A method for automatically generating structured emergency response plan templates in the power industry

Abstract

This invention discloses an automatic generation method for structured emergency response plan templates in the power industry, comprising: establishing standards for writing power scenario emergency response plan texts; standardizing the format of unstructured scenario emergency response plan texts to obtain standardized scenario emergency response plan texts; inputting the standardized scenario emergency response plan texts into a generative large language model to extract scenario information and generate scenario descriptions; establishing a basic information database for structured emergency response plans; using a bidirectional coding pre-trained language model for semantic matching to extract behavioral feature information; generating behavioral description information using the generative large language model; and constructing a structured emergency response plan template generation module to generate structured emergency response plan templates for specific scenarios. This invention significantly shortens template generation time, reduces the workload of staff, and the extraction method based on a large language model has higher accuracy, greatly reducing errors caused by manual operation, realizing rapid generation of emergency response plan templates, and improving the generation efficiency of emergency response plan templates.

Description

Technical Field

[0001] This invention relates to the field of safety and emergency technology in the power industry, specifically to a method for automatically generating structured emergency response plan templates for the power industry. Background Technology

[0002] With rapid societal development, the power system, as a crucial component of national infrastructure, is vital to the national economy and people's lives through its stable operation. However, natural disasters, equipment failures, and human error can all trigger emergencies in the power system, severely impacting social stability and people's livelihoods. Therefore, rapidly developing effective emergency plans for the power industry to address various unforeseen circumstances has become a key issue for the power sector.

[0003] Traditional emergency response plan development in the power industry typically requires significant investment of manpower, resources, and time, and often struggles to adapt to rapidly changing environments and the diversity of emergencies. Emergency response plan templates are fundamental for rapid development; however, traditional template generation relies heavily on manual extraction of key information, resulting in slow processing and unclear matching. Summary of the Invention

[0004] The purpose of this invention is to provide a method for automatically generating structured emergency response plan templates for the power industry. This aims to address the problems in existing technologies for developing emergency response plans in the power industry, which primarily rely on manual extraction of key information from plan templates, resulting in high manpower and material costs, slow template development speed, and unclear matching.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solution:

[0006] This invention provides a method for automatically generating structured emergency response plan templates in the power industry, comprising:

[0007] Step S1: Establish standards for writing power scenario contingency plans, standardize the format of unstructured scenario contingency plan texts, and obtain standardized scenario contingency plan texts;

[0008] Step S2: Input the standardized scenario contingency plan text into the generative large language model, extract scenario information from the standardized scenario contingency plan text, and generate a scenario description;

[0009] Step S3: Establish a structured emergency response plan basic information database;

[0010] Step S4: Input the standardized scenario plan text and the information database into the language similarity model, and perform semantic matching between the standardized scenario plan text and each sub-database in the information database to extract behavioral feature information;

[0011] Step S5: Invoke the generative large language model, input the scenario description and the behavioral feature information into the generative large language model to generate behavioral description information;

[0012] Step S6: Construct a structured emergency plan template generation module. Input the scenario description, the behavioral feature information, and the behavioral description information into the structured emergency plan template generation module to obtain a structured emergency plan template for a specific scenario.

[0013] Preferably, the step S1 of formulating the standard for writing power scenario contingency plan texts and standardizing the format of unstructured scenario contingency plan texts to obtain standardized scenario contingency plan texts specifically includes: the content of the power scenario contingency plan text includes: scenario name, scenario category, scenario tag, and scenario description.

[0014] Preferably, in step S2, the scenario information extracted from the standardized scenario plan text specifically includes: scenario name, scenario category, and scenario tag. Based on the extracted scenario information, a scenario description is generated using the generative large language model.

[0015] Preferably, the establishment of the structured emergency response plan basic information database in step S3 specifically includes: collecting and organizing representative emergency response plan texts of the power industry, manually extracting information from the representative emergency response plan texts of the power industry, and establishing the information database based on the extracted information from the representative emergency response plan texts of the power industry.

[0016] Preferably, the information extracted manually from the representative emergency response plan text of the power industry includes: behavior name, scenario category, behavior tag, behavior role, and behavior keyword.

[0017] Preferably, sub-databases of the information database are created based on the content of the information in the information database, and the sub-databases of the information database include:

[0018] A behavior name database, which provides standardized abbreviations for various behaviors in different emergency scenarios;

[0019] A scene category library, which is a collection of various scene names;

[0020] A behavior tag library, which is used to describe the relationships and commands of the actors in an emergency plan;

[0021] A behavioral role database, which includes information on relevant personnel, government departments, and enterprises;

[0022] A behavioral keyword library is used to summarize various behaviors in emergency response plans.

[0023] Preferably, in step S4, the semantic matching of the standardized scenario plan text with each sub-database in the information database specifically includes:

[0024] The standardized scenario contingency plan text and the behavioral features in the information database are respectively imported into the bidirectional encoding pre-trained language model;

[0025] The bidirectional encoding pre-trained language model encodes the imported normalized scenario plan text and the behavioral features through an encoder, respectively, to obtain the encoded scenario plan text sentence and the encoded behavioral information.

[0026] Based on the encoded scenario plan text sentences and the encoded behavioral information, calculate the cosine similarity;

[0027] Based on the calculation result of the cosine similarity, the behavioral feature information is extracted.

[0028] Preferably, the expression for calculating the cosine similarity is:

[0029]

[0030] Where a represents the encoded scenario plan text sentence expressed as a vector after encoding, b represents the encoded behavioral information expressed as a vector, and θ represents the angle between vectors a and b.

[0031] Preferably, the similarity between the scenario plan text sentence and the behavioral information is determined based on the similarity calculated using the cosine similarity. Specifically:

[0032] The degree to which the cosine similarity cosθ approaches 1 is determined. The higher the degree to which the cosine similarity cosθ approaches 1, the higher the similarity between the scenario plan text sentence and the behavioral information.

[0033] The degree to which the cosine similarity cosθ approaches 0 is determined. The higher the degree to which the cosine similarity cosθ approaches 0, the lower the similarity between the scenario plan text sentence and the behavioral information.

[0034] Preferably, in step S6, the construction of the structured emergency plan template generation module and the obtaining of the structured emergency plan template for a specific scenario specifically include:

[0035] By calling a Python library for processing Excel files, a structured emergency plan template generation module is constructed. The scenario description, the behavioral feature information, and the behavioral description information are input into the Excel-format structured emergency plan basic template in the structured emergency plan template generation module to obtain a structured emergency plan template for a specific scenario.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] 1) Traditional emergency response plan template generation requires manual selection of behavior names, scenario categories, behavior tags, behavior keywords, and behavior roles. This invention extracts key information from unstructured text using a generative large language model and a bidirectional encoding pre-trained language model, which can significantly shorten template generation time and reduce the workload of personnel. At the same time, the extraction method based on the large language model has higher accuracy and can greatly reduce the errors caused by manual operation.

[0038] 2) In the semantic matching proposed in this invention, by constructing a structured emergency plan basic information database, it is only necessary to perform semantic matching between sentences in the standardized scenario plan text and behavioral information in the information database, which greatly reduces the computational load of the model, improves the running efficiency of the model, and realizes the rapid generation of emergency plan templates.

[0039] 3) Traditional emergency response plan templates require manual creation of Excel spreadsheets. This invention, however, constructs a structured emergency response plan template generation module. By calling a Python library for processing Excel files, it builds a basic structured emergency response plan template in Excel format. Simply import the extracted scenario information, behavioral feature information, and behavioral description information into the structured emergency response plan template generation module to generate a structured emergency response plan template for a specific scenario, further improving the efficiency of emergency response plan template generation. Attached Figure Description

[0040] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the drawings described below are one embodiment of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort:

[0041] Figure 1 A flowchart illustrating an embodiment of the present invention for an automatic generation method of structured emergency response plan templates for the power industry;

[0042] Figure 2 The semantic matching flowchart is provided for an embodiment of the automatic generation method of structured emergency plan templates in the power industry. Detailed Implementation

[0043] The following is in conjunction with the appendix Figures 1 to 2The specific embodiments of this invention provide a more detailed description of the method for automatically generating structured emergency response plan templates for the power industry. The advantages and features of this invention will become clearer from the following description. It should be noted that the accompanying drawings are in a very simplified form and use non-precise proportions, used only to facilitate and clearly illustrate the purpose of the embodiments of this invention. Please refer to the accompanying drawings to make the objectives, features, and advantages of this invention more apparent and understandable. It should be understood that the structures, proportions, sizes, etc., depicted in the accompanying drawings are only used to complement the content disclosed in the specification, for those skilled in the art to understand and read, and are not intended to limit the implementation conditions of this invention. Therefore, they have no substantial technical significance. Any modifications to the structure, changes in proportions, or adjustments to the size, without affecting the effects and objectives achieved by this invention, should still fall within the scope of the technical content disclosed in this invention.

[0044] To address the current issues in the development of emergency response plans for the power industry, which relies heavily on manual extraction of key information from plan templates, resulting in high manpower and material costs, slow template development speed, and unclear matching, this paper proposes a new approach.

[0045] refer to Figure 1 As shown in the figure, this embodiment provides a method for automatically generating structured emergency response plan templates in the power industry, including the following steps:

[0046] Step S1: Establish standards for writing power scenario contingency plans to obtain standardized scenario contingency plan texts. The content of the power scenario contingency plan text includes: scenario name, scenario category, scenario tag, and detailed scenario description.

[0047] Step S2: Input the standardized scenario plan text into a generative large language model. In this embodiment, the generative large language model is the ChatGLM (Chat Generative Language Model). Extract scenario information from the standardized scenario plan text. The extracted scenario information specifically includes: scenario name, scenario category, and scenario tag. Based on the extracted scenario information, the ChatGLM model generates a scenario description.

[0048] Step S3: Establish a structured emergency response plan basic information database. Collect and organize representative emergency response plan texts from the power industry, manually extract information from these texts, and establish the database based on the extracted information. The manually extracted information from the representative emergency response plan texts includes: behavior name, scenario category, behavior tag, behavior role, and behavior keywords.

[0049] Based on the content of the information in the information database, various sub-databases are created. Each sub-database includes: a behavior name database, which is a standardized abbreviation of various behaviors in various emergency scenarios; a scenario category database, which is a collection of various scenario names; a behavior tag database, which is used to describe the relationships and commands of the main actors in the emergency plan; a behavior role database, which includes relevant personnel information, government departments and enterprises; and a behavior keyword database, which is used to summarize various behaviors in the emergency plan.

[0050] Step S4: Input the standardized scenario plan text and the information database into a bidirectional encoding pre-trained language model. In this embodiment, the bidirectional encoding pre-trained language model is the SBERT model (Sentence-BERT, a bidirectional encoding representation model for sentences). Perform semantic matching between the standardized scenario plan text and each sub-database in the information database to extract behavioral feature information.

[0051] The semantic matching of the standardized scenario plan text with each sub-database in the information database specifically includes: importing the standardized scenario plan text and the behavioral features in the information database into the SBERT model; the SBERT model encodes the imported standardized scenario plan text and the behavioral features through an encoder to obtain encoded scenario plan text sentences and encoded behavioral information; calculating cosine similarity based on the encoded scenario plan text sentences and the encoded behavioral information; and extracting the behavioral feature information based on the cosine similarity calculation result.

[0052] The expression for calculating the cosine similarity is:

[0053]

[0054] Where a represents the encoded scenario plan text sentence expressed as a vector after encoding, b represents the encoded behavioral information expressed as a vector, and θ represents the angle between vectors a and b.

[0055] The degree to which the cosine similarity cosθ approaches 1 is determined. The higher the degree to which the cosine similarity cosθ approaches 1, the higher the similarity between the scenario plan text sentence and the behavioral information.

[0056] The degree to which the cosine similarity cosθ approaches 0 is determined. The higher the degree to which the cosine similarity cosθ approaches 0, the lower the similarity between the scenario plan text sentence and the behavioral information.

[0057] Calculate cosine similarity and use the scenario plan text sentence with the highest cosine similarity as the output of each behavioral information, thereby extracting key behavioral feature information such as behavioral name, scenario category, behavioral label, behavioral role and behavioral keywords from the scenario plan text.

[0058] Step S5: Invoke the ChatGLM model, input the scenario description and the behavioral feature information into the ChatGLM model to generate behavioral description information;

[0059] Step S6: Construct a structured emergency plan template generation module. Input the scenario description, the behavioral feature information, and the behavioral description information into the structured emergency plan template generation module to obtain a structured emergency plan template for a specific scenario.

[0060] The aforementioned module for constructing a structured emergency plan template and the module for obtaining a structured emergency plan template for a specific scenario specifically include: calling a Python library for processing Excel files; in this embodiment, the Python library for processing Excel files is the Openpyxl library. The module for constructing the structured emergency plan template inputs the scenario description, the behavioral feature information, and the behavioral description information into the Excel-formatted structured emergency plan base template in the module to obtain a structured emergency plan template for a specific scenario.

[0061] The basic template for the structured plan in EXCEL format is an EXCEL document generated by calling the Openpyxl library, and the format is shown in the table below:

[0062]

[0063] In summary, traditional emergency response plan template generation requires manual selection of behavior names, scenario categories, behavior tags, behavior keywords, and behavior roles. The automatic generation method for structured emergency response plan templates in the power industry proposed in this embodiment extracts key information from unstructured text using ChatGLM and SBERT models, significantly reducing template generation time and labor intensity. Furthermore, the extraction method based on a large language model offers higher accuracy, greatly reducing errors caused by manual operation. In the semantic matching proposed in this embodiment, by constructing a structured emergency response plan basic information database, semantic matching is only required between sentences in the standardized scenario plan text and the behavior information in the database, greatly reducing the model's computational load, improving its operational efficiency, and enabling rapid generation of emergency response plan templates. Traditional emergency response plan templates require manual creation of Excel spreadsheets. This embodiment, however, constructs a structured emergency response plan template generation module. By calling a Python library for processing Excel files, it builds a basic structured emergency response plan template in Excel format. Simply import the extracted scenario information, behavioral feature information, and behavioral description information into the structured emergency response plan template generation module to generate a structured emergency response plan template for a specific scenario, further improving the efficiency of emergency response plan template generation.

[0064] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0065] It should be noted that the apparatus and methods disclosed in the embodiments herein can also be implemented in other ways. The apparatus embodiments described above are merely illustrative; for example, the flowcharts and block diagrams in the accompanying drawings show the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments herein. In this regard, each block in a flowchart or block diagram may represent a module, program, or part of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system to perform the specified function or action, or can be implemented using a combination of dedicated hardware and computer instructions.

[0066] In addition, the functional modules in the various embodiments of this article can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0067] Although the present invention has been described in detail through the preferred embodiments above, it should be understood that the above description should not be considered as a limitation of the present invention. Various modifications and substitutions to the present invention will be apparent to those skilled in the art after reading the above description. Therefore, the scope of protection of the present invention should be defined by the appended claims.

Claims

1. A method for automatically generating structured emergency response plan templates in the power industry, characterized in that, include: Step S1: Establish standards for writing power scenario contingency plans, standardize the format of unstructured scenario contingency plan texts, and obtain standardized scenario contingency plan texts; Step S2: Input the standardized scenario contingency plan text into the generative large language model, extract scenario information from the standardized scenario contingency plan text, and generate a scenario description; Step S3: Establish a structured emergency response plan basic information database; Step S4: Input the standardized scenario plan text and the information database into the bidirectional encoding pre-trained language model, and perform semantic matching between the standardized scenario plan text and each sub-database in the information database to extract behavioral feature information. Specifically, the semantic matching between the standardized scenario plan text and each sub-database in the information database includes: importing the standardized scenario plan text and the behavioral features from the information database into the bidirectional encoding pre-trained language model; encoding the imported standardized scenario plan text and the behavioral features using an encoder to obtain encoded scenario plan text sentences and encoded behavioral information; calculating cosine similarity based on the encoded scenario plan text sentences and the encoded behavioral information; and extracting the behavioral feature information based on the cosine similarity calculation result. Step S5: Invoke the generative large language model, input the scenario description and the behavioral feature information into the generative large language model to generate behavioral description information; Step S6: Construct a structured emergency plan template generation module. Input the scenario description, the behavioral feature information, and the behavioral description information into the structured emergency plan template generation module to obtain a structured emergency plan template for a specific scenario.

2. The method for automatically generating structured emergency response plan templates for the power industry as described in claim 1, characterized in that, The step S1, which involves establishing standards for writing power scenario contingency plans and standardizing the format of unstructured scenario contingency plan texts to obtain standardized scenario contingency plan texts, specifically includes: The content of the power scenario contingency plan text includes: scenario name, scenario category, scenario tag, and detailed scenario description.

3. The method for automatically generating structured emergency response plan templates for the power industry as described in claim 1, characterized in that, The scenario information extracted in step S2 specifically includes: scenario name, scenario category, and scenario tag. Based on the extracted scenario information, a scenario description is generated using the generative large language model.

4. The method for automatically generating structured emergency response plan templates for the power industry as described in claim 1, characterized in that, The establishment of a structured emergency response plan basic information database in step S3 specifically includes: collecting and organizing representative emergency response plan texts from the power industry, manually extracting information from the representative emergency response plan texts from the power industry, and establishing the information database based on the extracted information from the representative emergency response plan texts from the power industry.

5. The method for automatically generating structured emergency response plan templates for the power industry as described in claim 4, characterized in that, The information extracted manually from the representative emergency response plan texts of the power industry includes: behavior name, scenario category, behavior tag, behavior role, and behavior keyword.

6. The method for automatically generating structured emergency response plan templates in the power industry as described in claim 4, characterized in that, Each sub-database of the information database is created based on the content of the information in the information database. Each sub-database of the information database includes: A behavior name database, which provides standardized abbreviations for various behaviors in different emergency scenarios; A scene category library, which is a collection of various scene names; A behavior tag library, which is used to describe the relationships and commands of the actors in an emergency plan; A behavioral role database, which includes information on relevant personnel, government departments, and enterprises; A behavioral keyword library is used to summarize various behaviors in emergency response plans.

7. The method for automatically generating structured emergency response plan templates for the power industry as described in claim 1, characterized in that, The expression for calculating the cosine similarity is: Where a represents the encoded scenario plan text sentence expressed as a vector, b represents the encoded behavioral information expressed as a vector, and θ represents the angle between vectors a and b.

8. The method for automatically generating structured emergency response plan templates for the power industry as described in claim 7, characterized in that, Based on the similarity calculated using the cosine similarity, the similarity between the scenario-based solution text sentence and the behavioral information is determined, specifically: The degree to which the cosine similarity cosθ approaches 1 is determined. The higher the degree to which the cosine similarity cosθ approaches 1, the higher the similarity between the scenario plan text sentence and the behavioral information. The degree to which the cosine similarity cosθ approaches 0 is determined. The higher the degree to which the cosine similarity cosθ approaches 0, the lower the similarity between the scenario plan text sentence and the behavioral information.

9. The method for automatically generating structured emergency response plan templates for the power industry as described in claim 1, characterized in that, In step S6, the construction of the structured emergency plan template generation module and the obtaining of the structured emergency plan template for a specific scenario specifically include: By calling a Python library for processing Excel files, a structured emergency plan template generation module is constructed. The scenario description, the behavioral feature information, and the behavioral description information are input into the Excel-format structured emergency plan basic template in the structured emergency plan template generation module to obtain a structured emergency plan template for a specific scenario.

Images