588 results about "Structured analysis" patented technology

The invention discloses a structured decision-making method based on multi-agent collaborative decision-making and reinforcement learning, and relates to the technical field of natural language processing, knowledge engineering and agent collaboration, and the method comprises the steps: receiving an original rule document, analyzing the document type, complexity and constraint conditions, and defining a task target and a success standard; and according to the task target, matching and scheduling the intelligent agent from the registered intelligent agent library, and further analyzing the capacity configuration of the intelligent agent for standby. Through the multi-agent cooperation and reinforcement learning technology, full-process automation of rule documents from input to structured analysis is realized, document types, complexity evaluation and constraint condition analysis can be automatically identified, and a clear task target and a success standard are generated; and the large language model generates a structured workflow according to task requirements and agent capabilities, so that the performability is ensured through logic verification, manual intervention is greatly reduced, and the processing efficiency and the system intelligence degree are improved.

The invention discloses an AI-based animation split script automatic generation and visual preview method and system, and the method comprises the following steps: 1, receiving a natural language script text inputted by a user, the natural language script text comprising scene description, role action, dialogue and shot indication information; step 2, performing semantic analysis and structured analysis on the script text based on a natural language processing technology, and identifying and extracting key narrative elements; by introducing an artificial intelligence technology, end-to-end automatic generation and interactive optimization from a character script to a dynamic split rehearsal video are realized, the system can deeply understand scenes, actions, role emotions and shot languages in the script, corresponding visual elements are automatically matched and generated, and the dynamic split rehearsal effect is improved. And the timeline and the rhythm conforming to the film and television grammar are constructed, so that the efficiency and the consistency of the split creation are greatly improved, and the professional threshold and the manufacturing cost are reduced.

The invention relates to the technical field of knowledge extraction, in particular to a knowledge graph construction method and system based on a large model, and the method comprises the following steps: obtaining a current input statement of a user through a dialogue state tracker, inputting the statement into a BERT intention classification model for domain label analysis, behavior type recognition and emotional tendency detection, and outputting a three-dimensional classification vector; and extracting entity lexical items and relation predicates based on an LSTM sequence tagging device, and generating an original semantic structural body. According to the method, intention classification, behavior recognition and emotion detection are fused through three-dimensional semantic analysis, semantic comprehension granularity is improved, dynamic entity disambiguation is combined with a Manhattan distance threshold value and dialogue history tracking, semantic boundaries are defined to reduce anaphora ambiguity, and cross-modal alignment is enhanced through relation predicate hierarchical clustering and knowledge base dynamic matching; generative reply and semantic coherence reordering collaboratively keep topic continuation, and structured analysis and unstructured generation closed loop optimize semantic output and interaction fluency.

The invention provides a literature structured extraction method and system based on artificial intelligence, and aims to solve the problem that information extraction is incomplete and inaccurate in an existing literature processing technology. Firstly, an original literature data set comprising a plurality of literature units is obtained and preprocessed to obtain a standardized literature data set; calling a pre-trained literature feature extraction model to process the standardized literature data, extracting content features and structural features of the literature units, based on the content features and the structural features of the literature units, executing structured analysis processing to generate a structured element set containing theme elements, logic relation elements and key information elements, and finally, storing the structured element set. And integrating and optimizing the structured element set to generate a final structured literature result containing the element association relationship, thereby realizing automatic and structured extraction of the literature information, improving the literature processing efficiency and accuracy, and providing a new way for intelligent management and application of the literature.

The invention provides an official document key abstract generation method and system based on multi-modal feature extraction, and relates to the technical field of multi-modal artificial intelligence generation, and the method comprises the steps: firstly obtaining text modal data, image modal data and table modal data of a to-be-processed official document, then carrying out the hierarchical semantic analysis processing of the text modal data, and obtaining a to-be-processed official document key abstract; the method comprises the following steps: generating a text semantic feature set, performing visual element extraction processing on image modal data, generating an image feature set, performing structured analysis processing on table modal data, generating a table feature set, and performing cross-modal alignment processing on the text semantic feature set, the image feature set and the table feature set. According to the method, the dynamic association feature sets among the text semantics, the image elements and the table elements are determined according to the text semantics, the image elements and the table elements, the three feature sets are subjected to multi-modal fusion processing according to the feature sets, the target abstract content of the to-be-processed official document is generated, complementarity of multi-modal information in the official document is fully utilized, and the generated abstract is more complete, accurate and targeted.

The invention relates to the technical field of natural language processing, and discloses a structure prompt-based reasoning collaborative SQL generation method. According to the method, a small model carries out structured analysis on natural language query and a target database mode, SQL substructures and combination sequence prompts are generated, a large model constructs a multi-path inference tree based on the prompts, and path nodes sequentially generate SQL substructure fragments. Top-k paths are screened through path node scores and path cumulative scores, comprehensive sorting is performed by applying a heuristic scoring function, and candidate SQL with the highest score is selected. And verifying and correcting the candidate SQL according to execution feedback, and outputting a final SQL result after ensuring that semantics and structures are correct. According to the method, the problems of insufficient reasoning ability of a small model, poor reasoning stability and illusion of a large model and the problems of Tree-of-Though reasoning path redundancy and frequent focus switching are solved, the reasoning reasonability and execution efficiency in a Text2SQL task are improved, and the method is suitable for an application scene from a complex natural language to structured query.

The invention discloses a document link construction and evolution relation tracking method based on fragment-level semantic alignment, which relates to the technical field of document management, and comprises the following steps: carrying out structured analysis on a plurality of input documents, and dividing the document content into a plurality of semantic fragments; performing vectorization processing on each semantic fragment, and constructing a document-fragment-vector semantic mapping relationship; different document fragment-level semantic alignment is realized through cross-document semantic vector similarity calculation, a position offset tolerance algorithm and context association analysis, and a semantic link network is established; fusing the link relationship, the timestamp, the version information and the author information, and constructing a document evolution diagram taking the documents or fragments as nodes and evolution links as edges to record semantic flow paths between the documents; and outputting the semantic link network and the document evolution diagram in a structured form. The method can solve the problems that semantic relations between documents are missing, evolution paths are invisible, content reuse cannot be traced, and the structure induction capability is insufficient.

The invention discloses a document compliance judgment method based on violation traceability path scoring, and relates to the technical field of data compliance review, and the method comprises the following steps: carrying out structured analysis on a to-be-detected document, splitting the document content into semantic units, and identifying sensitive information entities contained in the semantic units; constructing a violation traceability path from the sensitive information entity to the regulation terms; performing scoring calculation on the violation tracing path, and determining a violation risk level of the path based on attributes of each node and edge in the path; on the basis of a path scoring result, matching corresponding regulation clause contents, extracting original text contents, clause numbers, application conditions, law domain classification information and punishment suggestions of the regulation clauses from the regulation knowledge graph, and generating an interpretable causal chain description; and outputting a violation result report. According to the method, the problems of non-traceable compliance basis, opaque violation judgment, lack of explanation support of risk grading and the like in the existing document review technology are solved.

The invention discloses a self-correction structured bid evaluation guide method for public resource transaction, and relates to the field of resource transaction processing, the method is based on a bid evaluation system, and the method comprises a data preprocessing unit, a structured analysis unit, a rule unit, an intelligent evaluation unit, a workflow management unit, a report generation unit and a data filing unit. Historical similar project scoring data is analyzed based on a large language model through an intelligent review unit, a real-time scoring reference interval is generated, expert experience and data driving are combined, professional judgment is reserved, scoring randomness is reduced through data quantification, a workflow management unit adopts an LSTM neural network to construct a review behavior prediction model, and the review behavior prediction model is used for predicting the review behavior. According to the method, the degree of deviation between expert scores and predicted values is compared in real time, meanwhile, multi-party review cases are integrated based on federal learning to form a dynamic knowledge base, review after the event is changed into real-time monitoring and intelligent intervention, the objectivity of bid evaluation is enhanced, and subjective item scores tend to be standardized.

The invention discloses an equipment state monitoring and anomaly analysis strategy method and system based on a PMS, and belongs to the technical field of equipment management.The method comprises the steps that equipment basic information, real-time operation state data, historical maintenance records and risk level parameters in an equipment management system are obtained, a comprehensive equipment state data set is generated, and a dynamic health attention index is calculated; and generating a strategy chain instruction set to schedule the sensor group to execute data acquisition operation, generating a target monitoring data set, inputting the target monitoring data set into the multi-stage adaptive analysis tree in combination with an analysis strategy instruction, generating a structured analysis report, and matching maintenance decision suggestions from the maintenance knowledge base and outputting the maintenance decision suggestions when a preset condition of a decision triggering strategy instruction is met. According to the method, the dynamic health attention index is adopted to drive strategy chain instruction generation, and the multi-stage adaptive analysis tree hierarchical diagnosis and closed-loop parameter optimization mechanism is combined, so that accurate distribution of monitoring resources, accurate positioning of fault root causes, economic optimization of maintenance decision and adaptive continuous upgrading of the system can be realized.

The invention relates to the field of constructional engineering, and discloses an intelligent construction management and control method for constructional engineering, which comprises the steps of collecting multi-dimensional data of a building construction site, including construction progress data, personnel positioning information, an equipment operation state and site environment parameters, and constructing a construction behavior feature data set in combination with a multi-source data fusion algorithm; performing automatic structured analysis on the construction behavior feature data set, constructing a construction process modeling framework based on a hierarchical feature clustering method, and introducing a dynamic feedback learning mechanism to perform adaptive optimization on a modeling result; judging whether the optimization process is stable or not according to the evolution trend of the process model, and if so, recording the stage state of the current construction process feature; and based on the corrected construction plan path, performing disturbance factor correction on the prediction progress by applying a multi-scale construction simulation algorithm, extracting corresponding control parameters, and performing intelligent adjustment on prediction nodes. The method has the advantage of improving intelligent construction management.

The invention relates to the technical field of medical image processing, and discloses a human body abdominal fat analysis method based on a medical image, which comprises the following steps: acquiring multi-modal medical image data such as CT (Computed Tomography), MRI (Magnetic Resonance Imaging) and ultrasonic images, constructing a fusion database through multi-scale affine transformation alignment, de-noising by using a model based on a residual self-encoder, and enhancing a boundary in combination with Canny edge detection. A segmentation model is constructed based on an improved U-Net architecture, multi-modal features are fused, and a dynamic convolution kernel and a channel attention mechanism are used for optimization. A quantitative analysis model is established by adopting a multi-task joint learning framework, gradient conflicts are solved, and a lightweight sub-network is searched and generated. Carrying out uncertainty modeling on the segmentation model, and carrying out active learning annotation to optimize the performance. A multi-granularity feature fusion framework is designed, anatomical priori knowledge is embedded to construct an association graph, a structured analysis report is generated, abdominal fat can be accurately analyzed, and diagnosis and treatment of obesity-related diseases are assisted.

The invention provides an automatic network protocol testing method and system based on a large language model. According to the method, through three core technologies of structured protocol specification extraction, hybrid test case generation and retrieval feedback enhanced code generation, full-process automation from a protocol specification document to an executable test code is realized. The method comprises the following steps: firstly, carrying out preprocessing and structured analysis on an RFC document, and extracting protocol field information and state machine description; a complete test case covering normal, abnormal and boundary conditions is automatically generated based on protocol elements; and finally, an initial test code is generated in combination with a test equipment API document retrieval result, and multi-round iterative optimization is performed through running log analysis and an experience knowledge base. Compared with the prior art, according to the scheme, an end-to-end automatic test work chain is achieved, new protocol testing can be adapted without manual protocol modeling, meanwhile, a large language model and expert experience are fused through a feedback mechanism, and the test efficiency and the code quality are remarkably improved.

The invention discloses a remote sensing image semantic segmentation method and system based on a dynamic attention mechanism, and relates to the technical field of remote sensing image processing, and the method comprises the following steps: carrying out the labeling and enhancement processing of a multi-scene remote sensing image, and generating a standardized data set; processing the data set through an encoder, and extracting a multi-scale high-dimensional feature map; decoding the multi-scale high-dimensional feature map, and fusing a decoding result with scale features to generate an optimized feature map; based on the optimized feature map, adopting a joint loss function to synchronously optimize segmentation, detection and classification tasks; performing dynamic up-sampling and boundary refinement on the optimized feature map, and outputting a structured analysis result; according to the method, the boundary information of the ground objects in the remote sensing image is accurately extracted through a dynamic processing flow and introduction of a double-flow decoder network and a multi-task joint optimization strategy, accurate segmentation and classification of the ground objects in a complex scene are achieved, and the overall effect of analysis and processing of the remote sensing image is improved.

The invention discloses a real-time place name and address multi-language translation system and method based on a neural network model, and relates to the technical field of multi-language translations, and the method comprises the steps: firstly extracting a topological relation of address components through structured analysis, and then carrying out the deep modeling of cross-component context dependence through employing a deep learning-based neural network model, deep semantic representation of the address text is mined through cross-component semantic association learning, and place name disambiguation based on dynamic semantic reasoning is realized based on the deep semantic representation; according to the method, the problem of semantic deviation in complex scenes such as homonymy, different places and different names is solved, the accuracy of judging the ambiguity of geographic entities is remarkably improved, the translation result can dynamically adapt to place name expression habits of different languages, translation ambiguity caused by limitation of a static knowledge base or imperfect rules is effectively eliminated, and the translation efficiency is improved. And a more accurate multi-language address conversion effect is achieved.

The invention provides an industrial T-MOD module working state visualization method and system, and the method comprises the steps: carrying out the time dimension preprocessing and multi-dimensional feature analysis of original operation data collected by a T-MOD module, and generating a multi-dimensional dynamic feature vector, the method comprises the following steps: acquiring a multi-dimensional dynamic feature vector of a T-MOD module, constructing a digital twin three-dimensional model corresponding to the T-MOD module according to the multi-dimensional dynamic feature vector, inputting the multi-dimensional dynamic feature vector into a pre-trained large language model, performing semantic recognition and potential anomaly analysis on the running state of the T-MOD module, and generating structured analysis data; and generating a three-dimensional dynamic visual interface in the digital twin three-dimensional model according to the structured analysis data. According to the scheme, the working state of each component of the T-MOD module can be detected in real time through the three-dimensional dynamic visual interface, the manual inspection cost is effectively reduced, and the fault detection efficiency is improved.

The invention discloses a memory enhancement and task planning method and system for large-model multi-agent. The method comprises the steps of performing structured analysis on historical task data, extracting planning experience and an abstract mode, and constructing and indexing an external memory library; retrieving related experience and modes from a memory library based on the new task description, and generating a memory enhanced task planning book; the planning scheme is distributed to a multi-agent network to be executed, an actual execution track is monitored and recorded, and the deviation between the actual execution track and the planning expectation is calculated; and evaluating the planning scheme based on the execution result and the deviation, extracting a planning correction rule, and updating the experience and the rule of the task to a memory bank. By introducing an external memory and closed-loop learning mechanism which can be dynamically evolved, the problems that existing system planning lacks experience guidance, knowledge cannot be precipitated and reused, and planning and execution are disjointed are solved, and the planning quality, the system reusability and the self-adaptive optimization capability are remarkably improved.

The invention relates to the field of digital emergency management, and provides a plan digitization method and system based on a large model technology, and the method comprises the steps: creating a multi-stage label system of a pre-configuration industry; when the user instruction has the tag features in the multi-level tag system, generating a cue word template guided by the domain knowledge corresponding to the tag features; receiving a cue word template through a preset cue word information large model, executing structured analysis of the unstructured plan, and generating a first digital instruction set; and obtaining error correction backflow data of the first digital instruction set, updating the cue word large model and the corresponding model interface fine tuning through the error correction backflow data, and generating a second digital instruction set after model structure fine tuning.

The invention provides a water conservancy knowledge structured extraction and verification method and device, and belongs to the technical field of artificial intelligence, and the method comprises the steps: carrying out the differential text processing of different formats of files, and generating an intermediate file; classifying the intermediate file into a regulation class or a non-regulation class based on a preset rule base; performing hierarchical title identification on the regulatory files to form entry knowledge blocks, and converting table contents into HTML (Hypertext Markup Language) knowledge blocks; performing semantic segmentation on the non-regulation file to generate knowledge blocks; performing knowledge block checking and filing, and marking an abnormal alarm block; converting the table knowledge blocks into natural language description by utilizing a large model; and positioning the context of the original text of the alarm knowledge block, and performing intelligent correction through a large model. According to the method, a traditional semantic analysis model and a large language model are creatively fused, a closed-loop process of preprocessing, extraction, verification and correction is formed, the problems of structured analysis and error correction of complex texts in the water conservancy field are solved, and the knowledge processing efficiency and accuracy are remarkably improved.

The invention relates to the technical field of computer vision, image recognition and intelligent medicine management, in particular to a medicine bottle label content recognition method based on multiple cameras and YOLOv8. The method at least comprises the following steps: S1, deploying a medicine bottle label generation system, and generating a label; s2, multi-camera image acquisition and preprocessing; s3, carrying out chessboard calibration and space positioning; s4, medicine bottle label detection and label character recognition and structured analysis; and S5, system integration and application. According to the invention, through combination of multi-camera and multi-angle acquisition and checkerboard calibration positioning and combination with YOLOv8 label detection and OCR identification, high precision, high efficiency, end-to-end automation and system integration of medicine bottle label identification are realized, the defects of precision, efficiency, environmental adaptability and management integration in the prior art are overcome, and the system is suitable for popularization and application. The method has obvious technical advantages and practical value.

The invention provides an automatic consumption tag analysis system and method based on multi-agent collaboration, and the system comprises a data processing agent which is used for collecting data from a social media platform and carrying out the data preprocessing; the label identification intelligent agent is used for extracting consumption labels of different dimensions from the preprocessed data; the sentiment analysis agent is used for carrying out context modeling and sentiment tendency recognition and binding the recognized sentiment tendency to the corresponding consumption label; the label normalization agent is used for performing clustering and normalization processing on all consumption labels bound with emotional tendencies to generate a structured multi-layer label atlas; the central scheduling agent is used for scheduling other agents, generating a label analysis result by using the multi-layer label atlas and sending the label analysis result to the user; according to the invention, based on a multi-agent architecture, structured analysis is carried out on user tags, behavior attributes and consumption intentions in social media contents, so that high-precision and high-efficiency intelligent consumption insight is realized.

The invention provides a mathematical question and answer process teaching system, which comprises a user interaction module, a question analysis and standardization module, a cognitive diagnosis engine, a generative teaching module, a mathematical knowledge graph database and a user portrait database, teaching content and guiding questions are presented to the user in a multi-mode form; the question analysis and standardization module is used for performing semantic understanding and structured analysis on mathematical questions and generating standardized question description and at least one standard question solving path; according to the method, the structured reasoning of the knowledge graph is combined with the natural language generation ability of the generative AI, so that a closed loop from'problem solving 'to'diagnosis' to'heuristic teaching 'is realized, thinking blockage points of students can be accurately positioned and personalized tutoring can be provided like human teachers, and the learning efficiency and the autonomous thinking ability are remarkably improved.

The invention discloses a property operation report generation method and device based on multiple agents and a related medium, and the method comprises the steps: calling an intention recognition agent to carry out intention analysis, and then calling a task planning agent to carry out path construction and scheme solving; determining an execution sequence of tasks in combination with the task planning data to obtain task processing data; calling a data collection agent to carry out data collection on the task processing data to obtain primary processing data; and calling a code calculation agent to carry out code generation and model operation on the primary processing data, calling an outline making agent to carry out outline arrangement and report generation processing, calling a report writing agent to complete report packaging, and outputting a property operation report. According to the invention, the structured analysis result obtained through calculation is subjected to outline arrangement and report generation processing, and the property operation report is packaged and output, so that manual report arrangement is not needed, the process is simplified, and the report output efficiency is improved.

The invention provides a large model retrieval enhancement generation method fused with a multi-source knowledge base, and relates to the technical field of large model retrieval enhancement generation. The method comprises the steps that firstly, user query is analyzed, multiple implied independent retrieval intentions are recognized and separated, and a knowledge source identifier is distributed to each retrieval intention subtask based on a mapping rule; according to the method, related evidence fragments are acquired in parallel from a heterogeneous knowledge source library in a targeted manner, multi-level relation analysis is further performed on the original evidence fragments by introducing a cross validation engine, so that a structured evidence conflict graph is constructed, and then the evidence conflict graph is intelligently processed by applying a game theory excitation algorithm. The method comprises the following steps: obtaining an evidence set with internal consistency, forming a guide signal through structured analysis, and finally, inputting original user query, the synthesized evidence set and the guide signal into a large language model in combination with a pre-constructed cue word template to generate a final answer under constraint, so as to realize retrieval enhancement generation fused with multi-source knowledge base retrieval.

The invention provides a data lake construction method and system based on multi-source distributed data, and relates to the field of data lake construction. The method comprises the following steps: firstly, deploying a data acquisition agent at each node of a distributed data source and establishing a distributed collaborative mechanism, and performing structured analysis on data through the data acquisition agent to obtain data characteristics and establish a relationship between fields; and then semantic description information is constructed, and an RDF triple is generated based on the information and stored in a source end node. And then inputting the RDF triple into an ontology registration service for processing to generate a distributed ontology, and analyzing a corresponding relationship between the RDF triple and concepts in the distributed ontology to obtain a semantic equivalence rule and a mapping rule. And finally, organizing the distributed data sources into a unified data view according to the rules, establishing a distributed index, configuring an access permission, and finally constructing a data lake containing the unified data view, the distributed index and the access permission. According to the method, the performance bottleneck problem caused by centralized processing is avoided.

The invention discloses a power grid fault report decision verification method based on digital twin replay and an interpretable neural network, and relates to the technical field of intelligent operation and maintenance and artificial intelligence decision verification of a power system. According to the method, structured analysis of a fault report is generated through AI, power grid digital twinning simulation replay and neural network reasoning with characteristic interpretability are combined, report conclusions and simulation results are automatically compared, interpretability analysis such as SHAP and LIME is integrated, and transparent tracing and characteristic contribution degree quantitative verification of the fault report reasoning process are achieved. Compared with a traditional power grid fault report processing method depending on manual checking or black box AI model output, the method can achieve automatic consistency criterion verification and whole-process data traceability of a fault report reasoning conclusion, and the credibility, transparency and batch engineering application efficiency of a power grid operation and maintenance decision are effectively improved.

The invention discloses a mining equipment state prediction method based on digital twinning and multi-modal fusion, and relates to the technical field of intelligent operation and maintenance, and the method comprises the steps: inputting a multi-modal alignment working condition window sequence into a digital twinning mechanism link, carrying out the same-window ideal response deduction, outputting an ideal multi-modal response, and constructing a twinning dynamic residual error; meanwhile, segmenting a residual structure event to generate a residual event token set; positioning a multi-modal data fragment based on the residual event token set, executing cross-modal attention alignment, and performing topology propagation aggregation in combination with a mechanical topology observation mapping table to generate a topology constraint fusion table set; and inputting the topological constraint fusion table set into the graph neural network, carrying out message passing in combination with a mechanical topological graph, outputting a component state and a complete machine state, and packaging the component state and the complete machine state into a mining equipment state prediction set. According to the method, structured analysis of the twinborn dynamic residual error is realized, and the method is used for accurately positioning an abnormal event and improving the sensitivity and timeliness of state prediction.

The invention provides an intelligent conference management system, method and device based on a large model and a medium, and belongs to the technical field of computers. The system comprises a pre-meeting module used for automatically generating and sending a meeting invitation through an integrated enterprise schedule system, using telephone notification and IVR interaction to confirm a meeting participation form, and counting a meeting participation condition and a meeting arrival state; the in-conference module is used for collecting multi-source audios based on a microphone array in the conference process, transferring conference content in real time and generating subtitles in combination with a voice recognition technology, synchronously recording videos, recording process information of the conference, and performing structured analysis; and the post-conference module is used for extracting key indication information and backlogs in the process information of the conference, generating a standardized conference summary, automatically distributing tasks, tracking the progress and supporting semantic retrieval of historical conference records. According to the invention, a large model technology is utilized, and technologies of cloud computing, big data, artificial intelligence and the like are combined, so that automatic management of the whole conference process is realized.

The invention discloses a video compliance monitoring system based on multistage event aggregation, which adopts a distributed two-stage architecture of an edge end and a center end, the edge end realizes video stream acquisition, dynamic sampling, multi-modal AI structured analysis and video segmentation buffer storage, and pushes an analysis result to the center end in real time, and the center end receives data and then sends the data to the edge end. Through a three-stage analysis system including atomic event extraction, session scene recognition and cross-time-period violation detection, violation detection is completed, a backtracking video with a superimposed mark can be generated, and a violation record and a video URL are pushed to a service system, so that efficient analysis and accurate backtracking of video compliance monitoring are realized; the invention further relates to a video compliance monitoring method based on multi-level event aggregation.

The invention relates to a multi-level data collection method, system and device and a storage medium. The method comprises the steps that an engineering project cost file is received; performing structured analysis on the construction cost file of the engineering project, and extracting an original data field; performing term mapping processing on the original data field to generate a standardized data entity; and according to a preset project cost index system, carrying out hierarchical collection on the standardized data entities to generate a structured knowledge base, and storing the project cost file and the corresponding structured knowledge base into a data collection case library. The method has the effect of improving the data collection efficiency and accuracy of the engineering project cost file.