Substation operation order filing method, device and equipment based on RPA technology

Abstract

The invention provides a substation operation ticket filing method, device and equipment based on an RPA technology, and relates to the technical field of electric power. The method comprises the following steps: acquiring a paper operation ticket of a target substation, and scanning and uploading the paper operation ticket to an operation ticket management system of a target power grid management platform; then, on the basis of a preset cutting area, the scanning version operation ticket in the electronic image format is segmented, and a plurality of operation ticket sub-images are generated; and determining content information contained in each operation ticket sub-image, and storing the content information to a preset path. And next, configuring the software robot used by the RPA, so that the configured software robot automatically logs in the target power grid management platform and enters an operation order management system. And through the software robot, based on the content information stored in the preset path, performing archiving operation on the scanning version operation order, and generating an archiving record. According to the method, the filing efficiency and the filing qualification rate of the substation operation tickets can be improved.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a method, device and equipment for archiving substation operation tickets based on RPA technology. Background Art

[0002] The substation operation ticket is an important written basis for electrical operations in the power system. After the electrical operation is completed, the information on the operation ticket needs to be filled back into the power grid management platform and archived to facilitate the management and subsequent inspection of the operation ticket.

[0003] Traditional substation operation tickets are mostly in paper form, which need to be filled out, reviewed and signed manually, and then manually classified and filed, and stored in a special archive room or file cabinet. At the same time, when historical operation tickets need to be consulted, they need to be manually searched.

[0004] Therefore, the prior art has the technical problems of low filing efficiency and low filing qualification rate of substation operation tickets. Summary of the invention

[0005] The present application provides a substation operation ticket archiving method, device and equipment based on RPA technology, which is used to solve the technical problems of low archiving efficiency and low archiving qualification rate of substation operation tickets in the prior art.

[0006] In a first aspect, the present application provides a substation operation ticket archiving method based on RPA technology, comprising:

[0007] Obtain a paper version of the operation ticket of the target substation, and scan and upload the paper version of the operation ticket to the operation ticket management system of the target power grid management platform; wherein the paper version of the operation ticket represents a written record used to record and guide the operation of the target substation;

[0008] Based on the preset cropping area, the scanned operation ticket in the operation ticket management system is segmented to generate multiple operation ticket sub-images; the content information contained in each operation ticket sub-image is determined, and the content information is stored in a preset path; wherein the scanned operation ticket is stored in the operation ticket management system in the format of an electronic image;

[0009] The software robot used by the Robotic Process Automation (RPA) is configured so that the configured software robot automatically logs into the target power grid management platform and enters the operation ticket management system; wherein the software robot represents a software program used to simulate human operations on a device terminal;

[0010] Through the software robot, the scanned operation ticket is archived based on the content information stored in the preset path, and an archive record is generated.

[0011] In a possible design, the determining of the content information contained in each operation ticket sub-image includes:

[0012] Classifying the operation ticket sub-images based on preset standards to obtain first-category sub-images, second-category sub-images, and third-category sub-images;

[0013] The first category of sub-images is recognized based on a preset optical character recognition (OCR) technology to determine first content information of the first category of sub-images; the second category of sub-images is recognized based on a preset template matching technology to determine second content information of the second category of sub-images; the third category of sub-images is recognized based on a preset graph learning technology to determine third content information of the third category of sub-images.

[0014] In a possible design, the identifying the second type of sub-image based on a preset template matching technology to determine the second content information of the second type of sub-image includes:

[0015] Based on a preset template matching technology, matching the second type of sub-image with a plurality of preset template images, and calculating the matching degree between the second type of sub-image and the plurality of preset template images;

[0016] The matching degrees are sorted in descending order, and the preset template image corresponding to the matching degree ranked first is determined as the target template image; and the content information of the target template image is determined as the second content information of the second-category sub-image.

[0017] In a possible design, the identifying the third type of sub-image based on the preset graph learning technology to determine the third content information of the third type of sub-image includes:

[0018] Acquire a first image comparison library from a target behavior center and a second image comparison library from a target dispatching center; wherein the target behavior center represents an organization responsible for controlling the target substation, and the target dispatching center represents an organization responsible for controlling the target behavior center;

[0019] Calculating the similarity between the third type of sub-image and the first comparison image in the first image comparison library, or the second comparison image in the second image comparison library;

[0020] The similarities are sorted in descending order, and the comparison image corresponding to the first similarity is determined as the target comparison image; and the content information of the target comparison image is determined as the third content information of the third category sub-image.

[0021] In a possible design, calculating the similarity between the third type of sub-image and the first comparison image in the first image comparison library, or the second comparison image in the second image comparison library, includes:

[0022] Extracting features from the third type of sub-image to obtain first image features;

[0023] Determine the operation type of the scanning version operation ticket where the third type of sub-image is located; wherein the operation type includes a self-adjustment operation or a scheduling operation;

[0024] If the operation type is a self-adjustment operation, extracting features from the first comparison image in the first image comparison library to obtain second image features; mapping the first image features and the second image features to the same feature space, and determining the similarity between the third type of sub-image and the first comparison image based on the distance between the first image features and the second image features in the feature space;

[0025] If the operation type is a scheduling operation, feature extraction is performed on the second comparison image in the second image comparison library to obtain a third image feature; the first image feature and the third image feature are mapped to the same feature space, and based on the distance between the first image feature and the third image feature in the feature space, the similarity between the third type of sub-image and the second comparison image is determined.

[0026] In a possible design, storing the content information to a preset path includes:

[0027] Constructing an empty dictionary for storing the content information based on a preset method; wherein the empty dictionary represents a data structure that does not contain any key-value pairs;

[0028] Name each operation ticket sub-image; store the name of each operation ticket sub-image and the corresponding content information in the empty dictionary in the form of key-value pairs; wherein the name of each operation ticket sub-image is used as the key of the key-value pair, and the corresponding content information is used as the value of the key-value pair.

[0029] In one possible design, configuring the software robot used by the robotic process automation (RPA) so that the configured software robot automatically logs into the target power grid management platform includes:

[0030] Add a preset script in the software robot used by RPA; wherein the preset script includes the account and password required to log in to the target power grid management platform, or includes the hardware certificate and electronic key of the target terminal device; the target terminal device represents the terminal device used to log in to the target power grid management platform;

[0031] The preset script is executed based on the software robot to automatically log in to the target power grid management platform.

[0032] In a possible design, the software robot performs an archiving operation on the scanned operation ticket based on the content information stored in the preset path, including:

[0033] Reading the content information stored in the preset path based on the software robot;

[0034] Based on the content information, determine the operation tickets to be archived from the operation ticket management system, and perform data backfill operation on the operation tickets to be archived through the software robot;

[0035] Archive the operation tickets to be archived that have completed the data backfill operation.

[0036] In one possible design, the method further includes:

[0037] Performing a preset correctness check and a preset integrity check on the content information stored in the preset path;

[0038] Determine the abnormal content information that fails the preset correctness check and the preset integrity check, and determine the abnormal scan version operation ticket corresponding to the abnormal content information;

[0039] The abnormal scanning version operation ticket is reissued.

[0040] In a second aspect, the present application provides a substation operation ticket archiving device based on RPA technology, including:

[0041] An upload module is used to obtain a paper version of the operation ticket of the target substation, and scan and upload the paper version of the operation ticket to the operation ticket management system of the target power grid management platform; wherein the paper version of the operation ticket represents a written record used to record and guide the operation of the target substation;

[0042] A cropping module, used to segment the scanned operation ticket in the operation ticket management system based on a preset cropping area to generate multiple operation ticket sub-images;

[0043] A determination module, used to determine the content information contained in each operation ticket sub-image, and store the content information in a preset path; wherein the scanned operation ticket is stored in the operation ticket management system in the format of an electronic image;

[0044] A configuration module, used to configure the software robot used by the Robotic Process Automation (RPA) so that the configured software robot automatically logs into the target power grid management platform and enters the operation ticket management system; wherein the software robot represents a software program used to simulate human operations on a device terminal;

[0045] The archiving module is used to archive the scanned operation ticket through the software robot based on the content information stored in the preset path and generate an archiving record.

[0046] In a possible design, the determination module further includes: a classification module, which is used to classify the operation ticket sub-image based on a preset standard to obtain a first type of sub-image, a second type of sub-image, and a third type of sub-image;

[0047] The determining module is further used for:

[0048] The first category of sub-images is recognized based on a preset optical character recognition (OCR) technology to determine first content information of the first category of sub-images; the second category of sub-images is recognized based on a preset template matching technology to determine second content information of the second category of sub-images; the third category of sub-images is recognized based on a preset graph learning technology to determine third content information of the third category of sub-images.

[0049] In a possible design, the determination module further includes: a matching module and a calculation module.

[0050] The matching module is used to match the second type of sub-image with a plurality of preset template images based on a preset template matching technology;

[0051] The calculation module is used to calculate the matching degree between the second type of sub-image and the plurality of preset template images;

[0052] The determination module is further used to sort the matching degrees in descending order, determine the preset template image corresponding to the first matching degree as the target template image; and determine the content information of the target template image as the second content information of the second type of sub-image.

[0053] In a possible design, the determination module further includes: an acquisition module, used to acquire a first image comparison library from a target behavior center and a second image comparison library from a target dispatching center; wherein the target behavior center represents an organization responsible for controlling the target substation, and the target dispatching center represents an organization responsible for controlling the target behavior center;

[0054] The calculation module is further used to calculate the similarity between the third type of sub-image and the first comparison image in the first image comparison library, or the second comparison image in the second image comparison library;

[0055] The determination module is further configured to sort the similarities in descending order, determine the comparison image corresponding to the first similarity as the target comparison image, and determine the content information of the target comparison image as the third content information of the third category sub-image.

[0056] In a possible design, the calculation module further includes: an extraction module, configured to perform feature extraction on the third type of sub-image to obtain first image features;

[0057] The determination module is further used to determine the operation type of the scanning plate operation ticket where the third type of sub-image is located; wherein the operation type includes a self-adjustment operation or a scheduling operation;

[0058] The extraction module is further configured to extract features of the first comparison image in the first image comparison library to obtain second image features if the operation type is a self-adjustment operation;

[0059] The determination module is further configured to map the first image feature and the second image feature to the same feature space, and determine the similarity between the third type of sub-image and the first comparison image based on the distance between the first image feature and the second image feature in the feature space;

[0060] The extraction module is further configured to extract features from the second comparison image in the second image comparison library to obtain third image features if the operation type is a scheduling operation;

[0061] The determination module is further used to map the first image feature and the third image feature to the same feature space, and determine the similarity between the third type of sub-image and the second comparison image based on the distance between the first image feature and the third image feature in the feature space.

[0062] In a possible design, the determining module further includes: a building module and a storage module.

[0063] The construction module is used to construct an empty dictionary for storing the content information based on a preset method; wherein the empty dictionary represents a data structure that does not contain any key-value pairs;

[0064] The storage module is used to name each operation ticket sub-image; store the name of each operation ticket sub-image and the corresponding content information in the empty dictionary in the form of key-value pairs; wherein the name of each operation ticket sub-image is used as the key of the key-value pair, and the corresponding content information is used as the value of the key-value pair.

[0065] In a possible design, the configuration module further includes: an adding module and an execution module.

[0066] The adding module is used to add a preset script in the software robot used by RPA; wherein the preset script includes the account and password required to log in to the target power grid management platform, or includes the hardware certificate and electronic key of the target terminal device; the target terminal device represents the terminal device used to log in to the target power grid management platform;

[0067] The execution module is used to execute the preset script based on the software robot to automatically log in to the target power grid management platform.

[0068] In a possible design, the archiving module further includes: a reading module, configured to read the content information stored in the preset path based on the software robot;

[0069] The determination module is further used to determine the operation ticket to be archived from the operation ticket management system based on the content information;

[0070] The archiving module is also used to perform data backfill operation on the operation ticket to be archived through the software robot; and to perform archiving operation on the operation ticket to be archived that has completed the data backfill operation.

[0071] In a third aspect, an embodiment of the present application provides an electronic device, comprising: at least one processor and a memory; the memory stores computer-executable instructions; the at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method described in the first aspect above and various possible designs.

[0072] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the method described in the first aspect and various possible designs is implemented.

[0073] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the method described in the first aspect and various possible designs of the first aspect.

[0074] The substation operation ticket archiving method, device and equipment based on RPA technology provided in this application obtains the paper version of the operation ticket of the target substation, and scans and uploads the paper version of the operation ticket to the operation ticket management system of the target power grid management platform. Among them, the scanned version of the operation ticket is stored in the operation ticket management system in the format of an electronic image. Afterwards, based on the preset cropping area, the scanned version of the operation ticket is segmented to generate multiple operation ticket sub-images. Determine the content information contained in each operation ticket sub-image, and store the content information in a preset path. Next, the software robot used by RPA is configured so that the configured software robot automatically logs in to the target power grid management platform and enters the operation ticket management system. Through the software robot, based on the content information stored in the preset path, the scanned version of the operation ticket is archived and an archive record is generated. Through the application of automation technology, many steps that originally required manual completion can be completed automatically, which not only reduces manual intervention, but also improves the accuracy and consistency of the entire archiving process. At the same time, since machines can process and enter information faster than humans, the automated process significantly shortens the time required for archiving and improves the archiving efficiency of substation operation tickets. Due to the reduction of human errors, the filing qualification rate of substation operation tickets has also been improved, which means that the archived substation operation tickets are more accurate and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0076] Figure 1 Schematic diagram of the process of the substation operation ticket archiving method based on RPA technology provided in the embodiment of the present application Figure 1 ;

[0077] Figure 2 Schematic diagram of the process of the substation operation ticket archiving method based on RPA technology provided in the embodiment of the present application Figure 2 ;

[0078] Figure 3 Schematic diagram of the process of the substation operation ticket archiving method based on RPA technology provided in the embodiment of the present application Figure 3 ;

[0079] Figure 4 Schematic diagram of the process of the substation operation ticket archiving method based on RPA technology provided in the embodiment of the present application Figure 4 ;

[0080] Figure 5 Schematic diagram of the process of the substation operation ticket archiving method based on RPA technology provided in the embodiment of the present application Figure 5 ;

[0081] Figure 6 A schematic diagram of the structure of a substation operation ticket archiving method based on RPA technology provided in an embodiment of the present application;

[0082] Figure 7 Schematic diagram of the process of the substation operation ticket archiving method based on RPA technology provided in the embodiment of the present application Figure 6 ;

[0083] Figure 8 A schematic diagram of the structure of a substation operation ticket archiving device based on RPA technology provided in an embodiment of the present application;

[0084] Fig. 9 A hardware structure diagram of an electronic device provided in an embodiment of the present application.

[0085] The above drawings have shown clear embodiments of the present application, which will be described in more detail later. These drawings and text descriptions are not intended to limit the scope of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0086] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the present application. Instead, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0087] The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in sequences other than those illustrated or described herein, for example.

[0088] In the embodiments of the present application, the words "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0089] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0090] Substation operation ticket is a written document used to record the steps and details of electrical operations performed in a substation. It provides a detailed list of operation steps to help operators perform tasks in the correct order and method.

[0091] After completing the electrical operation, the information on the substation operation ticket needs to be recorded in the power grid management platform, which usually includes detailed information such as the time, steps, and participants of the operation. This information backfilling helps to maintain digital records for subsequent management and analysis. After the substation operation ticket is backfilled to the power grid management platform, it needs to be archived, that is, the substation operation ticket is stored in a system for future inspection and audit.

[0092] Traditionally, substation operation tickets exist in paper form, and paper operation tickets need to be filled out manually, including recording operation steps, time, participants and other information. After filling out, the paper operation ticket needs to be manually reviewed and signed to ensure the accuracy and compliance of the information.

[0093] The completed and reviewed paper operation tickets need to be classified and filed, which is usually a manual process. The paper operation tickets need to be sorted by date, type or other criteria. The archived paper operation tickets are usually stored in a special archive room or file cabinet for future reference. When you need to check the historical operation tickets, you also need to manually search in the archive room or file cabinet.

[0094] Since the entire process relies on manual operation, manual processing is not only time-consuming, but also prone to errors, resulting in low filing efficiency. At the same time, due to the easy loss of paper operation tickets, classification errors or incomplete information during the manual filing process, the filing pass rate is also low.

[0095] With the rapid development of Robotic Process Automation (RPA) technology and image processing technology, the inventors have come up with the idea of ​​introducing RPA technology and image processing technology into the archiving process of substation operation tickets in response to the technical problems of low archiving efficiency and low archiving qualification rate caused by the above-mentioned manual operations. The paper version of the operation ticket is converted into a scanned version of the operation ticket in electronic image format through image processing technology, and other different image processing technologies are used to determine all the content information included in the scanned version of the operation ticket. Further, with the help of RPA technology, the automatic backfilling of content information is realized, which significantly reduces manual intervention, thereby reducing the human error rate, and effectively shortens the time required for archiving, improving the archiving efficiency and archiving qualification rate.

[0096] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0097] An embodiment of the present application provides a substation operation ticket archiving method based on RPA technology. Figure 1 Schematic diagram of the process of the substation operation ticket archiving method based on RPA technology provided in the embodiment of the present application Figure 1 ,like Figure 1 As shown in the figure, the RPA-based substation operation ticket archive includes:

[0098] S101. Obtain a paper version of the operation ticket of the target substation, and scan and upload the paper version of the operation ticket to the operation ticket management system of the target power grid management platform.

[0099] The paper operation ticket represents a written record used to record and guide the operation of the target substation. The paper operation ticket is placed in the scanner's feeder. When the scanner detects the paper operation ticket, the scanning function is automatically enabled and a high-definition electronic image is generated, namely the scanned operation ticket.

[0100] It should be noted that the storage location of the scanned operation ticket includes but is not limited to the local computer, network storage, cloud storage, built-in storage, etc., which usually depends on the settings and connection method of the scanner. At the same time, the scanned operation ticket can be saved in various formats, such as jpeg, png and other image formats.

[0101] In order to ensure a high-quality scanned operation ticket, the scanner should be set to a high resolution and the scanning speed should be adjusted to the lowest speed to minimize image distortion and improve recognition accuracy. The scanned operation ticket obtained by the scanner strictly corresponds to the paper operation ticket in size and resolution, that is, during the scanning process of the paper operation ticket through the scanner, it will not be deformed, nor will it be affected by ambient light, and there is no need to calibrate the generated scanned operation ticket.

[0102] After obtaining the scanned operation ticket, upload the scanned operation ticket to the operation ticket management system of the target power grid management platform.

[0103] S102, based on the preset cropping area, segment the scanned operation ticket in the operation ticket management system to generate multiple operation ticket sub-images; determine the content information contained in each operation ticket sub-image, and store the content information in a preset path.

[0104] Specifically, the scanned operation ticket is segmented according to the predefined cropping area using an image processing tool to generate a number of independent operation ticket sub-images, and the operation ticket sub-images are named according to their positions in the scanned operation ticket. Afterwards, the content information contained in each operation ticket sub-image is determined, and an empty dictionary containing no key-value pairs for storing the content information is constructed based on a preset method. The name of each operation ticket sub-image is used as the key of the key-value pair, and the corresponding content information is used as the value of the key-value pair, and the name of each operation ticket sub-image and the corresponding content information are stored in the empty dictionary in the form of key-value pairs.

[0105] It should be understood that since each operation ticket sub-image contains different content information, different image processing technologies need to be used to obtain the content information of each operation ticket sub-image. In one possible implementation, the operation ticket sub-images are classified based on preset standards to obtain first-category sub-images, second-category sub-images, and third-category sub-images. The first-category sub-images are recognized based on the preset optical character recognition (OCR) technology to determine the first content information of the first-category sub-images. The second-category sub-images are recognized based on the preset template matching technology to determine the second content information of the second-category sub-images. The third-category sub-images are recognized based on the preset graph learning technology to determine the third content information of the third-category sub-images.

[0106] Explanatory, OCR is a technology used to recognize characters and text in images, and can convert the text in the image into an editable text format. Through OCR technology, the text part in the first type of sub-image can be analyzed and converted into machine-readable text.

[0107] Template matching technology is used to search and identify parts in an image that are similar to a predefined template. Through template matching technology, parts of the second type of image that match the template image can be identified, thereby determining the content information contained in the second type of image.

[0108] Specifically, the specific steps of identifying the second type of sub-image by using the preset template matching technology include: matching the second type of sub-image with multiple preset template images based on the preset template matching technology, and calculating the matching degree between the second type of sub-image and the multiple preset template images. Sorting the matching degrees in descending order, determining the preset template image corresponding to the first matching degree as the target template image, and determining the content information of the target template image as the second content information of the second type of sub-image.

[0109] Graph learning technology is a branch of machine learning that focuses on processing and analyzing graph structured data. In image processing, graph learning can be used to model the relationship between pixels or features in an image. Through graph learning technology, the complex relationships and structures in the third-category sub-images can be identified and understood, thereby determining the content information contained in the third-category sub-images.

[0110] Specifically, the specific steps of identifying the third category sub-image by using the preset graph learning technology include: obtaining a first image comparison library from the target behavior center and a second image comparison library from the target dispatching center. The target behavior center is an organization responsible for controlling the target substation, and the target dispatching center is an organization responsible for controlling the target behavior center. Calculate the similarity between the third category sub-image and the first comparison image in the first image comparison library, or the second comparison image in the second image comparison library. Afterwards, sort the similarities in descending order, determine the comparison image corresponding to the first similarity as the target comparison image, and determine the content information of the target comparison image as the third content information of the third category sub-image.

[0111] It should be noted that whether the similarity between the third type of sub-image and the first comparison image or the second comparison image should be calculated is determined by the operation type of the substation operation ticket, wherein the operation type includes self-adjustment operation or dispatching operation.

[0112] In a possible implementation, feature extraction is performed on the third-category sub-image to obtain the first image feature, and the operation type of the scanned operation ticket where the third-category sub-image is located is further determined. If the operation type is a self-adjustment operation, feature extraction is performed on the first comparison image in the first image comparison library to obtain the second image feature. The first image feature and the second image feature are mapped to the same feature space, and based on the distance between the first image feature and the second image feature in the feature space, the similarity between the third-category sub-image and the first comparison image is determined.

[0113] If the operation type is a scheduling operation, feature extraction is performed on the second comparison image in the second image comparison library to obtain a third image feature. The first image feature and the third image feature are mapped to the same feature space, and based on the distance between the first image feature and the third image feature in the feature space, the similarity between the third type of sub-image and the second comparison image is determined.

[0114] After obtaining the first content information of the first type of sub-image, the second content information of the second type of sub-image, and the third content information of the third type of sub-image, the first content information, the second content information, and the third content information may be stored in the created empty dictionary.

[0115] Exemplarily, the serial number of each operation ticket sub-image (first type sub-image, second type sub-image or third type sub-image) is stored as a key in an empty dictionary, and the corresponding recognition result (first content information, second content information or third content information) is stored as a value in the empty dictionary. For example:

[0116] dict2 = {

[0117] key1:u"A substation",

[0118] key2:u"A ticket number",

[0119] key3: "Operations performed according to the unit's tasks",

[0120] key4: "self-adjustment"

[0121] key5: "A name",

[0122] key6: "B Name",

[0123] key7: "A time",

[0124] key8: "B time",

[0125] key9: "C time",

[0126] key10: "C Name",

[0127] key11: "D Name",

[0128] key12: "E Name"

[0129] }

[0130] It should be noted that the first content information, the second content information, and the third content information stored in the empty dictionary need to be analyzed to ensure that there is no unclear content, so that subsequent archiving operations can be continued.

[0131] Specifically, the first content information, the second content information, and the third content information stored in the empty dictionary are subjected to a preset correctness check and a preset integrity check, and abnormal content information that fails the preset correctness check and the preset integrity check is determined. The abnormal scanning version operation ticket corresponding to the abnormal content information is further determined, and the abnormal scanning version operation ticket is reissued.

[0132] Next, step S102 is explained in detail through a specific example.

[0133] In the first example, the scanned operation ticket is divided into 12 operation ticket sub-images according to the content information contained in the scanned operation ticket. The 12 operation ticket sub-images are named sub-image 1, sub-image 2, sub-image 3, sub-image 4, sub-image 5, sub-image 6, sub-image 7, sub-image 8, sub-image 9, sub-image 10, sub-image 11, and sub-image 12 respectively.

[0134] Among them, sub-image 1 is the substation operation ticket column, sub-image 2 is the ticket number column, sub-image 3 is the type column, sub-image 4 is the issuing unit column, sub-image 5 is the issuer column, sub-image 6 is the recipient column, sub-image 7 is the order receiving time column, sub-image 8 is the operation start time column, sub-image 9 is the operation end time column, sub-image 10 is the operator column, sub-image 11 is the guardian column, and sub-image 12 is the on-duty person in charge column.

[0135] Due to the inherent characteristics of sub-images 1 and 2 (the texts contained are all in standard fonts generated by computers), sub-image 4 (the text fonts contained are relatively simple), sub-images 7, 8 and 9 (the texts contained are composed of standard fonts generated by computers and handwritten numbers), and the fact that the current recognition of handwritten numbers is sufficiently accurate, OCR technology can be directly used to recognize sub-images 1, 2, 4, 7, 8 and 9 to obtain the content information contained therein.

[0136] Due to the inherent characteristics of sub-image 3 (check the rectangular box in front of the corresponding text), the preset template matching technology is used to match sub-image 3 with the template image. For example, template image 1 is a picture of a check in the rectangular box of the operation performed according to the dispatch order, and template image 2 is a picture of a check in the rectangular box of the operation performed according to the task of this unit. Among them, the sizes of template image 1, template image 2 and sub-image 3 are consistent, and the difference between template image 1 and template image 2 is in which rectangular box the check is made. From template image 1 and template image 2, determine the target template image that best matches sub-image 3, and determine the content information of the target template image as the content information of sub-image 3.

[0137] For sub-images 5, 6, 10, 11, and 12 (the texts contained are all handwritten names and signatures), due to the strong correlation between character morphology and writing style, OCR technology and preset template matching technology are difficult to achieve effective recognition. Therefore, graph learning technology in machine learning is used to recognize sub-images 5, 6, 10, 11, and 12 to obtain the content information contained.

[0138] Specifically, Figure 2 Schematic diagram of the process of the substation operation ticket archiving method based on RPA technology provided in the embodiment of the present application Figure 2 .like Figure 2 As shown in the figure, the image recognition using graph learning technology specifically includes the following steps:

[0139] S201, obtaining the electronic signature images of the staff of the target behavior center, and naming the electronic signature images with the corresponding names, to form a behavior center electronic signature comparison library (ie, the first image comparison library). The target behavior center is the organization responsible for controlling the target substation.

[0140] S202, obtaining the electronic signature image of the dispatcher of the target dispatch center, and naming the electronic signature image with the corresponding person's name to form the dispatch center electronic signature comparison library (ie, the second image comparison library). The target dispatch center is the institution responsible for controlling the target bank center.

[0141] S203, obtain the type column information from the sub-image 3 stored in the dictionary, and determine whether the current operation type is a self-adjusting operation or a scheduling operation. Assume that the type column information belongs to a self-adjusting operation. Then:

[0142] S204 , using a feature extractor (such as Gabor) to simultaneously extract features from sub-image 5 , sub-image 6 , sub-image 10 , sub-image 11 , and sub-image 12 to obtain first image features.

[0143] For the convenience of description, the first image feature is defined as X = [x 1 , x 2 , x 3 , x 4 , x 5 ]∈R d×5 . Where d represents the feature dimension.

[0144] S205 , using a feature extractor (such as Gabor) to simultaneously extract features from the electronic signature images in the behavior-centric electronic signature comparison library to obtain behavior-centric signature image features (ie, second image features).

[0145] The behavior center signature image feature is defined as Y = [y 1 ,y2 , …, y n ]∈R d×n , where d represents the feature dimension and n represents the number of electronic signature images.

[0146] S206. Use the Euclidean distance heat kernel to measure the similarity between the images to be identified (sub-image 5, sub-image 6, sub-image 10, sub-image 11 and sub-image 12) and the electronic signature images in the behavior center electronic signature comparison library.

[0147] The similarity between the image to be identified and the electronic signature image is defined as:

[0148]

[0149] Among them, δ is an adjustable parameter, S ij is the similarity matrix S∈R d×5 The element in the i-th row and j-th column of represents the similarity between sub-image i and the j-th electronic signature image.

[0150] S207, obtain similarity matrix S∈R d×5 The index corresponding to the maximum value of each row in is converted into the corresponding electronic signature text information (i.e. the name of the electronic signature image) according to the index.

[0151] If the type column information belongs to a scheduling operation, the process is similar to that of a self-scheduling operation:

[0152] S208 , using a feature extractor (such as Gabor) to simultaneously extract features from sub-image 5 , sub-image 6 , sub-image 10 , sub-image 11 , and sub-image 12 to obtain first image features.

[0153] S209, using a feature extractor (such as Gabor) to simultaneously extract features from the electronic signature images in the dispatch center electronic signature comparison library to obtain dispatch center signature image features (ie, third image features).

[0154] S210, using the Euclidean distance heat kernel to measure the similarity between the images to be identified (sub-image 5, sub-image 6, sub-image 10, sub-image 11 and sub-image 12) and the electronic signature images in the electronic signature comparison library of the dispatch center.

[0155] S211. Calculate the corresponding electronic signature text information (ie, the name of the electronic signature image) through similarity calculation.

[0156] After the corresponding electronic signature text information is found, S212, the name corresponding to the electronic signature text information is the name on the image to be identified (sub-image 5, sub-image 6, sub-image 10, sub-image 11 and sub-image 12).

[0157] So far, the content information contained in the 12 operation ticket sub-images has been determined. After that, this content information needs to be stored in the created empty dictionary. In order to avoid unclear content (such as text and numbers) in the dictionary, the content information stored in the dictionary needs to be analyzed. If there are no errors or omissions, the dictionary is input into the software robot used by RPA. Otherwise, it is recorded in the archive record and then a new substation operation ticket is re-executed.

[0158] Figure 3 Schematic diagram of the process of the substation operation ticket archiving method based on RPA technology provided in the embodiment of the present application Figure 3 .like Figure 3 As shown, S301, using OCR technology to identify the content information (substation name) of sub-image 1; S302, obtaining a pre-defined substation name comparison library; S303, determining whether the substation name included in sub-image 1 exists in the substation name comparison library; if not, then S304, selecting a most similar substation name in the substation name comparison library to correct the identification content of sub-image 1; S305, recording in the archived record.

[0159] Figure 4 Schematic diagram of the process of the substation operation ticket archiving method based on RPA technology provided in the embodiment of the present application Figure 4 ,like Figure 4 As shown, sub-image 4 can be verified by the results of sub-image 3.

[0160] S401, obtain the recognition result of sub-image 3; S402, use OCR technology to recognize the content information (order unit) of sub-image 4; S403, compare whether the recognition results of sub-image 3 and sub-image 4 are consistent; if not, then S404, record in the archive record.

[0161] Assuming that the recognition result of sub-image 3 is "operation performed according to the dispatch order", and the recognition result of sub-image 4 is "dispatching", then the recognition of the substation operation ticket is likely to be correct. If the recognition result of sub-image 4 is "self-adjustment", it is inconsistent with the recognition result of sub-image 3, indicating that there may be errors or omissions in other parts of the substation operation ticket. It is necessary to record it in the archived records and re-open a new operation ticket for archiving. The newly opened operation ticket can be manually verified and then archived manually.

[0162] Figure 5 Schematic diagram of the process of the substation operation ticket archiving method based on RPA technology provided in the embodiment of the present application Figure 5 ,like Figure 5 As shown, for sub-image 7, sub-image 8 and sub-image 9,

[0163] S501, using OCR technology to identify the content information of sub-image 7 (time of receiving the command);

[0164] S502, using OCR technology to identify the content information of the sub-image 8 (operation start time);

[0165] S503: Use OCR technology to identify the content information of the sub-image 9 (operation end time).

[0166] Comparing the time between sub-image 7, sub-image 8 and sub-image 9, the former are generally before the latter, that is, the "command receiving time" is earlier than the "operation start time", and the "operation start time" is earlier than the "operation end time".

[0167] S504, determine whether the command receiving time is earlier than the operation starting time; if so, execute S505, if not, execute S511.

[0168] S505, determine whether the operation start time is earlier than the operation end time; if so, execute S506, if not, execute S511.

[0169] Since the substation operation ticket can be archived within 6 days after the operation is completed, compare the time on sub-image 7, sub-image 8 and sub-image 9 with the current system time. The time on sub-image 7, sub-image 8 and sub-image 9 should be earlier than the current system time and later than the current system time of the previous day. That is,

[0170] S506, obtaining the current system time;

[0171] S507, obtaining the previous 48 hours of the current system time;

[0172] S508, determine whether the time 48 hours before the current system time is less than the command receiving time and less than the current system time; if so, execute S509, if not, execute S511.

[0173] S509, determine whether the time 48 hours before the current system time is less than the operation start time and less than the current system time; if so, execute S510, if not, execute S511.

[0174] S510, determine whether the time 48 hours before the current system time < the operation end time < the current system time; if not, execute S511.

[0175] S511. Record in the archive record.

[0176] It should be explained that the substation operation ticket can only be archived after execution is completed, so the time on sub-image 7, sub-image 8 and sub-image 9 must be earlier than the current system time. At the same time, the substation operation ticket must be archived in time after execution is completed. Even if there is a situation where the operation is performed today and archived the next day, the time on sub-image 7, sub-image 8 and sub-image 9 must occur within 48 hours before the current system time. If the time sequence does not meet the above logic, it needs to be recorded in the archive record and a new operation ticket needs to be opened for archiving.

[0177] In addition, for the text recognition of sub-image 3, sub-image 5, sub-image 6, sub-image 10, sub-image 11 and sub-image 12, since the text information is obtained indirectly instead of directly recognizing the text, there is no error or omission in text recognition.

[0178] S103. Configure the software robot used by RPA so that the configured software robot automatically logs into the target power grid management platform and enters the operation ticket management system.

[0179] Specifically, a preset script is added to the software robot used by RPA, and the preset script is executed based on the software robot to automatically log in to the target power grid management platform and enter the operation ticket management system. It should be noted that archiving substation operation tickets does not require the account and password of a specific person, but only requires the ability to successfully log in to the target power grid management platform.

[0180] Therefore, the preset script can include both the account and password required to log in to the target power grid management platform, and the hardware certificate and electronic key of the target terminal device to log in to the target power grid management platform. Both methods can realize the automation of the preset script, that is, the software robot can automatically log in to the target power grid management platform.

[0181] S104. Using a software robot, based on the content information stored in a preset path, archive the scanned operation ticket and generate an archive record.

[0182] Specifically, the software robot reads the content information stored in the dictionary, finds the operation ticket to be archived according to the content information, and then automatically backfills the data of the operation ticket to be archived. After the data backfilling is completed, the archiving operation is automatically performed and the archiving record is generated.

[0183] The substation operation ticket archiving method based on RPA technology provided in the present application obtains the paper version of the operation ticket of the target substation, and scans and uploads the paper version of the operation ticket to the operation ticket management system of the target power grid management platform. Among them, the scanned operation ticket is stored in the operation ticket management system in the format of an electronic image. Afterwards, based on the preset cropping area, the scanned operation ticket is segmented to generate multiple operation ticket sub-images. The operation ticket sub-images are classified based on the preset standard to obtain the first type of sub-image, the second type of sub-image and the third type of sub-image. Further, the first type of sub-image is identified by the preset OCR technology to determine the first content information of the first type of sub-image; the second type of sub-image is identified by the preset template matching technology to determine the second content information of the second type of sub-image; the third type of sub-image is identified by the preset graph learning technology to determine the third content information of the third type of sub-image. At the same time, the first content information, the second content information and the third content information are stored in the empty dictionary that has been created for storing content information in the form of key-value pairs. Next, a preset script is added to the software robot, and the preset script is executed based on the software robot to automatically log in to the target power grid management platform and enter the operation ticket management system. The software robot reads the content information stored in the dictionary to determine the operation tickets to be archived, and then performs data backfilling on the operation tickets to be archived, and archives the operation tickets to be archived after the data backfilling operation is completed. Through the application of automation technology, many steps that originally required manual work can be completed automatically, which not only reduces manual intervention, but also improves the accuracy and consistency of the entire archiving process. At the same time, because machines can process and enter information faster than humans, the automated process significantly shortens the time required for archiving and improves the efficiency of archiving substation operation tickets. Due to the reduction of human errors, the archiving qualification rate of substation operation tickets has also been improved, which means that the archived substation operation tickets are more accurate and reliable.

[0184] Next, a specific embodiment is used to Figure 1 The specific process of the substation operation ticket archiving method based on RPA technology is summarized as shown. Figure 6 The schematic diagram of the structure of the substation operation ticket archiving method based on RPA technology provided in this application is as follows: Figure 6 As shown, the substation operation ticket archiving method based on RPA technology includes: a scanning unit, an image segmentation unit, an information extraction unit, an information processing unit, an automatic login unit, a data backfilling and archiving unit, and a result feedback unit.

[0185] Among them, the scanning unit is used to convert the paper version of the operation ticket into a scanned version of the operation ticket. The image segmentation unit is used to segment the scanned version of the operation ticket to generate a number of operation ticket sub-images, which is convenient for subsequent information extraction and processing. The information extraction unit is used to obtain the content information contained in the operation ticket sub-image. The information processing unit is used to perform logical verification (preset correctness check, preset integrity check) on the content information contained in the operation ticket sub-image. The automatic login unit is used for the software robot to automatically log in to the target power grid management platform and enter the operation ticket management system. The data backfill and archiving unit is used to read the content information stored in the dictionary, and automatically backfill the data after finding the operation ticket to be archived according to the content information. The result feedback unit is used to summarize the situation of the operation tickets that have been archived, which is convenient for users to check.

[0186] It should be noted that the scanning unit is connected to the image segmentation unit, the image segmentation unit is connected to the information extraction unit, the information extraction unit is connected to the information processing unit, the information processing unit is connected to the automatic login unit, the automatic login unit is connected to the data backfilling and archiving unit, and the data backfilling and archiving unit is connected to the result feedback unit.

[0187] based on Figure 6 The structure shown, Figure 7 Schematic diagram of the process of the substation operation ticket archiving method based on RPA technology provided in the embodiment of the present application Figure 6 ,like Figure 7 As shown in the figure, the substation operation ticket archiving method based on RPA technology specifically includes the following steps:

[0188] S701, converting the paper operation ticket into a scanned operation ticket in electronic image format through a scanning unit;

[0189] S702, segmenting the scanned operation ticket through an image segmentation unit according to a predefined preset cropping area to generate a plurality of operation ticket sub-images;

[0190] S703, determining the content information contained in each operation ticket sub-image through the information extraction unit, and storing the content information in an empty dictionary;

[0191] S704, performing a preset correctness check and a preset integrity check on the content information stored in the dictionary through the information processing unit;

[0192] S705, adding a preset script to the software robot, and enabling the software robot to automatically log in to the target power grid management platform through the automatic login unit, and enter the operation ticket management system;

[0193] S706, reading the content information stored in the dictionary through the data backfilling and archiving unit, and automatically performing data backfilling after finding the operation ticket to be archived according to the content information;

[0194] S707. Summarize the archived operation tickets through the result feedback unit to generate archive records.

[0195] In terms of text information recognition, different specific image processing technologies are used for recognition according to the morphology and writing style of characters in different operation ticket images, which effectively improves the accuracy of text recognition. In terms of name recognition, considering the influence of character morphology and writing style, a predefined image comparison library and graph learning technology are used to indirectly obtain the name information on the operation ticket image. Compared with traditional OCR technology or other artificial intelligence methods, it not only improves the recognition accuracy, but also effectively overcomes the influence of character morphology and writing style on the recognition results. At the same time, by setting up a predefined image comparison library, the accuracy of image processing can be subsequently tested to ensure that timely records and feedback can be made when problems occur in recognition, thereby avoiding the occurrence of incorrect filing. In addition, by setting time verification logic, the time recognized on the operation ticket image is limited, which can not only verify the recognition accuracy and prevent recognition errors, but also verify the information on the operation ticket image to avoid filling errors. Finally, with the help of RPA technology, the automatic backfilling of operation ticket information can be realized, which significantly reduces manual intervention, thereby reducing the human error rate, and effectively shortens the time required for filing, improving the overall filing efficiency and filing qualification rate.

[0196] Figure 8 A schematic diagram of the structure of a substation operation ticket archiving device based on RPA technology provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, the substation operation ticket archiving device 800 based on the RPA technology includes: an uploading module 801, a cutting module 802, a determining module 803, a configuring module 804, and an archiving module 805;

[0197] The upload module 801 is used to obtain the paper version of the operation ticket of the target substation, scan and upload the paper version of the operation ticket to the operation ticket management system of the target power grid management platform; wherein the paper version of the operation ticket represents a written record used to record and guide the operation of the target substation;

[0198] The cropping module 802 is used to segment the scanned operation ticket in the operation ticket management system based on a preset cropping area to generate multiple operation ticket sub-images;

[0199] The determination module 803 is used to determine the content information contained in each operation ticket sub-image and store the content information in a preset path; wherein the scanned operation ticket is stored in the operation ticket management system in the format of an electronic image;

[0200] Configuration module 804, configured to configure the software robot used by the robotic process automation RPA, so that the configured software robot automatically logs into the target power grid management platform and enters the operation ticket management system; wherein the software robot represents a software program used to simulate human operations on a device terminal;

[0201] The archiving module 805 is used to archive the scanned operation ticket through a software robot based on the content information stored in the preset path and generate an archiving record.

[0202] In a possible design, the determination module 803 further includes: a classification module 806, for classifying the operation ticket sub-images based on a preset standard to obtain first-category sub-images, second-category sub-images, and third-category sub-images;

[0203] The determination module 803 is further used for:

[0204] Based on the preset optical character recognition (OCR) technology, the first type of sub-image is recognized to determine the first content information of the first type of sub-image; based on the preset template matching technology, the second type of sub-image is recognized to determine the second content information of the second type of sub-image; based on the preset graph learning technology, the third type of sub-image is recognized to determine the third content information of the third type of sub-image.

[0205] In a possible design, the determination module 803 further includes: a matching module 807 and a calculation module 808.

[0206] A matching module 807, configured to match the second type of sub-image with a plurality of preset template images based on a preset template matching technology;

[0207] A calculation module 808, configured to calculate the matching degree between the second type of sub-image and a plurality of preset template images;

[0208] The determination module 803 is further used to sort the matching degrees in descending order, determine the preset template image corresponding to the first matching degree as the target template image; and determine the content information of the target template image as the second content information of the second type of sub-image.

[0209] In a possible design, the determination module 803 further includes: an acquisition module 809, which is used to acquire a first image comparison library from a target behavior center and a second image comparison library from a target dispatching center; wherein the target behavior center represents an organization responsible for controlling the target substation, and the target dispatching center represents an organization responsible for controlling the target behavior center;

[0210] The calculation module 808 is further used to calculate the similarity between the third type of sub-image and the first comparison image in the first image comparison library, or the second comparison image in the second image comparison library;

[0211] The determination module 803 is further configured to sort the similarities in descending order, determine the comparison image corresponding to the first similarity as the target comparison image, and determine the content information of the target comparison image as the third content information of the third type of sub-image.

[0212] In a possible design, the calculation module 808 further includes: an extraction module 810, configured to extract features from the third type of sub-image to obtain first image features;

[0213] The determination module 803 is further used to determine the operation type of the scanning plate operation ticket where the third type of sub-image is located; wherein the operation type includes a self-adjustment operation or a scheduling operation;

[0214] The extraction module 810 is further configured to extract features of the first comparison image in the first image comparison library to obtain second image features if the operation type is a self-adjustment operation;

[0215] The determination module 803 is further used to map the first image feature and the second image feature to the same feature space, and determine the similarity between the third type of sub-image and the first comparison image based on the distance between the first image feature and the second image feature in the feature space;

[0216] The extraction module 810 is further configured to extract features from the second comparison image in the second image comparison library to obtain third image features if the operation type is a scheduling operation;

[0217] The determination module 803 is further configured to map the first image feature and the third image feature to the same feature space, and determine the similarity between the third type of sub-image and the second comparison image based on the distance between the first image feature and the third image feature in the feature space.

[0218] In a possible design, the determination module 803 further includes: a construction module 811 and a storage module 812.

[0219] A construction module 811 is used to construct an empty dictionary for storing content information based on a preset method; wherein the empty dictionary represents a data structure that does not contain any key-value pairs;

[0220] Storage module 812 is used to name each operation ticket sub-image; store the name of each operation ticket sub-image and the corresponding content information in an empty dictionary in the form of a key-value pair; wherein the name of each operation ticket sub-image is used as the key of the key-value pair, and the corresponding content information is used as the value of the key-value pair.

[0221] In a possible design, the configuration module 804 further includes: an adding module 813 and an execution module 814.

[0222] The adding module 813 is used to add a preset script in the software robot used by the RPA; wherein the preset script includes the account and password required to log in to the target power grid management platform, or includes the hardware certificate and electronic key of the target terminal device; the target terminal device represents the terminal device used to log in to the target power grid management platform;

[0223] The execution module 814 is used to execute a preset script based on the software robot to automatically log in to the target power grid management platform.

[0224] In one possible design, the archiving module 805 further includes: a reading module 815 for reading content information stored in a preset path based on a software robot;

[0225] The determination module 803 is further used to determine the operation ticket to be archived from the operation ticket management system based on the content information;

[0226] The archiving module 805 is also used to perform data backfilling operation on the operation tickets to be archived through a software robot; and to perform archiving operation on the operation tickets to be archived that have completed the data backfilling operation.

[0227] The substation operation ticket archiving device based on RPA technology provided in the embodiment of the present application can be used to execute the substation operation ticket archiving method based on RPA technology in any of the above embodiments. Its implementation principle and technical effects are similar and will not be repeated here.

[0228] It should be noted that it should be understood that the division of the various modules of the above device is only a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. And these modules can all be implemented in the form of software calling through processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software calling through processing elements, and some modules can be implemented in the form of hardware. In addition, all or part of these modules can be integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by an integrated logic circuit of hardware in the processor element or instructions in the form of software.

[0229] Fig. 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Fig. 9 As shown, the electronic device may include: a transceiver 91 , a processor 92 , and a memory 93 .

[0230] The processor 92 executes the computer execution instructions stored in the memory, so that the processor 92 executes the scheme in the above embodiment. The processor 92 can be a general-purpose processor, including a central processing unit CPU, a network processor (NP), etc.; it can also be a digital signal processor DSP, an application-specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components.

[0231] The memory 93 is connected to the processor 92 via a system bus and completes communication between them. The memory 93 is used to store computer program instructions.

[0232] The transceiver 91 may be used to communicate with other devices.

[0233] The system bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus. The transceiver is used to realize the communication between the database access device and other computers (such as clients, read-write libraries, and read-only libraries). The memory may include random access memory (RAM) and may also include non-volatile memory.

[0234] The electronic device provided in the embodiments of the present application can be used to execute the method provided in any of the above embodiments. The implementation principles and technical effects are similar and will not be repeated here.

[0235] An embodiment of the present application further provides a computer-readable storage medium, in which computer instructions are stored. When the computer instructions are executed on a computer, the computer executes the method provided in any of the above embodiments.

[0236] An embodiment of the present application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. At least one processor can read the computer program from the computer-readable storage medium. When at least one processor executes the computer program, the method provided in any of the above embodiments can be implemented.

[0237] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules is only a logical function division, and there may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0238] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to implement the solution of this embodiment.

[0239] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The above-mentioned module-composed unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0240] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the methods of various embodiments of the present application.

[0241] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

[0242] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0243] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0244] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special purpose computer.

[0245] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic control unit or a main control device.

[0246] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0247] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application 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 replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A substation operation ticket archiving method based on RPA technology, characterized in that: include: Obtain a paper version of the operation ticket of the target substation, and scan and upload the paper version of the operation ticket to the operation ticket management system of the target power grid management platform; wherein the paper version of the operation ticket represents a written record used to record and guide the operation of the target substation; Based on the preset cropping area, the scanned operation ticket in the operation ticket management system is segmented to generate multiple operation ticket sub-images; the content information contained in each operation ticket sub-image is determined, and the content information is stored in a preset path; wherein the scanned operation ticket is stored in the operation ticket management system in the format of an electronic image; The software robot used by the Robotic Process Automation (RPA) is configured so that the configured software robot automatically logs into the target power grid management platform and enters the operation ticket management system; wherein the software robot represents a software program used to simulate human operations on a device terminal; Through the software robot, the scanned operation ticket is archived based on the content information stored in the preset path, and an archive record is generated.

2. The method according to claim 1, characterized in that The content information contained in each operation ticket sub-image is determined, including: Classifying the operation ticket sub-images based on preset standards to obtain first-category sub-images, second-category sub-images, and third-category sub-images; The first category of sub-images is recognized based on a preset optical character recognition (OCR) technology to determine first content information of the first category of sub-images; the second category of sub-images is recognized based on a preset template matching technology to determine second content information of the second category of sub-images; the third category of sub-images is recognized based on a preset graph learning technology to determine third content information of the third category of sub-images.

3. The method according to claim 2, characterized in that The identifying the second type of sub-image based on a preset template matching technology to determine the second content information of the second type of sub-image includes: Based on a preset template matching technology, matching the second type of sub-image with a plurality of preset template images, and calculating the matching degree between the second type of sub-image and the plurality of preset template images; The matching degrees are sorted in descending order, and the preset template image corresponding to the matching degree ranked first is determined as the target template image; and the content information of the target template image is determined as the second content information of the second-category sub-image.

4. The method according to claim 2, characterized in that: The identifying the third type of sub-image based on the preset graph learning technology to determine the third content information of the third type of sub-image includes: Acquire a first image comparison library from a target behavior center and a second image comparison library from a target dispatching center; wherein the target behavior center represents an organization responsible for controlling the target substation, and the target dispatching center represents an organization responsible for controlling the target behavior center; Calculating the similarity between the third type of sub-image and the first comparison image in the first image comparison library, or the second comparison image in the second image comparison library; The similarities are sorted in descending order, and the comparison image corresponding to the first similarity is determined as the target comparison image; and the content information of the target comparison image is determined as the third content information of the third category sub-image.

5. The method according to claim 4, characterized in that The calculating the similarity between the third type of sub-image and the first comparison image in the first image comparison library, or the second comparison image in the second image comparison library, comprises: Extracting features from the third type of sub-image to obtain first image features; Determine the operation type of the scanning version operation ticket where the third type of sub-image is located; wherein the operation type includes a self-adjustment operation or a scheduling operation; If the operation type is a self-adjustment operation, extracting features from the first comparison image in the first image comparison library to obtain second image features; mapping the first image features and the second image features to the same feature space, and determining the similarity between the third type of sub-image and the first comparison image based on the distance between the first image features and the second image features in the feature space; If the operation type is a scheduling operation, feature extraction is performed on the second comparison image in the second image comparison library to obtain a third image feature; the first image feature and the third image feature are mapped to the same feature space, and based on the distance between the first image feature and the third image feature in the feature space, the similarity between the third type of sub-image and the second comparison image is determined.

6. The method according to claim 1, characterized in that The storing the content information to a preset path includes: Constructing an empty dictionary for storing the content information based on a preset method; wherein the empty dictionary represents a data structure that does not contain any key-value pairs; Name each operation ticket sub-image; store the name of each operation ticket sub-image and the corresponding content information in the empty dictionary in the form of key-value pairs; wherein the name of each operation ticket sub-image is used as the key of the key-value pair, and the corresponding content information is used as the value of the key-value pair.

7. The method according to claim 1, characterized in that The configuring of the software robot used by the robotic process automation (RPA) so that the configured software robot automatically logs into the target power grid management platform includes: Add a preset script in the software robot used by RPA; wherein the preset script includes the account and password required to log in to the target power grid management platform, or includes the hardware certificate and electronic key of the target terminal device; the target terminal device represents the terminal device used to log in to the target power grid management platform; The preset script is executed based on the software robot to automatically log in to the target power grid management platform.

8. The method according to claim 1, characterized in that The archiving operation of the scanned operation ticket by the software robot based on the content information stored in the preset path includes: Reading the content information stored in the preset path based on the software robot; Based on the content information, determine the operation tickets to be archived from the operation ticket management system, and perform data backfill operation on the operation tickets to be archived through the software robot; Archive the operation tickets to be archived that have completed the data backfill operation.

9. The method according to any one of claims 1 to 8, characterized in that: The method further comprises: Performing a preset correctness check and a preset integrity check on the content information stored in the preset path; Determine the abnormal content information that fails the preset correctness check and the preset integrity check, and determine the abnormal scan version operation ticket corresponding to the abnormal content information; The abnormal scanning version operation ticket is reissued.

10. A substation operation ticket archiving device based on RPA technology, characterized in that: include: An upload module is used to obtain a paper version of the operation ticket of the target substation, and scan and upload the paper version of the operation ticket to the operation ticket management system of the target power grid management platform; wherein the paper version of the operation ticket represents a written record used to record and guide the operation of the target substation; A cropping module, used to segment the scanned operation ticket in the operation ticket management system based on a preset cropping area to generate multiple operation ticket sub-images; A determination module, used to determine the content information contained in each operation ticket sub-image, and store the content information in a preset path; wherein the scanned operation ticket is stored in the operation ticket management system in the format of an electronic image; A configuration module, used to configure the software robot used by the Robotic Process Automation (RPA) so that the configured software robot automatically logs into the target power grid management platform and enters the operation ticket management system; wherein the software robot represents a software program used to simulate human operations on a device terminal; The archiving module is used to archive the scanned operation ticket through the software robot based on the content information stored in the preset path and generate an archiving record.

11. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the substation operation ticket archiving method based on RPA technology as described in any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the substation operation ticket archiving method based on RPA technology as described in any one of claims 1 to 9.

Images