Batch setting sheet matching method and system, electronic equipment and storage medium

Abstract

The invention discloses a batch setting list matching method and system, an electronic device and a storage medium, and the method comprises the steps: creating a setting list index file, taking a plant station, primary equipment, a device model and setting list number information related to each setting list as a record, and storing the record into the index file; the index file and the fixed value list file are pushed to a file server; obtaining and analyzing the setting value list index file from the file server, extracting plant station, primary equipment, device model and setting value list number information, and combining to generate a setting value list name; matching is carried out according to the device sleeve and sleeve information in the setting value list name, and all setting value lists consistent with the device sleeve are obtained; and in all the constant value lists consistent with the device set, identifying the constant value list most matched with the device based on an N-gram model and a cosine similarity algorithm. By adopting the scheme of the invention, batch accurate association matching of the fixed value sheet and the protection device can be realized, the fixed value sheet matching efficiency is improved, and the safety and reliability of the fixed value service are ensured.

Description

Technical Field

[0001] The present invention belongs to the field of power system dispatching, and particularly relates to a method, system, electronic device and storage medium for batch matching of setting sheets. Background Art

[0002] Currently, for setting operations such as downloading setting values in the relay protection specialty, they all need to be based on the setting sheet files pushed by the setting sheet system. Therefore, the correct association and matching between the setting sheet files and protection devices, and between the setting items and the protection device setting items are crucial. If entered one by one manually, it will be time-consuming and laborious when the number of setting sheet files is huge, affecting the business efficiency. At the same time, there will be errors in manual operations, and the safety and reliability of the business cannot be guaranteed. Currently, for the research on setting sheet matching, there are text recognition matching technologies such as OCR, mainly for matching the setting items of the setting sheets, and there is no research on the batch matching technology for the entire substation setting sheet files and devices. Using image recognition and text fuzzy matching technologies for comparison, the accuracy of the comparison results is unstable and it is difficult to provide strong guarantees. Summary of the Invention

[0003] The purpose of the present invention is to provide a method, system, electronic device and storage medium for batch matching of setting sheets to meet the requirements of batch matching of setting sheets and matching accuracy.

[0004] To achieve the above object, the solution of the present invention is:

[0005] According to the first aspect of the present application, a method for batch matching of setting sheets is proposed, including:

[0006] Create a setting sheet index file, store the information of the substation, primary equipment, device model and setting sheet number related to each setting sheet as a record in the index file, and push the index file and the setting sheet file to the file server; the device model includes the device set number.

[0007] Obtain and parse the setting sheet index file from the file server, and extract the combination of the substation, primary equipment, device model, and setting sheet number information related to each setting sheet to generate a setting sheet name.

[0008] Match according to the device set number and the set number information in the setting sheet name to obtain all setting sheets with the same device set number.

[0009] Among all the setting sheets with the same device set number, identify the setting sheet that best matches the device based on the N-gram model and the cosine similarity algorithm.

[0010] According to some embodiments, the step of identifying the setting sheet that best matches the device based on the N-gram model and the cosine similarity algorithm among all the setting sheets with the same device set number specifically includes:

[0011] Normalize the device model number of the normalization processing device, the associated primary equipment, and the device model number and primary equipment information in all the name of the setting sheets that match the device set

[0012] Establish an N-gram language model based on the normalized information, obtain the first identification string formed by splicing the device model number and the associated primary equipment information and the corresponding device vector, and the second identification string formed by splicing the device model number and the primary equipment information in the name of the setting sheet and the corresponding setting sheet vector

[0013] Calculate the similarity between the device vector and the setting sheet vector using the cosine similarity algorithm

[0014] Give a matching result according to the similarity result

[0015] According to some embodiments, the substation, primary equipment, device model number, and setting sheet number information related to each setting sheet are unique

[0016] According to some embodiments, assign a "matched" identifier to the matched setting sheet file, and only match the setting sheet without the "matched" identifier in the matching of the device and the setting sheet file

[0017] According to some embodiments, the matching according to the device set and the set information in the setting sheet name is specifically as follows

[0018] Extract the set information in the setting sheet name, expand the set information through the keyword library, and use all the set keywords related to the set information as the extended set names of the set information

[0019] Then compare the device set with the extended set names. If there is a consistent set name, it is considered that the setting sheet is consistent with the device set

[0020] According to some embodiments, if the set information in the setting sheet name is empty, all the set keywords in the keyword library are used as the extended set names of the set information; then compare the device set with the extended set names. If there is a consistent set alias, it is considered that the setting sheet is consistent with the device set

[0021] According to some embodiments, the normalization of the device model number of the normalization processing device, the associated primary equipment, and the device model number and primary equipment information in the setting sheet file specifically includes

[0022] For the associated primary equipment and the primary equipment information in the setting sheet file, unify the digital form; for the device model number and the device model number information in the setting sheet file, unify the case of letters and the digital form, and remove the characters other than letters and numbers

[0023] According to some embodiments, establishing an N-gram language model based on the normalized information, obtaining a first identification string formed by concatenating the device model number and the associated primary equipment information and the corresponding device vector, and a second identification string formed by concatenating the device model number and the primary equipment information in the name of the setting sheet document and the corresponding setting sheet vector, specifically including:

[0024] Performing word segmentation on the normalized associated primary equipment and the primary equipment information in the name of the setting sheet document by using an N-gram language model, where the word segmentation length is N1, and N1 is an integer less than or equal to 3;

[0025] Performing word segmentation on the normalized device model number and the device model number information in the name of the setting sheet document by using an N-gram language model, where the word segmentation length is N2, and N2 is an integer less than or equal to 3;

[0026] Concatenating the segmented device model number and the associated primary equipment information into a first identification string;

[0027] Concatenating the device model number and the primary equipment information in the name of the setting sheet document after word segmentation into a second identification string;

[0028] Obtaining a device vector according to the first identification string and obtaining a setting sheet vector according to the second identification string.

[0029] According to some embodiments, performing word segmentation on the normalized associated primary equipment and the primary equipment information in the name of the setting sheet document by using a unigram model; performing word segmentation on the normalized device model number and the device model number information in the name of the setting sheet document by using a bigram model.

[0030] According to some embodiments, the giving of a matching result according to the similarity result includes: sorting according to the similarity magnitude, if the similarities are all less than a set threshold, the matching fails, otherwise taking the one with the largest similarity result, and if there are multiple with the largest similarity, there are similar setting sheets.

[0031] According to some embodiments, in response to the existence of similar setting sheets, an operator associates and confirms the most matching setting sheet from multiple setting sheets with the largest similarity results.

[0032] According to some embodiments, when the matching fails or there are similar setting sheets, a prompt message is given.

[0033] According to a second aspect of the present application, a batch setting sheet matching system is proposed, including:

[0034] An index file creation module, which is used to create a fixed value list index file, store the information of the substation, primary equipment, device model, and fixed value list number related to each fixed value list as a record in the index file, and push the index file and the fixed value list file to the file server; the device model includes the device set number.

[0035] A fixed value list name generation module, which is used to obtain and parse the fixed value list index file from the file server, and extract the information combination of the substation, primary equipment, device model, and fixed value list number related to each fixed value list to generate a fixed value list name.

[0036] A primary matching module, which is used to match the device set number with the set number information in the fixed value list name to obtain all fixed value lists that are consistent with the device set number.

[0037] A secondary matching module, which is used to identify the fixed value list that best matches the device based on the N-gram model and the cosine similarity algorithm among all the fixed value lists that are consistent with the device set number.

[0038] According to the third aspect of the present application, an electronic device is proposed, which includes a processor and a memory. A program is stored on the memory, and the program can be loaded and executed by the processor to perform the foregoing batch fixed value list matching method.

[0039] According to the fourth aspect of the present application, a computer-readable storage medium is proposed, which stores a computer program. When the computer program is executed by a processor, the foregoing batch fixed value list matching method is implemented.

[0040] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0041] The present invention adopts a fixed value list batch matching technology based on N-gram model word segmentation combined with the cosine similarity algorithm, fully analyzes the characteristics of the fixed value list name, realizes batch and accurate association matching between the fixed value list and the protection device, replaces manual entry, improves the efficiency of fixed value list verification. Originally, it took 2 hours for manual entry of all device fixed value lists in a substation. Using the method of the present invention, all fixed value list matching and manual verification can be completed in only 10 minutes, ensuring the safety and reliability of the fixed value service. Description of the Drawings

[0042] Figure 1 It is a flowchart of a batch fixed value list matching method based on the N-gram model and the cosine similarity algorithm;

[0043] Figure 2 It is an example of a fixed value list index file;

[0044] Figure 3 It is an example of a keyword library provided by an embodiment of the present application;

[0045] Figure 4An example of the interface of the batch setting list matching system provided by the embodiment of the present application;

[0046] Figure 5 A schematic structural diagram of a batch setting list matching system provided by the embodiment of the present application;

[0047] Figure 6 A structural diagram of an electronic device provided by the present application. Detailed implementation manners

[0048] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific implementations described herein are only used to explain the present invention and do not limit the present invention.

[0049] Figure 1 A schematic flowchart of a batch setting list matching method provided by the embodiment of the present application, including steps S100 to S400.

[0050] In S100, a setting list index file is created, and the information of the substation, primary equipment, device model, and setting list number related to each setting list is stored as a record in the index file, and the index file and the setting list file are pushed to the file server; the device model includes the device set number.

[0051] An example of the setting list index file is as shown in the appendix Figure 2 Each piece of information of the substation, primary equipment, device model, and setting list number related to each setting list is unique, and there should not be two setting list files with the same substation, primary equipment, device model, and setting list number at the same time.

[0052] In S200, the setting list index file is obtained and parsed from the file server, and the information combination of the substation, primary equipment, device model, and setting list number related to each setting list is extracted to generate a setting list name for device matching under the substation.

[0053] In one embodiment, the format of the setting list file name can be "substation name_primary equipment_device model (including set number)_setting list number.xml", example: 220kV Matou Substation_110kV Maping I Line_First set of RCS-941-A_Protection 20210309.xml.

[0054] In S300, the device set number is matched with the set number information in the setting list name to obtain all setting lists that are consistent with the device set number.

[0055] In some embodiments, the specific method for matching the device set type with the set type information in the set value list is as follows: extract the set type information in the set value list, expand the set type information through a keyword library, and use all set type keywords related to the set type information as the extended set type names of the set type information; then compare the device set type with the extended set type names. If there is a consistent set type name, it is considered that the set value list is consistent with the device set type.

[0056] Further, if the set type information in the set value list is empty, all set type keywords in the keyword library are used as the extended set type names of the set type information; then compare the device set type with the extended set type names. If there is a consistent set type alias, it is considered that the set value list is consistent with the device set type.

[0057] In actual situations, the naming of the device set types in the setting system set value lists is diverse. For example: Main One, First Set, Set A, Protection A, etc. If the cosine similarity calculation is directly performed, it will affect the similarity result. Therefore, in this application, the set type keywords with the same meaning are clustered through a keyword library as Figure 3 shown, and the set type information is expanded by using the keyword library method.

[0058] In S400, among all the set value lists that are consistent with the device set type, the set value list that best matches the device is identified based on the N-gram model and the cosine similarity algorithm.

[0059] The N-gram language model refers to a class of language models that use the same text segmentation method. This segmentation method is very simple: use a window of length N and slide it character by character from left to right across the text; at each step, a string will be framed, which is a gram; all the grams in the text are the segmentation results of the text. As shown in Table 1, several common N-gram segmentation results are presented.

[0060] Table 1

[0061] Serial number Value of N Name Segmentation example 1 1 unigram a / b / c / d / e / f / g 2 2 bigram ab / bc / cd / de / ef / fg 3 3 trigram abc / bcd / cde / def / efg … … … …

[0062] Cosine similarity measures the similarity between two vectors by measuring the cosine value of the angle between them. Given two attribute vectors, A and B, their cosine similarity θ is given by the dot product and the vector lengths, as shown in Equation (1):

[0063]

[0064] Here, A i and B i represent the respective components of vectors A and B.

[0065] For text matching, the attribute vectors A and B are usually the term frequency vectors in a document. Each term is assigned a different dimension, and a dimension is represented by a vector whose values on each dimension correspond to the frequency of the term in the document. Since the frequency of a word cannot be negative, the cosine similarity between the two documents ranges from 0 to 1.

[0066] In some embodiments, the specific process of matching based on the N-gram model and the cosine similarity algorithm includes steps S401 to S404.

[0067] S401: Normalize the device model, the associated primary equipment, and the device model and primary equipment information in all the fixed value list files that are consistent with the device set.

[0068] There are both Roman numerals and Arabic numerals in the primary equipment, which affects the accuracy of matching. Therefore, normalization processing is required. In some embodiments, the normalization processing specifically includes: for the primary equipment information in the associated primary equipment and the fixed value list file name, unify the digital form; for the device model information in the device model and the fixed value list file name, unify the letter case and the digital form, and remove the characters other than letters and numbers.

[0069] For example, the unified digital form can be converting all Roman numerals to Arabic numerals or converting Arabic numerals to Roman numerals; the unified letter case can be converting capital letters to lowercase or converting lowercase letters to uppercase. The key information of the device model consists of uppercase and lowercase letters, Arabic numerals, and special symbols such as "-". The absence of special symbols does not change the model. The characters other than uppercase and lowercase letters and numbers in the device model can be removed through regular expressions, and all uppercase and lowercase letters can be unified.

[0070] S402: Establish an N-gram language model based on the normalized information to obtain the first identification string formed by splicing the device model and the associated primary equipment information and the corresponding device vector, and the second identification string formed by splicing the device model and the primary equipment information in the fixed value list file name and the corresponding fixed value list vector.

[0071] In some embodiments, the steps of using the N-gram language model to process and obtain the device vector and the fixed value list vector specifically include:

[0072] To improve the accuracy of the cosine similarity calculation results, the primary equipment information in the normalized associated primary equipment and the name of the setting list file is segmented using the N-gram language model, with the segmentation length being N1, where N1 is an integer less than or equal to 3; the equipment model information in the normalized equipment model and the name of the setting list file is segmented using the N-gram language model, with the segmentation length being N2, where N2 is an integer less than or equal to 3; the segmented equipment model and the associated primary equipment information are concatenated into a first identification string; the equipment model and the primary equipment information in the segmented name of the setting list file are concatenated into a second identification string; a device vector is obtained based on the first identification string, and a setting list vector is obtained based on the second identification string.

[0073] In a preferred embodiment, the primary equipment information in the normalized associated primary equipment and the name of the setting list file is segmented using the unigram model. For example, using the unigram model for segmentation, "110kV A-B line" after segmentation gives: 1 / 1 / 0 / k / v / A / B / line, and "110kV B-A line" after segmentation gives: 1 / 1 / 0 / k / v / B / A / line. This solves the problem that the name of the primary equipment may contain the initials of two connected stations, and may be reversed but represent the same equipment.

[0074] In a preferred embodiment, considering that the same numbers and letters in different orders will form different models, to improve the accuracy of the matching results, the equipment model information in the normalized equipment model and the name of the setting list file is segmented using the bigram model. Example: The equipment model is PS9867A, the setting list name 1 extracts the model PS-9867-A, and the setting list name 2 extracts the model PS-9876-A. Through the above processing, the equipment model is segmented into ps / s9 / 98 / 86 / 67 / 7a, the model of the setting list 1 name is segmented into ps / s9 / 98 / 86 / 67 / 7a, and the model of the setting list 2 name is segmented into ps / s9 / 98 / 87 / 76 / 6a.

[0075] An example of combining an equipment vector and a setting sheet vector is introduced as follows: Equipment string "110kv A-B line pss99886677a", setting sheet 1 string "110kv B-A line pss99886677a", setting sheet 2 string "110kv A-B line pss99887766a". After segmenting the identification strings as described above, the segmentation results are: Equipment "1 / 1 / 0 / k / v / A / B / line / ps / s9 / 98 / 86 / 67 / 7a", setting sheet 1 "1 / 1 / 0 / k / v / B / A / line / ps / s9 / 98 / 86 / 67 / 7a", setting sheet 2 "1 / 1 / 0 / k / v / A / B / line / ps / s9 / 98 / 87 / 76 / 6a". Based on the segmentation results, the equipment and setting sheet vectors are obtained. For the equipment and setting sheet 1: Equipment vector A = [2 1 1 1 1 1 1 1 1 1 1 1 1], setting sheet 1 vector B = [2 1 1 1 1 1 1 1 1 1 1 1 1]; For the equipment and setting sheet 2: Equipment vector A = [2 1 1 1 1 1 1 1 1 1 1 1 1], setting sheet 2 vector C = [2 1 1 1 1 1 1 1 1 1 0 0 0].

[0076] S403: Calculate the similarity between the equipment vector and the setting sheet vector using the cosine similarity algorithm.

[0077] In an example, equipment vector A = [2 1 1 1 1 1 1 1 1 1 1 1 1], setting sheet 1 vector B = [2 1 1 1 1 1 1 1 1 1 1 1 1], setting sheet 2 vector C = [2 1 1 1 1 1 1 1 1 1 0 0 0].

[0078] Calculate the cosine similarity of vectors A and B:

[0079]

[0080] Calculate the cosine similarity of vectors A and C:

[0081]

[0082] S404: Give the matching result according to the similarity result.

[0083] In some embodiments, matching results are given according to the similarity results, including: sorting by the size of the similarity. If all similarities are less than the set threshold, the matching fails. Otherwise, the one with the largest similarity result is taken. If there are multiple largest ones, there are similar fixed-value sheets. Specifically, in the example of step S403, since the cosine similarity between the device vector A and the fixed-value sheet 1 vector B is 1, and the cosine similarity between the device vector A and the fixed-value sheet 2 vector C is 0.901, according to the calculation results, the device matches successfully with the fixed-value sheet 1.

[0084] If there are similar fixed-value sheets, the most matching fixed-value sheet is associated and confirmed manually from multiple fixed-value sheets with the largest similarity results.

[0085] Optionally, when the matching fails or there are similar fixed-value sheets, a prompt message is given. When the matching fails, a matching failure message is prompted; when there are similar fixed-value sheets, a message indicating the existence of similar fixed-value sheets is prompted.

[0086] As Figure 4 Shown is a batch fixed-value sheet matching operation interface provided by an embodiment of the present application. On the left, a tree structure model of all substations-devices in this area is established. Clicking on a specific substation shows all device entries and information under that substation, including device description, device model, device-associated primary equipment name, associated fixed-value sheet file name, matching result, and matching degree. These interface information are stored in the database of the protection information master station server. Through automatic matching, all devices under the substation are matched with the fixed-value sheet files in the fixed-value sheet index file, and the fixed-value sheet matching situation is displayed according to the matching result and matching degree. For abnormal matching results, the reasons are found and processed according to the prompt, re-associated, and after verification without errors, the association relationship is saved to the database.

[0087] Preferably, in some embodiments, a "matched" identifier is given to the successfully matched fixed-value sheet file, and only the fixed-value sheet files without the "matched" identifier are matched in the matching of the device and the fixed-value sheet file. To reduce the workload in batch matching and further improve the matching efficiency.

[0088] The present application adopts a fixed-value sheet batch matching technology based on the N-gram model word segmentation combined with the cosine similarity algorithm. By obtaining and parsing the fixed-value sheet index file, information such as substation, primary equipment, model, and fixed-value sheet number are extracted to form the names of each fixed-value sheet file. Through the judgment of the device and the fixed-value sheet set, the N-gram model word segmentation processing is performed on the primary equipment and the model, and then the cosine similarity algorithm is used to calculate the similarity between the device and the fixed-value sheet name. According to the similarity, matching results are given, realizing the batch association and matching of all protection devices under the substation with the fixed-value sheets, replacing manual entry, improving the efficiency of fixed-value sheet matching verification, and ensuring the safety and reliability of the fixed-value service.

[0089] Figure 5Shown is a batch setting sheet matching system 500 provided by an embodiment of the present application, which can be used to run the method of the foregoing embodiment, including: an index file creation module 501, a setting sheet name generation module 502, a primary matching module 503, and a secondary matching module 504. Among them:

[0090] The index file creation module 501 is used to create a setting sheet index file, store the information of the substation, primary equipment, device model, and setting sheet number related to each setting sheet as a record in the index file, and push the index file and the setting sheet file to the file server; the device model includes the device set number.

[0091] The setting sheet name generation module 502 is used to obtain and parse the setting sheet index file from the file server, and extract the information of the substation, primary equipment, device model, and setting sheet number related to each setting sheet to combine and generate a setting sheet name.

[0092] The primary matching module 503 is used to match according to the device set number and the set number information in the setting sheet name to obtain all setting sheets that are consistent with the device set number.

[0093] The secondary matching module 504 is used to identify the setting sheet that best matches the device among all the setting sheets that are consistent with the device set number based on the N-gram model and the cosine similarity algorithm.

[0094] Figure 6 Shown is a structural diagram of an electronic device provided by the present application. It includes a processor and a memory. The memory stores computer instructions. When the computer instructions are executed by the processor, the processor executes the computer instructions to implement the method and refinement scheme as Figure 1 shown.

[0095] It should be understood that the above device embodiments are illustrative. The devices disclosed by the present invention can also be implemented in other ways. For example, the division of the above-mentioned units / modules is only a logical function division, and there can be other division methods in actual implementation. For example, multiple units, modules, or components can be combined, or can be integrated into another system, or some features can be ignored or not executed.

[0096] In addition, without special instructions, in each embodiment of the present invention, each functional unit / module can be integrated in one unit / module, or each unit / module can exist physically alone, or two or more units / modules can be integrated together. The above integrated unit / module can be implemented in the form of hardware or in the form of a software program module.

[0097] When the integrated unit / module is implemented in the form of hardware, the hardware can be a digital circuit, an analog circuit, etc. The physical implementation of the hardware structure includes but is not limited to transistors, memristors, etc. Unless otherwise specified, the processor or chip can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the on-chip cache, off-chip memory, and memory can be any suitable magnetic storage medium or magneto-optical storage medium, such as resistive random access memory (RRAM), dynamic random access memory (DRAM), static random access memory (SRAM), enhanced dynamic random access memory (EDRAM), high-bandwidth memory (HBM), hybrid memory cube (HMC), etc.

[0098] When the integrated unit / module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this disclosure. And the aforementioned memory includes: various media that can store program codes, such as USB flash drives, read-only memory (ROM), random access memory (RAM), external hard drives, magnetic disks, or optical discs.

[0099] The embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to execute the Figure 1 methods and refinement schemes as shown.

[0100] It should be clearly understood that this application describes how to form and use specific examples, but this application is not limited to any details of these examples. On the contrary, based on the teachings of the content disclosed in this application, these principles can be applied to many other embodiments.

[0101] In addition, it should be noted that the above-mentioned drawings are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present application, rather than for the purpose of limitation. It is easy to understand that the processes shown in the above-mentioned drawings do not indicate or limit the chronological order of these processes. Additionally, it is also easy to understand that these processes can be executed synchronously or asynchronously in, for example, multiple modules.

[0102] The above embodiments are only for illustrating the technical idea of the present invention, and the protection scope of the present invention cannot be limited thereby. Any modifications made on the basis of the technical solution according to the technical idea proposed by the present invention fall within the protection scope of the present invention.

Claims

1. A batch fixed-value list matching method, characterized in that Including: Create a fixed value list index file, store the information of the substation, primary equipment, device model, and fixed value list number related to each fixed value list as a record in the index file, and push the index file and the fixed value list file to the file server; the device model includes the device set number. Obtain and parse the fixed value list index file from the file server, extract the information combination of the substation, primary equipment, device model, and fixed value list number related to each fixed value list to generate a fixed value list name. Match the device set number with the set number information in the fixed value list name to obtain all fixed value lists that are consistent with the device set number. Among all the fixed value lists that are consistent with the device set number, identify the fixed value list that best matches the device based on the N-gram model and the cosine similarity algorithm.

2. The method according to claim 1, characterized in that The step of identifying the fixed value list that best matches the device among all the fixed value lists that are consistent with the device set number based on the N-gram model and the cosine similarity algorithm specifically includes: Normalize the device model, associated primary equipment, and the device model and primary equipment information in the names of all fixed value list files that are consistent with the device set number. Establish an N-gram language model according to the normalized information, obtain the first identification string formed by splicing the device model and the associated primary equipment information and the corresponding device vector, and the second identification string formed by splicing the device model and the primary equipment information in the fixed value list file name and the corresponding fixed value list vector. Use the cosine similarity algorithm to calculate the similarity between the device vector and the fixed value list vector. Give a matching result according to the similarity result.

3. The method according to claim 1, characterized in that, The information of the substation, primary equipment, device model, and fixed value list number related to each fixed value list is unique.

4. The method according to claim 1, characterized in that, Assign a "matched" label to the successfully matched fixed value list file, and only match the fixed value list file without the "matched" label in the matching between the device and the fixed value list file.

5. The method according to claim 1, characterized in that, The step of matching the device set number with the set number information in the fixed value list name specifically is: Extract the set number information in the fixed value list name, expand the set number information through the keyword library, and regard all set number keywords related to the set number information as the extended set number names of the set number information. Then compare the device set number with the extended set number names. If there is a consistent set number name, it is considered that the fixed value list is consistent with the device set number.

6. The method according to claim 5, characterized in that, If the set number information in the fixed value list name is empty, regard all set number keywords in the keyword library as the extended set number names of the set number information; then compare the device set number with the extended set number names. If there is a consistent set number alias, it is considered that the fixed value list is consistent with the device set number.

7. The method according to claim 2, wherein The step of normalizing the device model, associated primary equipment, and the device model and primary equipment information in the fixed value list file name specifically includes: For the associated primary equipment and the primary equipment information in the fixed value list file name, unify the digital form; for the device model and the device model information in the fixed value list file name, unify the letter case and the digital form, and remove the characters other than letters and numbers.

8. The method according to claim 2, wherein Establish an N-gram language model based on the normalized information to obtain a first identification string formed by concatenating the device model number and the associated primary equipment information, and the corresponding device vector, as well as a second identification string formed by concatenating the device model number and the primary equipment information in the name of the setting sheet file, and the corresponding setting sheet vector. Specifically, it includes: Segment the primary equipment information associated with the normalized primary equipment and the primary equipment information in the setting sheet file name using the N-gram language model, with the segmentation length being N1, where N1 is an integer less than or equal to 3; Segment the device model number information in the normalized device model number and the setting sheet file name using the N-gram language model, with the segmentation length being N2, where N2 is an integer less than or equal to 3; Concatenate the segmented device model number and the associated primary equipment information into a first identification string; Concatenate the device model number and the primary equipment information in the setting sheet file name after segmentation into a second identification string; Obtain the device vector based on the first identification string and obtain the setting sheet vector based on the second identification string.

9. The method according to claim 8, wherein Segment the primary equipment information associated with the normalized primary equipment and the primary equipment information in the setting sheet file name using the unigram model; segment the device model number information in the normalized device model number and the setting sheet file name using the bigram model.

10. The method according to claim 2, characterized in that, The step of giving a matching result according to the similarity result includes: sorting according to the similarity magnitude. If the similarities are all less than the set threshold, the matching fails; otherwise, take the one with the largest similarity result. If there are multiple with the largest similarity, there are similar setting sheets.

11. The method according to claim 10, wherein In response to the existence of similar setting sheets, manually associate and confirm the most matching setting sheet from multiple setting sheets with the largest similarity results.

12. The method according to claim 10, wherein When the matching fails or there are similar setting sheets, give a prompt message.

13. A batch fixed-value form matching system, characterized in that, It includes: An index file creation module for creating a setting sheet index file, storing the information of the substation, primary equipment, device model number, and setting sheet number related to each setting sheet as a record in the index file, and pushing the index file and the setting sheet file to the file server; the device model number includes the device set number; A setting sheet name generation module for obtaining and parsing the setting sheet index file from the file server, and extracting the information of the substation, primary equipment, device model number, and setting sheet number related to each setting sheet to generate a setting sheet name; A primary matching module for matching according to the device set number and the set number information in the setting sheet name to obtain all setting sheets that are consistent with the device set number; A secondary matching module for identifying the setting sheet that best matches the device based on the N-gram model and the cosine similarity algorithm among all the setting sheets that are consistent with the device set number.

14. An electronic device, characterized in that: It includes a processor and a memory, and a program is stored on the memory, and the program can be loaded and executed by the processor to perform the method according to any one of claims 1-12.

15. A computer-readable storage medium stores a computer program, characterized in that, When the computer program is executed by the processor, it implements the method according to any one of claims 1-12.

Images