Automatic association method and system for power grid equipment defect text and technical supervision detailed rule

Abstract

The invention discloses a power grid equipment defect text and technical supervision detailed rule automatic association method and system. The method comprises the steps of extracting a first feature in target defect text data and at least one second feature in at least one target technical supervision detailed rule data; calculating the similarity between the first feature and the at least one second feature by adopting a multi-factor weighted matching method to obtain a comprehensive score of each similarity, and sorting the comprehensive scores of each similarity based on the score value to obtain a comprehensive score sequence of similarity; and selecting at least one target similarity comprehensive score from the similarity comprehensive score sequence according to a preset interception rule, and associating the defect text data corresponding to the at least one target similarity comprehensive score with the technical supervision detailed rule data. According to the method, related technicians can be helped to get rid of the traditional tedious process of manually searching information in a lengthy and complex document, and the necessary technical supervision information is rapidly extracted by using an intelligent association tool.

Description

Technical Field

[0001] The invention belongs to the technical field of power grid equipment defect repair, and in particular relates to a method and system for automatically associating power grid equipment defect text with technical supervision details. Background Art

[0002] The full life cycle management of power grid equipment, including planning, scientific research, equipment procurement, manufacturing, acceptance, installation, commissioning, and operation and maintenance, may face problems such as unreasonable design, material defects, improper installation, or poor maintenance. These problems not only affect the normal operation of the equipment, but also potentially threaten the safety of the power grid, and thus affect the stability and reliability of the power supply. Therefore, it is particularly important to promptly discover and effectively rectify these problems to ensure the safe and efficient operation of the power grid. However, there are many pain points in the current technical supervision of power grid equipment, which hinders the digital development of supervision standards. First, traditional technical supervision mainly relies on paper records and manual experience judgment, which is inefficient and error-prone. In the context of the increasing scale of the power grid and the complexity of the operating environment, this approach is difficult to meet the needs. Summary of the invention

[0003] The present invention provides a method and system for automatically associating power grid equipment defect text with technical supervision details, which are used to solve the technical problem that traditional technical supervision mainly relies on paper records and manual experience judgment, which is inefficient and prone to errors.

[0004] In a first aspect, the present invention provides a method for automatically associating a defect text of a power grid device with technical supervision details, comprising: Convert the preprocessed defect text data and at least one technical supervision rule data into a high-dimensional vector to obtain target defect text data and at least one target technical supervision rule data; Extracting a first feature from the target defect text data and at least one second feature from the at least one target technical supervision rule data, and normalizing the first feature and the at least one second feature according to a preset maximum-minimum scaling method to obtain a target first feature and at least one target second feature having the same scale; Calculating the similarity between the target first feature and the at least one target second feature using a multi-factor weighted matching method to obtain respective similarity comprehensive scores, and sorting the respective similarity comprehensive scores based on the score values ​​to obtain a similarity comprehensive score sequence; At least one target similarity comprehensive score is selected from the similarity comprehensive score sequence according to a preset interception rule, and the defect text data corresponding to the at least one target similarity comprehensive score is associated with the technical supervision details data to obtain an association result.

[0005] In a second aspect, the present invention provides a system for automatically associating power grid equipment defect text with technical supervision details, comprising: A conversion module is configured to convert the preprocessed defect text data and at least one technical supervision rule data into a high-dimensional vector to obtain target defect text data and at least one target technical supervision rule data; An extraction module is configured to extract a first feature from the target defect text data and at least one second feature from the at least one target technical supervision rule data, and normalize the first feature and the at least one second feature according to a preset maximum-minimum scaling method to obtain a target first feature and at least one target second feature having the same scale; a calculation module configured to calculate the similarity between the target first feature and the at least one target second feature using a multi-factor weighted matching method to obtain respective similarity comprehensive scores, and to sort the respective similarity comprehensive scores based on the score values ​​to obtain a similarity comprehensive score sequence; The association module is configured to select at least one target similarity comprehensive score in the similarity comprehensive score sequence according to a preset interception rule, and associate the defect text data and technical supervision details data corresponding to the at least one target similarity comprehensive score to obtain an association result.

[0006] According to a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the method for automatically associating defect text of power grid equipment with technical supervision details of any embodiment of the present invention.

[0007] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor executes the steps of the method for automatically associating defect text of power grid equipment with technical supervision details of any embodiment of the present invention.

[0008] The method and system for automatically associating defect texts of power grid equipment with technical supervision rules of the present application adopt a multi-factor weighted matching method to calculate the similarity between a target first feature and at least one target second feature to obtain each similarity comprehensive score, and sort each similarity comprehensive score based on the score value to obtain a similarity comprehensive score sequence; at least one target similarity comprehensive score is selected from the similarity comprehensive score sequence according to a preset truncation rule, and the defect text data and technical supervision rules data corresponding to at least one target similarity comprehensive score are associated, which can help relevant technical personnel get rid of the traditional tedious process of manually searching for information in lengthy and complex documents, and instead use intelligent association tools to quickly extract necessary technical supervision information, so as to make more accurate and rapid judgments and decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A flowchart of a method for automatically associating a power grid equipment defect text with technical supervision details provided by an embodiment of the present invention; Figure 2 A structural block diagram of a system for automatically associating defect texts of power grid equipment with technical supervision details provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0011] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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.

[0012] See also Figure 1 , which shows a flow chart of a method for automatically associating defect text of power grid equipment with technical supervision details of the present application.

[0013] like Figure 1 As shown, the method for automatically associating the power grid equipment defect text with the technical supervision rules specifically includes the following steps: Step S101, converting the preprocessed defect text data and at least one technical supervision rule data into a high-dimensional vector to obtain target defect text data and at least one target technical supervision rule data.

[0014] In this step, the defect text data of power grid equipment is carefully cleaned, including automatic correction of typos, removal of redundant and invalid characters, elimination of data noise, and identification and deletion of repeated technical supervision details to ensure data accuracy and consistency. Information such as voltage level, line location, and tower number that are not related to the defect description is extracted and removed, and only information directly related to the power grid equipment defects is retained, thereby generating structured and high-quality defect text data for subsequent embedding and matching analysis.

[0015] We extract high-frequency words and specific terms in professional fields from defect text data and technical supervision data of power grid equipment, and then build a custom vocabulary library, such as various equipment names, defect names, etc. Based on the common occurrence patterns of words in defect text data and technical supervision data and the mutual correlation between their semantics, we accurately capture and strengthen the semantic usage of these words in specific contexts.

[0016] In defect descriptions, certain domain-specific words and terms tend to co-occur frequently in specific patterns. By analyzing these co-occurrence patterns, the semantic tendencies of the words in the field of power equipment defects can be captured. For example, "overload" often co-occurs with "transformer" or "overheating", reflecting the semantic association of specific fault types.

[0017] Step S102, extracting a first feature from the target defect text data and at least one second feature from the at least one target technical supervision details data, normalizing the first feature and the at least one second feature according to a preset maximum-minimum scaling method, and obtaining a target first feature and at least one target second feature having the same scale.

[0018] Step S103, using a multi-factor weighted matching method to calculate the similarity between the target first feature and the at least one target second feature, obtaining each similarity comprehensive score, and sorting each similarity comprehensive score based on the score value to obtain a similarity comprehensive score sequence.

[0019] In this step, the target first feature and the target second feature both include semantic features, device characteristic features, risk level features, historical frequency features, and time effect features; The expression for calculating the similarity between the first feature of a target and at least one second feature of a target is: , In the formula, A comprehensive score for the similarity between the target first feature and the at least one target second feature, is the weight of semantic feature similarity, is the semantic feature similarity, is the weight of the similarity of device characteristics, is the device characteristic feature similarity, is the weight of risk level feature similarity, is the risk level feature similarity, is the weight of the historical frequency feature similarity, is the historical frequency feature similarity, is the weight of the time effect feature similarity, is the time effect feature similarity.

[0020] The expression for calculating the similarity of semantic features is: , In the formula, The value range of is [0,1], is the normalized cosine similarity, Embedding vector for power grid equipment defect text, Embed vectors for technical supervision rules, is the modulus of the semantic vector.

[0021] If the category number of the defective equipment is the same as the number of the applicable equipment in the technical supervision rules, the similarity score is 1, otherwise it is 0. The expression for calculating the similarity of the equipment characteristics is: .

[0022] The expression for calculating the similarity of risk level features is: , In the formula, is the risk level of the equipment defect, is the risk level of the technical supervision rules, Equals 3.

[0023] The expression for calculating the similarity of historical frequency features is: , In the formula, is the historical matching frequency of defects and supervision details, is the total defect history matching count, is the inverse frequency.

[0024] The expression for calculating the similarity of time effect features is: , In the formula, Represents the frequency statistics of each type of defect occurring in 12 months, The frequency statistics of each type of defect occurring in January, The frequency statistics of each type of defect occurring in February, The frequency statistics of each type of defect occurring in December, Represents the frequency statistics of each supervisory rule applied in 12 months, For each supervision rule, the frequency of application in January is counted. For each supervision rule, the frequency of application in February is counted. For each supervision rule, the frequency of application in December is counted. is the frequency statistics of each type of defect in the i-th month, is the frequency statistics of application of each supervisory rule in the i-th month.

[0025] It should be noted that the initial weights are first set according to the importance of each type of feature, and then the weights are adjusted according to the matching success rate of the defect text data of the collected power grid equipment and the technical supervision details data to obtain the optimal weights. Thereafter, the weights are dynamically adjusted according to the matching success rate of the defect text data of the power grid equipment and the technical supervision details data newly collected last month.

[0026] Step S104, selecting at least one target similarity comprehensive score in the similarity comprehensive score sequence according to a preset interception rule, and associating the defect text data and technical supervision details data corresponding to the at least one target similarity comprehensive score to obtain an association result.

[0027] In this step, according to the characteristic that the defect problem may correspond to multiple technical supervision regulations, the three target similarity comprehensive scores with the highest scores are selected in the similarity comprehensive score sequence, and the defect text data and the technical supervision regulations data corresponding to the three target similarity comprehensive scores are associated to obtain the association result.

[0028] In summary, the method of the present application adopts a multi-factor weighted matching method to calculate the similarity between a target first feature and at least one target second feature, obtains each similarity comprehensive score, and sorts each similarity comprehensive score based on the score value to obtain a similarity comprehensive score sequence; selects at least one target similarity comprehensive score in the similarity comprehensive score sequence according to a preset truncation rule, and associates the defect text data and technical supervision details data corresponding to at least one target similarity comprehensive score, which can help relevant technical personnel get rid of the traditional tedious process of manually searching for information in lengthy and complex documents, and instead use intelligent association tools to quickly extract necessary technical supervision information, so as to make more accurate and rapid judgments and decisions.

[0029] See also Figure 2 , which shows a structural block diagram of a system for automatically associating defect texts of power grid equipment with technical supervision details of the present application.

[0030] like Figure 2 As shown, the automatic association system 200 includes a conversion module 210 , an extraction module 220 , a calculation module 230 and an association module 240 .

[0031] Among them, the conversion module 210 is configured to convert the preprocessed defect text data and at least one technical supervision details data into a high-dimensional vector to obtain the target defect text data and at least one target technical supervision details data; the extraction module 220 is configured to extract the first feature in the target defect text data and at least one second feature in the at least one target technical supervision details data, and normalize the first feature and the at least one second feature according to a preset maximum-minimum scaling method to obtain a target first feature and at least one target second feature with the same scale; the calculation module 230 is configured to use a multi-factor weighted matching method to calculate the similarity between the target first feature and the at least one target second feature to obtain each similarity comprehensive score, and sort each similarity comprehensive score based on the score value to obtain a similarity comprehensive score sequence; the association module 240 is configured to select at least one target similarity comprehensive score in the similarity comprehensive score sequence according to a preset truncation rule, and associate the defect text data and the technical supervision details data corresponding to the at least one target similarity comprehensive score to obtain an association result.

[0032] It should be understood that Figure 2 Modules and references documented in Figure 1 Therefore, the operations and features described above for the method and the corresponding technical effects are also applicable to Figure 2 The modules in it will not be described in detail here.

[0033] In other embodiments, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor executes the method for automatically associating a defect text of a power grid device with technical supervision details in any of the above method embodiments; As an implementation mode, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are configured as follows: Convert the preprocessed defect text data and at least one technical supervision rule data into a high-dimensional vector to obtain target defect text data and at least one target technical supervision rule data; Extracting a first feature from the target defect text data and at least one second feature from the at least one target technical supervision rule data, and normalizing the first feature and the at least one second feature according to a preset maximum-minimum scaling method to obtain a target first feature and at least one target second feature having the same scale; Calculating the similarity between the target first feature and the at least one target second feature using a multi-factor weighted matching method to obtain respective similarity comprehensive scores, and sorting the respective similarity comprehensive scores based on the score values ​​to obtain a similarity comprehensive score sequence; At least one target similarity comprehensive score is selected from the similarity comprehensive score sequence according to a preset interception rule, and the defect text data corresponding to the at least one target similarity comprehensive score is associated with the technical supervision details data to obtain an association result.

[0034] The computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required for at least one function; the data storage area may store data created according to the use of the automatic association system of the defect text of the power grid equipment and the technical supervision rules, etc. In addition, the computer-readable storage medium may include a high-speed random access memory, and may also include a memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the automatic association system of the defect text of the power grid equipment and the technical supervision rules via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0035] Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3 As shown, the device includes: a processor 310 and a memory 320. The electronic device may also include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330 and the output device 340 may be connected via a bus or other means. Figure 3In the example, the connection through the bus is taken as an example. The memory 320 is the above-mentioned computer-readable storage medium. The processor 310 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 320, that is, the method for automatically associating the defect text of power grid equipment with the technical supervision details of the above-mentioned method embodiment is realized. The input device 330 can receive input digital or character information, and generate key signal input related to the user settings and function control of the automatic association system of the defect text of power grid equipment with the technical supervision details. The output device 340 may include a display device such as a display screen.

[0036] The electronic device can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0037] As an implementation mode, the electronic device is applied to an automatic association system of power grid equipment defect text and technical supervision rules, and is used for a client, and includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: Convert the preprocessed defect text data and at least one technical supervision rule data into a high-dimensional vector to obtain target defect text data and at least one target technical supervision rule data; Extracting a first feature from the target defect text data and at least one second feature from the at least one target technical supervision rule data, and normalizing the first feature and the at least one second feature according to a preset maximum-minimum scaling method to obtain a target first feature and at least one target second feature having the same scale; Calculating the similarity between the target first feature and the at least one target second feature using a multi-factor weighted matching method to obtain respective similarity comprehensive scores, and sorting the respective similarity comprehensive scores based on the score values ​​to obtain a similarity comprehensive score sequence; At least one target similarity comprehensive score is selected from the similarity comprehensive score sequence according to a preset interception rule, and the defect text data corresponding to the at least one target similarity comprehensive score is associated with the technical supervision details data to obtain an association result.

[0038] Through the description of the above implementation modes, those skilled in the art can clearly understand that each implementation mode can be implemented by means of software plus a necessary general hardware platform, or of course by hardware. Based on such an understanding, the above technical solution can essentially or in other words be embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0039] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for automatically associating power grid equipment defect text with technical supervision details, characterized in that: include: Convert the preprocessed defect text data and at least one technical supervision rule data into a high-dimensional vector to obtain target defect text data and at least one target technical supervision rule data; Extracting a first feature from the target defect text data and at least one second feature from the at least one target technical supervision rule data, and normalizing the first feature and the at least one second feature according to a preset maximum-minimum scaling method to obtain a target first feature and at least one target second feature having the same scale; Calculating the similarity between the target first feature and the at least one target second feature using a multi-factor weighted matching method to obtain respective similarity comprehensive scores, and sorting the respective similarity comprehensive scores based on the score values ​​to obtain a similarity comprehensive score sequence; At least one target similarity comprehensive score is selected from the similarity comprehensive score sequence according to a preset interception rule, and the defect text data corresponding to the at least one target similarity comprehensive score is associated with the technical supervision details data to obtain an association result.

2. The method for automatically associating power grid equipment defect text with technical supervision details according to claim 1, characterized in that: The first target feature and the second target feature both include semantic features, device characteristic features, risk level features, historical frequency features, and time effect features; The expression for calculating the similarity between the target first feature and the at least one target second feature is: ， In the formula, A comprehensive score for the similarity between the target first feature and the at least one target second feature, is the weight of semantic feature similarity, is the semantic feature similarity, is the weight of the similarity of device characteristics, is the device characteristic feature similarity, is the weight of risk level feature similarity, is the risk level feature similarity, is the weight of the historical frequency feature similarity, is the historical frequency feature similarity, is the weight of the time effect feature similarity, is the time effect feature similarity.

3. The method for automatically associating power grid equipment defect text with technical supervision details according to claim 2, characterized in that: in, The expression for calculating the similarity of semantic features is: ， In the formula, The value range of is [0,1], is the normalized cosine similarity, Embedding vector for power grid equipment defect text, Embed vectors for technical supervision rules, is the modulus of the semantic vector.

4. The method for automatically associating power grid equipment defect text with technical supervision details according to claim 2, characterized in that: If the category number of the defective equipment is the same as the number of the applicable equipment in the technical supervision rules, the similarity score is 1, otherwise it is 0. The expression for calculating the similarity of the equipment characteristics is: 。 5. The method for automatically associating power grid equipment defect text with technical supervision details according to claim 2, characterized in that: The expression for calculating the similarity of risk level features is: ， In the formula, is the risk level of the equipment defect, is the risk level of the technical supervision rules, Equals 3.

6. The method for automatically associating power grid equipment defect text with technical supervision details according to claim 2, characterized in that: The expression for calculating the similarity of historical frequency features is: ， In the formula, is the historical matching frequency of defects and supervision details, is the total defect history matching count, is the inverse frequency.

7. The method for automatically associating power grid equipment defect text with technical supervision details according to claim 2, characterized in that: The expression for calculating the similarity of time effect features is: ， In the formula, Represents the frequency statistics of each type of defect occurring in 12 months, The frequency statistics of each type of defect occurring in January, The frequency statistics of each type of defect occurring in February, The frequency statistics of each type of defect occurring in December, Represents the frequency statistics of each supervisory rule applied in 12 months, For each supervision rule, the frequency of application in January is counted. For each supervision rule, the frequency of application in February is counted. For each supervision rule, the frequency of application in December is counted. is the frequency statistics of each type of defect in the i-th month, is the frequency statistics of application of each supervisory rule in the i-th month.

8. An automatic association system for power grid equipment defect text and technical supervision details, characterized in that: include: A conversion module is configured to convert the preprocessed defect text data and at least one technical supervision rule data into a high-dimensional vector to obtain target defect text data and at least one target technical supervision rule data; An extraction module is configured to extract a first feature from the target defect text data and at least one second feature from the at least one target technical supervision rule data, and normalize the first feature and the at least one second feature according to a preset maximum-minimum scaling method to obtain a target first feature and at least one target second feature having the same scale; a calculation module configured to calculate the similarity between the target first feature and the at least one target second feature using a multi-factor weighted matching method to obtain respective similarity comprehensive scores, and to sort the respective similarity comprehensive scores based on the score values ​​to obtain a similarity comprehensive score sequence; The association module is configured to select at least one target similarity comprehensive score in the similarity comprehensive score sequence according to a preset interception rule, and associate the defect text data and technical supervision details data corresponding to the at least one target similarity comprehensive score to obtain an association result.

9. An electronic device, characterized in that: include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images