55 results about "Dialog system" patented technology

The application discloses a specific field pipeline task type dialogue system based on an LLM, which comprises an inquiry subsystem and an answering subsystem, wherein: the inquiry subsystem parses and guides a user to supplement key information of a question according to user input task text, the answering subsystem summarizes key information of a dialogue task, and performs vector matching through a built-in vertical field local vector database to generate a final answer to the dialogue task. The application uses a large language model to realize natural language understanding, dialogue state tracking and natural language generation modules in a task type dialogue system pipeline, simultaneously realizes a rule matching-based strategy learning module, understands and replies to user input text, and combines the content of a local knowledge base, so that the whole process is more interpretable, the illusion problem of the large language model is reduced, only a small amount of sample prompt learning is needed, a large amount of data training or fine tuning is not needed, and the workload during field migration is reduced.

We provide the system. [Solution] A receiving method that accepts language selection, A generation means for generating learning content based on a generative AI model, An acoustic conversion means that presents the generated learning content as an audio output, A voice analysis method that converts user voice information into text data, A management system that continues the dialogue based on user responses and provides feedback, A dialogue system that includes this.

This invention belongs to the technical field of natural language processing and dialogue systems. It discloses a multi-target dialogue recommendation method based on hierarchical prompt optimization, including hierarchical target label modeling, learnable prompt embedding initialization, graph attention enhancement mechanism, multi-task learning framework, and response generation model. Hierarchical target label modeling encodes the hierarchical relationships between target labels into a graph structure. Learnable prompt embedding initialization integrates label semantics and deep hierarchical information into the encoder input space. The graph attention enhancement mechanism enhances the label vector structure perception ability through information transmission and aggregation between label prompts. The multi-task learning framework jointly optimizes masked language modeling and hierarchical multi-label classification. The response generation model uses the predicted target as a control signal to guide generation. This method effectively models the hierarchical dependency relationship between target types and target entities, enhances the structure perception ability of label vectors, maintains the model's language understanding ability, and improves the accuracy of target prediction.

In various examples, interactive systems that use neural networks to determine financial investment predictions or recommendations are presented. Systems and methods are disclosed that determine financial predictions or recommendations associated with one or more investments using a neural network(s). The financial predictions may include a predicted movement of an investment (e.g., extremely down, down, preserved, up, extremely up, etc.), a predicted price of an investment (e.g., a future stock price, etc.), a specific investment for a user to buy / sell / trade, and / or so forth. In some examples, the systems and methods may include an interactive system(s), such as a dialogue system(s), that interacts with users to provide the financial predictions.

The application discloses a dialogue method and device based on multi-agent driving, which is applied to a customer service dialogue system and includes the following steps: obtaining user features corresponding to current user input in a sample conversation, gold medal customer service input and a standard dialogue strategy; pre-training an expert model to predict a combined dialogue strategy corresponding to the user features and a decision sensitivity factor; taking the combined dialogue strategy as a constraint, pre-training a customer service model to generate a quasi-customer service reply corresponding to the user features; based on the gold medal customer service input, the quasi-customer service reply, the decision sensitivity factor, the standard dialogue strategy and the combined dialogue strategy, respectively optimizing the pre-trained customer service model and the pre-trained expert model to generate a quasi-customer service model and a quasi-expert model. Thus, the embodiment solves the problems of model decision and execution coupling and imprecise combined dialogue strategy execution in the prior art based on a double-model hierarchical collaborative architecture and a hard constraint transmission mechanism of the combined dialogue strategy.

This invention proposes a psychological diagnosis and treatment dialogue method based on dynamic knowledge evolution and adaptive retrieval, belonging to the fields of natural language processing and intelligent medical technology. The method includes constructing a psychological counseling generation model, an urgency prediction module, and a background process auxiliary model; initializing a patient knowledge base; sending the patient's current dialogue input to the background process auxiliary model to extract key information and determine whether retrieval is needed; if no retrieval is needed, the psychological counseling generation model generates a response, and the current dialogue ends; otherwise, the retrieval yields a set of candidate structured memory units, which are adaptively reordered to obtain context information; the context information is concatenated with the current dialogue input and sent to the psychological counseling generation model to generate a therapeutic response conforming to psychological counseling standards; and the knowledge base undergoes dynamic evolution and incremental updates. This invention overcomes the limitations of the traditional "static profile" of dialogue systems, achieving long-term continuity and dynamic adaptability of diagnostic and treatment memory.

The application discloses a retrieval enhancement generation method and system based on knowledge boundary perception, an electronic device and a storage medium, and belongs to the technical field of natural language processing. The method comprises the following steps: generating a high-quality supervised track by using a teacher model, and learning the ability of gap planning and answers by instruction fine-tuning of a weak model; paired samples reflecting overconfidence and over-conservatism are constructed, and a DPO algorithm is used for confidence calibration; gap planning is generated by a student model during actual prediction, and it is accurately determined whether each knowledge point needs retrieval according to cognitive information labels, and accurate retrieval is triggered only for the knowledge points with knowledge gaps. The application can be widely applied to open domain question answering, dialogue systems and knowledge-intensive tasks by explicitly identifying knowledge boundaries, dynamically adjusting thresholds and fine-grained on-demand retrieval, while ensuring the accuracy of answers, significantly reducing the consumption of computing resources and response delay.

Methods and systems are presented for providing multi-tiered cache system that works with an artificial intelligence (AI)-based conversation system for facilitating a conversation with users and processing transactions for the users. The multi-tiered cache system includes multiple tiers of cache modules that use different structures for caching and / or querying data. As a new utterance is received, the cache system uses each of the cache modules in sequence to determine whether a cache hit occurs. If a cache miss occurs at a first cache module, the cache system determines if a cache hit occurs at a second cache module. When a response is obtained from one of the cache modules and / or the AI model, the cache system updates the cache modules using the response.

The application discloses a spoken dialogue dynamic generation method and system based on voice emotion feedback and belongs to the technical field of voice interaction. The application obtains emotion change trend parameters, current task load indexes and interactive load acceleration parameters by performing data processing on the obtained data, and then calculates the comprehensive intervention tendency value by taking the emotion change trend parameters and the interactive load acceleration parameters as input. If the comprehensive intervention tendency value reaches the early warning trigger threshold value and does not reach the intervention trigger threshold value, preventive protection state data is output. If the comprehensive intervention tendency value reaches the intervention trigger threshold value, real-time intervention state data is output. According to the data output by the judgment, dialogue generation parameters are dynamically adjusted to output target dialogue reply data. The application improves the synergy of user emotion fluctuation and interactive load state in the spoken dialogue generation process and solves the problem that the existing dialogue system lacks the function of synergistically adjusting user emotion fluctuation and interactive load state.

The present disclosure relates to improved semantic parsers including a coarse semantic parser and a fine semantic parser. Techniques are described for improving a semantic parser of a dialog system by decomposing the semantic parser into a coarse semantic parser and a fine semantic parser. The methods described herein include accessing an utterance received in a dialog system. The utterance is a text-based natural language expression. The methods further include applying a coarse semantic parser to the utterance to determine an intermediate logical form for the utterance. The intermediate logical form indicates one or more intents in the utterance. The methods further include applying a fine semantic parser to the intermediate logical form to determine a logical form for the utterance. The logical form is a syntactic expression of the utterance according to an established grammar, and the logical form includes one or more parameters of the one or more intents. The logical form can be used to have a conversation with a user of the dialog system.

We provide the system. [Solution] A means for selecting from multiple dialogue systems based on user requests and providing the selected dialogue system to the user's device, A means for acquiring information from the above dialogue system from an information processing device and controlling the dialogue with the user based on that information, A means for integrating a dialogue system into a device that performs physical tasks in the user's living space, and for performing dialogue according to the task at hand, A means of providing the user with the option to change the dialogue system based on the interaction with the user, A system that includes this.

The application provides a medical conversation method and system based on intention jump identification and semantic completion, relates to the technical field of medical data retrieval, and comprises the following steps: jointly encoding historical conversation sentences and a current input sentence to obtain a context semantic vector; inputting the context semantic vector into a double-task classification model to obtain weighted prediction probabilities of each word element under a follow-up question classification task and a jump classification task; sequentially aggregating the weighted prediction probabilities of each word element to respectively obtain a sentence-level follow-up question probability score and a jump probability score of the current input sentence; calculating a dynamic determination threshold, performing threshold determination, and obtaining an intention determination result of the current input sentence; performing differential semantic completion processing on the current input sentence according to the intention determination result; and inputting a target query sentence into a preset knowledge base for matching retrieval, and generating a conversation response result based on the returned matching result. The application can improve the service quality and user experience of the conversation system in a complex interaction scene.

Embodiments of the present application provide a user intention recognition method and device, equipment and storage medium, and relate to the technical field of computer, aiming to improve the efficiency and accuracy of intention recognition, the method comprises: obtaining a to-be-recognized text and a plurality of candidate intention description sentences; processing the plurality of candidate intention description sentences to obtain a plurality of candidate intention corresponding sentence vectors; splicing each word vector corresponding to each word in the to-be-recognized text to obtain a word vector sequence corresponding to the to-be-recognized text; determining a user intention matching the to-be-recognized text from the plurality of candidate intentions based on the word vector sequence corresponding to the to-be-recognized text and the plurality of candidate intention corresponding sentence vectors.

To provide technology that enables more efficient modification of dialogue systems that generate responses based on information provided by users. [Solution] An information processing device that updates constraint information affecting the answers generated in a dialogue with a user, which is a dialogue interface that generates answers based on information provided by a user, comprising: an extraction unit that extracts areas that need improvement based on a record of the dialogue; a generation unit that receives input of knowledge information useful for improving the areas that need improvement and generates update instruction information for updating the constraint information based on the knowledge information; and an update unit that updates the constraint information based on the update instruction information.

A neural dialogue system has been designed to present a conversational user interface for managing security posture of an organization. The neural dialogue system determines intent and extracts entity names from a user input. The neural dialogue system grounds the entity names to an organizational context and maps the intent to a defined functionality related to security posture management for intent realization. Some of these defined functions involve editing the ordered ruleset. When realization of an intent involves editing the ordered ruleset, the neural dialogue system determines various ruleset command sequences that implement the ruleset editing and corresponding impacts on the ordered ruleset (e.g., creation of ruleset anomalies). The dialogue system collects the information retrieved based on the intent and grounded entities, including any ruleset impact assessment, and generates a response.

Methods and systems are provided herein for playing back indexed conversations based on the presence of other people. When a user asks a query, the system monitors the area, determines the other users in the area, and searches its database for a conversation that addresses the query in consideration of the other users present in the area. The system filters the indexed conversations to find conversations that included all the users present and determines the best matching conversation based on the words of the query as well as the keywords from the conversation. Once the system has determined the best match conversation, the system plays back the conversation to the user.

A system and method for agentic conversation for responsible artificial intelligence scoring of artificial intelligence is disclosed. The system includes a processor and memory storing instructions that cause the processor to: receive responses via a conversational interface with a candidate artificial intelligence model aligned to responsible artificial intelligence principles privacy, accountability, safety, security, fairness, explainability, reliability, sustainability; retrieve a question bank and generate question sets dynamically from contextual understanding of prior responses; perform a secure conversational exchange ensuring confidentiality; analyse responses for ethical risks, bias, factual inconsistencies, and compliance deviations; adaptively generate real-time follow- ups via dynamic logic; compute dynamic scores per principle using quantitative metrics for regulatory compliance; compile a structured compliance report with summary, gaps, remediations and confidence; and present via a user interface the scores, report, and metrics for visualization and comparison.

The application provides a dialogue system and a data processing method of the dialogue system. In the dialogue system, a first server receives a user request sent by an end-side device, acquires input query information, and sends the query information to a second server. The second server generates reply content segments contained in reply information in sequence according to the query information, and transmits the generated reply content segments to the first server in real time. The first server outputs the reply content segments to the end-side device in real time, and outputs the generated reply content segments to the end-side device in real time while generating each reply content segment of the reply information. The generation speed of each reply content segment is relatively fast. The generated reply content segments are continuously output to the end-side device in the process of generating the reply information. The generated reply content segments can be output to the user in advance before the complete reply information is generated, so that the response time of the system is shortened, and the timeliness of the dialogue system response is improved.

This application relates to a method and apparatus for evaluating turn-based takeover performance in a full-duplex voice dialogue system. The method includes acquiring a sample dataset, which is a turn-based takeover dialogue dataset. Each sample dataset includes sample speech data, a dialogue state label, a sample dialogue action label, and a sample action reason label. The sample speech data and dialogue state labels are input into the model to be evaluated to obtain predicted dialogue action labels and predicted action reason labels. Based on the predicted dialogue action labels and the sample dialogue action labels, a dialogue action evaluation result is determined. Based on the predicted action reason labels and the sample action reason labels, an action reason evaluation result is determined. Based on the predicted dialogue action labels and the sample dialogue action labels, and the predicted action reason labels and the sample action reason labels, a semantic mismatch result is determined. Finally, based on the dialogue action evaluation result, the action reason evaluation result, and the semantic mismatch result, the turn-based takeover performance of the model to be evaluated is determined.

The application discloses a multi-model parallel calling method and system and an anonymous login protection method. The method comprises the following steps: receiving request information input by a user; determining at least two target AI models which need to be called in parallel; sending the request to the server of each target AI model in parallel; receiving the returned response result; and merging and displaying the response result to the user. The application also provides an anonymous login protection method: generating a local anonymous token which is not associated with any device identifier; storing the token in a local secure storage area; the server only records the association between the token and the operation, and does not record information that can identify the identity; when the user logs out, the conversation record is cleared but the token is retained. The application also provides a subscription management method: storing the token in association with the subscription validity period; and realizing cross-device subscription transfer through a one-time recovery code. Through parallel calling of multiple models, the application improves the response speed and multi-angle answering capability; through the anonymous token mechanism, user identification and subscription management are realized without collecting personal information. The application can be widely applied to AI dialogue systems.

The embodiments provide a method and device for tracking dialogue state, which enables easy extension of services to multi-domain scenarios in a goal-oriented dialogue system by tracking dialogue state based on a non-parametric method using a distance metric and an attention mechanism between an utterance and a context semantic vector corresponding to a domain and an empty slot type when tracking dialogue state.

A method is disclosed for carrying out an automated conversation between a human user and a machine. The method includes providing a conversational graph representative of a user conversation flow in a defined conversation domain. The conversational graph includes a plurality of successively connected states. Each state includes at least one user node representative of a text of a phrase pronounced by the user and at least one agent node representative of a text of a respective at least one phrase automatically generated by a virtual conversational agent.

This application discloses a self-organizing evolution method and system for knowledge graphs based on causal attribution, relating to the field of artificial intelligence technology, aiming to solve the problems of insufficient creativity in dialogue systems and the degradation of knowledge graph structures. The method includes: selecting high-level intents from a causal strategy knowledge graph in response to a dialogue state; extracting subgraphs or paths as semantic constraints and causal utility guides; generating response dialogue using the constraints and guides; performing causal attribution analysis on the dialogue trajectory containing the dialogue to determine the causal contribution of the dialogue to business objectives; and performing a self-organizing rewriting operation on the knowledge graph based on the causal contribution. The system is used to implement this method. This application, by constructing an intelligent closed loop, enables the knowledge graph to self-purify and iterate, realizing a transformation from "limited selection" to "autonomous generation" and from "incremental growth" to "self-organizing evolution," thereby improving the long-term performance of the system.

Provided is a dialogue system including: a speech recognizer module configured to convert a speech of a user into a plurality of candidate texts, and prioritize the plurality of candidate texts; a understanding module configured to determine a first action corresponding to a first candidate text with a highest priority among the plurality of candidate texts; and a controller configured to attempt to perform the determined first action, and when the first action is not performable, reprioritize other candidate texts of the plurality of candidate texts.

A system comprising a hierarchy of language model-based subsystems has been created to deliver responses to end-users that are within the scope of their queries. A first subsystem, or “conversation tracker,” receives user queries and tracks conversations with users. The conversation tracker keeps track of the conversation state, which comprises the historical context of a conversation a user has with the system. The conversation tracker additionally rephrases user queries to include the relevant historical context identified from the conversation. The conversation tracker also analyzes each rephrased user query and determines a domain (e.g., knowledge or task domain) to which the rephrased query corresponds applies. The conversation tracker forwards the rephrased queries to one of a plurality of additional subsystems, or “task resolvers,” for generation of responses that are ultimately relayed to the user.

Methods, computer program products, and / or computer systems protect question and answer dialog systems from adversarial statements that incorrectly answer questions. A computing device accesses a plurality of adversarial statements that are capable of adversarially attacking a question and answer dialog system that is trained to provide correct answers to questions of a particular type. The computing device utilizes the plurality of adversarial statements to train a machine learning model for the question and answer dialog system. The computing device then hardens the trained machine learning model by directing adversarial strategies that identify a plurality of types of adversarial statements onto the trained machine learning model. The computing device then utilizes the trained and hardened machine learning model to avoid adversarial attacks when responding to questions submitted to the question and answer dialog system.