A Traceability Method and System Based on the Production Information of Power Enterprises

Abstract

The present invention discloses a traceability method and system based on production information of power enterprises, including content recognition of a number of production information data matching the target power enterprise to obtain initial information data; successively processing the initial information data based on the constructed large language model and classification model to obtain information data sets corresponding to different information dimensions; traversing the information data sets based on the depth-first search algorithm to obtain the entity information and attribute information corresponding to each information data set, and determining the first relationship result between the information data sets corresponding to different information dimensions; comparing the first relationship result with the second relationship result identified by the knowledge graph to obtain the target relationship result data; inputting the target relationship result data into the traceability model for processing to obtain each traceability information log of the target power enterprise. The method provided by the embodiments of the present invention realizes effective traceability of the production information of power enterprises.

Description

Technical Field

[0001] The present invention relates to the technical field of power enterprise production information data processing, and in particular, to a tracing method and system based on power enterprise production information. Background Art

[0002] In the field of power production management, power production involves a large amount of equipment, projects, maintenance records, and safety hazard information, and the demand for the interaction and query of these data is increasing.

[0003] Currently, the tracing methods in the field of power construction mainly rely on clerks in power enterprises to manually query relevant paper documents to track the production information of power enterprises. However, this method is time-consuming and laborious, and the tracing efficiency is low, and the accuracy is also difficult to guarantee. Information omission or error often occurs due to human factors, which cannot meet the requirements of modern power enterprises for efficient and accurate information tracing.

[0004] Therefore, how to effectively trace the production information of power enterprises has become a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0005] The present invention provides a tracing method and system based on power enterprise production information to solve the technical problem of low current tracing efficiency and to promote the process of intelligent and automated processing of power enterprise production information data.

[0006] To solve the above technical problem, an embodiment of the present invention provides a tracing method based on power enterprise production information, including:

[0007] Performing content recognition on a number of production information data matching the target power enterprise to obtain initial information data;

[0008] Successively processing the initial information data based on a constructed large language model and a classification model to obtain information data sets corresponding to different information dimensions, where the information dimensions at least include power enterprise personnel, power enterprise projects, and power enterprise equipment;

[0009] Traversing the information data sets based on the depth-first search algorithm to obtain entity information and attribute information corresponding to each information data set, and determining a first relationship result between the information data sets corresponding to different information dimensions according to the association matching characteristics between the entity information and the attribute information;

[0010] Comparing and analyzing the first relationship result with a second relationship result identified by a user-power knowledge graph to obtain target relationship result data of the target power enterprise;

[0011] Input the target relationship result data into the traceability model constructed by the hash algorithm for processing to obtain each traceability information log of the target power enterprise.

[0012] As one of the preferred solutions, before content recognition of a number of production information data matching the target power enterprise, the traceability method based on power enterprise production information further includes:

[0013] Train the constructed neural network recognition model based on the selected traceability sample data to obtain the original production information data;

[0014] Perform multi-label classification processing on the original production information data using a language representation model to determine whether the original production information data belongs to a number of production information data matching the target power enterprise; among them, the multi-label classification processing process includes:

[0015] Construct production information labels based on power enterprises;

[0016] Use the language representation model to train the original production information data to obtain the production information data to be recognized;

[0017] Use the association between the production information data to be recognized and the production information labels to determine whether it belongs to a number of production information data matching the target power enterprise.

[0018] As one of the preferred solutions, the types of the production information data at least include text, image, voice, and video;

[0019] The content recognition of a number of production information data matching the target power enterprise to obtain the initial information data includes:

[0020] Use a Chinese pre-training model based on the Transformer architecture to perform data cleaning processing on a number of the production information data to obtain noise-free data;

[0021] Perform word segmentation processing on the noise-free data based on the selected word segmentation method to obtain a word segmentation result;

[0022] Perform synonym standardization on the obtained power enterprise special dictionary and project named entity mapping table to obtain a power enterprise mapping relationship;

[0023] Process the word segmentation result according to the power enterprise mapping relationship to generate several types of standard production information data;

[0024] Integrate a number of the standard production information data to obtain the initial information data.

[0025] As one of the preferred solutions, the step of processing the initial information data based on the constructed large language model and classification model in sequence to obtain information data sets corresponding to different information dimensions includes:

[0026] Input the initial information data into the constructed large language model to obtain production information data to be classified;

[0027] Use the conditional random field classification algorithm to perform relation extraction processing on the production information data to be classified, and obtain information data sets corresponding to different information dimensions.

[0028] As one of the preferred solutions, the steps for constructing the traceability model include:

[0029] Extract responsibility traceability tags according to the user - power knowledge graph, where the responsibility traceability tags at least include user identity, operation time, operation type, and operation result;

[0030] Use the secure hash algorithm to perform hash calculation on the target relation result data to generate an operation log hash tree;

[0031] Perform label mapping processing on the nodes in the operation log hash tree and the responsibility traceability tags to obtain a label mapping result;

[0032] Construct a traceability model based on the operation log hash tree and the label mapping result.

[0033] As one of the preferred solutions, after obtaining the respective traceability information logs of the target power enterprise, the traceability method based on power enterprise production information further includes:

[0034] Perform screening processing on the traceability information logs to obtain a fault relation table;

[0035] Use the entropy weight method to calculate the weights of the fault relation table, obtain the fault correlation degree corresponding to the responsibility traceability tags, and determine the responsible object.

[0036] As one of the preferred solutions, after obtaining the respective traceability information logs of the target power enterprise, the traceability method based on power enterprise production information further includes:

[0037] Perform integrity verification of production information on the traceability information logs, where the integrity verification of production information is hash chain verification, and the process of hash chain verification includes calculating the hash value for each production information and comparing it with the hash value stored in the operation log hash tree. If the hash values do not match, it is determined that the data is abnormal.

[0038] As one of the preferred solutions, after obtaining the respective traceability information logs of the target power enterprise, the traceability method based on the production information of the power enterprise further includes:

[0039] Construct a local traceability database based on the respective traceability information logs of the target power enterprise, and determine visual interfaces for different information dimensions based on the local traceability database.

[0040] As one of the preferred solutions, after obtaining the respective traceability information logs of the target power enterprise, the traceability method based on the production information of the power enterprise further includes:

[0041] Use a natural language model to process the traceability information logs, generate a natural language report, and send it to the corresponding customer terminal for storage.

[0042] Another embodiment of the present invention provides a traceability system based on the production information of a power enterprise, including:

[0043] An identification module for content identification of a number of production information data matching the target power enterprise to obtain initial information data;

[0044] A processing module for successively processing the initial information data based on a constructed large language model and a classification model to obtain a set of information data corresponding to different information dimensions, where the information dimensions at least include power enterprise personnel, power enterprise projects, and power enterprise equipment;

[0045] A matching module for traversing the set of information data based on a depth-first search algorithm to obtain the entity information and attribute information corresponding to each set of information data, and determining the first relationship result between the sets of information data corresponding to different information dimensions according to the association matching characteristics between the entity information and the attribute information;

[0046] An analysis module for comparing and analyzing the first relationship result and the second relationship result identified from the user-power knowledge graph to obtain the target relationship result data of the target power enterprise;

[0047] A generation module for inputting the target relationship result data into a traceability model constructed by a hash algorithm for processing to obtain the respective traceability information logs of the target power enterprise.

[0048] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following:

[0049] Identify the content of a number of production information data that matches the target power enterprise to obtain the initial information data; sequentially process the initial information data based on the constructed large language model and classification model to obtain information data sets corresponding to different information dimensions, where the information dimensions at least include power enterprise personnel, power enterprise projects, and power enterprise equipment; traverse the information data sets based on the depth-first search algorithm to obtain the entity information and attribute information corresponding to each information data set, and determine the first relationship result between the information data sets corresponding to different information dimensions according to the association matching characteristics between the entity information and the attribute information; compare and analyze the first relationship result with the second relationship result identified by the user-power knowledge graph to obtain the target relationship result data of the target power enterprise; input the target relationship result data into the traceability model constructed by the hash algorithm for processing to obtain each traceability information log of the target power enterprise. Compared with the prior art, through a series of processing processes on a number of production information data that matches the target power enterprise, this method can solve the technical problem of low current tracking efficiency, realize the effective traceability of the production information of the power enterprise, and thus promote the process of intelligentization and automation of the production information data processing of the power enterprise. Brief Description of the Drawings

[0050] Figure 1 is a schematic flow chart of a traceability method based on power enterprise production information in one embodiment of the present invention;

[0051] Figure 2 is a schematic structural diagram of a traceability system based on power enterprise production information in one embodiment of the present invention;

[0052] Reference Signs:

[0053] Among them, 11, identification module; 12, processing module; 13, matching module; 14, analysis module; 15, generation module. Detailed Embodiment

[0054] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The purpose of providing these embodiments is to make the disclosure content of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present invention.

[0055] In the description of the present application, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise stated, the meaning of "a plurality" is two or more.

[0056] In the description of the present application, it should be noted that unless otherwise clearly defined and limited, the terms "installed", "connected", "connected to" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two components. The terms "vertical", "horizontal", "left", "right", "up", "down" and similar expressions used herein are only for the purpose of illustration and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be construed as a limitation of the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0057] In the description of the present application, it should be noted that unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those skilled in the technical field to which this technology belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0058] In the field of power production management, power production involves a large amount of equipment, projects, maintenance records, and safety hazard information, and the demand for the interaction and query of these data is increasing day by day.

[0059] Currently, the traceability method in the field of power construction mainly relies on clerks in power enterprises to manually query relevant paper documents to achieve the tracking of the production information of power enterprises. However, this method is time-consuming and laborious, and the tracking efficiency is low, and the accuracy is also difficult to guarantee. Often, due to human factors, information is omitted or incorrect, which cannot meet the needs of modern power enterprises for efficient and accurate information tracking.

[0060] For this reason, an embodiment of the present invention provides a traceability method based on the production information of power enterprises. Specifically, please refer to Figure 1 , Figure 1The flowchart of the traceability method based on the production information of power enterprises in one embodiment of the present invention is shown. The method includes:

[0061] S1: Identify the content of a number of production information data matching the target power enterprise to obtain initial information data;

[0062] S2: Process the initial information data based on the constructed large language model and classification model in sequence to obtain information data sets corresponding to different information dimensions, where the information dimensions at least include power enterprise personnel, power enterprise projects, and power enterprise equipment;

[0063] S3: Traverse the information data sets based on the depth - first search algorithm to obtain the entity information and attribute information corresponding to each information data set, and determine the first relationship result between the information data sets corresponding to different information dimensions according to the association matching characteristics between the entity information and the attribute information;

[0064] S4: Compare and analyze the first relationship result with the second relationship result identified from the user - power knowledge graph to obtain the target relationship result data of the target power enterprise;

[0065] S5: Input the target relationship result data into the traceability model constructed by the hash algorithm for processing to obtain the traceability information logs of the target power enterprise.

[0066] Before identifying the content of a number of production information data matching the target power enterprise, it is also necessary to judge the data, that is, to judge whether the production information data to be identified belongs to the production information data matching the target power enterprise. If it belongs, enter step S1 to start the traceability process of production information. The judgment process includes:

[0067] Step 1: Train the constructed neural network recognition model based on the selected traceability sample data to obtain the original production information data;

[0068] In this step, according to the characteristics of the selected traceability sample data and task requirements, a suitable neural network architecture can be selected, such as a fully - connected neural network, a convolutional neural network (CNN), a recurrent neural network (RNN), etc. The traceability sample data is divided into a training set, a validation set, and a test set for model training, validation, and testing. After training, the trained neural network recognition model is used to predict new production data to obtain the original production information data.

[0069] Step 2: Use a language representation model to perform multi - label classification processing on the original production information data to judge whether the original production information data belongs to a number of production information data matching the target power enterprise.

[0070] Specifically, in the above step two, according to the characteristics of the data and the task requirements, a suitable language representation model is selected. Commonly used models include pre-trained language models such as BERT and GPT, as well as fine-tuned versions based on these models. At the same time, before using the language representation model to classify the original production information data, the original production information data also needs to be pre-processed. The pre-processing process includes pre-processing steps such as cleaning, word segmentation, and stop word removal; the pre-processed data and the defined labels are used to train the language representation model. During the training process, the model will learn how to map the original production information data to the corresponding labels.

[0071] Specifically, the multi-label classification process includes:

[0072] Construct production information labels based on power enterprises, and use the language representation model to train the original production information data to obtain the production information data to be recognized;

[0073] Using the association between the production information data to be recognized and the production information labels, determine whether it belongs to a number of production information data that match the target power enterprise. That is to say, input the production information data to be recognized into the trained language representation model. The model will extract the feature vectors of the data to be recognized and map them to the predefined labels. By comparing the similarity between the feature vectors of the data to be recognized and each label, the model can determine whether the data to be recognized belongs to a certain label category. According to the classification result, determine whether the production information data to be recognized belongs to a number of production information data that match the target power enterprise. If the data to be recognized is classified into the label category related to the target power enterprise, it is considered to be a match; otherwise, it is considered to be a mismatch, and the result of the match judgment is output to the user or the system for subsequent processing or decision-making.

[0074] The types of production information data in step S1 at least include text, image, voice, and video.

[0075] Specifically, in step S1, the steps of content recognition for a number of production information data that match the target power enterprise to obtain the initial information data include:

[0076] Use a Chinese pre-trained model based on the Transformer architecture to perform data cleaning processing on a number of the production information data to obtain noise-free data;

[0077] Perform word segmentation processing on the noise-free data based on the selected word segmentation method to obtain the word segmentation result;

[0078] Perform synonym standardization on the obtained power enterprise-specific dictionary and project named entity mapping table to obtain the power enterprise mapping relationship;

[0079] Process the word segmentation results according to the power enterprise mapping relationship to generate standard production information data of several types;

[0080] Integrate several pieces of the standard production information data to obtain initial information data.

[0081] In this process, through a Chinese pre-trained model based on the Transformer architecture (such as BERT, ERNIE, etc.), the powerful semantic understanding ability of the model can be used to identify and remove noise in the production information data, such as invalid characters, redundant information, incorrect formats, etc. The cleaned data is cleaner and more accurate, providing a good foundation for subsequent steps such as word segmentation and standardization.

[0082] Segment the obtained noise-free data into meaningful words or phrases. This is a basic step in natural language processing. The word segmentation results can more clearly show the semantic structure of the data, facilitating subsequent tasks such as word frequency statistics, sentiment analysis, and named entity recognition; integrate and standardize synonyms in the power enterprise-specific dictionary and the project named entity mapping table, and establish specific mapping relationships for the special needs of power enterprises, which helps to more accurately understand and process relevant texts.

[0083] Use the power enterprise mapping relationship to map and replace the word segmentation results to generate production information data that complies with enterprise standards and specifications; integrate multiple pieces of standard production information data into a complete initial information data set. The integrated initial information data is more comprehensive and systematic, facilitating applications in scenarios such as production management and decision support in power enterprises.

[0084] In step S2, process the initial information data obtained in step 1 based on the constructed large language model and classification model in sequence to obtain information data sets corresponding to different information dimensions. Among them, the information dimensions at least include power enterprise personnel, power enterprise projects, and power enterprise equipment. Among them, the step of processing the initial information data based on the constructed large language model and classification model in sequence to obtain information data sets corresponding to different information dimensions includes:

[0085] Input the initial information data into the constructed large language model to obtain production information data to be classified; use the conditional random field classification algorithm to perform relationship extraction processing on the production information data to be classified to obtain information data sets corresponding to different information dimensions.

[0086] In step S2, the integrated initial information data is used as input, and the semantic understanding and generation capabilities of the large language model are utilized to preliminarily process and analyze the information. The output after being processed by the large language model is used as the production information data to be classified. These data have undergone reorganization and semantic refinement by the large language model, making it easier for subsequent classification and relationship extraction.

[0087] Conditional Random Fields (CRF) is a powerful tool for sequence labeling and segmentation tasks. In step S2, it is used to perform relationship extraction processing on the production information data to be classified.

[0088] Specifically, the purpose of relationship extraction is to identify entities (such as power enterprise personnel, power enterprise projects, power enterprise equipment, etc.) and the relationships between these entities from the text. Through the CRF algorithm, the entity boundaries and relationship types in the text can be accurately labeled.

[0089] After the relationship extraction processing, the original information is decomposed and classified under different information dimensions, forming information data sets corresponding to power enterprise personnel, power enterprise projects, power enterprise equipment, etc.

[0090] In steps S3 and S4, specifically, after obtaining the information data sets, the depth-first search algorithm is used to traverse the information data sets, and the entity information and attribute information corresponding to each information data set are obtained. The Depth-First Search (DFS) algorithm is an algorithm for traversing or searching trees or graphs. During the traversal process, the algorithm will identify and extract the entity information (such as power enterprise personnel, projects, equipment, etc.) and attribute information (such as personnel names, project names, equipment types, etc.) in each information data set. By using the association matching features between the entity information and attribute information (such as the same personnel name appears in different data sets, or the same project has different attribute descriptions at different stages, etc.), the algorithm can identify the potential relationships between the information data sets under different information dimensions. Based on these association matching features, the algorithm will generate a preliminary relationship result, that is, the first relationship result, which describes the connections and interactions between different information dimensions.

[0091] Specifically, the user - power knowledge graph is a known template composed of detailed information such as the organizational structure, personnel relationships, project progress, and equipment status of power enterprises. Comparing and analyzing the first relationship result with the second relationship result can verify and supplement the accuracy of the first relationship result, which helps to identify possible missing or incorrect relationships in the first relationship result.

[0092] Through comparison and analysis, the algorithm can integrate the information in the first relationship result and the second relationship result to generate a more comprehensive and accurate target relationship result data. The target relationship result data synthesizes information from different information dimensions and different data sources, providing a comprehensive and systematic view to display the internal structure and external relationships of the target power enterprise. This information is of great significance for aspects such as decision-making support, risk management, and project planning of power enterprises.

[0093] Input the target relationship result data obtained in step S4 into the traceability model constructed by the hash algorithm for processing, and various traceability information logs of the target power enterprise can be obtained.

[0094] Specifically, the construction steps of the traceability model include:

[0095] Extract the responsibility traceability tags based on the user-power knowledge graph. Among them, the responsibility traceability tags at least include user identity (such as username, user ID), operation time (the specific time point of the operation execution), operation type (such as reading data, modifying configuration, etc.), and operation result (whether the operation is successful, the specific impact generated, etc.); these tags are the basis for subsequent traceability analysis.

[0096] Use the secure hash algorithm (such as SHA-256) to perform hash calculation on the target relationship result data to generate an operation log hash tree. Through hash calculation, each log is converted into a unique hash value, and then the operation log hash tree is constructed. The hash tree is a data structure used to efficiently verify the integrity and consistency of data.

[0097] Perform label mapping processing on the nodes in the operation log hash tree and the responsibility traceability tags to obtain a label mapping result. Combine the structure of the operation log hash tree and the label mapping result to construct a traceability model. This model can support quickly finding and verifying the traceability information of specific operations or events. When tracing a certain operation or event, the corresponding node in the hash tree can be found, and then the detailed responsibility traceability information can be obtained according to the label mapping result.

[0098] In this way, it can ensure efficient and accurate traceability analysis of the operation logs of the target power enterprise, thereby improving the transparency and security of data management.

[0099] After obtaining various traceability information logs of the target power enterprise, the method further includes:

[0100] Filter the traceability information logs to obtain a fault relationship table; use the entropy weight method to calculate the weights of the fault relationship table to obtain the fault correlation degree corresponding to the responsibility traceability tags, and determine the responsible object.

[0101] Specifically, according to the preset screening criteria or rules, such as keywords or patterns like error codes, abnormal states, operation failures, etc. recorded in the logs, the traceability information logs are screened. Conditions such as time range and operation type can also be considered to further narrow down the screening scope.

[0102] The selected log entries will be organized into a fault relationship table. This table usually includes the time of the fault occurrence, the type of the fault, the devices or personnel involved, and relevant responsibility traceability labels (such as the operator, operation time, etc.). Establishing the fault relationship table helps to clearly show the association between the fault and each responsibility traceability label.

[0103] Based on the calculated fault correlation degree, the responsibility traceability labels most relevant to the fault occurrence can be identified. Through these labels, the responsible parties, such as specific personnel, departments, or devices, can be further determined. The determination of the responsible parties helps with subsequent fault handling, liability investigation, and the formulation of improvement measures.

[0104] After obtaining the various traceability information logs of the target power enterprise, the method further includes:

[0105] Perform integrity verification of production information on the traceability information logs. Among them, the integrity verification of production information is hash chain verification. The process of hash chain verification includes calculating the hash value for each piece of production information and comparing it with the hash value stored in the operation log hash tree. If the hash values do not match, it is determined that the data is abnormal.

[0106] That is to say, in the traceability information logs, for each entry containing production information, the above hash chain verification process is applied. If data anomalies are found, further measures can be taken, such as re-obtaining production information, marking abnormal data, triggering an alarm, etc. Through hash chain verification, it can be ensured that the production information in the traceability information logs has not been tampered with or damaged during transmission and storage, thus guaranteeing the integrity and accuracy of the data.

[0107] After obtaining the various traceability information logs of the target power enterprise, the method further includes:

[0108] Construct a local traceability database based on the various traceability information logs of the target power enterprise, and determine visual interfaces for different information dimensions based on the local traceability database.

[0109] After obtaining the various traceability information logs of the target power enterprise, the method further includes:

[0110] Use a natural language model to process the traceability information logs, generate a natural language report, and send it to the corresponding customer terminal for storage.

[0111] That is to say, the preprocessed logs are processed using a natural language model. During the processing, the natural language model extracts key information from the logs, such as fault descriptions, responsibility traceability tags, timestamps, etc., and integrates this information into a coherent narrative to generate a detailed natural language report. This report presents the core content of the traceability information log in a human-readable manner, and the information in the report is directly sourced from the traceability information log, ensuring the traceability and accuracy of the information.

[0112] Another embodiment of the present invention provides a traceability system based on power enterprise production information. Specifically, please refer to Figure 2 , Figure 2 which shows a schematic structural diagram of the traceability system based on power enterprise production information in one of the embodiments of the present invention. The structure includes:

[0113] An identification module 11 for content identification of a number of production information data matching the target power enterprise to obtain initial information data;

[0114] A processing module 12 for successively processing the initial information data based on a constructed large language model and a classification model to obtain information data sets corresponding to different information dimensions, where the information dimensions at least include power enterprise personnel, power enterprise projects, and power enterprise equipment;

[0115] A matching module 13 for traversing the information data sets based on a depth-first search algorithm to obtain entity information and attribute information corresponding to each information data set, and determining a first relationship result between the information data sets corresponding to different information dimensions according to the association matching characteristics between the entity information and the attribute information;

[0116] An analysis module 14 for comparing and analyzing the first relationship result and a second relationship result identified from a user-power knowledge graph to obtain target relationship result data of the target power enterprise;

[0117] A generation module 15 for inputting the target relationship result data into a traceability model constructed by a hash algorithm for processing to obtain each traceability information log of the target power enterprise.

[0118] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following:

[0119] Perform content recognition on a number of production information data matching the target power enterprise to obtain initial information data; sequentially process the initial information data based on the constructed large language model and classification model to obtain information data sets corresponding to different information dimensions, where the information dimensions at least include power enterprise personnel, power enterprise projects, and power enterprise equipment; traverse the information data sets based on the depth-first search algorithm to obtain entity information and attribute information corresponding to each information data set, and determine the first relationship result between the information data sets corresponding to different information dimensions according to the association matching characteristics between the entity information and the attribute information; compare and analyze the first relationship result and the second relationship result identified by the user-power knowledge graph to obtain the target relationship result data of the target power enterprise; input the target relationship result data into the traceability model constructed by the hash algorithm for processing to obtain each traceability information log of the target power enterprise. Compared with the prior art, through a series of processing processes on a number of production information data matching the target power enterprise, this method can solve the technical problem of low current tracking efficiency, realize the effective traceability of the production information of power enterprises, and thus promote the intelligent and automated process of power enterprise production information data processing.

[0120] The above embodiments merely represent several implementation manners of the present invention, and the description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several deformations and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the appended claims.

Claims

1. A traceability method based on the production information of power enterprises, characterized in that, Including: Performing content recognition on a number of production information data matching the target power enterprise to obtain initial information data; Successively processing the initial information data based on the constructed large language model and classification model to obtain information data sets corresponding to different information dimensions, where the information dimensions at least include power enterprise personnel, power enterprise projects, and power enterprise equipment; Traversing the information data sets based on the depth-first search algorithm to obtain entity information and attribute information corresponding to each information data set, and determining the first relationship result between the information data sets corresponding to different information dimensions according to the association matching characteristics between the entity information and the attribute information; Comparing and analyzing the first relationship result with the second relationship result identified by the user-power knowledge graph to obtain the target relationship result data of the target power enterprise; Inputting the target relationship result data into a traceability model constructed by the hash algorithm for processing to obtain each traceability information log of the target power enterprise, where the construction steps of the traceability model include: Extracting responsibility traceability tags according to the user-power knowledge graph, where the responsibility traceability tags at least include user identity, operation time, operation type, and operation result; Performing hash calculation on the target relationship result data using the secure hash algorithm to generate an operation log hash tree; Performing label mapping processing on the nodes in the operation log hash tree and the responsibility traceability tags to obtain a label mapping result; Constructing a traceability model based on the operation log hash tree and the label mapping result; After obtaining each traceability information log of the target power enterprise, it further includes: Performing integrity verification of production information on the traceability information log, where the integrity verification of production information is hash chain verification, and the process of hash chain verification includes calculating the hash value of each production information and comparing it with the hash value stored in the operation log hash tree. If the hash values do not match, it is determined that the data is abnormal.

2. The traceability method based on the production information of power enterprises according to claim 1, wherein Before performing content recognition on a number of production information data matching the target power enterprise, the traceability method based on power enterprise production information further includes: Training the constructed neural network recognition model based on selected traceability sample data to obtain original production information data; Performing multi-label classification processing on the original production information data using a language representation model to determine whether the original production information data belongs to a number of production information data matching the target power enterprise; where the multi-label classification processing process includes: Constructing production information labels based on power enterprises; Training the original production information data using the language representation model to obtain production information data to be recognized; Judging whether it belongs to a number of production information data matching the target power enterprise based on the association between the production information data to be recognized and the production information labels.

3. The traceability method based on power enterprise production information according to claim 1, characterized in that The types of the production information data at least include text, image, voice, and video; Performing content recognition on a number of production information data matching the target power enterprise to obtain initial information data, including: Using a Chinese pre-trained model based on the Transformer architecture to perform data cleaning on a number of the production information data to obtain noise-free data; Performing word segmentation on the noise-free data based on a selected word segmentation method to obtain a word segmentation result; Performing synonym standardization on the obtained power enterprise-specific dictionary and project named entity mapping table to obtain a power enterprise mapping relationship; Processing the word segmentation result according to the power enterprise mapping relationship to generate several types of standard production information data; Integrating a number of the standard production information data to obtain initial information data.

4. The traceability method based on the production information of power enterprises according to claim 1, characterized in that, The step of successively processing the initial information data based on the constructed large language model and classification model to obtain an information data set corresponding to different information dimensions includes: Inputting the initial information data into the constructed large language model to obtain production information data to be classified; Using a conditional random field classification algorithm to perform relationship extraction on the production information data to be classified to obtain an information data set corresponding to different information dimensions.

5. The traceability method based on the production information of power enterprises according to claim 1, wherein After obtaining each traceability information log of the target power enterprise, the traceability method based on power enterprise production information further includes: Performing screening on the traceability information log to obtain a fault relationship table; Using the entropy weight method to calculate the weight of the fault relationship table to obtain a fault correlation degree corresponding to the responsibility traceability label and determining the responsible object.

6. The traceability method based on the production information of power enterprises according to claim 1, characterized in that, After obtaining each traceability information log of the target power enterprise, the traceability method based on power enterprise production information further includes: Constructing a local traceability database based on each traceability information log of the target power enterprise, and determining a visualization interface for different information dimensions based on the local traceability database.

7. The traceability method based on the production information of power enterprises according to claim 1, wherein After obtaining each traceability information log of the target power enterprise, the traceability method based on power enterprise production information further includes: Using a natural language model to process the traceability information log to generate a natural language report and sending it to the corresponding customer terminal for storage.

8. A traceability system based on the production information of power enterprises, characterized in that, Including: An identification module for performing content recognition on a number of production information data matching the target power enterprise to obtain initial information data; A processing module for successively processing the initial information data based on the constructed large language model and classification model to obtain an information data set corresponding to different information dimensions, where the information dimensions at least include power enterprise personnel, power enterprise projects, and power enterprise equipment; A matching module for traversing the information data set based on a depth-first search algorithm to obtain entity information and attribute information corresponding to each information data set, and determining a first relationship result between the information data sets corresponding to different information dimensions according to the association matching characteristics between the entity information and the attribute information; An analysis module for comparing and analyzing the first relationship result and a second relationship result identified by a user-power knowledge graph to obtain target relationship result data of the target power enterprise; A generation module, configured to input the target relationship result data into a traceability model constructed by a hash algorithm for processing, so as to obtain each traceability information log of the target power enterprise, wherein the construction steps of the traceability model include: Extracting a responsibility traceability label according to the user-power knowledge graph, wherein the responsibility traceability label at least includes user identity, operation time, operation type, and operation result; Performing a hash calculation on the target relationship result data by using a secure hash algorithm to generate an operation log hash tree; Performing a label mapping process on the nodes in the operation log hash tree and the responsibility traceability label to obtain a label mapping result; Constructing a traceability model based on the operation log hash tree and the label mapping result; After obtaining each traceability information log of the target power enterprise, it further includes: Performing a production information integrity check on the traceability information log, wherein the production information integrity check is a hash chain verification, and the process of the hash chain verification includes calculating a hash value for each production information and comparing it with the hash value stored in the operation log hash tree. If the hash values do not match, it is determined that the data is abnormal.

Images