CN115953799A

CN115953799A - Patrol data processing method and device, computer equipment and storage medium

Info

Publication number: CN115953799A
Application number: CN202211537499.0A
Authority: CN
Inventors: 余建学; 叶国栋; 冯丰; 侯轶; 陈明蛟
Original assignee: China Merchants Shekou Digital City Technology Co ltd
Current assignee: China Merchants Shekou Digital City Technology Co ltd
Priority date: 2022-12-02
Filing date: 2022-12-02
Publication date: 2023-04-11

Abstract

The invention relates to the field of property management, and discloses a method and a device for processing routing inspection data, computer equipment and a storage medium, wherein the method comprises the following steps: acquiring a patrol work order image; identifying a plurality of inspection type codes from the inspection work order image; dividing the inspection work order image into a plurality of unit images; each unit image corresponds to one inspection type code; acquiring a work order identification model associated with the patrol type code; and acquiring equipment inspection data associated with the inspection type code through the work order identification model identification unit image. The invention realizes the digitization of the inspection data with lower implementation cost, and greatly improves the management efficiency of the inspection data.

Description

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

Technical Field

The invention relates to the field of property management, in particular to a method and a device for processing routing inspection data, computer equipment and a storage medium.

Background

With the development and scientific progress of the society, more and more public facilities and equipment are put in various places, such as industrial parks, office buildings, shopping malls, hotel apartments, residential quarters and the like, so that more convenient life is brought to people. In order to ensure that the utility equipment is in a normal operating state, the project manager needs to arrange the polling personnel to perform equipment polling regularly.

At present, manual field inspection is mainly adopted, and a paper inspection work order is used for recording an inspection result. However, in this paper recording manner, the project manager needs to look up and sort the paper inspection worksheets reported by the inspection staff one by one, which is inefficient and prone to errors. Moreover, along with the accumulation of the paper routing inspection work order, the difficulty of data marking and unified filing is more and more high, the statistical analysis of routing inspection data is not facilitated, the difficulty of digitization and informatization of the routing inspection data is aggravated, and the fine management requirement of a project is not met.

And the other method adopts an informatization technology, various intelligent sensors are installed on the facility equipment, the intelligent sensors automatically detect the operating parameters of the facility equipment, and then the data is sent to the routing inspection server in real time through the Internet of things. However, this method is expensive to implement and difficult to implement on a large scale.

Disclosure of Invention

In view of the above, it is necessary to provide a method and an apparatus for processing routing inspection data, a computer device, and a storage medium, so as to reduce the implementation cost and implement digitization of the routing inspection data.

A routing inspection data processing method comprises the following steps:

acquiring a patrol work order image;

identifying a plurality of inspection type codes from the inspection work order image;

dividing the inspection work order image into a plurality of unit images; each unit image corresponds to one inspection type code;

acquiring a work order identification model associated with the patrol type code;

and identifying the unit image through the work order identification model to obtain equipment inspection data associated with the inspection type code.

An inspection data processing apparatus comprising:

the work order image acquisition module is used for acquiring an inspection work order image;

the inspection type identification module is used for identifying a plurality of inspection type codes from the inspection work order image;

the image segmentation module is used for segmenting the inspection work order image into a plurality of unit images; each unit image corresponds to one patrol type code;

the acquisition identification model module is used for acquiring a work order identification model associated with the patrol type code;

and the identification module is used for identifying the unit image through the work order identification model and obtaining the equipment inspection data associated with the inspection type code.

A computer device comprises a memory, a processor and computer readable instructions stored in the memory and executable on the processor, wherein the processor executes the computer readable instructions to realize the patrol data processing method.

One or more readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the patrol data processing method as described above.

According to the patrol data processing method, the device, the computer equipment and the storage medium, the patrol type code on the patrol inspection work order image is quickly identified, the patrol inspection work order image is divided into unit images, then the work order identification model related to the patrol inspection type code is used for accurately identifying the unit images, and the equipment patrol inspection data with high accuracy can be obtained. Compared with the prior art, the invention does not need to install an intelligent sensor or a robot on the facility equipment, and has low modification cost; the data does not need to be reported in real time through a mobile phone in the inspection process, and the inspection process does not conflict with the existing mobile phone management system of the project; meanwhile, the digitization efficiency of the equipment inspection data is improved, and the low efficiency of manual processing is avoided.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive labor.

FIG. 1 is a schematic diagram of an application environment of a method for processing inspection data according to an embodiment of the present invention;

FIG. 2 is a flow chart of a method for processing polling data according to an embodiment of the invention;

FIG. 3 is a schematic diagram of an exemplary inspection data processing apparatus;

FIG. 4 is a schematic diagram of a computer device according to an embodiment of the invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

The inspection data processing method provided by the embodiment can be applied to the application environment shown in fig. 1, wherein the client communicates with the server. The client includes, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of a plurality of servers.

In an embodiment, as shown in fig. 2, a method for processing polling data is provided, which is described by taking the method applied to the server in fig. 1 as an example, and includes the following steps S10 to S50.

And S10, acquiring an inspection work order image.

Understandably, the inspection work order image may be an image obtained by photographing or scanning a paper inspection work order. In one example, after the inspection is finished, the inspection personnel uniformly hand the paper inspection work order to a project manager; and (4) taking a picture of the polling paper work order by the project manager to obtain a polling work order image.

In some examples, quality detection can be performed on inspection work order images, problems of shooting blur, insufficient illumination, text bending, background interference, page loss and the like can be intelligently identified, and inspection personnel can be prompted to re-collect and import.

And S20, identifying a plurality of inspection type codes from the inspection work order image.

S30, dividing the inspection work order image into a plurality of unit images; and each unit image corresponds to one patrol type code.

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 routing inspection type code is arranged at a certain fixed position of the work order, such as the upper left corner or the upper right corner of the work order. The patrol type code can be a two-dimensional code, a bar code and other patterns which are easy to be recognized by a computer.

One or more work orders may be included in one inspection work order image, and each work order has a corresponding inspection type code. Therefore, the inspection work order image can be divided into a plurality of unit images based on the inspection type codes, and each unit image corresponds to one work order.

And S40, acquiring a work order identification model associated with the inspection type code.

Understandably, in order to improve the identification accuracy of the work order data, each work order is provided with a corresponding work order identification model. The work order recognition model belongs to an OCR (optical character recognition) model.

And S50, identifying the unit image through the work order identification model to obtain equipment inspection data associated with the inspection type code.

Understandably, the unit image is identified by using the work order identification model adapted to the work order, and the equipment inspection data associated with the inspection type code, namely, the work order data, can be obtained. The equipment inspection data includes, but is not limited to, inspection cycle, inspection personnel shift, inspection duration, and parameters of the inspection facility equipment (such as equipment number, installation position, operation state, start-stop state, alarm, current, voltage, power, temperature, etc.).

In the embodiment, the inspection type codes on the inspection work order images are quickly identified, the inspection work order images are divided into the unit images, then the work order identification model associated with the inspection type codes is used for accurately identifying the unit images, and the equipment inspection data with high accuracy can be obtained. Compared with the prior art, the method does not need to install an intelligent sensor or a robot on the facility equipment, and is low in modification cost; the data does not need to be reported in real time through a mobile phone in the inspection process, and the inspection process does not conflict with the existing mobile phone management system of the project; meanwhile, the digitization efficiency of the equipment inspection data is improved, and the low efficiency of manual processing is avoided.

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

step S50, namely, identifying the unit image through the work order identification model to obtain the equipment inspection data associated with the inspection type code, wherein the step S comprises the following steps:

s501, identifying the unit image through the pre-identification model to obtain regular character image data and irregular character image data;

s502, recognizing the regular character image data through the regular character recognition model to obtain template characters;

s503, recognizing the irregular character image data through the irregular character recognition model to obtain handwritten characters;

s504, performing data integration on the template characters and the handwritten characters to obtain integrated data;

and S505, verifying the integrated data to generate the equipment inspection data.

In this embodiment, the work order recognition model includes three submodels, namely a pre-recognition model, a regular character recognition model and an irregular character recognition model. The pre-recognition model is used for analyzing the layout of the unit image, recognizing characters in the unit image and dividing the unit image into regular character image data and irregular character image data. The regular character recognition model is used for recognizing the regular character image data to generate template characters, and the template characters are the print characters. The irregular character recognition model is used for recognizing irregular character image data and generating handwritten characters. The handwritten characters are the characters recorded on the paper work order by the patrol personnel in the patrol process.

In one example, a rule character recognition model associated with the patrol type code is called, then resources such as a CPU, a GPU, a memory and a network are applied, the rule character recognition model is started, and scanning detection of the rule character is started. Regular characters, namely template characters, are obtained through text structure analysis, structural information extraction, table identification, character identification and special character identification of the inspection work order in the regular character image data.

In another example, the irregular character recognition model related to the patrol type code is called, then resources such as a CPU, a GPU, a storage and a network are applied, the irregular character recognition model is started, and scanning detection of the irregular character is started. In the identification process, validity verification is performed on irregular characters based on an AI algorithm according to metadata information (including position coordinates and numerical types of each character element) of the inspection work order template, and then the irregular characters are corrected into regular rectangles. And continuing to perform text structure analysis, structured information extraction, table recognition, character recognition and special character recognition to obtain irregular characters, namely the handwritten characters.

And integrating the data of the template characters and the handwritten characters according to certain specifications to obtain integrated data. In an example, the syndicated data may be JSON data.

After the integrated data are obtained, the integrated data can be verified according to a certain verification rule, and if the verification is passed, the equipment inspection data are obtained.

In the embodiment, the recognition process is decomposed into three recognition models, so that the complexity of the models can be further reduced; through further verification, the accuracy of the equipment inspection data can be ensured.

Optionally, in step S501, the recognizing the unit image through the pre-recognition model to obtain regular character image data and irregular character image data includes:

s5011, performing layout analysis on the unit images to obtain a layout analysis result;

s5012, performing element segmentation on each character of the unit image according to the layout analysis result to obtain a character element image;

s5013, performing type recognition on the character element image to obtain a character type;

s5014, classifying the character element images according to the character types to obtain the regular character image data and the irregular character image data.

Understandably, the inspection work order in the unit image comprises two types of character information, one type is a table, a header, characters and symbols printed by a machine, the shape of the characters is fixed, the rules are clear, and the inspection work order is suitable for reasoning and identifying by adopting a regression algorithm model; the other type is handwritten text and handwritten symbols of inspection personnel, the writing habits and font shapes of different personnel are different, the text belongs to text characters with irregular shapes, and the text is suitable for reasoning and recognition by adopting a segmentation algorithm model.

Therefore, when the pre-recognition model is used for recognition, the layout analysis is performed on the unit image to obtain a layout analysis result. The layout analysis result includes the pre-recognized characters and coordinates of the characters in the layout. Then, element segmentation is carried out on each character of the unit image according to the layout analysis result to obtain a character element image; and then carrying out type identification and classification on the character element images to obtain regular character image data and irregular character image data.

In some cases, different pre-recognition models may be used for different types of work orders in order to achieve more accurate recognition.

According to the embodiment, the unit images are pre-identified, so that the complexity of the model is greatly reduced.

Optionally, before step S501, that is, before the unit image is identified by the pre-recognition model to obtain the regular character image data and the irregular character image data, the method includes:

s50101, acquiring a work order template related to the patrol type code;

s50102, acquiring metadata information from the work order template; the metadata information comprises a first number and first page coordinates of regular characters, and a second number and second page coordinates of irregular characters;

s50103, configuring the pre-recognition model according to the metadata information.

Understandably, the work order template is set according to the actual project requirement. In an actual scene, different project requirements have different inspection standards. Different routing inspection standards are generated based on project service requirements and facility equipment types. For example, some projects only focus on key operating parameters of key facility equipment, and the polling period is once a week or once a month; and some projects require that all operation parameters of all facility equipment are subjected to fine management, and the inspection cycle is once a day or even once an hour. In addition, different types of facility equipment have different polling item parameters. For example, the inspection parameters of access gate systems, lighting systems, fire-fighting systems and air-conditioning systems are very different.

Thus, the patrol criterion may consist of one or more patrol items. The polling items include, but are not limited to, polling periods, polling personnel shifts, detection time durations, and parameters of the polled facility equipment (such as equipment number, installation location, operating state, start-stop state, alarms, current, voltage, power, temperature, etc.).

Different work order templates can be generated based on different inspection standards. The work order template comprises various metadata information of the inspection work order file, such as the number of character elements of the inspection work order, page position coordinates of the character elements, numerical types, numerical units, value ranges, default values and the like.

Thus, after the work order template is obtained, metadata information may be obtained from the work order template. Here, the metadata information includes a first number and first page coordinates of regular characters (template letters), and a second number and second page coordinates of irregular characters (handwritten letters).

The metadata information may be written to the pre-recognition model. When the pre-recognition model is used to recognize the unit images, the entire page of the routing inspection work order may be subjected to layout analysis based on the metadata information.

According to the embodiment, the unit image can be pre-identified by constructing the pre-identification model.

Optionally, in step S504, the performing data integration on the template text and the handwritten text to obtain integrated data includes:

s5041, acquiring a work order template related to the patrol type code;

s5042, acquiring metadata information from the work order template;

s5043, creating a data block template according to the metadata information;

s5044, filling the handwritten characters into the data block template according to the template characters to generate the integrated data.

Understandably, the work order template is preset with metadata information of the patrol work order. Thus, a blank data block template, such as a JSON data block, may be generated based on the metadata information. In the blank, the JSON data block consists of one or more key value pairs (key/value), the key (template characters) corresponds to the polling item of the work order template one by one, and the value is blank.

The handwritten text corresponding to the position of the template text in the unit image may be determined according to the position of the template text in the unit image, and then the handwritten text is filled in the key value position (value) corresponding to the template text (key). After the data block template is filled, the integration data can be formed.

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

{

and (3) polling period:

the shift of the inspection personnel:

the inspection time is as follows:

the number of inspection equipment is as follows:

[

{

the device type:

device ID:

the running state of the equipment is as follows:

device current:

}

{

the device type:

device ID:

and (4) equipment alarming:

voltage of the device:

device power:

}

]

}

in the embodiment, the data block template is created through the metadata information, and then the handwritten characters are filled into the data block template to form the integrated data, so that the data can be conveniently checked.

Optionally, in step S505, the verifying the integration data to generate the device inspection data includes:

s5051, acquiring a work order template related to the patrol type code;

s5052, acquiring metadata information from the work order template;

s5053, acquiring a character check rule associated with the metadata information;

s5054, checking the integrated data according to the character checking rule;

s5055, determining the integrated data passing the verification as the equipment inspection data.

Understandably, the work order template associated with the patrol type code can be obtained first, then the metadata information of the work order template is obtained, and the character check rule associated with the metadata information is obtained. The character checking rule sets the numerical type, the numerical unit, the value range and the default value of each character element. If all the character elements in the integrated data meet the verification rule, the integrated data pass the verification, and the integrated data can be determined as equipment inspection data and then stored in the work order database.

And if the character elements in the integrated data do not meet the verification rule, sending a verification error prompt to prevent the error data from being stored in the work order database. Meanwhile, retraining the corresponding work order recognition model through data backflow, and continuously iterating and optimizing the work order recognition model so as to improve the model recognition accuracy.

In an example, the data validity of the consolidated data (JSON data block) may be checked first; checking whether the Key of the JSON data block is matched with the Value one by one; and finally, checking the data integrity of the JSON data block.

According to the embodiment, automatic verification of the integrated data is realized, and due to the fact that each work order template is provided with the special character verification rule, the character verification rule is simpler to set, and the verification accuracy rate is high.

Optionally, after step S50, that is, after the unit image is identified by the work order identification model and the device inspection data associated with the inspection type code is obtained, the method further includes:

s61, sending the equipment inspection data to an inspection work order database so as to store the equipment inspection data through the inspection work order database;

s62, sending an analysis request to the inspection work order database;

and S63, obtaining an analysis result which is returned by the inspection work order database and used for responding to the analysis request.

Understandably, after the equipment inspection data is obtained, the equipment inspection data can be sent to an inspection work order database, and the inspection work order database stores the equipment inspection data. The inspection work order database stores equipment inspection data generated by inspection in a past time and provides a retrieval and statistics interface of the equipment inspection data.

Thus, the user may send an analysis request to the routing inspection work order database through the interface. And after receiving the analysis request, the routing inspection work order database performs statistical analysis on the equipment routing inspection data according to the analysis request to form an analysis result, and then returns the analysis result to the user.

The analysis result is flexibly displayed in the forms of a pie chart, a bar chart, a trend chart, a table and the like, and output modes such as exporting, printing and the like are supported, so that a project manager can clearly know the working state and index ranking of each project, facility equipment and inspection personnel, management visualization of the facility equipment is realized, and the project management efficiency is improved.

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

1. counting the total number of the routing inspection work orders, the total routing inspection time, the single routing inspection time, the total number of the routing inspection found problems, the problem repair average time and the variation conditions of the same ratio and the ring ratio according to the year/month/week/day;

2. counting the total number of routing inspection work orders, the total routing inspection time length, the single routing inspection time length, the total number of routing inspection found problems, the problem repair average time length and the ranking among the items according to the items;

3. counting the total number of the inspection work orders, the total inspection time length, the single inspection time length, the total number of the inspection found problems, the average problem repair time length and the ranking among the inspection personnel according to the inspection personnel;

4. and counting the total number of the routing inspection work orders, the total failure times, the failure rate of the equipment and the single failure repairing time according to the equipment.

Data are patrolled and examined through patrolling and examining work order database storage device to this embodiment, based on analysis demand output analysis result, can avoid the manual work of project manager to review, save and file the paper and patrol and examine the work order, show the efficiency that promotes the facility equipment and patrol and examine, practice thrift the system implementation cost simultaneously, realize that the management of facility equipment is visual to improve project management efficiency.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

In an embodiment, an inspection data processing device is provided, and the inspection data processing device corresponds to the inspection data processing method in the embodiment one to one. As shown in fig. 3, the inspection data processing device includes an acquisition work order image module 10, an identification inspection coding module 20, a segmentation image module 30, an acquisition identification model module 40 and an identification module 50. The detailed description of each functional module is as follows:

the acquiring work order image module 10 is used for acquiring an inspection work order image;

the inspection identifying coding module 20 is used for identifying a plurality of inspection type codes from the inspection work order image;

a segmentation image module 30, configured to segment the inspection work order image into a plurality of unit images; each unit image corresponds to one inspection type code;

an acquiring identification model module 40, configured to acquire a work order identification model associated with the inspection type code;

and the identification module 50 is used for identifying the unit image through the work order identification model and obtaining the equipment inspection data associated with the inspection type code.

the identification module 50 includes:

the pre-recognition unit is used for recognizing the unit image through the pre-recognition model to obtain regular character image data and irregular character image data;

the template character recognition unit is used for recognizing the regular character image data through the regular character recognition model to obtain template characters;

the handwritten character recognition unit is used for recognizing the irregular character image data through the irregular character recognition model to obtain handwritten characters;

the integration unit is used for performing data integration on the template characters and the handwritten characters to obtain integrated data;

and the checking unit is used for checking the integrated data to generate the equipment inspection data.

Optionally, the pre-recognition unit comprises:

the layout analysis unit is used for carrying out layout analysis on the unit images to obtain a layout analysis result;

the segmentation unit is used for carrying out element segmentation on each character of the unit image according to the layout analysis result to obtain a character element image;

the classification unit is used for carrying out type recognition on the character element image to obtain a character category;

and the image obtaining unit is used for classifying the character element images according to the character categories to obtain the regular character image data and the irregular character image data.

Optionally, the inspection data processing apparatus further includes a pre-recognition model generation module, and the pre-recognition model generation module includes:

the work order template obtaining unit is used for obtaining a work order template related to the inspection type code;

the acquiring metadata information unit is used for acquiring metadata information from the work order template; the metadata information comprises a first number and first page coordinates of regular characters, and a second number and second page coordinates of irregular characters;

and the configuration pre-recognition unit is used for configuring the pre-recognition model according to the metadata information.

Optionally, the integration unit comprises:

the acquisition metadata information unit is used for acquiring metadata information from the work order template;

a data block template creating unit for creating a data block template according to the metadata information;

and the integrated data generating unit is used for filling the handwritten characters into the data block template according to the template characters to generate the integrated data.

Optionally, the verification unit includes:

the character verification rule obtaining unit is used for obtaining a character verification rule related to the metadata information;

the verification unit is used for verifying the integrated data according to the character verification rule;

and the equipment inspection data determining unit is used for determining the integrated data passing the verification as the equipment inspection data.

Optionally, the inspection data processing apparatus further includes:

the storage data block module is used for sending the equipment inspection data to an inspection work order database so as to store the equipment inspection data through the inspection work order database;

the analysis request sending module is used for sending an analysis request to the inspection work order database;

and the analysis result acquisition module is used for acquiring an analysis result which is returned by the inspection work order database and used for responding to the analysis request.

For specific limitations of the inspection data processing device, reference may be made to the above limitations of the inspection data processing method, which are not described herein again. All or part of each module in the routing inspection data processing device can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a server, and the internal structure thereof may be as shown in fig. 4. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a readable storage medium and an internal memory. The readable storage medium stores an operating system, computer readable instructions, and a database. The internal memory provides an environment for the operating system and execution of computer-readable instructions in the readable storage medium. The database of the computer equipment is used for storing data related to the routing inspection data processing method. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer readable instructions, when executed by the processor, implement a method of routing inspection data processing. The readable storage media provided by the present embodiments include non-volatile readable storage media and volatile readable storage media.

In one embodiment, a computer device is provided, comprising a memory, a processor, and computer readable instructions stored on the memory and executable on the processor, the processor when executing the computer readable instructions implementing the steps of:

acquiring a patrol work order image;

In one embodiment, one or more computer-readable storage media storing computer-readable instructions are provided, the readable storage media provided by the embodiments including non-volatile readable storage media and volatile readable storage media. The readable storage medium has stored thereon computer readable instructions which, when executed by one or more processors, perform the steps of:

acquiring a patrol work order image;

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware related to computer readable instructions, which may be stored in a non-volatile readable storage medium or a volatile readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can 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), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

It should be clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional units and modules is only used for illustration, and in practical applications, the above function distribution may be performed by different functional units and modules as needed, that is, the internal structure of the apparatus may be divided into different functional units or modules to perform all or part of the above described functions.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.

Claims

1. A routing inspection data processing method is characterized by comprising the following steps:

acquiring a patrol work order image;

2. The inspection data processing method according to claim 1, wherein the work order recognition model includes a pre-recognition model, a regular character recognition model and an irregular character recognition model;

the unit image is identified through the work order identification model, and equipment inspection data associated with the inspection type code is obtained, wherein the equipment inspection data comprises the following steps:

identifying the unit image through the pre-identification model to obtain regular character image data and irregular character image data;

recognizing the regular character image data through the regular character recognition model to obtain template characters;

recognizing the irregular character image data through the irregular character recognition model to obtain handwritten characters;

performing data integration on the template characters and the handwritten characters to obtain integrated data;

and verifying the integrated data to generate the equipment inspection data.

3. The inspection data processing method according to claim 2, wherein the identifying the unit images through the pre-recognition model to obtain regular character image data and irregular character image data includes:

performing layout analysis on the unit images to obtain a layout analysis result;

performing element segmentation on each character of the unit image according to the layout analysis result to obtain a character element image;

performing type recognition on the character element image to obtain a character type;

and classifying the character element images according to the character categories to obtain the regular character image data and the irregular character image data.

4. The inspection data processing method according to claim 2, wherein before identifying the unit image through the pre-recognition model to obtain regular character image data and irregular character image data, the method includes:

acquiring a work order template associated with the patrol type code;

acquiring metadata information from the work order template; the metadata information comprises a first number of regular characters and first page coordinates, and a second number of irregular characters and second page coordinates;

and configuring the pre-recognition model according to the metadata information.

5. The inspection data processing method according to claim 2, wherein the data integration of the template characters and the handwritten characters to obtain integrated data includes:

acquiring a work order template associated with the patrol type code;

acquiring metadata information from the work order template;

creating a data block template according to the metadata information;

and filling the handwritten characters into the data block template according to the template characters to generate the integrated data.

6. The inspection data processing method according to claim 2, wherein the verifying the integration data to generate the equipment inspection data includes:

acquiring a work order template associated with the patrol type code;

acquiring metadata information from the work order template;

acquiring a character check rule associated with the metadata information;

checking the integrated data according to the character checking rule;

and determining the integration data passing the verification as the equipment inspection data.

7. The inspection data processing method according to claim 1, wherein after identifying the unit image via the work order identification model and obtaining the equipment inspection data associated with the inspection type code, the method further comprises:

sending the equipment inspection data to an inspection work order database so as to store the equipment inspection data through the inspection work order database;

sending an analysis request to the inspection work order database;

and obtaining an analysis result returned by the inspection work order database and used for responding to the analysis request.

8. An inspection data processing apparatus, comprising:

the image segmentation module is used for segmenting the inspection work order image into a plurality of unit images; each unit image corresponds to one inspection type code;

9. A computer device comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, wherein the processor when executing the computer readable instructions implements the inspection data processing method of any one of claims 1 to 7.

10. One or more readable storage media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to perform the inspection data processing method of any one of claims 1 to 7.