Inspection work order generation method, device and storage medium

Abstract

The present application discloses a method, device and storage medium for generating an inspection work order, and relates to the technical field of digital information processing. The invention discloses a method for generating an inspection work order, comprising: reading an inspection information entry template according to a serial number input by a user, wherein the inspection information entry template at least includes a record legend and a legend annotation; obtaining an inspection part of a selected device, calling a photographing device, and loading the legend annotation of the inspection part; based on the photographing device and the legend annotation, collecting an inspection image of the inspection part; determining the similarity between the inspection image and the record legend, and determining an upload result of the inspection image of the inspection part according to the similarity; after the upload results of all inspection parts of the device are successfully uploaded, generating an inspection work order for the device, thereby improving the accuracy of generating the inspection work order.

Description

Technical Field

[0001] The present application relates to the field of digital information processing technology, and in particular to a method, device and storage medium for generating an inspection work order. Background Art

[0002] With the development of science and technology and the popularization of intelligent equipment, equipment inspection has become an important part of ensuring the normal operation and stability of equipment. The traditional equipment inspection work order generation process mainly relies on the manual operation of on-site personnel, including data recording, on-site photography, and submission of inspection work orders. However, in large-scale or high-frequency inspection tasks, the manual operation and review process are complicated, and the photos taken on-site may lack standardization due to different conditions. The operating habits and standards of different inspection personnel may also lead to uneven quality of inspection work orders, resulting in low accuracy in the generation of inspection work orders.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a method, device and storage medium for generating inspection work orders, aiming to solve the technical problem of low accuracy in generating inspection work orders.

[0005] To achieve the above purpose, the present application proposes a method for generating an inspection work order, the method comprising:

[0006] Reading the inspection information entry template according to the serial number input by the user, wherein the inspection information entry template at least includes a record legend and a legend mark;

[0007] Obtain the inspection location of the selected equipment, call the shooting device, and load the legend annotation of the inspection location;

[0008] Based on the photographing device and the legend annotation, collecting the inspection image of the inspection part;

[0009] Determine the similarity between the inspection image and the record legend, and determine the upload result of the inspection image of the inspection part according to the similarity;

[0010] After the upload results of all inspection parts of the equipment are successfully uploaded, an inspection work order for the equipment is generated.

[0011] In one embodiment, the legend annotation includes a photography auxiliary line annotation, and the step of loading the legend annotation of the inspection location includes:

[0012] Determining the photography auxiliary line marking of the inspection location based on the edge shape of the inspection location;

[0013] Based on the photography auxiliary line marking, a photography mask layer is generated, and the shape of the photography mask layer is consistent with the shape of the photography auxiliary line marking to indicate the area that needs to be photographed.

[0014] In one embodiment, the legend annotation further includes image recognition area annotation, and the step of loading the legend annotation of the inspection location includes:

[0015] Determining the indicator object area of ​​the inspection location;

[0016] Based on the indicator object area, the image recognition area annotation is loaded.

[0017] In one embodiment, the step of determining the upload result of the inspection image of the inspection part according to the similarity includes:

[0018] When the similarity is greater than or equal to a first similarity threshold, determining that the upload result of the inspection image of the inspection part is successfully uploaded;

[0019] When the similarity is less than the first similarity threshold, it is determined that the upload result of the inspection image of the inspection part is an upload failure, and the inspection image of the inspection part is reacquired.

[0020] In one embodiment, the step of generating an inspection work order for the device includes:

[0021] Performing optical character recognition on the index object area of ​​the inspection part to obtain the index parameters of the inspection part;

[0022] Determine the health of the inspection part according to the index parameters of the inspection part;

[0023] An inspection work order for the equipment is generated based on the health of the inspection part and the similarity between the inspection image of the inspection part and the record legend.

[0024] In one embodiment, after the step of generating the inspection work order of the equipment, the method further includes:

[0025] The review decision of the equipment is determined based on the health of the inspection part and the similarity between the inspection image of the inspection part and the record legend.

[0026] In one embodiment, the step of determining the audit decision of the device based on the health of the inspection part and the similarity between the inspection image of the inspection part and the record legend includes:

[0027] If the similarity is less than the second similarity threshold, the inspection work order of the equipment is sent to the management end for manual review;

[0028] When the health of the inspection part is faulty, a repair work order for the equipment is generated;

[0029] When the health of the inspected part is at risk of failure, a maintenance work order for the equipment is generated;

[0030] When the health of the inspected parts is normal, the inspection work order of the equipment is reviewed and approved.

[0031] In one embodiment, after all inspection parts of the equipment are successfully uploaded, after the step of generating the inspection work order of the equipment, the step further includes:

[0032] Input the index parameters of the inspection parts into the decision model, wherein the historical inspection work orders of the equipment are classified to form audit decision data samples, and the decision model is constructed and trained based on the audit decision data samples;

[0033] An audit decision for the device is output based on the decision model.

[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes a patrol work order generation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the patrol work order generation method described above.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the inspection work order generation method described above are implemented.

[0036] The present application provides a method for generating an inspection work order, which comprises reading an inspection information entry template according to a serial number input by a user, wherein the inspection information entry template comprises at least an inspection order legend and a legend annotation; obtaining an inspection location of a selected device, calling a photographing device, and loading a legend annotation of the inspection location; collecting an inspection image of the inspection location based on the photographing device and the legend annotation; determining the similarity between the inspection image and the inspection order legend, and determining an upload result of the inspection image of the inspection location based on the similarity; and generating an inspection work order for the device after the upload results of all inspection locations of the device are successfully uploaded, thereby improving the accuracy of generating the equipment inspection work order. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] 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.

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0039] Figure 1 A flowchart of the first embodiment of the method for generating a patrol inspection work order of this application is provided;

[0040] Figure 2 This is an example diagram of the inspection information entry template provided in Example 1 of the present application;

[0041] Figure 3 A schematic diagram of a method flow provided for the first embodiment of the method for generating a patrol inspection work order of this application;

[0042] Figure 4 A schematic diagram of a method flow provided for the first embodiment of the method for generating a patrol inspection work order of this application;

[0043] Figure 5 A schematic diagram of the inspection image acquisition interface provided in Example 1 of the present application;

[0044] Figure 6 A schematic diagram of a method flow provided for the first embodiment of the method for generating a patrol inspection work order of this application;

[0045] Figure 7 This is an example diagram of device parameter value range setting information provided in Example 1 of the present application;

[0046] Figure 8 A schematic diagram of a method flow provided for the first embodiment of the method for generating a patrol inspection work order of this application;

[0047] Fig. 9 A flow chart of the second embodiment of the method for generating inspection work orders of this application;

[0048] Fig.10 A schematic diagram of a method flow provided for Embodiment 2 of the method for generating a patrol inspection work order of this application;

[0049] Fig.11 A flowchart of the third embodiment of the method for generating a patrol inspection work order of this application is provided;

[0050] Fig.12 This is an example diagram of an inspection work order provided in Example 3 of the present application;

[0051] Fig.13 This is an example diagram of the review decision results provided in Example 3 of the present application;

[0052] Fig.14A schematic diagram of a process for obtaining inspection images provided by the inspection work order generation method in an embodiment of the present application;

[0053] Fig.15 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the inspection work order generation method in the embodiment of the present application.

[0054] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0056] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0057] With the widespread use of intelligent equipment, it is essential to regularly inspect the equipment to ensure its normal operation and stability. In the traditional process of generating equipment inspection work orders, on-site personnel mainly rely on manual tasks such as data recording, on-site photography, and submitting inspection work orders. However, when faced with large-scale or frequent inspection needs, this process is cumbersome and prone to errors. Due to the inconsistency of shooting conditions, on-site photos are often difficult to meet standardization requirements. At the same time, differences in operating methods and standards of different users will also cause inconsistency in the quality of work orders, which in turn affects the accuracy of inspection work order generation.

[0058] In view of the above problems, the present application proposes a method for generating an inspection work order, which reads an inspection information entry template according to a serial number input by a user, wherein the inspection information entry template includes at least a record legend and a legend annotation; obtains the inspection part of the selected equipment, calls a shooting device, and loads the legend annotation of the inspection part; based on the shooting device and the legend annotation, collects the inspection image of the inspection part; determines the similarity between the inspection image and the record legend, and determines the upload result of the inspection image of the inspection part according to the similarity; after the upload results of all the inspection parts of the equipment are successfully uploaded, generates an inspection work order for the equipment, thereby improving the accuracy of generating equipment inspection work orders.

[0059] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, etc. The following takes the equipment inspection machine review system as an example to illustrate this embodiment and the following embodiments.

[0060] Based on this, the first embodiment proposed in this application provides a method for generating an inspection work order, referring to Figure 1In this embodiment, the inspection work order generation method includes steps S10 to S50:

[0061] Step S10, reading the inspection information entry template according to the serial number input by the user, wherein the inspection information entry template at least includes a record legend and a legend mark.

[0062] It should be noted that the serial number is the unique identifier of the equipment. Users can enter the serial number of the equipment by scanning or manually entering it, and retrieve the equipment inspection information entry template from the database based on the serial number. The inspection information entry template includes the inspection location record legend and legend annotation. The record legend can be an illustration in the equipment manual provided by the equipment manufacturer, an example diagram uploaded by the management personnel, or automatically generated by the equipment inspection machine review system; the legend annotation is a set of reference marks, which are used to assist users in accurately photographing and recording key parts of the equipment, such as indicator parameters on the display screen.

[0063] Optionally, the inspection information entry template also includes equipment-related information, such as model, specifications, installation location, etc. Based on the model and specifications of the equipment, the equipment inspection machine review system can determine the parts of the equipment that need to be inspected, such as sensors, interfaces, display screens, etc., and prepare recording legends and legend annotations for each inspection part.

[0064] For example, refer to Figure 2 , Figure 2 This is an example diagram of the inspection information entry template. Specifically, the serial number of the device is "XD100000234344", and the inspection steps of the device and the inspection and photo taking locations corresponding to each step are set in the template. Among them, the first step is to check the appearance of the device, including "water machine", "ice maker", "display screen" and "leakage protection switch"; the second step is to check the operating status of the device, including "compressor status", "water level switch" and "high pressure warning"; the third step is to check the equipment parameters of the device, including "pressure value", "equipment display temperature", "water tank surface temperature", "water tank pH value", "plug grounding test" and "plug zero fire test". Upload the standard photo taking legend in the record legend column, and the standard photo taking position reference line and machine inspection recognition area can be drawn in the legend annotation. Determine the analysis type of each inspection step, for example, perform image similarity verification in the first step, perform image similarity verification and reference value range verification in the second step, and similarly, perform image similarity verification and reference value range verification in the third step. Optionally, choose whether to analyze the specific photo taking location in each step.

[0065] Step S20, obtaining the inspection location of the selected equipment, calling the photographing device, and loading the legend annotation of the inspection location.

[0066] During the inspection process, the equipment inspection machine review system determines the specific parts that need to be inspected and recorded based on the equipment selected by the user, and uses a shooting device such as a smartphone or a dedicated camera to capture images of these parts, and displays corresponding legend annotations on the shooting interface to assist in accurate image capture and subsequent data analysis.

[0067] In a feasible implementation manner, the legend annotation includes a photography auxiliary line annotation, referring to Figure 3 , step S20 includes steps S21-S22:

[0068] Step S21, determining the photography auxiliary line marking of the inspection part based on the edge shape of the inspection part.

[0069] Step S22, generating a shooting mask layer based on the shooting auxiliary line marking, wherein the shape of the shooting mask layer is consistent with the shape of the shooting auxiliary line marking to indicate the area to be photographed.

[0070] It should be noted that the auxiliary line annotation for taking photos is a wireframe generated based on the edge shape of the inspection area, which is used to guide users to take photos of the inspection area. The shooting mask layer is used to provide visual guidance when users take photos of the inspection area, ensuring that the captured image includes all key areas that need to be inspected. Its shape is consistent with the shape of the auxiliary line annotation for taking photos. When the user uses the camera, the shooting mask layer will cover the inspection area with a darker layer.

[0071] Optionally, edge detection or contour extraction algorithms are used to extract the edge shape of the inspection part from the record legend, and the extracted edge shape is fitted into a closed shooting mask layer, which will be covered on the preview interface of the shooting device. The transparency of the shooting mask layer is adjusted according to the actual situation to ensure that it does not completely cover the inspection part, while providing sufficient visual guidance. When the user uses the shooting device to shoot, the equipment inspection machine review system will superimpose the generated shooting mask layer on the preview interface of the shooting device in real time.

[0072] Optionally, use the inspection record examples to train intelligent algorithms such as convolutional neural networks to identify the features of the inspection parts. The intelligent algorithm is installed and integrated on the camera of the shooting equipment. When the camera shoots the inspection parts in real time, the real-time image is analyzed by the intelligent algorithm to identify the location of the inspection parts, generate auxiliary line annotations for shooting, and guide users to shoot.

[0073] Optionally, the shooting mask layer may also be configured to shield areas that do not need to be shot, and only display the inspection parts that need to be shot.

[0074] In this embodiment, by loading the auxiliary line annotation when calling the camera device to shoot the inspection area, it is ensured that all users shoot according to a unified standard, thereby improving the consistency of the image and reducing errors or omissions of key information caused by improper shooting, so as to improve the accuracy of subsequent inspection work order generation.

[0075] In another feasible implementation, the legend annotation includes image recognition area annotation, referring to Figure 4 , step S20 includes steps S23-S24:

[0076] Step S23, determining the index object area of ​​the inspection location.

[0077] Step S24: loading the image recognition area annotation based on the indicator object area.

[0078] It should be noted that the indicator object area refers to those parts of the inspection site that contain key performance indicators or important status information during the equipment inspection. These areas include the equipment's dashboard, display screen, indicator light, switch status, reading area of ​​the measuring instrument, etc. They are directly related to the health and functional status of the equipment's operation and are used to monitor whether the equipment is operating normally, such as whether the switch is in the correct position and whether the indicator light displays the normal color. Once the indicator object area is determined, the equipment inspection machine review system will load the corresponding image recognition area annotations on the preview interface of the camera. These annotations typically include bounding boxes, marks, or other visual indicators drawn on the preview interface to indicate the location and range of the image recognition area.

[0079] Optionally, the image recognition area annotation may include an OCR (Optical Character Recognition) recognition area of ​​a text area, a graphic recognition area of ​​a device status indication, etc. These annotations help to more accurately identify and extract relevant information such as indicator parameters in the subsequent process.

[0080] Optionally, the YOLO algorithm or R-CNN (Region-based Convolutional Neural Network) algorithm is used to identify specific objects in the image. These algorithms can locate the location of the inspection part and generate one or more bounding boxes to represent the area in the inspection part where the indicator parameters need to be extracted.

[0081] In this embodiment, by loading the image recognition area annotation, it is ensured that the key information area in the inspection location is accurately identified and marked, and by quickly and accurately identifying the key area, the overall efficiency of inspection and data processing is improved.

[0082] For example, Figure 5As shown, there is a shooting auxiliary line marking on the periphery, namely the shooting reference line, and there is a darker shooting mask layer in the wireframe of the shooting reference line. The inner circle is the image recognition area marking, and a wireframe is drawn on the image recognition area to indicate the temperature data of the refrigerator.

[0083] Step S30: Based on the photographing device and the legend annotation, an inspection image of the inspection part is collected.

[0084] During the inspection process, the user logs in to the equipment inspection machine review system, enters the serial number of the equipment, obtains the inspection information entry template, selects the part to be inspected, and automatically obtains the record legend of the inspection part. Then the user starts the camera and loads the auxiliary line annotations and image recognition area annotations on the preview interface of the shooting device. The user takes a photo based on the auxiliary line annotations, collects the inspection image of the inspection part, and ensures that the captured picture contains the complete inspection part.

[0085] Step S40, determining the similarity between the inspection image and the record legend, and determining the upload result of the inspection image of the inspection part according to the similarity.

[0086] Use image processing algorithms such as the SSIM (Structural Similarity Index) algorithm or other image matching algorithms to quantify the similarity between the inspection image and the record legend, ensuring that the inspection image taken by the user is sufficiently consistent with the preset record legend, thereby ensuring the quality and accuracy of the inspection image.

[0087] For example, the SSIM algorithm is used to measure the similarity between two images, which takes into account the structural information, brightness information and contrast information of the image. Using the SSIM algorithm to compare the similarity between the pictures taken by the user and the record legend can help ensure the quality and consistency of the inspection images and improve the efficiency of equipment maintenance and management. Similarity is a value calculated by the SSIM algorithm or other similarity algorithms to indicate the similarity between the inspection image and the record legend.

[0088] For example, after acquiring the inspection image uploaded by the user, the equipment inspection machine review system crops the inspection image and the record legend into the same size, and normalizes the pixel values ​​of the two images to the range of [0, 1] to eliminate the influence of brightness differences for comparison. The inspection image is then divided into multiple local areas, such as 8×8 pixel blocks. For each local area, the SSIM value of the area corresponding to the record legend is calculated to obtain a local SSIM value matrix. The local SSIM value matrix is ​​weighted averaged to obtain an overall SSIM value. The weight can be set according to the importance of the local area. For example, the weight of the image area that displays the indicator parameters can be higher.

[0089] Optionally, in addition to the SSIM value, other similarity algorithms may be used to calculate other indicators, such as Mean Squared Error (MSE) and Peak Signal-to-Noise Ratio (PSNR), as auxiliary references.

[0090] In one possible implementation, refer to Figure 6 , step S40 includes steps S41-S42:

[0091] Step S41: when the similarity is greater than or equal to a first similarity threshold, determining that the upload result of the inspection image of the inspection part is successfully uploaded.

[0092] Step S42: when the similarity is less than the first similarity threshold, determining that the upload result of the inspection image of the inspection part is upload failure, and reacquiring the inspection image of the inspection part.

[0093] Optionally, use the SSIM algorithm or other similarity algorithms to compare the similarity values ​​between the inspection image taken by the user and the record list legend. Set a first similarity threshold as a reference standard for the similarity between the inspection image and the record list legend. If the similarity between the inspection image is lower than the preset first similarity threshold, it means that the similarity between the inspection image and the record list legend is not high enough, and there is a shooting error. The equipment inspection machine review system confirms that the inspection image shooting error occurs, the inspection image upload fails, and notifies the user to retake the photo. The user retakes the picture of the inspection part according to the instructions of the equipment inspection machine review system to ensure that the similarity between the picture and the record list legend reaches the first similarity threshold. If the similarity between the inspection image is greater than or equal to the preset first similarity threshold, it means that the inspection image and the record list legend are highly similar, the shooting quality is good, and the inspection image is successfully uploaded.

[0094] For example, suppose a chemical plant needs to inspect its equipment regularly to ensure safety and compliance. The plant uses an equipment inspection machine review system and uses the SSIM algorithm to evaluate the quality of inspection images. The preset first similarity threshold is 80%. After the user logs in to the equipment inspection machine review system, he uses a camera to take pictures of the inspection area according to the recording order legend, and uses the SSIM algorithm to compare the similarity between the captured picture and the pre-stored recording order legend. If the equipment inspection machine review system calculates that the similarity between the captured image and the pre-stored recording order legend is 75%, which is lower than the preset 80% threshold, it is judged that the shooting does not meet the requirements, and notifies the user: "The captured picture is not similar enough to the recording order legend, and the inspection image upload fails. Please retake it in time." and provides shooting guidance. According to the prompts of the equipment inspection machine review system, the user adjusts the shooting angle and light, and retakes the picture of the inspection area. The equipment inspection machine review system performs a similarity evaluation again, and the calculated similarity is 85%, which is higher than the preset threshold. The equipment inspection machine review system confirms that the picture meets the requirements and uploads the picture.

[0095] Optionally, the degree of similarity is determined based on different ranges of similarity values ​​of the inspection images, and the data is saved in the background database of the equipment inspection machine review system. Figure 7 Specifically, the parameter value range setting information includes the standard recording legend of the inspection equipment, the type of legend annotation such as the auxiliary line for taking photos and the image recognition area, the annotation area such as the front of the equipment and the temperature display screen, and the image analysis type such as similar image recognition and OCR recognition. In similar image recognition, when the similarity between the inspection image and the recording legend is 80%~100%, the similarity of the inspection image is "similar", and it can be judged that the inspection image is taken normally, the review is passed, and the inspection image is uploaded successfully; when the similarity between the inspection image and the recording legend is 60%~80%, the similarity is "suspected", and it is judged that the inspection image needs to be returned for re-inspection, and the inspection image upload fails; when the similarity between the inspection image and the recording legend is 0%~60%, the similarity is "unsimilar", and it is judged that the inspection image needs to be returned for re-inspection, and the inspection image upload fails.

[0096] In this embodiment, the quality of the inspection image is ensured through similarity evaluation, duplication of work and inaccurate data caused by shooting errors are avoided, the inspection process is simplified, the need for human judgment is reduced, and the inspection efficiency is improved.

[0097] Step S50: after the upload results of all inspection parts of the equipment are successfully uploaded, an inspection work order for the equipment is generated.

[0098] In one possible implementation, refer to Figure 8 , step S50 includes steps S51 to S53:

[0099] Step S51, performing optical character recognition on the index object area of ​​the inspection part to obtain the index parameters of the inspection part.

[0100] It should be noted that OCR is used to recognize and extract printed or handwritten text from an image, and index parameters can be extracted from the image recognition area of ​​the inspection image.

[0101] Optionally, the inspection image is resized to a size suitable for processing, converted to a grayscale image, and a filter is used to remove noise, such as a median filter or a Gaussian filter, to improve the quality of the inspection image. According to a preset object recognition algorithm, the indicator object area in the inspection image is automatically identified and the corresponding wireframe is displayed, where these wireframes usually correspond to specific parts of the inspection area or markings on the equipment, such as thermometers, pressure gauges, etc. The equipment inspection machine review system uses OCR to identify and extract text in the indicator object area, converts it into a machine-readable format, stores the extracted indicator parameters in the database, and uses them for subsequent data analysis and report generation.

[0102] For example, suppose you want to inspect the temperature of a refrigerator. When inspecting the refrigerator, the user selects the corresponding equipment and equipment parts, such as the refrigerator temperature display, from the equipment inspection machine review system. At this time, the equipment inspection machine review system will provide a record sheet legend of the refrigerator temperature display. The equipment inspection machine review system generates a photo auxiliary wireframe based on the edge shape of the temperature display in the record sheet legend. This wireframe will be covered on the preview interface of the camera. The user starts the camera and takes a photo according to the photo auxiliary wireframe on the preview interface. Due to the effect of the mask layer, the photo taken only contains the temperature display area, and other irrelevant areas are blocked. After correctly acquiring the inspection image, the equipment inspection machine review system automatically identifies the temperature display area in the captured temperature display image, uses OCR to identify the temperature reading in the temperature display area, such as "+25℃", extracts the recognized numbers and units, and converts them into numerical format, such as "25.0℃".

[0103] Step S52: determining the health of the inspection part according to the indicator parameters of the inspection part.

[0104] Step S53, generating an inspection work order for the equipment based on the health of the inspection part and the similarity between the inspection image of the inspection part and the record legend.

[0105] It should be noted that the health degree is a status result differentiated according to the indicator parameters relative to the preset value range, which is used to determine whether the inspected part is in a normal state, a risk state or a fault state.

[0106] For example, refer to Figure 7, set different ranges of preset indicator value domains according to the indicator parameters. In OCR recognition, the temperature indicator parameters identified from the temperature display screen of the ice maker are divided into three value domains of different degrees. When the temperature reading is -10℃~-25℃, the indicator parameter is a healthy value, and the health of the inspection part is normal; when the temperature reading is 0℃~-10℃, the indicator parameter is a risk value, and the health of the inspection part is at risk of failure; when the temperature reading is greater than 0℃, the indicator parameter is a fault value, and the health of the inspection part is a fault.

[0107] Optionally, the inspection work order may also include detailed inspection results, image data, and any necessary maintenance or repair recommendations for the inspection area. Figure 7 In the process, the inspection results of the inspection part can be determined according to the health of the inspection part, including normal, maintenance and repair, and suggestions can be provided, such as generating a maintenance work order or a repair work order.

[0108] In this embodiment, the inspection work order is automatically generated by reading the inspection information entry template corresponding to the equipment serial number and using a photographing device to capture and evaluate the similarity between the inspection image and the record legend, thereby improving the inspection efficiency, accuracy and standardization level, while reducing human errors and operating costs and improving the accuracy of inspection work order generation.

[0109] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can refer to the above introduction, and will not be repeated later. Fig. 9 After step S50, the inspection work order generation method further includes step S60:

[0110] Step S60, determining the audit decision of the equipment based on the health of the inspection part and the similarity between the inspection image of the inspection part and the record legend.

[0111] In one possible implementation, refer to Fig.10 , step S60 includes steps S61 to S64:

[0112] Step S61: if the similarity is less than the second similarity threshold, the inspection work order of the equipment is sent to the management end for manual review.

[0113] Step S62: When the health of the inspected part is faulty, a repair work order for the equipment is generated.

[0114] Step S63: When the health of the inspected part indicates that there is a risk of failure, a maintenance work order for the equipment is generated.

[0115] Step S64: When the health of the inspected parts is normal, the inspection work order of the equipment is reviewed and approved.

[0116] It should be noted that the second similarity threshold is used to distinguish the degree of difference of the inspection images, wherein the second similarity threshold is greater than the first similarity threshold. When the similarity between the inspection image and the record legend is lower than the second similarity threshold, it indicates that the equipment status may have changed, resulting in deviations in the inspection image, such as deformation of certain components. In this case, the equipment inspection machine review system will send the inspection work order to the back-end management personnel for manual review, and the reviewers on the management side will manually check these work orders to ensure the accuracy and reliability of the inspection results.

[0117] When the health status assessment result of the inspection part is a failure, it means that there is an obvious problem or damage to the equipment and it needs to be repaired immediately. In this case, the equipment inspection machine review system will automatically generate a repair work order so that the maintenance team can respond and handle the failure as soon as possible. If the health status assessment of the inspection part shows that there is a risk of failure, this may mean that although the equipment is currently operating normally, there are potential problems that may cause future failures. The equipment inspection machine review system will generate a maintenance work order so that preventive maintenance measures can be taken to reduce the risk of failure. When the health status assessment results of all inspection parts are normal, it means that the equipment is in good operating condition and no problems or risks are found. In this case, the equipment inspection machine review system will review and approve the inspection work order of the equipment to confirm that the equipment is in good condition.

[0118] In this implementation, the inspection work order of the equipment is automatically generated by intelligently analyzing the similarity between the inspection image and the record legend and the health of the inspection part, and intelligently reviewing and deciding whether manual review is required or generating corresponding repair and maintenance work orders based on the similarity results and the equipment status. This process not only improves the inspection efficiency and ensures the timeliness and accuracy of equipment maintenance, but also improves the overall equipment management quality by reducing human errors and optimizing resource allocation.

[0119] Based on the above embodiment, in the third embodiment of the present application, the same or similar contents as those in the above embodiment can be referred to the above introduction, and will not be described in detail later. Fig.11 After step S50, the inspection work order generation method further includes steps S70 to S80:

[0120] Step S70, inputting the index parameters of the inspection parts into the decision model, wherein the historical inspection work orders of the equipment are classified to form audit decision data samples, and based on the audit decision data samples, the decision model is constructed and trained.

[0121] Step S80: outputting the audit decision of the device based on the decision model.

[0122] Input the key performance indicators of the inspection site, such as temperature, pressure, flow, etc., into the decision model. These parameters are key data for evaluating the status of the equipment. Collect and analyze the historical inspection work orders of the equipment, and classify the data for easy analysis and learning. Classification can be based on equipment status, fault type, etc. Extract audit decision data samples from the classified historical data. These samples will be used to train the decision model to help the model learn how to make decisions based on the inspection data. Use the extracted data samples to build a decision model. This model may include multiple algorithms, such as classification algorithms, regression analysis, or other machine learning algorithms. Train the constructed decision model so that it can predict the status of the equipment based on the input indicator parameters and historical data, and provide audit decisions.

[0123] For example, historical inspection work orders of equipment are classified to form audit decision data samples, such as Fig.12 As shown, the data sample includes inspection work orders for three inspection locations, including the front of the device at location A, the power supply of the device at location B, and the plug of the device at location C. In the inspection work order for the front of the device, the inspection image similarity analyzed by similar image recognition is 88%, and within the similarity value range setting, the audit result is passed, and the inspection image is successfully uploaded; the OCR recognition and analysis result shows that the temperature reading of the temperature display screen on the front of the device is "-10 degrees Celsius", and within the normal value range setting, the audit result is passed. In the inspection work order for the power supply of the device, the inspection image similarity analyzed by similar image recognition is 82%, and within the similarity value range setting, the audit result is passed, and the inspection image is successfully uploaded; the OCR recognition and analysis result shows that the recognition result of the grounding test of the device power supply is "resistance value 100Ω", and within the normal value range setting, the audit result is passed. In the inspection work order of the equipment plug, the similarity of the inspection image analyzed by similar image recognition is 99%. Within the similarity value range setting, the review result is passed, and the inspection image is uploaded successfully; the OCR recognition and analysis result shows that the recognition result of the zero-fire test of the equipment plug is "resistance value 0.1". Within the risk value range setting, the review result is to generate a maintenance work order.

[0124] Exemplarily, the audit decision data sample is input into the decision model, and the audit decision of the equipment is output. Optionally, the judgment logic of the decision model can be defined as: the first step is to count the similarity of the decision data samples. If the result of any inspection part is found to be marked as "suspected" in the analysis, it is automatically decided to send the work order to the manual review process for further inspection and confirmation by professionals. If no "suspected" result is found in the first step, the second step will be carried out to check the health of the inspection part. If the health status of any part in the inspection part is found to be evaluated as a "fault value", it will be automatically decided to generate a repair work order so that maintenance can be carried out as soon as possible. If no inspection part is evaluated as a "fault value" in the second step, the inspection of the health of the inspection part will continue. At this time, if the health status of any inspection part is found to be marked as a "risk value", it will be automatically decided to generate a maintenance work order to take preventive maintenance measures. If no "risk value" is found, it will be automatically decided that the inspection work order has been reviewed and approved, and it is considered that the equipment inspection result meets the requirements and no additional manual intervention or maintenance measures are required. According to the judgment logic of the above decision model, the following can be obtained: Fig.13 The audit decision results are shown.

[0125] Specifically, in Fig.13 In the first set of data shown, the similarity of the three inspection parts is "similar", but the corresponding value range health of part A is "risk value", so the processing decision is "generate maintenance work order". Fig.13 In the second set of data shown, the similarity of the three inspection parts is "similar", but the corresponding value range health of part A is "fault value", so the processing decision is "generate repair work order". Fig.13 In the third set of data shown, the similarity of part A is "suspected", so the processing decision is "manual intervention". Fig.13 In the fourth set of data shown, the similarities of the three inspection locations are all "similar", and the corresponding range health of the three locations is "normal", so the processing decision is "approved".

[0126] In this embodiment, audit decision data samples are formed through historical inspection work order data to build and train a decision model, automatically analyze and output the audit decisions of the equipment, thereby improving the accuracy and reliability of the decision. In addition, automated decision support reduces the need for manual analysis and improves equipment inspection efficiency.

[0127] For example, in order to help understand the implementation process of the inspection work order generation method obtained by combining this embodiment with the above embodiments, please refer to Fig.14 , Fig.14A flow chart for obtaining inspection images based on the inspection information entry template is provided. Specifically: after logging into the equipment inspection machine review system, the user enters the serial number of the equipment to be inspected, obtains the corresponding inspection information entry template through the serial number, reads the information of the inspection information entry template, and selects the corresponding part to take a photo. After calling the camera, the equipment inspection machine review system will load the photo auxiliary wireframe according to the recording legend to help obtain the correct inspection image, and then calculate the similarity of the inspection image through the similarity algorithm. The calculated similarity is compared and verified with the preset first similarity threshold. If the similarity is less than the preset first similarity threshold, the inspection image upload fails and the inspection image is re-acquired; if the similarity is greater than or equal to the first similarity threshold, the inspection image upload is successful.

[0128] The present application provides an inspection work order generation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the inspection work order generation method in the above-mentioned embodiment one.

[0129] Reference below Fig.15 , which shows a schematic diagram of the structure of an inspection work order generation device suitable for implementing the embodiment of the present application. The inspection work order generation device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptops, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions: tablet computers), PMPs (Portable Media Players: portable multimedia players), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.15 The inspection work order generating device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0130] like Fig.15As shown, the inspection work order generation device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the inspection work order generation device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the inspection work order generation device to communicate with other devices wirelessly or wired to exchange data. Although the inspection work order generation device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided alternatively.

[0131] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0132] The inspection work order generation device provided by the present application adopts the inspection work order generation method in the above embodiment, which can solve the technical problem of low accuracy of inspection work order generation. Compared with the prior art, the beneficial effects of the inspection work order generation device provided by the present application are the same as the beneficial effects of the inspection work order generation method provided by the above embodiment, and other technical features in the inspection work order generation device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0133] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0134] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0135] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the inspection work order generation method in the above-mentioned embodiment.

[0136] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0137] The computer-readable storage medium may be included in the inspection work order generating device; or may exist independently without being assembled into the inspection work order generating device.

[0138] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the inspection work order generation device, the inspection work order generation device can write computer program codes for performing the operations of the present application in one or more programming languages ​​or a combination thereof. The programming languages ​​include object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0139] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0140] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0141] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned inspection work order generation method, and can solve the technical problem of low accuracy in inspection work order generation. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the inspection work order generation method provided in the above-mentioned embodiment, and will not be described in detail here.

[0142] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for generating an inspection work order, characterized in that: The method includes: The inspection information entry template is read according to the serial number input by the user. The inspection information entry template defines the inspection steps of the equipment and the inspection parts and photographing parts corresponding to each inspection step, as well as the record legend and legend annotation corresponding to each inspection part. The legend annotation includes the annotation of the auxiliary line for photographing and the annotation of the image recognition area; The inspection part of the selected equipment is obtained, a shooting device is called, and a legend annotation of the inspection part is loaded: based on the edge shape of the inspection part, the auxiliary shooting line annotation of the inspection part is determined; based on the auxiliary shooting line annotation, a shooting mask layer is generated, the shape of the shooting mask layer is consistent with the shape of the auxiliary shooting line annotation to indicate the area to be photographed; the indicator object area of ​​the inspection part is determined, and based on the indicator object area, the image recognition area annotation is loaded; Based on the photographing device and the legend annotation, collecting the inspection image of the inspection part; Determine the similarity between the inspection image and the record legend, and determine the upload result of the inspection image of the inspection part according to the similarity; After the upload results of all inspection parts of the equipment are successfully uploaded, an inspection work order for the equipment is generated.

2. The method according to claim 1, characterized in that The step of determining the upload result of the inspection image of the inspection part according to the similarity comprises: When the similarity is greater than or equal to a first similarity threshold, determining that the upload result of the inspection image of the inspection part is successfully uploaded; When the similarity is less than the first similarity threshold, it is determined that the upload result of the inspection image of the inspection part is an upload failure, and the inspection image of the inspection part is reacquired.

3. The method according to claim 1, characterized in that The step of generating the inspection work order of the equipment comprises: Performing optical character recognition on the index object area of ​​the inspection part to obtain the index parameters of the inspection part; Determine the health of the inspection part according to the index parameters of the inspection part; An inspection work order for the equipment is generated based on the health of the inspection part and the similarity between the inspection image of the inspection part and the record legend.

4. The method according to claim 3, characterized in that After the step of generating the inspection work order of the equipment, the method further includes: The review decision of the equipment is determined based on the health of the inspection part and the similarity between the inspection image of the inspection part and the record legend.

5. The method according to claim 4, characterized in that The step of determining the audit decision of the device based on the health of the inspection part and the similarity between the inspection image of the inspection part and the record legend includes: If the similarity is less than the second similarity threshold, the inspection work order of the equipment is sent to the management end for manual review; When the health of the inspection part is faulty, a repair work order for the equipment is generated; When the health of the inspected part is at risk of failure, a maintenance work order for the equipment is generated; When the health of the inspected parts is normal, the inspection work order of the equipment is reviewed and approved.

6. The method according to claim 1, characterized in that After all inspection parts of the equipment are successfully uploaded, after the step of generating the inspection work order of the equipment, the method further includes: Input the index parameters of the inspection parts into the decision model, wherein the historical inspection work orders of the equipment are classified to form audit decision data samples, and the decision model is constructed and trained based on the audit decision data samples; An audit decision for the device is output based on the decision model.

7. A device for generating inspection work orders, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the inspection work order generation method according to any one of claims 1 to 6.

8. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the inspection work order generation method according to any one of claims 1 to 6 are implemented.

Images