A method and apparatus for processing a work order

Abstract

The application relates to a work order processing method and device, wherein the method comprises the following steps: a background server generates an initial problem work order containing a current problem screenshot and sends the work order to a work order server; the work order server performs image preprocessing on the current problem screenshot, generates a current problem feature map, classifies the initial problem work order based on the current problem feature map, and sends the classified problem work order to a rule analysis engine for analysis; the rule analysis engine generates an analysis result and returns the analysis result to the background server; and the background server processes the problem work order according to the analysis result. Thus, the application does not need to rely on manual classification and analysis by operation and maintenance personnel, but can automatically classify the problem work order by the work order server, improves the accuracy of problem work order classification, and automatically analyzes the problem work order by the rule analysis engine, thereby improving the efficiency of work order processing.

Description

Technical Field

[0001] This invention relates to the field of software technology, and in particular to a method and apparatus for processing work orders. Background Technology

[0002] Traditional APP issue ticket processing systems rely on maintenance personnel to visually observe screenshots of user-provided issues and combine them with issue descriptions to categorize the issues, determine the issue type, and then manually query the database based on the issue type to analyze the issues according to their personal experience, thereby processing the issues. However, this method mainly depends on the experience of maintenance personnel, is highly subjective, time-consuming, labor-intensive, and inefficient.

[0003] Application No. CN201710390392.0 discloses "A method and system for processing business work orders". This solution performs logical processing on work order messages through the configuration of a policy rule table, and determines whether the work order needs to be updated by sending a policy control instruction based on the result of the logical processing. However, the policy rule table configuration of this solution is only applicable to text type work orders with fixed format. It cannot match policy rules for different problem work orders provided by users, and therefore cannot actually solve the problem. Summary of the Invention

[0004] The technical problem to be solved by the present invention is: to provide a method and apparatus for processing work orders, so as to realize flexible processing of work orders and improve the efficiency of work order processing.

[0005] To solve the above-mentioned technical problems, the technical solution adopted by the present invention is as follows:

[0006] In a first aspect, the present invention provides a method for processing work orders, comprising:

[0007] The backend server obtains the problem information from the application and generates an initial problem ticket based on the problem information, which is then sent to the ticket server. The initial problem ticket includes a screenshot of the current problem.

[0008] The work order server receives the initial problem work order, performs image preprocessing on the current problem screenshot to generate a current problem feature map, classifies the initial problem work order based on the current problem feature map, obtains and sends the classified problem work orders to the rule analysis engine, so as to instruct the rule analysis engine to analyze the classified problem work orders to generate analysis results, and sends the analysis results to the backend server;

[0009] The backend server receives the analysis results and processes the initial problem work order based on the analysis results.

[0010] The beneficial effects of this invention are as follows: the work order server can receive problem work orders containing problem screenshots, and will perform image preprocessing on the problem screenshots to generate problem feature maps. Based on the problem feature maps, the problem work orders are classified, eliminating the need for maintenance personnel to visually observe problem screenshots and classify problem work orders based on personal experience. This improves the objectivity of problem work order classification, saves time, and increases work efficiency. The analysis of problem work orders is performed through a relational analysis engine, eliminating the need for maintenance personnel to manually query the database to analyze problem work orders, thus improving the efficiency of work order processing.

[0011] Optionally, the work order server receives the initial problem work order and performs image preprocessing on the current problem screenshot, including:

[0012] The work order server receives the initial problem work order, adds the initial problem work order to the work order list according to the path of the current problem screenshot, and performs image preprocessing on the current problem screenshot.

[0013] As described above, the ticket server adds the initial problem ticket to the ticket list under the same path based on the path of the current problem screenshot in the initial problem ticket. By classifying problem tickets by screenshot path, the ticket server can not only improve the retrieval and processing speed of problem tickets of the same category, but also make it easier for maintenance personnel to analyze and process problem tickets with the same path when browsing the ticket list.

[0014] Optionally, the work order server performs image preprocessing on the screenshot of the current problem to generate a feature map of the current problem, and classifies the initial problem work order based on the feature map of the current problem, including:

[0015] The work order server performs image preprocessing on the current problem screenshot to generate a grayscale problem screenshot.

[0016] Obtain the problem feature map of the historical problem screenshots stored in the same path in the database, and calculate the slope of each diagonal of the problem feature map of the historical problem screenshots, the sample standard deviation of the gray value of each pixel along each diagonal, and the number of pixels whose difference in the sample standard deviation of the gray value of adjacent pixels along each diagonal exceeds the threshold.

[0017]

[0018] Where S represents the sample standard deviation of the gray values ​​of each pixel along the diagonal, and X... i This represents the grayscale value of the i-th pixel. The grayscale value represents the average value of the feature map of the problem, and n represents the number of pixels;

[0019] Based on the slope of each diagonal line of the problem feature map of the historical problem screenshot, the grayscale problem screenshot is traversed row by row and pixel by pixel to extract line segments corresponding to the diagonal slope, generating line segments to be compared.

[0020] Calculate the sample standard deviation of the grayscale values ​​of each pixel along the line segment to be compared, and calculate the difference between the sample standard deviations of the grayscale values ​​of adjacent pixels along the line segment to be compared. When the difference of the sample standard deviations exceeds a threshold and the number of pixels exceeding the threshold is consistent with the number of pixels whose difference of the sample standard deviations of the grayscale values ​​of adjacent pixels along each diagonal of the problem feature map of the historical problem screenshot exceeds the threshold, then generate the current problem feature map based on the adjacent pixels that exceed the threshold.

[0021] The initial problem work orders are categorized based on the current problem feature map.

[0022] As described above, image preprocessing of the current problem screenshot involves converting the color problem screenshot into a grayscale problem screenshot. This process preserves the semantic information and feature distribution of the color problem screenshot while reducing the computational load of generating the subsequent problem feature map, thus improving the retrieval speed. Furthermore, detecting each pixel in each row of the current problem screenshot in a diagonal format is more accurate and effective than detecting pixels along the horizontal and vertical axes, thereby improving the accuracy of the current problem feature map.

[0023] Optionally, classifying the initial problem work order based on the current problem feature map includes:

[0024] The work order server deletes the current problem feature image and fixed display area from the current problem screenshot to obtain a second problem screenshot;

[0025] The historical problem screenshots are traversed based on the second problem screenshot to obtain the corresponding position of the current problem screenshot in the historical problem screenshots, and a historical screen area is generated based on the screen area of ​​the corresponding position.

[0026] The similarity between the screenshot of the second problem and the historical image area was calculated using Python's PIL algorithm.

[0027] Determine whether the similarity meets the threshold. If so, classify the current issue work order according to the category of the historical issue screenshot.

[0028] As described above, since the problem feature map may also appear on other interfaces, after determining the current problem feature map of the current problem screenshot, it is necessary to compare the similarity of the screen areas other than the current problem feature map in the current problem screenshot, so as to improve the accuracy of problem work order classification. When calculating the similarity of the screen areas other than the current problem feature map, the fixed display area is deleted. Since the fixed display area has no practical meaning and interferes with the similarity calculation, its deletion can reduce the amount of calculation, improve the calculation speed, and improve the accuracy of the results.

[0029] Optionally, the rule analysis engine analyzes the categorized problem work orders to generate analysis results, including:

[0030] The rule analysis engine obtains the user numbers of categorized problem work orders;

[0031] The execution result is obtained by executing a pre-stored SQL authentication statement associated with the historical problem screenshot in the database based on the user number;

[0032] When the execution result is successful, the user number meets the rule conditions of the SQL authentication statement, and the analysis result is generated according to the SQL authentication statement;

[0033] If the execution result is a failure, the user number does not meet the rule conditions of the SQL authentication statement, and the categorized problem work order is marked as a problem work order that does not meet the conditions, and the problem work order that does not meet the conditions is returned to the work order server.

[0034] As described above, the analysis of problem tickets is performed automatically by the rule analysis engine based on the user number of the problem ticket, executing pre-stored SQL authentication statements in the database. This eliminates the need for maintenance personnel to manually query the database and rely on personal experience to analyze problem tickets, saving labor costs while improving the efficiency and accuracy of the analysis.

[0035] Optionally, sending the analysis results to the backend server includes:

[0036] The rule analysis engine sends the analysis results to the message server, which instructs the message server to obtain the notification type of the analysis results based on the analysis results, and then sends the analysis results to the application based on the notification type.

[0037] As described above, the rule analysis engine also sends the analysis results to the message server, which then promptly sends the results to the application, enabling users to stay informed about the status of problem tickets and optimizing the user experience.

[0038] In a second aspect, the present invention provides an apparatus for processing work orders, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement a work order processing method as described in the first aspect.

[0039] The technical effects of the work order processing device provided in the second aspect are described in reference to the work order processing method provided in the first aspect. Attached Figure Description

[0040] Figure 1 A flowchart illustrating a work order processing method provided in an embodiment of the present invention;

[0041] Figure 2 This is a flowchart illustrating a work order processing method provided in an embodiment of the present invention.

[0042] Figure 3 This is a schematic diagram of the problem features involved in the embodiments of the present invention;

[0043] Figure 4 This is a schematic diagram illustrating the generation of a feature map of the current problem as described in an embodiment of the present invention;

[0044] Figure 5 This is a schematic diagram illustrating how the rule analysis engine involved in this embodiment of the invention analyzes categorized problem work orders;

[0045] Figure 6 This is a schematic diagram of a work order processing device provided in an embodiment of the present invention.

[0046] [Explanation of Labels in the Attached Image]

[0047] 1: A device for processing work orders;

[0048] 2: Processor;

[0049] 3: Memory. Detailed Implementation

[0050] To better understand the above technical solutions, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that the present invention can be understood more clearly and thoroughly, and that the scope of the present invention can be fully conveyed to those skilled in the art.

[0051] Example 1

[0052] Please refer to Figures 1 to 5 This invention provides a method for processing work orders, comprising the following steps:

[0053] S1. The backend server obtains the problem information from the application and generates an initial problem ticket based on the problem information, which is then sent to the ticket server. The initial problem ticket includes a screenshot of the current problem.

[0054] in, Figure 2 The web server described in this invention is the backend server.

[0055] In this embodiment, as Figure 2 As shown, taking a mobile device as an example, when a user fails to conduct business or participate in activities on the mobile device application for some reason, the application will pop up a toast window or error dialog box to inform the user. The user takes a screenshot of the error interface, fills in the problem description on the problem feedback interface, and uploads the problem screenshot to the application. The application will send the problem screenshot, problem description, user number, and problem screenshot path to the backend server. The backend server will generate a complete initial problem ticket including the problem screenshot based on the problem information and send the initial problem ticket to the ticket server.

[0056] S2. The work order server receives the initial problem work order, performs image preprocessing on the current problem screenshot to generate a current problem feature map, classifies the initial problem work order based on the current problem feature map, obtains and sends the classified problem work orders to the rule analysis engine, so as to instruct the rule analysis engine to analyze the classified problem work orders to generate analysis results, and sends the analysis results to the backend server.

[0057] In this embodiment, as Figures 2 to 5 As shown, the backend server will perform image preprocessing on the screenshot of the problem in the received initial problem ticket, generate the current problem feature map, and classify the initial problem ticket according to the current problem feature map, that is, determine the type of the initial problem ticket. After classification, the classified problem tickets will be sent to the rule analysis engine. The rule analysis engine will analyze the classified problem tickets and generate analysis results to return to the backend server.

[0058] At this point, the work order server in step S2 receives the initial problem work order and performs image preprocessing on the current problem screenshot, including:

[0059] S21. The work order server receives the initial problem work order, adds the initial problem work order to the work order list according to the path of the current problem screenshot, and performs image preprocessing on the current problem screenshot.

[0060] In this embodiment, the work order server will add the initial problem work order to the work order list under the same path according to the path of the current problem screenshot in the initial problem work order. Problem work orders are classified by the problem screenshot path, and problem work orders with the same path are grouped into one category to achieve unified management.

[0061] At this point, the work order server in step S2 performs image preprocessing on the current problem screenshot to generate a current problem feature map, and classifies the initial problem work order based on the current problem feature map, including:

[0062] S22. The work order server performs image preprocessing on the current problem screenshot to generate a grayscale problem screenshot;

[0063] In this embodiment, as Figure 2 As mentioned above, the screenshots uploaded by users are all in color. The toast window that pops up in the application is a dark gray window, surrounded by a normally bright interface. The error dialog box is a normally bright window, surrounded by a background interface covered with shadows. Due to the complexity of the colors in the screenshots, it is not easy to classify them later. Therefore, image preprocessing is required for the current screenshots, that is, grayscale quantization is performed on the current screenshots. The brightest grayscale is pure white, and the darkest grayscale is pure black. By processing the screenshots with a uniform grayscale, the color screenshots can be converted into grayscale screenshots.

[0064] S23. Obtain the problem feature map of the historical problem screenshots stored in the same path in the database, and calculate the slope of each diagonal of the problem feature map of the historical problem screenshots, the sample standard deviation of the gray value of each pixel along each diagonal, and the number of pixels whose difference in the sample standard deviation of the gray value of adjacent pixels along each diagonal exceeds the threshold.

[0065]

[0066] Where S represents the sample standard deviation of the gray values ​​of each pixel along the diagonal, and X... i This represents the grayscale value of the i-th pixel. The grayscale value represents the average value of the feature map of the problem, and n represents the number of pixels;

[0067] In this embodiment, as Figure 3As shown, the database pre-stores screenshots of historical issues encountered by operations and maintenance personnel during application testing. These screenshots are stored according to their paths. The database stores screenshots that have already undergone grayscale quantization, and marks toast windows or error dialog boxes on these screenshots in a rectangular format to form a problem feature map. Since the problem feature map has a significant brightness contrast with the surrounding interface, the brightness change can be determined by comparing the grayscale values ​​of each pixel. Calculating the sample standard deviation using the diagonal method is more efficient than using the horizontal and vertical axes. Therefore, it is necessary to calculate the slope of each diagonal line of the problem feature map, the sample standard deviation of the grayscale values ​​of each pixel along each diagonal line, and the number of pixels whose difference in the sample standard deviation of the grayscale values ​​of adjacent pixels along each diagonal line exceeds a threshold. The threshold is set to 50%, and this threshold value can be adjusted according to actual conditions. This serves as the standard for determining the problem feature map of the current problem screenshot.

[0068] S24. Based on the slope of each diagonal line of the problem feature map of the historical problem screenshot, traverse the grayscale problem screenshot row by row and pixel by pixel to extract line segments corresponding to the diagonal slope, and generate line segments to be compared.

[0069] S25. Calculate the sample standard deviation of the gray values ​​of each pixel along the line segment to be compared, and calculate the difference of the sample standard deviations of the gray values ​​of adjacent pixels along the line segment to be compared. When the difference of the sample standard deviations exceeds a threshold and the number of pixels exceeding the threshold is consistent with the number of pixels whose difference of the sample standard deviations of the gray values ​​of adjacent pixels along each diagonal of the problem feature map of the historical problem screenshot exceeds the threshold, then generate the current problem feature map based on the adjacent pixels that exceed the threshold.

[0070] In this embodiment, as Figure 4As shown, line segments 1, 2, 3, 4, and 5 are all line segments corresponding to the diagonal slopes of the problem feature map obtained in step S23 from the historical problem screenshot. The standard deviation of the grayscale values ​​of each pixel on these line segments is calculated, and then the difference in the standard deviations of the grayscale values ​​of adjacent pixels is calculated. This difference in standard deviations is compared with a preset threshold, which is the same as the threshold in step 23, set to 50%. The difference in the standard deviations of the grayscale values ​​of adjacent pixels is compared with 50% to determine if there is a significant change in grayscale. Line segment 1 is... The current problem screenshot shows a diagonal segment corresponding to a pixel in a certain row. If no area with a significant grayscale change is found at this point, then segment 2 is taken from the next pixel in the same row. If no area with a significant grayscale change is found again, this process is repeated until all pixels in the same row have had their corresponding diagonal segments taken. If no area with a significant grayscale change is found, then segment 3 is taken from the first pixel in the next row. If no area with a significant grayscale change is found, this process is repeated until segment 4 shows an area with a significant grayscale change. At this point, the number of pixels whose sample standard deviation difference exceeds 50% is determined. If the number of pixels with a sample standard deviation difference exceeding 50% for line segment 4 is N, it is compared with the number of pixels whose sample standard deviation difference of grayscale values ​​in the problem feature map of the historical problem screenshot in step 23 exceeds a threshold. If the number of pixels whose sample standard deviation difference of grayscale values ​​in the problem feature map of the historical problem screenshot in step 23 exceeds a threshold is N+1, since N≠N+1, line segment 4 does not meet the requirements of the problem feature map. Therefore, line segment extraction continues. Line segment 5 finds an area with obvious grayscale changes, and the difference in sample standard deviation of line segment 5 exceeds... The number of pixels exceeding 50% is N+1. This is consistent with the number of pixels whose sample standard deviation of grayscale values ​​exceeds the threshold in the problem feature map of the historical problem screenshot in step 23. Therefore, line segment 5 meets the requirements of the problem feature map. Line segment 5 is the diagonal of the current problem feature map. At this time, according to the slope of the other diagonal of the problem feature map of the historical problem screenshot obtained in step S23, the same operation is performed on the current problem screenshot until a line segment that meets the requirements is found. This line segment that meets the requirements is the other diagonal of the current problem feature map. Connecting all the pixels that meet the requirements will generate the current problem feature map of the current problem screenshot.

[0071] S26. Classify the initial problem work order based on the current problem feature map.

[0072] At this point, step S26 includes:

[0073] S261. The work order server deletes the current problem feature image and fixed display area of ​​the current problem screenshot to obtain a second problem screenshot.

[0074] S262. Traverse the historical problem screenshots according to the second problem screenshot to obtain the corresponding position of the current problem screenshot in the historical problem screenshots and generate a historical screen area according to the screen area of ​​the corresponding position.

[0075] In this embodiment, since the historical problem screenshots stored in the database are complete long screenshots, while the problem screenshots provided by the user may only be a part of the long screenshots, in order to further confirm the category of the current problem screenshot, it is necessary to compare the screen area in the current problem screenshot other than the current problem feature map. At this time, the fixed display area of ​​the problem screenshot, such as the status bar area at the top of the screenshot and the task bar area at the bottom of the screenshot, is deleted to avoid interference from other screen factors such as system time, carrier signal, and device battery level. At the same time, the current problem feature map generated in step S25 is also deleted from the current problem screenshot. In the remaining problem screenshots, the historical problem screenshots are scanned line by line with every ten rows of pixels as a template. It is checked which position in the historical problem screenshots can capture the same size screen starting from the specified position and then extracted from the historical screenshots to generate a historical screen area with the same size as the remaining problem screenshots.

[0076] S263. Calculate the similarity between the screenshot of the second problem and the historical image area using Python's PIL algorithm;

[0077] S264. Determine whether the similarity meets the threshold. If so, classify the current problem work order according to the category of the historical problem screenshot.

[0078] In this embodiment, the current problem work order is classified by calculating the similarity between the second problem screenshot and the historical screen area. When the similarity exceeds a threshold, the threshold is set to 90%. That is, when the similarity exceeds 90%, the current problem work order is classified according to the category of the historical screen area.

[0079] At this point, step S2 involves the rule analysis engine analyzing the categorized problem work orders to generate analysis results, and then sending the analysis results to the backend server, including:

[0080] S27. The rule analysis engine obtains the user numbers of the categorized problem work orders;

[0081] S28. Execute the SQL authentication statement pre-stored in the database and associated with the historical problem screenshot based on the user number to obtain the execution result;

[0082] S29. When the execution result is successful, the user number meets the rule conditions of the SQL authentication statement, and an analysis result is generated according to the SQL authentication statement.

[0083] S30. When the execution result is a failure, the user number does not meet the rule conditions of the SQL authentication statement, and the categorized problem work order is marked as a problem work order that does not meet the conditions, and the problem work order that does not meet the conditions is returned to the work order server.

[0084] In this embodiment, as Figure 5 As shown, operations and maintenance personnel store the rule conditions of SQL authentication statements for different types of problem tickets in the database. When the rule analysis engine analyzes the categorized problem tickets, it retrieves the SQL authentication statements stored in the database by the operations and maintenance personnel under the same category based on the category of the problem ticket. It executes the SQL authentication statement using the user number in the problem ticket. If the execution is successful, it means that the user number meets the rule conditions of the current SQL authentication statement, and the analysis result is generated based on the SQL authentication statement. If the execution fails, it means that the user number does not meet the rule conditions of the current SQL authentication statement, and the problem ticket is marked as a non-compliant problem ticket and returned to the ticket server. This allows operations and maintenance personnel to further optimize the handling of problem tickets by viewing the non-compliant problem tickets on the ticket server.

[0085] At this point, sending the analysis results to the backend server in step S2 includes:

[0086] S31. The rule analysis engine sends the analysis result to the message server, which instructs the message server to obtain the notification type of the analysis result based on the analysis result, and sends the analysis result to the application based on the notification type.

[0087] In this embodiment, as Figure 2 As shown, the rule analysis engine sends the analysis results to the backend server and also to the message server. When the message server receives the analysis results, it retrieves the notification type of the analysis results previously stored by the operations and maintenance personnel from the analysis results. Based on the notification type, it returns the analysis results to the application and provides timely feedback to the user. The notification types here include: push notification and voice broadcast. The specific notification type can be set according to the actual situation.

[0088] S3. The backend server receives the analysis results and processes the problem work order based on the analysis results.

[0089] In this embodiment, the backend server will process the problem work order based on the analysis results of the work order server and the processing method of the corresponding analysis results stored in the database by the operation and maintenance personnel. For example, invalid data will be removed and data will be modified. The processing method can be continuously improved and supplemented according to the actual situation.

[0090] Example 2

[0091] Please refer to Figure 6 A work order processing device 1 includes a memory 3, a processor 2, and a computer program stored in the memory 3 and executable on the processor 2. When the processor 2 executes the computer program, it implements the steps in the above embodiment 1.

[0092] Since the systems / devices described in the above embodiments of the present invention are systems / devices used to implement the methods of the above embodiments of the present invention, those skilled in the art can understand the specific structure and modifications of the systems / devices based on the methods described in the above embodiments of the present invention, and therefore will not be repeated here. All systems / devices used in the methods of the above embodiments of the present invention fall within the scope of protection of the present invention.

[0093] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0094] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions.

[0095] It should be noted that any reference numerals placed between parentheses in the claims should not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention can be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In claims that enumerate several means, several of these means may be embodied by the same hardware. The use of the terms first, second, third, etc., is merely for convenience of expression and does not indicate any order. These terms can be understood as part of the component names.

[0096] Furthermore, it should be noted that in the description of this specification, the terms "one embodiment," "some embodiments," "embodiment," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0097] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the claims should be interpreted to include both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0098] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, then this invention should also include these modifications and variations.

Claims

1. A method for processing work orders, characterized in that, include: The backend server obtains the problem information from the application and generates an initial problem ticket based on the problem information, which is then sent to the ticket server. The initial problem ticket includes a screenshot of the current problem. The work order server receives the initial problem work order, performs image preprocessing on the current problem screenshot to generate a current problem feature map, classifies the initial problem work order based on the current problem feature map, obtains and sends the classified problem work orders to the rule analysis engine, so as to instruct the rule analysis engine to analyze the classified problem work orders to generate analysis results, and sends the analysis results to the backend server; The backend server receives the analysis results and processes the initial problem work order based on the analysis results; The work order server performs image preprocessing on the screenshot of the current problem to generate a feature map of the current problem. Based on the feature map of the current problem, the initial problem work orders are classified as follows: The work order server performs image preprocessing on the current problem screenshot to generate a grayscale problem screenshot. Obtain the problem feature map of the historical problem screenshots stored in the same path in the database, and calculate the slope of each diagonal of the problem feature map of the historical problem screenshots, the sample standard deviation of the gray value of each pixel along each diagonal, and the number of pixels whose difference in the sample standard deviation of the gray value of adjacent pixels along each diagonal exceeds the threshold. Where S represents the sample standard deviation of the gray values ​​of each pixel along the diagonal line. This represents the grayscale value of the i-th pixel. The grayscale value represents the average value of the feature map of the problem, and n represents the number of pixels; Based on the slope of each diagonal line of the problem feature map of the historical problem screenshot, the grayscale problem screenshot is traversed row by row and pixel by pixel to extract line segments corresponding to the diagonal slope, generating line segments to be compared. Calculate the sample standard deviation of the grayscale values ​​of each pixel along the line segment to be compared, and calculate the difference between the sample standard deviations of the grayscale values ​​of adjacent pixels along the line segment to be compared. When the difference of the sample standard deviations exceeds a threshold and the number of pixels exceeding the threshold is consistent with the number of pixels whose difference of the sample standard deviations of the grayscale values ​​of adjacent pixels along each diagonal of the problem feature map of the historical problem screenshot exceeds the threshold, then generate the current problem feature map based on the adjacent pixels that exceed the threshold. The initial problem work orders are categorized based on the current problem feature map.

2. The work order processing method as described in claim 1, characterized in that, The work order server receives the initial problem work order and performs image preprocessing on the current problem screenshot, including: The work order server receives the initial problem work order, adds the initial problem work order to the work order list according to the path of the current problem screenshot, and performs image preprocessing on the current problem screenshot.

3. The work order processing method as described in claim 1, characterized in that, The classification of the initial problem work order based on the current problem feature map includes: The work order server deletes the current problem feature image and fixed display area from the current problem screenshot to obtain a second problem screenshot; The historical problem screenshots are traversed based on the second problem screenshot to obtain the corresponding position of the current problem screenshot in the historical problem screenshots, and a historical screen area is generated based on the screen area of ​​the corresponding position. The similarity between the screenshot of the second problem and the historical image area was calculated using Python's PIL algorithm. Determine whether the similarity meets the threshold. If so, classify the current issue work order according to the category of the historical issue screenshot.

4. The work order processing method as described in claim 1, characterized in that, The rule analysis engine analyzes the categorized problem work orders and generates analysis results, including: The rule analysis engine obtains the user numbers of categorized problem work orders; The execution result is obtained by executing a pre-stored SQL authentication statement associated with the historical problem screenshot in the database based on the user number; When the execution result is successful, the user number meets the rule conditions of the SQL authentication statement, and the analysis result is generated according to the SQL authentication statement; If the execution result is a failure, the user number does not meet the rule conditions of the SQL authentication statement, and the categorized problem work order is marked as a problem work order that does not meet the conditions, and the problem work order that does not meet the conditions is returned to the work order server.

5. The work order processing method as described in claim 1, characterized in that, Sending the analysis results to the backend server includes: The rule analysis engine sends the analysis results to the message server, which instructs the message server to obtain the notification type of the analysis results based on the analysis results, and then sends the analysis results to the application based on the notification type.

6. An apparatus for processing work orders, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 5.

Images