CN113204993A - Work ticket log processing method and system for power plant - Google Patents
Work ticket log processing method and system for power plant Download PDFInfo
- Publication number
- CN113204993A CN113204993A CN202110326749.5A CN202110326749A CN113204993A CN 113204993 A CN113204993 A CN 113204993A CN 202110326749 A CN202110326749 A CN 202110326749A CN 113204993 A CN113204993 A CN 113204993A
- Authority
- CN
- China
- Prior art keywords
- image
- work ticket
- character recognition
- processing
- power plant
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 51
- 238000000034 method Methods 0.000 claims description 14
- 238000003702 image correction Methods 0.000 claims description 8
- 238000004380 ashing Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000009877 rendering Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 description 3
- 238000012550 audit Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of work ticket statistics, and discloses a work ticket log processing method for a power plant, which comprises the following steps: acquiring a target image, wherein the target image is an image of a work ticket in a work ticket filing system; performing character recognition on the target image to generate a character recognition result; and generating a statistical table according to the character recognition result. According to the invention, the character recognition is carried out on the acquired work ticket image, the extracted character information is classified and then automatically filled in the statistical table, manual statistics is not needed, and the work efficiency is improved. In addition, the invention also provides a work ticket log processing system of the power plant, which comprises an image acquisition module, an image processing module, a character recognition module and a data processing module, wherein the system can acquire the image of the work ticket and perform character recognition, and adds the extracted character information to the corresponding position of the statistical table, thereby being convenient and efficient.
Description
Technical Field
The invention relates to the technical field of work ticket statistics, in particular to a work ticket log processing method and system for a power plant.
Background
In the daily work of a power plant, work tickets need to be filled in, and the work tickets need to be counted to form a work ticket log, and the existing counting mode is manual counting and is tedious work. The work tickets are various in types, and mainly comprise the following 11 types: the heat engine comprises a work ticket of one kind, two kinds of work tickets of the heat engine, a work ticket of one kind in thermal control, a work ticket of two kinds in thermal control, a work ticket of one kind in electrical and electrical, a work ticket of one kind in fire, a work ticket of two kinds in fire, a work ticket for construction in a plant area, a work ticket of one kind in successive insurance and two kinds of work tickets of successive insurance.
Each work ticket typically contains the following information: the serial number, the work ticket number, the work content, the work approval time, the work leader, the work start time, the work licensor, the work ticket postponement, the work leader change, the work licensor, the work ticket break, the work licensor, the work ticket end time, and the work licensor.
The work ticket is stored in a cloud server of the power plant, and is locally stored in a main control room. When the work ticket data is stored locally, the staff generally adopts an Excel manual storage mode. During the peak period of maintenance, the maximum number of working tickets of the power plant can reach 100 sheets/day. The staff needs to spend 3 hours to carry out the manual statistics of the work ticket, and the data is easy to make mistakes.
The Chinese invention patent CN110046720A (published as 2019, 07, 23) discloses a work ticket management method based on electric power field overhaul safety control, which comprises the following steps: the method comprises the steps that a work ticket filing APP system is installed on a mobile terminal, a work ticket auditing system and a security project database are installed on a remote monitoring computer terminal, maintainers fill in work ticket text contents, confirm and operate one by one according to safety protection measure projects, pictures are taken of operation results, the pictures are uploaded to the remote monitoring computer terminal, remote operators audit the text and the pictures, the work ticket is confirmed to be issued if the audit meets safety operation requirements, the paper work ticket pictures can only be transmitted to the remote monitoring computer terminal to be watched, statistics cannot be carried out, and manual work is still needed during statistics.
Disclosure of Invention
The invention aims to provide a high-efficiency working order log processing method and system for a power plant.
In order to achieve the above object, the present invention provides a work ticket log processing method for a power plant, comprising the following steps:
s1, acquiring a target image, wherein the target image is an image of a work ticket in the work ticket filing system;
s2, performing character recognition on the target image to generate a character recognition result;
and S3, generating a statistical table according to the character recognition result.
Preferably, in step S2, the target image is preprocessed to output image data that meets a preset specification.
Preferably, in the preprocessing of the target image, gray processing, binarization processing, laplacian sharpening, symmetric mean filtering, fixed-coordinate cutting of the image, image expansion processing, image character thinning processing and antialiasing rendering are sequentially performed.
Preferably, when performing the gray scale processing on the target image, the target image is subjected to the ashing processing to obtain a gray scale image containing only one gray scale value, and the ashing formula is as follows:
f(x,y)＝0.30R(x,y)+0.59G(x,y)+0.11B(x,y)；
where f (x, y) represents the gray value of a pixel in a gray scale image, R represents a red component value, G represents a green component value, and B represents a blue component value.
Preferably, in step S2, when character recognition is performed, image correction processing is performed on the target image according to the recognized character, and feedback type repeated recognition is performed in the character recognition and image correction processes until the final character recognition result is obtained.
Preferably, in step S2, an image of a preset size is cut out near a character on the target image that is the same as the preset item character according to the character recognition result, and the target image is decomposed into a plurality of single item maps and saved.
Preferably, in step S1, a screenshot is taken of the work ticket filing system terminal to obtain the target image.
Preferably, in step S3, a statistical table is generated by filling the corresponding cells of the table with the characters at the positions of the characters in the image.
The invention also provides a work ticket log processing system of the power plant, which comprises:
the image acquisition module is used for acquiring an image of a work ticket in the work ticket filing system;
the character recognition module is used for carrying out character recognition on the image to generate a character recognition result;
and the data processing module is used for filling the characters at the positions into corresponding cells of the form according to the positions of the characters in the image to generate a statistical table.
Preferably, the image processing device further comprises an image processing module, configured to pre-process the image to output image data meeting a preset specification.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the character recognition is carried out on the acquired work ticket image, the extracted character information is classified and then automatically filled in the statistical table, manual statistics is not needed, and the work efficiency is improved.
Drawings
Fig. 1 is a flowchart of a method for processing a job ticket log according to an embodiment of the present invention.
Fig. 2 is a block diagram of a work ticket log processing system according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
As shown in fig. 1, a method for processing a work ticket log of a power plant according to a preferred embodiment of the present invention includes the following steps:
and S1, acquiring a target image, wherein the target image is an image of the work ticket in the work ticket filling system. In this embodiment, a screenshot is performed on the work ticket filing system terminal to obtain a target image. In the work filling system adopted in this embodiment, the columns of the work ticket include "plan and value long approval time", "issue, receipt, execution signature" and "work end", and the background colors of "plan and value long approval time", "issue, receipt, execution signature" and "work end" are different, in this embodiment, 3 target images are captured according to the background color in the image, and 3 images are named and stored according to "plan and value long approval time", "issue, receipt, execution signature" and "work end" respectively according to the background color.
And S2, performing character recognition on the target image to generate a character recognition result. And preprocessing the acquired target image to output image data meeting a preset specification, and then performing character recognition. In the embodiment, in the preprocessing of the target image, gray processing, binarization processing, laplacian sharpening, symmetric mean filtering, fixed-coordinate image cutting, image expansion processing, image character thinning processing and anti-aliasing rendering are sequentially performed.
Gray level processing: performing ashing treatment on the 3 target images to obtain a gray image only containing one gray value, wherein an ashing formula is as follows:
f(x,y)＝0.30R(x,y)+0.59G(x,y)+0.11B(x,y)；
where f (x, y) represents a gray scale value of a pixel in a gray scale image, R represents a red component value, G represents a green component value, and B represents a blue component value.
Image binarization: and determining a gray threshold value, and performing binarization processing on the gray image according to the gray threshold value to obtain a binary image. The gray value of a pixel point on the image is set to be 0 or 255, and the binarization of the image greatly reduces the data volume in the image, so that the outline of a target can be highlighted;
image laplacian sharpening: in image enhancement, smoothing is to eliminate noise interference in an image or reduce contrast, and conversely, sometimes to emphasize edges and details of an image, the image needs to be sharpened to improve the contrast, a laplacian sharpened image is related to the mutation degree of surrounding pixels of a certain pixel of the image to the pixel, that is, the laplacian sharpened image is based on the change degree of the pixel of the image, and the details of the image can be enhanced by using laplacian sharpening to find the edges of the image;
and (3) symmetrical mean filtering of the image: the core idea of the symmetric mean filtering is that in a local range, the difference between a relative region and different regions is obtained through comparison of a plurality of pairs of symmetric point pixels, then the mean calculation is carried out in the same determined region, so that the boundary can be kept more flexibly and the calculation is reduced, and a (2N +1) × (2N +1) template is arranged, so that 2N × 2N +1 symmetric points are provided, and the pixel mean of 2N × 2N +1 selection points replaces the original pixel value;
fixed-coordinate cutting image: determining the position coordinate corresponding to the image to be cut, and cutting the acquired image according to the position coordinate to obtain the image to be identified of the related key information;
and (3) image expansion processing: the picture is stretched and amplified in the horizontal direction, so that compression blurring of the Chinese characters is prevented, and OCR recognition efficiency is improved;
thinning the image characters: the Chinese character strokes are various and are easy to overlap, a Chinese character skeleton is extracted by using a thinning algorithm, the thinning is to remove some points from an original picture but still keep the original shape, the skeleton of the original picture is actually kept, and whether one point can be removed or not is judged by taking the condition that 8 adjacent points (eight connected) are taken as a criterion, wherein the specific criterion is as follows: the inner point cannot be deleted, the encouragement point cannot be deleted, and the straight line end point cannot be deleted, if P is a boundary point, after P is removed, if the connected component is not increased, P can be deleted;
anti-aliasing rendering is performed on the font: the fonts can be more clearly and comfortably seen.
The previous preparation work is made for character recognition. The character recognition of the present embodiment employs an OCR technique.
When character recognition is carried out, image correction processing is carried out on the target image according to the recognized characters, and feedback type repeated recognition is carried out in the character recognition and image correction processes until a final character recognition result is obtained. Firstly, in a preliminary character recognition feedback stage, performing secondary correction processing on an image to be recognized according to information fed back in the character recognition process by additionally arranging a target function; and secondly, in the stage of character recognition and understanding feedback, the image to be recognized is corrected again according to the information fed back in the process of checking the character recognition information by additionally arranging a target function.
After the character recognition is carried out, according to the character recognition result, an image with a preset size is intercepted near characters which are the same as the preset project characters on the target image, and the target image is decomposed into a plurality of single project images and stored. In the work ticket of the present embodiment, the column "plan and value long approval time" includes 2 items of "work ticket number" and "work content"; the column "sign-off, receipt, execution signature" includes 5 items of "work responsible person", "work licensor", "construction project responsible person", approval work time "and" start work time "; the column "work end" includes "work ticket end time" 1 item. Therefore, in the 3 target images, the single project image is cut out and stored near the character position corresponding to the project character on the corresponding target image, and the corresponding image can be checked conveniently when a worker checks the statistical table.
And S3, generating a statistical table according to the character recognition result. In this embodiment, the text at the position is filled into the corresponding cell of the table according to the text position in the image, so as to generate the statistical table. Firstly, keyword judgment is carried out according to the 'work ticket number', the work ticket type of the work content is determined, a corresponding statistical table is started according to the work ticket type, and extracted character information is filled into a cell corresponding to the statistical table according to the position of the identified character on the target image.
As shown in fig. 2, the present embodiment further provides a work ticket log processing system for a power plant, including:
the image acquisition module is used for acquiring an image of a work ticket in the work ticket filing system, and the embodiment is used for carrying out screenshot on the work ticket of the work ticket filing system terminal;
the image processing module of the embodiment comprises a gray processing unit, a binarization processing unit, a laplacian sharpening unit, a symmetric mean filtering unit, a fixed coordinate cutting image unit, an image expansion processing unit, an image character thinning processing unit and an anti-aliasing rendering unit; in addition, the image processing module of this embodiment further includes an image decomposition unit, configured to intercept an image of a preset size near a character on the image that is the same as a preset item character, and generate a plurality of single item maps, and in addition, the image processing module of this embodiment further includes an image correction unit, configured to receive feedback information of the character recognition module to perform image correction;
the character recognition module is used for performing character recognition on the image to generate a character recognition result, and the character recognition module is also used for generating recognition information and feeding the recognition information back to the image processing module;
and the data processing module is used for filling the characters at the positions into corresponding cells of the form according to the positions of the characters in the image to generate a statistical table.
In summary, the embodiment of the present invention provides a job ticket log processing for a power plant, which performs text recognition on an acquired job ticket image, classifies extracted text information, and automatically fills the classified text information into a statistical table, so that manual statistics is not required, and the work efficiency is improved. In addition, the invention also provides a work ticket log processing system of the power plant, which can acquire the image of the work ticket, perform character recognition on the image, classify the extracted character information and automatically fill the classified character information into a statistical table, and is efficient and convenient.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and substitutions can be made without departing from the technical principle of the present invention, and these modifications and substitutions should also be regarded as the protection scope of the present invention.
Claims (10)
1. A working ticket log processing method for a power plant is characterized by comprising the following steps:
s1, acquiring a target image, wherein the target image is an image of a work ticket in the work ticket filing system;
s2, performing character recognition on the target image to generate a character recognition result;
and S3, generating a statistical table according to the character recognition result.
2. The work ticket log processing method of a power plant according to claim 1, wherein in step S2, the target image is preprocessed to output image data that meets a preset specification.
3. The power plant work ticket log processing method as claimed in claim 2, wherein in the pre-processing of the target image, a gray processing, a binarization processing, a laplacian sharpening, a symmetric mean filtering, a fixed-coordinate cut image, an image expansion processing, an image text thinning processing, and an antialiasing rendering are sequentially performed.
4. The log processing method for the work tickets of the power plant according to claim 3, wherein when the target image is subjected to gray scale processing, the target image is subjected to ashing processing to obtain a gray scale image only containing one gray scale value, and the ashing formula is as follows:
f(x,y)＝0.30R(x,y)+0.59G(x,y)+0.11B(x,y)；
where f (x, y) represents the gray value of a pixel in a gray scale image, R represents a red component value, G represents a green component value, and B represents a blue component value.
5. The method for processing the work ticket log of the power plant as claimed in claim 2, wherein in the step S2, when the character recognition is performed, the image correction process is performed on the target image according to the recognized character, and the character recognition and the image correction process are repeated in a feedback manner until the final character recognition result is obtained.
6. The method for processing the work ticket log of the power plant as claimed in claim 1, wherein in step S2, an image with a predetermined size is cut out near a text on the target image that is the same as the predetermined project character based on the text recognition result, and the target image is divided into a plurality of single project maps and stored.
7. The work ticket log processing method for a power plant as claimed in claim 1, wherein in step S1, a screen shot is taken on the work ticket filing system terminal to obtain the target image.
8. The method for processing work ticket log of power plant as claimed in claim 1, wherein in step S3, the statistical table is generated by filling the text of the position into the corresponding cell of the table according to the text position in the image.
9. A work order log processing system for a power plant, comprising:
the image acquisition module is used for acquiring an image of a work ticket in the work ticket filing system;
the character recognition module is used for carrying out character recognition on the image to generate a character recognition result;
and the data processing module is used for filling the characters at the positions into corresponding cells of the form according to the positions of the characters in the image to generate a statistical table.
10. The work ticket log processing system of a power plant of claim 9, further comprising an image processing module for preprocessing the image to output image data that meets a preset specification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110326749.5A CN113204993A (en) | 2021-03-26 | 2021-03-26 | Work ticket log processing method and system for power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110326749.5A CN113204993A (en) | 2021-03-26 | 2021-03-26 | Work ticket log processing method and system for power plant |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113204993A true CN113204993A (en) | 2021-08-03 |
Family
ID=77025725
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110326749.5A Pending CN113204993A (en) | 2021-03-26 | 2021-03-26 | Work ticket log processing method and system for power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113204993A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113791860A (en) * | 2021-09-16 | 2021-12-14 | 金蝶软件（中国）有限公司 | Information conversion method, device and storage medium |
| CN113850569A (en) * | 2021-09-29 | 2021-12-28 | 广东电网有限责任公司东莞供电局 | Electronic work ticket management method |
-
2021
- 2021-03-26 CN CN202110326749.5A patent/CN113204993A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113791860A (en) * | 2021-09-16 | 2021-12-14 | 金蝶软件（中国）有限公司 | Information conversion method, device and storage medium |
| CN113791860B (en) * | 2021-09-16 | 2023-09-22 | 金蝶软件（中国）有限公司 | Information conversion method, device and storage medium |
| CN113850569A (en) * | 2021-09-29 | 2021-12-28 | 广东电网有限责任公司东莞供电局 | Electronic work ticket management method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113204993A (en) | Work ticket log processing method and system for power plant | |
| CN110569769A (en) | image recognition method and device, computer equipment and storage medium | |
| CN107085505B (en) | CDR file automatic processing and automatic comparison method and system | |
| CN113569863B (en) | Document checking method, system, electronic equipment and storage medium | |
| CN112966537B (en) | Form identification method and system based on two-dimensional code positioning | |
| CN111368511A (en) | PDF document analysis method and device | |
| CN108038441B (en) | System and method based on image recognition | |
| CN112949471A (en) | Domestic CPU-based electronic official document identification reproduction method and system | |
| CN102968638A (en) | Image sharpness judgment method based on keyword optical character recognition | |
| CN115457591A (en) | Identification method for topological relation of main wiring diagram of power grid station | |
| CN112182263A (en) | Image processing method and system for power generation equipment engineering drawing and processing equipment | |
| CN112906695A (en) | Form recognition method adapting to multi-class OCR recognition interface and related equipment | |
| CN111369133A (en) | Big data risk monitoring system | |
| CN109635729B (en) | Form identification method and terminal | |
| CN113743725B (en) | Ascending qualification detection method and system for ascending operators based on edge calculation | |
| CN113505780A (en) | Two-dimensional code-based intelligent detection maintenance method and equipment | |
| CN117079297A (en) | Relay protection fixed value checking method, system, equipment and medium | |
| CN117058157A (en) | CAD drawing cutting and labeling method | |
| CN111414889A (en) | Financial statement identification method and device based on character identification | |
| CN115620329A (en) | Stamp deviation intelligent identification method based on artificial intelligence | |
| CN115457581A (en) | Table extraction method and device and computer equipment | |
| CN115376139A (en) | Label collecting and analyzing system based on OCR high-speed image recognition | |
| CN106980604A (en) | Treaty content collates device | |
| CN114973274A (en) | Substation equipment ledger checking method and system | |
| CN114283442A (en) | Intelligent identification method and device for secondary wiring diagram and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |