Patrol data processing method and device, computer device and storage medium

Abstract

The present application relates to the field of property management, and discloses a kind of inspection data processing method, device, computer equipment and storage medium, its method includes: obtaining inspection work order image;Identify several inspection type codes from inspection work order image;Inspection work order image is segmented into several unit images;Each unit image corresponds to an inspection type code;Obtain the work order identification model associated with the inspection type code;Identify unit image by work order identification model, obtain the equipment inspection data associated with the inspection type code.The present application realizes the digitization of inspection data with lower implementation cost, greatly improves the management efficiency of inspection data.

Description

Technical Field

[0001] This invention relates to the field of property management, and more particularly to a method, apparatus, computer equipment, and storage medium for processing inspection data. Background Technology

[0002] With social development and scientific progress, more and more public facilities and equipment are being deployed in various locations, such as industrial parks, office buildings, shopping malls, hotels, apartments, and residential communities, bringing greater convenience to people's lives. To ensure that these public facilities and equipment are in normal operating condition, project managers need to arrange for inspection personnel to conduct regular inspections of the facilities and equipment.

[0003] Currently, inspections are primarily conducted manually on-site, with results recorded using paper inspection work orders. However, this paper-based recording method requires project managers to review and organize each paper inspection work order submitted by inspectors, which is inefficient and prone to errors. Moreover, as paper inspection work orders accumulate, data traceability and unified archiving become increasingly difficult, hindering statistical analysis of inspection data and exacerbating the challenges of digitizing and informatizing inspection data, thus failing to meet the requirements of refined project management.

[0004] Another approach utilizes information technology, installing various smart sensors on facilities and equipment. These sensors automatically detect the operating parameters of the facilities and equipment, and then transmit the data to an inspection server in real time via the Internet of Things (IoT). However, this method is costly to implement and difficult to carry out on a large scale. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer equipment, and storage medium for processing inspection data to address the aforementioned technical problems, thereby reducing implementation costs and realizing the digitization of inspection data.

[0006] A method for processing inspection data, comprising:

[0007] Acquire inspection work order images;

[0008] Several inspection type codes are identified from the inspection work order images;

[0009] The inspection work order image is divided into several unit images; each unit image corresponds to an inspection type code.

[0010] Obtain the work order identification model associated with the inspection type code;

[0011] The unit image is identified by the work order recognition model to obtain equipment inspection data associated with the inspection type code.

[0012] An inspection data processing device, comprising:

[0013] The work order image acquisition module is used to acquire inspection work order images;

[0014] The inspection code identification module is used to identify several inspection type codes from the inspection work order image;

[0015] The image segmentation module is used to segment the inspection work order image into several unit images; each unit image corresponds to an inspection type code.

[0016] The module for obtaining the identification model is used to obtain the work order identification model associated with the inspection type code;

[0017] The identification module is used to identify the unit image through the work order identification model and obtain equipment inspection data associated with the inspection type code.

[0018] A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the processor implements the above-described inspection data processing method when executing the computer-readable instructions.

[0019] One or more readable storage media storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the inspection data processing method described above.

[0020] The aforementioned inspection data processing method, apparatus, computer equipment, and storage medium quickly identify the inspection type code on the inspection work order image, segment the inspection work order image into unit images, and then use a work order recognition model associated with the inspection type code to accurately identify the unit images, thus obtaining highly accurate equipment inspection data. Compared with existing technologies, this invention does not require the installation of intelligent sensors or robots on facilities and equipment, resulting in low modification costs; it does not require real-time data reporting via mobile phone during the inspection process, thus not conflicting with the project's existing mobile phone management system; at the same time, it improves the efficiency of digitizing equipment inspection data and avoids the inefficiency of manual processing. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of an application environment for the inspection data processing method in one embodiment of the present invention;

[0023] Figure 2 This is a flowchart illustrating an inspection data processing method according to one embodiment of the present invention;

[0024] Figure 3 This is a schematic diagram of the inspection data processing device in one embodiment of the present invention;

[0025] Figure 4 This is a schematic diagram of a computer device according to an embodiment of the present invention. Detailed Implementation

[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0027] The inspection data processing method provided in this embodiment can be applied to, for example, Figure 1 In this application environment, the client communicates with the server. Clients include, but are not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. The server can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0028] In one embodiment, such as Figure 2 As shown, a method for processing inspection data is provided, which can be applied to... Figure 1 Taking the server side as an example, the explanation includes the following steps S10-S50.

[0029] S10. Obtain the inspection work order image.

[0030] Understandably, the inspection work order image can be an image obtained by photographing or scanning a paper inspection work order. In one example, after the inspection is completed, the inspection personnel hand over the paper inspection work orders to the project administrator; the project administrator then photographs the paper inspection work orders to obtain the inspection work order image.

[0031] In some examples, the quality of inspection work order images can be inspected, intelligently identifying problems such as blurry images, insufficient lighting, distorted text, background interference, and missing pages, and prompting inspection personnel to re-capture and import the images.

[0032] S20. Identify several inspection type codes from the inspection work order image.

[0033] S30. Divide the inspection work order image into several unit images; each unit image corresponds to an inspection type code.

[0034] Understandably, different inspection work order templates are generated based on different inspection standards. Each inspection work order template has a corresponding inspection type code. The inspection type code is set in a fixed position on the work order, such as the upper left or upper right corner. The inspection type code can be a pattern that is easily recognized by computers, such as a QR code or barcode.

[0035] An inspection work order image may contain one or more work orders, each with a corresponding inspection type code. Therefore, the inspection work order image can be segmented into several unit images based on the inspection type code, with each unit image corresponding to one work order.

[0036] S40. Obtain the work order identification model associated with the inspection type code.

[0037] Understandably, to improve the accuracy of work order data recognition, each type of work order has a corresponding work order recognition model. The work order recognition model belongs to the OCR model (optical character recognition).

[0038] S50. Identify the unit image through the work order identification model to obtain equipment inspection data associated with the inspection type code.

[0039] Understandably, by using a work order recognition model adapted to the work order to recognize the unit image, equipment inspection data associated with the inspection type code can be obtained, which is the work order data. Equipment inspection data includes, but is not limited to, inspection cycle, inspection personnel shifts, inspection duration, and parameters of the inspected facilities and equipment (such as equipment quantity, installation location, operating status, start / stop status, alarms, current, voltage, power, temperature, etc.).

[0040] This embodiment quickly identifies the inspection type code on the inspection work order image, segments the inspection work order image into unit images, and then uses a work order recognition model associated with the inspection type code to accurately identify the unit images, thus obtaining highly accurate equipment inspection data. Compared with existing technologies, this embodiment does not require the installation of smart sensors or robots on facilities and equipment, resulting in low modification costs; it does not require real-time data reporting via mobile phone during the inspection process, thus not conflicting with the project's existing mobile phone management system; at the same time, it improves the efficiency of digitizing equipment inspection data and avoids the inefficiency of manual processing.

[0041] Optionally, the work order recognition model includes a pre-recognition model, a regular character recognition model, and an irregular character recognition model;

[0042] Step S50, namely, identifying the unit image through the work order recognition model to obtain equipment inspection data associated with the inspection type code, includes:

[0043] S501. The pre-recognition model is used to identify the unit image to obtain regular character image data and irregular character image data;

[0044] S502. Recognize the regular character image data using the regular character recognition model to obtain template text;

[0045] S503. Identify the irregular character image data using the irregular character recognition model to obtain handwritten text;

[0046] S504. Integrate the template text and the handwritten text to obtain integrated data;

[0047] S505. Verify the integrated data and generate the equipment inspection data.

[0048] In this embodiment, the work order recognition model includes three sub-models: a pre-recognition model, a regular character recognition model, and an irregular character recognition model. The pre-recognition model performs layout analysis on the unit image, identifies the characters within the unit image, and segments the unit image into regular character image data and irregular character image data. The regular character recognition model identifies the regular character image data and generates template text, which in this case is printed text. The irregular character recognition model identifies the irregular character image data and generates handwritten text, which in this case is the text recorded by the inspector on the paper work order during the inspection process.

[0049] In one example, the regular character recognition model associated with the inspection type code is first invoked. Then, resources such as CPU, GPU, storage, and network are allocated to start the regular character recognition model and begin scanning and detecting regular characters. By analyzing the text structure of the inspection work order in the regular character image data, extracting structured information, recognizing tables, recognizing characters, and recognizing special characters, the regular characters are obtained, which are the template text.

[0050] In another example, the irregular character recognition model associated with the inspection type code is first invoked. Then, resources such as CPU, GPU, storage, and network are allocated to start the irregular character recognition model and begin scanning and detecting irregular characters. During the recognition process, the irregular characters are first validated using AI algorithms based on the metadata information of the inspection work order template (including the position coordinates and numerical types of each character element). Then, the irregular characters are corrected into regular rectangles. Text structure analysis, structured information extraction, table recognition, character recognition, and special character recognition are then performed to obtain the irregular characters, which are essentially handwritten text.

[0051] The template text and handwritten text are integrated according to certain specifications to obtain integrated data. In one example, the integrated data can be JSON data.

[0052] After obtaining the integrated data, it can be verified according to certain verification rules. If the verification passes, the equipment inspection data is obtained.

[0053] This embodiment decomposes the identification process into three identification models, which can further reduce the complexity of the models; through further verification, the accuracy of equipment inspection data can be guaranteed.

[0054] Optionally, step S501, namely, identifying the unit image through the pre-recognition model to obtain regular character image data and irregular character image data, includes:

[0055] S5011. Perform layout analysis on the unit image to obtain the layout analysis results;

[0056] S5012. Based on the layout analysis results, perform element segmentation on each character of the unit image to obtain a character element image;

[0057] S5013. Perform type recognition on the character element image to obtain the character category;

[0058] S5014. Classify the character element images according to the character category to obtain the regular character image data and the irregular character image data.

[0059] Understandably, the inspection work orders in the unit image include two types of character information. One type is machine-printed tables, headers, text, and symbols. These characters have fixed shapes and relatively clear rules, making them suitable for inference and recognition using regression algorithm models. The other type is handwritten text and handwritten symbols by the inspectors. Different people have different writing habits and font shapes, which are irregularly shaped text characters. This type of text is suitable for inference and recognition using segmentation algorithm models.

[0060] Therefore, when using the pre-recognition model, the layout of the unit image is first analyzed to obtain the layout analysis results. The layout analysis results include the pre-recognized characters and their coordinates in the layout. Then, based on the layout analysis results, each character in the unit image is segmented to obtain character element images; next, the character element images are type-identified and classified to obtain regular character image data and irregular character image data.

[0061] In some cases, different pre-identification models can be used for different types of work orders in order to achieve more accurate identification.

[0062] This embodiment greatly reduces the complexity of the model by pre-identifying the unit images.

[0063] Optionally, before step S501, that is, before the process of identifying the unit image through the pre-recognition model to obtain regular character image data and irregular character image data, the following steps are included:

[0064] S50101. Obtain the work order template associated with the inspection type code;

[0065] S50102. Obtain metadata information from the work order template; the metadata information includes a first number of regular characters and a first page coordinate, and a second number of irregular characters and a second page coordinate;

[0066] S50103. Configure the pre-identification model according to the metadata information.

[0067] Understandably, work order templates are set up based on actual project needs. In real-world scenarios, different projects have different inspection standards. These standards are generated based on project business requirements and the type of facilities and equipment. For example, some projects focus only on key operating parameters of critical facilities and equipment, with inspections conducted weekly or monthly; while other projects require detailed management of all operating parameters for all facilities and equipment, with inspections conducted daily or even hourly. Furthermore, different types of facilities and equipment have different inspection parameters. For instance, the inspection parameters for access control systems, lighting systems, fire protection systems, and air conditioning systems differ significantly.

[0068] Therefore, inspection standards can consist of one or more inspection items. Inspection items include, but are not limited to, inspection cycle, inspection personnel shifts, inspection duration, and parameters of the inspected facilities and equipment (such as equipment quantity, installation location, operating status, start / stop status, alarms, current, voltage, power, temperature, etc.).

[0069] Different work order templates can be generated based on different inspection standards. The work order template includes various metadata information of this type of inspection work order file, such as the number of character elements in the inspection work order, the page position coordinates of the character elements, the numeric type, the numeric unit, the value range, the default value, etc.

[0070] Therefore, after obtaining the work order template, metadata information can be retrieved from the work order template. Here, the metadata information includes the first quantity and first page coordinates of regular characters (template text), and the second quantity and second page coordinates of irregular characters (handwritten text).

[0071] Metadata information can be written into the pre-identification model. When the pre-identification model is used to identify unit images, the layout of the entire inspection work order can be analyzed based on this metadata information.

[0072] This embodiment can achieve pre-recognition of unit images by constructing a pre-recognition model.

[0073] Optionally, step S504, namely, integrating the template text and the handwritten text to obtain integrated data, includes:

[0074] S5041. Obtain the work order template associated with the inspection type code;

[0075] S5042. Obtain metadata information from the work order template;

[0076] S5043. Create a data block template based on the metadata information;

[0077] S5044. Fill the handwritten text into the data block template according to the template text to generate the integrated data.

[0078] Understandably, the work order template contains pre-defined metadata information for the inspection work order. Therefore, a blank data block template, such as a JSON data block, can be generated based on this metadata information. In the blank JSON data block, one or more key-value pairs are composed of one or more key\value pairs, where the key (template text) corresponds one-to-one with the inspection item in the work order template, and the value is blank.

[0079] The corresponding handwritten text can be determined based on the position of the template text in the unit image, and then the handwritten text is filled into the key-value position (value) corresponding to the template text (key). After the data block template is filled, integrated data can be formed.

[0080] In one example, a blank JSON data block is represented as:

[0081] {

[0082] Inspection cycle:

[0083] Patrol personnel shifts:

[0084] Inspection duration:

[0085] Number of inspection equipment: [

[0087] {

[0088] Equipment type:

[0089] Device ID:

[0090] Equipment operating status:

[0091] Equipment current:

[0092] }

[0093] {

[0094] Equipment type:

[0095] Device ID:

[0096] Equipment alarm:

[0097] Equipment voltage:

[0098] Equipment power:

[0099] } ]

[0101] }

[0102] In this embodiment, a data block template is created using metadata information, and then handwritten text is filled into the data block template to form integrated data, which facilitates data verification.

[0103] Optionally, step S505, namely, verifying the integrated data and generating the equipment inspection data, includes:

[0104] S5051. Obtain the work order template associated with the inspection type code;

[0105] S5052. Obtain metadata information from the work order template;

[0106] S5053. Obtain the character verification rules associated with the metadata information;

[0107] S5054. Verify the integrated data according to the character verification rules;

[0108] S5055. The integrated data that has passed verification is determined as the equipment inspection data.

[0109] Understandably, one can first obtain the work order template associated with the inspection type code, then obtain the metadata information of that work order template, and finally obtain the character validation rules associated with the metadata information. The character validation rules set the numeric type, unit, range, and default value of each character element. If all character elements in the integrated data meet the validation rules, the integrated data passes the validation. At this point, the integrated data can be identified as equipment inspection data and then stored in the work order database.

[0110] If any character elements in the integrated data do not meet the validation rules, a validation error alert is issued to prevent erroneous data from being stored in the work order database. Simultaneously, the corresponding work order recognition model is retrained through data feedback, continuously iterating and optimizing the model to improve its recognition accuracy.

[0111] In one example, you can first verify the validity of the integrated data (JSON data block); then check whether the key and value of the JSON data block match one by one; and finally verify the integrity of the JSON data block.

[0112] This embodiment achieves automatic verification of integrated data. Moreover, since each work order template has dedicated character verification rules, the setting of character verification rules is simpler and the verification accuracy is high.

[0113] Optionally, after step S50, that is, after identifying the unit image through the work order recognition model and obtaining the equipment inspection data associated with the inspection type code, the method further includes:

[0114] S61. Send the equipment inspection data to the inspection work order database so as to store the equipment inspection data through the inspection work order database;

[0115] S62. Send an analysis request to the inspection work order database;

[0116] S63. Obtain the analysis results returned by the inspection work order database in response to the analysis request.

[0117] Understandably, after obtaining equipment inspection data, this data can be sent to the inspection work order database, which then stores the equipment inspection data. The inspection work order database stores equipment inspection data generated from previous inspections and provides interfaces for retrieving and statistically analyzing this data.

[0118] Therefore, users can send analysis requests to the inspection work order database through this interface. After receiving the analysis request, the inspection work order database performs statistical analysis on the equipment inspection data according to the analysis request, generates analysis results, and then returns the analysis results to the user.

[0119] The analysis results are presented flexibly in the form of pie charts, bar charts, trend charts, and tables, and support export and printing output methods, so that project managers can clearly know the work status and indicator ranking of each project, facility and equipment, and inspection personnel, realize the visualization of facility and equipment management, and thus improve project management efficiency.

[0120] In some examples, the analysis results include, but are not limited to:

[0121] 1. Statistically analyze the total number of inspection work orders, total inspection time, single inspection time, total number of problems found during inspections, average problem repair time, and year-on-year and month-on-month changes by year / month / week / day;

[0122] 2. Statistically analyze the total number of inspection work orders, total inspection time, single inspection time, total number of problems found during inspections, average problem repair time, and ranking of projects by project;

[0123] 3. Compile statistics on the total number of inspection work orders, total inspection time, single inspection time, total number of problems found during inspections, average time for problem repair, and ranking of inspection personnel according to the inspection personnel.

[0124] 4. Statistically record the total number of inspection work orders, the total number of faults, the equipment failure rate, and the repair time for each fault by equipment.

[0125] This embodiment stores equipment inspection data in an inspection work order database and outputs analysis results based on analysis requirements. This can avoid project managers manually reviewing and archiving paper inspection work orders, significantly improving the efficiency of facility and equipment inspection, saving system implementation costs, realizing visualization of facility and equipment management, and thus improving project management efficiency.

[0126] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0127] In one embodiment, an inspection data processing device is provided, which corresponds one-to-one with the inspection data processing method described in the above embodiments. For example... Figure 3 As shown, the inspection data processing device includes a work order image acquisition module 10, an inspection code recognition module 20, an image segmentation module 30, a recognition model acquisition module 40, and a recognition module 50. Detailed descriptions of each functional module are as follows:

[0128] The work order image acquisition module 10 is used to acquire inspection work order images;

[0129] The inspection code identification module 20 is used to identify several inspection type codes from the inspection work order image;

[0130] The image segmentation module 30 is used to segment the inspection work order image into several unit images; each unit image corresponds to an inspection type code.

[0131] The identification model acquisition module 40 is used to acquire the work order identification model associated with the inspection type code;

[0132] The identification module 50 is used to identify the unit image through the work order identification model and obtain equipment inspection data associated with the inspection type code.

[0133] Optionally, the work order recognition model includes a pre-recognition model, a regular character recognition model, and an irregular character recognition model;

[0134] The recognition module 50 includes:

[0135] A pre-recognition unit is used to recognize the unit image through the pre-recognition model to obtain regular character image data and irregular character image data;

[0136] The template text recognition unit is used to recognize the regular character image data through the regular character recognition model to obtain the template text;

[0137] A handwritten text recognition unit is used to recognize the irregular character image data through the irregular character recognition model to obtain handwritten text;

[0138] An integration unit is used to integrate the template text and the handwritten text to obtain integrated data.

[0139] The verification unit is used to verify the integrated data and generate the equipment inspection data.

[0140] Optionally, the pre-identification unit includes:

[0141] The layout analysis unit is used to perform layout analysis on the unit image and obtain the layout analysis results.

[0142] A segmentation unit is used to segment each character of the unit image according to the layout analysis results to obtain a character element image;

[0143] A classification unit is used to perform type recognition on the character element image to obtain the character category;

[0144] An image acquisition unit is used to classify the character element image according to the character category to obtain the regular character image data and the irregular character image data.

[0145] Optionally, the inspection data processing device further includes a pre-identification model generation module, which includes:

[0146] The work order template acquisition unit is used to acquire the work order template associated with the inspection type code;

[0147] A metadata information acquisition unit is used to acquire metadata information from the work order template; the metadata information includes a first number of regular characters and a first page coordinate, and a second number of irregular characters and a second page coordinate;

[0148] A pre-identification unit is configured to configure the pre-identification model based on the metadata information.

[0149] Optionally, the integration unit includes:

[0150] The work order template acquisition unit is used to acquire the work order template associated with the inspection type code;

[0151] A metadata information acquisition unit is used to acquire metadata information from the work order template;

[0152] A data block template creation unit is used to create a data block template based on the metadata information;

[0153] Generate an integrated data unit, which is used to fill the handwritten text into the data block template according to the template text, and generate the integrated data.

[0154] Optionally, the verification unit includes:

[0155] The work order template acquisition unit is used to acquire the work order template associated with the inspection type code;

[0156] A metadata information acquisition unit is used to acquire metadata information from the work order template;

[0157] A character verification rule acquisition unit is used to acquire character verification rules associated with the metadata information;

[0158] A verification unit is used to verify the integrated data according to the character verification rules;

[0159] A device inspection data unit is defined to identify the integrated data that has passed verification as the device inspection data.

[0160] Optionally, the inspection data processing device also includes:

[0161] The data block storage module is used to send the equipment inspection data to the inspection work order database so as to store the equipment inspection data through the inspection work order database.

[0162] The analysis request sending module is used to send analysis requests to the inspection work order database;

[0163] The module for obtaining analysis results is used to obtain the analysis results returned by the inspection work order database in response to the analysis request.

[0164] Specific limitations regarding the inspection data processing device can be found in the limitations of the inspection data processing method described above, and will not be repeated here. Each module in the aforementioned inspection data processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0165] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes a readable storage medium and internal memory. The readable storage medium stores an operating system, computer-readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The database stores data related to the inspection data processing method. The network interface communicates with external terminals via a network connection. When the computer-readable instructions are executed by the processor, an inspection data processing method is implemented. The readable storage medium provided in this embodiment includes both non-volatile and volatile readable storage media.

[0166] In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, wherein the processor performs the following steps when executing the computer-readable instructions:

[0167] Acquire inspection work order images;

[0168] Several inspection type codes are identified from the inspection work order images;

[0169] The inspection work order image is divided into several unit images; each unit image corresponds to an inspection type code.

[0170] Obtain the work order identification model associated with the inspection type code;

[0171] The unit image is identified by the work order recognition model to obtain equipment inspection data associated with the inspection type code.

[0172] In one embodiment, one or more computer-readable storage media storing computer-readable instructions are provided. The readable storage media provided in this embodiment include non-volatile readable storage media and volatile readable storage media. The readable storage media stores computer-readable instructions, which, when executed by one or more processors, perform the following steps:

[0173] Acquire inspection work order images;

[0174] Several inspection type codes are identified from the inspection work order images;

[0175] The inspection work order image is divided into several unit images; each unit image corresponds to an inspection type code.

[0176] Obtain the work order identification model associated with the inspection type code;

[0177] The unit image is identified by the work order recognition model to obtain equipment inspection data associated with the inspection type code.

[0178] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing related hardware with computer-readable instructions. These computer-readable instructions can be stored in a non-volatile readable storage medium or a volatile readable storage medium. When executed, these computer-readable instructions can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0179] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0180] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for processing inspection data, characterized in that, include: Acquire inspection work order images; Several inspection type codes are identified from the inspection work order images; The inspection work order image is divided into several unit images; Each of the aforementioned unit images corresponds to one of the aforementioned inspection type codes; Obtain the work order identification model associated with the inspection type code; The unit image is identified by the work order recognition model to obtain equipment inspection data associated with the inspection type code; the work order recognition model includes a pre-recognition model, a regular character recognition model and an irregular character recognition model. The step of identifying the unit image through the work order recognition model to obtain equipment inspection data associated with the inspection type code includes: The pre-recognition model is used to identify the unit image to obtain regular character image data and irregular character image data. The template text is obtained by recognizing the regular character image data using the regular character recognition model. The irregular character recognition model is used to identify the irregular character image data to obtain handwritten text; The template text and the handwritten text are integrated to obtain integrated data; The integrated data is verified to generate the equipment inspection data.

2. The inspection data processing method as described in claim 1, characterized in that, The step of identifying the unit image through the pre-recognition model to obtain regular character image data and irregular character image data includes: Perform layout analysis on the unit image to obtain layout analysis results; Based on the layout analysis results, the characters of the unit image are segmented to obtain character element images; The character element image is subjected to type recognition to obtain the character category; The character element images are classified according to the character category to obtain the regular character image data and the irregular character image data.

3. The inspection data processing method as described in claim 1, characterized in that, Before identifying the unit image through the pre-recognition model to obtain regular character image data and irregular character image data, the process includes: Obtain the work order template associated with the inspection type code; Metadata information is obtained from the work order template; the metadata information includes a first number of regular characters and a first page coordinate, and a second number of irregular characters and a second page coordinate. Configure the pre-identification model based on the metadata information.

4. The inspection data processing method as described in claim 1, characterized in that, The process of integrating the template text and the handwritten text to obtain integrated data includes: Obtain the work order template associated with the inspection type code; Obtain metadata information from the work order template; Create a data block template based on the metadata information; The handwritten text is filled into the data block template according to the template text to generate the integrated data.

5. The inspection data processing method as described in claim 1, characterized in that, The step of verifying the integrated data and generating the equipment inspection data includes: Obtain the work order template associated with the inspection type code; Obtain metadata information from the work order template; Obtain the character verification rules associated with the metadata information; The integrated data is validated according to the character validation rules. The integrated data that passes the verification is identified as the equipment inspection data.

6. The inspection data processing method as described in claim 1, characterized in that, After identifying the unit image through the work order recognition model and obtaining the equipment inspection data associated with the inspection type code, the method further includes: The equipment inspection data is sent to the inspection work order database so that the equipment inspection data can be stored in the inspection work order database; Send an analysis request to the inspection work order database; Obtain the analysis results returned by the inspection work order database in response to the analysis request.

7. A patrol inspection data processing device, characterized in that, include: The work order image acquisition module is used to acquire inspection work order images; The inspection code identification module is used to identify several inspection type codes from the inspection work order image; The image segmentation module is used to segment the inspection work order image into several unit images; each unit image corresponds to an inspection type code. The module for obtaining the identification model is used to obtain the work order identification model associated with the inspection type code; The identification module is used to identify the unit image through the work order identification model and obtain equipment inspection data associated with the inspection type code; The work order recognition model includes a pre-recognition model, a regular character recognition model, and an irregular character recognition model; The identification module includes: A pre-recognition unit is used to recognize the unit image through the pre-recognition model to obtain regular character image data and irregular character image data; The template text recognition unit is used to recognize the regular character image data through the regular character recognition model to obtain the template text; A handwritten text recognition unit is used to recognize the irregular character image data through the irregular character recognition model to obtain handwritten text; An integration unit is used to integrate the template text and the handwritten text to obtain integrated data. The verification unit is used to verify the integrated data and generate the equipment inspection data.

8. A computer device comprising a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, characterized in that, When the processor executes the computer-readable instructions, it implements the inspection data processing method as described in any one of claims 1 to 6.

9. One or more readable storage media storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to perform the inspection data processing method as described in any one of claims 1 to 6.

Images