343 results about "Question Text" patented technology

The present invention provides an output detection method for a large language model, comprising: acquiring an output text of a large language model for a questioning text, and acquiring a target knowledge graph of a field to which the questioning text belongs, the target knowledge graph comprising knowledge data in the field to which the questioning text belongs; performing knowledge extraction on the output text to obtain knowledge data to be detected of the output text; and by means of the target knowledge graph, detecting the knowledge data to be detected, so as to obtain a knowledge detection result of the output text. Knowledge extraction is performed on the output text of the large language model so as to obtain the knowledge data to be detected of the output text, and the target knowledge graph in the field is used to detect the knowledge data to be detected, such that whether there is a knowledge error in the output text can be determined, thus preventing the large language model from outputting incorrect knowledge to users.

The present invention relates to the related technical field of natural language inference. Disclosed is a large language model joint inference method based on a knowledge graph-enhanced chain-of-thought prompt, comprising: constructing a local knowledge subgraph; decomposing an original question text into S sub-question texts and concatenating the original question text and the S sub-question texts; inputting a concatenated question text into a graph inference model to obtain a weighted entity distribution; from the weighted entity distribution, extracting first G answer entities having the highest confidence level, using an inference transition matrix to trace an inference process of each answer entity, and generating an inference path from a question entity to the corresponding answer entity; and using the inference path to assist a large language model in predicting an answer to the original question text. By means of the method, the large language model can quickly and accurately find an answer to a question text.

The invention belongs to the technical field of artificial intelligence, and relates to an image-text question answering method, system and device based on multi-modal RAG and a storage medium, and the method comprises the following steps: 1) extracting multi-modal information from a PDF document, representing the multi-modal information as dense vectors, and storing the dense vectors in a text vector database and an image vector database; 2) obtaining a semantic embedding vector of the problem text and a multi-modal embedding vector of the problem text; obtaining a semantic embedding vector of the description text of the problem image and a multi-mode embedding vector of the problem image; 3) performing coarse screening in the text vector database and the image vector database by using the semantic embedding vector and the multi-modal embedding vector, finding out coarse screening text data and coarse screening image data, performing multi-modal fine ranking on the coarse screening text data and the coarse screening image data, and obtaining text data and image data which are retrieved and recalled; and 4) generating a final answer by the multi-modal large language model. According to the method, multi-modal data in a long document can be effectively analyzed, and information most relevant to a problem can be accurately retrieved.

The invention discloses an AI (artificial intelligence) agent construction system based on hybrid retrieval and father-child segmentation, which comprises the following steps of: dividing a subclass knowledge base according to domain knowledge, performing father-child segmentation processing, and constructing a hierarchical semantic network; vectorization embedding and deep semantic reconstruction are carried out on the user question text; retrieving the reconstructed problem by adopting a mixed retrieval algorithm combining sparse retrieval and dense retrieval, and forming a high-score sub-segment set according to a comprehensive score obtained by dynamic weight distribution; mapping the sub-segments to the parent segment through a hierarchical backtracking algorithm, aggregating brother nodes to form an extended candidate set, and generating an associated sub-segment set after duplicate removal and re-retrieval; and finally inputting a large language model to generate a complete answer. According to the method, the problems of context segmentation, low retrieval accuracy and complicated knowledge base maintenance of traditional document segments are solved, the answer coverage and accuracy of an intelligent question-answering system are remarkably improved, and the method is suitable for knowledge question-answering scenes in the complicated technical fields such as intelligent network connection automobiles and the like.

The invention discloses a large model retrieval enhancement generation method and system, and the method comprises the steps: obtaining the comprehensive document data of a power grid field, carrying out the partitioning processing of the comprehensive document data, and obtaining the partitioned text data; performing deep analysis on the block text data to generate a thinking chain enhanced text; encoding the thinking chain enhanced text based on a hierarchical weighted encoding method to generate a thinking chain enhanced semantic vector; inputting the block text data into a pre-trained large language model to obtain a generated task perception representation vector; splicing the thinking chain enhanced semantic vector and the generated task perception representation vector to obtain a fusion vector, and constructing a vector database in the power grid field based on the fusion vector; responding to the text retrieval signal, obtaining question text data of the target user, analyzing the question text data to obtain a question fusion vector, comparing the question fusion vector with a vector database, and obtaining retrieval data of the question text data based on a comparison result.

The invention relates to a construction method of a letter intelligent question-answering system based on self-adaptive knowledge graph enhanced LLM, and the method comprises the steps: obtaining the text data of a target region, carrying out the preprocessing of the text data, converting the text data into a vector format through a fine-tuning sentence converter, and constructing a vector database; vectorizing the user question text and the identity information, calculating the similarity of the user question text and the identity information with a vector database to generate context information, jointly inputting the context information and the user question into a generative large language model, and outputting a plurality of candidate answers; and based on a pre-constructed target domain knowledge graph, carrying out joint reasoning verification on the plurality of candidate answers, sorting the candidate answers through a scoring mechanism, and selecting a final answer. Complex questions can be answered, and the accuracy and reliability of questions and answers are improved; the answer can be accurately generated through reasoning without based on a preset answer template, and the accuracy and logicality of the answer are ensured.

The invention relates to the technical field of artificial intelligence, in particular to a process reward model training method and system. The method comprises the following steps: calculating a confidence score of a question text in each sample; based on the correctness score, the confidence score and the tolerance distance hyper-parameter of each reasoning step of the problem text in the labeled sample, obtaining a target correctness score of each reasoning step of the problem text in the labeled sample; and training the process reward model based on binary cross entropy loss between the correctness prediction score of each reasoning step of the problem text in the labeled sample and the target correctness score, and taking the trained process reward model as a target process reward model. According to the method, the accuracy and reliability of process reward model training are improved, and the text generation precision of a large language model is enhanced.

The invention provides an RAG method based on semantic precise blocking and precise background information generation, and belongs to the technical field of artificial intelligence. The method comprises the following steps: in a preparation stage before reasoning, preprocessing a large number of related knowledge texts, and segmenting the texts into coarse-grained text blocks according to the number of words; dividing the coarse-grained text block into a plurality of fine-grained text blocks according to semantics through a large language model, and generating a context abstract and an association problem for each fine-grained text block; splicing the fine-grained text block and the context abstract into a final text block, and taking the final text block as a block containing accurate background information; and storing the final text blocks and association problems in different vector databases after vectorization. In the reasoning stage, when facing a user question, the system firstly vectorizes a user question text, then retrieves the most relevant items from the different vector databases for merging, and then optimizes and sorts the retrieved results through a reordering model. And selecting the top-ranked text blocks for the large language model to generate answers. According to the method, the problems of inaccurate blocking, context information missing and inaccurate retrieval in the traditional RAG method are effectively improved.

The invention provides a construction method of an intelligent personalized interaction system. The construction method comprises the following steps: constructing a database; preparing a training set and a test set with problem texts, constructing a vocabulary of high-frequency words for the training set and the test set, and performing text coding; constructing a workflow scheduler for counting high-frequency problem types; the user portrait building module is used for obtaining a user portrait according to historical dialogues, user questions and high-frequency question types of the database; the intelligent personalized interaction system comprises a user question input interface, a question classification module and a database which are connected in sequence, and the database is connected with a workflow scheduler and a user portrait construction module. And outputting the user portrait and the high-frequency question type to a pre-trained large language model to generate a recommendation question. The invention further provides a corresponding system. According to the method, deep understanding, accurate analysis and personalized interaction of user questions are realized, so that the user experience is remarkably improved, and diversified requirements of users in different scenes are met.

The invention provides a question answering method and device based on a large language model, equipment and a storage medium, and relates to the technical field of artificial intelligence. The method comprises the following steps: acquiring a question text; performing semantic understanding on the question text through a large language model to obtain a structured data query instruction; retrieving in a database based on the data query instruction to obtain target data related to the question text, the data included in the database being obtained by integrating first business data obtained from at least one business system; and obtaining a target answer of the question text through the large language model according to the question text and the target data related to the question text.

The invention relates to the technical field of large models, and provides a thinking chain-based large model question and answer method and device. The method comprises the following steps: obtaining a subjective question text; inputting the subjective question text into a question and answer model to obtain a target answer output by the question and answer model; the target answer is an answer conforming to a social moral specification; the question and answer model is obtained by using a historical subjective question text and a historical target answer tag corresponding to the historical subjective question text to train the large model on the basis of expanding the reasoning process of the large model into a structured reasoning chain and applying budget constraint to the structured reasoning chain. According to the question and answer model, when subjective questions are processed, answers conforming to social moral specifications can be stably output, and the reasoning efficiency and accuracy are effectively improved in the reasoning process.

The embodiment of the invention relates to a reply text generation method and device, computer equipment and a storage medium, and the method comprises the steps: extracting a question entity and a question intention from a question text when the question text is obtained; determining a retrieval strategy and a target database corresponding to the question text according to the question intention; generating a prompt word corresponding to the question text through a reinforcement learning model, wherein the prompt word is generated based on feedback data of a user; retrieving a retrieval result corresponding to the question text from the target database according to the retrieval strategy and the cue word; and generating a reply text corresponding to the question text according to the retrieval result. Therefore, a fixed prompt word template does not need to be used, the prompt word corresponding to the current question text is generated through the reinforcement learning model, the generated prompt word is more targeted, then the reply text is generated based on the prompt word, and the accuracy of generating the reply text is improved.

The embodiment of the invention relates to the technical field of artificial intelligence, and provides a personalized content recommendation method and system based on a large model and electronic device.The method comprises the steps that in response to a received content query instruction, at least one large language model is used for generating a question text corresponding to the content query instruction; determining a corresponding text block according to the similarity between each question text and the text block in the content library; based on a first prompt word generated according to each question text and the corresponding text block, using at least one large language model to generate a recommendation result corresponding to the question text; and outputting a recommendation result. On the basis of the scheme, the to-be-recommended content can be subjected to text division, the multiple problem texts are generated according to information such as user requirements, progressive retrieval is performed on the text library through the multiple problem texts, then the recommendation result meeting the personalized requirements of the user is generated on the basis of the retrieval result, the adaptability of the recommended content to the user is improved, and the user experience is improved. And the personalized requirements of the user are met.

The invention provides a Token compression method and device for large model dialogues, which can effectively reduce the number of Tokens (lexical elements) of texts input into a large model in multiple rounds of dialogues, and can also retain key information of early parts of historical dialogue texts at the same time. The method is applied to a Token compression management agent, and comprises the following steps: after obtaining a question text input by a user to a terminal, determining the number of lexical elements in an initial text (including a historical dialogue text and the question text) to be sent to a large model; if the initial text lexical element number does not meet the threshold requirement, switching the state into a lexical element compression state, interacting with the large model to obtain the lexical element number of compressed intermediate dialogue texts (parts except for the previous k rounds of dialogue texts, k is greater than or equal to 0), and keeping a semantically generated abstract text. And splicing the first k rounds of dialogue texts, abstract texts and question texts to obtain a target text. If the number of the target text lexical elements meets the threshold requirement, sending to the first large model.

The invention discloses a file analysis and knowledge recall method and device for a large model question-answering system, equipment and a storage medium. The method comprises the following steps: analyzing a document, and extracting fine-grained information; receiving a natural language query request, and generating a question text containing similar questions; performing keyword extraction and weight distribution on the question text to generate keyword weight mapping; calculating similarity scores of different documents and question texts by using keyword weights based on a BM25 algorithm, and preliminarily screening documents associated with similar questions; in the primarily screened document, accurately querying a specific fragment; and smoothing the specific segments, and returning the final result after sorting the final result according to the comprehensive scores of the segments. According to the method and the device, the operation cost of the question-answering system is reduced, the analysis capability of fine-grained information is improved, the user can accurately position required specific information during query, and the retrieval efficiency and accuracy are improved.

The invention provides a text generation method and device based on a pre-trained language model, equipment and a medium, and can be applied to the technical field of text generation. The method comprises the following steps: inputting a target question text into a pre-trained language model to generate a target path; generating a confusion value based on the conditional probability of each step in the logic step sequence; in response to determining that the confusion value is greater than the preset threshold value, correcting at least one step in the logic step sequence by utilizing a pre-trained language model to obtain a corrected logic step sequence; and processing the target question text and generating the target reply text according to the corrected logic step sequence by using the pre-trained language model, so that the correctness of each step in the logic step sequence is ensured, the reasoning efficiency is improved, the consumption of computing resources is reduced, and meanwhile, the robustness and interpretability of the target reply text are improved.

The invention discloses an intelligent tool calling method based on knowledge base matching, and the method comprises the following steps: S1, carrying out the blocking processing of prompt words of an MCP tool set, marking a feature tag for each tool, and forming a tool prompt word knowledge base; s2, obtaining a question text input by a user, carrying out semantic matching on the question text of the user and the feature tag of the tool cue word knowledge base, calculating the similarity and obtaining a corresponding matching result; s3, according to the matching result, entering the tool cue word knowledge base to recognize and automatically output a matched tool name; s4, if the user confirms that the tool name is accurate, tool execution is started; if the user neglects the tool name, displaying a tool list arranged according to a similarity descending order to the user for manual selection; s5, calling a tool confirmed or selected by the user and obtaining an execution result; and S6, summarizing the execution result through a large language model, and returning the summarized execution result to the user. The problem that a user cannot accurately call the optimal MCP tool is solved.

The invention provides a knowledge question-answering method and device based on a large model and a medium, and relates to the technical field of knowledge questions.The method comprises the steps that a data query period corresponding to a question text is obtained through a first large language model; if the duration of the data query time period is smaller than the preset duration, determining a target operation and maintenance tool from a plurality of preset operation and maintenance tools through a second large language model; controlling the target operation and maintenance tool to perform data acquisition, and taking the acquired data as intermediate data corresponding to the target operation and maintenance tool; performing data compression on the intermediate data based on the character number of the intermediate data to obtain target data; merging the target data into the context information, and obtaining an answer text according to the context information and a specified large language model after merging is completed; according to the method, input overflow, model reasoning failure or response delay caused by too large data volume or exceeding of the context length limit of the large language model can be avoided, the stability of answer generation is ensured, and the user experience is improved.

The invention provides a knowledge slice recall method and device, equipment, a medium and a program product, and relates to the technical field of data processing. The method comprises the steps that under the condition that a question text of a user is received, target keywords of the question text, a target score corresponding to each target keyword and knowledge slices associated with the target keywords are extracted through an AC automaton; wherein a plurality of keywords and the score of each keyword are pre-stored in the AC automaton, and the keywords comprise the target keyword; based on the target score corresponding to each target keyword, calculating a correlation score between each knowledge slice and the question text; determining a target knowledge slice according to the correlation score between each knowledge slice and the question text; and recalling the target knowledge slice. By adopting the method provided by the embodiment of the invention, the accuracy of the recalled knowledge slices can be improved.

The invention provides a reinforcement learning training method and device for a large language model, equipment and a storage medium, and belongs to the technical field of computers. The method comprises the steps of obtaining first sample data, wherein the first sample data comprises a first question text and a first reply text output by a large language model for the first question text; through the generative model, on the basis of the first sample data, generating supervision information of the first reply text, the supervision information comprising a first corrected text obtained by correcting the first reply text and a reproduction probability of each lexical element in the first reply text, the reproduction probability being used for representing an occurrence probability of the corresponding lexical element in the first corrected text, the accuracy of the first corrected text is higher than that of the first reply text; and based on the first reply text and the supervision information of the first reply text, performing reinforcement learning training on the large language model. According to the technical scheme, reinforcement learning training can be carried out on the large language model, so that the accuracy of executing the language generation task by the large language model is improved.

The invention discloses an intelligent question answering method and system based on multi-model collaboration. The method comprises the following steps: S1, preprocessing a question text input by a user; s2, performing collaborative reasoning on the preprocessed text through large-scale language models, and generating candidate answers by utilizing complementarity among the large-scale language models; s3, a question type is judged based on a semantic classification and rule feature combined judgment method; s4, when the question type is closed, counting the number of votes supported by the large language model of the candidate answers through a confidence-based dynamic voting method, and taking the candidate answer with the highest number of votes as a final answer; when the question type is open, screening the candidate answers through a consistency quantitative evaluation method and outputting a final answer; and S5, dynamically adjusting the weight of the large language model based on the correctness data of the output final answer, and optimizing the collaborative reasoning ability of the large language model, thereby effectively improving the efficiency and precision of outputting question and answer results by multiple models.

The invention relates to the technical field of data processing, in particular to a large model generation control method and device, electronic equipment and a storage medium, and the method comprises the steps: firstly obtaining a to-be-processed question text; generating a thinking chain statement based on the question text by adopting a preset reasoning model; for each text block in the thinking chain statement, executing the following operations: when a function feature meeting a feature similarity condition with the text feature of one text block exists in a preset function feature set, generating a target text based on one text block by adopting an intelligent agent corresponding to the function feature; replacing one text block in the thinking chain statement with the target text; generating a reply text of the question text based on the processed thinking chain statement by adopting a preset large model; therefore, by adjusting the thinking chain statement, the black box limitation in the traditional large model reasoning process can be broken through, so that the generation control of the large model can be fundamentally realized.

The embodiment of the invention provides a retrieval method and device based on a knowledge graph, and the method comprises the steps: carrying out the semantic recognition and question extraction of a question text in a retrieval process based on the knowledge graph, and obtaining question features, according to the problem characteristics, map hierarchy retrieval is carried out in a resource knowledge map obtained through knowledge map construction and map hierarchy division based on resource data to obtain a retrieval result, and a retrieval sub-map is constructed based on a corresponding map relation of data elements contained in the retrieval result in the resource knowledge map; and performing filling processing on the retrieval sub-graph to obtain a target sub-graph, and performing text conversion on the target sub-graph to obtain a retrieval answer, thereby realizing retrieval processing on the question text through the resource knowledge graph and the retrieval sub-graph.

The invention relates to the technical field of data retrieval and analysis, and discloses an intelligent knowledge retrieval method based on an RAG framework, which comprises the following steps: acquiring a question text input by a user, judging the specialty and concrete of a question, judging the professional degree of the user in the field to which the question searched by the user belongs, and according to the conditions of the user and the question, determining whether the question belongs to the field or not; according to the intelligent knowledge retrieval method based on the RAG framework, the situation that the user outputs the answer with the high professional degree to the user under the condition that the professional degree is not high is avoided, the user cannot understand the answer easily, the situation that the user outputs the answer with the low professional degree to the user under the condition that the professional degree is high is also avoided, and the user experience is improved. Therefore, the user cannot use the searched data, the method is more friendly to the user, and the use experience of the user is improved.

The invention discloses a difficulty perception instruction and retrieval enhancement-based text generation SQL method and system, and the method comprises the steps: S1, inputting a natural language question, carrying out the difficulty classification of the question through a text classification model based on a Transform architecture, and obtaining an SQL class corresponding to the input question text; s2, according to the input natural language question, a sample related to the input target question is retrieved from a knowledge base through a double-tower sorting model and used for organizing few-sample learning cue words; s3, dynamically constructing cue words according to the input natural language question, the predicted SQL category and the retrieved sample related to the target question; s4, inputting the cue word into the large language model to generate an executable SQL query statement; according to the method, a special sorting model and a dynamic cue word construction strategy are combined, so that the dynamic few-sample learning cue word which is more related to the question and is more helpful for guiding LLM to correctly solve the question is efficiently constructed.

To efficiently conduct interviews.SOLUTION: An information processing device comprises a text generation unit and an output unit. The text generation unit generates response texts to user utterances and question texts for asking the user preset interview items using a text generation model for generating responses to the input texts on the basis of expert knowledge related to an interview subject and interview knowledge related to interviewing skills. The output unit outputs the response texts and question texts generated by the text generation unit to the user.SELECTED DRAWING: Figure 2

The invention discloses a question answering method and device based on multi-modal retrieval enhancement, a storage medium and a processor. According to the scheme, a question text is obtained; determining a plurality of target blocks corresponding to the question text through a double-flow cross-modal attention searcher, and determining a plurality of target pages corresponding to the plurality of target blocks; generating answer information according to the question text, the plurality of target blocks and the plurality of target pages; the answer information comprises answer content and answer position coordinates. Compared with the prior art that a multi-modal retrieval enhancement generation method has fundamental limitation in the aspect of understanding and utilizing deep information and structured information of a document, and the limitation leads to inaccurate and non-traceable answers generated by a language model, the multi-modal retrieval enhancement generation method has obvious advantages.

The invention discloses a large model context conflict resolution method and device based on dynamic coordination decoding, and relates to the technical field of natural language processing. The method comprises the following steps: acquiring a question text, a target context and a Transform model for answering a question; based on the question text token, the target context token, the generation token and a plurality of parallel attention heads of a Transform model, determining context loyalty, and determining a conflict prediction result according to the context loyalty; and when the conflict prediction result is true, adjusting a balance weight in decoding based on a dynamic adjustment mechanism, determining dynamic comparison decoding distribution according to the adjusted balance weight, and outputting an answer text corresponding to the question text according to the dynamic comparison decoding distribution. By adopting the answer generation method and device, the correctness and robustness of answer generation can be improved.

The invention relates to the technical field of artificial intelligence, and particularly provides an answer generation method, system and device based on an RAG technology and a storage medium, and the method comprises the steps: receiving a question text input by a user; based on the question text, performing semantic retrieval in a pre-constructed knowledge base, calculating semantic similarity between the question text and knowledge fragments in the knowledge base, and retrieving target knowledge fragments of which the semantic similarity meets a preset threshold value; performing splicing processing on the question text and the target knowledge fragment to form an input prompt word; and inputting the input prompt word into a pre-trained generative large language model, generating a corresponding answer text by the generative large language model, and outputting the answer text. According to the method, three breakthroughs of semantic understanding, association mining and result optimization are realized, and multi-modal retrieval is supported.

The invention provides a text data enhancement method and device of an FAQ system, and the method comprises the steps: employing a part of original question texts in a question and answer corpus of the current FAQ system and synonymous sentences corresponding to the part of original question texts to construct a training set, and employing the training set to train an initial Simbert model; performing synonymous sentence generation on all the original question texts by adopting the trained Simbert model to obtain a plurality of synonymous sentences corresponding to each original question text; processing all the original question texts and the synonymous sentences corresponding to all the original question texts by adopting a word-level text enhancement method to obtain first target synonymous sentences corresponding to the original question texts; screening the first target synonymous sentences to obtain second target synonymous sentences corresponding to the original question texts; and adding all the second target synonymous sentences to a question and answer corpus. The method solves the problem that original problem texts are difficult to obtain in the prior art.