551 results about "Dialog system" patented technology

Systems and methods are described herein for detecting and reducing hallucinations and improving the reliability of an LLM-based QA system. Particularly, the disclosure provides a set of hallucination detection and handling approaches that address different types of hallucinations of the QA system. The hallucination detection approaches described herein include comparing a natural language answer with context information by way of sentence similarity estimation and keyword matching. The hallucination handling approaches described herein include removing hallucinated sentences from the natural language answer or regenerating the natural language answer using better context information, depending on a level of hallucination detected in the natural language answer. A hybrid framework is also provided that systematically combines the hallucination detection approaches and hallucination handling approaches into one system to achieve an optimal hallucination-reduction performance for the QA system.

The invention relates to the field of natural language understanding in an artificial intelligence technology man-machine dialogue system, in particular to a psychological accompanying dialogue method based on multi-agent collaboration and a storage medium. The psychological accompanying dialogue with individuation, high naturalness and accurate emotion recognition is provided, the user experience is effectively improved, and the psychological support requirement of the user is met. According to the main scheme, the method comprises the steps of performing multi-mode emotion evaluation on user input to obtain user emotion state description; retrieving related dialogue states and external knowledge from a shared memory module according to user questions and user emotional state description; according to the retrieved dialogue state and external knowledge, the strategy planning module generates a reply strategy to obtain a strategy group; the dialogue content generation module calls a corresponding vertical domain agent according to the generated reply strategy to generate specific reply content; and storing the user questions and model replies in the current round into the short-term memory of the shared memory module, and updating the long-term memory. The method is used for AI dialogues.

A task-oriented dialog system determines an endpoint in a user utterance by receiving incremental portions of a user utterance that is provided in real time during a task-oriented communication session between a user and a virtual agent (VA). The task-oriented dialog system recognizes words in the incremental portions using an automated speech recognition (ASR) model and generates semantic information for the incremental portions of the utterance by applying a natural language processing (NLP) model to the recognized words. An acoustic-prosodic signature of the incremental portions of the utterance is generated using an acoustic-prosodic model. The task-oriented dialog system can generate a feature vector that represents the incrementally recognized words, the semantic information, the acoustic-prosodic signature, and corresponding confidence scores of the model outputs. A model is applied to the feature vector to identify a likely endpoint in the user utterance.

The invention discloses a personalized care method, device and equipment based on an AI technology and a storage medium, and solves the technical problem that an artificial intelligence dialogue system lacks dynamic memory, multi-dimensional user portrait updating and personalized care strategies in the prior art. The method comprises the steps of collecting data and preprocessing the data; the method comprises the following steps: generating a dynamic user feature vector by constructing an LSTM-GRU hybrid neural network structure; dynamic evolution of a user portrait is realized through incremental learning and memory attenuation, and a user multi-dimensional portrait is constructed; constructing a memory storage hierarchical architecture; extracting and optimizing keywords based on a medium-term memory storage system, and optimizing and constructing an interest graph by utilizing a hierarchical clustering method according to a keyword weight enhancement formula; based on a memory storage hierarchical architecture, establishing a causal relationship and a sequential relationship between entity nodes and emotion nodes to construct a memory association knowledge graph; and establishing a trigger mechanism, performing emotion memory composite analysis based on the memory association knowledge graph, and generating a care strategy. The method can be widely applied to the artificial intelligence technology field.

The invention discloses a generative dialogue system based on a large language model, relates to the technical field of artificial intelligence, and aims at the limitation of an existing generative dialogue system in multiple rounds of dialogues, and adopts the scheme that a dialogue interface module is responsible for receiving user input and displaying an output result; the dialogue state tracking module generates prompts by using key information codes, combines context conversion, finely adjusts a large language model by using transfer learning, constructs a sample library real-time retrieval example, and realizes accurate tracking of multiple rounds of dialogue states; the thinking chain reasoning module stores and manages intermediate state information, dynamically retrieves and calls a tool to execute a task and integrate a result, and establishes reasoning logic to understand a user intention; and the dialogue generation module captures a context and adjusts a generation strategy based on a Transform architecture large language model to realize personalized reply. The method is used for accurately identifying the user intention in multiple rounds of conversations.

An LLM is adapted to generate database queries that are compatible with a proprietary database of a security provider. Adapting the LLM includes evaluating performance of the LLM after initial prompt engineering / fine-tuning to ensure that generated database queries are valid (i.e., comport to the database schema and can be executed to return results). When the LLM performance is satisfactory, a dialogue system uses the LLM to generate database queries from user queries. The dialogue system determines intent of each user query, which informs whether the query is supported. Supported user queries are converted to database queries using the LLM and submitted to the database. The dialogue system leverages another language model to generate a summarized, natural language representation of the database query results and constructs a response from the summary. The dialogue system also checks for XSS and prompt injection before database queries are ultimately submitted to the database.

In various examples, systems and methods are disclosed relating to language model jailbreak detection using length-perplexity metrics. A system can identify a prompt for a language model—such as an LLM, VLM, etc.—and generate a perplexity score for the prompt. The system can determine, based at least on the perplexity score and a length of the prompt, that the prompt is indicative of a jailbreak attempt for the large language model. The system can restrict the prompt from input to the large language model—or block an output generated based on the prompt from being shared—responsive to determining that the prompt is indicative of the jailbreak attempt.

The invention relates to the technical field of customer services, in particular to an intelligent outbound call skill generation method, system and device using LLM and a medium, and the method comprises the steps: collecting user voice data and text dialogue data in real time, and converting the user voice data and the text dialogue data into a time sequence aligned text sequence matrix based on the user voice data and the text dialogue data; inputting the time sequence aligned text sequence matrix into a preset multi-mode sentiment analysis model, and calculating a user sentiment tendency value; extracting an intention keyword based on the text sequence matrix with the aligned time sequence, inputting the intention keyword into a preset intention recognition model, and outputting a purchase intention probability of the user; and according to the user emotion tendency value and the user purchase intention probability, calling LLM to generate a personalized outbound call, and outputting the personalized outbound call to a dialogue system. The method has the advantages that high-quality and dynamic-adaptability customer service is achieved, and user experience is remarkably improved.

An intelligent task-type dialogue method based on a large language model, comprising: acquiring a dialogue with a user; identifying and parsing input information of the user to obtain an identification and parsing result; on the basis of the identification and parsing result, synchronously updating the state of a dialogue state tracker; on the basis of the intelligent guidance of the tracker, entering a proper dialogue scene node; executing a preset Action to complete a specific task; and on the basis of the current dialogue node context and dialogue historical data, generating a feedback message of a robot. In the method, by combining the large language model, rapid adaptation and efficient configuration of a scene can be achieved, and by dynamically loading the configuration information of a specific scene, a round of dialogue process can be efficiently pushed on the basis of preset process logic. Also disclosed are an intelligent task-type dialogue system based on a large language model, an electronic device, and a computer program product.

The invention discloses a speech recognition streaming feature extraction and batch reasoning method for a high-concurrency artificial intelligence real-time dialogue system. According to the method, a heterogeneous computing architecture in which a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit) cooperatively work is adopted, operations such as preprocessing, feature extraction and normalization of voice data are executed through the CPU, and batch feature reasoning is executed by utilizing the GPU; the method specifically comprises the following steps: after segmenting and preprocessing voice data at a CPU (Central Processing Unit) end, executing Mel filter bank feature extraction and cepstrum mean variance normalization to obtain a standardized acoustic feature vector; extracting feature vectors from the feature buffer area in batches at the GPU end, filling and aligning the feature vectors, and sending the feature vectors to a neural network model for parallel reasoning calculation; according to the method, streaming processing and batch reasoning in the speech recognition process are realized, and the concurrent processing capability and the real-time performance of the system are effectively improved.

Disclosed in the present application are a task-type dialogue response method and apparatus. The method comprises: acquiring basic dialogue information of a task-type dialogue, wherein the basic dialogue information at least comprises: intent information of the current round of request, and historical dialogue information; using a dialogue state large language model to analyze the basic dialogue information, so as to obtain a target dialogue policy request based on a domain-specific language; using a dialogue policy loader to load a target dialogue policy sample corresponding to the target dialogue policy request; using a dialogue policy large language model to analyze the target dialogue policy sample, so as to obtain a target dialogue generation policy; and using an engineered-dialogue generation module to execute the target dialogue generation policy, so as to obtain request response information, and outputting the request response information. The present application solves the technical problems in the related art of the capability of processing a multi-round task-type dialogue by means of a dialogue system being relatively poor and the user experience being poor.

Provided are a content generation method and apparatus, a model construction method and apparatus, and a data processing method and apparatus, a device, and a medium. The method comprises: in response to a dialogue initiated by a user, obtaining dialogue data (202); when this round of dialogue is the first round of dialogue, the dialogue data being a current question of the user in this round of dialogue; when this round of dialogue is not the first round of dialogue, the dialogue data comprising a current question of the user and previous historical questions of the user; inputting the dialogue data to an independent question transformation model, so that the independent question transformation model transforms the dialogue data into an independent question that represents a user intention of the user in this round of dialogue (204), wherein training samples used by the model comprise a plurality of rounds of dialogue samples and an independent question sample, and the independent question sample indicates a user intention of a latest round of dialogue sample among the plurality of rounds of dialogue samples; and inputting the transformed independent question to a multi-round dialogue system, so that the multi-round dialogue system generates reply content for this round of dialogue on the basis of the independent question (206). The reply accuracy of the multi-round dialogue system can be improved.

The invention provides an emotional dialogue generation method fusing knowledge and an emotional reason context graph, and relates to the technical field of information processing. The invention provides a common emotional dialogue generation model fusing knowledge and an emotional reason context graph, and the model comprises six modules: an utterance coding module, a dialogue context graph fusing knowledge, a knowledge-enhanced KDCG network module, an emotional classification module, an emotional reason recognition module and a reply generation module. The problem of contextual information integration in multiple rounds of dialogues is effectively solved by introducing an emotion reason contextual graph, the understanding ability of the system on implicit expression emotions and intentions is improved by introducing background knowledge in a knowledge base and combining the emotion reason contextual graph, and finally the understanding depth of the dialogue system on user emotions is comprehensively improved. Through joint modeling of emotions and reasons, the system can more clearly understand the emotion source of the user, so that a more targeted and humanized emotional response is generated.

The invention relates to the technical field of artificial intelligence dialogue systems, in particular to an intention correction and optimization method and system for multi-round dialogue context memory. According to the method, joint semantic coding is carried out on user input and historical dialogues, key semantic elements are extracted to construct an intention evolution relation graph, context consistency verification is carried out on an initial intention recognition result, and an intention correction candidate set is generated when conflicts are detected; and dynamically adjusting the context coding weight of the historical dialogue based on the corrected intention recognition result. According to the method, the intention recognition accuracy and context coherence in multiple rounds of conversations are effectively improved, and the semantic migration risk is reduced.

The invention provides a dynamic tool integration method and system for an intention-driven AI dialogue system, and the method comprises the steps: S5, extracting resource occupation information from a transaction log according to a state persistence record, carrying out the resource release and temporary context cleaning of each heterogeneous component, and obtaining a released resource list; s6, searching a breakpoint state snapshot and a transaction log from the distributed database according to the released resource list, and reconstructing a tool chain execution flow historical state to obtain a fault context analysis result; and S8, according to the context recovery state and the semantic feature vector, updating a tool chain execution stream, and reallocating computing resources through a heterogeneous component coordination mechanism to obtain a task continuity confirmation result. According to the method, the recovery efficiency and the resource utilization rate of the tool chain in an abnormal scene are remarkably improved, and the task continuity and the system robustness in a high-concurrency environment are guaranteed.

The invention discloses a media file query and retrieval method and system based on an AI dialogue scene, the method combines a mixed mode of vector retrieval and keyword retrieval, realizes accurate retrieval of cross-modal data, and can process various media files including texts, pictures, videos, PPT and the like. According to the method, a double-round scoring mechanism of a large language model (LLM) is combined, firstly, the relevancy of file content is scored, then secondary scoring is carried out according to the matching degree of a file title and user query, and it is ensured that the file most relevant to query is called. In addition, the system can further utilize a user feedback mechanism to continuously optimize the retrieval precision, and the user experience is improved. Compared with the prior art, the method has the advantages that the accuracy and the efficiency of multi-modal data retrieval are remarkably improved, the limitation of a traditional AI dialogue system during multimedia file processing is solved, and the method is suitable for intelligent dialogue application scenes needing to quickly and accurately obtain various types of media files.

A method, apparatus and system configured to provide automated dialog engagement through the use of at least one dialog playbook to guide a dialog conversation between an automated dialog engagement system and an automated dialog engagement system user. The automated dialog engagement system utilizes a large language model (LLM) in conjunction with the at least one dialog playbook to guide the dialog conversation. The LLM provides responses to the automated dialog system user when a response is not available from the at least one playbook.

The invention relates to the field of treatment healing dialogues, and particularly discloses a large model dialogue system for psychological treatment healing, which is characterized in that word segmentation processing of consultation texts is carried out by using a deep learning-based natural language processing technology and a coding mode, and then semantic embedding coding is carried out on word granularity description of each consultation text after word segmentation, so that a large model dialogue is obtained; and intelligently generating a recommended dialogue strategy tag according to the feature jump semantic propagation representation between the word granularity description semantic embedding features of each consultation text, and obtaining a dialogue text based on the tag and the consultation text. According to the method, the intention and the emotional state of the user can be better understood, and according to the real-time emotional state and the consultation content of the user, a common-situation or question-asking strategy is flexibly selected, so that a more personalized response is provided, and the problem of improper question asking or insufficient common-situation asking in a traditional system is avoided.

To solve the problem of the restriction and efficiency of dialogue in the conventional market research method by providing a market research tool allowing a user interview by a chat with a feeling conducting a web questionnaire.SOLUTION: A system for providing a market research tool allowing a user interview by a chat with a feeling conducting a web questionnaire includes: means allowing dialogue with a user; means for achieving chat dialogue with a target customer by AI; and means for preparing and presenting a report.SELECTED DRAWING: Figure 1

The invention belongs to the technical field of natural language processing, discloses a historical dialogue screening method and device for a dialogue system, and solves the problems that according to a historical dialogue screening scheme in the traditional technology, cross-time and cross-theme content may be omitted, dialogues without obvious keywords are difficult to process, the screening result deviates from user expectation, and the screening effect is poor. And the effect of screening dialogues lacking obvious intentions is poor. The method comprises the following steps: storing historical dialogue data between a user and a dialogue system based on the time and theme of a dialogue; when historical dialogue screening is carried out, firstly, the similarity between a current question and stored historical dialogue data is calculated, and weighted fusion of semantic similarity, keyword similarity, theme similarity and context similarity is included; and then based on a preset dialogue screening threshold, combining a similarity calculation result of the current question and the stored historical dialogue data, and screening out historical dialogue data most related to the current question from the stored historical dialogue data. The method is suitable for the dialogue system.

The invention discloses a cascade-based multi-modal digital human real-time dialogue system and method, belongs to the technical field of artificial intelligence, and aims to solve the technical problem of how to realize efficient, multi-modal and customizable digital human real-time dialogue. Comprising a voice recognition module used for converting user voice into text information through an industrial-grade voice recognition toolkit; the large voice model module is used for generating dialogue reply information according to the text output by the voice recognition module; the text-to-voice module is used for converting the reply information output by the large voice model module into voice information; the speaker generation module is used for generating a digital human speaking video through an accurate lip shape synchronization technology based on the voice information; and the front and back end interaction module is used for realizing streaming transmission of videos and user interaction.

The invention provides an AI dialogue system based on multi-modal input, relates to the field of AI intelligent interaction, and adopts a data analysis technology based on artificial intelligence to perform image semantic feature extraction on an intention expression image input by a user and perform text semantic understanding on an intention expression text input by the user. And intelligently generating a reply text based on features and cue words obtained by performing principal component analysis interactive fusion on the semantic coding features of the intention expression image and the semantic coding features of the intention expression text. Therefore, by analyzing the multi-modal intention expression data, the AI dialogue system can more accurately understand the actual intention of the user, so that more accurate answering is provided, and the user experience is improved.

The invention discloses a 3D point cloud large model dialogue security protection system and method based on reinforcement learning and a protection layer, a reinforcement learning security alignment module takes a GPT4Point framework as a base, constructs a point cloud-language joint embedding space, extracts global semantic features by using a multi-layer Transform architecture, realizes efficient alignment of 3D point cloud and text instructions, and improves the security of the 3D point cloud large model dialogue. According to the multi-modal protection layer architecture, lightweight Lama Guard serves as a core model, and cross-modal risk interception is achieved by analyzing geometric features of text entities and associated point clouds generated by a target model in real time. According to the invention, through fusion of reinforcement learning security alignment, a large model protection layer and a GPT4Point multi-mode framework, a multi-level security protection system oriented to a 3D point cloud large model dialogue system is constructed. According to the collaborative design of a reinforcement learning dynamic optimization strategy and a Lama Guard filtering mechanism, the robustness of the model under attack resistance and the adaptability of the model in a natural distortion scene are remarkably improved, and the unified architecture of GPT4Point provides efficient support for point cloud-language understanding and generation.

The invention relates to the field of medical information processing, and discloses a reinforcement learning and cooperation system based on Internet hospital medical dialogues and medical records, and the system comprises a complete dialogue chain obtaining module which is used for obtaining a complete dialogue chain of patient input-large model reply-doctor modification in each round; the feedback format construction module is used for constructing a structured feedback format based on the complete dialogue chain to serve as a training sample of reinforcement learning, and the structured feedback format comprises input content, original reply, doctor editing content, editing behavior labels and semantic difference; and the reinforcement learning optimization module is used for introducing a reinforcement learning algorithm PPO on the basis of the existing supervised fine tuning model, and executing reinforcement learning optimization oriented to the medical dialogue system based on the training sample. According to the method, the problems that in an existing medical inquiry dialogue system, the response lacks reasoning transparency, the model cannot be continuously optimized, doctor feedback is not utilized, and the system request pressure is uncontrollable can be solved.

The invention relates to the technical field of government affair entrepreneurship guidance service intelligent dialogue systems, in particular to a dialogue intention recognition and correction method based on a knowledge graph, and the method comprises the steps: obtaining a voice signal and text information inputted by a user, and carrying out the cross-modal fusion processing to generate a semantic vector; carrying out evolution modeling on the dialogue state by adopting a graph neural network, and outputting a dynamic dialogue state graph containing a time sequence relationship between a user entity and a business object; taking the semantic vector and the focus information as query conditions, executing dynamic subgraph sampling from the government affair knowledge graph, and generating an intention correction strategy vector; and finally, utilizing reinforcement learning to generate personalized guide statements and outputting the guide statements to the user. According to the method, through deep coupling of semantic understanding, state tracking, knowledge reasoning and decision optimization, real-time perception and active completion of dynamic updating of hidden nodes and policies of the government affair process are achieved, and the intention recognition accuracy and systematic adaptive capacity are effectively improved.

The invention relates to the technical field of intelligent customer service, and discloses an intelligent customer service automatic answering method and system. The method comprises the following steps: constructing a dialogue semantic vector according to a question input by a user and a historical dialogue context; calculating an activation probability corresponding to each field sub-expert model based on the dialogue semantic vector; determining a first core expert model and a second core expert model by using the activation probability, and calculating a corresponding first core expert weight and a corresponding second core expert weight; according to the first core expert weight and the second core expert weight, utilizing a first core expert model and a second core expert model to carry out collaborative reasoning on the dialogue semantic vector to obtain a fusion feature vector; according to the method, the continuity and semantic comprehension accuracy of multiple rounds of dialogues are improved, the expert scheduling accuracy and efficiency are improved, and then the accuracy and integrity of a dialogue system in problem processing in the professional field are improved.

The invention discloses a large language model fine-grained prejudice removing method and system based on prejudice intensity, and belongs to the field of generative artificial intelligence. According to the method, a multi-model collaborative fine-grained data labeling method is introduced, the prejudice intensity of samples is quantified through a plurality of mainstream large language model voting mechanisms, and the problem that the prejudice intensity cannot be measured in a traditional method is solved; in addition, an improved direct preference optimization loss function is designed, optimization weights of different prejudice are distinguished through prejudice intensity weighting, a probability decoupling regular term is introduced to block homodromous growth of neutral answer and prejudice answer generation probabilities, and the prejudice probability is prevented from abnormally rising in the prejudice removing process. According to the method, fine-grained and differentiated prejudice removal optimization is realized, prejudice in a large language model can be effectively removed, meanwhile, the training stability can be effectively improved, and the method is suitable for scenes such as a dialogue system and text generation.

The invention relates to the technical field of natural language processing, and discloses a natural language processing-based customer service intention recognition method, which comprises the following steps of: firstly, acquiring user text information from a customer service dialogue system, and performing preprocessing such as word segmentation, stop word removal and word form reduction to obtain a standardized text; then calculating semantic features, extracting intention frequency and change trend, judging an intention stage, and dynamically adjusting an intention recognition confidence threshold; adjusting intention classification model parameters through a classification control algorithm, and feeding back optimized word segmentation algorithm parameters according to accuracy; and finally, optimizing a control signal output time sequence, dynamically updating preset parameters, and realizing accurate identification. The system comprises a text processing module, an intention calculation module, a classification control module, an intention adjustment module and a dynamic optimization module. The method and system can improve the accuracy and efficiency of customer service intention recognition, adapt to intention state changes of different users, and have good application prospects.

The invention discloses an accompanying dialogue system and method based on real-time environment perception and knowledge graph enhancement. The system comprises a multi-mode real-time environment perception module, a knowledge graph construction and enhancement module, a natural language understanding and dialogue management module, a personalized recommendation and narration generation module and an immersive multi-mode interaction module. The method comprises the steps of multi-modal real-time environment perception and situation data generation; performing dynamic association, query and enhanced reasoning on the knowledge graph; natural language understanding and dialogue management, personalized recommendation and narrative generation, and immersive multi-modal interaction presentation and feedback reception. According to the method and the system, the concern point of the user, namely scenery or details, can be accurately positioned, and context information required by subsequent service intelligence is provided, so that the problems of poor environment perception ability, weak interaction immersion, dull knowledge service, lack of individuation, insufficient intelligent accompanying experience and the like in the existing tourism auxiliary technology are solved.

The invention provides a man-machine conversation method and device, a storage medium and a program product. The method comprises the steps that whether an input problem relates to at least one target professional knowledge point or not is detected; when the input question relates to at least one target professional knowledge point, constructing a large model reading understanding cue word according to each target professional knowledge point and the input question; and inputting the large model reading understanding cue word into the large language model to determine a corresponding reply answer. Therefore, through an intelligent target knowledge point detection and cue word construction mechanism, the dialogue system can automatically adjust the answer strategy according to questions in different fields, and more accurate and professional answers can be provided for users.