43 results about "Question Text" patented technology

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 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.

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.

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 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.

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.

The application discloses a voice question and answer method based on audio retrieval enhancement generation and double-layer rearrangement, which comprises the following steps: dividing a plurality of original documents contained in a knowledge base document according to a plurality of blocking strategies to obtain a plurality of types of document blocks divided based on different blocking strategies; converting a voice question input by a user end into a user question text and generating a user query vector based on the user question text; determining the relevance ranking results of the plurality of types of document blocks through a plurality of retrieval methods according to the user query vector; reordering the plurality of document blocks ranked higher than a preset ranking threshold in the relevance ranking results according to the semantic relevance between the user question text and the plurality of document blocks ranked higher than the preset ranking threshold, to obtain a reordering result; generating a question answer text according to the user question text and the corresponding document blocks in the reordering result, and generating a voice answer based on the question answer text and returning the voice answer to the user end.

The present disclosure provides a question and answer method, device, equipment and storage medium, which can be applied to the field of artificial intelligence and finance. The method comprises: determining a question text vector; determining N target word vectors; determining answer information according to the N target word vectors; wherein, the N target word vectors are determined by repeatedly performing the following operations until the N target word vectors are obtained: under the condition that 1 < n ≤ N, determining an n th first candidate word vector set from a preset word vector set according to the question text vector and the first n-1 target word vectors in the preset word vector set; randomly dividing the n th first candidate word vector set to obtain a plurality of n th first candidate word vector subsets; determining an n th second candidate word vector set from the n th first candidate word vector subsets according to the n th first candidate word vector set, the question text vector and the first n-1 target word vectors in the preset word vector set; and determining an n th target word vector according to the n th second candidate word vector set.

The present application relates to the field of artificial intelligence, and in particular to a question and answering method, comprising: inputting initial question text of a user into a quantized language model to obtain a slot parameter corresponding to the initial question text, wherein the slot parameter comprises description information related to a target question and answer scenario, and the quantized language model is a language model obtained by compressing a model parameter of a large language model; inputting the slot parameter and the initial question text into a quantized language model to obtain standardized question text, wherein the standardized question text is text that conforms to a predefined text structure and clearly reflects a user intention; inputting the standardized question text into a vector model to obtain a plurality of documents having a highest degree of correlation with the standardized question text; and inputting the standardized question text and the plurality of documents into the quantized language model to obtain response text generated for answering the initial question text. In addition, the present application also relates to the field of natural language processing.

The application discloses an intention recognition method and device. The method generates a feature vector according to a plurality of known intention question texts in advance and saves the feature vector into a preset vector library. When a first question text to be processed is generated, a question vector is generated according to the first question text, and a plurality of intention vectors matching the question vector are obtained from the preset vector library. Since the intention vectors match the features of the question vector, the intention vectors and the question vector have completely same or sufficiently similar intentions. Then, at least two similarity algorithms are used to calculate the similarity between the first question text and a second question text corresponding to each intention vector, and the at least two similarity calculation results are weighted and fused. Finally, the intention corresponding to the second question text meeting a preset similarity condition is determined as the candidate intention of the first question text. The intention recognition result is evaluated from multiple algorithm dimensions, so that the intention recognition result is more accurate.

This invention provides an artificial intelligence-based enterprise knowledge question answering method and apparatus. A specific implementation of the method includes: using a set of limiting conditions and tags determined based on user question text as retrieval conditions; retrieving a set of document nodes satisfying the conditions from a graph database to obtain a document identifier set; determining multiple clause knowledge items containing the document identifiers in the document identifier set from a knowledge base; determining a candidate set of clause knowledge items based on the user question vector corresponding to the user question text; determining a set of preceding document nodes from the graph database that have a priori relationship with the document nodes corresponding to the clause knowledge items in the candidate set; determining multiple preceding clause knowledge items from the knowledge base based on the preceding document identifier set; determining a candidate set of preceding clause knowledge items from the multiple preceding clause knowledge items based on the user question vector; and inputting the user question text, the candidate set of clause knowledge items, and the candidate set of preceding clause knowledge items into a large language model, which then outputs a response.

The application provides a question text processing method and device, equipment and medium, which are used in the technical field of language processing and can solve the problem of low accuracy of existing question text classification. The method comprises the following steps: determining an initial question text according to a preset template, preprocessing the initial question text, obtaining a first probability value corresponding to each question category and a word sequence; calculating a sentence probability value and a text distribution value of each word in the word sequence, and mapping each word to a feature vector according to the sentence probability value and the text distribution value; inputting the feature vector into a target Bart model to obtain a second probability value corresponding to each question category output by the target Bart model, and determining a category probability value according to the first probability value and the second probability value; comparing a target probability value in the category probability value with a preset threshold to determine a target question category corresponding to the initial question text; in this way, the accuracy and efficiency of question text classification are improved.

This application provides a text retrieval method and apparatus. The text retrieval method includes: acquiring a query question text; determining at least one target question text matching the query question text from various reference question texts, and determining a first knowledge document corresponding to each target question text, wherein the reference question texts are questions corresponding to pre-set knowledge documents and stored in a pre-built target knowledge base; determining at least one second knowledge document matching the query question text from various knowledge documents in the target knowledge base; and determining a target knowledge document corresponding to the query question text based on each first knowledge document and each second knowledge document. When retrieving target knowledge documents similar to the query question text, not only the knowledge document itself can be referenced, but also the reference question texts corresponding to the knowledge document, thereby improving the relevance between the retrieved target knowledge documents and the query question text.

The application provides a Token compression method and device for large model dialogue, which can effectively reduce the Token (word element) number of text input into the large model in multi-round dialogue, while also retaining the key information of the early part of the historical dialogue text. The method is applied to a Token compression management agent, which comprises the following steps: after obtaining the question text of a user input terminal, determining the number of word elements in the initial text (containing historical dialogue text and question text) to be sent to the large model. If the number of word elements in the initial text does not meet the threshold requirement, the state is switched to the word element compression state, and the number of word elements in the compressed intermediate dialogue text (part of the historical dialogue text except the first k rounds of dialogue text, k>0) is obtained by interacting with the large model, and the generated summary text is retained. The first k rounds of dialogue text, the summary text and the question text are spliced to obtain a target text. If the number of word elements in the target text meets the threshold requirement, it is sent to the first large model.

The present disclosure provides a knowledge graph-based question answering method and device and related equipment, and relates to the technical field of natural language processing. The method comprises: acquiring a question text; processing the question text to obtain a sentence vector of each sentence in the question text; matching the sentence vector of each sentence with a knowledge graph vector model to obtain one or more entity vectors corresponding to each sentence, wherein the knowledge graph vector model is a model obtained by vectorizing entities and relationships between entities in a pre-constructed entity relationship knowledge graph; generating a joint vector corresponding to each sentence vector according to each sentence vector and the corresponding entity vector; and inputting the joint vector corresponding to each sentence in the question text into a pre-trained question answering model to output an answer text corresponding to the question text. The present disclosure can overcome the problem of lack of coding information interaction between natural language questions and entities in a knowledge graph in related technologies to some extent.

This application provides a method and system for classifying consultation questions based on AI text mining. First, a collection of consultation question texts in the target domain is obtained, containing multiple interactive conversation text fragments with temporal attributes. Next, semantic feature extraction processing is performed on the consultation question text collection to generate contextual semantic representations and intent association features for each interactive conversation text fragment. Subsequently, a multi-level attention mechanism is used to process the dynamic classification weight distribution of the generated interactive conversation text fragments, and a target classification label index is determined through semantic alignment processing. Finally, the classification label priority of the classification label library is updated according to the target classification label index, and the updated classification label library is mapped to the consultation question recommendation interface. This achieves intelligent classification and personalized recommendation of consultation questions, improving the efficiency and accuracy of consultation question classification and optimizing the consultation service experience.

This invention relates to the field of knowledge base construction technology, specifically to a question-and-answer knowledge base construction method, system, and storage medium. The invention categorizes question-and-answer pairs in the current batch to obtain question texts, their job tags, and business intents. It calculates the semantic repetition rate of any two question texts and groups the two question texts with the highest semantic repetition rate together. Through semantic repetition rate calculation and grouping, it achieves representative extraction of multiple question texts with different expressions but the same intent under the same job position, avoiding the duplicate storage of similar questions in the knowledge base. The invention constructs candidate question-and-answer pairs based on a representative question set, calculates a weighted matching rate using the storage duration of in-situ question-and-answer pairs in the knowledge base as a weight, and evaluates the degree of matching between candidate question-and-answer pairs and in-situ knowledge through the weighted matching rate.

The application discloses a self-adaptive fine-tuning intelligent question reasoning and feedback method and system, and relates to the technical field of intelligent text analysis. The method comprises the following steps: system initialization; receiving user input, extracting question text and mathematical formula, converting the question text and the mathematical formula into LaTeX and natural language description, and integrating the question text and the mathematical formula into structured data; generating a problem solving thought chain containing question understanding, step decomposition, step-by-step reasoning and result verification; positioning an error step and determining the type by means of semantic similarity calculation, sequence alignment and step matching degree evaluation, comprehensively obtaining an answer correctness conclusion and missing step information, generating improvement suggestions and outputting in a multi-modal form; and simultaneously, performing self-adaptive fine-tuning on a basic model by using LoRA according to a trigger condition, so as to adapt to the question style and difficulty of a user. The application improves the accuracy and individualization of correction, and simultaneously considers the reasoning process explainability, deployment cost controllability and multi-modal input processing capability.

A textbook text question and answer method and system based on multi-level attention, the method comprising: inputting the question text and the corresponding chapter context paragraph into the first attention model after tokenization and coding, performing self-attention calculation and pooling within the sentence to obtain the sentence representation vector; calculating the cosine similarity of the question sentence representation vector and the representation vector of all context paragraph sentences, retaining only the representation vector corresponding to the sentence with the maximum similarity of each paragraph as the context representation vector of each paragraph corresponding to the question; inputting the question and the context representation vector of each paragraph corresponding to the question into the second attention model, performing self-attention calculation and pooling between the paragraphs and the question to obtain the answer representation vector corresponding to the question as the input of the classifier; outputting the answer options by the classifier, and obtaining the context paragraph of the answer text corresponding to the chapter. The application can select more accurate answer options for textbook text questions.

The application discloses a language mode debiasing visual question answering method based on knowledge distillation, and comprises the following steps: 1) obtaining a given image and a question about the image; 2) processing the question and the image by using a student model to obtain an answer to the question; wherein the obtaining process of the student model is as follows: 2.1) constructing a teacher model and a student model; 2.2) training the teacher model by using a training set, wherein the training set data comprises pictures, question texts and answer texts; 2.3) training the student model; 2.4) performing knowledge distillation on the student model by using the teacher model and based on a set loss function, fixing the parameters of the teacher model and not updating, optimizing the whole learning process by updating the parameters of the student model, and obtaining the trained student model. The scheme of the application introduces a teacher model, takes the output of the teacher model as a soft label for supervising the student model, and can avoid additional data labeling.

This invention discloses a domain classification method for complex legal question-and-answer questions embedded in the frequency domain, comprising: acquiring the original legal question text; concatenating the original legal question text with preset category labels to obtain a joint input sequence; converting the joint input sequence into a frequency domain feature sequence representing the text structure features through a fast Fourier transform; inputting the frequency domain feature sequence into an encoder to extract text feature representations and label feature representations; and calculating the confidence scores of the text feature representations belonging to each category label through a pre-trained scoring function to obtain the sub-case classification results.

The present disclosure relates to the technical field of text processing, and provides a text question and answer method and device, electronic equipment and readable storage medium. The method comprises: performing tool search processing on a question text based on a preset tool library to obtain a candidate tool list; performing conditional filtering processing on the candidate tool list to obtain an updated tool list; performing adaptation degree evaluation processing on the updated tool list based on a preset adaptation degree threshold to obtain an evaluation tool list; performing capacity verification processing on the evaluation tool list to obtain a target tool list; and performing retrieval enhancement generation processing on the target tool list and the question text to obtain a target answer text corresponding to the question text. The real-time adaptability of the tool set and the dynamic dialogue context is enhanced, the task execution efficiency and the answer accuracy in the multi-round dialogue scene are improved, the stability and reliability of the operation are ensured, the flexibility of tool calling is improved, the task execution efficiency is improved, and the coherence of the text dialogue is enhanced.

The embodiment of the application belongs to the field of artificial intelligence, and relates to a question and answer processing method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining a question and answer request carrying question text features, wherein the question text features are generated based on a question text; obtaining a plurality of initial information features, wherein the initial information features are image features or text features; screening the initial information features related to the question text to obtain a plurality of recall information features; constructing a question and answer feature according to the question text features and each recall information feature and inputting the question and answer feature into a question and answer model, so as to generate image answer information by processing the image features in the question and answer feature based on an image processing submodel in the question and answer model, and generate text answer information by processing the text features in the question and answer feature based on a text processing submodel in the question and answer model, thereby obtaining answer information. The application also relates to blockchain technology, and the initial information features can be stored in the blockchain. The application improves the accuracy of multi-modal question and answer.

Embodiments of the present application provide a text processing method and device based on multi-round question and answer, equipment and storage medium, belonging to the technical field of financial technology. The method comprises: obtaining a first question text and a first answer text in a historical round to splice and construct a first text set; inputting the first text set into a to-be-trained model for dialogue modeling training to obtain a target model; inputting the first text set corresponding to a plurality of historical rounds into the target model to output semantic information; generating a first vector of the historical round according to the semantic information, combining the first vector with a second vector of a second dialogue text to obtain a first fusion vector; and performing target answer prediction to determine a start position, an end position and a target answer in the second text. The present application scheme can have stronger historical analysis capability; and by simulating the memory mode, the historical dialogue is modeled, which can effectively reduce the noise and improve the accuracy and interpretability of the prediction output result.

The application discloses a dialogue text generation method, system and equipment based on an adversarial generation network, and belongs to the technical field of machine learning. The method is as follows: real-time question text of a first dialogue party is input into a target dialogue model to obtain real-time reply text of a second dialogue party. The target dialogue model is obtained by reinforcement learning training on an intermediate dialogue model. In each round of reinforcement learning training, a current dialogue model is trained based on a current training sample and a current reward sequence. The current training sample and the current reward sequence are obtained according to several rounds of dialogue interaction training of the current dialogue model and a target generator. Therefore, the application can enhance the generalization ability of the model and improve the dialogue effect.

A question-and-answer method and apparatus are disclosed to improve the accuracy of memory retrieval. The method includes: an electronic device acquiring a target question text input by a user; the electronic device retrieving a first historical question text with the highest semantic similarity to the target question text from at least one set of stored historical dialogue records, and outputting a first response text corresponding to the first historical question text; wherein each set of historical dialogue records contains historical question text and corresponding response text; the electronic device acquiring at least one target keyword of the target question text, and acquiring keywords corresponding to at least one set of historical dialogue records; the electronic device determining a target historical dialogue record with the highest similarity between the corresponding keyword and at least one target keyword, and acquiring a second response text from the target historical dialogue record; when the first response text and the second response text are inconsistent, the electronic device outputting a correction text based on the second response text.

The application relates to the technical field of natural language processing, and discloses a guided question and answer system and method based on implicit premise triple extraction, which comprises the following steps: receiving user question text and performing implicit premise triple extraction to construct a premise triple set; performing multi-layer conflict detection on the set, including internal mutual consistency verification and external domain knowledge collision detection, labeling internal mutual consistency states and external collision states for each premise triple, and generating a premise verification report by summarizing; generating a counter-question sentence according to the states by using a corresponding guided counter-question generation strategy, verifying a conflict premise correction state according to a user feedback reply text, executing a closed-loop correction according to the state, and outputting a final answer; and the application eliminates logical misdirection caused by a large language model blindly obeying input conditions through structured verification and closed-loop correction of a question premise, and ensures the correctness of a question and answer conclusion in a complex professional scenario.

The application discloses a kind of multi-expert architecture AI intelligent question and answer method and system in government field, comprising: A1: new policy text data, enterprise policy consultation question text data, historical policy answer example text data are collected and respectively preprocessed;A2: extracting new policy preliminary semantic features, then extracting explicit rule text segment set;A3: extracting the implicit constraint text corresponding to explicit rule text segment, then carrying out associated integration operation, obtain structured policy explicit and implicit rule text set;A4: extract historical case experience initial feature;Again, through government semantic bridging mechanism, complete semantic dimension alignment;A5: extract policy-case fusion feature;A6: calculate expert fusion weight vector, then decode, obtain policy question and answer reasoning result.The application can solve the problem that the AI question and answer effect is poor caused by the fact that the historical case experience cannot be quickly adapted after the traditional method is updated.