Electric power document autonomous review method and system fusing causal reasoning and compliance review

Abstract

The invention belongs to the technical field of intelligent document management and auditing in the electric power industry, and provides an electric power document autonomous review method and system fusing causal reasoning and compliance review. According to the technical scheme, obtained electric power document data is subjected to semantic analysis, and semantic representation of a document is obtained; based on the semantic representation of the document, performing event extraction on each sentence recognized in the document, and encoding each event to obtain the semantic representation of the event; constructing an initial event causal chain based on the semantic representation of the event; verifying the constructed initial event causal chain by adopting a causal reasoning algorithm, comparing each event in the verified causal chain and the incidence relation between the events with a power industry compliance rule, calculating a compliance score, and calculating the incidence relation between the events of which the compliance score is lower than a set score value or the incidence relation between the events of which the compliance score is lower than the set score value; and generating a correction suggestion, and generating a review report. And the efficiency and the accuracy of document review are obviously improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent document management and auditing in the electric power industry, and in particular to an autonomous review method and system for electric power documents integrating causal reasoning and compliance review. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] With the digital transformation and intelligent development of the power industry, the complexity and data volume of power document management and audit processes are increasing. The operation and maintenance, equipment management, engineering construction and other links of the power system will generate a large amount of document data, including equipment failure reports, project progress reports, audit reports, etc. These documents not only contain static descriptive information, but also often hide complex cause and effect relationships. For example, equipment failure may trigger a series of chain reactions, leading to power outages, project delays and even greater economic losses. Therefore, how to efficiently and accurately identify and review the cause and effect relationships in documents has become one of the urgent problems to be solved in the digital management of the power industry.

[0004] Most existing power document review methods rely on manual review of documents one by one, which not only consumes a lot of human resources, but also easily misses potential risks or compliance issues due to human negligence. Especially when dealing with large-scale documents across departments and projects, manual review is inefficient and has limited ability to analyze complex multi-cause and multi-effect relationships. This traditional method can no longer meet the needs of modern power systems for efficient and intelligent document management.

[0005] In order to solve the above problems, in recent years, large-scale pre-trained language models (LLMs) have made significant progress in the field of natural language processing. Through the training of massive corpus, LLM has the ability to deeply analyze complex semantics and understand events, relationships, and logic in the text. In particular, by combining causal reasoning technology and hypergraph models, LLM can further identify causal chains in texts and help users understand the complex relationships between events. However, the power industry has a strict system of regulations and standards. All power-related operations, construction, and auditing behaviors must comply with the requirements of relevant regulations. The current causal reasoning model does not consider the compliance inspection of the power industry, and cannot ensure that the identified causal chain meets the standards and regulatory requirements of the power industry, and does not meet the actual review needs. Summary of the invention

[0006] In order to solve at least one technical problem in the above background technology, the present invention provides an autonomous review method and system for power documents that integrate causal reasoning and compliance review. By constructing a fusion framework of causal reasoning and hypergraph model, combined with a compliance rule engine, it can automatically complete the causal relationship identification and compliance review of power documents, significantly improving the efficiency and accuracy of document review. This method can effectively meet the needs of complex document processing in the power industry and provide intelligent support for the digital transformation of power companies.

[0007] In order to achieve the above object, the present invention adopts the following technical solution: A first aspect of the present invention provides an autonomous review method for power documents integrating causal reasoning and compliance review, comprising the following steps: Based on the semantic representation of the document, events are extracted for each sentence identified in the document, and each event is encoded to obtain the semantic representation of the event; Construct the initial event causal chain based on the semantic representation of events; Use causal reasoning algorithms to verify the constructed initial event causal chain, compare each event and the correlation between events in the verified causal chain with the compliance rules of the power industry, calculate the compliance score, and generate correction suggestions for events or correlations between events with compliance scores lower than the set score value; Based on the verified causal chain that complies with the compliance rules of the power industry, the overall causal structure diagram of the power document is constructed, and a review report is generated.

[0008] Furthermore, the event-based semantic representation constructs the initial event causal chain, including: Combine the semantic representation of events with the causal hypergraph model to establish corresponding node relationships for each event; each event node represents a specific event, and the hyperedge represents the relationship between multiple event nodes; Use causal reasoning algorithms to perform causal reasoning on event nodes and construct causal relationships between events; The causal hypergraph model is used to perform multi-layer convolution calculations on the causal relationship network between events. The deep features of event nodes are learned in the hypergraph, and the features are transferred and aggregated in the hyperedges to obtain the complex causal chain in the document and the deep relationship between nodes, thereby identifying the core events and the relationship between core events. The initial event causal chain is constructed based on the identified core events and the relationships between core events.

[0009] Furthermore, a large language model is used to perform semantic analysis on the acquired power document data to obtain a semantic representation of the document.

[0010] Furthermore, the use of a causal inference algorithm to verify the constructed causal chain of initial events includes: Check whether the logic in each causal chain is reasonable, and exclude irrelevant or weakly causally related paths based on the calculated causal strength between each event; Analyze the timing and semantic information of each event node and its associated nodes, and delete the paths with logical inconsistencies or contradictions.

[0011] Furthermore, the calculation formula for the causal strength between events is: , in, X, Y, Z Represents different events or variables, X represents an external intervening event or variable, Y Represents a result event, that is, the target event of interest, Z Represents an intermediate variable or covariate, that is, a variable that may affect the causal chain. X and Y Other factors in the relationship between Indicates external intervention Events, events The probability of occurrence, Indicates an operation of "human intervention" or "influence". Indicates an event Z The probability of taking the value z, Express Z The sum of the conditional probabilities of all possible values ​​of . Further, the calculation formula of the compliance score is: , in, Indicates an event Compliance score, Indicates an event Regulatory standards The degree of conformity between them.

[0012] Furthermore, the method also includes: updating the parameters of the causal reasoning algorithm based on the causal relationship in the feedback reasoning chain or the misjudgment or omission in the compliance review.

[0013] A second aspect of the present invention provides an autonomous review system for power documents integrating causal reasoning and compliance review, comprising: A semantic parsing module, which is used to perform semantic parsing on the acquired power document data to obtain a semantic representation of the document; The initial causal chain construction module is used to extract events from each sentence identified in the document based on the semantic representation of the document, encode each event, and obtain the semantic representation of the event; the initial event causal chain is constructed based on the semantic representation of the event; The causal chain review module is used to verify the constructed initial event causal chain using a causal reasoning algorithm, compare each event and the correlation between events in the verified causal chain with the compliance rules of the power industry, calculate the compliance score, and generate correction suggestions for events or correlations between events with compliance scores lower than the set score value; The review report generation module is used to construct an overall causal structure diagram of the power document based on the causal chain that has passed verification and complies with the compliance rules of the power industry, and generate a review report.

[0014] A third aspect of the present invention provides a computer-readable storage medium.

[0015] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in the above-mentioned method for autonomous review of electric power documents integrating causal reasoning and compliance review.

[0016] A fourth aspect of the present invention provides a computer device.

[0017] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the method for autonomous review of electric power documents integrating causal reasoning and compliance review as described above are implemented.

[0018] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention innovatively proposes an autonomous review method for power documents that integrates causal reasoning and compliance review. Based on causal reasoning technology, it can accurately identify and construct a causal chain with multiple causes and effects, so as to better understand the logical relationship in the document; at the same time, the causal chain in the document is compared with the laws and regulations and standards of the power industry to ensure that the document content complies with the latest industry specifications, solves the problem of omissions in manual review, reduces compliance risks, and not only improves the quality and consistency of the review, but also helps users identify potential risk points, provides automated feedback and improvement suggestions, and further improves the quality and security of the document.

[0019] 2. The present invention proposes to combine semantic parsing and causal reasoning, which can quickly process and analyze a large number of power documents, greatly reducing the reliance on manual participation in document review, reducing the manpower cost of the enterprise, and improving the efficiency of the overall review process. At the same time, it can accurately identify the ability of causal relationships, especially in the complex causal chains commonly seen in power documents. Through hypergraph models and causal reasoning technology, it can accurately identify and construct causal chains with multiple causes and effects, such as chain reactions caused by equipment failures, so as to better understand the logical relationships in the documents.

[0020] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0022] Figure 1 It is a flow chart of an autonomous review method for electric power documents integrating causal reasoning and compliance review provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0024] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0025] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0026] The current causal reasoning model mentioned in the background technology does not take into account the compliance inspection of the power industry, and cannot ensure that the identified causal chain complies with the standards and regulatory requirements of the power industry, and does not meet the actual review needs.

[0027] The present invention aims to solve the complex causal relationship identification and compliance checking problems in power documents. The method first uses a semantic big model to perform deep semantic analysis on power documents to identify key events and causal relationships therein. By constructing a hypergraph model combined with causal reasoning technology, the system can automatically generate and verify the causal chain in the document. Subsequently, the compliance rule engine compares the causal reasoning results with the laws and regulations of the power industry, automatically performs compliance reviews of the documents, identifies potential logical loopholes and non-compliance factors, ensures that the identified causal chains meet the standards and regulations of the power industry, and generates detailed review reports and improvement suggestions. This method greatly improves the efficiency and accuracy of power document review, reduces the workload of manual review, and ensures that the documents meet the requirements of industry regulations.

[0028] Embodiment 1 This embodiment provides an autonomous review method for power documents integrating causal reasoning and compliance review, including the following steps: Step 1: semantically parse the acquired power document data to obtain the document semantic representation; In this embodiment, the power document data includes equipment failure reports, construction progress reports, audit files, etc. The documents usually use natural language to describe multiple events and their associations.

[0029] In this embodiment, a large language model (LLM), such as the GPT series model, is used for deep semantic analysis. LLM can capture the complex context and long-distance dependencies in the text, deeply understand the semantics of the event, and generate high-quality semantic vector representations.

[0030] The model will first process the document content into sentences, that is, divide the document into sentence units, so as to ensure that each sentence can be semantically parsed independently. Because the events and information in power documents are often scattered in multiple sentences, sentence processing can ensure that the semantic information of each sentence can be fully extracted.

[0031] The core semantics and implicit causal information of each sentence are deeply extracted through the contextual association capture model, which can be expressed as follows: , in, Indicates that the input text is analyzed through a large language model The generated hidden semantic vector not only contains the basic semantic information of the sentence, but also combines the association between events in the context to form a representation with semantic and causal information. This semantic representation is crucial for event recognition and causal reasoning unique to power documents, because events in power industry documents often have complex backgrounds and technical terms, and LLM can effectively identify and parse this information.

[0032] Step 2: Based on the semantic representation vector, perform event extraction on each sentence identified in the document to obtain the semantic representation of the event and the context information of the event; Encode each extracted event to generate a semantic representation of the event ; The goal of event extraction is to find those events or behaviors from the document that are critical to causal reasoning. For example, in a power equipment failure report, common key events may include "equipment failure", "equipment maintenance", "fault repair", etc.; in a construction progress report, it may involve events such as "construction delay", "project progress", and "resource scheduling". Each event is not just a simple word or phrase, but also involves the semantic context of the event and its potential relationship with other events. LLM encodes the semantic meaning of events by generating semantic vectors. The system encodes these events to prepare for the subsequent causal reasoning steps.

[0033] During event recognition, the system uses contextual information to enhance the representation of events. .

[0034] For example, an event "equipment failure" identified in a sentence may mention related events such as "power outage" or "maintenance" in subsequent sentences. When constructing event vector representations, the system combines this contextual information to enhance the expressiveness of each event node, so that the representation of each event contains not only the independent information of the event, but also its potential association with other events. This process enables the semantic vector representation to describe the causal relationship between events at a deeper level.

[0035] In order to ensure the accuracy and completeness of the semantic representation of events, each event is encoded. This process is carried out by combining the contextual representation of the event with its own semantic representation to generate a comprehensive event representation vector. This can be described by the following formula: , in, represents the semantic representation of the event, while is the semantic representation of its context. The system combines these two pieces of information to generate a comprehensive event representation , which contains both the information of the event itself and the relationship and context of the event with other events in the document.

[0036] In this way, the system is able to extract structured event nodes and their associated semantic information from power documents. These event nodes and semantic representations provide a key foundation for causal reasoning, enabling the system to build and verify causal chains in subsequent steps.

[0037] Step 3: Construct the initial event causal chain based on event semantic representation; The introduction of the hypergraph model enables the system to capture more complex multi-cause and multi-effect relationships in documents, especially the complex associations commonly found in power industry documents. For example, an equipment failure event may lead to multiple results at the same time, such as power grid outages and project delays. At the same time, multiple events (such as equipment aging and insufficient maintenance) may jointly lead to a result (such as equipment failure). The hypergraph model can simulate complex causal structures well.

[0038] The specific steps include: Step 301: Add each event node in the document to the causal hypergraph model to identify the causal relationship of the events in the document; Each event node represents a specific event, while a hyperedge represents the relationship between multiple nodes. Unlike traditional graph models, the hypergraph model allows one edge to connect multiple nodes, so that it can represent a situation where multiple events jointly lead to a result. The system uses the event semantic representation generated in step 1 to combine the event with the hypergraph structure, establish corresponding node relationships for each event, and enable the model to better capture the complex causal chain structure in the document.

[0039] Step 302: Use a causal reasoning algorithm (such as CausalNLP or DoWhy) to perform causal reasoning on these event nodes to construct event causal relationships; The goal of causal reasoning is to reveal the causal dependencies between events by analyzing the relationships between nodes and constructing causal chains. For example, the system can deduce the causal relationship between "grid outage" and "project delay" from the "equipment failure" event. Specifically, the causal reasoning algorithm analyzes the timing and association of each event and generates causal relationships using a causal reasoning model. This reasoning process uses the generation capability of a large language model (LLM) to express the reasoning results as a natural language causal chain description, making the logic of the causal chain clear and understandable.

[0040] Step 303: perform deep modeling on the causal relationship, identify the core events in the causal chain and the relationship between the events, and construct the initial event causal chain; In order to further model the causal chain in depth, a hypergraph convolutional neural network (HGCN) is used to perform convolution calculations on the causal network. The introduction of HGCN can effectively handle the multi-node association problem in the hypergraph, and aggregate and learn the features of event nodes and their hyperedges through convolution operations.

[0041] Specifically, the aggregation and propagation of node features are achieved through the following formula: , in, Represents the hypergraph convolutional network in l The node representation obtained by the layer is is the incidence matrix of the hypergraph, and are the degree matrices of nodes and hyperedges respectively, is the weight matrix, To learn the parameters, is the activation function.

[0042] The hypergraph convolutional network can capture the complex associations between event nodes in a document. Through multi-layer convolution calculations, HGCN can learn the deep features of event nodes in the hypergraph structure, and transfer and aggregate these features between hyperedges, thereby learning the global causal structure in the document in the hypergraph.

[0043] After multiple layers of hypergraph convolution, the system can capture the complex causal chains and deep relationships between nodes in the document, and then identify the core events in the causal chain and their associations. For example, the system can not only identify the direct causal relationship of "power grid outage" caused by "equipment failure", but also identify intermediate events in the causal chain, such as "improper maintenance" may be one of the causes of equipment failure. Through multiple layers of feature aggregation operations, the hypergraph convolutional network can effectively mine the key nodes and paths in complex causal relationships, ensuring that the system can fully understand the causal logic in the document.

[0044] Step 4: Verify the constructed causal chain, and use the verified causal chain as the final causal chain; In this process, the system first needs to extract events and their associated paths from the hypergraph model. The hypergraph model has identified potential causal relationships through multi-node association and convolution operations, and the goal of this step is to further refine and verify the causal chain so that the final output causal chain is not only logically clear, but also accurately reflects the actual causal relationship in the document.

[0045] During the specific processing, the system will start from each central event (such as equipment failure) and gradually expand outward to find other nodes associated with the event. Through the hyperedges in the hypergraph, the system can identify causal paths where multiple events may work together. For example, equipment failure may not only cause a power outage, but also cause a project delay. In this case, the causal chain will contain multiple intermediate links, describing the complete path of the event from the cause to the final result. The generated causal chain not only contains direct causal relationships, but may also reveal hidden multi-level causal relationships.

[0046] Furthermore, the system uses causal reasoning algorithms to verify the generated causal chain.

[0047] During the verification process, causal reasoning algorithms (such as CausalNLP or DoWhy) mainly check whether the logic in each causal chain is reasonable and exclude irrelevant or weakly causally related paths. By analyzing the timing and semantic information of each event node and its associated nodes, the system can evaluate the rationality of the causal chain. If the system finds that the association paths between certain events have weak causality, or that some links in the association paths are logically contradictory or inconsistent, the system will automatically exclude these paths to ensure that the causal chain finally identified is logically clear and reasonable. When verifying the causal chain, the system relies on the core formula of causal reasoning for calculation. The system uses the following formula to calculate the causal strength between each event in the causal chain: , in, X, Y, Z Represents different events or variables, X An event or variable that represents an external intervention, usually one that controls or influences. Y Represents a result event, that is, the target event of interest, Z Represents an intermediate variable or covariate, that is, a variable that may affect the causal chain. X and Y Other factors in the relationship between Indicates external intervention Events, events The probability of occurrence, Denotes a "human intervention" or "influence" operation used to eliminate confounding factors in order to assess the effect of pure cause The causal effect of Indicates an event Z The probability of taking the value z, Express Z The sum of the conditional probabilities of all possible values ​​of .

[0048] For example, when X Indicates a device failure. Y Represents project delay. Through this formula, the system can estimate the impact of intervening in a certain event on other events and evaluate the credibility of its causal chain. The system can determine whether there is a clear causal relationship and the strength of the relationship by calculating the causal effect of "equipment failure" on "project delay".

[0049] During the verification process, the system will also carefully analyze the intermediate links in the chain. For example, if an intermediate event in the causal chain (such as "insufficient equipment maintenance") is the common cause of multiple final results (such as "project delay" and "grid outage"), the system will further analyze these multiple causes and multiple results to ensure that each link in the causal chain has a reasonable explanation.

[0050] In addition, the system will combine the structural information in the hypergraph model to optimize and simplify the redundant paths in the causal chain. For example, if there are different association paths between multiple events, the system will select the most logical and realistic path and prune the redundant paths. This process is completed through further reasoning and calculation of the causal reasoning algorithm to ensure that the final causal chain is both complete and concise.

[0051] Step 5: Conduct compliance review of the causal chain; The core of this step is to compare the generated causal chain with the latest laws, standards and operating procedures of the power industry through the compliance rule engine to ensure that the events and their associations in each causal chain comply with industry standards. Compliance review is particularly important for the power industry, because operations involving safety, construction, maintenance, etc. must strictly comply with relevant laws and regulations to avoid potential safety hazards and legal risks.

[0052] The specific steps include: The system calls the compliance rule engine, which contains the latest laws, standards, and operating procedures of the power industry. These laws and regulations may cover all aspects from equipment operation to construction management. For example, the safety standards of the power industry, the operating specifications of power equipment, the requirements of construction management, and other important laws and regulations involving project compliance. By storing these laws and regulations in a structured manner, the rule engine can automatically compare them with the causal chain to determine whether the events in the chain meet the relevant legal requirements.

[0053] During the compliance check, the system reviews each event and its relationship in the causal chain one by one. To ensure that each step in the chain complies with industry regulations, the system performs specific rule checks for each event.

[0054] For example, in the causal chain caused by power equipment failure, the system will check whether the relevant equipment maintenance standards are followed, whether regular inspections are carried out as required, and whether safe operating specifications are met during the event handling process. The system uses a formula to calculate whether each event complies with industry regulations. The formula is expressed as: , in, Indicates an event Compliance score, Indicates an event Regulatory standards The degree of conformity between Through this formula, the system can quantify the degree of match between each event and relevant regulatory standards, thereby determining whether it is compliant. When the compliance score is high, it means that the event node meets most regulatory requirements; otherwise, it indicates that the event may have a risk of violation.

[0055] For each pair of event associations in the causal chain, the system also performs compliance checks for logical consistency. The system verifies whether these relationships meet the logical requirements of regulations through the rule engine to ensure that the event associations in the causal chain are reasonable and compliant. For example, if a decision in the causal chain fails to fully consider potential risks (such as failure to take remedial measures in accordance with regulatory requirements in the event of a project delay), the system will mark these non-compliant parts through the rule engine and automatically generate prompts to indicate the specific violation clauses.

[0056] Another important function of the compliance rule engine is the ability to provide intelligent correction suggestions based on regulatory requirements in different scenarios. When the system detects that certain events or relationships in the causal chain do not meet regulatory standards, the rule engine automatically generates improvement suggestions based on the best practices of industry regulations. For example, the system may recommend increasing the frequency of inspections during equipment maintenance or adding contingency measures to project plans to reduce risks and ensure compliance.

[0057] Specifically, if the compliance score of an event node If it is below a certain threshold, the system will automatically generate prompts and give rectification suggestions to help users optimize the decision-making process.

[0058] Through the above steps, the system can generate a comprehensive compliance review report for the causal chain. The system not only marks the non-compliant parts, but also provides improvement suggestions to help users correct violations in a timely manner. This compliance review process effectively improves the reliability and security of the causal chain, making the final causal chain more accurate both logically and legally. By combining the natural language description generated by LLM, the system can output detailed compliance check results, allowing users to clearly understand each violation and its rectification measures, providing strong support for the standardized management of documents in the power industry.

[0059] Step 6: Generate an audit report based on the compliance audit results; After completing the identification of the causal chain and compliance review, the large language model LLM integrates all the information and generates a detailed review report in a structured manner with the assistance of RAG knowledge base enhancement, etc., to help users fully understand the causal logic and compliance status in the document.

[0060] The specific steps include: Step 601: extract the causal chain after compliance check; Each causal chain has been verified to ensure its logical consistency and compliance with the regulatory requirements of the power industry. Therefore, the system will build an overall causal structure diagram of the document based on these chains. This causal structure shows the complete path from the initial event (such as equipment failure) to the final result (such as project delay or power grid outage), and marks each intermediate event and its relationship.

[0061] Step 602: List the compliance assessment results of each causal chain in detail in the report.

[0062] This part not only includes the logic verification of each chain, but also scores and explains the compliance of each event node. Specifically, the system will use the previous compliance check formula , for each event A compliance score is given and it is noted whether the event fully complies with the relevant power industry regulations. If certain events or paths do not comply with regulatory requirements, the system will clearly mark these non-compliant parts in the report and explain the specific clauses that have been violated.

[0063] Step 603: For the identified non-compliant parts, the system will provide detailed feedback and improvement suggestions.

[0064] For example, if a risk point in a causal chain is not fully considered, the system will automatically generate suggestions through the compliance rule engine to remind users to add more preventive measures when dealing with such issues. The system proposes specific modification plans based on industry best practices and regulatory standards to help users better adjust the content of the document. This part of the report usually includes specific operational suggestions, such as "increase the frequency of regular equipment inspections" or "add emergency measures to the project plan", etc., to ensure that users can effectively deal with potential risks.

[0065] During the report generation process, the system will not only ensure the integrity of the report content, but also support multiple output formats according to user needs. The review report can be exported in multiple formats such as PDF and Word, which is convenient for users to review and save in different environments. In addition, the format and content structure of the report can be customized according to different application scenarios to ensure that the report not only meets the standard requirements of the power industry, but also has practicality and readability.

[0066] Against the backdrop of the accelerated digital transformation of the power industry, as the volume and complexity of documents increase, the system can efficiently process and manage a large number of documents to meet the needs of future intelligent management. Through the identification of causal chains and compliance checks, the system can also reveal potential risks in documents, helping managers better understand the content of documents and the basis for decision-making, thereby providing intelligent support for the management and operation of power systems and reducing risks in operations. These benefits make this patent of great application value, and can help the power industry achieve more efficient, smarter, and more compliant operational management.

[0067] Step 7: Continuously optimize the system’s causal reasoning accuracy and compliance review efficiency through user feedback.

[0068] The system has entered the closed-loop optimization stage. The core of the process is to continuously optimize the accuracy of the system's causal reasoning and the efficiency of compliance review through user feedback. After reading the review report, users may find that some problems are not accurately identified by the system, or that there are misjudgments and omissions in the causal relationship or compliance review in some reasoning chains. These feedbacks will become the basis for further improvement and optimization of the system.

[0069] The first step in the process is for users to provide feedback on the generated review report. Users can directly annotate parts of the system that are incorrectly identified or not fully processed through the interactive interface. For example, users may find that the system has not identified an important event node or has not considered certain potential risk points. These user annotations and feedback will serve as input data for system improvement.

[0070] Furthermore, the system analyzes user feedback to identify specific improvement needs.

[0071] The system will input the user's feedback data into the Large Language Model (LLM) for natural language processing, and extract key points related to system reasoning and review. For example, if user feedback points out that there are unreasonable causal relationships in certain causal chains, the system will automatically identify the problem nodes in these causal chains and use them as optimization priorities.

[0072] To enhance the adaptability of the model, the system uses the following formula to update the parameters of the inference model: , in, are the parameters of the causal inference model, is the learning rate, Based on user feedback data Compute the loss function.

[0073] Using this formula, the system can use the back-propagation algorithm to adjust the model parameters, thereby reducing the errors or biases indicated in the feedback and improving the accuracy of causal reasoning.

[0074] At the same time, the system can also continuously improve the compliance rule engine through user feedback. If user feedback indicates that certain regulatory standards are not applied accurately or fail to consider certain specific scenarios, the system will update the regulatory library accordingly and optimize the comparison algorithm of the rule engine. For example, if the regulations in a certain region change and the system is not updated in time, user feedback can help the system automatically retrieve and update the relevant regulations to ensure the real-time and accuracy of compliance checks.

[0075] In addition, the system will use user feedback to further expand the knowledge base and semantic understanding capabilities of the large language model. By incorporating the content of user feedback into the knowledge base data of the LLM, the system can gradually improve its semantic parsing and causal reasoning capabilities in specific scenarios in the power industry. For example, if the user feedback involves professional terms for specific equipment or operating procedures, the system can embed the semantics of these terms into the semantic space of the LLM, so as to more accurately understand and process subsequent similar documents.

[0076] Through this optimization cycle, the system can gradually improve the accuracy of its causal reasoning and the efficiency of compliance review, and continue to improve over time. In this stage, users are not only users of the system, but also participants in system improvement. By learning from user feedback, the system can gradually expand its applicability and intelligence level to ensure that it can still maintain efficient and accurate performance when facing more diverse power document scenarios.

[0077] Finally, after processing each user feedback, the system will generate a new review report again and feed back the improved reasoning and review results to the user. This closed-loop optimization process can continuously improve the performance of the system, and as the feedback data accumulates, the system will become more and more intelligent, reducing the possibility of errors and omissions, making it more valuable and practical in document review in the power industry.

[0078] Embodiment 2 This embodiment provides an autonomous review system for electric power documents integrating causal reasoning and compliance review, including: A semantic parsing module, which is used to perform semantic parsing on the acquired power document data to obtain a semantic representation of the document; The initial causal chain construction module is used to extract events from each sentence identified in the document based on the semantic representation of the document, encode each event, and obtain the semantic representation of the event; the initial event causal chain is constructed based on the semantic representation of the event; The causal chain review module is used to verify the constructed initial event causal chain using a causal reasoning algorithm, compare each event and the correlation between events in the verified causal chain with the compliance rules of the power industry, calculate the compliance score, and generate correction suggestions for events or correlations between events with compliance scores lower than the set score value; The review report generation module is used to construct an overall causal structure diagram of the power document based on the causal chain that has passed verification and complies with the compliance rules of the power industry, and generate a review report.

[0079] Embodiment 3 This embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the method for autonomous review of electric power documents integrating causal reasoning and compliance review as described above.

[0080] Embodiment 4 This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the method for autonomous review of electric power documents integrating causal reasoning and compliance review as described above are implemented.

[0081] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0082] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0083] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0084] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0085] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0086] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An autonomous review method for power documents integrating causal reasoning and compliance review, characterized in that: The steps include: Perform semantic analysis on the acquired power document data to obtain the semantic representation of the document; Based on the semantic representation of the document, events are extracted for each sentence identified in the document, and each event is encoded to obtain the semantic representation of the event; Construct the initial event causal chain based on the semantic representation of events; Use causal reasoning algorithms to verify the constructed initial event causal chain, compare each event and the correlation between events in the verified causal chain with the compliance rules of the power industry, calculate the compliance score, and generate correction suggestions for events or correlations between events with compliance scores lower than the set score value; Based on the verified causal chain that complies with the compliance rules of the power industry, the overall causal structure diagram of the power document is constructed, and a review report is generated.

2. The method for autonomous review of electric power documents integrating causal reasoning and compliance review as claimed in claim 1 is characterized in that: The event-based semantic representation constructs an initial event causal chain, including: Combine the semantic representation of events with the causal hypergraph model to establish corresponding node relationships for each event; each event node represents a specific event, and the hyperedge represents the relationship between multiple event nodes; Use causal reasoning algorithms to perform causal reasoning on event nodes and construct causal relationships between events; The causal hypergraph model is used to perform multi-layer convolution calculations on the causal relationship network between events. The deep features of event nodes are learned in the hypergraph, and the features are transferred and aggregated in the hyperedges to obtain the complex causal chain in the document and the deep relationship between nodes, thereby identifying the core events and the relationship between core events. The initial event causal chain is constructed based on the identified core events and the relationships between core events.

3. The method for autonomous review of electric power documents integrating causal reasoning and compliance review as claimed in claim 1 is characterized in that: A large language model is used to perform semantic analysis on the acquired power document data to obtain the semantic representation of the document.

4. The method for autonomous review of electric power documents integrating causal reasoning and compliance review as claimed in claim 1 is characterized in that: The verification of the constructed causal chain of initial events by using the causal inference algorithm includes: Check whether the logic in each causal chain is reasonable, and exclude irrelevant or weakly causally related paths based on the calculated causal strength between each event; Analyze the timing and semantic information of each event node and its associated nodes, and delete the paths with logical inconsistencies or contradictions.

5. The method for autonomous review of electric power documents integrating causal reasoning and compliance review as claimed in claim 4 is characterized in that: The calculation formula for the causal strength between events is: ， in, X, Y, Z Represents different events or variables, X represents an external intervening event or variable, Y Represents a result event, that is, the target event of interest, Z Represents an intermediate variable or covariate, that is, a variable that may affect the causal chain. X and Y Other factors in the relationship between Indicates external intervention Events, events The probability of occurrence, Indicates an operation of "human intervention" or "influence". Indicates an event Z The probability of taking the value z, Express Z The sum of the conditional probabilities of all possible values ​​of .

6. The method for autonomous review of electric power documents integrating causal reasoning and compliance review as claimed in claim 1, characterized in that: The compliance score is calculated as: ， in, Indicates an event Compliance score, Indicates an event Regulatory standards The degree of conformity between them.

7. The method for autonomous review of electric power documents integrating causal reasoning and compliance review as claimed in claim 1, characterized in that: The method also includes: updating the parameters of the causal reasoning algorithm based on the causal relationship in the feedback reasoning chain or the misjudgment or omission in the compliance review.

8. The power document autonomous review system integrating causal reasoning and compliance review is characterized by: include: A semantic parsing module, which is used to perform semantic parsing on the acquired power document data to obtain a semantic representation of the document; The initial causal chain construction module is used to extract events from each sentence identified in the document based on the semantic representation of the document, encode each event, and obtain the semantic representation of the event; the initial event causal chain is constructed based on the semantic representation of the event; The causal chain review module is used to verify the constructed initial event causal chain using a causal reasoning algorithm, compare each event and the correlation between events in the verified causal chain with the compliance rules of the power industry, calculate the compliance score, and generate correction suggestions for events or correlations between events with compliance scores lower than the set score value; The review report generation module is used to construct an overall causal structure diagram of the power document based on the causal chain that has passed verification and complies with the compliance rules of the power industry, and generate a review report.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the method for autonomous review of electric power documents integrating causal reasoning and compliance review as described in any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the method for autonomous review of electric power documents integrating causal reasoning and compliance review as described in any one of claims 1-7 are implemented.

Images