Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

415 results about "Human computer dialogue" patented technology

Multimodal dialogs using large language model(s) and visual language model(s)

Implementations relate to leveraging large language model(s) (LLMs) and vision language model(s) (VLMs) to facilitate human-to-computer dialogs. In various implementations, one or more digital images may be processed using one or more VLMs to generate VLM output indicative of a state of an environment. An LLM prompt may be assembled based on the VLM output and a natural language input. The LLM prompt may be processed using one or more LLMs to generate content that is responsive to the natural language input. The content that is responsive to the natural language input may subsequently be rendered at one or more output devices.
Owner:GOOGLE LLC

Psychological accompanying dialogue method based on multi-agent collaboration and storage medium

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.
Owner:GUANGDONG DIGITAL IND INTELLIGENT TECH CO LTD

Automatic prompt construction method based on man-machine conversation history and semantic retrieval

The invention relates to the technical field of artificial intelligence, and discloses a man-machine dialogue history and semantic retrieval-based prompt automatic construction method, which comprises the following steps of S1, performing text preprocessing on historical dialogue data and user input, including dynamically generating query keywords, verifying and analyzing a file uploaded by a user, and extracting core contents; s2, utilizing a pre-training language model to map the historical dialogue and the user request into semantic vectors, matching in combination with the keyword weight, and constructing a historical vector set and a user request vector; and S3, extracting a context fragment most relevant to the user request from the historical dialogue vector based on a convex optimization method. The context information highly related to the user request is accurately extracted through the sparse optimization technology, and the background information, the user request and the generation instruction are organically integrated in combination with the dynamic Prompt template design, so that the semantic correlation and context coherence of the generated reply are improved, and the interference of redundancy and irrelevant information is avoided.
Owner:BEIJING QIBU TIANXIA TECH CO LTD

Cabin scene recommendation method and device, storage medium, program product and vehicle

The invention discloses a cockpit scene recommendation method and device, a storage medium, a program product and a vehicle, and relates to the technical field of artificial intelligence, and the method comprises the steps: carrying out the preprocessing of man-machine conversation text data of a voice burying point log of the vehicle, obtaining the natural language description of a user, carrying out the similarity screening in a preset scene knowledge base, and obtaining a voice burying point log of the vehicle; obtaining corresponding scene knowledge; splicing the user natural language description with the scene knowledge to obtain a scene recommendation prompt word; and performing scene action reasoning on the scene recommendation prompt word through the large model agent, and outputting a scene action execution list corresponding to the scene knowledge. According to the method, man-machine conversation text data is converted into user natural language description, corresponding scene knowledge is screened, scene action reasoning is carried out based on the powerful text understanding and generating capacity of a large model agent, and the intelligent scene recommendation service of the cockpit can be automatically realized according to the voice description of a vehicle owner; and the accuracy of cabin scene recommendation is improved.
Owner:DONGFENG MOTOR GRP

Man-machine conversation method, device and equipment and computer readable storage medium

The embodiment of the invention provides a man-machine conversation method, device and equipment and a computer readable storage medium. The method provided by the embodiment of the invention comprises the steps that a reading document is selected to enter a first mode, and an interface of a man-machine conversation program in the first mode comprises a reading area and a conversation area; displaying the content of the reading document in the reading area; obtaining first prompt information in the dialogue area, wherein the first prompt information is used for generating a mind map of at least one part of content of the read document; and in response to first prompt information obtained in the dialogue area, generating and displaying a mind map for at least one part of content in the read document in the dialogue area.
Owner:BAICHUAN INTELLIGENT TECHNOLOGY CO LTD

Household appliance fault diagnosis method, terminal device and server

The embodiment of the invention discloses a household appliance fault diagnosis method, terminal equipment and a server. The terminal equipment execution method comprises the following steps: acquiring fault description data input by a user; sending a first query instruction to a server, wherein the first query instruction is used for instructing the server to query target knowledge from a knowledge base according to the fault description data; the knowledge base is generated according to a fault tree structured file, the fault tree structured file comprises at least one fault tree associated with the target household appliance, the fault tree comprises a plurality of nodes, and the nodes are configured with a fault representation image, a fault log, a repair mode and a fault phenomenon corresponding to one fault type; generating prompt word information according to the fault description data and the target knowledge and sending the prompt word information to a server; displaying corresponding response content on the man-machine conversation page according to response information sent by the server; the response information comprises the fault type and the recommended repair mode of the target household appliance. Therefore, the fault diagnosis accuracy and the fault repair efficiency of the household appliance can be improved.
Owner:HISENSE VISUAL TECH CO LTD

Man-machine conversation method based on large language model, program product, equipment and medium

The invention provides a man-machine dialogue method based on a large language model, and the method comprises the steps: starting a dialogue from a starting node of a predefined dialogue process, and transmitting initial problem information configured by the starting node to a user; initial reply information input by the user for the initial question information is received, and a first intention recognition node is determined based on the initial reply information; displaying a node question corresponding to the current node to the user, and receiving intention reply information input by the user for the node question; determining subsequent nodes according to the intention reply information and a candidate option set predefined by the current node through a large language model; and displaying reply information corresponding to the reply node to the user until the determined node is the reply node. The combination of the graphical process and the large language model enables the dialogue path to advance according to the preset logic, reduces the risk of deviating from the core target, and enhances the naturalness and flexibility of the dialogue by using the semantic understanding capability of the large language model, so that the reply of the user can be better understood.
Owner:上海金桥信息科技有限公司

Human-computer interaction method and electronic equipment

The invention discloses a man-machine interaction method and electronic equipment, and relates to the field of AI. The method is applied to the electronic equipment and comprises the steps that a user instruction is received, multiple target APIs are obtained according to a scene intention in a scene where the user instruction represents the scene intention, and the multiple target APIs correspond to the scene intention. And outputting a result of calling the plurality of target APIs, wherein the result of calling the plurality of APIs can be used for realizing a user demand corresponding to the scene intention. Thus, the electronic equipment can directly output the API calling result meeting the user requirement under the scene intention based on the scene intention of the user, the API is the direct exposure of the application function, the more abundant, comprehensive and convenient response result is achieved by directly outputting the result of calling the multiple APIs, the user requirement can be met, and the man-machine conversation effect is improved.
Owner:HUAWEI TECH CO LTD

Spoken English man-machine conversation interaction training method and system

The invention discloses a spoken English man-machine conversation interaction training method and system, and relates to the technical field of spoken English training, spoken English audio signals of a user are monitored in real time through a microphone, and the frequency spectrum information of the audio signals is refined into each frame of spectrogram and cepstrum coefficient feature vectors by using Fourier transform and feature extraction technologies; therefore, the voice signal characteristics of the user can be completely captured; three core dimensions of semantic similarity, grammatical structure similarity and fluency are incorporated into an evaluation model, a comprehensive oral English training evaluation system is formed, a text sequence is generated by analyzing a time sequence dependency relationship through a convolutional neural network, and the oral English training evaluation model of a deep learning technology is combined, so that the oral English training evaluation accuracy is improved. According to the method, the expressions of the user in the aspects of semantics, grammar and fluency can be accurately measured, the oral training level of the user can be comprehensively judged by the system by comparing the comprehensive evaluation coefficient with the preset qualified threshold value, and a personalized learning guide is provided according to a result.
Owner:SCHOOL OF SCI & LITERATURE JIANGSU NORMAL UNIV

Maintenance consultation intelligent customer service system based on large language model

The invention relates to the technical field of instant messaging, and discloses a maintenance consultation intelligent customer service system based on a large language model, and the system consists of a user input processing and checking module, an intention recognition and information extraction module, a dynamic knowledge retrieval module, an intelligent reply generation module and a reply optimization and quality control module. According to the system, safety and compliance check is conducted on user input through a large language model, improper or potentially harmful content is automatically filtered out, dialogue safety is ensured, key information is extracted through the system, accurate information support is provided for follow-up processing, targeted preliminary replies are generated according to the dialogue state and user input, and the dialogue efficiency is improved. The system can judge whether the information is complete or not and guide the user to supplement the information if necessary, so that the reply effectiveness is improved, and the beneficial effect of intelligent and accurate man-machine conversation is achieved.
Owner:SHANGHAI LOONGJOY ELECTRONIC CO LTD

Generating a composite response to natural language input using a trained generative model and based on responsive content from disparate content agents

Generating expanded responses that guide continuance of a human-to computer dialog that is facilitated by a client device and that is between at least one user and an automated assistant. The expanded responses are generated by the automated assistant in response to user interface input provided by the user via the client device, and are caused to be rendered to the user via the client device, as a response, by the automated assistant, to the user interface input of the user. An expanded response is generated based on at least one entity of interest determined based on the user interface input, and is generated to incorporate content related to one or more additional entities that are related to the entity of interest, but that are not explicitly referenced by the user interface input.
Owner:GOOGLE LLC

Man-machine conversation method and device based on RAG, storage medium and program product

The invention provides an RAG-based man-machine conversation method and device, a storage medium and a program product, and the method comprises the steps: obtaining conversation context information associated with an input question, and completing the input question according to the conversation context information to determine a rewriting optimization question; performing RAG retrieval according to the rewriting optimization questions to determine at least one corresponding related background knowledge, and constructing large model cue words according to the related background knowledge and the rewriting optimization questions; and inputting the big model cue word into the man-machine conversation big language model, and determining a reply answer for the input question according to the output content of the man-machine conversation big language model. Therefore, through continuous tracking and analysis of the dialogue context information and rewriting of user questions, the retrieval accuracy, the generation intelligence and the dialogue consistency of the system are effectively improved, and then the application performance and the user experience in a multi-round human-computer interaction scene are improved.
Owner:AISPEECH CO LTD

Human-machine conversation method and apparatus, device, and storage medium

A human-machine conversation method and apparatus, a device, and a storage medium. The method comprises: acquiring a user statement of a current round; determining, from one or more candidate tables, one or more target tables that match the user statement; parsing the user statement of the current round to obtain a first query statement; according to the first query statement, querying from the one or more target tables to obtain target data; and generating a system reply of the current round according to the target data.
Owner:ALIBABA DAMO (HANGZHOU) TECH CO LTD

Intelligent tour guide man-machine conversation method and system based on knowledge graph retrieval

The invention provides an intelligent tour guide man-machine conversation method and system based on knowledge graph retrieval, and relates to the technical field of artificial intelligence and natural language processing. The method comprises the following steps: collecting relevant data of scenic spots in a preset range, carrying out structured processing on all the relevant data of the scenic spots, and constructing a knowledge graph in the tour guide field; establishing indexes for entities and relationships in the knowledge graph, and introducing an adaptive query optimization mechanism; selecting a pre-trained language model and performing LoRA fine tuning on the pre-trained language model to obtain a fine tuning language model; a user initiates a dialogue request; the dialogue request accesses the fine tuning language model to obtain a preliminary answer result, and accesses the knowledge graph to obtain knowledge graph information; and matching and fusing the preliminary answer result and the knowledge graph information, and outputting a corrected answer result. According to the invention, knowledge can be effectively fused between the tour guide explanation field and the general field, and the accuracy and comprehensiveness of answers are improved.
Owner:XUSHI YIDONG CULTURE TECHNOLOGY (SHANGHAI) CO LTD

Man-machine conversation method and device, storage medium and program product

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.
Owner:AISPEECH CO LTD

Man-machine conversation method based on AI intelligent large model

The invention discloses a man-machine dialogue method based on an AI intelligent large model, relates to the technical field of artificial intelligence man-machine dialogue methods, and aims to solve the problems that during man-machine dialogue of Chinese contexts, word meanings and sentences are different in different contexts and different dialect using habits, the man-machine dialogue is difficult to accurately analyze, and the man-machine dialogue effect is poor. The method comprises the following steps: step 1, constructing a large model, and carrying out pre-training through text data; 2, carrying out fine adjustment on a specific task or field; 3, understanding a historical dialogue; 4, generating a natural language reply; 5, setting a dialogue management capability; 6, learning different dialogue styles and emotions; 7, adding and implementing a filtering mechanism and setting a dialogue rule; 8, the user sets the required field and sets the type of the interaction role; 9, learning domain knowledge and corresponding expression modes; and step 10, replying and collecting and feeding back optimization performance.
Owner:南京千雪智能科技有限公司

Schedule creation method, system and device and medium

The invention provides a schedule creation method, system and device and a medium, the method comprises the following steps: receiving a to-be-processed message representing natural language content, the to-be-processed message being used for indicating creation of a target schedule; according to the to-be-processed message, a response message is generated, and the response message comprises schedule description information; and creating a target schedule according to the schedule description information. In the method, a user only needs to input natural language content indicating schedule creation intention, a server side (such as a digital assistant) can generate a response message aiming at the message input by the user by analyzing the message input by the user, and the schedule is automatically created according to schedule description information. Therefore, a user does not need to manually input schedule information one by one in the schedule creation module, and rapid and efficient schedule creation can be realized through man-machine conversation.
Owner:BEIJING ZITIAO NETWORK TECH CO LTD

Man-machine conversation model training method based on generative pre-training model and related device

According to the man-machine conversation model training method and device based on the generative pre-training model provided by the invention, the model is trained by using the data sets of different dimensions, so that the applicability of the model to the preset field is improved. Moreover, a reinforcement learning data set and a score output by the reward model are used to train the model to obtain a dialogue model, and the reinforcement learning data set comprises a question belonging to a preset field, a first answer corresponding to the question, a second answer corresponding to the question, first security data and second security data. The first security data indicates that the first answer meets the use rule, and the second security data indicates that the second answer does not meet the use rule, so that the fusion training is beneficial to improving the stability, accuracy and applicability of the model. The dialogue device obtained based on the method has relatively high understanding and reasoning capabilities for data in a preset field, and also has relatively high anti-interference capability.
Owner:QINGDAO HAIER TECH +2

Response method, dialogue system and storage medium in human-computer dialogue

The present application provides a response method, a dialogue system and a storage medium in a human-computer dialogue, and belongs to the field of artificial intelligence technology. The present application can be applied to a dialogue robot, such as a children's companion education robot. During a dialogue between a user and a machine, the present application determines the user's intention in this round of dialogue based on the expected user intention associated with the machine's answer to the user in the previous round of dialogue, and then responds. Since the processing logic of the expected user intention is introduced, the accuracy of the generated response statement is improved.
Owner:HUAWEI TECH CO LTD

Information recommendation method, device, equipment and storage medium based on user portrait

The present invention relates to the field of big data technology, and discloses an information recommendation method based on user portrait, comprising the following steps: receiving a human-computer dialogue chat record in a first scenario in real time through a log collection system Flume; performing desensitization processing on the chat record to obtain first data; performing stop word removal processing on the first data to obtain second data; extracting keywords of the second data through a preset word graph; obtaining a first tag set according to the keywords; removing duplicates from the first tag set data to obtain a second tag set; generating a user interest portrait based on the second tag set, and storing the user interest portrait in a database; receiving a recommendation instruction, and obtaining a user interest portrait according to the recommendation instruction; obtaining information to be recommended corresponding to the recommendation instruction according to the user interest portrait. The present invention also provides an information recommendation device, equipment and storage medium based on user portrait, and the information recommendation method based on user portrait provided by the present invention improves the accuracy of user portrait.
Owner:CHINA PING AN LIFE INSURANCE CO LTD

Multimodal dialogs using large language model(s) and visual language model(s)

Implementations relate to leveraging large language model(s) (LLMs) and vision language model(s) (VLMs) to facilitate human-to-computer dialogs. In various implementations, one or more digital images may be processed using one or more VLMs to generate VLM output indicative of a state of an environment. An LLM prompt may be assembled based on the VLM output and a natural language input. The LLM prompt may be processed using one or more LLMs to generate content that is responsive to the natural language input. The content that is responsive to the natural language input may subsequently be rendered at one or more output devices.
Owner:GOOGLE LLC

Model training method, text processing method and related products

The invention discloses a model training method, a text processing method and a related product, and relates to the technical field of artificial intelligence. In combination with a first single intention recognition model, screening out a first subtext group which is reasonably segmented (a first target single intention set of the first subtext group is matched with a first candidate single intention set of the multi-intention text) as a first training sample, and using the multi-intention text as a first label of the first training sample for training an initial text merging model; therefore, the target text merging model is obtained through training without manual data annotation, and the model training cost is reduced. When the target text merging model trained by the method is used in man-machine conversation, multiple single-intention texts can be merged into one multi-intention text, so that text expression closer to reality expression is obtained, and the purpose of enhancing the text expression capability is achieved.
Owner:MASHANG CONSUMER FINANCE CO LTD

Human-machine conversation method and apparatus, device, and storage medium

A human-machine conversation method and apparatus, a device, and a storage medium. The method comprises: acquiring a user statement of a current round; determining, from one or more candidate tables, one or more target tables that match the user statement; parsing the user statement of the current round to obtain a first query statement; according to the first query statement, querying from the one or more target tables to obtain target data; and generating a system reply of the current round according to the target data.
Owner:ALIBABA DAMO (HANGZHOU) TECH CO LTD

AI agent interaction method and system based on semantic analysis

The invention relates to the technical field of semantic recognition of man-machine conversation, and provides an AI agent interaction method and system based on semantic analysis, and the method comprises the steps: collecting voice data of a user, converting the voice data into text data, and obtaining the collection time of each character in the text data; determining the information complexity of the text data of the user and the repeated interaction rate of the voice data, performing syntactic analysis on the text data, and screening the deviation voice data of the user in combination with the entity number difference, the repeated interaction rate and the information complexity; determining a voice habit characteristic value of the user and a real intention probability of deviation voice data; and according to the real intention probability of the deviation voice data, re-screening voice data from the deviation voice data, and according to the re-screened voice data and the deviation voice data, realizing AI agent interaction based on semantic analysis. According to the method, the accuracy of AI agent semantic analysis and user real intention recognition can be improved.
Owner:上海炎凰数据科技有限公司

Intelligent software cost evaluation interaction method and system based on man-machine conversation

The invention provides a man-machine conversation-based software cost intelligent evaluation interaction method and system, and relates to the technical field of software cost evaluation, and the method comprises the steps: obtaining project description information, carrying out intention recognition and entity extraction, and carrying out semantic matching in combination with a knowledge graph to obtain candidate cost references; according to the method, the estimation reference value is generated based on multi-dimensional similarity calculation and weight self-adaptive adjustment, user feedback correction is supported, accurate evaluation and dynamic adjustment of the software cost are achieved, and the accuracy, transparency and efficiency of software cost evaluation are improved.
Owner:BEIJING ZHONGJI DIGITAL TECHNOLOGY CO LTD

Intelligent reply method for user service, medium and electronic equipment

The invention provides an intelligent reply method for a user service, a medium and electronic equipment, and can input current input information and historical context information of a user into a deep learning model to obtain an identified user intention, and then input the user intention and a question decomposition instruction into the deep learning model to obtain decomposed sub-intentions, thereby improving the user service reply efficiency. Acquiring skill indication information according to the sub-intention, inputting the sub-intention, the skill indication information and the user associated information into a deep learning model to acquire reply content, inputting the reply content and a content retouching instruction into the deep learning model, acquiring the reply content after combined retouching, and feeding back the reply content to the user, so that the user intention can be accurately understood; and accurate reply contents and services related to the business are provided according to the user association information in combination with the user demand, so that the problem that the intelligent customer service cannot accurately reply the intention of the user in combination with the business information in the prior art is solved, man-machine conversation can be more natural, smoother and more concise, and the conversation efficiency and service experience of the user are effectively improved.
Owner:FENGLAN XINGCHEN (SHANGHAI) ARTIFICIAL INTELLIGENCE TECHNOLOGY CO LTD

Intelligent voice interaction official document exchange system based on large model and man-machine conversation control method

The invention relates to the technical field of official document exchange, and discloses an intelligent voice interaction official document exchange system based on a large model and a man-machine conversation control method, and the system comprises a confidential document management subsystem which is used for the transmitting and receiving business management of a document; the voice interaction module is used for receiving and analyzing a user voice instruction; the control module is used for scheduling each sub-module in the system to complete an operation instruction; the data processing module is used for analyzing and processing contents, states and circulation of documents and letters based on a large model; and the feedback module is used for feeding back the execution result to the user in a voice or text form. According to the technical scheme, a three-member management platform is adopted to perform labor division management and real-time safety auditing on the system permission, the technical effect of improving the system permission distribution reasonability and the overall operation safety is achieved, and compared with the technical scheme of concentrated permission and lack of effective auditing and safety management in the prior art, the technical scheme has the advantages that the system permission distribution reasonability and the overall operation safety are improved. And the defects of permission abuse and security vulnerability hidden dangers are overcome.
Owner:CHENGUANG ANYI (BEIJING) TECH CO LTD

Man-machine conversation method and system based on retrieval enhancement

The invention discloses a man-machine dialogue method and system based on retrieval enhancement, and relates to the technical field of artificial intelligence. The man-machine dialogue method comprises the steps that firstly, innovative example retrieval is introduced, personalized example pairs with rich information are selected, and then four cognitive relationships are recognized through a preset common sense conversion model; the understanding of the situation and implicit psychological state of the help seeker is deepened. Finally, the multi-source knowledge is fused through the support decoder, it is ensured that response generation has the same psychology and cognitive consciousness, and the dialogue experience feeling of the user is improved.
Owner:SUN YAT SEN UNIV

Man-machine conversation method and device, computer equipment and storage medium

The invention relates to a man-machine conversation method and device, computer equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: for a to-be-processed problem sent by a user terminal, obtaining a vector similarity corresponding to the to-be-processed problem; the vector similarity is determined based on the vector of the to-be-processed question and the vector corresponding to each question and answer text in the question and answer library; under the condition that the vector similarities are smaller than a preset threshold value, determining a target classification result corresponding to the to-be-processed problem based on the large model and the classification prompt word; the target classification result is one of question and answer texts in a question and answer library and performance functions in a function library; under the condition that the target classification result is the performance function in the function library, performing parameter extraction on the to-be-processed problem based on the large model and the parameter cue word to obtain a function parameter corresponding to the performance function; and determining an output result of the performance function through the function parameter, and returning the output result to the user terminal. By adopting the method, the reply accuracy can be improved.
Owner:CHINA LIFE INSURANCE CO LTD

Task type multi-round dialogue system enhancement method based on general intention

The invention discloses a task type multi-round dialogue system enhancement method based on a general intention. The method comprises the following steps: loading a general intention recognition model of a task type multi-round dialogue; obtaining current user input and a corresponding man-machine conversation history; inputting the current user input and the corresponding man-machine conversation history into a general intention recognition model, and outputting a corresponding general intention list by the model; extracting the intention and task elements of the dialogue from the general intention enhanced task dialogue large model input by the current user and the corresponding man-machine dialogue history, and generating a corresponding reply; and repeating the steps until the dialogue task is completed, and ending the dialogue. According to the method, the capability of a large language model thinking chain is utilized, a general intention is introduced into a task type multi-round dialogue system in a large language model era to serve as an auxiliary means, the intention recognition capability in the task type multi-round dialogue system is effectively improved, and the success rate of the whole dialogue of the system is effectively increased.
Owner:HARBIN INSTITUTE OF TECHNOLOGY (SHENZHEN) (INSTITUTE OF SCIENCE AND TECHNOLOGY INNOVATION HARBIN INSTITUTE OF TECHNOLOGY SHENZHEN)