247 results about "Question Text" patented technology

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 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 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 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 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 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 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 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 relates to the technical field of data processing, in particular to a traffic question and answer method, device and equipment based on a large model. In the embodiment of the invention, the question text is converted into the structured target instruction, so that the target instruction contains complete semantic information of the question text, and then the SQL statement is generated based on the structured target query instruction, so that question and answer are performed based on the SQL statement, and the problem that the question and answer efficiency is poor due to insufficient understanding of the question text in traditional question and answer is solved. The problems that generated SQL statements are not related to question texts, questions and answers are inaccurate, and the effect is poor are solved.

The invention discloses a question answering method and device based on structured data. The question answering method and device are used for generating high-quality answers to questions based on the structured data. According to the scheme, the method comprises the steps of obtaining a target question text and structured data associated with the target question text; analyzing the target problem text into a target task group based on the structured data through a first upper layer large language model, the target task group comprising a plurality of subtasks arranged in order, and the plurality of subtasks being used for extracting target structured data corresponding to the target problem text from the structured data; executing each subtask in the target task group on the structured data in sequence through a plurality of lower-layer large language models to obtain the target structured data; and generating an answer corresponding to the target question text based on the target structured data through a second upper layer large language model.

The invention provides a retrieval method and device based on an electric power regulation document. The method comprises the steps that an input question text is acquired from a large language model; performing word segmentation processing on the question text; obtaining a standard term related to each question segmented word in the knowledge graph; the question segmented words without the corresponding standard terms and the standard terms corresponding to the question segmented words with the corresponding standard terms are combined according to the sequence of the question segmented words in the question text; performing similarity matching on the vector of each question text and the vector of each slice of the power regulation document, and aggregating the similarity of each question text; and based on the comprehensive similarity, selecting a preset number of slices as target slices of the problem text, and taking the target slices and the problem text as input of the large language model again. And finally, the precisely recalled slices are combined with the large language model, so that the professionality and the safety of generating the target slices are ensured, and a reliable technical guarantee is provided for intelligent questions and answers in the power industry.

The application relates to the technical field of data processing, in particular to a traffic question and answer method, device and equipment based on a large model. In the embodiment of the application, the question text is converted into a structured target instruction, so that the target instruction contains complete semantic information of the question text, and an SQL statement is generated based on the structured target query instruction, so that the question and answer are performed based on the SQL statement, and the problem that the generated SQL statement is irrelevant to the question text, the question and answer are inaccurate and the effect is poor due to insufficient understanding of the question text in traditional question and answer is solved.

The invention provides a knowledge tracking method for student and question joint modeling based on a large language model, and the method comprises the steps: collecting student answering behavior data, question text and knowledge point related information, and carrying out the preprocessing, and forming an input data set; constructing a prompt template and a question understanding prompt template based on student answering behaviors, and respectively guiding the large language model to identify student features and question features; and carrying out feature fusion through an adaptive gating feature fusion mechanism, taking the fused features as input, taking a structured semantic result corresponding to the question answering correct probability of the student as output, and carrying out joint modeling and training on a knowledge tracking model to predict the prediction correct probability of the next question of the student. And giving a knowledge mastery degree change curve and a question difficulty distribution result, and triggering an explanation generation module to form an explanation text. According to the invention, joint modeling of individual features of students and semantic features of questions is realized, so that prediction performance and interpretability of a knowledge tracking model are enhanced.

The invention discloses a mathematical question and answer method and device and a computer program product, and the method comprises the steps: firstly carrying out the tool integration cooperative reasoning of a to-be-answered sample mathematical question text proposed by a sample user through a tool integration data synthesis mode of an Actor agent and a Critic agent; and a high-quality tool integrated reasoning path sample data set is constructed by utilizing a reasoning result, so that good cross-model and cross-tool applicability is realized while the data quality is ensured. On the basis, after a fine-tuned question and answer model is obtained by utilizing a sample data set in a supervised fine-tuning manner, track-level and step-level layered optimization is performed on the fine-tuned question and answer model based on a reinforcement learning strategy, so that the mathematical reasoning ability of the optimized question and answer model is enhanced, and the question and answer model is optimized. And when the optimized question and answer model is used for answering the target mathematical question text proposed by the target user, the answering efficiency and accuracy can be effectively improved, and the question and answer experience of the target user is improved.

This invention discloses an expert relearning reasoning question-answering method combined with a gating network. It uses a pre-trained language model for scoring and preprocessing to obtain the question context and reasoning graph. Finally, through an expert network, it deeply learns the semantic features of two representation forms and dynamically adjusts the contribution of the two representation forms to answer prediction using a gating network. Experimental results demonstrate that the proposed method is effective for question-answer prediction. By comprehensively considering the different contributions of the question text representation and the reasoned knowledge graph representation to answer prediction, the prediction accuracy can be improved. Experiments on public datasets also show good results, indicating that the method is not only applicable to fixed question-answer prediction but also has a certain generalization ability.

The application discloses a kind of deep learning question and answer method, device and system based on mass knowledge graph, first question text is obtained after text preprocessing, and first entity and first entity relationship are obtained by calling preset named entity recognition model and carrying out deep learning identification processing;First candidate answer set is obtained by searching first entity and first entity relationship by preset search model, and after obtaining, first entity, first entity relationship and first candidate answer set are iteratively trained until an output answer text is obtained as first answer text and is output and shown.The application simplifies and clarifies the question of user input by text preprocessing and named entity recognition model, improves the accuracy and efficiency of obtaining first entity and first entity relationship, and further improves the matching degree of the obtained answer text and the question text of user input by search model and cyclic iterative training.

The invention relates to an automatic question answering method and device, computer equipment and a computer readable storage medium. The method comprises the following steps: acquiring an input question text; determining candidate answers of the question text; determining a decision threshold value of the candidate answer according to a question type of the question text and a preset context length; and determining a target answer of the question text from the candidate answers according to the decision threshold. By adopting the method, the decision threshold can be dynamically adjusted, so that the number of recalled candidate answers is adjusted, the correlation between the candidate answers input into the large model for reasoning and the questions is higher, and the accuracy of intelligent answering of the large model is improved.

The present invention discloses a method and device for answer sentence selection by fusing hierarchical capsules with multi-view information. First, question texts containing multiple answers on the Internet are collected and preprocessed; then, a hierarchical capsule network is used to perform information aggregation and word aggregation on the representation of the encoded output through its progressive aggregation feature, thereby ensuring the accurate transmission of effective information and being able to use the same feature for parameter transmission; then, in order to solve the problem of instability in the fine-tuning step and the problem that the final output of the pre-trained model can only predict a single label, the weight of the entire BERT encoding intermediate layer output is calculated using a multi-view information fusion method to weight the learning information. The present invention can improve the problems in previous answer sentence selection methods, such as ignoring the influence of the multiple layers of intermediate output within the model on the answer sentence selection and being able to only predict a single result, thereby improving the accuracy and efficiency of answer sentence selection.

This application discloses a text processing method, apparatus, storage medium, and device. The method includes: firstly, acquiring the target question text input by a target user; then calculating the clarity of the target question text and determining whether the clarity is not lower than a preset threshold; if so, directly generating a response text; if not, performing importance analysis on the target question text, supplementing the target question text with information based on the analysis results, and using the supplemented target question text as the target question text again, repeatedly iteratively calculating the clarity of the target question text and subsequent steps until a preset stopping condition is reached, and using the supplemented target question text obtained at this point as the final target question text. This allows for a more accurate identification of the target user's true intent based on the final target question text, thereby generating the response information the target user truly wants and improving the target user's interactive experience.

The application discloses a table question and answer task ability enhancement processing method of a large language model. For table data, a TABLE-UAM network including an encoding part and a decoding part is constructed; different table data sets are sequentially input into the TABLE-UAM network for two-stage training, the first stage is difference reconstruction training, and the second stage is combined with multiple large language models for training; the trained TABLE-UAM network and the large language model are spliced, and used for processing input question text and table data to output answers. The newly-built TABLE-UAM network structure can efficiently encode and feature extract table data, effectively perceive table row and column dependency features, multi-table dependency features and global relationship features; and the two-stage training method can improve the table analysis task ability, significantly enhance the cross-model migration ability, and has strong generalization and practical value.

A method includes: obtaining a document comprising at least one page for question answering; determining a first vector corresponding to each of the at least one page; determining a second vector corresponding to a target question text to be answered; performing the following first operations: determining, based on the second vector and the first vector corresponding to each of the at least one page, a first similarity between the target question text and each of the at least one page; determining, based on the first similarities, at least one candidate page with the highest similarity to the target question text among the at least one page; and generating, based on the at least one candidate page and the target question text, a first identifier and first content, or second identifier and second content, using a large language model.

This invention relates to the field of natural language processing technology, and more particularly to a method, apparatus, terminal, and storage medium for question answering related to power finance knowledge. The method first performs word segmentation and entity linking on the question text, identifying multiple candidate word sets corresponding to multiple keywords in the power finance knowledge graph. The power finance knowledge graph includes multiple entities and multiple relationships. Then, relationship path matching is performed based on the multiple candidate word sets to obtain multiple candidate relationship paths. Finally, the final relationship path is selected from the multiple candidate relationship paths, and the final answer is determined based on the final relationship path. This invention utilizes a link reasoning model based on the intersection of candidate word sets for power finance knowledge graph question answering tasks, which can reduce the scope of relationship matching, improve the accuracy of relationship path matching, and thus enhance the accuracy of the question answering task.

The present disclosure relates to a model prompt generation method and device, electronic equipment and computer readable medium, belonging to the field of artificial intelligence. The method comprises: obtaining a corresponding input question vector according to an input question text; matching the input question vector with text segment vectors in a vector database to determine a plurality of candidate text segment vectors; the text segment vectors in the vector database include a plurality of parent segment vectors, and child segment vectors in each parent segment vector; converting the candidate text segment vectors into corresponding candidate text segments, and filtering and processing according to parent-child relationship data between each candidate text segment to obtain a target text segment; obtaining a language model prompt used in a language model according to the input question text and the target text prompt. The present disclosure can make the content of the language model prompt more reasonable and sufficient, thereby improving the correct rate of the language model in the private knowledge field.

The present invention relates to the field of artificial intelligence technology, and in particular to a process reward model training method and system. The present invention calculates the confidence score of the question text in each sample; obtains the target correctness score of each reasoning step of the question text in the labeled sample based on the correctness score, confidence score, and tolerance distance hyperparameter of each reasoning step of the question text in the labeled sample; trains the process reward model based on the binary cross entropy loss between the correctness prediction score of each reasoning step of the question text in the labeled sample and the target correctness score, and uses the trained process reward model as the target process reward model. The present invention improves the accuracy and reliability of process reward model training and enhances the accuracy of text generation by large-scale language models.