Verification method, device and equipment of power business system and medium

Abstract

The invention provides a verification method and device of a power business system, equipment and a medium, relates to the field of computers, and is used for solving the problem that the verification efficiency of the power business system is relatively low. The method comprises the following steps: constructing an index tree according to the latest policy text of the power industry; determining a target keyword set according to a function module of the power business system; searching in the index tree according to the target keyword set to obtain key statements related to the power business system; converting the key statement into an SQL statement; executing the SQL statement in a database of the power business system to obtain a verification result; the verification result is used for indicating whether the power business system is compliant. According to the method, the end-to-end conversion from the policy text to the SQL statement is realized, and the executable compliance verification logic is automatically generated, so that the verification efficiency of the power business system is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and provides a verification method, device, equipment and medium for a power service system. Background Art

[0002] A power service system refers to a professional information system that supports the production, operation, management and services of the power industry. With the continuous improvement of the requirements of the power grid industry for safe, stable and economic operation, the continuous introduction of new policies and new specifications has put forward higher requirements for the operation of the power service system. Compliance verification is not only a key step to ensure that the system complies with new policies and specifications, but also an important means to improve the safety and efficiency of the power grid and cope with future challenges.

[0003] Currently, the manual verification method is mainly used to verify the power service system according to the latest policy text, but the efficiency is low. Summary of the Invention

[0004] The present application provides a verification method, device, equipment and medium for a power service system, which is used to solve the problem of low verification efficiency of the power service system.

[0005] In a first aspect, a verification method for a power service system is provided, including: Construct an index tree according to the latest policy text in the power industry; Determine a target keyword set according to the function modules of the power service system; Retrieve in the index tree according to the target keyword set to obtain key sentences related to the power service system; Convert the key sentences into SQL statements; Execute the SQL statements in the database of the power service system to obtain a verification result; the verification result is used to indicate whether the power service system is compliant.

[0006] Optionally, the determining a target keyword set according to the function modules of the power service system includes: Extract basic keywords from the function modules of the power service system; Expand the basic keywords according to the power industry standard thesaurus to obtain expanded keywords; Obtain a target keyword set according to the basic keywords and the expanded keywords.

[0007] Optionally, the obtaining a target keyword set according to the basic keywords and the expanded keywords includes: Determine a similarity threshold according to the type of the policy text; Merge the basic keywords and the expanded keywords to obtain an initial keyword set; Calculate the semantic similarity between each keyword in the initial keyword set and the policy text, retain the keywords with a semantic similarity higher than the similarity threshold, and obtain the target keyword set.

[0008] Optionally, determining the similarity threshold according to the type of the policy text includes: If the type of the policy text is a legal provision, determine the first threshold as the similarity threshold; If the type of the policy text is a technical specification, determine the second threshold as the similarity threshold; If the type of the policy text is a notice or announcement, determine the third threshold as the similarity threshold; where the first threshold is greater than the second threshold, and the second threshold is greater than the third threshold.

[0009] Optionally, constructing an index tree according to the latest policy text in the power industry includes: Divide the latest policy text in the power industry into multiple paragraphs, generate vector representations of the multiple paragraphs through text embedding technology, and use the vector representations of the multiple paragraphs as leaf nodes; Cluster the vector representations of the multiple paragraphs to obtain multiple clusters; Generate a summary for each cluster through a large language model; Perform weighted averaging on the vector representations of the paragraphs in each cluster to obtain the vector representation of each cluster; Embed the summaries and vector representations of the multiple clusters into the upper-level nodes of the leaf nodes, and through recursive embedding until the root node is constructed to obtain the index tree; where the index tree contains multiple nodes, and each node contains a node index, child nodes, a summary, and a vector representation.

[0010] Optionally, clustering the vector representations of the multiple paragraphs to obtain multiple clusters includes: Use the vector representations of the multiple paragraphs as independent clusters; Calculate the fidelity between clusters using the swap test; Merge the two clusters with the maximum fidelity until the number of clusters reaches the preset number to obtain the clustered multiple clusters.

[0011] Optionally, converting the key sentences into SQL statements includes: Identify the fields and constraint types in the key sentences; Based on a predefined field mapping table, map the fields in the key sentences to the fields of the database table; If the constraint type is a numerical range constraint, generate an SQL statement with a BETWEEN condition or a comparison operator according to the fields of the database table; if the constraint type is an enumerated value constraint, generate an SQL statement with an IN condition according to the fields of the database table; if the constraint type is a regular constraint, generate an SQL statement for REGEXP matching according to the fields of the database table.

[0012] In a second aspect, a verification device for a power service system is provided, including: A construction module, configured to construct an index tree according to the latest policy text of the power industry; A determination module, configured to determine a target keyword set according to the functional modules of the power service system; A retrieval module, configured to retrieve in the index tree according to the target keyword set to obtain key sentences related to the power service system; A conversion module, configured to convert the key sentences into SQL statements; An inspection module, configured to execute the SQL statements in the database of the power service system to obtain an inspection result; the inspection result is used to indicate whether the power service system is compliant.

[0013] In a third aspect, the present application provides a computer device, which includes a memory and a processor. A computer program is stored in the memory, and the processor executes the computer program to implement the verification method for the power service system described in the first aspect.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and the processor executes the computer program to implement the verification method for the power service system described in the first aspect.

[0015] Compared with the prior art, the beneficial effects of the embodiments of the present application are as follows: The present application provides a verification method for a power service system, and the method includes: constructing an index tree according to the latest policy text of the power industry; determining a target keyword set according to the functional modules of the power service system; retrieving in the index tree according to the target keyword set to obtain key sentences related to the power service system; converting the key sentences into SQL statements; executing the SQL statements in the database of the power service system to obtain an inspection result; the inspection result is used to indicate whether the power service system is compliant.

[0016] It can be seen that this application can automatically match the relevant content of the latest policy text according to the target keyword set of the power business system, retrieve the relevant data in the database through SQL statements, automatically verify whether the power business system meets the latest policy requirements, reduce the cumbersome process of manual inspection, improve the verification efficiency, enable decision-makers to quickly obtain feedback on compliance, thus accelerating the decision-making process and avoiding risks and delays caused by compliance issues. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments or related technologies. Obviously, the drawings in the following description are only the embodiments of this application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on the provided drawings.

[0018] Figure 1 Schematic structural diagram of a computing device for the hardware operating environment involved in the solution of the embodiment of this application; Figure 2 Schematic flow diagram of the verification method for the power business system provided by the embodiment of this application; Figure 3 Schematic structural diagram of the index tree provided by the embodiment of this application; Figure 4 Schematic diagram of the formation of intermediate layer nodes provided by the embodiment of this application; Figure 5 Schematic structural diagram of the verification device for the power business system provided by the embodiment of this application.

[0019] Reference numerals in the figures: 101 - processor, 102 - communication bus, 103 - network interface, 104 - user interface, 105 - memory. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] To make the objectives, technical solutions, and advantages of this application clearer and more understandable, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all of them. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of this application. Without conflict, the embodiments in this application and the features in the embodiments can be combined arbitrarily with each other. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0021] To solve the problem of low verification efficiency of the power service system, an embodiment of the present application provides a verification method for the power service system, and this method can be executed by a computer device. Please refer to Figure 1 , which is a schematic structural diagram of a computer device for the hardware operating environment involved in the solution of the embodiment of the present application.

[0022] As Figure 1 shown, the computer device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Among them, the communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen (Display) and an input unit such as a keyboard (Keyboard). The user interface 104 may include a standard wired interface and a wireless interface. The network interface 103 may include a standard wired interface and a wireless interface (such as a wireless fidelity (WI-FI) interface). The memory 105 may be a high-speed random access memory (Random Access Memory, RAM) or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk memory. The memory 105 may also be a storage device independent of the aforementioned processor 101.

[0023] Those skilled in the art can understand that Figure 1 the structure shown in

[0024] does not constitute a limitation on the computer device, and it may include more or fewer components than shown in the figure, or combine some components, or have different component arrangements. Figure 1 As

[0025] shown, in the memory 105 as a storage medium, there may be included an operating system, a network communication module, a user interface module, and a verification device for the power service system. Figure 1 In the computer device shown in

[0026] Based on Figure 1 the computer device shown in Figure 2An introduction to a verification method for a power service system provided by an embodiment of the present application is as follows: S201. Construct an index tree according to the latest policy text in the power industry.

[0027] In the specific implementation process, the policy text is an official document issued by the government, organization or other management agencies, aiming to convey policy directions, regulations, decisions or action plans, and guide or regulate the behaviors and operations in relevant fields. For example, "Blue Book on the Development Plan of the National Unified Power Market". The latest policy text in the power industry can be obtained through ways such as downloading from the official website, being issued by the superior or relevant departments. The policy text can be in formats such as pdf, txt, word, web document, etc.

[0028] The types of policy text can be legal provisions, technical specifications or notices. The following will introduce them separately: 1. Policy text of legal provisions This type of text has legal effect and is mainly formulated by the government or legislative bodies, aiming to regulate the basic operations of the power industry and ensure the safety and stability of power supply. For example, legal texts related to the power market, electricity consumption management, environmental protection regulations, etc.

[0029] 2. Policy text of technical specifications This type of text mainly involves the technical requirements and standards in the power industry, usually issued by the state or relevant industry competent departments, aiming to ensure the safety, stability and sustainability of the power system.

[0030] 3. Policy text of notices This type of text is usually used to release information such as administrative measures, policy changes, management methods, etc., and has strong timeliness. They are usually issued by government departments or industry management agencies, aiming to notify power enterprises or the public about the latest trends or policy changes in the power industry. For example, the annual plan of the power industry, price adjustment announcements, policy implementation notices, etc.

[0031] In a possible embodiment, the specific steps of S201 include S1.1 - S1.6.

[0032] S1.1. Divide the latest policy text in the power industry into multiple paragraphs.

[0033] Specifically, after obtaining the latest policy text in the power industry, the corresponding preset rules can be determined according to the type of the policy text. The delimiters in the policy text are identified through the preset rules, and the policy text is divided into multiple paragraphs according to the delimiters. If the type of the policy text is a legal provision, the delimiters are "Article X", "Paragraph X", and the document number identification; if the type of the policy text is a technical specification, the delimiters are the power standard number (GB / T / DL, etc.) and the technical parameter table, and splitting across tables is prohibited; if the type of the policy text is a notice or announcement, the delimiters are the hierarchical serial numbers such as "(1)", "1.", etc.

[0034] Alternatively, a power policy corpus can be constructed. The power policy corpus contains multiple policy texts with manually marked paragraph boundaries. A semantic segmentation model is trained based on the power policy corpus, and then the trained semantic segmentation model is used to calculate the boundary probability between adjacent sentences in the policy text to generate multiple paragraphs.

[0035] S1.2 Generate vector representations of multiple paragraphs through text embedding technology, and use the vector representations of multiple paragraphs as leaf nodes.

[0036] Specifically, text embedding technology (such as models like Word2Vec, BERT, RoBERTa, etc.) can be used to convert each paragraph into a fixed-length vector representation, and the vector representation of each paragraph is used as a leaf node of the index tree. This method not only depends on the text content but also can identify semantically similar paragraphs, avoiding the limitations of traditional keyword-based retrieval.

[0037] S1.3 Cluster the vector representations of multiple paragraphs to obtain multiple clusters after clustering.

[0038] Specifically, a clustering algorithm can be used to cluster the vector representations of multiple paragraphs, and similar paragraphs are grouped into the same cluster. This can help the system better identify and organize semantically similar content, thereby supporting efficient multi-dimensional search. For example, when a user queries a topic related to a certain policy, the system can find the most relevant part by calculating the distance from the cluster center.

[0039] S1.4 Generate a summary for each cluster through a large language model.

[0040] Specifically, a large language model (such as GPT or T5) can be used to generate a summary for each cluster. The summary of each cluster generalizes the core content of all paragraphs in the cluster, which can reduce redundancy and extract the key points of the cluster.

[0041] S1.5 Perform weighted averaging on the vector representations of paragraphs in each cluster to obtain the vector representation of each cluster.

[0042] Specifically, the vector representations of all paragraphs in each cluster can be weighted averaged to generate the vector representation of each cluster. The weighted average can set weights according to the length, importance, or other metrics of the paragraphs to ensure that the most representative paragraphs within the cluster play a dominant role in the vector representation of the cluster.

[0043] S1.6. Embed the summaries and vector representations of multiple clusters into the node at the level above the leaf nodes, and through recursive embedding until the root node is constructed to obtain the index tree.

[0044] Specifically, embed the summary and vector representation of each cluster into the node at the level above the leaf nodes, and through recursive embedding, finally construct the index tree. The root node of the tree represents the overall content summary and vector representation of the policy text.

[0045] Among them, the index tree contains multiple nodes, and each node contains a node index, child nodes, a summary, and a vector representation. Please refer to Figure 3 , which is the structural schematic diagram of the index tree provided by the embodiment of the present application. Among them, A, B, C, D, and E are leaf nodes. Clustering the leaf nodes forms the intermediate layer nodes F, G, and H, and then clustering the intermediate layer nodes forms the root nodes I and J.

[0046] Please refer to Figure 4 , which is the schematic diagram of the formation of the intermediate layer nodes provided by the embodiment of the present application. Cluster A, B, C, D, and E, and the clustering result is: C and E are one cluster, A and D are one cluster, and B is one cluster. Merge C and E into F, merge A and D into G, and use B as H.

[0047] In the embodiment of the present application, by embedding the summaries and vector representations of multiple text paragraphs into a tree structure, a large amount of policy text can be effectively organized and indexed. When specific information needs to be searched, the system can more efficiently locate relevant content quickly according to the summary of the node, reducing unnecessary full-scale scans. By recursively embedding to construct the index tree level by level, it can be ensured that the high-level nodes can represent the essence of the entire document, which can improve the retrieval efficiency of policies related to a certain theme or field.

[0048] In a possible embodiment, clustering the vector representations of multiple paragraphs to obtain multiple clusters includes: using the vector representation of each paragraph as an independent cluster; calculating the fidelity between clusters using the swap test; merging the two clusters with the maximum fidelity until the number of clusters reaches the preset number to obtain multiple clusters after clustering.

[0049] In the specific implementation process, the quantum condensation hierarchical clustering algorithm is selected. Each sample (i.e., the vector representation of each paragraph) is initially considered as an independent cluster. The vector representation of each cluster is converted into a quantum state, and the fidelity between every two clusters is calculated using the swap test. The two clusters with the maximum fidelity are merged. Each merge updates the center of the cluster and recalculates the fidelity between every two clusters. Continue to select the pair of clusters with the highest fidelity for merging, and stop merging when the number of clusters reaches the preset number.

[0050] For example, the fidelity C i between cluster C j is defined as the maximum fidelity between all samples in cluster C i and the average value of all samples in cluster C j . The specific formula is as follows:

[0051] Where, L ij represents the fidelity between cluster C i and cluster C j , max represents the maximum value function, w i_t represents all samples in cluster C i , L is the number of samples in cluster C j , w j_k_t represents the k-th sample in cluster C j , and k is a positive integer from 0 to L - 1. represents the fidelity between all samples in cluster C i and the average value of all samples in cluster C j .

[0052] In the embodiments of the present application, considering that language words may have multiple meanings and need to be determined through context, and that a quantum has multiple states and needs to be determined through observation, the similarity between natural language and quantum mechanics is utilized to construct index trees of different summary levels through recursive embedding, quantum clustering, and text fragment aggregation. This can not only capture the high-level and low-level details of the text, but also improve the generation speed and aggregation accuracy of the index tree.

[0053] S201. Determine the target keyword set according to the functional modules of the power business system.

[0054] In the specific implementation process, the functional modules of the power business system can be a power generation module, a power transmission module, a power distribution module, a power marketing and billing module, a power dispatching and monitoring module, a power safety and protection module, etc. Further, core terms can be extracted from the functional modules of the above power business system to obtain basic keywords, and these basic keywords can be combined into a target keyword set. The basic keywords can be artificially defined based on the key business functions of the above functional modules. For example, the basic keywords corresponding to the power generation module can be power plants, power generation dispatching, electric energy production, power plant equipment, etc.; the basic keywords of other functional modules are the same, and will not be elaborated here.

[0055] Although the basic keywords can provide keywords for specific functional modules, they may not take into account the differences and diversities in other professional fields or regions within the industry. By expanding the basic keywords, more synonyms, variants, and related terms can be generated to enhance the diversity and accuracy of the keywords. In this way, during retrieval, not only can exact terms be matched, but also related terms can be found, avoiding information omission. Therefore, in a possible embodiment, the specific steps of S201 include: extracting basic keywords from the functional modules of the power business system; expanding the basic keywords according to the power industry standard thesaurus to obtain expanded keywords; and obtaining a target keyword set based on the basic keywords and the expanded keywords.

[0056] The power industry standard thesaurus refers to the set of terms and their synonyms used within the power industry. For example, synonyms of power plant include power station and electric power plant. By combining the basic keyword (power station) and the expanded keyword (electric power plant), a target keyword set is obtained to improve the subsequent retrieval efficiency.

[0057] In a possible embodiment, the step of obtaining a target keyword set based on the basic keywords and the expanded keywords includes: determining a similarity threshold according to the type of policy text; combining the basic keywords and the expanded keywords to obtain an initial keyword set; calculating the semantic similarity between each keyword in the initial keyword set and the policy text, and retaining the keywords with a semantic similarity higher than the similarity threshold to obtain the target keyword set.

[0058] In the specific implementation process, the BERT model can be used to convert each keyword in the initial keyword set and the policy text into context-related vector representations, and then calculate the cosine similarity of these vectors. By comparing with the similarity threshold, the keywords with a cosine similarity lower than the similarity threshold are excluded, and the keywords with a cosine similarity higher than the similarity threshold are retained, and finally the target keyword set is screened out.

[0059] In the embodiments of the present application, by setting a similarity threshold, only the keywords highly relevant to the policy text will be retained. This can effectively eliminate the keywords that do not conform to the semantics of the policy text, reduce the interference of irrelevant information, and improve the accuracy of subsequent analysis or processing.

[0060] The similarity threshold is determined based on the type of the policy text. For example: If the type of the policy text is a legal provision, the first threshold is determined as the similarity threshold; If the type of the policy text is a technical specification, the second threshold is determined as the similarity threshold; If the type of the policy text is a notice or announcement, the third threshold is determined as the similarity threshold; where the first threshold is greater than the second threshold, and the second threshold is greater than the third threshold.

[0061] In the specific implementation process, legal provisions usually have rigorous and formal language and are relatively standardized in expression. To ensure the rigor of keyword extraction, a relatively high first threshold (e.g., 0.9) is set, so as to ensure that only the keywords highly relevant to the text content are selected and avoid the selection of low-relevant or misleading keywords. Technical specification texts usually contain a large number of industry terms, operation processes, etc., and have a certain degree of complexity and professionalism. Setting a medium second threshold (e.g., 0.8) helps to capture the keywords related to technical details while avoiding over-screening of low-relevant keywords that deviate too much. Notice and announcement texts generally have relatively concise and clear language, and the content is more general and announcement-like. The selection of keywords can be relatively broad. Setting a lower third threshold (e.g., 0.7) helps to capture more potential and relevant keywords without missing possible key information.

[0062] In the embodiments of the present application, by setting different similarity thresholds for different types of policy texts, more flexible and accurate keyword screening can be achieved. It is more strict in legal provision texts, while in technical specification texts and notice and announcement texts, a lower threshold is used to increase the scope of keyword extraction. This method can effectively improve the accuracy and relevance of keyword screening.

[0063] S203. Retrieve in the index tree according to the target keyword set to obtain the key sentences related to the power business system.

[0064] In the specific implementation process, all keywords in the target keyword set are cyclically applied with the depth-first search strategy to traverse and retrieve in the index tree, and the number of cycles is equal to the number of keywords in the target keyword set. For example, if the target keyword set is {"ancillary service", "price"}, two key sentences in this policy document regarding ancillary service and price can be found: "In principle, the upper limit of the peaking service price shall not be higher than the on-grid electricity price of local new energy projects at par" and "The upper limit of the reserve service price shall not exceed the upper limit of the local electricity energy market price."

[0065] S204. Convert the key sentences into SQL statements.

[0066] In a possible embodiment, identify the fields and constraint types in the key sentences; based on a predefined field mapping table, map the fields in the key sentences to the fields of the database table; if the constraint type is a numerical range constraint, generate an SQL statement with a BETWEEN condition or a comparison operator (<=) according to the fields of the database table; if the constraint type is an enumerated value constraint, generate an SQL statement with an IN condition according to the fields of the database table; if the constraint type is a regular constraint, generate an SQL statement with a REGEXP match according to the fields of the database table.

[0067] For example, for the key sentence "In principle, the upper limit of the peaking service price shall not be higher than the on-grid electricity price of local new energy projects at par", its constraint type is a numerical range constraint, and the generated SQL statement with a comparison operator (<=) is as follows: SELECT * FROM energy_prices WHERE peak_price <= base_price Among them, SELECT * means to select data from all columns, FROM energy_prices means the data is stored in the energy_prices table, and WHERE peak_price <= base_price is the constraint condition to ensure that the upper limit of the peaking service price (peak_price) is not higher than the on-grid electricity price of local new energy projects at par (base_price). Only the records that meet this condition will be returned.

[0068] For example, for the key sentence: "The status of power equipment can only be normal, faulty, or under maintenance", its constraint type is an enumerated value constraint, and the generated SQL statement with an IN condition is as follows: SELECT * FROM equipment WHERE status IN ("normal", "faulty", "under maintenance") The meaning of this SQL statement is: Retrieve all equipment from the equipment table where the equipment number format is correct and the status conforms to normal, faulty, or under maintenance.

[0069] For example, for the key sentence: "The power equipment number must conform to the format of 'ED-' followed by 5 digits", its constraint type is a regular constraint, and the generated SQL statement for REGEXP matching is as follows: ELECT * FROM equipment WHERE equipment_id REGEXP '^ED-\d{5}$' The meaning of this SQL statement is: Retrieve all equipment from the equipment table, where the equipment number (equipment_id) conforms to the format of 'ED-' followed by 5 digits. The regular expression ^ED-\d{5}$ ensures that the equipment number follows this pattern.

[0070] In the embodiment of this application, by identifying the fields and constraint types in natural language and combining with a predefined field mapping table, the natural language is converted into the corresponding SQL statement. For different constraint types, SQL statements with different conditions (BETWEEN, <=, IN, REGEXP, etc.) can be generated, so as to ensure that the generated SQL statement can correctly query the data in the database.

[0071] S205. Execute the SQL statement in the database of the power service system to obtain the verification result.

[0072] In the specific implementation process, the verification result is used to indicate whether the power service system is compliant. If the verification result indicates that the power service system is compliant, it means that the power service system meets the latest policy requirements. If the verification result indicates that the power service system is non-compliant, the decision maker can make corresponding decisions based on the verification result, so as to optimize the power service system and make the power service system meet the latest policy requirements.

[0073] For example, it is possible to select the data table reflecting the ancillary service business in the database of the power marketing 2.0 system, select the two columns of data of the peaking service price and the new energy on-grid price in this table, and compare the data in the same row of these two columns according to the generated SQL statement to obtain the verification result regarding the peaking service price. If the peaking service price is lower than the new energy on-grid price, the verification result is compliant; if the peaking service price is higher than the new energy on-grid price, the verification result is non-compliant.

[0074] In summary, the present application provides a verification method for a power business system. By constructing an extensible index tree structure, it realizes the multi-level semantic representation of power industry policy texts. Using a recursive embedding clustering method, it hierarchically abstracts the semantic information of policy texts, improving the retrieval efficiency of large-scale policy texts. A three-level keyword processing process is established, from the extraction of basic keywords to the expansion of synonyms and then to semantic screening, ensuring that the target keyword set is both comprehensive and accurate. A similarity threshold mechanism adaptable to policy types is proposed, setting different matching criteria for different policy types such as legal provisions and technical specifications. It realizes the end-to-end conversion from policy texts to SQL queries. By identifying field mappings and constraint types, it automatically generates executable compliance verification logic, greatly improving the verification efficiency. Through the deep combination of natural language processing and database technology, the present application constructs a policy-business mapping system unique to the power industry, providing an effective compliance guarantee tool for the construction of a new power system, which can be used for rapid system compliance assessment after the introduction of new policies, verification of settlement rules in power trading systems, etc.

[0075] Based on the same inventive concept, as Figure 5 shown, the embodiment of the present application also provides a verification device for a power business system, including: A construction module, configured to construct an index tree according to the latest policy text of the power industry; A determination module, configured to determine a target keyword set according to the function modules of the power business system; A retrieval module, configured to retrieve in the index tree according to the target keyword set to obtain key sentences related to the power business system; A conversion module, configured to convert the key sentences into SQL statements; An inspection module, configured to execute the SQL statements in the database of the power business system to obtain an inspection result; the inspection result is used to indicate whether the power business system is compliant.

[0076] It should be noted that each module in the verification device of the power business system in this embodiment corresponds one-to-one to each step in the verification method of the power business system in the foregoing embodiment. Therefore, the specific implementation manner of this embodiment can refer to the implementation manner of the foregoing verification method of the power business system, which will not be elaborated here.

[0077] In addition, in one embodiment, the present application further provides a computer device, which includes a processor, a memory, and a computer program stored in the memory. When the computer program is run by the processor, it implements the foregoing verification method of the power business system.

[0078] In addition, in one embodiment, the present application further provides a computer storage medium, on which a computer program is stored, and when the computer program is run by a processor, the foregoing verification method of the power service system is implemented.

[0079] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disc, or CD-ROM; or may be various devices including one or any combination of the foregoing memories. The computer may be various computing devices including smart terminals and servers.

[0080] In some embodiments, the executable instructions may be in the form of a program, software, software module, script, or code, and may be written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including being deployed as an independent program or being deployed as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0081] As an example, the executable instructions may or may not correspond to a file in the file system, and may be stored as part of a file that stores other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, stored in a single file dedicated to the program being discussed, or stored in multiple cooperating files (for example, files that store one or more modules, subroutines, or code portions).

[0082] As an example, the executable instructions may be deployed to be executed on one computing device, or on multiple computing devices located at one location, or on multiple computing devices distributed at multiple locations and interconnected by a communication network.

[0083] It should be noted that in this article, the terms "include", "comprise", or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system including a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article, or system. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article, or system including the element.

[0084] The serial numbers of the embodiments of the present application above are only for description and do not represent the superiority or inferiority of the embodiments.

[0085] Through the description of the above embodiments, those skilled in the art can clearly understand that the above method of the embodiment can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present application, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a read-only memory / random access memory, magnetic disk, optical disk), and includes several instructions for causing a multimedia terminal device (which can be a mobile phone, computer, television receiver, or network device, etc.) to execute the methods described in the various embodiments of the present application.

[0086] The above are only the preferred embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A verification method for an electric power service system, characterized in that Including: Construct an index tree according to the latest policy text in the power industry; Determine a set of target keywords according to the functional modules of the power business system; Retrieve in the index tree according to the set of target keywords to obtain key sentences related to the power business system; Convert the key sentences into SQL statements; Execute the SQL statements in the database of the power business system to obtain a verification result; The verification result is used to indicate whether the power business system is compliant.

2. The verification method of the power service system according to claim 1, characterized in that, The determining a set of target keywords according to the functional modules of the power business system includes: Extract basic keywords from the functional modules of the power business system; Expand the basic keywords according to the power industry standard synonym library to obtain expanded keywords; Obtain a set of target keywords according to the basic keywords and the expanded keywords.

3. The verification method of the power service system according to claim 2, characterized in that The obtaining a set of target keywords according to the basic keywords and the expanded keywords includes: Determine a similarity threshold according to the type of the policy text; Merge the basic keywords and the expanded keywords to obtain an initial set of keywords; Calculate the semantic similarity between each keyword in the initial set of keywords and the policy text, and retain the keywords with a semantic similarity higher than the similarity threshold to obtain a set of target keywords.

4. The verification method of the power service system according to claim 3, characterized in that, The determining a similarity threshold according to the type of the policy text includes: If the type of the policy text is a legal provision, determine the first threshold as the similarity threshold; If the type of the policy text is a technical specification, determine the second threshold as the similarity threshold; If the type of the policy text is a notice or announcement, determine the third threshold as the similarity threshold; where the first threshold is greater than the second threshold, and the second threshold is greater than the third threshold.

5. The verification method of the power service system according to claim 1, characterized in that The constructing an index tree according to the latest policy text in the power industry includes: Divide the latest policy text in the power industry into multiple paragraphs, generate vector representations of the multiple paragraphs through text embedding technology, and use the vector representations of the multiple paragraphs as leaf nodes; Cluster the vector representations of the multiple paragraphs to obtain multiple clustered clusters; Generate a summary for each cluster through a large language model; Perform weighted averaging on the vector representations of the paragraphs in each cluster to obtain a vector representation of each cluster; Embed the summaries and vector representations of the multiple clusters into the upper-level nodes of the leaf nodes, and through recursive embedding until a root node is constructed to obtain an index tree; where the index tree contains multiple nodes, and each node contains a node index, child nodes, a summary, and a vector representation.

6. The verification method of the power service system according to claim 5, characterized in that, The clustering the vector representations of the multiple paragraphs to obtain multiple clustered clusters includes: Use the vector representation of each paragraph as an independent cluster; Calculate the fidelity between clusters using the swap test; Merge the two clusters with the maximum fidelity until the number of clusters reaches a preset number to obtain multiple clustered clusters.

7. The verification method of the power service system according to claim 1, characterized in that, The converting the key sentences into SQL statements includes: Identify the fields and constraint types in the key sentences; Based on a predefined field mapping table, map the fields in the key sentences to the fields of the database table; If the constraint type is a numerical range constraint, generate an SQL statement with a BETWEEN condition or a comparison operator according to the fields of the database table; if the constraint type is an enumerated value constraint, generate an SQL statement with an IN condition according to the fields of the database table; if the constraint type is a regular constraint, generate an SQL statement for REGEXP matching according to the fields of the database table.

8. A verification device for an electric power service system, characterized in that, Including: A construction module, configured to construct an index tree according to the latest policy text in the power industry; A determination module, configured to determine a target keyword set according to the functional modules of the power business system; A retrieval module, configured to retrieve in the index tree according to the target keyword set to obtain key sentences related to the power business system; A conversion module, configured to convert the key sentences into SQL statements; A verification module, configured to execute the SQL statements in the database of the power business system to obtain a verification result; The verification result is used to indicate whether the power business system is compliant.

9. A computer device, characterized in that, The computer device includes a memory and a processor. A computer program is stored in the memory, and the processor executes the computer program to implement the verification method of the power business system according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and the processor executes the computer program to implement the verification method of the power business system according to any one of claims 1-7.

Images