151 results about "Semantic expansion" patented technology

The invention relates to the technical field of intelligent recommendation, and discloses a hybrid retrieval RAG-based resource recommendation method and system, and the method comprises the steps: collecting resource text data, and constructing a vector library and a tag library; expanding the user question based on the language model to obtain a plurality of semantic extension questions; performing intention recognition, judging whether the user question is a resource recommendation question, and if yes, determining a target classification type; screening the data according to the field definition in the tag library to obtain a candidate knowledge fragment set; obtaining candidate vectors, mapping the user question and the semantic extension question into query vectors, calculating the similarity between the query vectors and each candidate vector, and selecting knowledge supplement content; and performing resource splicing on all the knowledge supplement contents to generate resource recommendation answers. According to the method, a structured label screening mechanism and a semantic vector fine arrangement mechanism are fused, and the problems of recall redundancy, matching deviation and the like caused by the fact that an existing RAG system only depends on semantic similarity retrieval are solved.

The invention discloses a long-tail image recognition method based on multi-modal semantic generation and image-text fusion. The method comprises the following steps: extracting structured semantic description from a tail image; carrying out semantic rewriting and enhancement based on a multi-modal visual language model, and generating an image semantic extension description; the image semantic extension description is optimized based on semantic duplicate judgment and a style alignment mechanism, and an optimized text description set is obtained; inputting the optimized text description set into a text graph model, generating a tail class image sample, performing semantic and visual quality screening, and constructing to obtain an enhanced image set for training; constructing a training data set based on the original long-tail data set and the enhanced image set, and training an image-text fusion classification model; and inputting a to-be-identified image into the trained image-text fusion classification model, and outputting classification results of all categories. According to the method, the discrimination capability in a long-tail distribution scene is enhanced, and the method has a stronger generalization characteristic.

The invention provides a method for generating an SQL (Structured Query Language) by a natural language based on bidirectional mapping and semantic parsing, which relates to the technical field of database query and comprises the following steps of: extracting natural language query elements and packaging the natural language query elements into structured data, and establishing a mapping relationship from a query field to a service attribute and a physical data table by adopting a bidirectional Hash index technology; and automatically identifying multi-table association keys, performing semantic extension and compliance verification, generating an abstract syntax tree, performing processing according to user permission, and finally converting the abstract syntax tree into an SQL statement conforming to a target database syntax specification. According to the method, the accuracy and the efficiency of converting the natural language into the SQL are improved, and the flexibility and the safety of the system are enhanced.

The invention relates to the technical field of natural language processing and information retrieval, and discloses a deep dense document recall method based on multi-view vector fusion, comprising the following steps: S1, preprocessing user query and candidate documents to generate a standardized text; s2, respectively constructing multi-view semantic vector representation of the query and the document, wherein multiple views at least comprise a keyword view, a semantic extension view and an intention view; s3, calculating a similarity score between the query and the document for each semantic view, and fusing the scores of all the views through a dynamic weight; and S4, sorting the documents according to the fusion score, and returning a front Top-K result. By constructing multi-dimensional semantic representation of keywords, semantic extension and an intention perspective, multiple semantic information such as term accurate matching, context association and task target consistency is effectively fused. The dynamic weight distribution mechanism adaptively adjusts the contribution degree of each view angle according to the query content, and overcomes the defect of insufficient semantic coverage of a single view angle.

The invention provides a knowledge graph-based government policy question and answer method and related equipment, which realize intelligent processing of government policy question and answer, contribute to improving the intelligent level of government policy service and meet the actual question and answer requirements of actual government policies. The method comprises the steps of obtaining multi-modal government affair policy data, wherein the multi-modal government affair policy data comprises structured policy data, an unstructured policy text, an OCR text, layout features and a policy document; the multi-modal government affair policy data are fused through a Transform hybrid architecture, a knowledge graph is constructed, and the knowledge graph comprises five elements including entities, relationships, attributes, time and space; constructing a time sequence diagram structure of policy conditions based on the dynamic graph neural network; receiving user query information, and extracting a geographic position keyword based on the query information; and carrying out semantic extension on the keyword by utilizing a Geo-BERT model, and obtaining a target keyword.

The invention belongs to the technical field of text processing, and particularly relates to a method and system for retrieving DOCX document content based on keywords, which comprises the following steps: analyzing an Office Open XML structure of a DOCX document, combining with multi-dimensional features such as style names, and utilizing a title classification score model to accurately distinguish a title and a text, so that a semantic hierarchical structure of the document is effectively reserved; and secondly, a multi-level semantic extension mechanism is introduced, and a Sension-BERT, a HowNet knowledge base and a Word2Vec model are fused, so that intelligent extension of synonyms and synonyms of keywords is realized, and the recall rate and semantic understanding ability of retrieval are remarkably improved. And in addition, a BM25 model is combined with paragraph length normalization and structure position weight to calculate a correlation score, so that retrieval results are sorted more accurately and reasonably. The construction of the reverse index is combined with the position coding and compression optimization strategy, and the retrieval efficiency and the storage performance are both considered.

The invention provides a water conservancy industry electronic dark bidding document enterprise internal examination method and system based on artificial intelligence, and belongs to the field of water conservancy industry bidding. Performing automatic pre-auditing on the bidding file: performing compliance inspection and integrity inspection, identifying problems existing in the bidding file, and providing improvement suggestions to ensure that the problems conform to the basic requirements of electronic dark label review; carrying out data standardization and cleaning on the bidding file: carrying out semantic extension and ambiguity elimination, identifying images, tables and handwritten contents in the bidding file, identifying a main body structure of the water conservancy design drawing, extracting engineering quantity list data, and carrying out compliance verification; identifying an abnormal behavior in the bidding file through a machine learning model; and an internal examination decision tree is constructed according to preset key indexes and score weights of the water conservancy project, an interpretable artificial intelligence algorithm is utilized to carry out internal examination decision making on the bidding document, an internal examination score result is fed back, and specific score deduction reasons are explained. And the standardization and the accuracy of internal examination of the bidding document are improved.

The invention relates to the technical field of operation and maintenance automation, and provides an operation and maintenance field professional question and answer and diagnosis Agent design method and system, and the method comprises the steps: receiving and structurally analyzing an original query request of a user, carrying out the parameter validity check and safety verification, and extracting the query content and a session identifier; identifying task types through an intention classification algorithm based on the pre-training language model and performing content risk assessment; performing semantic extension on the query to generate an extended query word, performing similarity matching in the operation and maintenance knowledge base by using a hybrid retrieval algorithm, and fusing related knowledge fragments; inputting the enhanced query information and the task type into an inference engine for intelligent inference to obtain a diagnosis result; the reasoning result is stored in a historical memory library, and session context state information is updated; and performing formatting processing and security check on the reasoning result, packaging the result and context information, and outputting a standard response result. According to the method, the accuracy and the intelligent level of operation and maintenance professional question answering and diagnosis are improved.

The invention discloses a large language model training method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence and reinforcement learning. The method comprises the steps of obtaining an initial prediction answer statement corresponding to a question statement; semantic expansion retrieval is carried out on the initial prediction answer statement, and a retrieval answer statement corresponding to the initial prediction answer statement is determined; scoring the retrieval answer statement, and determining a target reward value of the initial prediction answer statement based on a scoring result of the retrieval answer statement; and if the target reward value is smaller than a preset reward threshold value, adjusting the pre-trained large language model based on the target reward value, and inputting the question statement into the adjusted model again until the finally obtained target reward value is greater than or equal to the preset reward threshold value, thereby completing training of the pre-trained large language model. The optimization training efficiency of the large language model and the accuracy of model output can be improved, and the stability of large language model output is improved.

The invention discloses a weak supervision video anomaly detection method based on prompt learning knowledge enhancement, and belongs to the technical field of video intelligent analysis. A video side gives a section of abnormal scene video, video sequence features and audio sequence features are obtained through a feature extraction network, then a trained and complete feature aggregation network is input to carry out multi-modal feature aggregation, an abnormal score is obtained through a score prediction network, and text representation is carried out based on prompt learning. A prompt template is constructed for abnormal video tags through a knowledge graph, semantic expansion is performed on normal tags through a plurality of learnable parameters, cross-modal alignment is performed on the normal tags and a video side, so that features of the video side are close to different normal semantics, knowledge enhancement is performed by introducing external information, positive abnormal boundaries of the video are learned, and the detection performance is improved. And finally, multi-task joint optimization is carried out through different loss functions, and abnormal video clip positioning is carried out.

The invention relates to a knowledge graph enhanced multi-modal file retrieval method, and belongs to the field of artificial intelligence and multi-modal information retrieval. The invention aims to solve the problems of multi-modal information semantic segmentation, weak semantic reasoning ability and low semantic matching precision in the existing multi-modal archive resource retrieval process. Through four stages of archive multi-modal data preprocessing and feature extraction, knowledge graph construction and enhancement, semantic retrieval request analysis and intention modeling, and multi-modal semantic matching and sorting, a semantic relationship is enhanced by utilizing a knowledge graph, so that the semantic relevancy and context consistency of a retrieval result are remarkably improved; a user is allowed to input and inquire in various forms such as texts, images and voices, and semantic extension retrieval is supported. According to the method, more efficient and accurate archive resource retrieval can be realized, and the user retrieval experience and archive knowledge utilization are improved.

The invention discloses a semantic extension matching method and system based on a domain synonym library, and relates to the technical field of data processing, the method comprises the following steps: obtaining a query keyword input by a user, and generating a query context vector according to the query keyword and user context information; if the query keyword does not belong to the category word in the platform service category system, determining an extended synonym set matched with the query keyword from a pre-constructed field synonym library; for each extended synonym in the extended synonym set, calculating a correlation score between the extended synonym and the query context vector, and performing weighting processing to obtain a corresponding weighted extended synonym; and according to each weighted extended synonym and the query keyword, generating an extended query index for search matching. Therefore, dynamic expansion combining the field scene and the synonym library is realized, multi-dimensional semantic expansion can be carried out when complex and non-standardized user query is processed, and the intelligent level of the system is improved.

In accordance with an embodiment, described herein is a system and method for providing support for extensibility and customization in an analytic applications environment. An extract, transform, load (ETL) or other data pipeline or process provided by the analytic applications environment, can operate in accordance with an analytic applications schema and / or a customer schema associated with a customer (tenant), to receive data from the customer's enterprise software application or data environment, for loading into a data warehouse instance. A semantic layer enables the use of custom semantic extensions to extend a semantic model, and provide custom content at a presentation layer. Extension wizards or development environments can guide users in using the custom semantic extensions to extend or customize the semantic model, through a definition of branches and steps, followed by promotion of the extended or customized semantic model to a production environment.

The invention provides a scientific research question answering and reasoning all-in-one machine based on multi-agent cooperation and a control method, and relates to the technical field of artificial intelligence and multi-agent reasoning, and the all-in-one machine comprises a first agent which is used for carrying out the semantic understanding of a scientific research problem inputted by a user, and obtaining a semantic understanding result; performing semantic extension on the semantic understanding result according to a configured extension rule to obtain a first query request corresponding to the scientific research problem; the second intelligent agent is used for screening response information associated with the query request sent by the first intelligent agent from a pre-constructed scientific research knowledge base and sending the corresponding response information to the first intelligent agent; and the third agent is used for evaluating whether the target response information, the corresponding semantic understanding result, the first query request and the second query request meet the configured evaluation rule or not to obtain an evaluation result. The scientific research problem of the user can be accurately, comprehensively and reliably responded.

The invention provides a class incremental learning method based on prompt guidance and multi-modal fusion, and relates to the technical field of artificial intelligence and computer vision. The method comprises the following steps: firstly, performing semantic extension on a category label, and constructing semantic enhanced text representation through a text encoder; then block embedding and hierarchical feature extraction are carried out on the input image by using a pre-trained visual encoder, a cross-modal unified embedding space is constructed, a bimodal prompt gating fusion module is introduced into the unified embedding space, and adaptive weighting is carried out on text prompt and image prompt according to gating weight to generate fusion prompt; through a bimodal prompt collaborative filtering module, screening out a prompt set most relevant to the current task according to the similarity of the semantic features of the image and the text; the pre-training backbone network is frozen in the increment stage, only prompt parameters and fusion layer weights are optimized, a joint loss function is used for parameter updating, finally, image and text data are input in the reasoning stage, cross-modal similarity is calculated, and a classification prediction result is output.

The invention relates to the field of business type judgment, in particular to a method for judging the business type of an unknown business database based on a large model, which comprises the following steps of: connecting the unknown business database through a standardized interface to obtain metadata and sample data; extracting multi-dimensional meta-information according to database types; performing semantic extension on the meta-information by utilizing a pre-training language model BERT; fusing multiple features through an attention mechanism to generate a fused feature, and outputting a service type reasoning prompt in combination with a historical reasoning result; after LLM multi-round reasoning, the matching degree is judged through comprehensive confidence, a confidence matrix is constructed, and a final service type is output; the method realizes automatic and high-precision judgment of the service type of the unknown service database, and is suitable for scenes of database management, data analysis and the like.

The invention discloses a dynamic updating law and regulation knowledge graph construction and recall method. The method comprises the following steps: collecting law and regulation text data in real time; generating a structured law article object sequence through regular fragmentation processing; performing full-text structure recognition and semantic processing to generate segmentation-level and full-text-level semantic data; carrying out composite vectorization on the content of the law article, the outline of the segmented text and the abstract to generate a context enhanced semantic vector; fusing the full-text and segmented triads and enhancing relation attributes; respectively storing the vector and the original data to a vector database and an original index; importing the fused triple into a graph database to construct a knowledge graph; and based on the map response query, outputting a structured answer through entity recognition, semantic extension, multi-hop query and result fusion. According to the method, efficient, accurate and real-time retrieval and dynamic updating of law and regulation knowledge are achieved, and the recall rate and accuracy of complex legal questions and answers are effectively improved.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a target data sample set construction and screening method, device, equipment and medium, and the method comprises the steps: obtaining a target type description, carrying out semantic extension to generate an extension description, generating a reference image sample based on an image generation model, real data units are screened through feature extraction and similarity comparison, and a target data sample set is constructed in combination with knowledge base verification. According to the method, by introducing semantic extension, reference image generation, cross-domain feature comparison and knowledge base consistency verification, real samples highly fitting target type semantics are automatically screened from massive original data, so that the manual annotation dependence is reduced, the illegal sample construction efficiency is improved, and the manual annotation time is shortened. And the training quality and the expansion capability of a subsequent detection model are enhanced.

The invention discloses a collaborative problem traceability and strategy matching method based on entity recognition, and the method comprises the steps: carrying out the semantic expansion of a negative problem text through a T5 generation type pre-training model, and extracting time, a subject, a problem, a strategy and other entities and position information through a BERT-BiLSTM-CRF model; splicing the subject entity, the question and the strategy entity to generate a text with a prefix, correcting by using a BART generation type pre-training model, and classifying and mapping the question to a subsystem for storage through a BERT-DPCNN model; coarse screening is conducted on texts in the subsystem through a regular rule base, vector representation is generated in combination with BERT and RoBERTa models, cosine similarity is calculated, and matching results are determined by synthesizing sentence positions and keyword overlapping degrees; constructing a question-strategy keyword knowledge graph based on a matching result, and inputting the keywords into a DeepSeek-V3 big language model to generate an optimization strategy scheme; according to the method, multiple deep learning models and large language models are fused, so that semantic understanding, entity extraction and accurate matching of negative problem texts are realized, and a final optimization strategy scheme is generated.

The invention relates to the field of data processing, in particular to an information retrieval method for a smart city system, which comprises the following steps of: obtaining a historical data block of a business system and user interaction session data, and performing word segmentation to obtain an original word and a to-be-processed word set; calculating topic probabilities and topic correlation degrees of original words and historical data blocks through a topic model, screening candidate words and calculating importance degrees of the candidate words; expansion words and historical perception words are generated and spliced into a dynamic sequence, the semantic similarity of the sequence and historical data blocks is calculated, a preset number of data blocks are sequenced and displayed, and retrieval is completed. The topic probability of the original word and the historical data block and the corresponding topic correlation degree are calculated through the topic model, the candidate word inherits the topic attribute of the original word, the topic probability distribution consistency of the candidate word and the original word is quantified in combination with the JS divergence to screen the extension word, the topic deviation risk of semantic extension is avoided from the source, and the semantic extension efficiency is improved. And the retrieval matching precision is improved.

The invention discloses a multi-modal retrieval method and system based on a knowledge graph, and the method is characterized in that the method comprises the steps: recognizing the entity information of multi-modal archive data to calculate a cross-modal consistency score; constructing semantic anchor points based on the cross-modal consistency scores to generate knowledge events; obtaining a plurality of times of cross-modal verification information of the knowledge event to perform structure optimization on a preset knowledge graph to obtain a target knowledge graph; determining a query intention based on the query information in combination with historical query habits of the user, and extracting semantic extension information based on the target knowledge graph to disambiguate the query intention; determining a plurality of retrieval results by utilizing a target knowledge graph based on the disambiguated query intention, and analyzing semantic paths of the disambiguated query intention and each retrieval result; and calculating relevance scores of the retrieval results based on the semantic path to sort the retrieval results. According to the method, a deeper retrieval result can be provided, and the relevance and the coverage range of the retrieval result are improved.

The invention relates to the technical field of government affair services, in particular to an NLP entity recognition method based on semantic extension, which comprises the following steps: collecting multi-source time sequence data and generating an entrepreneurship ecological data graph through a dynamic time warping algorithm; dynamic evolution of a term library is realized by using a generative adversarial network, and a term semantic association graph is constructed in combination with a graph convolutional network; a double-path attention mechanism is deployed in a Transform encoder, and global semantics and local attention guided by terms are fused through a gating loop unit; modeling fuzzy query analysis into a Markov decision process, and optimizing a semantic extension strategy by adopting a reinforcement learning agent; multi-granularity features are extracted through a feature pyramid network, and model parameters are optimized in combination with a bidirectional long-short-term memory network and an online learning feedback loop; and finally, calculating entity service association strength by using a graph attention network, and generating an interpretable report based on a Shapley value attribution algorithm. A closed-loop learning system is formed, and the business starting policy matching accuracy is improved.

The invention provides a root cause analysis method and system based on multi-modal data and multi-agent collaboration, directional collaboration of multi-modal evidence is realized through three special agents, an RCA coordination agent analyzes unstructured exception description of a user into structured query, cross-agent workflow is dynamically coordinated, and the user experience is improved. According to the technical scheme, semantic ambiguity is solved, implicit association recognition is achieved, the error accumulation problem of a single agent system is relieved, a retrieval agent achieves retrieval of historical cases and proposing of root cause hypotheses according to analyzed structured query in combination with keyword matching and semantic extension, a verification agent converts the root cause hypotheses into quantifiable verification tasks, and the verification efficiency is improved. And querying real-time data of the system, calculating a semantic similarity score of the real-time data and the historical mode, and performing root cause judgment. Experiments show that the MA-RCA system provided by the invention has an accuracy rate of 95.8% and an F1 rate of 95.2%, which are significantly superior to those of a single-agent baseline model, and verifies the effectiveness of a multi-agent cooperative system in performing root cause analysis by using multi-modal data.

The invention relates to the field of voice analysis, in particular to a robot control method based on voice analysis, and the method comprises the steps: obtaining image information in a space region where a target robot is located, determining semantic tags, determining a potential association semantic tag group, and screening out a semantic guiding corpus group for the target robot; when voice control data is received, instruction fuzzy parameters of the voice control data are determined so as to judge instruction fuzzy tendency, optimization is carried out on the voice control data with the instruction fuzzy tendency, specifically, confidence centralized clusters and semantic discrete clusters are determined, semantic expansion is carried out on the semantic discrete clusters, and then an expansion text is obtained; and screening the expanded text based on the semantic oriented corpus group to obtain a confidence instruction text. According to the method, the semantic oriented corpus group is constructed in combination with the image information, the analysis of the voice control data with the instruction fuzzy tendency is guided, the analysis accuracy of the voice control data under the semantic fuzzy condition is improved, and the control instruction recognition precision is ensured.

The invention relates to a system cue word dynamic generation method and system based on multi-model feedback loop. The method comprises the following steps: (1) receiving an original cue word of a user; (2) calling an auxiliary large language model to perform semantic extension on the cue word of the user; (3) inputting each candidate system prompt word and a user prompt word combination into the main large language model; (4) performing multi-dimensional quantitative scoring on each preliminary answer through an evaluation model; (5) selecting an optimal system cue word according to the comprehensive score sequence, and triggering a main big model to generate a final answer; and (6) if all the preliminary answer scores are lower than a preset threshold value, starting a feedback loop to regenerate candidate system cue words. The method has the advantages that (1) the system cue word and the user cue word are strictly distinguished, and the intention purity of the user is ensured; and (2) the system prompt words are dynamically generated, and the adaptability is high.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses a memory analysis question and answer data construction method and device, equipment and a medium. The method comprises the steps of extracting a fact information set containing entities, relationships and values based on structured message representation, generating candidate question and answer pairs by utilizing a language model, executing multi-source verification to form a target question and answer set, performing semantic extension and question method transformation to generate a diversified question and answer set, and completing credibility screening based on a verification result to obtain a memory analysis question and answer set. And generating a memory analysis data set in combination with the user message sequence. According to the method, through multi-stage extraction, generation, verification and screening, reliability and diversity unification of question and answer content are achieved, the constructed memory analysis data set has the advantages of being consistent in context, accurate in fact, rich in expression and the like, and therefore the credibility of memory ability evaluation of the large language model is improved.

The invention discloses an intelligent archive keyword indexing method based on multi-modal semantic association, and relates to the technical field of archive keyword indexing. The method comprises the following steps: initially performing text segmentation of different target detection on text modal information; semantic expansion information block segmentation of corresponding target detection is carried out on image, audio and video modal information in an associated manner in sequence, and keyword extraction weight value statistics of positive samples with similar semantics and negative samples with opposite semantics is carried out on segmented sub-information blocks, and the segmented sub-information blocks are combined; the method comprises the following steps of: segmenting information blocks of image, audio and video modal information which are respectively used as initial processing objects in sequence, combining segmented text sub-information I, image sub-information II, audio sub-information III and video sub-information IV, and carrying out keyword extraction weight value statistics; and summarizing the test sample set obtained by statistics to realize keyword indexing through an established file keyword extraction model test. The keyword indexing accuracy can be improved.

The invention discloses an intelligent information consultation service system based on machine learning, and relates to the technical field of artificial intelligence. Through natural language processing and semantic extension technologies and in combination with a cross-domain knowledge fusion mechanism of a knowledge graph retrieval module, the problems that a traditional system depends on a preset rule, understanding of real intentions of a user is not deep, and the cross-domain information integration capability is weak are effectively solved; accurate analysis of the user consultation request and efficient acquisition of multi-field related information are realized; through context awareness and cold start processing, in combination with personalized adjustment of the information recommendation module based on user characteristics, the defect that a traditional system lacks targeted services is overcome, and information meeting the requirements of different users can be provided for the different users; the system can dynamically update the model, the knowledge graph and the user portrait and continuously adapt to user requirements and knowledge environment changes, so that the accuracy, pertinence and long-term effectiveness of intelligent information consultation service are comprehensively improved.

The present application discloses a method and apparatus for generating a dynamic video, an electronic device, and a storage medium. The method comprises: acquiring a textual script of a storyboard; performing semantic expansion on the textual script by means of a large language model to obtain a plurality of scene descriptions, and generating storyboard still images corresponding to the scene descriptions; using a fusion inpainting model to perform inpainting processing on a target storyboard still image selected from the plurality of storyboard still images; generating a mask image of a dynamic area on the target storyboard still image selected by a user; by means of an image-to-video model, using feature information of the target storyboard still image and the mask image to generate a dynamic video of the storyboard according to image generation prompt information; performing video post-processing on the dynamic video; generating audio generation prompt information on the basis of a theme and style of the dynamic video, and generating a current video-based audio according to the audio generation prompt information by means of an audio generation model; and adding the current video-based audio to the dynamic video of the storyboard to obtain a final dynamic video of the storyboard.

The invention belongs to the technical field of artificial intelligence, and particularly relates to an AI-based file data content accurate and deep analysis and interpretation method, which comprises the following steps: acquiring multi-format file data and file meta-information, constructing an AI analysis network, extracting text semantic vectors, image visual features, table structure information and document layout features, and constructing a multi-dimensional semantic map. According to a user query intention, semantic extension is performed in combination with a domain knowledge base, an enhanced semantic description vector is generated through a graph attention mechanism, semantic reasoning and relation mining are performed by adopting an improved knowledge distillation Transform model, and a deep analysis conclusion is generated through a multi-hop reasoning model in combination with file data complexity, information density and user requirements. And generating a personalized interpretation report in combination with a user role and a task scene, and outputting an analysis result through a visual interface. Therefore, the problems of poor understanding ability, poor file adaptability and the like in the prior art are solved.