132 results about "Question Text" patented technology

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 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 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 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.

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 application is suitable for the field of financial technology, and particularly relates to a dialogue model training method and device based on artificial intelligence, equipment and medium. The application splices the initial question text, the initial answer text and the preset category prompt word into a first sample, obtains an augmented question text, an augmented answer text and an augmented answer keyword by back translation, and splices the augmented question text, the augmented answer text and the augmented answer keyword to obtain a second sample, thereby expanding the text data amount and solving the problem that the question text and the answer text in the splicing result are prone to confusion; a first question and answer category of the initial answer keyword is obtained and spliced into a label of the first sample, a second question and answer category of the augmented answer keyword is obtained and spliced into a label of the second sample, the reply performance of the dialogue model on different category questions is improved by adding the question and answer category information in the label; and the accuracy of the dialogue model is improved through training, the dialogue accuracy of the customer service robot and the service efficiency and quality of the financial business are improved in the field of financial technology.

The present disclosure relates to the technical field of natural language processing, and particularly provides a knowledge question answering method, device, medium and product. The method comprises: in response to receiving a query request sent by a user terminal, obtaining a target question text to be processed, and determining a target text vector corresponding to the target question text; based on a document block vector filtering condition, starting from a leaf node at the bottom layer of a document block vector tree in a knowledge vector database, determining a target node according to a comparison result between the target text vector and a document block vector of the node, wherein the document block corresponding to the document block vector of the parent node in the document block vector tree contains text content in the document block corresponding to the document block vector of each child node under the parent node; based on a large language model, processing the target question text and the target text vector of the target node in the document block vector tree to obtain a question answering result, and sending the question answering result to the user terminal; and the present disclosure improves the accuracy, comprehensiveness and reliability of the determined question answering result.

The invention relates to the technical field of computers, and discloses a text processing method and device for a large language model and a program. The method comprises the steps of obtaining an ultra-long knowledge text in response to a question text input to a target large language model by a user; the super-long knowledge text contains the content of the question answering text; generating a plurality of semantic boundaries corresponding to the super-long knowledge text and a score of each semantic boundary based on a natural language processing algorithm; segmenting the super-long knowledge text into a plurality of text blocks based on the available text budget of the target large language model, the plurality of semantic boundaries, the score of each semantic boundary and a preset coincidence proportion; determining a temporary reply corresponding to each text block based on the question text and the target large language model; generating a summary prompt word according to the question text and the temporary reply corresponding to each text block; and inputting the summary prompt word into the target large language model, and generating an answer text for the question text. According to the method, the compatibility of the large language model to the super-long knowledge text can be improved.

A reasoning acceleration method based on AI native storage is applied to the reasoning process of an acceleration model. In the reasoning acceleration method, aiming at an acquired problem text and an acquired reference text, a plurality of feature fragments corresponding to the reference text are firstly acquired, the plurality of feature fragments respectively correspond to different text fragments in the reference text, then partial feature fragments related to the problem text are selected from the plurality of feature fragments, and the partial feature fragments are selected from the reference text. And then partial selected feature segments are used as the features of the reference text to process the problem text, so that the feature quantity needing to be processed in the reasoning process of the target model is effectively reduced, the feature can be searched and calculated on the basis of the pre-stored features, the situation that calculation is executed on the features again is avoided, and the calculation efficiency is improved. The reasoning speed of the target model is improved, and the reasoning precision is not affected. Namely, according to the scheme, the memory of the large model is stored, secondary reasoning of the large model is not needed, and the characteristics can be used and taken by searching instead of calculation, so that the reasoning efficiency of the large model is improved.

The application discloses a model training method and device based on semantic question answering, equipment and a storage medium, relates to the technical field of data processing, and discloses a method comprising: constructing an adversarial sample corresponding to an original sample; after inputting question text information of the original sample and question text information of the adversarial sample into a semantic question answering model to be trained respectively, obtaining response data of each neural network level in the semantic question answering model to the original sample and response data of each neural network level in the semantic question answering model to the adversarial sample respectively; determining at least one fragile layer in the multiple neural network levels of the semantic question answering model based on the response data of the original sample and the response data of the adversarial sample; repairing a target fragile layer in the at least one fragile layer by using a pre-set repair strategy to obtain a repaired target question answering model. The application changes the model repair range from blind global parameter adjustment to accurate directional intervention, and improves the accuracy of the output answer of the semantic question answering model when facing the adversarial sample.

This invention relates to the field of semantic understanding technology, specifically to a method for semantic understanding and intelligent question answering in online courses for mobile terminals. The method includes the following steps: parsing the question text to identify subject-verb-object semantic relationships and generate corresponding structural expressions; collecting concept and behavioral terms from a knowledge base for semantic comparison and generation of course semantic expressions; reading positional analysis to generate question relationship expressions based on concept associations; collecting subtitles and knowledge structures for comparative association and generation of knowledge correspondence expressions; and extracting subtitle fragments and integrating playback positions to generate a processing scheme. In this invention, deep semantic comparison and positional analysis are performed by linking object terms in the course knowledge base, overcoming the limitations of shallow character matching to achieve deep question intent restoration. Simultaneously, subtitle content and chapter structure are collected for contextual analysis, and subtitle fragments are deeply integrated with video playback progress to construct a response mechanism that highly fits the actual teaching context, completely changing the isolated retrieval mode and eliminating interaction breaks.

The application discloses a question and answer method and device, equipment and medium, and relates to the technical field of computers, which comprises the following steps: cutting a target question and answer text to obtain each target word, and vectorizing the target word to obtain each target vector; generating a question text matrix based on the target vector through a question encoder in a target question and answer model; calculating the target similarity between the target question text and each reference text based on the question text matrix and each reference text matrix through a similarity calculation module in the target question and answer model, and selecting the target number of reference texts with the highest target similarity; the reference text matrix is a matrix constructed by a reference text encoder in the target question and answer model based on the reference text; each reference text is a standard question text and a reference answer text, or a reference answer text; and generating a target answer text based on the target number of reference texts through an answer generator. The application can improve the accuracy and generality of question and answer, and speed up the efficiency of question and answer.

The application discloses a kind of thinking chain enhancement method and device for RAG system, the method includes: after obtaining input question text set, relevant document set associated with question text set is obtained from corpus as enhancement information;Multiple candidate thinking chains and corresponding answer texts are generated in parallel;Each candidate thinking chain is automatically scored by multiple dimension evaluation algorithm, and comprehensive score is generated based on multidimensional score and is sorted;When determining that initial optimal thinking chain is less than preset threshold, the optimal thinking chain that does not reach threshold is progressively refined and optimized, and improved version thinking chain is obtained;Preference pair sample is constructed, and LoRA fine-tuning is carried out on model based on preference pair sample by preference optimization algorithm;The model after fine-tuning is loaded to execute input question text reasoning task.The scheme can enable model to directly generate high-quality thinking chain in subsequent reasoning, and can improve the accuracy of reasoning answer.

The invention discloses a table question and answer task capability enhancement processing method of a large language model. Aiming at the table data, constructing a TABLE-UAM network comprising a coding part and a decoding part; the different table data sets are sequentially input into the TABLE-UAM network for two-stage training in sequence, the first stage is reconstruction difference training, and the second stage is combined with multiple large language model training; and splicing the trained TABLE-UAM network and the large language model for processing the input question text and table data and outputting an answer. According to the method, a newly established TABLE-UAM network structure can efficiently perform coding and feature extraction on table data, and the table row and column dependency feature, the multi-table dependency feature and the global relationship feature are effectively perceived; moreover, the two-stage training method can improve the table analysis task capability, remarkably enhances the cross-model migration capability, and is higher in generalization and practical value.

The application provides an interpretable text question and answer method and system based on structural semantic flow modeling, relates to the fields of artificial intelligence and text question and answer technology, and comprises the following steps: obtaining an original token vector sequence from a question text to be answered; performing knowledge injection on the original token vector sequence to obtain an enhanced token vector sequence; performing semantic flow label identification on each token vector in the enhanced token vector sequence to obtain a token vector sequence with semantic flow labels; performing multi-flow aggregation and cross-flow attention on the token vector sequence with semantic flow labels to obtain a final flow-aware token vector sequence; and generating an answer and an inference path graph based on the final flow-aware token vector sequence through reasoning. The application combines text knowledge graph injection and flow-based semantic modeling, realizes the structuralized representation and reasoning of text, and improves the interpretability and diagnostic accuracy of the model.

The invention discloses a query statement generation method and device, electronic equipment and a storage medium. The accuracy of query statement generation can be improved. The method comprises the following steps: determining first enhanced information corresponding to an original question text; rewriting the original question text by utilizing the first enhancement information, and determining a target question text; determining second enhanced information corresponding to the target question text; the second enhanced information comprises information representing the difficulty level of the query statement; and generating a query statement based on the target question text and the second enhanced information by using the large language model.

The application discloses an intelligent question-answering method based on a large language model and a domain knowledge graph, which comprises the following steps: obtaining target vertical domain data, constructing a target domain knowledge graph, and determining a first large language model; when a user's question text is received, a second large language model is determined, if it is determined that the user's question text is related to the target domain knowledge graph, the user's question text is input into the first large language model and the second large language model respectively, and a first query result and a second query result are obtained; a first answer result and a second answer result are obtained from the first query result and the second query result through the second large language model; if it is determined that the first answer result is reasonable according to the second answer result, a final answer result is output according to the first answer result and the second answer result through the second large language model. The application can effectively improve the output efficiency and accuracy of the answer result of the large language model in the vertical domain knowledge question-answering.

The invention provides a question answering method based on intention recognition, electronic equipment and a storage medium, and relates to the technical field of intention recognition, the method comprises the following steps: preferentially matching a target question text with a preset question text, and then generating a first answer text by adopting a first large language model with small parameter quantity; obtaining an answer text corresponding to the target question text; if the accuracy score corresponding to the first answer text obtained based on the second large language model is not less than a preset score, storing the target question text and the first answer text into an intention database; otherwise, performing intention recognition on the target question text through a third large language model to obtain a second answer text, and if an accuracy score corresponding to the second answer text obtained based on the second large language model is not less than a preset score, obtaining a training sample and adding the training sample into a training sample set for performing instruction fine tuning on the first large language model; and the question and answer processing speed, efficiency and resource utilization rate are obviously improved.

This application discloses a question-answering method, apparatus, device, medium, and product, relating to the field of computer technology. The question-answering method includes: matching a user's question with standard question text in a target question-answering knowledge base to obtain a semantic matching degree corresponding to the matched result question text; determining an answer strategy for the user's question based on the semantic matching degree of the result question text; and generating an answer statement corresponding to the user's question based on the answer strategy. Based on this application embodiment, the accuracy and reasonableness of answers to telecommunications service questions can be improved.

A reasoning acceleration method based on AI native storage, applied to acceleration of a model reasoning process. In the reasoning acceleration method, for acquired question text and reference text, a plurality of feature fragments corresponding to the reference text are first acquired, wherein the plurality of feature fragments respectively correspond to different text fragments in the reference text; then some feature fragments related to the question text are selected from among the plurality of feature fragments; and the selected some feature fragments are used as features of the reference text to implement processing of the question text, thereby effectively reducing the amount of features needing to be processed by a target model during reasoning. Additionally, the features can be obtained by means of lookup rather than computation on the basis of pre-stored features, thereby avoiding re-computation of the features, increasing the reasoning speed of the target model without affecting reasoning accuracy. That is, in the present solution, the internal memory of a large model is stored, eliminating the need for secondary reasoning by the large model, and the features can be retrieved and used immediately by means of lookup rather than computation, thereby improving the reasoning efficiency of the large model.

The invention provides a text processing method and device, equipment and a storage medium, and relates to the technical field of artificial intelligence. In some embodiments of the invention, the method comprises the following steps: obtaining a current question text; determining whether the first scene label is consistent with the second scene label; wherein the second scene label is a scene label corresponding to a historical context vector, and the historical context vector is a vector extracted based on a historical dialogue text; under the condition that the first scene label is consistent with the second scene label, acquiring a historical question detail text corresponding to the historical context vector, and enhancing logic continuity among questions of the user by combining the context with the current question text; inputting the historical question detail text and the current question text into a compliance scene language model to obtain an answer text and an association basis corresponding to the answer text, and improving the accuracy of compliance questions and answers by means of the model; the association basis enables the answer text to have knowledge traceability, and the credibility of compliance questions and answers is improved.

The application provides a question and answer method based on multi-agent collaborative reasoning, which comprises the following steps: imitating the multi-angle argumentation and consensus formation process of a human expert team by configuring a plurality of agents with different professional analysis roles; taking a complete dialogue reasoning record, a structured answer plan and an answer text as a triple training data set, selecting a basic language model as a student model, and using the triple training data set to fine-tune and optimize the student model; inputting the question text of a user into the optimized model to obtain a final answer text. The application further discloses that a high-quality (question, plan, answer) data pair is generated by using the method, and a small model is fine-tuned based on the data pair; the method can distill the complex multi-agent reasoning and planning capability into a single model with lower deployment cost, solves the problem that a complex model is difficult to be deployed on a large scale in actual application, and improves the industrial practicability and economy of the technology.

The invention provides a text generation model training method, a text generation method and computing equipment, and the text generation model training method comprises the steps that an explanation video corresponding to a sample question is acquired, a sample explanation text corresponding to the explanation video is determined, and a question image corresponding to the sample question comprises a question text; performing text marking on the question text to obtain text marking information, and performing position marking on the question text according to position information of the question text in the question image to obtain position marking information; generating sample marking information according to the text marking information and the position marking information; and training a text generation model according to the sample topic, the sample marking information and the sample explanation text to obtain a trained text generation model.

The invention discloses a dialogue text generation method, system and device based on a generative adversarial network, and belongs to the technical field of machine learning, and the method comprises the steps: obtaining a real-time question text of a first dialogue party, inputting the real-time question text into a target dialogue model, and obtaining a real-time reply text of a second dialogue party; wherein the target dialogue model is obtained by performing reinforcement learning training on the intermediate dialogue model, and in each reinforcement learning training process, training the current dialogue model based on the current training sample and the current reward sequence, the current training sample and the current reward sequence are obtained according to a plurality of rounds of dialogue interaction training performed by the current dialogue model and the target generator; therefore, by implementing the method, the model generalization ability can be enhanced, and the dialogue effect can be improved.