response to the current client message, the input to the LLM including at least a portion of the conversation history and including one or more example message pairs inserted into the portion of the conversation history in proximity to the current client message, wherein each example message pair includes a respective example client message and a respective example LLM message. An LLM message is outputted to the client based on the output generated by the LLM in response to the input. The one or more example message pairs are omitted from the maintained conversation history.
Methods and systems for enforcing restrictions against actions by a software agent are described. A request is received from a software agent to cause execution of an attempted action. A policy header is extracted from the request. Data representing an instructed task assigned to the software agent is extracted from the policy header. The attempted action is selectively caused to be executed based on whether the attempted action is suitable to a semantic meaning of the instructed task.
Systems and methods for the automatic dispatching of change events in an event-driven system are described. In examples, a change event dispatcher module may receive an indication of a change event associated with a data source in a distributed network, the change event being generated by an event producer in an event-driven system. The change event dispatcher module may determine a corresponding priority level for the received indication, based on a priority function and may dispatch the received indication for processing by one or more event consumers in the event-driven system, based on the priority level, to cause the one or more event consumers to perform one or more data actions. The disclosed systems and methods enable messages associated with high priority changes to be retrieved from a corresponding message queue by event consumers and processed more quickly than lower priority messages.
41 - Education, entertainment, sporting and cultural services
Goods & Services
Clothing, namely, T-shirts, hats, caps, windbreakers, racing
jerseys. Advertising services, namely, providing advertising space on
an automobile participating in automobile racing events and
exhibitions; promotional sponsorship of racing events;
online retail store services for sports equipment, clothing,
headwear, and toys; retail store services for sports
equipment, clothing, headwear, and toys. Entertainment services in the nature of professional
athletes competing in sports car races; entertainment
services in the nature of participating in professional
automobile races and automobile racing exhibitions;
provision of information regarding automobile racing via
website; providing sports information online; provision of
information relating to motor racing; entertainment in the
nature of organizing and hosting social entertainment events
in the field of automobile racing.
25.
METHODS AND SYSTEMS FOR ENFORCING RESTRICTIONS ON SOFTWARE AGENT
Methods and systems for enforcing restrictions against actions by a software agent are described. A request is received from a software agent to cause execution of an attempted action. A policy header is extracted from the request. Data representing an instructed task assigned to the software agent is extracted from the policy header. The attempted action is selectively caused to be executed based on whether the attempted action is suitable to a semantic meaning of the instructed task.
A textual description that includes a body of unstructured text is received. Using a rating model configured to output a rating based on a degree of similarity of the received textual description and each of a set of selected textual descriptions, a rating is generated based on the received textual description. The rating model to also used to generate a suggested modification of the received textual description that, when applied to the received textual descriptions, changes the rating of the received textual description. An indication of the suggested modification can be output to a user.
Systems and methods are disclosed for positioning of a device of interest within a merchant environment. In this regard, embodiments of a computer implemented method for positioning of a device of interest within a merchant environment are disclosed. In one embodiment, the computer implemented method comprises obtaining positions of a plurality of mobile merchant devices within a merchant environment, obtaining data indicative of a relative position of a device of interest relative to one or more of the plurality of mobile merchant devices, and computing a position of the device of interest within the merchant environment based on the data indicative of the relative position of the device of interest relative to the one or more of the plurality of mobile merchant devices and positions of the one or more of the plurality of mobile merchant devices.
A method for categorizing a product, the method including receiving information for the product; inputting the information into a trained machine learning model for a taxonomy tree; receiving a plurality of arrays, each array representing a level in the taxonomy tree and consisting of probabilities for each category represented in the level that the product is categorized in that category; choosing, from a highest level tier array, a category having a highest probability, thereby designating a tier prediction; collecting, from a second level tier array, all children of the tier prediction; determining whether a highest probability from the children of the tier prediction exceeds a threshold, and if yes, choosing the category with the highest probably as a new tier prediction; and repeating the determining; when the threshold is not exceeded or if the tier prediction has no children, and selecting the tier prediction as a predicted category.
A computer-implemented method is provided. The computer-implemented method may include automatically aggregating a subset of reviews from a plurality of reviews into an input prompt, the subset of reviews selected based on relevancy values assigned to reviews in the plurality of reviews. The computer-implemented method may further include inputting the input prompt into a generative language model yielding a summary review of the subset of reviews generated by the generative language model by: inputting the input prompt into the generative language model yielding attribute data associated with the subset of reviews and generated by the generative language model; and inputting the attribute data into the generative language model yielding the summary review generated by the generative language model.
A generative machine-learning model may be used for data compression/decompression. The model at an encoder may be prompted with at least one symbol, e.g. the first portion of information to be compressed. The model may generate an array of values, each corresponding to a possible next symbol. A code word representing the index of the array at which there is a value corresponding to the next symbol of the information may be selected and included in a compressed version of the information in place of the next symbol. The model at the decoder may be prompted with the same at least one symbol. The model may generate an array of values, each corresponding to a possible next symbol. A symbol corresponding to a value at an index of the array represented by the code word may be selected. A decompressed version of the information may be generated.
A generative machine-learning model may be used for data encryption/decryption. In one example, a model may be configured based on at least one configuration setting. The model at an encoder may be prompted. The model may generate an array of values, each corresponding to a possible next symbol. A code word representing the index of the array at which there is a value corresponding to the next symbol of the information may be selected as an encrypted version of the symbol. The model at the decoder may be configured like the model at the encoder. The model at the decoder may be prompted. The model may generate an array of values, each corresponding to a possible next symbol. A decrypted symbol corresponding to a value at an index of the array represented by the code word may be selected.
H04L 9/06 - Arrangements for secret or secure communicationsNetwork security protocols the encryption apparatus using shift registers or memories for blockwise coding, e.g. D.E.S. systems
33.
METHODS AND SYSTEMS FOR IMPROVED BROWSER INTERACTIONS WITH AI MODELS
A computer system and computer-implemented method are described. The method may include obtaining user data and a set of defined queries; generating a set of answers to the set of defined queries, the generation including causing a model to create, based on the user data and the set of defined queries, the set of answers; using an embedding model to generate a vector based on the set of answers; and uploading, by a browser application, the vector to a server during a browsing session.
A generative machine-learning model may be used for data compression/decompression. The model at an encoder may be prompted with at least one symbol. The model may generate an array of values, each corresponding to a possible next symbol. A code word representing the index of the array at which there is a value corresponding to the next symbol of the information may be selected. The model at the decoder may be prompted with the same at least one symbol. The model may generate an array of values, each corresponding to a possible next symbol. A symbol corresponding to a value at an index of the array represented by the code word may be selected. To provide for encryption/decryption, the model at the encoder may be configured based on at least one configuration setting. The model at the decoder may be configured like the model at the encoder.
A computer-implemented method is disclosed. The method includes: clustering a set of queries into first clusters; identifying, using a first large language model (LLM), queries in the first clusters that are semantically dissimilar from other queries in their cluster; clustering the queries identified as semantically dissimilar into one or more further clusters; and processing an incoming query based on matching said query to a particular cluster from the first clusters or the further clusters.
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
Methods and systems for generating output content using a generative artificial intelligence (AI) model based on an input. A similarity-assessment layer at the output of the generative AI model determines a similarity measure for the output content vis-à-vis pre-existing items in a repository. The similarity measure is compared to a threshold value and, responsive to the comparison indicating excessive similarity, one or both of the input and the generative AI model are adjusted, and the generative AI model is re-run to generate new output content.
A computing resource may be monopolized or dominated by a client, if the client has a large quantity of tasks for execution and/or the tasks from that client take a long time to execute. In some embodiments, each client is associated with a respective counter, and the counter is indicative of how much the computing resource has been recently occupied by the client associated with that counter. In some embodiments, the computing resource refrains from executing new tasks for a client if its counter is within a particular range. In some embodiments, a counter increments when the computing resource is occupied by a client and decrements otherwise based on the passage of time. In some embodiments, different counters may have different rates of incrementing or decrementing, or different particular ranges.
Methods and devices for capturing images for use in online retail of product items. A mobile device having a camera may be used when building a product item record having an associated image of the product. The method of capturing a suitable image may include obtaining a product item display page for a product item, the product item display page having a designated portion defined for display of an image of the product item; obtaining a real-time live stream of images from the camera; processing the live stream from the camera to create a processed live stream, and displaying the product item display page with the processed live stream displayed within the designated portion; and storing a processed image for the product item in association with an item record for the product item.
A computer-implemented method is disclosed. The method includes: obtaining a stack trace associated with an error detected in connection with execution of a computer program by a processor; determining a location of the error within source code of the computer program based on the stack trace, wherein the source code contains a template code section and a custom code section; generating an error message for the error, wherein the generating includes: in response to determining that the error is located in the custom code section, appending a first representation of the stack trace to the error message; and in response to determining that the error is located in the template code section, formatting the error message to indicate a generic template code error, and presenting the error message via a computing device.
A system and method for using generative recommenders to fetch data based on expected next events. The method includes providing a sequence of events to a generative recommender and obtaining an output from the generative recommender. The method also includes using the output to determine an expected next event associated with an application, identifying data to be retrieved based on the expected next event, and fetching at least some of the identified data.
A server of a first network domain receives an indication container object created in a second network domain. The server identifies, based on the indication container object, a unique identifier, where the unique identifier allows initiation of logging into an account. The server transmits a confirmation code to a user device that is identified based on the unique identifier. Transmitting the confirmation code allows completion of login to the account.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
SYSTEM, COMPUTER-IMPLEMENTED METHOD, AND COMPUTER READABLE MEDIA FOR USING GENERATIVE RECOMMENDERS TO DETERMINE PROPENSITY TOWARDS OR PROBABILITY OF ACTIONS BEING TAKEN
A system and method for using a generative recommender to determine a propensity towards or probability of actions being taken. The method includes providing a sequence of events to a generative recommender and obtaining an output from the generative recommender. The method also includes using the output and a model to generate a result, the model having been trained to determine the propensity towards, or probability of, an action occurring following the sequence of events as processed by the generative recommender.
Methods and devices for automatic optimization of a large data retrieval request are described. A viewport size for displaying data records on a display associated with the client device is obtained. Responsive to a user query for a plurality of data records, a first request, a second request and a third request are sent to a data server for retrieving a first subset of data records, a set of partial data records, and at least a remainder of the plurality of data records. Responsive to receiving at least the first subset of data records and the set of partial data records, providing the first subset of data records to be viewable in a viewport via the display associated with the client device, and responsive to receiving at least the remainder of the plurality of data records, providing the remainder of the plurality of data records for output via the display.
A computer-implemented method including parsing a stream of data; detecting an identifier for a resource within the stream of data; checking the detected identifier against a manifest; and based on the checking, prefetching the resource. Also, a computing device having a processor; a memory; and a communications subsystem, where the computing device is configured to parse a stream of data; detect an identifier for a resource within the stream of data; check the detected identifier against a manifest; and based on the check, prefetch the resource.
G06F 9/50 - Allocation of resources, e.g. of the central processing unit [CPU]
G06F 21/62 - Protecting access to data via a platform, e.g. using keys or access control rules
46.
System, Computer-Implemented Method, and Computer Readable Media for Using Generative Recommenders to Determine Propensity Towards or Probability of Actions Being Taken
A system and method for using a generative recommender to determine a propensity towards or probability of actions being taken. The method includes providing a sequence of events to a generative recommender and obtaining an output from the generative recommender. The method also includes using the output and a model to generate a result, the model having been trained to determine the propensity towards, or probability of, an action occurring following the sequence of events as processed by the generative recommender.
A system and method for performing parallel local and remote searches, in particular to searching a local cache and remote database in parallel while accepting a search input, to obtain additional data for the local cache. The method includes, responsive to detecting a first portion of a search input, searching a local cache using the first portion to populate a search results list and initiating a remote search using the first portion; and responsive to receiving remote search results from the remote search, updating the search results list based on the remote search results and updating the local cache with data associated with items in the remote search results.
Methods and systems for automatically ordering a set of images for consistent user interface display. The methods may include receiving a set of further images related to a first record, the first record referencing an ordered set of existing images, each of the existing images being assigned one or more respective image attributes. It may include assigning, using image analysis, one or more respective image attributes to each image in the set of further images and comparing image attributes assigned to the further images with image attributes assigned to the existing images to determine, for each of the further images, a corresponding one of the existing images. The further images are then ordered based on the determined corresponding ones of the existing images and the ordering of those existing images in the ordered set of existing images, and displayed in order in a user interface.
G06V 10/56 - Extraction of image or video features relating to colour
G06V 10/70 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning
G06V 10/74 - Image or video pattern matchingProximity measures in feature spaces
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/94 - Hardware or software architectures specially adapted for image or video understanding
49.
SYSTEMS AND METHODS FOR COMPUTER CONTROL OF ACCESS TO RESOURCES
A computer system may be designed to control access to resources. A ledger may be used to reflect how many units of each resource are available. There may be contention for access to the ledger. To address the technical problem of contention and to ensure more units cannot be claimed than exist, in one example, a number of rows, each corresponding to one or more units of a resource, may be created in a first intermediary database table. For each request the first database table may be queried for one or more units of a resource. The corresponding subset of rows may be returned, and row locks may be taken on each of the subset of rows, reserving the corresponding one or more units of the resource and ensuring they do not form part of the result sets for other queries that are received while the first query is in-flight.
Methods and systems for managing functions calls by a large language model are described. A generated message is received from a generative language model, based on an input message in an ongoing conversation, the generated message indicating a function call related to the input message. The function is executed using the function call. A function response is received from the executed function. An output message is provided to the ongoing conversation based on the function response, wherein the providing of the output message bypasses the generative language model.
In the field of machine learning, there may be challenges associated with constructing a comprehensive and diverse training data set. For example, the data that is available may not be sufficiently diverse, which may cause issues such as overfitting in a model trained using the available data. A computer-implemented method and system are provided to use an embedding function as a tool in assessing the diversity of a data set. The embedding function may be employed in constructing a training data set having a high degree of data diversity for training a model.
A computer-implemented method is disclosed. The method includes: presenting, via a first user interface, an initial set of user interface elements associated with results of a search query; generating user prompt data for soliciting user selection of a subset of object attributes associated with one or more of the search query results; presenting the user prompt data as chat outputs in a second user interface; receiving, via the second user interface, an indication of one or more preferred object attributes; and updating the first user interface in real-time to display user interface elements corresponding to a reduced set of searchable objects associated with the one or more preferred object attributes.
In the field of machine learning, there may be challenges associated with constructing a comprehensive and diverse training data set. For example, the data that is available may not be sufficiently diverse, which may cause issues such as overfitting in a model trained using the available data. A computer-implemented method and system are provided to use an embedding function as a tool in assessing the diversity of a data set. The embedding function may be employed in constructing a training data set having a high degree of data diversity for training a model.
A computer-implemented method is disclosed. The method includes: receiving a search query for a first application programming interface (API); generating an embedding of the search query; performing a search of the first API by using the search query embedding to search a set of first vector embeddings generated by: obtaining API schema of the first API; determining a set of all API paths associated with the first API based on the API schema, each API path defining a root API object and a sequence of one or more field elements of the API ending in a terminal field element; obtaining, using a large language model (LLM), natural language descriptions of each API path associated with the first API; and generating the first vector embeddings based on the obtained descriptions, and providing results of the search, the results identifying one or more API paths similar to the search query.
Methods and systems for managing functions calls by a large language model are described. A generated message is received from a generative language model, based on an input message in an ongoing conversation, the generated message indicating a function call related to the input message. The function is executed using the function call. A function response is received from the executed function. An output message is provided to the ongoing conversation based on the function response, wherein the providing of the output message bypasses the generative language model.
A computer-implemented method is disclosed. The method includes: receiving a search query for a first application programming interface (API); generating an embedding of the search query; performing a search of the first API by using the search query embedding to search a set of first vector embeddings generated by: obtaining API schema of the first API; determining a set of all API paths associated with the first API based on the API schema, each API path defining a root API object and a sequence of one or more field elements of the API ending in a terminal field element; obtaining, using a large language model (LLM), natural language descriptions of each API path associated with the first API; and generating the first vector embeddings based on the obtained descriptions, and providing results of the search, the results identifying one or more API paths similar to the search query.
Mobile fulfillment container apparatus, systems, and related methods are disclosed. An example apparatus includes memory; instructions; and processor circuitry to execute the instructions to associate a first order with a first mobile container based on goods stored in the first mobile container; select a first retrieval destination based on a current location of the first mobile container and a location associated with the first order; and output a first instruction including the first retrieval destination for the first mobile container.
A computer-implemented is disclosed. The method includes: obtaining a composite image depicting an identifiable foreground object; performing image segmentation to isolate a foreground object from the composite image, the image segmentation yielding a segmented composite image; determining object attributes of the foreground object based on image analysis of the segmented composite image; obtaining at least one prompt for a text-to-image model based on the object attributes of the foreground object, the at least one prompt defining an intended replacement background for the composite image; providing, to the text-to-image model, instructions to generate a replacement background image for the composite image based on the at least one prompt; receiving, from the text-to-image model, a replacement background image for the composite image; and generating a new composite image, the generating including compositing portions of the composite image corresponding to the foreground object with the replacement background image.
G06V 10/26 - Segmentation of patterns in the image fieldCutting or merging of image elements to establish the pattern region, e.g. clustering-based techniquesDetection of occlusion
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
During computer operation, it is sometimes necessary for the computer to retrieve data by performing a query. There may be situations in which multiple queries may need to be executed. In some embodiments, when multiple individual queries need to be executed, instead of executing each individual query to obtain data requested by each individual query, a single query may be generated from the individual queries. The single query encompasses all the data requests in each individual query and may therefore be referred to as a “merged query”. The merged query is then executed, and the data returned is mapped to responses for the individual queries. Technical benefits may include the reduction or elimination of duplicate data fetching, e.g. fewer query operations/data fetches, while still fetching all data requested by all of the individual queries.
A computer-implemented method for detecting malicious code injection into checkout operations, the method including receiving a report regarding a checkout operation; determining based on the report that a checkout operation includes one or more events satisfying a first criterion; determining that a modification of customizable software code related to the checkout operation satisfies a second criterion; and responsive to the satisfaction of the first criterion and the second criterion, providing an indication of a detection of a potential malicious code injection into the checkout operation.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
61.
SYSTEMS AND METHODS FOR RESPONSIVE USER INTERFACE BASED ON GAZE DEPTH
In virtual reality (VR) and augmented reality (AR), eye tracking may be performed to determine the user's gaze direction. The gaze direction may be used to enhance user interaction. However, when a user gazes in a particular direction, it could sometimes be the case that there are multiple items located in that gaze direction, each at a different depth. The gaze of direction alone might not be indicative of the item at which the user is looking. Therefore, in some embodiments, to try to further enhance user interaction, a gaze depth of the gaze may be determined. Some embodiments are directed to performing eye tracking to detect a gaze depth of a human's gaze and modifying a user interface (UI) responsive to a change in the gaze depth.
G06F 3/01 - Input arrangements or combined input and output arrangements for interaction between user and computer
G06F 3/04845 - Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range for image manipulation, e.g. dragging, rotation, expansion or change of colour
62.
COMPUTER SYSTEM, COMPUTER-IMPLEMENTED METHOD, AND COMPUTER READABLE MEDIA FOR HANDLING INCOMPLETE INPUTS TO LARGE LANGUAGE MODELS (LLMS)
A system and method are provided for handling incomplete inputs to large language models (LLMs). The method includes, responsive to detecting an incomplete input in a messaging conversation, buffering the incomplete input prior to having an LLM respond to a prompt associated with the incomplete input.
H04L 51/02 - User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
63.
SYSTEMS AND METHODS FOR GENERATING CUSTOMIZED AUGMENTED REALITY VIDEO
Methods and systems are disclosed for generating an augmented reality (AR) video. A set of products is obtained, where each product is associated with a respective virtual model and a respective object class. An AR video segment is generated for each product in the set of products. In a real-world video segment, a real-world object belonging to a relevant object class that is relevant to the object class of the given product is detected. A render of the virtual model associated with the given product is overlaid in the real-world video segment to obtain the AR video segment. The render of the virtual model is overlaid relative to the detected real-world object belonging to the relevant object class. A continuous AR video is generated from the AR video segments and outputted to be viewable by a user device.
G06F 3/04815 - Interaction with a metaphor-based environment or interaction object displayed as three-dimensional, e.g. changing the user viewpoint with respect to the environment or object
G06T 19/00 - Manipulating 3D models or images for computer graphics
64.
METHODS AND SYSTEMS FOR DYNAMIC USER INTERFACE CREATION
A computer-implemented method including associating, at a resource having a plurality of task elements, a task element manifest with each task element from the plurality of task elements, thereby creating a resource map, receiving a request to complete a task; providing the request to complete the task and at least a portion of the resource map to a Large Language Model (LLM); and obtaining, from the LLM, a dynamic user interface to complete the task.
A system and method are provided for handling incomplete inputs to large language models (LLMs). The method includes, responsive to detecting an incomplete input in a messaging conversation, buffering the incomplete input prior to having an LLM respond to a prompt associated with the incomplete input.
H04L 51/216 - Handling conversation history, e.g. grouping of messages in sessions or threads
66.
Computer System, Computer-Implemented Method, and Computer Readable Media for Synchronizing Chat Histories Used in Prompting Large Language Models (LLMS)
A system and method are provided for synchronizing chat histories used in prompting large language models (LLMs). The method includes receiving an indication of an interruption in a messaging conversation at a client application. The method also includes determining a last presented portion of a response. The response is generated by an LLM for the messaging conversation and provided to the client application in response to prompting the LLM with a prompt based on at least a first input provided to the client application. The method also includes modifying a chat history maintained by a server application based on the last presented portion of the response.
H04L 51/216 - Handling conversation history, e.g. grouping of messages in sessions or threads
H04L 51/02 - User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages
67.
METHODS AND SYSTEMS FOR DYNAMIC USER INTERFACE CREATION
A computer-implemented method including associating, at a resource having a plurality of task elements, a task element manifest with each task element from the plurality of task elements, thereby creating a resource map, receiving a request to complete a task; providing the request to complete the task and at least a portion of the resource map to a Large Language Model (LLM); and obtaining, from the LLM, a dynamic user interface to complete the task.
A generative language model, such as an LLM, may "hallucinate," such that it provides an output category that is incorrect or not relevant to its input. One solution is to use semantic replacement after the generative language model finishes outputting the category. A prompt may be provided to a generative language model, the prompt instructing the generative language model to generate output that classifies an input to the generative language model. Output may be received from the generative language model, the output classifying the input into a category. It may be determined that the category is an invalid category. A valid category be obtained based on the invalid category. The invalid category may be substituted with the valid category.
G06F 18/241 - Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
G06F 18/2413 - Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
A generative language model, such as an LLM, may “hallucinate,” such that it provides an output category that is incorrect or not relevant to its input. One solution is to use semantic replacement after the generative language model finishes outputting the category. A prompt may be provided to a generative language model, the prompt instructing the generative language model to generate output that classifies an input to the generative language model. Output may be received from the generative language model, the output classifying the input into a category. It may be determined that the category is an invalid category. A valid category be obtained based on the invalid category. The invalid category may be substituted with the valid category.
Methods and systems for automatic installation of applications against a service instance of an online store are described. A change in status of a service instance for the online store is detected. A functionality associated with the changed status is identified, where the functionality is currently absent from the service instance. A software application is identified to provide the functionality. The identified software application is automatically installed against the service instance, to enable the functionality for the online store.
H04L 43/0817 - Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking functioning
H04L 67/51 - Discovery or management thereof, e.g. service location protocol [SLP] or web services
71.
METHODS AND SYSTEMS FOR INTERACTIONS WITH VIRTUAL SHOPPING CART VIEW
Methods and systems for interactions with a virtual shopping cart view are disclosed. A graphical user interface (GUI) is displayed on a touchscreen of a computing system. The GUI presents a virtual shopping cart view. The GUI also presents an edge region of an active view partially overlaid over a first side of the virtual shopping cart view. A first drag gesture is detected on the touchscreen at the edge region of the active view that moves towards an opposing second side of the virtual shopping cart view. Responsive to the first drag gesture, the GUI is caused to gradually show the active view by moving the active view over the virtual shopping cart view corresponding to movement of the first drag gesture.
G06F 3/04845 - Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range for image manipulation, e.g. dragging, rotation, expansion or change of colour
G06F 3/04886 - Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus
72.
METHODS AND SYSTEMS FOR INTERACTIONS WITH VIRTUAL SHOPPING CART VIEW
Methods and systems for interactions with a virtual shopping cart view are disclosed. A graphical user interface (GUI) is displayed on a touchscreen of a computing system. The GUI presents a virtual shopping cart view. The GUI also presents an edge region of an active view partially overlaid over a first side of the virtual shopping cart view. A first drag gesture is detected on the touchscreen at the edge region of the active view that moves towards an opposing second side of the virtual shopping cart view. Responsive to the first drag gesture, the GUI is caused to gradually show the active view by moving the active view over the virtual shopping cart view corresponding to movement of the first drag gesture.
G06F 3/04883 - Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures for inputting data by handwriting, e.g. gesture or text
G06F 3/0481 - Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
Systems and methods are disclosed for presenting, on a display of a portable computing device having an integrated camera, a Graphical User Interface (GUI) that enables simultaneous scanning of computer-readable indicia affixed to items and a resulting list of scanned items.
G06K 7/14 - Methods or arrangements for sensing record carriers by electromagnetic radiation, e.g. optical sensingMethods or arrangements for sensing record carriers by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
77.
COMPUTER USER INTERFACE TO DISPLAY WHAT PAGES A PARTICULAR ASSET IN "USED IN"
Systems and methods are disclosed herein for providing a Graphical User Interface (GUI) for a website builder software platform that includes a “used in” feature for digital assets used in blocks within the website. More specifically, digital assets are associated to blocks in which the digital assets are used within the website. Information about these associations is dynamically updated and displayed via the GUI. In this manner, a website creator can quickly and easily see that a particular digital asset is used in certain blocks and take this information into account when, e.g., updating that digital asset.
Methods and systems for prompting a large language model (LLM) to generate a description of an object with indications of any unsubstantiated information are disclosed. A prompt is generated to a LLM to generate a description of an object, where the prompt includes one or more object attributes to include in the generated description. The prompt also includes an instruction for the LLM to annotate any portions of the generated description that are, involve, and/or include unsubstantiated information according to a defined format. The prompt is provided to the LLM and the generated description is received. The generated description is parsed to identify, based on the defined format, one or more annotated portions indicating unsubstantiated information. The generated description is presented for display via a user device.
Methods and systems for automatic detection and filling of information gaps in a reference database are described. Responsive to a user query in an ongoing chat session, a query embedding associated with the user query is obtained. A synthetic question embedding is identified from a vector database, based on a similarity to the query embedding. Responsive to determining that the similarity between the synthetic question embedding and the query embedding does not meet a similarity threshold, the ongoing chat session is monitored to detect an answer to the user query. A prompt is provided to a large language model (LLM) to generate and display a textual content corresponding to the user query, based on the detected answer, for automatically updating the reference database. The disclosed methods and systems effectively incorporate new or undocumented information that is not currently captured within the reference database, as gaps are identified.
A system and method are provided for function selecting when prompting a large language model (LLM). The method includes receiving an input for the LLM and selecting one or more functions from a set of functions based on the input. The method also includes generating a prompt based on the input and the selected one or more functions and providing the prompt to the LLM and obtaining a response.
Disclosed herein are methods and systems for electronic authentication using delegated credentials to complete checkout and payment operations on a trusted device of a user. A computing system is structured to perform operations comprising receiving transaction information corresponding to an incomplete checkout operation, transmitting at least a subset of transaction information to a customer device, causing the customer device to generate and display a notification comprising a request for user authorization to complete the incomplete checkout operation, receiving customer input indicative of instructions to complete the incomplete checkout operation, and, responsive to receiving customer input, completing the incomplete checkout operation.
G06Q 20/40 - Authorisation, e.g. identification of payer or payee, verification of customer or shop credentialsReview and approval of payers, e.g. check of credit lines or negative lists
G06Q 20/32 - Payment architectures, schemes or protocols characterised by the use of specific devices using wireless devices
G06Q 20/36 - Payment architectures, schemes or protocols characterised by the use of specific devices using electronic wallets or electronic money safes
A system and method are provided for function selecting when prompting a large language model (LLM). The method includes receiving an input for the LLM and selecting one or more functions from a set of functions based on the input. The method also includes generating a prompt based on the input and the selected one or more functions and providing the prompt to the LLM and obtaining a response.
Methods and systems for automatic detection and fdling of information gaps in a reference database are described. Responsive to a user query in an ongoing chat session, a query embedding associated with the user query is obtained. A synthetic question embedding is identified from a vector database, based on a similarity to the query embedding. Responsive to determining that the similarity between the synthetic question embedding and the query embedding does not meet a similarity threshold, the ongoing chat session is monitored to detect an answer to the user query. A prompt is provided to a large language model (LLM) to generate and display a textual content corresponding to the user query, based on the detected answer, for automatically updating the reference database. The disclosed methods and systems effectively incorporate new or undocumented information that is not currently captured within the reference database, as gaps are identified.
A computer-implemented method is disclosed. The method includes: obtaining a stack trace associated with an error detected in connection with execution of a computer program by a processor; determining a location of the error within source code of the computer program based on the stack trace, wherein the source code contains a template code section and a custom code section; generating an error message for the error, wherein the generating includes: in response to determining that the error is located in the custom code section, appending a first representation of the stack trace to the error message; and in response to determining that the error is located in the template code section, formatting the error message to indicate a generic template code error, and presenting the error message via a computing device.
A server of a first tenant network domain receives one or more identifiers associated with a browser application that was used to access a webpage of the first tenant network domain. The server identifies, based on the one or more identifiers associated with the browser application, a likelihood that an active login cookie associated with a service network domain is stored by the browser application. If the likelihood exceeds a threshold, the server causes the browser application to be directed to a webpage on the service network domain that is associated with a logged-in state at the service network domain.
A system and method for generating a three-dimensional (3D) model of an object. The method includes: determining that a first portion of an object has a lower priority; obtaining a plurality of images of the object; and training a three-dimensional model of the object using a training algorithm that processes the plurality of images as training data to generate and refine Gaussian splats defining the three-dimensional model. Obtaining the plurality of images includes obtaining images including views of the first portion of the object from a first concentration of viewpoints; and obtaining images including views of the another portion of the object from a second concentration of viewpoints, the first concentration being less than the second concentration.
There is provided a computer method, system and device comprising detecting an updated iteration of a document for query response generation; comparing the updated iteration to a prior iteration to identify chunks of the updated iteration of the document that differ from corresponding chunks of the prior iteration, the prior iteration for generating a set of synthetic questions and answers using an LLM. Responsive to identifying that a given chunk of the updated iteration differs from a corresponding chunk of the prior iteration, the method triggers generation, using the LLM, of a new set of synthetic questions associated with corresponding text in the given chunk defining a new set of synthetic responses, and wherein the new set of synthetic questions and responses replaces at least a subset of the set of synthetic questions and answers associated together by a mapping with the corresponding chunk of the prior iteration.
G06F 16/383 - Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
93.
METHODS AND SYSTEMS FOR UPDATING A RETRIEVAL-AUGMENTED GENERATION FRAMEWORK
There is provided a computer method, system and device comprising detecting an updated iteration of a document for query response generation; comparing the updated iteration to a prior iteration to identify chunks of the updated iteration of the document that differ from corresponding chunks of the prior iteration, the prior iteration for generating a set of synthetic questions and answers using an LLM. Responsive to identifying that a given chunk of the updated iteration differs from a corresponding chunk of the prior iteration, the method triggers generation, using the LLM, of a new set of synthetic questions associated with corresponding text in the given chunk defining a new set of synthetic responses, and wherein the new set of synthetic questions and responses replaces at least a subset of the set of synthetic questions and answers associated together by a mapping with the corresponding chunk of the prior iteration.
Although sales history may be used to determine which products are likely to be purchased together, new products or stores may have little to no usable sales history. It is challenging to use the sales history of other products or stores because there is no system for uniquely identifying products that is common to all stores. Aspects of the present disclosure provide systems and methods for processing product information using a machine-learning model to predict the likelihood of products being purchased together. According to some aspects of the present disclosure, product information may be encoded to obtain numerical vectors for input to a machine-learning model to transform product information into a format in which it can be leveraged by the machine-learning model to identify co-purchasing trends that may be common to different stores and/or products.
Methods and systems for prompting a large language model (LLM) to generate a revised text passage with formatting are described. A text-editing instruction is received that is related to at least a portion of a text passage having at least one formatting tag. The text passage is processed to identify the at least one formatting tag in the text passage. A prompt to the LLM is generated, to cause the LLM to generate a revised text passage. The prompt includes the text-editing instruction related to at least the portion of the text passage and also includes a formatting-specific instruction to format the revised text passage using the at least one formatting tag in the revised text passage. The revised text passage is received and caused to be displayed based on the formatting tag.
To improve user experience when interacting with AR content within an AR environment, the AR content may be overlaid over a proxy object in a real-world space. Differences in dimension between the proxy object and the virtual model may be such that the object is larger than the virtual model, which may result in portions of the object appearing to protrude from behind the virtual model, decreasing user enjoyment. In some embodiments, an AR system for the overlay of AR content on a proxy object and concealment of the proxy object may be implemented. The system may overlay a virtual model to a proxy object, and then conceal any remaining visible portions of the proxy object from the visual field of a device displaying the AR environment. The system may overlay the virtual model so that any remaining visible portion of the proxy object is a single continuous region.
41 - Education, entertainment, sporting and cultural services
Goods & Services
(1) Clothing, namely, t-shirts, hats, caps, windbreakers, racing jerseys (1) Advertising services, namely, providing advertising space on an automobile participating in automobile racing events and exhibitions; promotional sponsorship of racing events; Online retail store services for sports equipment, clothing, headwear, and toys; retail store services for sports equipment, clothing, headwear, and toys
(2) Entertainment services in the nature of professional athletes competing in sports car races; Entertainment services in the nature of participating in professional automobile races and automobile racing exhibitions; providing a website featuring information regarding automobile racing; Providing sports information online; provision of information relating to motor racing; Entertainment in the nature of organizing and hosting social entertainment events in the field of automobile racing
41 - Education, entertainment, sporting and cultural services
Goods & Services
(1) Clothing, namely, t-shirts, hats, caps, windbreakers, racing jerseys (1) Advertising services, namely, providing advertising space on an automobile participating in automobile racing events and exhibitions; promotional sponsorship of racing events; Online retail store services for sports equipment, clothing, headwear, and toys; retail store services for sports equipment, clothing, headwear, and toys.
(2) Entertainment services in the nature of professional athletes competing in sports car races; Entertainment services in the nature of participating in professional automobile races and automobile racing exhibitions; providing a website featuring information regarding automobile racing; Providing sports information online; provision of information relating to motor racing; Entertainment in the nature of organizing and hosting social entertainment events in the field of automobile racing.
41 - Education, entertainment, sporting and cultural services
Goods & Services
Clothing, namely, t-shirts, hats, caps, windbreakers, racing jerseys Advertising services, namely, providing advertising space on an automobile participating in automobile racing events and exhibitions; promotional sponsorship of racing events; Online retail store services featuring a wide variety of consumer goods; retail store services featuring a wide variety of consumer goods Entertainment services in the nature of professional athletes competing in sports car races; Entertainment services in the nature of participating in professional automobile races and automobile racing exhibitions; providing a website featuring information regarding automobile racing; Providing sports information online; provision of information relating to motor racing; Entertainment in the nature of organizing and hosting social entertainment events
41 - Education, entertainment, sporting and cultural services
Goods & Services
Clothing, namely, t-shirts, hats, caps, windbreakers, racing jerseys Advertising services, namely, providing advertising space on an automobile participating in automobile racing events and exhibitions; promotional sponsorship of racing events; Online retail store services featuring a wide variety of consumer goods; retail store services featuring a wide variety of consumer goods Entertainment services in the nature of professional athletes competing in sports car races; Entertainment services in the nature of participating in professional automobile races and automobile racing exhibitions; providing a website featuring information regarding automobile racing; Providing sports information online; provision of information relating to motor racing; Entertainment in the nature of organizing and hosting social entertainment events
