Regulation checking method and device, terminal equipment and storage medium

Abstract

The invention discloses a regulation checking method and device, terminal equipment and a storage medium. The method comprises the steps of obtaining an operation description text input by a dispatcher; inputting the operation description text into a natural language processing model, so that the natural language processing model outputs a standardized query statement corresponding to the operation description text; wherein the standardized query statement comprises an operation object, an operation action and an operation environment; inputting the standardized query statement into a regulation checking model, so that the regulation checking model outputs a regulation checking result corresponding to the standardized query statement; wherein the regulation checking result comprises operation compliance. According to the invention, the regulation checking efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the field of natural language processing technology, and in particular to a regulation verification method, device, terminal equipment and storage medium. Background Art

[0002] During the operation of the power system, dispatchers must follow strict behavioral regulations to ensure the safety and stability of the power system. Traditional regulation verification methods mainly rely on knowledge graph systems, which are usually composed of complex rule bases and algorithms. Due to the complex internal rules and algorithms of the knowledge graph system, it is difficult to quickly retrieve the rules corresponding to the dispatcher's behavioral regulations to verify whether the dispatcher's behavioral regulations meet the requirements of the regulations when using the system to verify the dispatcher's behavioral regulations. Summary of the invention

[0003] The embodiments of the present invention provide a regulation verification method, apparatus, terminal device and storage medium, which can improve the processing efficiency during regulation verification.

[0004] An embodiment of the present invention provides a method for checking regulations, including:

[0005] Get the operation description text entered by the dispatcher;

[0006] Inputting the operation description text into a natural language processing model so that the natural language processing model outputs a standardized query sentence corresponding to the operation description text; wherein the standardized query sentence includes: an operation object, an operation action, and an operation environment;

[0007] The standardized query statement is input into a regulation verification model, so that the regulation verification model outputs a regulation verification result corresponding to the standardized query statement; wherein the regulation verification result includes operation compliance.

[0008] Furthermore, the step of inputting the operation description text into a natural language processing model so that the natural language processing model outputs a standardized query statement corresponding to the operation description text includes:

[0009] Inputting the operation description text into a natural language processing model so that the natural language processing model performs text segmentation on the operation description text to obtain a first preprocessed operation description text;

[0010] Performing part-of-speech tagging on the first preprocessed operation description text, determining the operation object, operation action and operation environment in the word segmentation result of the operation description text, and obtaining a second preprocessed operation description text;

[0011] Stop words in the second preprocessed operation description text are removed to generate a standardized query statement corresponding to the operation description text.

[0012] Furthermore, the step of inputting the standardized query statement into a regulation verification model so that the regulation verification model outputs a regulation verification result corresponding to the standardized query statement includes:

[0013] Inputting the standardized query statement into a regulation verification model so that the regulation verification model calculates a query vector according to the standardized query statement;

[0014] Acquire related regulatory documents according to the query vector;

[0015] Segmenting the associated regulation document to obtain a plurality of associated regulation text blocks;

[0016] The standardized query statement is verified according to each associated regulation text block, and a regulation verification result corresponding to the standardized query statement is output.

[0017] Furthermore, acquiring the associated regulatory document according to the query vector includes:

[0018] Obtaining the chapter vectors of all regulatory documents in the regulatory document library that has been learned in the regulatory verification model;

[0019] Determine, based on each chapter vector and the query vector, a chapter vector having the greatest similarity to the query vector;

[0020] The regulatory document associated with the query vector is obtained according to the chapter vector having the greatest similarity to the query vector.

[0021] Furthermore, the segmentation of the associated regulation document to obtain a plurality of associated regulation text blocks includes:

[0022] Acquiring semantic information and logical structure of the associated regulation document;

[0023] Slicing the associated regulation document according to the semantic information to obtain a plurality of regulation chapter texts;

[0024] The text of each regulation chapter is segmented according to the semantic information and logical structure to obtain a number of related regulation text blocks.

[0025] Based on the above method embodiment, the present invention provides a corresponding device embodiment;

[0026] An embodiment of the present invention provides a regulation checking device, including: a text data acquisition module, a natural language processing module and a regulation checking module;

[0027] The text data acquisition module is used to acquire the operation description text input by the dispatcher;

[0028] The natural language processing module is used to input the operation description text into a natural language processing model, so that the natural language processing model outputs a standardized query statement corresponding to the operation description text; wherein the standardized query statement includes: an operation object, an operation action, and an operation environment;

[0029] The regulation verification module is used to input the standardized query statement into a regulation verification model, so that the regulation verification model outputs a regulation verification result corresponding to the standardized query statement; wherein the regulation verification result includes operation compliance.

[0030] Furthermore, the step of inputting the operation description text into a natural language processing model so that the natural language processing model outputs a standardized query statement corresponding to the operation description text includes:

[0031] Inputting the operation description text into a natural language processing model so that the natural language processing model performs text segmentation on the operation description text to obtain a first preprocessed operation description text;

[0032] Performing part-of-speech tagging on the first preprocessed operation description text, determining the operation object, operation action and operation environment in the word segmentation result of the operation description text, and obtaining a second preprocessed operation description text;

[0033] Stop words in the second preprocessed operation description text are removed to generate a standardized query statement corresponding to the operation description text.

[0034] Furthermore, the step of inputting the standardized query statement into a regulation verification model so that the regulation verification model outputs a regulation verification result corresponding to the standardized query statement includes:

[0035] Inputting the standardized query statement into a regulation verification model so that the regulation verification model calculates a query vector according to the standardized query statement;

[0036] Acquire related regulatory documents according to the query vector;

[0037] Segmenting the associated regulation document to obtain a plurality of associated regulation text blocks;

[0038] The standardized query statement is verified according to each associated regulation text block, and a regulation verification result corresponding to the standardized query statement is output.

[0039] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, a regulation verification method described in the above-mentioned embodiment of the invention is implemented.

[0040] Another embodiment of the present invention provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute a regulation verification method described in the above-mentioned embodiment of the invention.

[0041] The following beneficial effects are achieved by implementing the present invention:

[0042] The present invention provides a regulations verification method, device, terminal equipment and storage medium. The regulations verification method obtains an operation description text input by a dispatcher, inputs the operation description text into a natural language processing model, so that the natural language processing model outputs a standardized query statement corresponding to the operation description text to determine the operation object, operation action and operation environment contained in the operation description text; after extracting the information required for regulations verification in the input operation description text through the natural language processing model, the standardized query statement is input into the regulations verification model, so that the regulations verification model outputs the regulations verification result corresponding to the standardized query statement, which can improve the processing efficiency during regulations verification. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flowchart of a regulation verification method provided by one embodiment of the present invention.

[0044] Figure 2 It is a structural schematic diagram of a regulation checking device provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0048] In the description of the embodiments of the present application, the technical terms "first", "second", etc. are only used to distinguish different objects, and cannot be understood as indicating or implying relative importance or implicitly indicating the number, specific order or primary and secondary relationship of the indicated technical features. In the description of the embodiments of the present application, the meaning of "multiple" is more than two, unless otherwise clearly and specifically defined.

[0049] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0050] In the description of the embodiments of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0051] In the description of the embodiments of the present application, the term "multiple" refers to more than two (including two). Similarly, "multiple groups" refers to more than two groups (including two groups), and "multiple pieces" refers to more than two pieces (including two pieces).

[0052] In the description of the embodiments of the present application, unless otherwise clearly specified and limited, technical terms such as "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the internal connection of two elements or the interaction relationship between two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments of the present application can be understood according to the specific circumstances.

[0053] like Figure 1 As shown, a method for checking regulations provided by an embodiment of the present invention includes:

[0054] Step S1: Obtain the operation description text input by the dispatcher;

[0055] Step S2: inputting the operation description text into a natural language processing model, so that the natural language processing model outputs a standardized query statement corresponding to the operation description text; wherein the standardized query statement includes: an operation object, an operation action, and an operation environment;

[0056] Step S3: inputting the standardized query statement into a regulation verification model, so that the regulation verification model outputs a regulation verification result corresponding to the standardized query statement; wherein the regulation verification result includes operational compliance.

[0057] For step S1, obtain the operation description text input by the dispatcher through the computer front-end interface.

[0058] For step S2, in a preferred embodiment, the inputting the operation description text into a natural language processing model so that the natural language processing model outputs a standardized query statement corresponding to the operation description text includes: inputting the operation description text into a natural language processing model so that the natural language processing model performs text segmentation on the operation description text to obtain a first preprocessed operation description text; performing part-of-speech tagging on the first preprocessed operation description text, determining the operation object, operation action and operation environment in the operation description text segmentation result, and obtaining a second preprocessed operation description text; removing stop words in the second preprocessed operation description text to generate a standardized query statement corresponding to the operation description text.

[0059] Specifically, the operation description text is input into a natural language processing model, and preferably, the natural language processing model adopts an LLM model. After receiving the operation description text, the natural language processing model first performs text segmentation on the operation description text, and the text segmentation mainly relies on the learned power field dictionary content in the natural language processing model for word segmentation. The professional terms in the operation description text are identified through the learned power field dictionary content, such as "10kV switchgear", "circuit breaker" and other professional terms; after the operation description text is segmented according to the identified content, the first pre-processed operation description text is obtained; further, the natural language processing model performs part-of-speech tagging on the first pre-processed operation description text, mainly tagging action words, operation objects and operation environments; for example, action words such as "closing", "disconnecting", and "reversing" are marked, and the operation actions in the operation description text are further determined according to the marked action words, thereby obtaining the second pre-processed operation description text. Finally, the stop words in the above-mentioned second preprocessed description text are removed, so as to retain the operation description text containing key information such as the operation object, operation action and operation environment. The operation description text retaining the key information is constructed into a standardized query statement corresponding to the operation description text entered by the dispatcher through automatic generation technology (Auto prompt).

[0060] It should be noted that the operation object refers to a specific device or component in the power system, the operation action describes the specific operation content of the object, and the operation environment includes the system state or special conditions during the operation. One implementation result of the final standardized query statement can be: "10kV switchgear (operation object) + circuit breaker closing (operation action) + normal operating state (operation environment)", and another implementation result can also be "220kV transformer (operation object) + step-down operation (operation action) + high load conditions (operation environment).

[0061] Preferably, during the process of processing the standardized query statement, key elements such as time information and special conditions contained in the operation description text may also be extracted to improve the information richness of the standardized query statement.

[0062] By processing the operation description text input by the dispatcher through the natural language processing model, the key information in the operation description text can be obtained from the operation description text and irrelevant information can be eliminated, thereby improving the efficiency and accuracy of subsequent regulations verification.

[0063] For step S3, the standardized query statement is input into the regulation verification model, and whether the operation description text input by the dispatcher complies with the operation norms is determined according to the regulation verification result output by the regulation verification model. Preferably, the regulation verification model is constructed based on RAG technology.

[0064] In a preferred embodiment, the step of inputting the standardized query statement into a regulations verification model so that the regulations verification model outputs a regulations verification result corresponding to the standardized query statement comprises: inputting the standardized query statement into the regulations verification model so that the regulations verification model calculates a query vector according to the standardized query statement; obtaining an associated regulations document according to the query vector; segmenting the associated regulations document to obtain a plurality of associated regulations text blocks; verifying the standardized query statement according to each associated regulations text block, and outputting a regulations verification result corresponding to the standardized query statement.

[0065] Specifically, the standardized query statement is input into the regulation verification model. When the standardized query statement is received, the regulation verification model converts the standardized query statement into a vector representation to improve the subsequent calculation efficiency, that is, calculates the corresponding query vector according to the standardized query statement, and then obtains the associated regulation document according to the query vector.

[0066] In a preferred embodiment, the obtaining of associated regulatory documents based on the query vector includes: obtaining chapter vectors of all regulatory documents in a regulatory document library that has been learned in a regulatory verification model; determining a chapter vector having the greatest similarity to the query vector based on each chapter vector and the query vector; and obtaining associated regulatory documents with the query vector based on the chapter vector having the greatest similarity to the query vector.

[0067] Specifically, when obtaining the associated regulatory documents according to the query vector, it is first necessary to obtain the chapter vectors of all regulatory documents in the regulatory document library that has been learned in the regulatory verification model, and the chapter vector is used to indicate the chapter title of the regulatory document. The similarity between each chapter vector and the query vector is calculated one by one; preferably, in order to make the similarity calculation more accurate, the chapter content vector corresponding to each chapter vector can also be obtained, and the chapter content vector is used to indicate the content contained in each chapter; and then, according to the similarity between each chapter vector, each chapter content vector and the query vector, a chapter with the greatest similarity to the query vector is determined, that is, a chapter with the strongest correlation with the query vector is determined as the associated regulatory document.

[0068] In a preferred embodiment, said segmenting the associated regulation document to obtain a number of associated regulation text blocks includes: acquiring semantic information and a logical structure of the associated regulation document; segmenting the associated regulation document according to the semantic information to obtain a number of regulation chapter texts; and segmenting each regulation chapter text according to the semantic information and the logical structure to obtain a number of associated regulation text blocks.

[0069] Specifically, after determining the associated regulatory document, the semantic information and logical structure of the associated regulatory document are obtained. The above semantic information is used to indicate the content theme and content coherence of each text content in the regulatory document, and the above logical structure is used to indicate the paragraph hierarchy structure existing in the regulatory document. For example, Chapter 1 of the regulatory document contains Chapter 1.1 and Chapter 1.2, and Chapter 1.1 contains Chapter 1.1.1. At this time, the logical structure of the regulatory document can refer to the nested relationship between the sub-chapters under the document, and its structure can be exemplarily: Chapter 1: [Chapter 1.1 (Chapter 1.1.1), Chapter 1.2].

[0070] According to the semantic information, the first round of segmentation of the associated regulation document is performed according to the chapters, and the associated regulation document is divided into several regulation chapter texts. Then, according to the semantic information and logical structure, the second round of segmentation of each regulation chapter text is performed to divide each regulation chapter text into smaller text blocks, and the associated regulation text blocks under each regulation chapter text are obtained.

[0071] It should be noted that when cutting, it is necessary to ensure that the resulting regulatory chapter text and related regulatory text blocks are coherent and complete.

[0072] Through this layer-by-layer cutting method, a hierarchical document association structure is formed, and then by calculating the similarity of the associated regulation text block, the associated regulation chapter text can be more effectively located, and then the associated regulation document can be queried upward based on the associated regulation chapter text. This structure can improve the retrieval speed of the standardized query statement to retrieve relevant content before verification in the regulation verification model, so as to improve the verification efficiency.

[0073] The standardized query statements are checked according to the associated regulation text blocks, that is, the operation objects, operation actions and operation environments in the standardized query statements are checked according to the text contents of the associated regulation text blocks to determine whether the operation complies with the requirements of the specification.

[0074] Specifically, in the process of checking the operation objects, operation actions and operation environments in the standardized query statements according to the text content of each associated regulation text block, the regulation verification model will extract the operation objects, operation actions and operation environments in the standardized query statements, and build a scenario model based on the extracted information. When building the scenario model, additional data such as the prerequisites, potential impacts and possible risks of the operation are added. These additional data are obtained through the content pre-learned during the training of the regulation verification model. This scenario model construction method makes the constructed scenario model have richer expressions than the content contained in the standardized query statement, so as to facilitate the understanding of the technical meaning and potential impact in the operation description text. For example: for "10kV switch cabinet circuit breaker closing operation", the constructed scenario model will include multi-dimensional scenario descriptions such as equipment status, operating environment, and personnel configuration. Therefore, the standardization of the operation description text is judged based on the constructed scenario model, and its potential impact is prompted.

[0075] It should be added that the training of the regulations verification model mainly includes: data collection and preprocessing stage, model pre-training stage, domain adaptability training stage and task-specific training stage.

[0076] Construct an initial regulation verification model. In the data collection and preprocessing stage, a large amount of text data needs to be collected from various documents, procedures, operation manuals and historical cases of the power system. After cleaning, annotation and structural processing, training data for training is obtained. In the model pre-training stage, a general large-scale corpus is obtained to conduct preliminary training on the initial regulation verification model, so that the pre-trained initial rule verification model can master basic language comprehension capabilities. In the domain adaptability training stage, a professional data set of the power system is used for fine tuning, so that the model can learn professional knowledge and terminology in the power field. In the task-specific training stage, the model is trained with training data so that the model can output the regulation verification results that meet the predicted loss according to the text of the input standardized query sentence structure. Preferably, when the text or regulation content in the training data is updated, the model is locally trained according to the updated content so that the model can learn the updated content.

[0077] In order to make the final output of the regulation verification results better guide the dispatcher, after the scenario model is constructed and the associated regulation text blocks are obtained, the regulation verification model obtains all the relevant regulations, operating procedures and safety standards learned. The regulation requirements usually contain the following information: the prerequisites for the operation (such as equipment status, environmental requirements), specific operation steps and sequence, safety precautions, required personnel configuration, inspection items after operation, etc. Then, compare these data with the operation description text. Specifically, first, the model will check whether each key step in the operation description has a corresponding one in the regulation requirements; then, analyze whether the operation sequence complies with the regulations; then, evaluate whether all safety prerequisites are met; again, check whether all necessary safety measures are followed; finally, confirm whether the cooperation of other departments is required and whether the cooperation process is correct. For example, for the "10kV switch cabinet circuit breaker closing operation", the model will first check whether the safety confirmation requirements before closing are met, such as checking the insulation status of the equipment and confirming that no one is in the dangerous area. Then, the model will analyze whether the operation sequence is correct, such as whether the electrical index test is performed first and then the closing operation is performed. Next, the model will evaluate whether the cooperation of relevant departments is needed, such as whether communication confirmation with the system dispatch center is needed. In addition, the model will also consider a wider range of factors, such as whether weather conditions, system load conditions, etc. meet the operating requirements. In this comprehensive verification process, the model not only mechanically compares the rules, but is based on an in-depth understanding of the operating principles of the entire power system, comprehensively considers various factors, and makes comprehensive and accurate judgments, so that the output regulations verification results are more accurate. In addition to the compliance judgment of the operation in the regulations verification results, it can also include: specific operation violation information, reasons for violations and corresponding procedural clauses, relevant risk warnings, improvement suggestions and specific clauses cited during the verification. These output contents are presented in a structured form for the dispatcher to understand and refer to.

[0078] In this way, the system can accurately understand the dispatcher's operational intentions, quickly locate relevant regulatory requirements, and provide professional and detailed compliance analysis results. This not only improves the efficiency and accuracy of regulatory verification, but also provides clear operational guidance for dispatchers.

[0079] For example, the input operation description text is: I am a dispatcher, I have completed the voltage coordination operation, please help me check whether it is correct; my operation process is: the long-term (LV) and short-term (SV) voltage changes are -15% and +20% respectively. The output procedure verification result is: Based on the operation process you provided and the regulatory information provided previously, your operation may not meet the prescribed voltage change limits. According to Section CC.6.1.7, the acceptable levels of long-term (LV) and short-term (SV) voltage changes are as follows:

[0080] 1. For systems from 3.3kV to 400kV, the planning level is LV 0.9, SV0.7;

[0081] 2. For systems from 66kV to 400kV, the planning level is LV0.8 and SV0.6;

[0082] This means that the acceptable lower limit of long-term voltage variation is 90% of the nominal voltage, and the acceptable upper limit of short-term voltage variation is 107% of the nominal voltage. In the operating process you mentioned, the long-term voltage variation is -15% and the short-term voltage variation is +20%, which exceeds the specified acceptable range.

[0083] Therefore, your operations may require adjustments to ensure that voltage variations remain within specified limits. You should recheck voltage levels and take steps to adjust them back to the compliance range specified in regulatory documents. If voltage variations are due to system faults or other external factors, you will also need to evaluate those factors and take appropriate corrective actions. After completing adjustments, you should again confirm that voltage levels have returned to the specified planned levels.

[0084] Based on the above method embodiment, the present invention provides a corresponding device embodiment.

[0085] like Figure 2 As shown, an embodiment of the present invention provides a regulation checking device, including: a text data acquisition module, a natural language processing module and a regulation checking module;

[0086] The text data acquisition module is used to acquire the operation description text input by the dispatcher;

[0087] The natural language processing module is used to input the operation description text into a natural language processing model, so that the natural language processing model outputs a standardized query statement corresponding to the operation description text; wherein the standardized query statement includes: an operation object, an operation action, and an operation environment;

[0088] The regulations verification module is used to input the standardized query statement into the regulations verification model so that the regulations verification model outputs the regulations verification results corresponding to the standardized query statement; wherein the regulations verification results include operation compliance, that is, outputting a judgment of operation compliance or operation non-compliance.

[0089] In a preferred embodiment, the step of inputting the operation description text into a natural language processing model so that the natural language processing model outputs a standardized query statement corresponding to the operation description text includes:

[0090] Inputting the operation description text into a natural language processing model so that the natural language processing model performs text segmentation on the operation description text to obtain a first preprocessed operation description text;

[0091] Performing part-of-speech tagging on the first preprocessed operation description text, determining the operation object, operation action and operation environment in the word segmentation result of the operation description text, and obtaining a second preprocessed operation description text;

[0092] Stop words in the second preprocessed operation description text are removed to generate a standardized query statement corresponding to the operation description text.

[0093] In a preferred embodiment, the step of inputting the standardized query statement into a regulation verification model so that the regulation verification model outputs a regulation verification result corresponding to the standardized query statement comprises:

[0094] Inputting the standardized query statement into a regulation verification model so that the regulation verification model calculates a query vector according to the standardized query statement;

[0095] Acquire related regulatory documents according to the query vector;

[0096] Segmenting the associated regulation document to obtain a plurality of associated regulation text blocks;

[0097] The standardized query statement is verified according to each associated regulation text block, and a regulation verification result corresponding to the standardized query statement is output.

[0098] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0099] Those skilled in the art can clearly understand that for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0100] Based on the above method item embodiments, the present invention provides corresponding terminal device item embodiments.

[0101] An embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a regulation verification method described in any one of the present invention is implemented.

[0102] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0103] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0104] The memory can be used to store the computer program, and the processor realizes various functions of the terminal device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Med ia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0105] Based on the above method item embodiments, the present invention provides a corresponding storage medium item embodiment.

[0106] An embodiment of the present invention provides a storage medium, wherein the storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute a regulation verification method described in any one of the present inventions.

[0107] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium.

[0108] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for checking regulations, characterized in that: include: Get the operation description text entered by the dispatcher; Inputting the operation description text into a natural language processing model so that the natural language processing model outputs a standardized query sentence corresponding to the operation description text; wherein the standardized query sentence includes: an operation object, an operation action, and an operation environment; The standardized query statement is input into a regulation verification model, so that the regulation verification model outputs a regulation verification result corresponding to the standardized query statement; wherein the regulation verification result includes operation compliance.

2. A method for checking regulations as claimed in claim 1, characterized in that: The step of inputting the operation description text into a natural language processing model so that the natural language processing model outputs a standardized query statement corresponding to the operation description text includes: Inputting the operation description text into a natural language processing model so that the natural language processing model performs text segmentation on the operation description text to obtain a first preprocessed operation description text; Performing part-of-speech tagging on the first preprocessed operation description text, determining the operation object, operation action and operation environment in the word segmentation result of the operation description text, and obtaining a second preprocessed operation description text; Stop words in the second preprocessed operation description text are removed to generate a standardized query statement corresponding to the operation description text.

3. A method for checking regulations as claimed in claim 1, characterized in that: The step of inputting the standardized query statement into a regulation verification model so that the regulation verification model outputs a regulation verification result corresponding to the standardized query statement includes: Inputting the standardized query statement into a regulation verification model so that the regulation verification model calculates a query vector according to the standardized query statement; Acquire related regulatory documents according to the query vector; Segmenting the associated regulation document to obtain a plurality of associated regulation text blocks; The standardized query statement is verified according to each associated regulation text block, and a regulation verification result corresponding to the standardized query statement is output.

4. A method for checking regulations as claimed in claim 3, characterized in that: The acquiring of the associated regulation document according to the query vector includes: Obtaining the chapter vectors of all regulatory documents in the regulatory document library that has been learned in the regulatory verification model; Determine, based on each chapter vector and the query vector, a chapter vector having the greatest similarity to the query vector; The regulatory document associated with the query vector is obtained according to the chapter vector having the greatest similarity to the query vector.

5. A method for checking regulations as claimed in claim 3, characterized in that: The segmenting of the associated regulation document to obtain a plurality of associated regulation text blocks includes: Acquiring semantic information and logical structure of the associated regulation document; Slicing the associated regulation document according to the semantic information to obtain a plurality of regulation chapter texts; The text of each regulation chapter is segmented according to the semantic information and logical structure to obtain a number of related regulation text blocks.

6. A regulation verification device, characterized in that: include: Text data acquisition module, natural language processing module and regulations verification module; The text data acquisition module is used to acquire the operation description text input by the dispatcher; The natural language processing module is used to input the operation description text into a natural language processing model, so that the natural language processing model outputs a standardized query statement corresponding to the operation description text; wherein the standardized query statement includes: an operation object, an operation action, and an operation environment; The regulation verification module is used to input the standardized query statement into a regulation verification model, so that the regulation verification model outputs a regulation verification result corresponding to the standardized query statement; wherein the regulation verification result includes operation compliance.

7. A regulation checking device as claimed in claim 6, characterized in that: The step of inputting the operation description text into a natural language processing model so that the natural language processing model outputs a standardized query statement corresponding to the operation description text includes: Inputting the operation description text into a natural language processing model so that the natural language processing model performs text segmentation on the operation description text to obtain a first preprocessed operation description text; Performing part-of-speech tagging on the first preprocessed operation description text, determining the operation object, operation action and operation environment in the word segmentation result of the operation description text, and obtaining a second preprocessed operation description text; Stop words in the second preprocessed operation description text are removed to generate a standardized query statement corresponding to the operation description text.

8. A regulation checking device as claimed in claim 6, characterized in that: The step of inputting the standardized query statement into a regulation verification model so that the regulation verification model outputs a regulation verification result corresponding to the standardized query statement includes: Inputting the standardized query statement into a regulation verification model so that the regulation verification model calculates a query vector according to the standardized query statement; Acquire related regulatory documents according to the query vector; Segmenting the associated regulation document to obtain a plurality of associated regulation text blocks; The standardized query statement is verified according to each associated regulation text block, and a regulation verification result corresponding to the standardized query statement is output.

9. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a regulation checking method according to any one of claims 1 to 5 is implemented.

10. A storage medium, characterized in that: The storage medium includes a stored computer program, wherein when the computer program is executed, the device where the storage medium is located is controlled to execute a regulation verification method as claimed in any one of claims 1 to 5.

Images