93 results about "Human computer dialogue" patented technology

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.

The application relates to the technical fields of artificial intelligence and man-machine natural language dialogue, and provides a general memory management method and system based on a language model, which extracts memory information needing to be memorized from dialogue content with the language model, generates temporary memory, integrates the temporary memory to obtain persistent memory about a dialogue user, and is integrated into a dialogue process of the dialogue user and the language model to form memory of the dialogue user, so that the dialogue of the dialogue system is controlled, memory type classification management is performed according to the importance of the memory information in the persistent memory, so that the persistent memory contains short-term memory and long-term memory, the importance of the memory information in the persistent memory is updated and managed, and the short-term memory and the long-term memory are forgotten and upgraded, so that flexible and efficient storage and calling of user memory independent of the model type are realized, and the humanized, continuous and personalized dialogue experience in the man-machine dialogue process is improved.

1. Name of the product in this design: Dialog box body of a home decoration graphical user interface for electronic devices. 2. Intended use of this design: for use in electronic devices. 3. The key design features of this product are the graphical user interface. 4. The image or photograph that best illustrates the design's key features: the front view. 5. For electronic devices, which are conventional devices, the rear view, left view, right view, top view, and bottom view are omitted. 6. Purpose of the graphical user interface: The home decoration dialog graphical user interface is used for human-computer interaction, and the dialog box body is used for human-computer dialogue. 7. Human-computer interaction methods of graphical user interface: Human-computer interaction can be carried out through clicking, input, etc., to realize human-computer questioning and answering. 8. Description of the changing states of the graphical user interface: The main view displays the home decoration dialog graphical user interface. Questions can be entered through the input box at the bottom of the dialog box, and the questions and answers are displayed in the chat box in the middle of the dialog box. During the machine's response after a question is entered, the input box displays the current response progress, as shown in the changing state diagram 1. You can click on the status bar to view the changing state diagram 2, which displays the progress list in a pop-up window. 9. Other situations requiring explanation: This design is a partial design, wherein the pink-coated part is the part for which protection is not sought, and the other parts are the parts for which protection is sought.

The application is suitable for the technical field of man-machine conversation, and provides a multi-round conversation generation method and device based on emotion judgment and terminal equipment, the method comprising: obtaining conversation information; identifying first emotion information in the conversation information through an emotion classifier, wherein the emotion classifier identifies and classifies emotions contained in the conversation information based on a classification model, and the first emotion information represents the emotion of the conversation information; determining second emotion information based on the first emotion information by using an emotion transfer mathematical model, wherein the second emotion information is one kind of emotion information in multiple first emotion information, and the emotion transfer mathematical model is used to determine the second emotion information based on conversation time and conversation round; and outputting the current round of conversation containing the second emotion information according to the second emotion information through a conversation generation model. The application can improve the recognition accuracy of the emotion classifier and improve the experience of users using the man-machine conversation system.

The invention discloses a man-machine dialogue psychological stress identification and intervention method and system, a medium and a product, and relates to the field of natural language data processing, and the method comprises the steps: carrying out man-machine dialogue based on a man-machine dialogue strategy through employing a preset man-machine dialogue model; acquiring a multi-modal signal of the detected object in a man-machine conversation process in real time, and performing feature extraction and mapping on the multi-modal signal to obtain a multi-modal fusion answer space; performing psychological stress identification on the multi-modal fusion answer space to obtain a real-time psychological stress level of the tested object; a man-machine conversation strategy of the man-machine conversation model is adaptively adjusted according to the real-time psychological stress level; and executing corresponding operation based on the adjusted man-machine dialogue strategy by utilizing the man-machine dialogue model. The accuracy and robustness of psychological pressure recognition are improved, the man-machine conversation strategy can be automatically adjusted according to the recognition result, and the emotional stability and psychological assistance value of man-machine conversation are improved.

The invention discloses an intelligent fish tank for children enlightenment education, and the fish tank comprises a fish tank main body which is internally provided with a voice interaction module, an audio playing module, an image recognition module and a wireless transmission module; wherein the voice interaction module is used for carrying out dialogue interaction with children, the audio playing module is used for playing audio, the image recognition module is used for recognizing expressions and objects, and the wireless transmission module is used for carrying out data transmission with external terminal equipment. Intelligent upgrading and child-friendly design of the fish tank equipment are achieved, and the technical defect that traditional equipment lacks interaction ability is overcome. The system can recognize the emotional state of a user and make intelligent feedback, establishes a natural AI intelligent man-machine conversation mechanism, effectively improves the interaction experience of the child user, enables the child to carry out natural science popularization and accompanying conversation in the fish culture and observation process, is a child enlightenment education tool with interaction and accompanying functions, and improves the interestingness of the child. And the requirements of families on children education and accompanying are met.

The embodiment of the invention provides an online man-machine conversation optimization method, system and device, electronic equipment, a storage medium and a program product. In the scheme provided by the embodiment, when a first dialogue generation model executes a streaming response based on user input data, a currently generated first dialogue text fragment is subjected to repeated detection, and when it is detected that repeated content exists in the first dialogue text fragment, the first dialogue generation model is controlled to interrupt execution of the streaming response; in addition, reply generation constraint information is determined according to the repeated content in the first reply text segment, and then reply generation cue words are generated based on the reply generation constraint information and the non-repeated content in the first reply text segment. And after the dialogue generation cue word is input into the first dialogue generation model, the first dialogue generation model is triggered to determine a dialogue generation starting point according to the non-repeated content in the first dialogue text fragment, and streaming response is continuously executed from the dialogue generation starting point.

The invention relates to a control method and device of clothes processing equipment and the clothes processing equipment. The control method of the clothes processing equipment comprises the steps that clothes information of clothes to be processed is acquired based on man-machine conversation; obtaining a target processing program matched with the clothes information and a target processing parameter corresponding to the target processing program; and processing the to-be-processed clothes according to the target processing program and the target processing parameters. According to the embodiment of the invention, the method can guide the user to provide the expression related to the to-be-processed clothes through the man-machine conversation, converts the oral and fragmented expression of the user into the formatted clothes information, and recommends the target processing program and the target processing parameters suitable for the to-be-processed clothes for the user according to the clothes information. Therefore, the problem that the user does not know which processing program and parameter are selected to process the to-be-processed clothes in daily life is solved, and better clothes processing service is provided for the user.

The invention relates to the technical field of artificial intelligence, in particular to a papermaking employee virtual practical training method and system combined with a large model. According to the papermaking employee virtual practical training method and system combined with the large model, immersive interaction with a high-fidelity virtual papermaking production line is achieved through data collection, virtual simulation and large model interaction and reasoning. According to the method, a large-scale language model is introduced, so that the method has strong natural language understanding, deep reasoning and multi-modal information fusion capabilities, complex and changeable virtual environment states can be analyzed in real time, and intelligent diagnosis and guidance are performed in combination with natural language questions of employees; and even non-preset or multi-factor coupled fault scenes which cannot be processed by a traditional rule system can be processed, man-machine dialogue interaction similar to experienced experts is realized, and the intelligent level of the system on solving complex problems is remarkably improved.

Embodiments of the present application provide a contrastive learning, query and human-computer dialogue method, an electronic device and a storage medium. The contrastive learning method comprises: constructing a similar sample pair and a non-similar sample pair based on at least a similar enhanced sample and a labeled sample of a training sample; constructing a loss function of an encoder of a task model based on a similarity of the similar sample pair and a similarity of the non-similar sample pair, a function value of the loss function being directly proportional to the similarity of the similar sample pair and inversely proportional to the similarity of the non-similar sample pair; and training the encoder of the task model based on the loss function. In the scheme of the embodiments of the present application, based on the inventive concept of contrastive learning, the function value of the constructed loss function is directly proportional to the similarity of the similar sample pair and inversely proportional to the similarity of the non-similar sample pair, so that through such a loss function, the confidence of the training sample is improved, and the training sample itself is not only enhanced, and therefore the performance of the trained task model is improved.

The invention relates to an intelligent voice remote control system and method based on AI semantic analysis, belongs to the field of voice recognition, and particularly belongs to the application field of programs used in the man-machine conversation process. And the voice remote control module is used for intelligently analyzing an authorized user identifier and a voice remote control instruction corresponding to the field audio data of the intelligent remote controller of the television box based on the selected basic data by adopting an AI semantic analysis model designed by a dynamic structure, and providing multiple items of reference data for determining a voice remote control strategy. According to the invention, aiming at the technical problem that the reliability, the stability and the simplification level of intelligent voice remote control in the prior art cannot be considered at the same time, the AI semantic analysis model of the corresponding dynamic structure can be designed for the field audio data of the intelligent remote controller of the television box; and synchronous intelligent analysis of the voice remote control instruction corresponding to the field audio data and whether the corresponding source user belongs to the authorized user is completed, so that the technical problem is solved.

The invention relates to the field of artificial intelligence and man-machine conversation, and particularly discloses an emotion-enhanced historical session representation and drive response generation method, which comprises the following steps: S1, outputting a normalized historical session text sequence; s2, encoding a historical session text, and generating a text vector representation; s3, emotion recognition and coding are carried out, and emotion vector representation is converted; s4, identifying and coding a vertical field, and converting vertical field vector representation; s5, fusing the text vector, the emotion vector and the standing vector by adopting a splicing fusion mode, and outputting historical session vector representation of emotion enhancement; and S6, generating the response of the intelligent customer service, and adjusting a generation strategy according to the emotion intensity and the standing trend. According to the emotion-enhanced historical session representation and drive response generation method provided by the invention, the LLM structure does not need to be modified, the compatibility and expansibility are high, the deployment is convenient, and the pertinence of customer service response and the user satisfaction can be remarkably improved.

This invention discloses a human-computer interaction method for service robots, involving human-computer dialogue systems and mobile robot navigation control. The biggest drawback of current human-computer dialogue systems, which primarily use sequence-to-sequence models, is that these models tend to generate high-frequency, generic responses and lack sufficient useful information, making it difficult to provide practical assistance to users. This patent introduces external knowledge to enrich the information content of the model's generated responses, improve the diversity of responses, and alleviate the problem of high-frequency generic responses. Based on this model, a human-computer interaction method for service robots is designed. This method not only has dialogue capabilities but can also parse user navigation control commands, enabling fixed-point navigation control in home or office scenarios and improving the robot's human-computer interaction capabilities.

The invention relates to a multi-field dialogue model training and task processing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring general dialogue data and at least one type of domain tag data; performing parameter fine tuning on the pre-trained large language model through the at least one type of domain tag data to obtain an initial professional model; according to a target sampling proportion, sampling each type of domain tag data to obtain target sampling data, and performing parameter fine tuning on the initial professional model through the target sampling data and the general dialogue data to obtain a target dialogue model; the target dialogue model is used for being deployed in task processing equipment, so that the task processing equipment processes the dialogue tasks of the target fields based on the target dialogue model. In this way, the target dialogue model has the universal capacity of processing all the target fields and man-machine dialogue related tasks, and occupation of storage resources in task processing equipment is reduced.

The present invention relates to the technical field of digital humans. Disclosed is a large-model-driven method for real-time interaction with a digital human, comprising the following steps: S1, inputting a question text by means of a human-machine dialog frontend and sending the question text to a large model backend; S2, the large model backend performing large model inference on the basis of the question text and a knowledge base to generate an answer summary and a full answer and respectively sending the answer summary and the full answer to a digital human backend and the human-machine dialog frontend for display; S3, a classifier generating a plurality of classification labels on the basis of the answer summary, and the digital human backend performing retrieval and matching on a preset video library on the basis of the classification labels to obtain a target preset video and sending the target preset video to the human-machine dialog frontend; and S4, a digital human processing engine generating a digital human summary video on the basis of the answer summary and pushing the digital human summary video to a player, and the player sequentially playing the target preset video and the digital human summary video. Smoother experience of real-time question-and-answer interaction with a digital human is finally achieved, thereby reducing loss of realism in the experience.

1. Name of the design product: children's companion robot (Doudou). 2. Use of the design product: for human-computer dialogue communication and interaction feedback. 3. Design points of the design product: in shape. 4. Picture or photo that best indicates the design points: perspective view.

This disclosure relates to context-aware human-to-computer dialog. Methods, devices, and computer-readable media are described that involve utilizing the context of an ongoing human-to-computer dialog to enhance the ability of an automated assistant to interpret and respond when a user abruptly transitions between different domains (topics). In various implementations, natural language input from a user can be received during an ongoing human-to-computer dialog with an automated assistant. A grammar can be selected to parse the natural language input. The selection can be based on a topic that is stored as part of a context data structure associated with the ongoing human-to-computer dialog. The natural language input can be parsed based on the selected grammar to generate a parse. Based on the parse, a natural language response can be generated and output to the user by using an output device. Any topic raised by the parse or the natural language response can be identified and added to the context data structure.

1. Name of the product in this design: Intelligent Conversational Robot. 2. Purpose of this design: This design is mainly used for human-computer interaction. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

The application provides a man-machine conversation method, device and equipment and a readable storage medium, and relates to the technical field of artificial intelligence. The man-machine conversation method comprises the following steps: determining the category of an incoming call; determining the conversation mode corresponding to the category of the incoming call; acquiring language information of a conversation object in the conversation mode and identifying first key information of the language information; determining a reply strategy based on the first key information and a preset deep reinforcement learning model; generating reply language information corresponding to the first key information based on the reply strategy, and returning the reply language information to the conversation object. Thus, the problem of high complexity of the existing man-machine conversation can be solved.

The invention provides a dialogue processing method and device, electronic equipment and a computer readable storage medium. The dialogue processing method and device are applied to a man-machine dialogue scene. The method comprises the steps of obtaining input information of a current dialogue and dialogue information of a historical dialogue; classifying the input information to obtain a classification label of the input information; performing context processing on the input information, the classification tag and the dialogue information to obtain a first prompt word of the current dialogue; and based on the first prompt word, performing dialogue prediction processing on the input information to obtain first reply information of the current dialogue.

The invention provides an intelligent customer service problem decomposition method based on a large language model, a medium and electronic equipment. According to the method, error correction and compliance cleaning can be carried out on the input information of the user, and the user intention is accurately recognized in combination with the historical dialogue context. When it is detected that a plurality of intentions are included in user input, the intentions are decomposed into independent sub-intentions (including question description, categories and key parameters) by using a preset dynamic rule base, and corresponding skill knowledge base tool instructions are matched for different sub-intentions; and when key information is lacked, automatic asking and complementing are carried out. And then, inputting the skill indication information corresponding to each sub-intention and the user associated data into the large language model to generate a reply for each sub-intention. And for a plurality of reply results, a content generation rule is applied to combine and embellish the reply results, and the results are uniformly fed back to the user. Through the above mode, according to the scheme of the invention, multiple rounds of contexts and vertical industry knowledge bases in the same session can be fused, and accurate disassembly and response to complex multi-intention user requests can be realized; the technical problems that in the prior art, intelligent customer service is lack of knowledge in specific fields such as hotels, catering, fitness, theaters and scenic spots, and user intentions and continuous dialogues cannot be refined are solved, reply accuracy and service experience are remarkably improved, and man-machine dialogues are more efficient and natural.

The application discloses a human-computer conversation output delay control system, which acquires first and second type interaction data of different biological behavior dimensions in parallel through a data acquisition unit, provides reliable support for rhythm difference quantization, generates a quantization index through a difference determination unit, objectively quantizes rhythm dislocation degree, and solves the defect that the prior art cannot accurately identify rhythm dislocation, and when the trigger condition is met, the delay adjustment unit performs a control operation, delays the rhythm of a large language model output, avoids the asynchronization of user cognition and emotional integration, effectively reduces psychological risk, and improves the safety, adaptability and reliability of human-computer conversation.

The embodiment of the invention provides a man-machine conversation method and device, electronic equipment and a readable storage medium. The method comprises the following steps: receiving first question information sent by a client; inputting the first question information into a language model to generate corresponding user intention information; based on the user intention information, document identification information is retrieved from a pre-constructed knowledge index database, the knowledge index database is constructed based on a unified document knowledge base, and a part, corresponding to the task knowledge, in the unified document knowledge base is provided with preset identification information which is used for associating a corresponding task process; inputting related document segments corresponding to the document identification information and the user intention information into a language model, and outputting reply content; and sending the reply content to the client.

The invention discloses a rehabilitation semantic understanding and intelligent inquiry method based on large language model fine tuning, which comprises the following steps of: analyzing an input natural language into a standardized rehabilitation semantic structure, identifying semantic information and generating a semantic tag; and after semantic analysis is completed, dynamic and interpretable inquiry interaction is realized through a context memory unit, semantic state modeling and a strategy controller. According to the invention, an intelligent inquiry strategy controller and a semantic confidence mechanism are adopted, so that the model has self-review and dynamic inquiry capabilities. And when the system detects that the semantic meaning is fuzzy or the confidence coefficient is low, a follow-up question can be automatically generated, so that the model is not a passive responder any more and becomes an active information collector, and the naturalness and clinical practicability of man-machine conversation are improved. Meanwhile, an attention heat map and a semantic interpretation interface of the model provide a visual basis for doctors, the black box problem of the deep model is solved, and the supervision requirements of traceability, safety and controllability of medical artificial intelligence are met.

The application discloses a man-machine conversation device and a method for realizing man-machine conversation, and comprises the following steps: obtaining a user's inquiry in a conversation process for providing service for the user; putting forward a question to the user in a multi-round question and answer mode based on the user's inquiry and a question in a question database, and determining a user's intention according to the user's reply. Through the technical scheme provided by the application, when the user's intention is uncertain, the user's intention is clarified by actively putting forward a question to the user, the man-machine conversation process is intelligently realized, and the accuracy of the user's intention recognition is improved.

A long short-term memory-based multi-round dialog inference acceleration method, which is applied to human-machine dialog scenarios implemented on the basis of models. In the inference acceleration method, for a question text obtained in a question-and-answer scenario, features of some historical dialog content under a same dialog role and features of summaries of other dialog content prior to said historical dialog content are acquired, and then a target model is assisted in processing the question text on the basis of the features, thus ensuring the accuracy of the target model in processing the question text. In addition, as the present solution is based on AI native storage, that is, memory of a large model itself (i.e., features pre-extracted by the model) is stored, there is no need for secondary inference by the large model; thus, by means of replacing computation with lookup, features can be retrieved and used on demand, thereby improving the inference efficiency of large models.

The invention relates to the technical field of man-machine conversation, in particular to a man-machine conversation method and device, an electronic device and a storage medium. The method comprises the following steps: responding to a dialogue triggering operation initiated by a client, and collecting full-amount original data; performing standardized preprocessing on the full-amount original data to generate a model fine-tuning annotation data set and a knowledge base original data set; supervised fine tuning is carried out based on the model fine tuning annotation data set, and a second-hand car special large model is generated; classifying and sorting based on the knowledge base original data set, and constructing a second-hand car special knowledge base; receiving a current dialogue request of a client in real time, inputting the current dialogue request into the second-hand car special large model to complete intention recognition, and triggering to generate a professional reply if professional knowledge query is involved; and if the professional knowledge query is not involved, generating a natural language reply, and pushing the professional reply or the natural language reply to the client terminal for iteratively optimizing the special large model and the special knowledge base. According to the invention, the live broadcast private message man-machine interaction response efficiency can be greatly improved.

The invention discloses a man-machine dialogue method and device, a vehicle, a medium and a product, and the method comprises the steps: responding to a received first dialogue instruction, and outputting first reply content for the first dialogue instruction based on a man-machine dialogue function; in the state that the man-machine conversation function is interrupted, responding to the received second conversation instruction, and outputting second reply content aiming at the second conversation instruction; the second reply content at least comprises the first reply content. In the man-machine conversation function interruption state, the determination and output of the first reply content under the historical conversation instruction are triggered through the second conversation instruction. The problem that the dialogue in the vehicle machine is interrupted and cannot be traced back is solved, and the use feeling of the user in the vehicle machine is improved.

1. The name of the design product: capacitive touch pen. 2. The use of the design product: pen for completing man-machine dialogue operation on capacitive touch screen. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view.

The application discloses a complex problem knowledge externalization modeling system and method based on human-computer conversation, and belongs to the technical field of computers. Through compliance preliminary screening and structured coding of multi-source cross-modal knowledge, a dynamic conflict graph with double time markers is constructed, and the conflict detection sensitivity is dynamically adjusted based on the user cognitive state, solving the problems of traditional human-computer conversation system knowledge fusion black box and cross-modal conflict detection deficiency. The decision logic is encapsulated as a visual decision path graph through a dynamic arbitration engine, and the presentation complexity is adjusted according to the user cognitive state, realizing the transparency and interpretability of the arbitration process. At the same time, the user intervention result is obtained in real time and strategy recalculation is triggered, combining with the ethical pre-check and example library mechanism, a closed-loop system of deep coupling of conflict detection, dynamic arbitration, user intervention and ethical compliance is constructed, promoting the co-evolution of each module and improving the credibility and intervenability of the system.