Substation flood prevention emergency case recommendation method and device, electronic equipment and medium
By preprocessing the historical flood prevention case data of the substation and processing neural network models, and building a flood prevention map structure with knowledge graphs, the problems of inaccurate and low efficiency of flood prevention decision recommendations are solved, intelligent flood prevention case recommendations are achieved, and decision-making accuracy and efficiency are improved.
Patent Information
- Application Number
- CN202411667916.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-21
- Publication Date
- 2025-03-18
AI Technical Summary
In the flood control and operation and maintenance of substations, massive historical case data need to be processed manually, which is time-consuming and easy to cause subjective errors, and the recommendations for flood control decisions are inaccurate and inefficient.
Provide a method for recommending flood prevention emergency case cases in substations. By pre-processing the data of historical flood prevention case data, inputting it into the neural network model to obtain flood prevention entities, and constructing a flood prevention graph structure based on the knowledge graph, mapping the entity into the graph structure, and finally inputting the cases to be input into the historical graph structure to obtain the recommended cases.
Through the intelligent search and knowledge reasoning functions of the knowledge graph, intelligent recommendation of flood prevention cases can be realized, and the accuracy and efficiency of flood prevention decision recommendations are improved.
Smart Images
Figure CN119646205A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, electronic equipment and medium for recommending flood prevention emergency cases for a substation. Background Art
[0003] In the flood control operation and maintenance of substations, a large number of historical cases are recorded in the form of text data, which contains rich knowledge about substation "material reserves" and "flood control measures". However, these massive data usually need to be processed manually, which is not only time-consuming but also prone to subjective errors. In addition, when floods occur, managers usually rely on their own experience and knowledge to make decisions, which is often highly subjective and limited, resulting in inaccurate and inefficient flood control decision recommendations. Summary of the invention
[0004] In view of this, it is necessary to provide a substation flood control emergency case recommendation method, device, electronic equipment and medium to solve the problems of inaccurate and low efficiency of flood control decision recommendations.
[0005] In order to solve the above problems, the present invention provides a method for recommending flood control emergency cases for substations, comprising: Perform data preprocessing on the historical flood prevention case data of the substation to obtain preprocessed data; The preprocessed data is input into the preset neural network model to obtain the substation flood control entity; Construct flood prevention graph structure for substation flood prevention based on knowledge graph; Mapping the substation flood control entity to a flood control graph structure to obtain a historical flood control graph structure; The substation flood prevention case to be input is input into the historical flood prevention graph structure to obtain a recommended substation flood prevention case of the substation flood prevention case to be input.
[0006] In a possible implementation, the substation flood prevention entity includes: one or more of the substation name, the name of the city where it is located, the geographical location of the site, the flood prevention risk of the site, flood prevention measures, and material reserves.
[0007] In a possible implementation, preprocessing the historical flood prevention case data of the substation to obtain the preprocessed data includes: Based on the specialized vocabulary in the power sector, a specialized dictionary in the power sector is constructed; Based on the electric power field-specific dictionary and the Jieba word segmentation algorithm, the substation historical flood prevention case data is segmented to obtain the pre-processed data after word segmentation.
[0008] In a possible implementation, the flood prevention graph structure of substation flood prevention is constructed based on the knowledge graph, including: Based on the knowledge graph, the flood prevention measures of substations are taken as nodes and the risk levels are used as node labels. A semantic network is constructed in the form of nodes and edges to obtain the flood prevention graph structure of substation flood prevention.
[0009] In a possible implementation, inputting the substation flood prevention case to be input into the historical flood prevention graph structure to obtain a recommended substation flood prevention case of the substation flood prevention case to be input includes: The substation flood prevention cases to be input are input into the historical flood prevention graph structure, and the recommended substation flood prevention cases of the substation flood prevention cases to be input are obtained based on similarity calculation.
[0010] In a possible implementation, obtaining the recommended substation flood prevention case to be input as the substation flood prevention case based on similarity calculation includes: Get the portrait of the substation flood prevention case to be input; Calculate the cosine similarity between the portrait of the substation flood prevention case to be input and each case portrait in the historical flood prevention graph structure to obtain a similarity score; Sorting in descending order according to the similarity scores to obtain a recommended list of substation flood prevention cases; A recommended substation flood prevention case for the substation flood prevention case to be input is determined based on the substation flood prevention case recommendation list.
[0011] In a possible implementation, the step of obtaining the portrait of the substation flood prevention case to be input includes: Obtain the feature vector of each entity in the substation flood prevention case to be input; The feature vector is subjected to TF-IDF and category weighting to obtain a portrait of the substation flood prevention case to be input.
[0012] On the other hand, the present invention also provides a substation flood prevention emergency case recommendation device, comprising: A data preprocessing module is used to preprocess the historical flood prevention case data of the substation to obtain preprocessed data; The substation flood control entity acquisition module is used to input the preprocessed data into a preset neural network model to obtain the substation flood control entity; Substation flood control graph structure acquisition module, used to construct the substation flood control graph structure based on the knowledge graph; A historical flood control image acquisition module is used to map the substation flood control entity to the flood control map structure to obtain a historical flood control map structure; The data preprocessing module is used to input the substation flood prevention cases to be input into the historical flood prevention graph structure to obtain the recommended substation flood prevention cases of the substation flood prevention cases to be input.
[0013] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in a substation flood control emergency case recommendation method described in any one of the above implementations.
[0014] On the other hand, the present invention also provides a computer-readable storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can implement the steps in a substation flood control emergency case recommendation method described in any of the above-mentioned implementation methods.
[0015] The beneficial effects of the present invention are as follows: a method for recommending substation flood control emergency cases provided by the present invention first inputs preprocessed data into a preset neural network model to obtain a substation flood control entity, thereby obtaining standardized data, and then constructs a flood control graph structure of substation flood control based on a knowledge graph, and further maps the substation flood control entity into the flood control graph structure to obtain a historical flood control graph structure, thereby more intuitively matching data, and finally inputs the substation flood control case to be input into the historical flood control image to obtain a recommended substation flood control case of the substation flood control case to be input. The present invention realizes intelligent recommendation of flood control cases through the intelligent retrieval and knowledge reasoning functions of the knowledge graph, thereby improving the accuracy and efficiency of flood control decision recommendations. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Figure 1 A flowchart of an embodiment of a method for recommending flood prevention emergency cases for substations provided by the present invention; Figure 2 For the present invention Figure 1 A schematic flow chart of an embodiment of S102; Figure 3 A schematic flow chart of an embodiment of a device for recommending flood emergency cases for substations provided by the present invention; Figure 4 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION
[0017] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.
[0018] Before presenting the embodiments, the following terms are explained.
[0019] A knowledge graph (KG) is a directed labeled graph whose nodes represent entities or concepts in the real world and whose edges describe the relationships between nodes. This structured data format has shown significant utility in many fields such as biology and finance. Knowledge graphs can not only effectively model the relationships between entities, but also provide a deep understanding of lexical semantics through their context or neighboring nodes. The data in a knowledge graph is usually represented in the form of (subject, object, predicate) triples, and a specialized graph database is usually used to manage and query the data.
[0020] Graph databases (such as Neo4j and Amazon Neptune) can efficiently process and store graph structured data and support complex graph query and analysis operations. This storage method can not only process large-scale data, but also support dynamic updating and expansion of graphs. Through graph databases, efficient relationship query, pattern matching, and graph analysis can be achieved, thereby providing rich knowledge support for various applications. This storage mechanism enables knowledge graphs to quickly respond to and adapt to new knowledge and relationship changes in practical applications.
[0021] The present invention provides a method, device, electronic equipment and medium for recommending flood prevention emergency cases for a substation, which are described below respectively.
[0022] Figure 1 A schematic flow chart of an embodiment of a method for recommending flood emergency cases for substations provided by the present invention is shown in FIG. Figure 1 As shown in the figure, the recommended method for substation flood emergency case includes: S101, preprocessing the historical flood prevention case data of the substation to obtain preprocessed data; S102, inputting the preprocessed data into a preset neural network model to obtain a substation flood control entity; S103, constructing a flood prevention graph structure for substation flood prevention based on the knowledge graph; S104, mapping the substation flood control entity to a flood control graph structure to obtain a historical flood control graph structure; S105 , inputting the substation flood prevention case to be input into the historical flood prevention graph structure, and obtaining a recommended substation flood prevention case of the substation flood prevention case to be input.
[0023] Compared with the prior art, the present embodiment provides a method for recommending substation flood emergency cases, firstly inputting the preprocessed data into a preset neural network model to obtain a substation flood prevention entity, thereby obtaining standardized data, then constructing a flood prevention graph structure of substation flood prevention based on a knowledge graph, further mapping the substation flood prevention entity into the flood prevention graph structure to obtain a historical flood prevention graph structure, thereby more intuitively matching data, and finally inputting the substation flood prevention case to be input into the historical flood prevention image to obtain a recommended substation flood prevention case of the substation flood prevention case to be input. The present invention realizes intelligent recommendation of flood prevention cases through the intelligent retrieval and knowledge reasoning functions of the knowledge graph, thereby improving the accuracy and efficiency of flood prevention decision recommendations.
[0024] In some embodiments of the present invention, the substation flood prevention entity includes: one or more of the substation name, the name of the city where it is located, the geographical location of the site, the flood prevention risk of the site, flood prevention measures and material reserves.
[0025] In some embodiments of the present invention, in step S101, Figure 2 As shown, the data preprocessing of the substation historical flood prevention case data to obtain the preprocessed data includes: Based on the specialized vocabulary in the power sector, a specialized dictionary in the power sector is constructed; Based on the electric power field-specific dictionary and the Jieba word segmentation algorithm, the substation historical flood prevention case data is segmented to obtain the pre-processed data after word segmentation.
[0026] In a specific embodiment of the present invention, a large amount of structured and unstructured text data is manually recorded in the long-term flood prevention work. Structured text data usually exists in the form of a table, contains clear fields and formats, covers basic information such as substation name, voltage level, geographical location, site elevation, etc., and is relatively simple to process and analyze; unstructured text data consists of flood prevention material reserves and flood prevention risks and measures data, including information such as material quantity, material storage location, flood prevention risks, potential hidden dangers, and historical flood prevention measures and effects, and has problems such as colloquialism and non-standard records.
[0027] The sources of unstructured substation flood control text data include web page information, HTML files and table information, etc., which have problems such as multi-source heterogeneity and information missing. Regular expressions, case conversion and other methods are used to clean the data.
[0028] There are a lot of professional terms in the substation flood control text, such as "storage and discharge flood", "strong drainage valve" and "waterproof plugging material". It is difficult to correctly segment it with the commonly used word segmentation method, so a custom dictionary will be used to complete the task.
[0029] The power equipment defect text contains a large number of words and symbols without actual meaning, such as "ne", "le", "%", etc., which seriously damage the processing efficiency of the computer. A stop word dictionary will be used to record these words and symbols, and then delete them to simplify the power equipment defect text.
[0030] According to the characteristics of substation flood prevention text, a custom dictionary was created and the text was preprocessed to complete the standardization and normalization of flood prevention text.
[0031] It should be noted that the preset neural network model is transformer, and it can be understood that it can also be other neural network models. In a specific embodiment of the present invention, entity recognition is performed on the preprocessed data based on transformer to obtain the substation flood control entity, and then the relationship of the substation flood control entity is extracted to obtain the substation historical flood control case table, and the substation historical flood control case table is mapped to the graph database to obtain the knowledge graph of the substation historical flood control case.
[0032] In some embodiments of the present invention, the flood prevention graph structure of substation flood prevention is constructed based on the knowledge graph, including: Based on the knowledge graph, the flood prevention measures of substations are taken as nodes and the risk levels are used as node labels. A semantic network is constructed in the form of nodes and edges to obtain the flood prevention graph structure of substation flood prevention.
[0033] In some embodiments of the present invention, the step of inputting the substation flood prevention case to be input into the historical flood prevention graph structure to obtain the recommended substation flood prevention case of the substation flood prevention case to be input includes: The substation flood prevention cases to be input are input into the historical flood prevention graph structure, and the recommended substation flood prevention cases of the substation flood prevention cases to be input are obtained based on similarity calculation.
[0034] In some embodiments of the present invention, obtaining the recommended substation flood prevention case to be input as the substation flood prevention case based on similarity calculation includes: Get the portrait of the substation flood prevention case to be input; Calculate the cosine similarity between the portrait of the substation flood prevention case to be input and each case portrait in the historical flood prevention graph structure to obtain a similarity score; Sorting in descending order according to the similarity scores to obtain a recommended list of substation flood prevention cases; A recommended substation flood prevention case for the substation flood prevention case to be input is determined based on the substation flood prevention case recommendation list.
[0035] In some embodiments of the present invention, obtaining the portrait of the substation flood prevention case to be input includes: Obtain the feature vector of each entity in the substation flood prevention case to be input; The feature vector is subjected to TF-IDF and category weighting to obtain a portrait of the substation flood prevention case to be input.
[0036] In a specific embodiment of the present invention, TF-IDF and category weighting are performed on the flood control entities in the case to obtain the portrait representation of the case, realize the substation flood control portrait embedding (Figure Embedding, FE), and perform similarity calculation based on this. When performing similarity calculation, the extracted flood control entity vector representation is subjected to TF-IDF feature weighting and category weighting respectively to obtain the portrait representation of the flood control case. , entity The feature weight calculation formula is:
[0037] In the formula, is the flood control entity vector; for The flood prevention cases include The number of is the total frequency of all entities in the flood control case; represents the total number of all cases in the flood control database; To contain entities The number of cases.
[0038] Specifically, for example, in the flood prevention case, "The flood risk of River X is high, and substation Y is at risk." The entities in this sentence and their occurrence times are "flood risk" 1 time, "River X" 1 time, and "substation Y" 1 time. The term frequency (TF) of each entity is as follows: TF(flood risk) = 1 / 7 = 0.1428 (the sentence has 7 words) TF(X River)=1 / 7=0.1428 TFY(substation)=1 / 7=0.1428 To further calculate the inverse document frequency, assume that there are 1,000 cases in the knowledge base, “flood risk” appears in 500 cases, “River X” appears in 300 cases, and “Substation Y” appears in 200 cases.
[0039]
[0040] is the total number of documents in the knowledge base (1000), is the number of documents containing the term.
[0041] IDF calculation of flood risk:
[0042] Similarly:
[0043] further
[0044] Flood risk:
[0045]
[0046] The weights of different categories are preset according to the importance and relevance of the roles of different entities in different categories. For example, "Y substation" may be more important in the "flood prevention and control measures" category than in the "flood risk" category.
[0047] Assumption: The category weighting for "Y substation" is: , corresponding categories: 1. Flood risk, 2. Substation name, 3. Flood prevention and control measures, 4. Material reserves. The category weighting of "Flood risk" is: , the category weight of "River X" is: .
[0048] The above specifically introduces the TF-DF and category weighting of the entity of the flood prevention case "The flood risk of River X is high, and substation Y is at risk." Then, the portrait of the case is obtained based on the TF-DF and category weighting of the entity. The portrait represents The calculation formula is:
[0049] In the formula, the category weight They represent the weights of the categories to which the entity nodes belong, namely, the substation name, the city name, the site geographical location, the site flood prevention risk, the site flood prevention measures and the site material reserves; the category vector Represents the set of all vectors belonging to the category.
[0050] According to the flood prevention case "The flood risk of River X is high and substation Y is at risk." The TF-DF and category weighting of the entity are used to obtain the portrait of the case, as follows: For "Y Substation":
[0051] On "flood risk"
[0052] About "River X"
[0053] After obtaining the portrait representation of the input flood control case, the cosine similarity between it and the portrait representation of the historical flood control case is calculated. The formula is:
[0054] In the formula, , Represent the input and historical flood control case portrait representation vectors respectively.
[0055] After obtaining the portrait of the flood prevention case "The flood risk of River X is very high, and substation Y is at risk.", the similarity between this flood prevention case and the flood prevention cases in the knowledge graph is calculated as follows: Calculate the similarity between the flood prevention case "River X has a high flood risk and substation Y is at risk." and the portrait representation of the existing cases in the knowledge base. Use cosine similarity to measure:
[0056] Suppose we want to compare the icon representations of sentences related to “Y substation” with existing examples.
[0057] The portrait representation of the current sentence (the result calculated above):
[0058] Iconic representation of existing cases (assumed values):
[0059] Cosine similarity calculation: First calculate the dot product and the modulus of the vector:
[0060]
[0061] Final similarity:
[0062] This similarity score is used to identify the similarity between the flood prevention case "The flood risk of the X River is high, and the Y substation is at risk." and the historical cases in the knowledge graph. The higher the score, the more similar the two are, thus obtaining cases similar to the flood prevention case "The flood risk of the X River is high, and the Y substation is at risk."
[0063] In order to better implement a method for recommending flood emergency cases for substations in an embodiment of the present invention, based on a method for recommending flood emergency cases for substations, correspondingly, Figure 3 As shown, the embodiment of the present invention further provides a substation flood control emergency case recommendation device, a substation flood control emergency case recommendation device 300 includes: The data preprocessing module 301 is used to preprocess the historical flood prevention case data of the substation to obtain preprocessed data; The substation flood control entity acquisition module 302 is used to input the pre-processed data into a preset neural network model to obtain the substation flood control entity; A substation flood prevention graph structure acquisition module 303 is used to construct a substation flood prevention graph structure based on a knowledge graph; A historical flood control image acquisition module 304 is used to map the substation flood control entity to the flood control map structure to obtain a historical flood control map structure; The data preprocessing module 305 is used to input the substation flood prevention cases to be input into the historical flood prevention graph structure to obtain the recommended substation flood prevention cases of the substation flood prevention cases to be input.
[0064] The substation flood control emergency case recommendation device 300 provided in the above embodiment can implement the technical solution described in the above embodiment of the substation flood control emergency case recommendation method. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above embodiment of the substation flood control emergency case recommendation method, which will not be repeated here.
[0065] like Figure 4 As shown, the present invention also provides an electronic device 400. The electronic device 400 includes a processor 401, a memory 402 and a display 403. Figure 4 Only some components of the electronic device 400 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.
[0066] In some embodiments, the processor 401 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 402, such as a substation flood emergency case recommendation method in the present invention.
[0067] In some embodiments, processor 401 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, processor 401 may be local or remote. In some embodiments, processor 401 may be implemented in a cloud platform. In some embodiments, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination thereof.
[0068] In some embodiments, the memory 402 may be an internal storage unit of the electronic device 400, such as a hard disk or memory of the electronic device 400. In other embodiments, the memory 402 may also be an external storage device of the electronic device 400, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 400.
[0069] Furthermore, the memory 402 may include both an internal storage unit of the electronic device 400 and an external storage device. The memory 402 is used to store application software installed in the electronic device 400 and various data.
[0070] In some embodiments, the display 403 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 403 is used to display information on the electronic device 400 and to display a visual user interface. The components 401-403 of the electronic device 400 communicate with each other via a system bus.
[0071] In one embodiment, when the processor 401 executes a substation flood prevention emergency case recommendation program in the memory 402, the following steps may be implemented: Perform data preprocessing on the historical flood prevention case data of the substation to obtain preprocessed data; The preprocessed data is input into the preset neural network model to obtain the substation flood control entity; Construct flood prevention graph structure for substation flood prevention based on knowledge graph; Mapping the substation flood control entity to a flood control graph structure to obtain a historical flood control graph structure; The substation flood prevention case to be input is input into the historical flood prevention graph structure to obtain a recommended substation flood prevention case of the substation flood prevention case to be input.
[0072] It should be understood that: when the processor 401 executes a substation flood control emergency case recommendation program in the memory 402, in addition to the above functions, other functions can also be implemented. For details, please refer to the description of the corresponding method embodiment above.
[0073] Furthermore, the embodiment of the present invention does not specifically limit the type of the electronic device 400 mentioned, and the electronic device 400 may be a portable electronic device such as a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, etc. Exemplary embodiments of portable electronic devices include but are not limited to portable electronic devices equipped with IOS, Android, Microsoft or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 400 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (e.g., a touch panel).
[0074] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.
[0075] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.
Claims
1. A method for recommending flood emergency cases for substations, characterized in that: include: Perform data preprocessing on the historical flood prevention case data of the substation to obtain preprocessed data; The preprocessed data is input into the preset neural network model to obtain the substation flood control entity; Construct flood prevention graph structure for substation flood prevention based on knowledge graph; Mapping the substation flood control entity to a flood control graph structure to obtain a historical flood control graph structure; The substation flood prevention case to be input is input into the historical flood prevention graph structure to obtain a recommended substation flood prevention case of the substation flood prevention case to be input.
2. The method for recommending substation flood emergency cases according to claim 1, characterized in that: The substation flood prevention entity includes: one or more of the substation name, the name of the city where it is located, the geographical location of the site, the flood prevention risk of the site, flood prevention measures and material reserves.
3. The method for recommending substation flood emergency cases according to claim 1, characterized in that: The data preprocessing of the substation historical flood prevention case data to obtain the preprocessed data includes: Based on the specialized vocabulary in the power sector, a specialized dictionary in the power sector is constructed; Based on the electric power field-specific dictionary and the Jieba word segmentation algorithm, the substation historical flood prevention case data is segmented to obtain the pre-processed data after word segmentation.
4. The method for recommending substation flood emergency cases according to claim 1, characterized in that: The flood prevention graph structure of substation flood prevention is constructed based on the knowledge graph, including: Based on the knowledge graph, the flood prevention measures of substations are taken as nodes and the risk levels are used as node labels. A semantic network is constructed in the form of nodes and edges to obtain the flood prevention graph structure of substation flood prevention.
5. The method for recommending substation flood emergency cases according to claim 1, characterized in that: The step of inputting the substation flood prevention case to be input into the historical flood prevention graph structure to obtain the recommended substation flood prevention case of the substation flood prevention case to be input includes: The substation flood prevention cases to be input are input into the historical flood prevention graph structure, and the recommended substation flood prevention cases of the substation flood prevention cases to be input are obtained based on similarity calculation.
6. The method for recommending substation flood emergency cases according to claim 5, characterized in that: The recommended substation flood prevention case to be input based on similarity calculation includes: Get the portrait of the substation flood prevention case to be input; Calculate the cosine similarity between the portrait of the substation flood prevention case to be input and each case portrait in the historical flood prevention graph structure to obtain a similarity score; Sorting in descending order according to the similarity scores to obtain a recommended list of substation flood prevention cases; A recommended substation flood prevention case for the substation flood prevention case to be input is determined based on the substation flood prevention case recommendation list.
7. The method for recommending substation flood emergency cases according to claim 6, characterized in that: The obtaining of the portrait of the substation flood prevention case to be input includes: Obtain the feature vector of each entity in the substation flood prevention case to be input; The feature vector is subjected to TF-IDF and category weighting to obtain a portrait of the substation flood prevention case to be input.
8. A substation flood control emergency case recommendation device, characterized in that: include: A data preprocessing module is used to preprocess the historical flood prevention case data of the substation to obtain preprocessed data; The substation flood control entity acquisition module is used to input the preprocessed data into a preset neural network model to obtain the substation flood control entity; Substation flood control graph structure acquisition module, used to construct the substation flood control graph structure based on the knowledge graph; A historical flood control image acquisition module is used to map the substation flood control entity to the flood control map structure to obtain a historical flood control map structure; The data preprocessing module is used to input the substation flood prevention cases to be input into the historical flood prevention graph structure to obtain the recommended substation flood prevention cases of the substation flood prevention cases to be input.
9. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the substation flood control emergency case recommendation method described in any one of claims 1 to 7 above.
10. A computer-readable storage medium, characterized in that: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the substation flood control emergency case recommendation method described in any one of claims 1 to 7 above.