77 results about "Virtual agent" patented technology

In various examples, systems and methods are disclosed relating to displaying images in chatbot / NPC / virtual agent / digital avatar / etc. responses. A system can identify text corresponding to an image in an electronic document and can store a representation of the text in association with an identifier of the image. The system can receive an input prompt for a machine-learning model. The system can generate a response to the input prompt using the machine-learning model. The response can include the image responsive to identifying the representation of the text using a searching function and an output of the machine-learning model.

Embodiments of the present disclosure provide a computer-implemented method. The computer-implemented method performed by a controller includes generating a plurality of virtual agents with Artificial Intelligence (AI) capabilities based at least on organizational data. Furthermore, the computer-implemented method includes delegating at least a portion of operational workflows to one or more of the plurality of virtual agents. The computer-implemented method further includes generating a plurality of employee digital twins associated with a plurality of respective employees, based at least on employee-specific data. Furthermore, the computer-implemented method includes generating at least one workplace digital twin representing at least one respective workplace environment. The computer-implemented method also includes enabling communication amongst a plurality of disparate groupings generated by selecting a plurality of entities from one or more of a plurality of employee devices, the plurality of virtual agents, the plurality of employee digital twins, or the at least one workplace digital twin.

A method and system for training a virtual agent is provided herein. The method and system comprises storing conversations between the virtual agent and a user in logs. The method and system further comprises mining the logs to retrieve utterances. The method and system further comprises computing regression for each of the plurality of the charging time segments. The method and system further comprises providing a score to the utterances. Further, the method ranking the utterances based on the score.

An execution method and an execution system for a virtual meeting are provided. The execution method includes the following steps. A discussion item is received. The discussion item is compiled into a plurality of tasks. The tasks are distributed to a plurality of virtual agents. At least one analysis information is obtained by at least one of the virtual agents using an industrial data database. The industrial data database is built via an analytic AI model. At least one guidance information is obtained by at least one of the virtual agents using an industrial knowledge database. The industrial knowledge database is built via a generative AI model. If the analysis information and the guidance information meet the predetermined condition, the virtual expert compiles the analysis information and the guidance information into a recommendation report.

Techniques are disclosed that relate to a computer system implementing a conversational artificial intelligence platform. The computer system may receive a request that includes text data specifying an utterance of a user. The computer system determines, form the utterance, an intent of the user. The computer system selects a first virtual agent to handle the request based on the determined intent. The computer system routes the text data and subsequent text data of the request to the first virtual agent for handling. The computer system receives, from the first virtual agent, a message that the determined intent is incorrect, the message including state information indicative of actions taken by the first virtual agent relative to the request. The computer system selects a second virtual agent to handle the request based on the state information. The computer system may receive input from an interactive voice response system or another channel.

In various examples, virtual participant-based microservices for video conferencing applications and systems are provided. A virtual participant service provides a subject matter expert to participants of a conference session. A virtual participant may be presented within a video conferencing environment as a simulated meeting participant that other meeting participants may interact with using natural conversational language. The virtual participant service may include a virtual participant controller frontend service that interfaces with the video conferencing platform, an avatar manager to generate an avatar representing the virtual participant, and an LLM services gateway that functions as a microservices server for one or more LLM-based services that may be accessed through the virtual participant. The virtual participant service may use natural language processing to evaluate spoken requests for information and provide a response back to the human user participants of the conference channel using an animated avatar.

A method and system for generating a response through a virtual agent is provided herein. The method comprises receiving information associated with a plurality of themes and topics. The method further comprises creating a knowledgebase based on the information received. The method further comprises analyzing the knowledgebase based on an intent identified, using an Artificial Intelligence (AI) model. Further, the method comprises generating a response corresponding to the intent through the virtual agent based on analyzation.

An artificial intelligence, AI, controller network entity (120) is disclosed for controlling a plurality of AI agents (110a-n) of a distributed AI, DAI, group of AI agents (110a-n) for jointly performing an AI task in a mobile network (100). The AI controller network entity (120) is configured to determine for each of the plurality of AI agents (110a-n) a current AI agent status of a plurality of possible AI agent statuses, wherein the plurality of possible AI agent statuses comprise an active status, an idle status, and a dummy status, wherein in the active status an AI agent is active in the AI task of the DAI group of agents (110a- n) and wherein in the idle status an AI agent is temporally not active in the AI task of the DAI group of agents (110a-n), wherein the DAI group of AI agents (110a-n) comprises a dummy AI agent (110a) and wherein the dummy AI agent (110a) is not capable of being active in the AI task of the DAI group. Moreover, the controller network entity (120) is configured to control for one or more of the plurality of AI agents (110a-n) a transition from the current AI agent status of the AI agent to a different AI agent status of the plurality of possible AI agent statuses during the AI task.

Persistent storage contains a state machine for a request routing process and a plurality of requests related to the request routing process. One or more processors are configured to apply the state machine through operations including: obtaining a request from the plurality of requests; providing, to a criticality detection application and to an intent detection application, a representation of the request, wherein the criticality detection application is configured to detect a criticality of the request, and wherein the intent detection application is configured to determine a semantic intent of the request; receiving, from the criticality detection application and the intent detection application, respective indications of a detected criticality of the request and a detected intent of the request; determining whether to route the request to a channel that is one of a live agent, a virtual agent, or a search-based application; and routing the request to the channel as determined.

A request processing method, executed by a load balancing node in a request processing system, wherein the request processing system comprises a reverse proxy node, a virtual proxy node, and the load balancing node, and request forwarding is performed between the reverse proxy node and the virtual proxy node by means of a plurality of socket nodes. The method comprises: upon receipt of a plurality of traffic requests by the reverse proxy node, determining, from among the plurality of socket nodes, socket nodes available for processing (302); for each socket node available for processing, determining, from the virtual proxy node, a processing instance having a binding relationship with the socket node available for processing, so as to obtain a plurality of processing instances (304); determining, from among the plurality of processing instances, selected processing instances matching socket nodes available for processing (306); and on the basis of multiple pieces of instance running information respectively corresponding to the selected processing instances, respectively distributing the plurality of traffic requests to the selected processing instances, so that the selected processing instances process the distributed traffic requests (308).

The invention discloses an automatic driving test method and system. Belongs to the technical field of automatic driving testing. According to the method, a high-fidelity virtual environment is constructed by collecting real scene data, and a virtual sensor is configured; mapping the real track to a virtual space, and generating a dynamic traffic flow in combination with a car following and lane changing model; after the real vehicle and the virtual intelligent agent are synchronously initialized, the real vehicle runs in the physical field and periodically updates the state; the virtual traffic flow is dynamically evolved according to the state of the main vehicle, and the virtual sensor senses the target in the field of view and generates a virtual sensing result; real sensor data is used as a reference, and virtual and real perception information is fused to form unified input; and circularly executing until the task is completed, wherein each virtual agent only participates in one test. According to the scheme, high-reality and high-efficiency closed-loop testing is achieved, the defects of a traditional method in the aspects of scene richness and testing safety are overcome, and the reliability and repeatability of verification of the automatic driving system are improved.

The invention relates to the technical field of computers, and discloses a dialogue processing method and device for a virtual seat and electronic equipment. The method comprises the steps of receiving dialogue content input by a user; reasoning the dialogue content to obtain a virtual seat reasoning result; obtaining a dialogue context feature set corresponding to the dialogue content according to the dialogue content; inputting the virtual seat reasoning result and the dialogue context feature set into a preset large language model, and generating a result corresponding to the dialogue content through the large language model; and feeding back a result corresponding to the dialogue content to the user through the virtual seat. According to the method, the system can better understand the background and context of the dialogue by using the dialogue context feature set and the virtual seat reasoning result, and the anthropomorphic performance of the system is improved. Through combination of virtual seat reasoning and large language model generation, the system can exceed the limitation of a traditional knowledge base algorithm and provide more intelligent replies meeting user requirements, so that the problem that the performance of the knowledge base algorithm is limited is solved.

In an illustrative embodiment, systems for performing automated comparisons of contractual agreements include a vector database storing high-dimensional vectors each representing a translated text section of an unstructured document related to corresponding contractual agreement, a knowledge graph storing a taxonomy and / or ontology of relationships pertinent to a standard document type, a generative AI model tuned to analyze sets of vectors corresponding to a set of documents, a document processing pipeline configured to convert unstructured documents for storage in the vector database, and an AI- enhanced virtual agent configured to automatically compare contents of a set of unstructured documents using vector sets from the vector database and information stored in the knowledge graph.

In an illustrative embodiment, systems for performing automated comparisons of contractual agreements include a vector database storing high-dimensional vectors each representing a translated text section of an unstructured document related to corresponding contractual agreement, a knowledge graph storing a taxonomy and / or ontology of relationships pertinent to a standard document type, a generative AI model tuned to analyze sets of vectors corresponding to a set of documents, a document processing pipeline configured to convert unstructured documents for storage in the vector database, and an AI-enhanced virtual agent configured to automatically compare contents of a set of unstructured documents using vector sets from the vector database and information stored in the knowledge graph.

Methods and systems for providing context for alarms and resolving alarms using a virtual agent are described. Inputs including imaging, patient information, and aural, visual, and mechanical patient inputs are analyzed to provide context for an alarm. Based on the context, the methods and systems may identify a patient action that may resolve the alarm. A virtual agent may interact with the patient to identify and resolve the alarm without additional caregiver input.

Techniques for a container orchestration system are disclosed. A container orchestration API server receives a request from a virtual agent in a container orchestration cluster that includes a cloud provider authentication token. The request is generated by the virtual agent using a resource principal that corresponds to the virtual agent. The container orchestration API server attempts authentication of the virtual agent using a container orchestration native authentication. Upon failure of the container orchestration native authentication, the container orchestration API server authenticates the virtual agent using a cloud provider authentication unit via an authentication webhook using the cloud provider authentication token.

Methods and systems for providing context for alarms and resolving alarms using a virtual agent are described. Inputs including imaging, patient information, and aural, visual, and mechanical patient inputs are analyzed to provide context for an alarm. Based on the context, the methods and systems may identify a patient action that may resolve the alarm. A virtual agent may interact with the patient to identify and resolve the alarm without additional caregiver input.

Several examples disclose systems and methods related to displaying images in responses from chatbots, NPCs, virtual agents, digital avatars, etc. A system can identify text corresponding to an image in an electronic document and store a representation of the text associated with an identifier for the image. The system can receive an input prompt for a machine learning model. Using the machine learning model, the system can generate a response to the input prompt. The response can include the image resulting from the identification of the text representation using a search function, as well as output from the machine learning model.

The invention relates to the technical field of man-machine interaction, in particular to a virtual seat construction method and a virtual seat interaction system and method. According to the virtual seat construction method, a real session is used as training data, so that a trained model can better fit a real scene when replying to a user; according to the method, the sessions are spliced into the text for pre-training, and the session features of the real sessions are supplemented to perform two-stage training, so that the model has the long text understanding ability, the accuracy of positioning user questions by the model is improved, and the model is assisted to generate more professional and stable replies. And in combination with an iterative optimization mode based on a loss value, it is ensured that the virtual seat model can be continuously improved by itself along with data accumulation and technology progress, the service quality and efficiency are improved, and a better reply is given to a problem proposed by a user.

Techniques for a container orchestration system are disclosed. A system executes a virtual agent in a cloud network on a virtual node of a container orchestration system. The virtual node hosts multiple container instances within the cloud environment. The system executes a first container instance within the virtual node and connects the first container instance to a first subnet. The system executes a second container instance within the same virtual node and connects the second container instance to a second subnet distinct from the first subnet. The system enables access to the first container instance through the first subnet and enables access to the second container instance via the second subnet. This architecture allows for flexible network configurations within a single virtual node, enhancing resource utilization and network segmentation capabilities in containerized environments.

A system for assisting a customer is provided. The system includes a database comprising multimedia files, where one or more tags are associated with one or more of the multimedia files. The system further includes a virtual agent server 100 configured to receive input from a first user (customer) and a second user (customer service representative). Further, the virtual agent server 100 processes the received input to understand a context of the input. Subsequently, the virtual agent server 100 identifies one or more multimedia files based on the context and the tags associated with the multimedia files. Subsequently, the virtual agent server 100 shares at least one of the identified multimedia files with at least one of the first user and the second user to enable better understanding between the first user and the second user.

A method of generating a set of test datasets for evaluating large language model agents, the method including: extracting, using a large language model, application programming interfaces (APIs) associated with procedures for one or more target intents; generating, using the large language model, a flowgraph based on the APIs and the procedures for the one or more target intents; generating, using the large language model, a conversation graph based on the flowgraph; generating, using the large language model, conversations based on at least the conversation graph, the APIs, and a series of sampled paths from the conversation graph; and extracting the set of test datasets from the conversations.

This disclosure relates to method and system for generating near real-time responses to user queries. The method may include generating, via a Large Language Model (LLM), a set of predicted queries and a corresponding set of predicted responses, based on historical data or a real-time input user query associated with a user account, using a customized knowledge graph; creating a set of predicted query embeddings and a set of predicted response embeddings, using an embedding model; comparing a subsequently received real-time input user query with each of the set of predicted queries through a similarity analysis; and upon successful comparison of at least one of the set of predicted queries, generating in near real-time, via the LLM, a response to the real-time input user query based on the set of predicted response embeddings of each of corresponding predicted responses using the customized knowledge graph.

Techniques are provided (e.g., a method, a system, non-transitory computer-readable medium storing code, or instructions executable by one or more processors) herein for automated compatibility assessment and migration asset shape generation. A method can include receiving replication strategy from a user, receiving metadata of a source asset collected via a virtual agent located in a source environment, applying rules for shape recommendation based on the replication strategy received from the user, selecting potential shapes based on the rules for shape recommendation and the collected metadata, filtering the shapes based on user limits, identifying a best shape based on shape price, and providing a recommendation for the best shape to the user.

A system and method are provided for context-aware virtual assistance and cross-application action execution based on real-time visual input. A client device captures real-time images of a real-world environment and analyzes the images to identify objects or regions of interest. Eye-tracking information is used to determine user interest in the identified objects or regions, and a user context is determined based on visual information, eye-tracking information, and a history of user interactions aggregated across multiple applications. Computer-generated visual content is presented as an overlay on the real-time images based on the determined user context, the overlay comprising a recommendation for a follow-on action associated with a second application. The response is presented via at least one of text, synthesized speech, or computer-generated visual content on a wearable display. Upon detecting user acceptance, the system causes execution of the follow-on action by the second application.

The invention relates to a multi-agent video multi-round question and answer method based on implicit knowledge enhancement, and the method comprises the steps: merging the video features of a real agent and the features of a virtual agent, and generating an extended agent feature set; constructing a multi-agent video question and answer model; training a multi-agent video question and answer model based on the extended agent feature set to obtain a trained multi-agent video question and answer model; and inputting the video features of the plurality of real agents and the to-be-processed question text features into the trained multi-agent video question and answer model to obtain a final video question and answer result. According to the method and the device, support features of historical rounds are expressed as virtual agent features, and unified modeling is carried out on the virtual agent features and real agent features of the current round, so that efficient multiplexing of context information in multi-round questions and answers is realized. The method has remarkable advantages in question and answer accuracy, calculation efficiency and communication overhead, and a new solution is provided for multi-round multi-modal question and answer tasks.

We provide a conversation delivery system with improved usability. [Solution] The conversation provision system comprises conversation units 84, 86, 88 that instruct a task processing device 50, which processes tasks using artificial intelligence in response to task processing instructions, to generate conversation content for at least one of a plurality of virtual agents for the user, and acquire the conversation content generated by the task processing device 50 and output it to the user; and notification units 78, 82, 92 that, for multiple individual notifications to the user from multiple virtual agents, summarize and combine the individual notification sources and individual notification content of the multiple individual notifications, and notify the user of the main agent among the plurality of virtual agents as the notification subject.

Systems, methods and / or computer program products personalizing user interactions with virtual agents of applications and / or services, using audio / visual components customized to appeal to user preferences. Upon initial interaction with virtual agents, AI ranking algorithms are triggered to adopt the highest ranked persona for the virtual agent based on previous positive interactions with the user, learned preferences, the user's state inferred from facial expressions, body language, tone. Personas can emulate voice signatures of popular characters, actors, celebrities and sports figures, and access a corpus of dialogue of the available personas to learn unique speech patterns, slang, tone, grammar, speed, and vocabulary. The corpus that comprises various personas of real and / or fictional individuals can include data of the mannerisms and visual likeness of the various characters and people, allowing avatars depicting the virtual agents to be animated in the likeness of the selected persona in real-time during conversational workflows.