1354results about How to "Improve relevance" patented technology

The invention relates to the technical field of database construction, in particular to a knowledge base question-answering system construction method and device, equipment and a storage medium. The method comprises the following steps: acquiring a user question instruction, and performing part-of-speech tagging and keyword vectorization on a target text to generate a retrieval text keyword vector; performing semantic linear embedding and spatial projection processing on the keyword vectors to obtain keyword semantic vectors; logic mining is conducted on the keywords, a logic relation set among the keywords is obtained, logic recognition is conducted on the target text based on the relations, and retrieval text logic is generated; performing matching retrieval with semantic vectors in a knowledge base to obtain a candidate semantic query data set; and performing coherent logic retrieval on the candidate data set according to the retrieval text logic and the keyword vector to generate a final retrieval target answer. According to the method and the system, more accurate and efficient knowledge base question-answering system construction is realized.

The invention provides a plasticizing product recommendation method and system based on user demands, and relates to the technical field of plasticizing product recommendation, and the method comprises the steps: S1, constructing a plasticizing industry knowledge graph; s2, acquiring user historical data and current user requirements, including historical search data, historical browsing data, historical interaction data and historical transaction data; s3, preprocessing the historical data of the user, analyzing the preprocessed historical data of the user, and extracting historical demand features; s4, performing keyword extraction on the current user demand by utilizing the semantic understanding model, and generating an optimized query condition in combination with the chemical and plastic industry knowledge graph; s5, searching in a plasticizing product database by utilizing the optimized query condition to obtain a first list; and S6, carrying out personalized sorting on the first list by utilizing the chemical and plastic industry knowledge graph, generating a recommendation list from the first k lists, and presenting the recommendation list to the user. According to the invention, the relevance and accuracy of recommendation can be improved, so that the user experience is improved.

The invention belongs to the technical field of artificial intelligence, and relates to a power document intelligent question and answer method and system based on a large language model. The method comprises the steps of obtaining document data according to a preset period; preprocessing the document data to obtain an adaptive document; constructing a vector retrieval library through an embedded model according to the adaptive document; obtaining a user query question, inputting the user query question into a vector retrieval library, performing retrieval based on a vector similarity retrieval method and a keyword retrieval method to obtain related text blocks, and screening out the most related text block from the related text blocks through a two-stage rearrangement technology; a user queries the question and the most relevant text block and inputs the question and the most relevant text block into the large language model to obtain preliminary intelligent answer information; and correcting the preliminary intelligent answer information based on a preset self-provincial inversion mechanism to obtain final intelligent answer information. Multiple rounds of questions and answers and context understanding are supported based on a correction mechanism, context consistency can be kept in continuous query of complex technical questions, and the accuracy of multiple rounds of questions and responses is ensured.

The invention relates to the technical field of knowledge question answering, in particular to an intelligent question answering method and system based on multi-module collaborative optimization, and the method comprises the steps: inputting a question to be answered into a knowledge question answering model, and outputting a knowledge question answering result by the knowledge question answering model; a knowledge range judgment module in the model judges whether the problem can be solved by relying on own knowledge, and if not, a dynamic retrieval module is entered; the dynamic retrieval module performs similarity retrieval on the content of the memory knowledge base according to the question to be answered, and if the retrieval result does not meet the requirement, the multi-level question rewriting module is entered; the multi-level question rewriting module rewrites questions to be answered and inputs the rewritten questions into the knowledge screening module; the knowledge screening module outputs the screened documents according to the rewritten questions, the auto-reflection optimization module generates preliminary answers according to the documents and the questions and judges whether the preliminary answers are reasonable or not, auto-reflection optimization is carried out if the preliminary answers are not reasonable, and a new solution is provided for development of the intelligent question and answer technology.

The invention relates to the technical field of agricultural intelligent detection, in particular to a fruit tree disease and pest detection method based on machine vision, which comprises the following steps: acquiring visible light, infrared light and ultraviolet light images of a fruit tree at multiple angles through a multispectral camera to obtain complete fruit tree surface information, and preprocessing the acquired images to obtain a fruit tree disease and pest detection result; comprising the steps of denoising, illumination correction and image alignment, extracting feature vectors, including the color, shape and size of scabs, pest distribution and other features, of pest and disease damage from preprocessed images through a convolutional neural network, fusing the pest and disease damage features with environmental data by using a multi-modal data fusion algorithm, and enhancing the accuracy of pest and disease damage classification. Classifying and identifying diseases and pests based on a support vector machine classification algorithm; according to the dynamically adjusted threshold value and suggestions provided by the expert system, a disease and pest diagnosis report is generated, and prevention and control measure suggestions are provided; according to the invention, efficient and accurate detection and management of fruit tree diseases and insect pests can be realized, and the intelligent level of agricultural management is improved.

The invention provides a user interest intelligent recommendation method and system based on the Internet, and relates to the technical field of the Internet, the system collects and integrates behavior data of a user on different platforms in real time to form a multi-source data set; by utilizing natural language processing and time sequence analysis technologies, the system deeply digs user interests and interest change trends, and identifies potential interest sudden increase trends; through a clustering algorithm, the system divides users with similar interest characteristics into dynamic user interest clusters, and dynamically adjusts parameters of the user interest clusters according to instantaneous data; the system predicts future demands of the user through a deep learning model, generates personalized recommendation content in combination with a time sequence analysis model and user interest cluster features, and pushes the personalized recommendation content to the user through multiple channels. According to the method and the device, the related content is accurately pushed under the condition that the user suddenly changed interest characteristics are improved.

The invention discloses an automatic labeling and acquisition standardization method and system based on video content, and the method comprises the steps: decoding a video file into a processable video frame sequence, carrying out the standardization processing, unifying the format and the coding standard, and adjusting the resolution and the frame rate; performing content analysis on the standardized video frame sequence, extracting key frames, identifying objects, scenes and actions, and generating a video analysis result and a preliminary label; according to a video content analysis result, separating an audio stream from the video to carry out noise reduction processing and voice-to-text analysis, and combining the processed text with the video content analysis result to generate multi-modal comprehensive annotation information; based on the comprehensive labeling information, taking feedback of the user in video retrieval, label clicking and watching behaviors as an adjustment basis of label weights, and updating weight distribution of labels by analyzing user behavior data; labeling information and weight distribution are integrated into an index database, and indexes are updated in real time according to user behaviors and content changes.

The invention relates to a knowledge base question answering method and device and a computer readable storage medium, and belongs to the technical field of artificial intelligence. A query question input by a user is received; the query problem is analyzed, and keywords in the query problem are extracted; retrieving slice data matched with the query problem from a retrieval enhancement generation system on the basis of the text correlation between the keyword and the slice data; wherein a plurality of slice data are pre-stored in the retrieval enhancement generation system, the slice data comprise text slices and image-text slices, and the image-text slices comprise storage paths of images and image descriptions with text context information of the images; and inputting the retrieved slice data into a multi-modal large model, generating an answer related to the query question and an image matched with the answer, and outputting the question answer with the image. According to the method, the capability of an original retrieval enhancement generation system is remarkably improved, and the information requirement of a user in an image-text environment is more comprehensively met.

The invention relates to the technical field of database retrieval, in particular to a knowledge database retrieval method based on feature extraction. The method comprises the following steps of obtaining a document to be retrieved, performing local hash de-duplication processing and extracting multi-modal features, performing feature spectrum clustering processing and associated entity analysis on the extracted features, generating a feature associated entity structure, performing document topic modeling and semantic direction positioning, and extracting a semantic topic of the document. The method comprises the following steps: performing word vector retrieval on a to-be-retrieved document and a knowledge database by utilizing a document semantic topic, generating word vector retrieval data, performing sentence vector retrieval, generating a final document retrieval result, integrating word vectors and the document retrieval result, and executing feature retrieval of the knowledge database through an intelligent retrieval engine, thereby realizing efficient knowledge query. The knowledge database retrieval method is more intelligent and more accurate.

The invention relates to the technical field of business adaptation, in particular to a business adaptation degree intelligent analysis method and system combined with a customer portrait. The method comprises the following steps: firstly, collecting customer data from a plurality of data sources, then processing the collected data, extracting interest labels of customers, constructing a customer-interest label matrix, comprehensively evaluating the purchase ability and loyalty of the customers, updating the portraits of the customers according to the interest preferences of similar customers, and then collecting the business demand data of the customers. The method comprises the following steps: constructing a business demand model, quantifying the demand intensity of a customer, generating a demand score vector, matching a customer portrait with the demand score vector, calculating an adaptation degree score, generating personalized recommendation for the customer, preferentially recommending a product or service with the highest matching degree with the customer demand, and pushing related recommendation through multiple channels. And the satisfaction degree and the conversion rate of customers are improved. According to the invention, the resource utilization efficiency and the customer satisfaction are improved, so that more efficient enterprise operation and customer service are realized.

The invention discloses a short video advertisement putting optimization evaluation method based on deep learning, and relates to the technical field of advertisement putting, and the method collects user behavior data in real time, constructs a dynamic user portrait, enables an advertisement system to adjust the advertisement content and putting strategy in time according to the interest change of a user, improves the correlation of advertisements, and improves the advertisement putting efficiency. Meanwhile, user behavior mode data and advertisement content labels are subjected to multi-dimensional matching, and the matching degree of the advertisements and user interests is calculated by combining cosine similarity with a weighting algorithm, so that advertisement recommendation is more personalized and accurate, the advertisement click rate and conversion rate are greatly improved, and the advertisement recommendation efficiency is improved. Meanwhile, the optimal opportunity of advertisement display is defined by analyzing the exit tendency of the user and the advertisement clicking tendency, it is guaranteed that the advertisement can be displayed at the moment when the user is most likely to interact and click, and the problem of low conversion rate caused by poor opportunity in a traditional method is solved.

The invention provides a test case generation method and system based on a large model and retrieval enhancement generation, and the method comprises the steps: obtaining a software description document, carrying out text fragment segmentation and vectorization, and constructing a software knowledge base; obtaining and vectorizing a demand document, and recalling a content optimization demand document in the reference software knowledge base based on the retrieval enhancement generation framework; constructing a first Prompt instruction, and splitting the optimized demand document into demand fragments of different test points by using a large language model; and finally, constructing a second Prompt instruction for the demand fragment of each test point, generating a test case by using a large language model, and establishing a mapping relationship between each test point and the test case for linkage output. According to the method, the understanding ability of the large model on the demand document is effectively enhanced; meanwhile, the requirements are decomposed into test points, mapping is carried out on the test points and related test cases, and completeness and accuracy of the requirements and the test cases can be conveniently sorted.

The invention relates to the technical field of machine learning, in particular to a supervised time sequence water level data generation method and system and a storage medium. The method comprises the following steps: acquiring multi-source hydrological monitoring data; performing abnormal value identification and data preprocessing according to the hydrological monitoring data to generate standardized hydrological basic data; constructing a data generation model of the conditional generative adversarial network based on the standardized hydrological basic data; hydrological variable driven condition feature regulation and control are carried out on the data generation model, parameter optimization of the generation network is carried out, and hydrological adaptability enhanced condition input feature data are generated; and injecting the condition input characteristic data into the data generation model to generate initial water level time sequence data. According to the method, the rare extreme hydrological events are oversampled by using a hierarchical importance sampling and self-service method (Bootstrap), so that the performance of the generative model in rare event prediction is remarkably enhanced.

The invention relates to the technical field of knowledge maps, and discloses a knowledge map searching method and system based on local semantics and global communitization, and the method comprises the steps: extracting entities and relationships thereof from a knowledge map to construct an undirected graph; the undirected graph is divided into multiple levels of community information, and a community report is obtained by generating a community information table; selecting an instance triple containing data source information from the knowledge graph, constructing an instance triple information source table, extracting IDs, names and attributes of entities, and generating an entity attribute table to obtain an entity attribute vector table; key entities in a to-be-queried question are extracted and subjected to vector representation, the similarity between the key entities and an entity attribute vector table is calculated, first N related entities are selected to generate contexts (including an entity context, a relation context, a data source context and a community context), and finally a search result of the to-be-queried question is obtained. According to the method, the information related to the to-be-queried question can be accurately retrieved from the knowledge graph.

The invention discloses a knowledge tracking cold start optimization method and system based on a large language model, and belongs to the field of knowledge tracking. The method comprises the following steps: firstly, acquiring student answering records of an online learning platform, constructing a prompt template to enable a large language model to output question solving steps, labeling knowledge concepts, and generating a binary pairing relationship between the question solving steps and the knowledge concepts; secondly, taking the problem and the knowledge concept as heterogeneous graph nodes, establishing edge connection and generating a semantic embedding vector; then, a heterogeneous graph encoder is used in combination with a graph attention network and a jump knowledge mechanism, and final node embedding of knowledge concepts and problems is output. And finally, predicting the answer of the student to the target question by comparing, learning and training the answer prediction model. According to the method, the performance and accuracy of the knowledge tracking cold start stage on the online learning platform are effectively improved.

The invention provides a method for creating a structured document based on a deep learning model, and relates to the technical field of data processing, and the method comprises the steps: obtaining basic text information collected by a user, obtaining text data, fragmenting the text data, obtaining text fragmented data, and creating a structured document according to the text fragmented data. Analyzing the structures of the sentences in the paragraphs, determining keywords in the sentences, analyzing the logical relationship between the sentences in the paragraphs, associating the sentence keywords in the paragraphs, analyzing the association degree between the paragraphs in the chapters, identifying core keywords of the chapters, obtaining a chapter keyword data set, and analyzing the field involved in the text. The method comprises the steps of extracting field information of a text to obtain a text keyword data set, constructing a structured document model based on a graph neural network model, and inputting the text keyword data set and text data into the structured document model to obtain a structured document. According to the method, the structured document can be constructed through the deep learning model.

The invention relates to a tree neighbor context-based big language model RAG optimization method, which comprises the following steps of: reading a directory structure and content of a document, generating a corresponding directory tree, converting the directory tree into a Markdown format containing a title and a level, and automatically extracting according to a document template if no title exists; segmenting the document into knowledge blocks according to the priority; after the knowledge blocks are recalled, the context is expanded by using a tree adjacent context method, and a new knowledge block list is formed; grouping and sorting the expanded knowledge blocks according to document identifiers, splicing reference data based on different fields and confidence coefficients, and generating a character string set from the original document; and splicing prompt words by using the constructed reference data and the new knowledge block list, and sending the spliced prompt words to the large model for processing. According to the scheme, the performance and practicability of the large model in the information retrieval and answer generation process are comprehensively enhanced by optimizing context information, emphasizing key content, adapting to various document formats, improving user experience and the like.

The invention discloses a personalized medical record analysis recommendation method and system based on a patient portrait. The method comprises the following steps: S1, generating a preprocessed health data set; s2, according to the preprocessed health data set, detecting a health event of the patient through a predefined health event triggering rule and an event classification model; s3, based on the priority of the health event, setting a trigger condition to start an updating process of the patient portrait; s4, the preprocessed health data set is combined with health event information, and a dynamic patient portrait is generated through a multi-modal data fusion technology and a time sequence modeling technology; s5, calculating a similarity index and selecting an optimally matched similar medical record; s6, according to the intelligent medical record analysis result and the medical knowledge graph, a diagnosis and treatment suggestion for the current patient is generated in combination with the rule base. The intelligent level and the precision level of the personalized medical record analysis recommendation system are remarkably improved.

The invention provides an advertisement recommendation method and system based on deep reinforcement learning. The method comprises the following steps: receiving a real-time interaction signal of a user, analyzing time sequence characteristics in the real-time interaction signal to extract behavior characteristics of the user, and identifying a contextual model of the user; modeling the interest preference of the user to generate a personalized interest dynamic graph; performing intelligent exploration and decision processing on the optimal advertisement content and the corresponding pushing opportunity to obtain an advertisement recommendation strategy; calculating the optimal pushing opportunity corresponding to the optimal advertisement content from the optimal advertisement content and the corresponding pushing opportunity, and pushing the optimal advertisement content to the user based on the optimal pushing opportunity; establishing a real-time feedback mechanism to obtain an adjusted advertisement recommendation strategy; and performing comprehensive evaluation processing on the advertisement effect of the adjusted advertisement recommendation strategy to generate an advertisement effect evaluation result. According to the technical scheme provided by the invention, the flexibility and efficiency of advertisement recommendation can be improved.

The invention provides an unmanned aerial vehicle visual language navigation method based on large model task analysis, and the method comprises the following steps: S1, decomposing a navigation instruction into a plurality of sub-tasks through a navigation task analysis module, and obtaining the text features of the currently executed sub-tasks through a sub-task switching module after the sub-tasks pass through a text encoder; s2, utilizing a visual encoder to obtain visual features of a current subtask input front view image; and S3, acquiring navigation action output corresponding to each moment of the current subtask through a multi-mode encoder by utilizing the visual text features. According to the method, the interpretability and the accuracy of visual language navigation action decisions can be improved.

The invention relates to the technical field of financial services, in particular to a testing method and system based on financial environment stability. The method comprises the following steps: carrying out real-time state monitoring on a financial transaction system, and generating system state basic data; constructing a virtual test environment according to the system state basic data, and performing test scene adaptive configuration to generate test environment parameter data; performing multi-dimensional pressure test analysis on the test environment parameter data, calculating a system stability index, and generating stability reference data; performing dynamic load gradient processing according to the stability reference data to obtain system pressure gradient data; and performing risk level mapping on the system pressure gradient data to generate risk assessment mapping data. According to the invention, the virtual test environment is constructed and self-adaptive configuration is carried out, so that a real transaction scene can be simulated, the correlation and effectiveness of the test are improved, and the stable operation of the system under different pressure conditions is ensured.

The invention discloses a customer information resource integration analysis method and system based on big data, and relates to the technical field of customer information services, and the method comprises the steps: collecting customer multi-modal data, carrying out the preprocessing, extracting data features, and carrying out the customer emotion analysis according to the data features; clustering and layering the clients according to the client sentiment analysis result to generate client tags, constructing a knowledge graph based on the client tags, and performing personalized recommendation based on the knowledge graph; monitoring personalized recommendation feedback of the client in real time, and optimizing the knowledge graph based on the feedback; and generating a customer recommendation strategy based on the knowledge graph, and comprehensively forming a customer decision support report. According to the method, the CNN model and quantum analysis are combined for emotion analysis, so that the efficiency and accuracy of emotion analysis are greatly improved, clustering analysis and knowledge graph construction are synchronously performed based on emotion analysis and customer data for personalized recommendation, the accuracy and correlation of customer recommendation are improved, and the user experience is remarkably improved.

The invention discloses a live broadcast method and device for free matching combined e-commerce operation, and the method comprises the steps: S1, collecting and analyzing user data, and building a user portrait; s2, based on the user portrait and the real-time behavior data, generating and dynamically updating a personalized commodity recommendation list; s3, in the live broadcast process, the anchor displays a commodity combination effect and provides a real-time interaction function; s4, virtual reality and augmented reality technologies are adopted to realize virtual commodity display and trial; s5, analyzing the real-time behavior data of the user by using an improved collaborative filtering algorithm, and recommending related commodities; s6, analyzing the emotional tendency of the user in interaction by adopting a multi-modal fusion emotion analysis algorithm, and providing personalized interaction suggestions for the anchor; and S7, providing an integrated online shopping function, and supporting the user to seamlessly complete the purchase operation. Through the technical steps, the personalized shopping experience of the user is improved, the live broadcast interactivity is enhanced, and the method has the beneficial effects of high recommendation accuracy, strong participation sense of the user and the like.

The invention discloses a cross-modal image text retrieval method based on deep learning, and provides a novel cross-modal feature extraction and alignment framework, efficient cross-modal retrieval is performed by learning semantic representation of an image and a text in a common feature space, the framework comprises a plurality of modules, and in a feature extraction stage, the cross-modal feature extraction and alignment framework is used for extracting and aligning the images and the texts. BERT Tokenizer and BERT Embedding are adopted for text coding, and the image feature extraction is combined with a Faster R-CNN (Convolutional Neural Network) model and a ResNet-101 model, so that the dimensional consistency of image features and text features is ensured. In the feature alignment stage, fine-grained semantic alignment of image and text features is realized through an I2T Attention module and a T2I Attention module, and the cross-modal matching precision is remarkably improved. In the correlation scoring stage, a correlation scoring matrix is generated by calculating the similarity score between the image features and the text features, so that the accuracy of cross-modal matching is improved. And further optimizing the feature alignment effect through normalization and attention redistribution. In an optimization stage, the system innovatively adopts a shared semantic and sorting loss strategy, integrates an OpenCLIP model framework, efficiently mines a semantic relationship between an image and a text from unlabeled large-scale data through comparative learning, and shows strong transfer learning ability and inference precision.

The invention relates to the technical field of recommendation methods, in particular to a consumer behavior-based commodity recommendation method, which comprises the following steps of: extracting behavior sequence data including clicking, browsing, searching and purchasing from a user interaction behavior log in an e-commerce platform, and carrying out sequence data slicing on the behavior sequence data through a sequence data slicing technology; dividing the long-time behavior sequence of the user into a plurality of behavior segments with a long-term dependency relationship; generating a behavior context feature vector; based on the long-term dependency feature vector and the behavior context feature vector, constructing a context-based intention speculation model, speculating the long-term shopping intention of the user, and generating an intention vector of the user behavior; and through a multi-target optimization algorithm, generating a recommendation strategy meeting various targets, and applying the generated recommendation strategy to real-time recommendation. According to the method and the device, the personalized degree of recommendation is improved, and diversified requirements of the user can be better met, so that the satisfaction degree of the user is improved.

The invention discloses an intelligent retrieval management method and system based on OCR and document analysis, and relates to the technical field of intelligent retrieval management. The system comprises a document scanning and processing module, a semantic analysis and label generation module, a feature extraction and mapping module and a user demand analysis and retrieval module. The document scanning and processing module is used for converting a paper document into an image file by using a scanner and forming a text data set; the semantic analysis and label generation module performs semantic analysis on each text in the text data set to form a semantic label; the feature extraction and mapping module extracts keywords in the text data, generates word vectors of a keyword set, and constructs a mapping matrix of tags and text word vectors; and the user demand analysis and retrieval module analyzes the user demand data, generates a feature matrix queried by the user, evaluates the matching degree between the text data and the user demand, and sorts and outputs retrieval results.

The invention relates to the technical field of association retrieval, and discloses an internal and external network knowledge association retrieval method based on an RAG technology. The method comprises the following steps: S1, based on query content input by a user, retrieving matched entries from an enterprise internal knowledge base, and reducing a retrieval range through metadata filtering; and S2, converting internal retrieval results into vector representation through an embedded model, and sorting the results according to correlation on the basis of cosine similarity. By combining an enterprise internal knowledge base and external network search, the limitation that a traditional method only depends on a single data source is broken through, the coverage range of knowledge is remarkably expanded, professional and authoritative domain knowledge is provided for the enterprise internal knowledge base, and latest industry dynamic and open information is supplemented by external network search, so that the enterprise internal knowledge base and the external network search are combined, and the enterprise internal knowledge base and the external network search are combined. Through dynamic weight adjustment and a unified sorting algorithm, the most relevant data source can be preferentially selected according to user requirements, so that balance is achieved between content depth and breadth.

The invention is suitable for the technical field of health monitoring, and provides a health monitoring method and system based on time sequence Transform and data fusion, and the method comprises the following steps: collecting multi-modal biosensor data; carrying out asynchronous time processing and normalization processing on the acquired multi-mode biosensor data; extracting features from the processed multi-modal biosensor data by using TimesNet, forming an independent input channel by the data of each modal, performing feature extraction on the data of each modal, extracting time sequence features of different scales and abstract levels, and performing feature extraction on the extracted time sequence features of different scales and abstract levels; the extracted features are input into a time sequence Transform network for feature fusion, time sequence prediction and anomaly monitoring; carrying out online platform display on the obtained prediction data, and giving an alarm when abnormity exists in the prediction data; through the time sequence Transform model, the health state of the worker can be monitored in real time, potential abnormal behaviors can be found and diagnosed in time, and the safety management level is improved.

The invention discloses a virtual reality interaction method for constructing multi-modal fusion based on application scene features, and relates to the technical field of virtual reality. In order to solve the technical problem that in the prior art, when an existing multi-modal fusion technology is used for processing fusion of different modal data, the characteristic difference between different modals is large, the technical scheme provided by the invention comprises the following steps: acquiring and preprocessing multi-modal data; constructing a cross-modal knowledge enhancement network, extracting initial features, and enhancing the consistency and difference between visual and auditory features; important context information in fusion features is optimized and enhanced based on an optimization network of frequency spectrum and space attention; constructing an edge guide learning network, and combining the edge guide learning network to the tactile data; the visual, auditory and tactile features are fused and applied to a virtual reality scene; and optimizing the model through structural similarity loss, mean square error loss, significance weight loss and edge loss. The method is suitable for cooperative work of multi-modal features in a complex environment.

The invention discloses an intelligent question answering system and method for cross-domain knowledge reasoning, and relates to the technical field of intelligent question answering. In order to solve the problem that an existing intelligent question answering system is limited by technical shortages and cannot give satisfactory reply to a user in cross-domain question processing, the adopted scheme comprises the steps that a domain knowledge base construction module collects multi-domain knowledge data, and the multi-domain knowledge data is stored in a corresponding domain vector knowledge base after being preprocessed and vectorized; the user interaction module provides an interface, receives input, interacts and returns a result; the field identification module identifies the field and extracts key information by using a large language model; the knowledge retrieval module retrieves related information accordingly; the cross-domain knowledge reasoning module is used for reasoning a knowledge logic relationship of each domain and guiding a large language model to integrate fused knowledge; and the intelligent question-answering module generates prompt words, inputs the prompt words into the large language model to obtain a final response, and returns each result to the user interaction module for display. According to the method, knowledge from multiple fields can be processed, and the method is suitable for various different types of problems and scenes.