CN111506348A - Handwriting board correction multithreading parallel processing method, device, equipment and medium - Google Patents
Handwriting board correction multithreading parallel processing method, device, equipment and medium Download PDFInfo
- Publication number
- CN111506348A CN111506348A CN202010323599.8A CN202010323599A CN111506348A CN 111506348 A CN111506348 A CN 111506348A CN 202010323599 A CN202010323599 A CN 202010323599A CN 111506348 A CN111506348 A CN 111506348A
- Authority
- CN
- China
- Prior art keywords
- handwriting
- calculation
- picture
- corrected
- calculation range
- 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
- 238000012937 correction Methods 0.000 title claims abstract description 65
- 238000003672 processing method Methods 0.000 title claims abstract description 22
- 238000004364 calculation method Methods 0.000 claims abstract description 210
- 238000012545 processing Methods 0.000 claims abstract description 28
- 238000010586 diagram Methods 0.000 claims description 52
- 238000004590 computer program Methods 0.000 claims description 13
- 238000000034 method Methods 0.000 claims description 11
- 238000012163 sequencing technique Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 abstract description 4
- 238000012360 testing method Methods 0.000 description 17
- 230000006870 function Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000009432 framing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000005674 electromagnetic induction Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
- G06F9/38—Concurrent instruction execution, e.g. pipeline or look ahead
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5066—Algorithms for mapping a plurality of inter-dependent sub-tasks onto a plurality of physical CPUs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- G06V30/10—Character recognition
- G06V30/32—Digital ink
- G06V30/36—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention relates to the technical field of handwriting boards, in particular to a handwriting board correction multithreading parallel processing method, a handwriting board correction multithreading parallel processing device, handwriting board correction multithreading parallel processing equipment and a handwriting board correction multithreading parallel processing medium, which comprise the following steps: s10: if the handwriting picture to be corrected is obtained, obtaining a corresponding reference picture according to the handwriting picture to be corrected; s20: setting a circulating calculation range according to the handwriting picture to be corrected and the reference picture; s30: acquiring the number of CPU core threads, and calculating the calculation range of unit threads according to the number of CPU core threads and the circular calculation range; s40: and distributing each unit thread calculation range to the corresponding CPU core according to the number of the CPU core threads to perform handwriting board correction calculation. The invention has the effect of improving the efficiency of correcting and calculating the handwriting recognized by the handwriting board.
Description
Technical Field
The invention relates to the technical field of handwriting boards, in particular to a handwriting board correction multithreading parallel processing method, device, equipment and medium.
Background
At present, the electromagnetic pen often uses with the handwriting pad cooperation, covers paper on the handwriting pad, writes the content on the paper with the electromagnetic pen, and according to the electromagnetic induction principle, the handwriting that the handwriting pad was written with the electromagnetic pen is recorded one by one and is preserved, and the electronic handwriting of preserving is unanimous with the handwriting of writing on the paper, and the handwriting pad supplies student or teacher to look up on transmitting the electronic handwriting of record to the computer.
The Chinese utility model patent with publication number CN207489093U discloses an intelligent handwriting board system, which comprises an intelligent handwriting board, wherein the intelligent handwriting board comprises a handwriting board body and a paper clamping device; the paper clamping device is arranged right above the handwriting board body. When the handwriting board is used, the written paper is placed on the handwriting board body, and the paper is effectively prevented from falling off through the paper clamping device. When a user clamps paper on the handwriting board body through the clamping device, the paper is usually placed at will, and the paper is not placed on the handwriting board correspondingly, for example, the paper is left, right or left, so that written answers cannot be matched with questions directly, and therefore the positions of the written answers need to be corrected.
The above prior art solutions have the following drawbacks: when a picture formed by written answers recognized by the handwriting board is corrected, the picture needs to be continuously compared with a preset reference picture for calculation, the overlapping rate of the picture and the reference picture is calculated, the interval of each calculation is in a pixel unit, the resolution of the existing handwriting board is high, the calculated amount of the calculated overlapping rate is large, the correction efficiency is affected, and therefore space is further improved.
Disclosure of Invention
The invention aims to provide a handwriting board correction multithreading parallel processing method, a handwriting board correction multithreading parallel processing device, handwriting board correction multithreading parallel processing equipment and a handwriting board correction multithreading parallel processing medium, wherein the efficiency of correction calculation of handwriting recognized by a handwriting board is improved.
The above object of the present invention is achieved by the following technical solutions:
a handwriting board correction multithreading parallel processing method comprises the following steps:
s10: if the handwriting picture to be corrected is obtained, obtaining a corresponding reference picture according to the handwriting picture to be corrected;
s20: setting a circulating calculation range according to the handwriting picture to be corrected and the reference picture;
s30: acquiring the number of CPU core threads, and calculating the calculation range of unit threads according to the number of CPU core threads and the circular calculation range;
s40: and distributing each unit thread calculation range to the corresponding CPU core according to the number of the CPU core threads to perform handwriting board correction calculation.
By adopting the technical scheme, when the handwriting is corrected, the corresponding reference picture is obtained according to the handwriting picture to be corrected, and the circular calculation range is calculated when the handwriting picture to be corrected is corrected, so that the total calculation amount can be determined when the handwriting board is corrected; meanwhile, the cycle calculation range is divided into corresponding unit thread calculation ranges according to the obtained CPU core thread number, the advantage of multi-core and multi-thread parallel processing of the CPU can be utilized, different parts in the cycle are distributed to each CPU core for calculation according to the CPU core number during calculation, and therefore calculation efficiency is greatly improved.
The present invention in a preferred example may be further configured to: step S10 includes:
s11: if the to-be-completed operation set is obtained, obtaining to-be-completed operation identifications and to-be-completed exercise templates corresponding to the to-be-completed operation identifications from the to-be-completed operation set;
s12: if the actual handwriting is obtained, taking the picture where the actual handwriting is located as the handwriting picture to be corrected, and obtaining the operation identification to be matched from the handwriting picture to be corrected;
s13: and acquiring the corresponding reference picture from the to-be-matched exercise template according to the to-be-matched operation identifier.
By adopting the technical scheme, when the to-be-completed exercise set is obtained, the answering area is defined in the to-be-completed exercise template in the to-be-completed exercise set, the to-be-matched exercise mark is obtained in the recognized actual answering handwriting, the to-be-completed exercise template corresponding to the actual answering handwriting can be obtained according to the to-be-matched exercise mark, and therefore the reference picture can be obtained according to the to-be-completed exercise template.
The present invention in a preferred example may be further configured to: step S20 includes:
s21: acquiring a handwriting block diagram from the handwriting picture to be corrected, acquiring a reference block diagram corresponding to the handwriting block diagram from the reference picture, and respectively acquiring handwriting block diagram position information and reference block diagram position information of the handwriting block diagram and the reference block diagram;
s22: and calculating the relative offset of the handwriting block diagram position information and the reference block diagram position information, and taking the relative offset as the circular calculation range.
By adopting the technical scheme, the circular calculation range is calculated by acquiring the handwriting block diagram and the corresponding reference block diagram and according to the relative offset between the position information of the handwriting block diagram corresponding to the reference block diagram and the position information of the reference block diagram, so that the correction calculation of the handwriting board can be more reasonable.
The present invention in a preferred example may be further configured to: step S30 includes:
s31: acquiring a horizontal circulation calculation range and a vertical circulation calculation range in the circulation calculation range;
s32: and selecting the horizontal circulation calculation range or the vertical circulation calculation range, and calculating the unit thread calculation range according to the number of the CPU core threads.
By adopting the technical scheme, the horizontal cycle calculation range or the vertical cycle calculation range is selected as the unit thread calculation range obtained by splitting, so that the calculation content can not be repeated when the CPU core thread number is calculated in the unit thread calculation range respectively, and the calculation efficiency is ensured.
The present invention in a preferred example may be further configured to: step S40 includes:
s41: acquiring a preset circulation interval and a circulation initial position of each unit thread calculation range, and circularly calculating an intersection ratio in each unit thread calculation range from the corresponding circulation initial position according to the circulation interval;
s42: acquiring the intersection ratio and the corresponding candidate offset obtained by each cycle calculation, and sorting according to the sequence of the intersection ratio from large to small to obtain a sorting result;
s43: and acquiring the candidate offset corresponding to the intersection ratio with the first ranking in the sequencing result, and taking the candidate offset as the calculation result of the correction calculation of the handwriting board.
By adopting the technical scheme, the accuracy of balance correction and the calculated amount during calculation of the actual offset can be based on the resolution of the handwriting board by setting the circulation interval, so that the optimal correction accuracy can be achieved under the appropriate calculated amount; meanwhile, the candidate offset with the maximum intersection ratio is used as the actual offset, so that the best correction effect on the handwriting picture to be corrected can be achieved.
The second aim of the invention is realized by the following technical scheme:
a handwriting pad correction multithreaded parallel processing apparatus, comprising:
the image acquisition module is used for acquiring a corresponding reference image according to the handwriting image to be corrected if the handwriting image to be corrected is acquired;
the range calculation module is used for setting a circular calculation range according to the handwriting picture to be corrected and the reference picture;
the calculation amount distribution module is used for acquiring the number of CPU core threads and calculating the calculation range of the unit thread according to the number of the CPU core threads and the circulation calculation range;
and the calculation module is used for distributing each unit thread calculation range to the corresponding CPU core according to the number of the CPU core threads to carry out correction calculation on the handwriting board.
By adopting the technical scheme, when the handwriting is corrected, the corresponding reference picture is obtained according to the handwriting picture to be corrected, and the circular calculation range is calculated when the handwriting picture to be corrected is corrected, so that the total calculation amount can be determined when the handwriting board is corrected; meanwhile, the cycle calculation range is divided into corresponding unit thread calculation ranges according to the obtained CPU core thread number, the advantage of multi-core and multi-thread parallel processing of the CPU can be utilized, different parts in the cycle are distributed to each CPU core for calculation according to the CPU core number during calculation, and therefore calculation efficiency is greatly improved.
The third object of the invention is realized by the following technical scheme:
a computer device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, said processor implementing the steps of the above described handwriting pad correction multi-threaded parallel processing method when executing said computer program.
The fourth object of the invention is realized by the following technical scheme:
a computer-readable storage medium, storing a computer program which, when executed by a processor, implements the steps of the above-described handwriting pad correction multithread parallel processing method.
In summary, the invention includes at least one of the following beneficial technical effects:
1. when the handwriting is corrected, the corresponding reference picture is obtained according to the handwriting picture to be corrected, and the circular calculation range is calculated when the handwriting picture to be corrected is corrected, so that the total calculation amount can be determined when the handwriting board is corrected;
2. according to the obtained number of the CPU core threads, the cycle calculation range is decomposed into the corresponding unit thread calculation range, the advantages of multi-core and multi-thread parallel processing of the CPU can be utilized, different parts in the cycle are distributed to each CPU core for calculation according to the number of the CPU cores during calculation, and therefore the calculation efficiency is greatly improved;
3. by selecting the horizontal cycle calculation range or the vertical cycle calculation range as the unit thread calculation range obtained by splitting, the calculation contents can not be repeated when the calculation is respectively carried out in the unit thread calculation range according to the number of the CPU core threads, and the calculation efficiency is ensured.
Drawings
FIG. 1 is a flow chart of a multi-thread parallel processing method for handwriting board correction according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating an implementation of step S10 in the multi-thread parallel processing method for handwriting board correction according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating an implementation of step S20 in the multi-thread parallel processing method for handwriting board correction according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating an implementation of step S30 in the multi-thread parallel processing method for handwriting board correction according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating an implementation of step S40 in the multi-thread parallel processing method for handwriting pad correction according to an embodiment of the present invention;
FIG. 6 is a functional block diagram of a handwriting pad correction multithreaded parallel processing device in an embodiment of the invention;
FIG. 7 is a schematic diagram of a computer device according to an embodiment of the invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The first embodiment is as follows:
in an embodiment, as shown in fig. 1, the present invention discloses a handwriting board correction multithread parallel processing method, which specifically includes the following steps:
s10: and if the handwriting picture to be corrected is obtained, obtaining a corresponding reference picture according to the handwriting picture to be corrected.
In this embodiment, the handwriting picture to be corrected is a picture formed by handwriting which is acquired by using an electromagnetic handwriting board and answered by students according to a received to-be-finished homework set. The reference picture is used for comparing with the handwriting picture to be corrected.
Specifically, after the handwriting written by the user is acquired through the electromagnetic handwriting board, namely, after the student fixes and clamps the corresponding paper test paper with the electromagnetic handwriting board according to the received homework, the electromagnetic pen is used for answering on the paper test paper, the corresponding page number is input during answering, a button for page turning function is triggered on the electromagnetic handwriting board or the personal terminal during page turning, the electromagnetic handwriting board acquires the answered handwriting of the current page of the student in real time, and the picture where the handwriting of the page is located is used as the picture of the handwriting to be corrected.
Further, according to the specific page number of the test paper which is specifically written by the student, the test paper template is obtained from a preset examination question library, and the page which is the same as the specific page number of the test paper which is being written by the student is obtained from the test paper template and used as a reference picture.
S20: and setting a circulating calculation range according to the handwriting picture to be corrected and the reference picture.
In this embodiment, the loop calculation range refers to the total calculation amount of the amount of position adjustment required for calculating the handwriting picture to be corrected.
Specifically, a positioning point is selected at the content in the handwriting picture to be corrected and marked by using a first coordinate, and meanwhile, a reference point corresponding to the positioning point is selected at the position of the same content and marked by using a second coordinate.
Further, the loop calculation range is set according to an abscissa distance and an ordinate distance between the first coordinate and the second coordinate.
S30: and acquiring the number of the CPU core threads, and calculating the calculation range of the unit threads according to the number of the CPU core threads and the circulation calculation range.
In the present embodiment, the CPU core thread number refers to the number of cores of the CPU in the device. The unit thread calculation range refers to a calculation amount by which each CPU core calculates the amount of the position adjustment.
Specifically, the number of cores of the CPU of the personal mobile terminal is acquired from the device parameter information of the mobile terminal as the number of threads of the CPU core by the device parameter information, for example, the device information of the personal mobile terminal such as a mobile phone or a tablet of a student.
Further, the calculation range of the unit thread is obtained by dividing the calculation range of the loop by the number of the core threads of the CPU.
Preferably, if the division is not complete, the loop calculation range may be divided by the number of CPU core threads to obtain a result, the result is rounded down, the number rounded down is used as the unit thread calculation range, and the obtained remainder is added to one of the unit thread calculation ranges.
S40: and distributing the calculation range of each unit thread to the corresponding CPU core according to the number of the CPU core threads to perform correction calculation on the handwriting board.
In this embodiment, the handwriting board correction calculation refers to calculating the amount of the position of the handwriting picture to be corrected that needs to be adjusted actually.
Specifically, according to the unit thread calculation range, a range in which each CPU core is responsible for calculation within the loop calculation range is obtained, that is, although the calculation ranges of each unit thread have the same numerical value, the actual calculation ranges do not overlap with each other.
Furthermore, the unit thread calculation range is distributed to the corresponding CPU cores one by one according to the number of the CPU core threads, so that in the CPU of the personal mobile terminal of the student, each CPU core synchronously carries out handwriting board correction calculation in the unit thread calculation range.
In this embodiment, when correcting the handwriting, a corresponding reference picture is obtained according to the to-be-corrected handwriting picture, and when correcting the to-be-corrected handwriting picture, the circular calculation range is calculated, so that the total calculation amount can be determined when performing correction calculation on the handwriting board; meanwhile, the cycle calculation range is divided into corresponding unit thread calculation ranges according to the obtained CPU core thread number, the advantage of multi-core and multi-thread parallel processing of the CPU can be utilized, different parts in the cycle are distributed to each CPU core for calculation according to the CPU core number during calculation, and therefore calculation efficiency is greatly improved.
In an embodiment, as shown in fig. 2, in step S10, that is, if the handwriting picture to be corrected is obtained, the method obtains a corresponding reference picture according to the handwriting picture to be corrected, and specifically includes the following steps:
s11: and if the to-be-completed operation set is obtained, obtaining the to-be-completed operation identification and the to-be-completed exercise template corresponding to each to-be-completed operation identification from the to-be-completed operation set.
In this embodiment, the to-be-completed job set refers to a job set that is issued by a teacher and needs to be completed within a certain time. Wherein, the certain time may be the current day of the publication, the entire vacation or a certain part of the vacation. The to-be-completed job identifier is a character or a character string used for distinguishing each job in the to-be-completed job set. The to-be-completed problem template is a blank template which is scanned in advance and stored in a problem library for each job.
Specifically, the teacher collects questions or test papers in advance, and the collected questions or test papers are scanned for each page to form an electronic file, thereby forming a question bank. The paper problem or test paper that has been entered into the problem bank is distributed to students before the teacher issues the assignment, especially before the remote issue of the vacation assignment in the vacation, i.e., before the vacation is released.
Further, when the teacher needs to remotely issue the homework needing to be completed within a certain time to the students, the homework identifier to be completed of the specific homework needing to be completed is sent to the cloud, so that the students can check the homework identifier to be completed of the homework needing to be completed through the personal terminal at the cloud, wherein the homework identifier to be completed can refer to a certain complete examination paper, and can also be a specific exercise in an exercise book.
And further, acquiring a corresponding exercise template to be finished from a preset exercise library according to the operation identifier to be finished.
S12: and if the actual handwriting is obtained, taking the picture where the actual handwriting is as the handwriting picture to be corrected, and obtaining the operation identification to be matched from the handwriting picture to be corrected.
In this embodiment, the actual handwriting is a writing trace obtained by the electromagnetic writing pad when the student uses the electromagnetic writing pad.
Specifically, before writing according to the homework in the to-be-completed homework set, the student selects a test paper to be answered and the page number of the test paper at the personal mobile terminal, takes the to-be-completed homework identifier of the test paper to be answered as the to-be-matched homework identifier, and obtains the to-be-completed exercise template corresponding to the page number of the test paper through the to-be-matched homework identifier.
S13: and acquiring a corresponding reference picture from the to-be-completed exercise template according to the to-be-matched operation identifier.
Specifically, the to-be-matched job identifier is used to obtain a specific page number of a test paper actually written from the to-be-completed problem template, and a test paper template corresponding to the page number is obtained and used as a reference picture.
In one embodiment, as shown in fig. 3, in step S20, namely, setting a loop calculation range according to the handwriting picture to be corrected and the reference picture, the method specifically includes the following steps:
s21: acquiring a handwriting block diagram from the handwriting picture to be corrected, acquiring a reference block diagram corresponding to the handwriting block diagram from the reference picture, and respectively acquiring the handwriting block diagram position information and the reference block diagram position information of the handwriting block diagram and the reference block diagram.
In this embodiment, the handwriting block diagram refers to a rectangular frame for framing the actual answer handwriting of each topic in the handwriting picture to be corrected. The reference frame indicates an area defined in the reference picture in which each topic is answered. The handwriting frame position information and the reference frame position information are coordinate information in the picture.
Specifically, after actual preprocessing in the handwriting picture to be corrected, a handwriting block diagram is obtained in a contour searching mode. The specific pretreatment method is as follows:
(1) and carrying out binarization processing on the actual answer handwriting to obtain a binarization picture.
In this embodiment, the binarized picture refers to a picture obtained by binarizing an actual handwriting.
Specifically, a binarization function is established, and a picture recorded with actual handwriting is input into the binarization function, so that a corresponding binarization picture is obtained.
(2) And carrying out transverse expansion processing on the binary image to obtain a transverse expansion image.
In this embodiment, the horizontal expansion picture is a picture obtained by performing expansion processing on the actual response handwriting in the binarized picture.
Specifically, the average interval between each word of the student during writing is counted, the interval is used as the amplitude of the transverse expansion processing, the handwriting in the binary image is subjected to the transverse expansion processing, and the handwriting in the binary image forms an area as much as possible, so that the transverse expansion image is obtained. The transverse expansion picture can be referred to fig. 7.
(3) And finding a handwriting area in the transversely expanded picture, and taking the handwriting block as a handwriting block.
In the present embodiment, the handwriting area refers to a rectangular frame for framing the actual handwriting of each question in the horizontal expansion map.
Specifically, through the horizontal expansion processing, in the handwriting in the obtained horizontal expansion picture, the handwriting area is obtained by using the handwriting of each area in a contour searching manner, the handwriting area is represented by using x0, y0, x1 and y1 (coordinates of the upper left corner and the lower right corner), so that a handwriting frame diagram is obtained, and coordinate information represented by the coordinates of the upper left corner and the lower right corner is used as the position information of the handwriting frame diagram.
Further, when the teacher issues a job to the students to form the to-be-completed job set, in the answer area of each question in each to-be-completed exercise template in the to-be-completed job set, the answer area is defined and is represented by a rectangular frame represented by x0, y0, x1 and y1 (coordinates of upper left corner and lower right corner), a reference frame diagram is obtained, and coordinate information represented by coordinates of the upper left corner and the lower right corner is used as reference frame diagram position information.
S22: and calculating the relative offset of the handwriting block diagram position information and the reference block diagram position information, and taking the relative offset as a circular calculation range.
In the present embodiment, the relative shift amount is a distance by which the handwriting frame position information is shifted from the reference frame position information.
Specifically, the relative shift amount is set to be a difference between the abscissa and the ordinate in the coordinate information of the handwriting frame position information and the reference frame position information, and the relative shift amount is set to be the loop calculation range.
In an embodiment, as shown in fig. 4, in step S30, the method includes the following steps:
s31: and acquiring a horizontal circulation calculation range and a vertical circulation calculation range in the circulation calculation range.
In the present embodiment, the horizontal loop calculation range refers to a difference between the abscissa in the coordinate information of the handwriting frame position information and the reference frame position information. The vertical circulation calculation range is a difference between the ordinate in the coordinate information of the handwriting frame position information and the reference frame position information.
Specifically, a horizontal cycle calculation range and a vertical cycle calculation range are acquired within the cycle calculation range.
S32: and selecting a horizontal circulation calculation range or a vertical circulation calculation range, and calculating the unit thread calculation range according to the number of the CPU core threads.
Specifically, when the horizontal loop calculation range or the vertical loop calculation range is selected for parallel calculation, the total calculation amount is consistent, so that the horizontal loop calculation range or the vertical loop calculation range is arbitrarily selected, and the unit thread calculation range is calculated according to the number of the CPU core threads.
For example, the number of cores of the CPU is hc =8, search _ x _ offset =480, and search _ y _ offset =800, and the search _ x _ offset is decomposed into batch _ x = search _ x _ offset/hc =60 according to hc, where search _ x _ offset is a horizontal loop calculation range, search _ y _ offset is a vertical loop calculation range, and batch _ x is a unit thread calculation range calculated by each CPU core. Each CPU Core allocation range is as follows:
the x range of the CPU Core1 is 0-59, the y range is 0-799;
the x range calculated by CPU Core2 is 60-119, and the y range is 0-799;
…
…
the x range calculated by the CPU Core8 is 420-479, and the y range is 0-799;
that is, the amount of calculation per CPU core is batch _ x search _ y _ offset = 48000.
Or, the search _ y _ offset is decomposed into batch _ x = search _ y _ offset/hc =100 according to hc, and each CPU Core allocation range is as follows:
the x range calculated by CPU Core1 is 0-479, and the y range is 0-99;
the x range calculated by the CPU Core2 is 0-479, and the y range is 100-199;
…
…
the x range calculated by the CPU Core8 is 0-479, and the y range is 700-799;
that is, the calculation amount per CPU core is batch _ y search _ x _ offset = 48000, where batch _ y is the unit thread calculation range calculated per CPU core.
In an embodiment, as shown in fig. 5, in step S40, that is, according to the number of CPU core threads, allocating each unit thread calculation range to a corresponding CPU core for performing the handwriting board correction calculation, specifically includes the following steps:
s41: and acquiring a preset circulation interval and a circulation initial position of each unit thread calculation range, and circularly calculating the intersection ratio in each unit thread calculation range from the corresponding circulation initial position according to the circulation interval.
In this embodiment, the cycle interval refers to the offset between the intersection ratio calculated IoU for two adjacent horizontal or vertical cycles. The Intersection-over-Union ratio IoU (IoU) refers to a concept used in target detection, and is the overlapping rate of the generated candidate frame (candidate frame) and the original marker frame (ground channel frame), i.e. the ratio of their Intersection to Union. In this embodiment, the candidate frame (candidate frame) and the original mark frame (ground route frame) are the handwriting frame and the reference frame, respectively. The loop start position refers to the start position at which the loop calculates IoU the intersection ratio.
Specifically, according to the resolution of the existing electromagnetic handwriting board, the calculation amount of the IoU cross-over ratio is reduced and the effect of correcting the actual answer handwriting in the actual answer area is ensured finally, in the embodiment, after long-term test, and according to the test result, the cycle interval is set to be 2 pixels.
Further, a coordinate point is selected in the reference picture as a loop initial position of the first CPU core, and in this embodiment, in order to reduce the amount of calculation, a coordinate of the upper left corner of the reference frame diagram in each page of the reference picture is selected as the loop initial position. Meanwhile, according to the mode of dividing the calculation range of the unit thread, namely selecting the horizontal circulation calculation range or the vertical circulation calculation range as the dividing basis, the circulation initial position of each CPU core at the beginning of the second CPU core is obtained. For example, the horizontal loop calculation range is selected as the basis of the division, and the loop start position of the first CPU core is (0,0), then, from the second CPU core, the loop start position of each CPU core is (60,0), (120,0), (180,0) … … (420, 0).
Further, each CPU core simultaneously calculates the IoU cross-over ratio from the corresponding cycle initial position according to the cycle interval, when calculating the IoU cross-over ratio each time, the track block diagram is moved transversely or vertically, namely when calculating the IoU cross-over ratio each time, the IoU cross-over ratio is calculated relative to the previous time, the actual answering area is moved transversely or vertically by 2 pixels, and when calculating the IoU cross-over ratio each time, the difference between the abscissa and the ordinate of the upper left-hand coordinate of the track block diagram relative to the coordinate of the cycle initial position at the moment is recorded.
Further, when the horizontal movement and the vertical movement reach the maximum value of the horizontal circulation range or the maximum value of the vertical circulation in the circulation movement range, the displacement is stopped, and the intersection ratio of the circulation calculation IoU is guaranteed, and all points are traversed in a dot matrix formed by the horizontal circulation range, the vertical circulation range and the circulation interval in the circulation movement range.
S42: and acquiring the intersection ratio and the corresponding candidate offset obtained by each cycle calculation, and sequencing according to the sequence from large intersection ratio to small intersection ratio to obtain a sequencing result.
In the present embodiment, the candidate offset is an offset of the actual response region with respect to the loop initial position in each calculation of the IoU cross-over ratio in the loop calculation IoU cross-over ratio.
Specifically, after IoU cross-over ratios are obtained for each calculation, the difference between the coordinates of the upper left corner of the recorded actual response area with respect to the abscissa of the coordinates of the loop initial position, and the difference between the differences between the vertical coordinates are taken as the candidate offsets.
Further, after all the CPU cores stop calculating IoU union ratios, IoU union ratios obtained by each CPU core are collected, and then sorted in descending order to obtain the sorting result.
S43: and acquiring the first-ranked intersection and comparison corresponding candidate offset in the sequencing result, and taking the candidate offset as a calculation result of correction calculation of the handwriting board.
In this embodiment, the calculation result of the handwriting board correction calculation refers to the amount of displacement specifically required when the actual response area is corrected.
Specifically, in the sorting result, the IoU cross-over ratio with the first rank, that is, the maximum value of the IoU cross-over ratio, is selected, and the candidate offset corresponding to the selected IoU is used as the calculation result of the handwriting board correction calculation.
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.
Example two:
in one embodiment, a handwriting board correction multithread parallel processing device is provided, and the handwriting board correction multithread parallel processing device corresponds to the handwriting board correction multithread parallel processing method in one-to-one mode in the embodiment. As shown in fig. 6, the multi-thread parallel processing device for handwriting board correction includes a picture acquiring module 10, a range calculating module 20, a calculation amount allocating module 30 and a calculating module 40. The functional modules are explained in detail as follows:
the image obtaining module 10 is configured to obtain a corresponding reference image according to the handwriting image to be corrected if the handwriting image to be corrected is obtained;
the range calculation module 20 is used for setting a circular calculation range according to the handwriting picture to be corrected and the reference picture;
the calculation amount distribution module 30 is configured to obtain the number of CPU core threads, and calculate a unit thread calculation range according to the number of CPU core threads and a cycle calculation range;
and the calculating module 40 is used for distributing the calculating range of each unit thread to the corresponding CPU core according to the number of the threads of the CPU core to perform the correction calculation of the handwriting board.
Preferably, the picture taking module 10 comprises:
the operation obtaining submodule 11 is configured to obtain, if a to-be-completed operation set is obtained, to-be-completed operation identifiers and to-be-completed problem templates corresponding to each to-be-completed operation identifier from the to-be-completed operation set;
the handwriting obtaining sub-module 12 is configured to, if the actual answer handwriting is obtained, take a picture where the actual answer handwriting is located as a to-be-corrected handwriting picture, and obtain an operation identifier to be matched from the to-be-corrected handwriting picture;
and the reference picture obtaining submodule 13 is used for obtaining a corresponding reference picture from the to-be-completed exercise template according to the to-be-matched operation identifier.
Preferably, the range calculation module 20 includes:
the position information acquisition sub-module 21 is configured to acquire a handwriting frame from the handwriting picture to be corrected, acquire a reference frame corresponding to the handwriting frame from the reference picture, and acquire position information of the handwriting frame and the reference frame and position information of the reference frame, respectively;
and the range calculation submodule 22 is used for calculating the relative offset between the handwriting block diagram position information and the reference block diagram position information, and taking the relative offset as a circular calculation range.
Preferably, the calculation amount distribution module 30 includes:
the range setting submodule is used for acquiring a horizontal cycle calculation range and a vertical cycle calculation range in the cycle calculation range;
and the selection calculation submodule is used for selecting a horizontal circulation calculation range or a vertical circulation calculation range and calculating the unit thread calculation range according to the number of the CPU core threads.
Preferably, the calculation module 40 comprises:
the parallel computing submodule is used for acquiring a preset cycle interval and a cycle initial position of each unit thread computing range, and circularly computing an intersection ratio in each unit thread computing range from the corresponding cycle initial position according to the cycle interval;
the sorting submodule is used for acquiring the intersection ratio and the corresponding candidate offset obtained by each cycle calculation, and sorting according to the sequence of the intersection ratio from large to small to obtain a sorting result;
and the result returning submodule is used for acquiring the first-ranked intersection and comparison corresponding candidate offset in the sequencing result, and taking the candidate offset as the calculation result of the correction calculation of the handwriting board.
For specific limitations of the handwriting board correction multithread parallel processing device, reference may be made to the above limitations of the handwriting board correction multithread parallel processing method, which is not described herein again. All or part of each module in the handwriting board correction multithread parallel processing device can be realized by software, hardware and combination thereof. The modules can be embedded in a hardware form or independent from 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.
Example three:
in one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. 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 nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for pre-inputting the exercises to form an exercise library. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a handwriting pad correction multi-thread parallel processing method.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
s10: if the handwriting picture to be corrected is obtained, obtaining a corresponding reference picture according to the handwriting picture to be corrected;
s20: setting a circulating calculation range according to the handwriting picture to be corrected and the reference picture;
s30: acquiring the number of CPU core threads, and calculating the calculation range of unit threads according to the number of CPU core threads and the circulation calculation range;
s40: and distributing the calculation range of each unit thread to the corresponding CPU core according to the number of the CPU core threads to perform correction calculation on the handwriting board.
Example four:
in one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
s10: if the handwriting picture to be corrected is obtained, obtaining a corresponding reference picture according to the handwriting picture to be corrected;
s20: setting a circulating calculation range according to the handwriting picture to be corrected and the reference picture;
s30: acquiring the number of CPU core threads, and calculating the calculation range of unit threads according to the number of CPU core threads and the circulation calculation range;
s40: and distributing the calculation range of each unit thread to the corresponding CPU core according to the number of the CPU core threads to perform correction calculation on the handwriting board.
It will be understood by those of ordinary skill in the art that all or a portion of the processes of the methods of the embodiments described above may be implemented by a computer program that may be stored on a non-volatile computer-readable storage medium, which when executed, may include the processes of the embodiments of the methods described above, wherein any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-mentioned 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 (10)
1. A handwriting board correction multithreading parallel processing method is characterized by comprising the following steps:
s10: if the handwriting picture to be corrected is obtained, obtaining a corresponding reference picture according to the handwriting picture to be corrected;
s20: setting a circulating calculation range according to the handwriting picture to be corrected and the reference picture;
s30: acquiring the number of CPU core threads, and calculating the calculation range of unit threads according to the number of CPU core threads and the circular calculation range;
s40: and distributing each unit thread calculation range to the corresponding CPU core according to the number of the CPU core threads to perform handwriting board correction calculation.
2. The handwriting board correction multithread parallel processing method according to claim 1, wherein step S10 includes:
s11: if the to-be-completed operation set is obtained, obtaining to-be-completed operation identifications and to-be-completed exercise templates corresponding to the to-be-completed operation identifications from the to-be-completed operation set;
s12: if the actual handwriting is obtained, taking the picture where the actual handwriting is located as the handwriting picture to be corrected, and obtaining the operation identification to be matched from the handwriting picture to be corrected;
s13: and acquiring the corresponding reference picture from the to-be-matched exercise template according to the to-be-matched operation identifier.
3. The handwriting board correction multithread parallel processing method according to claim 1, wherein step S20 includes:
s21: acquiring a handwriting block diagram from the handwriting picture to be corrected, acquiring a reference block diagram corresponding to the handwriting block diagram from the reference picture, and respectively acquiring handwriting block diagram position information and reference block diagram position information of the handwriting block diagram and the reference block diagram;
s22: and calculating the relative offset of the handwriting block diagram position information and the reference block diagram position information, and taking the relative offset as the circular calculation range.
4. The handwriting board correction multithread parallel processing method according to claim 1, wherein step S30 includes:
s31: acquiring a horizontal circulation calculation range and a vertical circulation calculation range in the circulation calculation range;
s32: and selecting the horizontal circulation calculation range or the vertical circulation calculation range, and calculating the unit thread calculation range according to the number of the CPU core threads.
5. The handwriting board correction multithread parallel processing method according to claim 1, wherein step S40 includes:
s41: acquiring a preset circulation interval and a circulation initial position of each unit thread calculation range, and circularly calculating an intersection ratio in each unit thread calculation range from the corresponding circulation initial position according to the circulation interval;
s42: acquiring the intersection ratio and the corresponding candidate offset obtained by each cycle calculation, and sorting according to the sequence of the intersection ratio from large to small to obtain a sorting result;
s43: and acquiring the candidate offset corresponding to the intersection ratio with the first ranking in the sequencing result, and taking the candidate offset as the calculation result of the correction calculation of the handwriting board.
6. A handwriting pad correction multithreaded parallel processing apparatus, comprising:
the image acquisition module is used for acquiring a corresponding reference image according to the handwriting image to be corrected if the handwriting image to be corrected is acquired;
the range calculation module is used for setting a circular calculation range according to the handwriting picture to be corrected and the reference picture;
the calculation amount distribution module is used for acquiring the number of CPU core threads and calculating the calculation range of the unit thread according to the number of the CPU core threads and the circulation calculation range;
and the calculation module is used for distributing each unit thread calculation range to the corresponding CPU core according to the number of the CPU core threads to carry out correction calculation on the handwriting board.
7. The handwriting board correction multithreading parallel processing apparatus according to claim 6, wherein the picture taking module comprises:
the operation acquisition submodule is used for acquiring to-be-completed operation identifications and to-be-completed exercise templates corresponding to each to-be-completed operation identification from the to-be-completed operation set if the to-be-completed operation set is acquired;
the handwriting obtaining sub-module is used for taking a picture where the actual handwriting is located as the handwriting picture to be corrected and obtaining the operation identification to be matched from the handwriting picture to be corrected if the actual handwriting is obtained;
and the reference picture acquisition submodule is used for acquiring the corresponding reference picture from the to-be-completed exercise template according to the to-be-matched operation identifier.
8. The handwriting board correction multithreading parallel processing apparatus of claim 6, wherein the range calculation module comprises:
the position information acquisition sub-module is used for acquiring a handwriting block diagram from the handwriting picture to be corrected, acquiring a reference block diagram corresponding to the handwriting block diagram from the reference picture, and respectively acquiring the handwriting block diagram and the position information of the reference block diagram;
and the range calculation submodule is used for calculating the relative offset of the handwriting block diagram position information and the reference block diagram position information, and taking the relative offset as the circular calculation range.
9. Computer device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, characterized in that said processor realizes the steps of a method for multi-threaded parallel processing of handwriting correction according to any of claims 1 to 5 when executing said computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of a method for handwriting correction multithreading parallel processing according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010323599.8A CN111506348A (en) | 2020-04-22 | 2020-04-22 | Handwriting board correction multithreading parallel processing method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010323599.8A CN111506348A (en) | 2020-04-22 | 2020-04-22 | Handwriting board correction multithreading parallel processing method, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111506348A true CN111506348A (en) | 2020-08-07 |
Family
ID=71872898
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010323599.8A Pending CN111506348A (en) | 2020-04-22 | 2020-04-22 | Handwriting board correction multithreading parallel processing method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111506348A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11250179A (en) * | 1998-02-27 | 1999-09-17 | Matsushita Joho System Kk | Character reocognition device and its method |
| JP2005301652A (en) * | 2004-04-12 | 2005-10-27 | Pentel Corp | Coordinate input correction method for handwritten character input device |
| CN101697201A (en) * | 2009-09-25 | 2010-04-21 | 华南理工大学 | Handwritten Chinese character identification method irrelevant to rotation direction |
| CN101958989A (en) * | 2009-07-16 | 2011-01-26 | 富士施乐株式会社 | Image processing apparatus, image processing system and image processing method |
| CN102135821A (en) * | 2011-03-08 | 2011-07-27 | 中国科学技术大学 | Handwriting pen and graphic restoration system |
| CN105786289A (en) * | 2016-03-31 | 2016-07-20 | 联想(北京)有限公司 | Method for reducing screen input disturbance and electronic device |
| CN106201172A (en) * | 2016-06-24 | 2016-12-07 | 广州视睿电子科技有限公司 | Canvas display method and device for touch screen terminal |
| CN106648418A (en) * | 2016-11-14 | 2017-05-10 | 北京爱知之星科技股份有限公司 | Handwriting correction method and device |
| CN107247623A (en) * | 2017-05-22 | 2017-10-13 | 哈工大大数据产业有限公司 | A kind of distributed cluster system and data connecting method based on multi-core CPU |
| CN108415600A (en) * | 2018-03-09 | 2018-08-17 | 宁波宁大教育设备有限公司 | Time writer handwriting aligning method and device |
| CN209784982U (en) * | 2019-05-20 | 2019-12-13 | 鲁伯特（北京）教育科技有限公司 | handwriting board page code recognition and writing track correction device |
| CN110781643A (en) * | 2019-09-29 | 2020-02-11 | 广东墨痕教育科技有限公司 | Handwriting recognition method of Word document electronic test paper and computer readable storage medium |
| CN110928459A (en) * | 2019-10-09 | 2020-03-27 | 广州视源电子科技股份有限公司 | Writing operation method, device, equipment and storage medium of intelligent interactive tablet |
-
2020
- 2020-04-22 CN CN202010323599.8A patent/CN111506348A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11250179A (en) * | 1998-02-27 | 1999-09-17 | Matsushita Joho System Kk | Character reocognition device and its method |
| JP2005301652A (en) * | 2004-04-12 | 2005-10-27 | Pentel Corp | Coordinate input correction method for handwritten character input device |
| CN101958989A (en) * | 2009-07-16 | 2011-01-26 | 富士施乐株式会社 | Image processing apparatus, image processing system and image processing method |
| CN101697201A (en) * | 2009-09-25 | 2010-04-21 | 华南理工大学 | Handwritten Chinese character identification method irrelevant to rotation direction |
| CN102135821A (en) * | 2011-03-08 | 2011-07-27 | 中国科学技术大学 | Handwriting pen and graphic restoration system |
| CN105786289A (en) * | 2016-03-31 | 2016-07-20 | 联想(北京)有限公司 | Method for reducing screen input disturbance and electronic device |
| CN106201172A (en) * | 2016-06-24 | 2016-12-07 | 广州视睿电子科技有限公司 | Canvas display method and device for touch screen terminal |
| CN106648418A (en) * | 2016-11-14 | 2017-05-10 | 北京爱知之星科技股份有限公司 | Handwriting correction method and device |
| CN107247623A (en) * | 2017-05-22 | 2017-10-13 | 哈工大大数据产业有限公司 | A kind of distributed cluster system and data connecting method based on multi-core CPU |
| CN108415600A (en) * | 2018-03-09 | 2018-08-17 | 宁波宁大教育设备有限公司 | Time writer handwriting aligning method and device |
| CN209784982U (en) * | 2019-05-20 | 2019-12-13 | 鲁伯特（北京）教育科技有限公司 | handwriting board page code recognition and writing track correction device |
| CN110781643A (en) * | 2019-09-29 | 2020-02-11 | 广东墨痕教育科技有限公司 | Handwriting recognition method of Word document electronic test paper and computer readable storage medium |
| CN110928459A (en) * | 2019-10-09 | 2020-03-27 | 广州视源电子科技股份有限公司 | Writing operation method, device, equipment and storage medium of intelligent interactive tablet |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220101030A1 (en) | Examination paper correction method and apparatus, electronic device, and storage medium | |
| CN109343845A (en) | A kind of code file generation method and device | |
| CN107273002B (en) | Handwriting input answering method, terminal and computer readable storage medium | |
| CN109145904A (en) | A kind of character identifying method and device | |
| US11093701B2 (en) | Form input processing | |
| CN111104883B (en) | Job answer extraction method, apparatus, device and computer readable storage medium | |
| CN108197596B (en) | Gesture recognition method and device | |
| CN114782970B (en) | Table extraction method, system and readable medium | |
| CN106131630A (en) | Web page browsing control method based on television set and relevant apparatus | |
| CN109086336A (en) | Paper date storage method, device and electronic equipment | |
| CN111582405B (en) | Data labeling method and device | |
| EP3761288A1 (en) | Print, and production method and production system for touch-and-talk content of print | |
| CN113793538B (en) | Method and system for collecting teaching assistance operation wrong questions | |
| CN111523387A (en) | Method and device for detecting hand key points and computer device | |
| CN111506348A (en) | Handwriting board correction multithreading parallel processing method, device, equipment and medium | |
| CN113378823A (en) | Psychological scale test paper generation and automatic reading system | |
| CN109727299A (en) | A kind of control mechanical arm combines the method drawn a picture, electronic equipment and storage medium | |
| CN112364867B (en) | Intelligent correcting method and system for handwriting operation, electronic equipment and storage medium | |
| CN113065477B (en) | Intelligent classroom textbook content identification method | |
| CN111507292A (en) | Handwriting board correction method and device, computer equipment and storage medium | |
| CN115482547A (en) | Method, storage medium and equipment for realizing examination question correction trace identification | |
| CN115272018A (en) | Job processing method, job processing apparatus, electronic apparatus, and storage medium | |
| CN114296564A (en) | Writing deleting method and system for electronic whiteboard, electronic whiteboard and storage medium | |
| CN103700047A (en) | Roll call system based on attendance probability and roll call method based on attendance probability | |
| CN112000786A (en) | Dialogue robot problem processing method, device and equipment combining RPA and AI |
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 | ||
| CB02 | Change of applicant information |
Address after: 510032 Part 402, No. 7, caipin Road, Science City, Luogang District, Guangzhou City, Guangdong Province Applicant after: Guangdong Everbright Information Technology Co.,Ltd. Address before: 510032 Part 402, No. 7, caipin Road, Science City, Luogang District, Guangzhou City, Guangdong Province Applicant before: GUANGZHOU EVERBRIGHT EDUCATION SOFTWARE TECHNOLOGY CO.,LTD. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200807 |
|
| RJ01 | Rejection of invention patent application after publication |