434 results about "Chatbot" patented technology

Techniques are described for performing automated operations related to generating and providing housing-related information, such as to automatically respond to free-form natural language query requests for housing-related information of various types received by a chatbot by using a combination of automated tools to generate and provide responsive housing-related information. In at least some situations, the described techniques generates responses using a trained large language model that maintains context over an interaction session with a user involving multiple user queries and corresponding responses, and ensuring accurate response information by restricting the generation of the response information in particular ways and by identifying and providing citations to authoritative sources used to generate the response information.

There are provided systems and methods for a fine-tuning system for large language models trained for open-ended domain-specific tasks. An online transaction processor or other service provider may provide computing services and platforms to entities, which may include chatbots, information retrieval systems, question-and-answer systems, and the like. To provide better LLM training and fine-tuning, which may improve LLM performance in answering users' questions in an automated manner, the service provider may implement a fine-tuning system that may utilize automated annotations of training data, such as query and response pairs. An LLM may be prompted to determine an annotation to such pairs, and the annotations may be used to label the training data. A fine-tuning system and operations may then be implemented to fine-tune the LLMs using different processes including question-answering, retrieval augmented generation, or a continuous fine-tuning based on a size of the training data.

Apparatuses, systems, and techniques to cause weights assigned to properties of chatbot answers to be dynamically adjusted. In at least one embodiment, one or more neural networks are used to characterize one or more chatbot queries and cause weight values assigned to properties of answers to the one or more chatbot queries to be dynamically adjusted, based, at least in part, on the characterization of the one or more chatbot queries.

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.

An end-side-cloud three-in-one active chat robot system for high-emotional merchants comprises an end side, a local edge server and a cloud end, and the end side is used for collecting multi-modal data of a user and performing local lightweight real-time processing and response execution; the local edge server is used for receiving and fusing the multi-modal features and the context information from the end side, and carrying out sentiment calculation, dialogue management and active trigger decision making with medium complexity; the cloud end is used for operating a super-large-scale model and providing global knowledge management, long-term user portrait storage and model training optimization; and the end side, the local edge server and the cloud end carry out cooperative communication through an encrypted channel to form a distributed intelligent processing architecture. According to the method, global optimization is realized by integrating end-side lightweight sensing, edge multi-modal fusion and cloud long-term memory. A composite finite state machine (FSM) active questioning mechanism is combined with sentiment calculation, and is different from traditional rule type triggering. Off-line and on-line fusion scheduling and multi-agent role playing are combined to be applied to a high-emotional-quotient interaction scene, and the simulation is improved. Multi-modal emotion perception circulation is introduced, and the problem of single text emotion misjudgment is solved.

A retrieval-augmented generation method for a large language model receives a user query and generates a vector embedding of the user query. The vector embedding of the user query is stored in an embedding vectors space. Also stored in the embedding vectors space are embeddings of documents retrieved from a corpus of information / A retrieval-based artificial intelligence (Al) model identifies which documents are relevant to the user query according to a similarity measure applied to the vector embedding of the user query and the vector embeddings of the documents. The generative Al model receives the user query and the documents identified as relevant to the user query and generates new content, based on the user query and the documents identified as relevant to the user query.

A system for an automated generation of legal documents based on legal case-related data, including a processor of a legal assistant server (LAS) node configured to host a machine learning (ML) module coupled to a chatbot module and connected to at least one user-entity node over a network and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: acquire a user request comprising legal case-related data from the at least one user-entity node; parse the legal case-related data to extract a plurality of key classifying features; acquire legal consultation with the user data from the chatbot module; query a local database to retrieve local historical legal cases′-related data based on the plurality of key classifying features and the legal consultation data; generate at least one classifier vector based on the plurality of the key classifying features, the legal consultation with the user data and the local historical legal cases′-related data; and provide the at least one classifier vector to the ML module configured to generate a legal jurisdiction-based predictive model for producing a set of legal case evaluation parameters for a document generation module configured to generate at least one legal document for the legal case comprising an electronic pleading paper.

An autonomous customer support Chatbot Agent utilizes a large language model to aid in implementing a workflow to solve a customer issue. A natural language workflow policy may be selected by an admin, along with tools such as API calls. The large language model determines the implementation details for the workflow based on the workflow policy and the selected tools.

There are provided systems and methods for identifying relevance of documents for automated retrieval models using large language models. An online transaction processor or other service provider may provide computing services and platforms to entities, which may include chatbots, information retrieval systems, question-and-answer systems, and the like. To provide better retrieval model training and refinement, the service provider may generate training data from user interaction logs, which may include user feedback that may be used to determine if documents are relevant to queries, and therefore should be retrieved for answering those queries by automated retrieval models. An LLM may be used as a judge to determine whether chatbot responses reference certain document. If not references, the query may be analyzed to determine whether certain retrieved documents are relevant. Data pairs may be generated for the training data from these processes and used for model refinement.

The technology described herein, among other things, relates to testing applications, backed by language models (LMs), for compliance with responsible artificial-intelligence (RAI) guidelines. For example, LM-based chatbots have proliferated across many different domains and implementations. These chatbots, however, may be susceptible to attacks or attempts to cause the chatbots to violate RAI guidelines by producing harmful content and / or potentially violating copyrights. To evaluate whether an LM-based application, such as a chatbot, is complying with respective RAI guidelines, the technology disclosed herein adaptively simulates conversations with the LM-based application in an attempt to cause the LM-based application to violate the RAI guidelines in a controlled, simulated environment.

A building security system including computer-readable storage media having instructions stored thereon that, when executed by processors, cause the processors to: provide one or more machine learning models, at least one of the one or more machine learning models trained to identify contextual information within video data, the at least one machine learning model trained using at least one of video data or image data and annotations to the at least one of the video data or the image data, and provide a chatbot configured to: receive and process one or more input videos using the at least one machine learning model to identify the contextual information from the one or more input videos, receive a query from a user relating to the one or more input videos, and generate, by the one or more machine learning models, a response to the query using the contextual information.

The invention discloses an information recommendation method and device, a storage medium and electronic equipment, and relates to the technical field of recommendation systems.The method comprises the steps that in response to terminal interaction operation, input data is obtained; filling the input data into a first preset prompt word template according to a preset format to form first fusion data containing prompt guide information; inputting the first fusion data into a prediction model, and outputting an intention label and an associated extended keyword set through intention analysis and keyword extension processing; performing semantic matching and preference matching based on the intention tag, the extended keyword set and locally stored chat robot Chatt related data to obtain a candidate Chatt set; filling a second preset cue word template with the first fusion data and the candidate Chatpot set according to a preset format to form second fusion data containing an adaptive service scene; and inputting the second fusion data into the prediction model, and determining Chatpot recommendation information.

An intelligent assistant incorporating a Large Language Model (LLM) can transform a transcript containing communications regarding tasks into structured data. The transcript can be a meeting transcript or a transcript of a chatbot chat that was autonomously initiated by the intelligent assistant to obtain additional information regarding a task. With LLM assistance, the intelligent assistant transforms unstructured communication data from the transcript into structured data which is then assigned to relevant task objects stored in a database. Prior to processing a transcript, personal data therein can be sanitized, and the intelligent assistant can divide the transcript into smaller segments which each encapsulate a discussion of a different topic.

The disclosure improves the efficiency and accuracy of Financial Planning & Analysis functions within large companies. This improvement is facilitated via a chatbot tool, which functions against financial systems in an organization. Key tool components include a chat interface, a presentation component, a visualization component, a forecast component, and an AI component. The AI component provides AI capabilities to the other components (chat, presentation, visualization, and forecast). Behind the scenes, the tool provides data reconciliation functions, which permits information to be gathered from multiple sources, which are reconciled to each other. Data sources include various types of databases relational and non-relational ones, as well as data cube structures. The query functions permit natural language queries and other queries through a chatbot or chat-like interface.

A computer-implemented method for facilitating telemedicine service is provided. The method includes receiving, by a server computer from a client device over a network, a user request for telemedicine services, wherein the user request is received through a chatbot application for facilitating the telemedicine service. The method includes analyzing the user request using an AI application on the server computer, wherein the AI application includes machine learning algorithms configured to interpret the user request. The method includes generating a response to the user request based on the analysis. The method includes transmitting the generated response to the client device through the chatbot application.

A system for automating information technology software actions using advanced AI techniques including a processing system, storage medium, a communications interface, a user interface, a natural language processing model or neural network, operable to interface with at least one of an embedded prompt or chatbot prompt and hosted on a control node which communicates with one or more nodes comprised by a node network via the communications interface, and program instructions on storage medium that direct the processing system to receive an instruction from the user interface, process the instruction using the one or more natural language processing model or neural network, along with one or more AI agents, and execute the instruction one of locally or on a node of the node network via the communications interface.

Techniques for a knowledge-graph system to use large language models (LLMs) to build knowledge graphs to answer queries submitted to a chatbot by users. The knowledge-graph system builds the knowledge graph using answers produced by an LLM for novel queries. The chatbot will continue to use the LLM to answer novel queries, but the chatbot may harness the knowledge graph to answer repeat questions to gain various efficiencies over LLM-backed chatbots. For example, the knowledge-graph system may easily debug or otherwise improve the answers in knowledge graphs, store provenance information in knowledge graphs, and augment the knowledge graphs using other data sources. Thus, the reliability and correctness of chatbots will be improved as the bugs and inaccuracies in answers provided by the LLM will be corrected in the knowledge graphs, but the chatbots can still harness the abilities of LLMs to provide answers across various subject-matter domains.

A system for dynamically adapting a conversational artificial intelligence (AI) system includes a chatbot system, a feedback and classifier unit, and a document generator. The chatbot system generates a response to a user query. The feedback and classifier unit receives the user query, a large language model (LLM) provided response, and system architect provided feedback to create a data object. The unit retrieves a set of ternary questions from a questions database and processes the data object using the LLM to generate answers, creating a feature vector of ternary answers. It then determines a classification label for the feedback by processing the feature vector with a decision tree, where the label indicates a knowledge or behavioral update. The document generator creates a new document based on the classification label and feedback and updates a knowledge base or prompts database with the new document based on the determined classification label.

Provided is a method for providing a user interface pattern recommendation service. In the method: (a) an administrator terminal registers app information; (b) a user terminal selects the app information and inputs a question to request a chatbot query; (c) a platform server refers to a platform DB and transmits key data including an UI pattern, a user preference, and a selection history via an information inquiry API; (d) an AI model within the platform server receives user input data, analyzes the data in real time using RAG technology and a self-trained model, and recommends a UI pattern preferred by a user; (e) a chatbot response module within a chatbot server receives the chatbot query; (f) the chatbot response module generates a chatbot response by referring to a chatbot DB; and (g) the chatbot response API receives the generated chatbot response and transmits the response to the user terminal.

Various systems and methods are presented regarding detecting data drift. The data of interest can be batches of utterances received at an interface (e.g., a chatbot). The batches of utterances can be compared with topics present in training data utilized to train a data classifier (e.g., an autoencoder), wherein topics identified in the batches of utterances that are not present in the training data can be considered to be novel topics. The greater the presence of novel topics in a batch of utterances, the greater the divergence of the batch of utterances from the content of the training data. The novel topics can be identified and subsequently applied to the training data such that the data classifier can be re-trained with the novel topics, thereby causing the data classifier to be contemporaneous with the novel topics. In an embodiment, the utterances can be short streams of text, symbols, and suchlike.

Methods and system is provided for enhancing online grocery shopping through an Artificial Intelligence (AI) Virtual Shopping Assistant integrated within retail online shopping or ordering platforms. User inputs in natural language are received, specifying shopping requests such as recipes or events along with any user desired conditions. The assistant processes these inputs, interacts with a chat bot to generate a preliminary list of items, and checks item availability against an online inventory. Fuzzy matching algorithms are processed which consider user and / or store-based preferences, store discount data, store price data, and inventory data to refine the item suggestions. The refined list is presented to the user for review, allowing modifications like additions, deletions, or substitutions. Confirmed items are automatically added to the user's online cart for checkout with the corresponding retail shopping or ordering platform providing seamless integration with the online platform.

An active chatbot system with behavioral awareness and on-demand conversation and a method thereof are disclosed. In the active chatbot system, a client-end host continuously senses a client behavior state, and transmits the sensed client behavior state and an on-demand conversation setting to a server-end host to generate a rough question message having a natural language structure, and input the rough question message to a plurality of finite state machines to generate a precise question message. The server-end host transmits the precise question message to an artificial intelligence platform to obtain a corresponding answer message, stores the answer message to an answer list, filters out an answer message matching the on-demand conversation setting as an on-demand conversation message, transmits the on-demand conversation message to the client-end host for output. Therefore, the technical effect of improving human-computer interaction and initiative of chatbot can be achieved.

It is a challenge to ensure the reliability of generative artificial intelligence (AI), due to a number of factors, including uncertainty, ambiguity, the absence of ground truth, variability among models, ethical implications, and the like. Accordingly, embodiments implement a chatbot that is capable of determining a user's intent, uses a preference model to select one of a plurality of generative AI models that is best suited for that intent, and responds using the selected generative AI model. In addition, the chatbot may capture users' sentiments in their replies and update the preference model accordingly, for continual improvement in the selection of the generative AI models using reinforcement learning from human feedback. The preference model may also account for other metrics of each generative AI model, such as performance, utility, and ethics.

Security, privacy, and data use restrictions in group communication with multiple large language model (LLM) chatbots or agents are provided. In-context user consent is obtained for operations performed by LLM agents on behalf of the user as and when needed. A first message directed to a first LLM agent is received via a user interface (UI). Based on a determination that the first message is to invoke a second LLM agent, a consent request for consent of a user to invoke the second LLM agent is provided via the UI. Upon receiving the consent of the user to invoke the second LLM agent, the second LLM agent is invoked within the context of the UI. In some examples, a command to enter private mode may be received to limit the communication in the private mode only selected LLM agents.

An apparatus in an illustrative embodiment comprises at least one processing device that includes at least a processor and a memory coupled to the processor. The at least one processing device is configured to implement an artificial intelligence system comprising at least one large language model (LLM) agent, to perform in the LLM agent interactive image segmentation of at least one input image through interaction of the LLM agent with one or more users, to generate in the LLM agent an interactive image understanding comprising attention values computed by multiple distinct attention mechanisms based on one or more results of the interactive image segmentation, and to carry out additional user interactions via the LLM agent utilizing the interactive image understanding comprising the attention values computed by the multiple distinct attention mechanisms. In some embodiments, the LLM agent is illustratively utilized to provide at least a portion of an AI chatbot.

An artificial intelligence based chatbot development system discloses a method including receiving from a user a configuration file including chatbot framework information for configuring a framework for a chatbot for a team of end users, the user configuration file including at least one of a name of a team, one or more document sites related to the team, one or more incident identifications searched by the team, determining a plurality of data sources relevant to the team based on the chatbot framework information, downloading a plurality of document chunks from the data sources relevant to the team, processing the plurality of document chunks to generate metadata tags related to the document chunks, vectorizing the metadata tags to generate metadata embeddings for the plurality of document chunks, and in response to receiving a user query, using the metadata embeddings to select a collection of the document chunks that are passed to a language model (LM) with the user query.

A chatbot system includes a computer hardware system for implementing a chatbot and a hardware processor configured to initiate the following executable operations. A user prompt associated with a user and directed to the chatbot is received from a client device. An interactive voice response (IVR) tree associated with the user prompt is identified. The user prompt and the IVR tree are encoded into an encoded input. The encoded input is consumed by a trained neural model, and the neural model generates, using the encoded input, business process information. The trained neural model generates, using the business process information, an answer, and the answer is provided to the client device.

Systems and methods are disclosed for automated generation, validation, and deployment of infrastructure-as-code (IaC) using a multi-agentic artificial intelligence / machine learning (AI / ML) architecture. An extraction agent parses multimodal artifacts (e.g., diagrams and / or configuration data) to derive or generate infrastructure set-up parameters. A coding agent generates IaC units based on the extracted parameters. A validation agent determines the syntactic and semantic compliance of the generated IaC, classifying the IaC as executable, non-executable, or identifying corrective actions. A deployment agent transmits executable IaC to target computing environments and manages automated provisioning of the IaC in the target environments. In cases of validation failure, error indicators are provided to a user (e.g., via an agentic chat bot) for clarification or correction, enabling iterative refinement.

Metadata associated with program code documentation is identified, wherein the program code documentation is associated with corresponding program code. A natural language question regarding the corresponding program code is obtained via a virtual agent. A response to the natural language question is determined based on the metadata using one or more trained machine learning models. The response to the natural language question is provided to the virtual agent.

An industrial chatbot system and associated chatbot interface support various user experience features designed to improve the chatbot's utility within an industrial context. These features include the ability to invite selected users or teams to participate in an ongoing chatbot thread or conversation, the ability to switch between knowledge domains during a chatbot session, the ability to save prompts for selective resubmission to the system, the ability to organize and share multiple chatbot threads among different teams or team members, constraining submission of prompts in a collaborative multiuser context so that prompts are submitted and processed in an organized manner, and the ability to define prompt-based dashboards that can be stored and deployed on demand or in response to defined conditions.