Work condition information acquisition method, device and equipment and storage medium

Abstract

The invention relates to the technical field of image processing, in particular to a method, a device and equipment for collecting work condition information and a storage medium, and the scheme comprises the steps that a panoramic image shot by a camera in a learning area is acquired, the learning area comprises a plurality of work clamping plates, and the work clamping plates are used for clamping a to-be-checked work page; extracting a region image corresponding to the operation clamping plate as an operation region image according to the panoramic image; generating operation acquisition data according to the operation area image; and sending the operation acquisition data to a server, so that the server generates operation information according to the operation acquisition data. Through the panoramic image collected by the camera, the information of the learning area can be comprehensively obtained, the situation of omission of the operation clamping plate is avoided, the area image corresponding to the operation clamping plate is further extracted, the operation area image is processed, and then complete and accurate operation collection data in the learning area is obtained. And accurate operation information is generated according to the operation acquisition data.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a method, device, equipment and storage medium for collecting homework learning information. Background Art

[0002] With the development of camera technology and data processing technology, more and more traditional manual tasks can be completed by machine operations. For example, in teaching scenarios, by statistically analyzing homework information, students' learning characteristics and grades can be obtained, which is of great significance for understanding students' learning status and guiding teachers to adjust teaching methods.

[0003] The related technology provides a method for collecting learning information, which uses a high-definition camera to collect students' homework information. The teacher operates the high-definition camera to collect each student's homework information one by one, and then generates homework learning information based on the homework information of all students. This method of collecting learning information requires the teacher to spend more time and has low collection efficiency. Summary of the invention

[0004] One purpose of an embodiment of the present invention is to provide a method, device, equipment and storage medium for collecting homework learning information, which can solve the technical problem of low efficiency of existing learning information collection.

[0005] In a first aspect, an embodiment of the present invention provides a method for collecting homework learning information, which is applied to a terminal device of a homework learning information collection system, wherein the homework learning information collection system includes a camera, a server, and the terminal device; the method includes:

[0006] Acquire a panoramic image captured by the camera in a learning area, wherein the learning area includes a plurality of work clamps, and the work clamps are used to clamp work pages to be checked;

[0007] Extracting a region image corresponding to the working clamping plate according to the panoramic image as a working region image;

[0008] generating operation acquisition data according to the operation area image;

[0009] Send each of the homework collection data to the server, so that the server generates homework learning information according to each of the homework collection data.

[0010] Optionally, generating the operation acquisition data according to the operation area image includes:

[0011] extracting the operation writing information contained in the operation area image;

[0012] Scanning the homework area image to obtain student identity information;

[0013] The homework writing information and the student identity information are combined to obtain homework collection data.

[0014] Optionally, extracting the area image corresponding to the work clamping plate according to the panoramic image as the work area image includes:

[0015] Performing contour recognition on the panoramic image to obtain a contour area, wherein the contour of the contour area is the contour of the work clamping plate;

[0016] Gaussian blur is performed on the area except the outline area in the panoramic image to obtain a working area image.

[0017] Optionally, before generating the operation acquisition data according to the operation area image, the method further includes:

[0018] Determining whether the working area image is in an abnormal state;

[0019] If so, mark the work area image and output prompt information;

[0020] If not, generate operation acquisition data according to the operation area image.

[0021] Optionally, the determining whether the working area image is in an abnormal state includes:

[0022] extracting a plurality of keywords according to the work area image;

[0023] Matching the multiple keywords with the preset first information to obtain a target matching value;

[0024] If the target matching value is lower than a first preset threshold, it is determined that the working area image is in an abnormal state;

[0025] If the target matching value is higher than a first preset threshold, it is determined that the working area image is in a normal state.

[0026] Optionally, the panoramic image is configured with a reference line, and the determining whether the working area image is in an abnormal state includes:

[0027] Determining an angle between a designated line of the work area image and the reference line;

[0028] If the angle is greater than or equal to a second preset threshold, it is determined that the working area image is in an abnormal state;

[0029] If the angle is smaller than the second preset threshold, it is determined that the working area image is in a normal state.

[0030] Optionally, the determining whether the working area image is in an abnormal state includes:

[0031] Determining whether a label area can be scanned in the working area image;

[0032] If it is scanned, it is determined that the image of the working area is in a normal state;

[0033] If it is not scanned, it is determined that the working area image is in an abnormal state.

[0034] In a second aspect, an embodiment of the present invention provides a device for collecting homework learning information, which is applied to a terminal device of a homework learning information collection system, wherein the homework learning information collection system includes a camera, a server, and the terminal device; the method includes:

[0035] An acquisition unit, used for acquiring a panoramic image captured by the camera in a learning area, wherein the learning area includes a plurality of work clamps, and the work clamps are used for clamping work pages to be checked;

[0036] An extraction unit, configured to extract a region image corresponding to the working clamping plate as a working region image according to the panoramic image;

[0037] A generating unit, configured to generate operation acquisition data according to the operation area image;

[0038] The sending unit is used to send each of the homework collection data to the server, so that the server generates homework learning information according to each of the homework collection data.

[0039] In a third aspect, an embodiment of the present invention provides a system for collecting homework learning information, characterized in that it includes a camera, a terminal device and a server, wherein the terminal device is respectively connected to the camera and the server for communication;

[0040] The camera is used to respond to the acquisition command sent by the terminal device to acquire a panoramic image of the learning area, wherein the learning area includes a plurality of work clamps, and the work clamps are used to clamp the work pages to be checked;

[0041] The terminal device is used to receive the panoramic image sent by the camera, extract the area image corresponding to the work clamping plate as the work area image according to the panoramic image, generate work collection data according to the work area image, and send each of the work collection data to the server;

[0042] The server is used to receive the homework collection data sent by the terminal device, and generate homework learning information according to the homework collection data.

[0043] In a fourth aspect, an embodiment of the present invention provides a computer device, including:

[0044] at least one processor; and,

[0045] a memory communicatively connected to the at least one processor; wherein,

[0046] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to the first aspect.

[0047] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method as described in the first aspect.

[0048] In the scheme implemented by the above-mentioned method, device, equipment and storage medium for collecting homework learning information, the terminal device of the homework learning information collection system first obtains the panoramic image taken by the camera in the learning area, and the learning area includes multiple homework clamps, and the homework clamps are used to clamp the homework pages to be checked. Secondly, the area image corresponding to the homework clamp is extracted as the homework area image according to the panoramic image, and then the homework collection data is generated according to the homework area image. Finally, each of the homework collection data is sent to the server so that the server generates homework learning information according to each of the homework collection data. In this embodiment, the panoramic image collected by the camera can fully obtain the information of the learning area. This collection method has a relatively high collection efficiency and can also avoid the situation of missing homework clamps. The area image corresponding to the homework clamp is further extracted, and the homework area image is processed to obtain complete and accurate homework collection data in the learning area, and accurate homework learning information is generated based on the accurate and complete homework collection data. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0050] Figure 1 It is a schematic diagram of a homework learning information collection system in one embodiment of the present invention;

[0051] Figure 2AA schematic diagram of a flow chart of a method for collecting homework learning information in one embodiment of the present invention;

[0052] Figure 2B is a schematic diagram of a working splint in one embodiment of the present invention;

[0053] Figure 2C is a schematic diagram of a panoramic image interface in one embodiment of the present invention;

[0054] Figure 2D This is a schematic diagram of an abnormal operation area image interface in one embodiment of the present invention;

[0055] Figure 2E This is a schematic diagram of an image interface of a working area in one embodiment of the present invention;

[0056] Figure 2F It is a schematic diagram of homework learning information in one embodiment of the present invention;

[0057] Figure 3 It is a flowchart of another method for collecting homework learning information in one embodiment of the present invention;

[0058] Figure 4 It is a structural schematic diagram of a device for collecting homework learning information in one embodiment of the present invention;

[0059] Figure 5 Schematic diagram of the structure of a computer device in one embodiment of the present invention DETAILED DESCRIPTION

[0060] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0061] It should be noted that, if there is no conflict, the various features in the embodiments of the present invention can be combined with each other, all within the scope of protection of the present invention. In addition, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order from the module division in the device or the flow chart. Furthermore, the words "first", "second", "third", etc. used in the present invention do not limit the data and execution order, but only distinguish the same items or similar items with basically the same functions and effects.

[0062] The present invention is described in detail below through specific embodiments.

[0063] See also Figure 1 , Figure 1 A schematic diagram of a homework learning situation information collection system provided in an embodiment of the present invention, wherein the homework learning situation information collection system 10 includes a camera 22, a terminal device 23 and a server 24, wherein the terminal device 23 is communicatively connected to the camera 22 and the server 24 respectively; the camera 22 is used to respond to a collection command sent by the terminal device 23, and collect a panoramic image of a learning area, wherein the learning area includes a plurality of homework clamps, and the homework clamps are used to clamp homework pages to be checked; the terminal device 23 is used to receive the panoramic image sent by the camera 22, extract the area image corresponding to the homework clamp as the homework area image according to the panoramic image, generate homework collection data according to the homework area image, and send each of the homework collection data to the server 24; the server 24 is used to receive each of the homework collection data sent by the terminal device 23, and generate homework learning situation information according to each of the homework collection data.

[0064] For example, refer to Figure 1 , Figure 1 As shown, a learning area 20 includes a plurality of student positions 21, a camera 22, a terminal device 23 and a server 24, wherein a homework clamp 25 is provided next to each student position 21, and the homework clamp 25 is used to clamp the homework page to be checked. The camera 22 is connected to the terminal device 23 and the server 24, and the terminal device 23 is connected to the server 24.

[0065] There are multiple cameras 22 , which are arranged at various positions in the learning area 20 . The cameras 22 can take pictures of the homework boards 25 of each student to obtain a panoramic image. The cameras 22 can send the panoramic image to the terminal device 23 .

[0066] The terminal device 23 is used to process the panoramic image and obtain the homework collection data, wherein the computer device 23 can be operated and controlled by the teacher, and the teacher can operate the terminal device 23 to send the homework collection data to the server 24.

[0067] The server 24 can receive instructions and data from the terminal device 23, and send relevant content to the terminal device 23, and the terminal device 23 can display the content sent by the server 24. For example, based on the data collected by the homework, the server 24 can automatically correct the homework through the AI ​​model, and send the correction results to the terminal device 23 and save them in the server 24. Alternatively, the students' homework can be corrected by manual online reading (subjective questions) + automatic correction (objective questions). With the data of automatic correction, data analysis and statistics of the academic situation can be performed by dimensions such as homework, student, class, and school, so as to generate a homework report. Conduct a detailed analysis of students' wrong questions, knowledge points, etc., and generate a data overview, question details, student answers, etc.

[0068] As shown in the above scenario, see Figure 2A , Figure 2A A schematic diagram of a method for collecting homework learning information provided by an embodiment of the present invention is applied to a terminal device of a homework learning information collection system, wherein the homework learning information collection system includes a camera, a server, and the terminal device; the method includes the following steps:

[0069] S10, obtaining a panoramic image captured by the camera in a learning area, wherein the learning area includes a plurality of work clamps, and the work clamps are used to clamp work pages to be checked.

[0070] The learning area may be a classroom scene, a conference room, or an auditorium, and is not limited here.

[0071] For example, when the teaching area is a classroom, a camera device is installed on the ceiling of the classroom. One camera device can cover about 12 square meters. Four cameras installed in a classroom can cover the entire teaching plan. The telephoto lens of the camera can capture the student's homework very clearly.

[0072] In a specific implementation, when shooting, the four cameras will shoot the students' images through telephoto lenses in sequence, and the images of the four cameras will be fused and merged into one video stream, forming a panoramic image based on the interface in the video stream.

[0073] Among them, the above-mentioned work splint is a board that can fix data. The board has at least two clips, and the clips are located on the above-mentioned board. The color of the board surface of the work splint is different from the color of the table and chair.

[0074] For example, the schematic diagram of the above-mentioned work splint is as follows Figure 2BAs shown, the homework clamp includes clips on the left and top sides. The clips in the clamp are used to fix the teaching aids and flatten the pages of the teaching aids. When taking pictures, the pictures of the teaching aids can be clearly captured. It can also be used to fix A3 and A4 paper. And this homework clamp is affixed with a QR code, which identifies the student's student number, name, class and other information. As for the position of the QR code, it is not fixed, as long as it can be recognized when taking pictures.

[0075] It can be seen that limiting the shooting area to the position of the work splint can improve the efficiency and accuracy of recognition. Through subsequent steps, the information in the work splint area can be further processed to obtain accurate work learning information.

[0076] S20, extracting a region image corresponding to the work clamping plate as a work region image according to the panoramic image.

[0077] The above-mentioned homework area image may include homework writing information and identification information, and the homework writing information is matched and authenticated with the student's identity based on the identification information.

[0078] S30: Generate operation acquisition data according to the operation area image.

[0079] The homework collection data is the pairing data of each homework and the corresponding student information.

[0080] S40, sending each of the homework collection data to the server, so that the server generates homework learning information according to each of the homework collection data.

[0081] Among them, the data collected from each homework is integrated to generate homework learning information, and the collected homework data is transmitted to the server through the network. After the students' homework pictures are collected, the homework can be automatically graded through the ability of AI, and the results of the correction can be saved in the background server. It is also possible to correct students' homework by manual online reading (subjective questions) + automatic correction (objective questions). With the data for automatic correction, data analysis and statistics of the learning situation can be performed by dimensions such as homework, student, class, and school to generate a homework report. Conduct a detailed analysis of students' wrong questions, knowledge points, etc., and generate a data overview, question details, student answer details, etc. In addition to homework reports, teachers can also directly open the homework situation in the software during class and explain the homework questions.

[0082] In step S30, in some embodiments, generating the homework collection data based on the homework area image includes: extracting the homework writing information contained in the homework area image; scanning the homework area image to obtain the student identity information; combining the homework writing information and the student identity information to obtain the homework collection data.

[0083] The above extraction step may be performed by optical character recognition (OCR), template matching, a preset image analysis algorithm, etc., and is not limited here.

[0084] Specifically, the above extraction step can be performed by a preset image analysis algorithm, that is, the operation writing information contained in the image of the operation area is extracted according to the preset image analysis algorithm. The above preset image analysis algorithm is a calculation method for extracting relevant structures, features and information from the image, which can be set manually. Common ones include edge detection, feature extraction, target detection and recognition, etc., which are not limited here.

[0085] In some embodiments, extracting the written work information contained in the work area image according to a preset image analysis algorithm includes: performing target detection on the work area image to obtain the written work information contained in the work area image.

[0086] In some embodiments, scanning the homework area image includes: determining a label area in the homework area image, and determining the student identity information based on scanning the label area.

[0087] Among them, the label area contains labels that can identify the identity of students, which are identified by scanning and other means. Each student's identity information corresponds to a unique label. The label can be a QR code, which is not limited here.

[0088] In combining and matching the homework writing information of each combination with the student identity information, each homework area image contains label information and homework writing information, so that the homework situation of each student can be confirmed in the collected homework collection data.

[0089] It can be seen that in this example, the homework is associated with the student through the student identity information in each homework area image, and the homework content corresponding to each student is obtained, which improves the accuracy and convenience of homework collection data.

[0090] In some embodiments, extracting the area image corresponding to the work clamp based on the panoramic image as the work area image includes: performing contour recognition on the panoramic image to obtain a contour area, the contour of the contour area is the contour of the work clamp; and performing Gaussian blur on the area in the panoramic image except the contour area to obtain a work area image.

[0091] Among them, the above-mentioned contour recognition can use feature extraction to distinguish the work clamp and the desktop according to the contour edge features, and the work clamp can use a specific color to distinguish it from the desktop, which makes it easier to identify the contour area.

[0092] The surrounding images corresponding to each contour image are Gaussian blurred. Gaussian blur is usually used to reduce image noise and detail levels, and blur the image. The visual effect is like observing the image through a semi-transparent screen. Figure 2C , Figure 2C It is demonstrated that multiple contour areas are obtained in a panoramic image, and Gaussian blur processing is performed on the image outside the contour area.

[0093] It can be seen that in this solution, contour processing and preliminary image filtering are performed on the panoramic image collected in real time to obtain multiple contour area images, which facilitates further image processing of the contour images to obtain accurate working area images.

[0094] In some embodiments, before generating the job collection data based on the work area image, the method also includes: determining whether the work area image is in an abnormal state; if so, marking the work area image and outputting a prompt message; if not, generating the job collection data based on the work area image.

[0095] Among them, the above-mentioned abnormal state is the inability to recognize the complete homework area image. The above situation may be caused by the incorrect number of homework pages placed on the homework clipboard by the current student, or the homework content does not meet the teacher's requirements, or the identification information is blocked, and the student identity corresponding to the homework writing information cannot be obtained, or the homework is placed on the clipboard too tilted, and the homework area image cannot be clearly obtained.

[0096] For example, see Figure 2D , Figure 2D This is a schematic diagram of the display interface when the collected working area image is in an abnormal situation. The abnormal working area is marked in the figure, and the corresponding content is displayed in the mark column on the right.

[0097] Among them, the above-mentioned abnormal operation area images are marked and can be displayed in the collection interface, so that the teacher can quickly see which position of the students has the problem and guide the students to make adjustments.

[0098] Optionally, marking the work area image includes highlighting a work area image frame or displaying a specific symbol in the work area image.

[0099] There is no restriction on the display form of the above prompt information, but the prompt information in each different situation may have different prompt contents according to the abnormal situation.

[0100] It can be seen that by verifying the image of the work area, the collected learning information can be made more accurate, avoiding the situation of unqualified information after collection, and the need to collect abnormal operations separately, which is time-consuming and labor-intensive.

[0101] In some embodiments, determining whether the work area image is in an abnormal state includes: extracting multiple keywords based on the work area image; matching the multiple keywords with a preset first information to obtain a target matching value; if the target matching value is lower than a first preset threshold, determining that the work area image is in an abnormal state; if the target matching value is higher than the first preset threshold, determining that the work area image is in a normal state.

[0102] Among them, the above keywords can be the number of pages of the homework, the name of the homework, etc., without any limitation here. The keywords are keywords extracted from the target interface that is pre-input by the teacher or backstage personnel in advance.

[0103] Among them, the above-mentioned first preset matching value can be different values ​​such as 40%, 50%, etc., which can be obtained from the number of words in the question in each homework interface. The matching value of each page is determined according to the number of words in different questions on different pages.

[0104] Optionally, keyword recognition is performed on the last page area in the second area information in each of the working area images to determine whether there is a working area image that is not the same page number. If so, the abnormal working area is determined and a prompt message is output. The prompt message may be: Area A - abnormal number of pages.

[0105] Optionally, all text information in the second area information in each of the working area images is extracted and matched with the text information of the target interface acquired in the background. If the matching value is as high as 50%, it is confirmed that no working area image appears.

[0106] In some embodiments, the panoramic image is configured with a baseline, and the judging whether the working area image is in an abnormal state includes: determining the angle between a designated line of the working area image and the baseline; if the angle is greater than or equal to a second preset threshold, determining that the working area image is in an abnormal state; if the angle is less than the second preset threshold, determining that the working area image is in a normal state.

[0107] The reference line may be a straight line parallel to the panoramic image, and the straight line is divided into an upper and lower line and a left and right line.

[0108] The designated line may be a straight line parallel to the working area image, and the straight line may be divided into an upper and lower line and a left and right line.

[0109] Among them, it is reasonable that there is a certain inclination of the displayed font in human writing, but when the inclination is less than the normal inclination angle, it is in abnormal behavior. The angle between the designated line of the working area image and the reference line can be used to determine whether the text or pattern in the current working area image is abnormally tilted, causing the photographed working area image to be abnormal. At this time, the corresponding prompt information needs to be output, such as: Please readjust the placement position.

[0110] The second preset threshold may be 30 degrees, etc., which is not limited here.

[0111] In some embodiments, determining whether the work area image is in an abnormal state includes: determining whether a label area can be scanned in the work area image; if so, determining that the work area image is in a normal state; if not, determining that the work area image is in an abnormal state.

[0112] Among them, the above-mentioned label area can be a QR code identification area. Identification and authentication of the label area can quickly associate the homework information with the student identity. However, when the identification authentication fails, it may be that the label area is blocked or the identification information is damaged, resulting in unrecognizable situation. At this time, the corresponding prompt information needs to be output, such as: Please do not block the label.

[0113] It can be seen that through the above three verification methods, abnormal situations can be noticed at the first time, and accurate prompt information can be output in time for the teacher's reference. Then the teacher can prompt the students through the prompt information, which improves the accuracy and timeliness of the collection of homework learning information.

[0114] For example, if Figure 2E As shown, Figure 2E Schematic diagram of the display interface for collecting data pairs for all operations without abnormalities.

[0115] For example, the method according to this solution can be used in the following scenarios:

[0116] After the teacher has finished explaining a knowledge point in class, he or she can ask a question or select a question from the teaching aids / test paper at any time, so that students can do on-the-spot exercises in class. The student clears the handwriting board and writes down the answer to the teacher's current question (A). The camera device installed on the ceiling of the classroom collects the student's homework. When the camera is shooting, it will identify the area of ​​the homework clipboard in real time, highlight the area of ​​the homework clipboard, and Gaussian blur other areas, and present the acquired homework information in the display interface of the terminal device. The display interface will display the real-time picture of the homework clipboard that has been identified in the class, and count the number of identified homework clipboards in real time, as well as the total number of students in the class. Among them, after the camera captures the picture of the student's homework clipboard, it will automatically recognize the QR code on the homework clipboard, and analyze the student's student number, class, name and other information through the QR code, so that the homework picture can be associated with the student. The student's name is displayed in the upper left corner of the picture. After the shooting is completed, if there is no abnormality, the teacher can click the submit button to pass the collected homework data to the server through the network. After the images are collected, if the exercises are objective questions, the OCR technology can be used to identify the students' written content and then count them (for example, 40% for A, 20% for B, 10% for C, and 30% for D). In this way, the teacher can quickly and conveniently obtain the students' mastery of the knowledge. If they have not mastered it, the teacher can explain the knowledge point again. If everyone has mastered it, the teacher can quickly explain the next knowledge point. If it is a subjective question (such as a calculation question), after the images are collected, the teacher can randomly select a student's answer to explain it, without having to ask the student to go to the podium to do it again. This can improve the teacher's spot check efficiency and pay attention to the answers of more students.

[0117] Or it can be used for: After a class, the teacher says: Today's homework is to complete pages 17-18 of Sunshine Mathematics for Junior High School. After the students finish 17-18 pages of homework on the original teaching aids. The teacher starts to collect homework, asks students to open pages 17-18, and then put the teaching aids on the homework clipboard. The teacher opens the software on the computer or all-in-one machine and starts collecting the teaching aids homework. After the collection is completed, the students will automatically / manually correct it, and a homework learning report will be generated. For example, if Figure 2F As shown, Figure 2F This is one of the display diagrams of homework learning information. The teacher can also explain the homework during class, thus completing a closed loop of homework learning information collection and analysis.

[0118] The above scenarios are only examples, but they are all implemented using the method for collecting homework learning information proposed in this solution.

[0119] In the scheme implemented by the above-mentioned method, device, equipment and storage medium for collecting homework learning information, the terminal device of the homework learning information collection system first obtains the panoramic image taken by the camera in the learning area, and the learning area includes multiple homework clamps, and the homework clamps are used to clamp the homework pages to be checked. Secondly, according to the panoramic image, the area image corresponding to the homework clamp is extracted as the homework area image, and then the homework collection data is generated according to the homework area image. Finally, each of the homework collection data is sent to the server, so that the server generates homework learning information according to each of the homework collection data. Through the panoramic image collected by the camera, the information of the learning area can be fully obtained to avoid the situation of missing homework clamps, and the area image corresponding to the homework clamp is further extracted. The homework area image is processed, and then the complete and accurate homework collection data in the learning area is obtained, and accurate homework learning information is generated based on the accurate and complete homework collection data.

[0120] See also Figure 3 , Figure 3 Another flowchart of a method for collecting homework learning information provided by an embodiment of the present invention includes the following steps:

[0121] S31, obtaining a panoramic image captured by the camera in a learning area, wherein the learning area includes a plurality of work clamps, and the work clamps are used to clamp work pages to be checked.

[0122] S32. Extracting the homework writing information contained in the image of the homework area according to a preset image analysis algorithm.

[0123] S33, scanning the homework area image to obtain student identity information.

[0124] S34. Combine the homework writing information and the student identity information to obtain homework collection data.

[0125] S35. Generate operation acquisition data according to the operation area image.

[0126] S36. Send each of the homework collection data to the server, so that the server generates homework learning information according to each of the homework collection data.

[0127] In the scheme implemented by the above-mentioned method, device, equipment and storage medium for collecting homework learning information, the terminal device of the homework learning information collection system first obtains the panoramic image taken by the camera in the learning area, and the learning area includes multiple homework clamps, and the homework clamps are used to clamp the homework pages to be checked. Secondly, according to the panoramic image, the area image corresponding to the homework clamp is extracted as the homework area image, and then the homework collection data is generated according to the homework area image. Finally, each of the homework collection data is sent to the server, so that the server generates homework learning information according to each of the homework collection data. Through the panoramic image collected by the camera, the information of the learning area can be fully obtained to avoid the situation of missing homework clamps, and the area image corresponding to the homework clamp is further extracted. The homework area image is processed, and then the complete and accurate homework collection data in the learning area is obtained, and accurate homework learning information is generated based on the accurate and complete homework collection data.

[0128] The method of the present application is introduced above, and the device of the present application is introduced below.

[0129] See also Figure 4 , Figure 4 Schematic diagram of a device for collecting homework learning information provided by an embodiment of the present application. Figure 4 As shown, the device for collecting homework learning information includes:

[0130] An acquisition unit 401 is used to acquire a panoramic image captured by the camera in a learning area, wherein the learning area includes a plurality of work clamps, and the work clamps are used to clamp work pages to be checked;

[0131] An extraction unit 402 is used to extract a region image corresponding to the working clamping plate as a working region image according to the panoramic image;

[0132] A generating unit 403, configured to generate operation acquisition data according to the operation area image;

[0133] The sending unit 404 is used to send each of the homework collection data to the server, so that the server generates homework learning information according to each of the homework collection data.

[0134] In one embodiment, in the step of generating the operation acquisition data according to the operation area image, the generating unit 403 is further configured to:

[0135] extracting the operation writing information contained in the operation area image;

[0136] Scanning the homework area image to obtain student identity information;

[0137] The homework writing information and the student identity information are combined to obtain homework collection data.

[0138] In one embodiment, in extracting the area image corresponding to the work clamping plate according to the panoramic image as the work area image, the extracting unit 402 is further used to:

[0139] Performing contour recognition on the panoramic image to obtain a contour area, wherein the contour of the contour area is the contour of the work clamping plate;

[0140] Gaussian blur is performed on the area except the outline area in the panoramic image to obtain a working area image.

[0141] In one embodiment, before generating the operation acquisition data according to the operation area image, the generating unit 403 is further configured to:

[0142] Determining whether the working area image is in an abnormal state;

[0143] If so, mark the work area image and output prompt information;

[0144] If not, generate operation acquisition data according to the operation area image.

[0145] In one embodiment, in the process of determining whether the working area image is in an abnormal state, the generating unit 403 is further configured to:

[0146] extracting a plurality of keywords according to the work area image;

[0147] Matching the multiple keywords with the preset first information to obtain a target matching value;

[0148] If the target matching value is lower than a first preset threshold, it is determined that the working area image is in an abnormal state;

[0149] If the target matching value is higher than a first preset threshold, it is determined that the working area image is in a normal state.

[0150] In one embodiment, a reference line is configured in the panoramic image, and in determining whether the working area image is in an abnormal state, the generating unit 403 is further configured to:

[0151] Determining an angle between a designated line of the work area image and the reference line;

[0152] If the angle is greater than or equal to a second preset threshold, it is determined that the working area image is in an abnormal state;

[0153] If the angle is smaller than the second preset threshold, it is determined that the working area image is in a normal state.

[0154] In one embodiment, in the process of determining whether the working area image is in an abnormal state, the generating unit 403 is further configured to:

[0155] Determining whether a label area can be scanned in the working area image;

[0156] If it is scanned, it is determined that the image of the working area is in a normal state;

[0157] If it is not scanned, it is determined that the working area image is in an abnormal state.

[0158] In the scheme implemented by the above-mentioned method, device, equipment and storage medium for collecting homework learning information, the terminal device of the homework learning information collection system first obtains the panoramic image taken by the camera in the learning area, and the learning area includes multiple homework clamps, and the homework clamps are used to clamp the homework pages to be checked. Secondly, according to the panoramic image, the area image corresponding to the homework clamp is extracted as the homework area image, and then the homework collection data is generated according to the homework area image. Finally, each of the homework collection data is sent to the server, so that the server generates homework learning information according to each of the homework collection data. Through the panoramic image collected by the camera, the information of the learning area can be fully obtained to avoid the situation of missing homework clamps, and the area image corresponding to the homework clamp is further extracted. The homework area image is processed, and then the complete and accurate homework collection data in the learning area is obtained, and accurate homework learning information is generated based on the accurate and complete homework collection data.

[0159] See also Figure 5 , Figure 5 is a schematic diagram of the structure of a computer device provided in an embodiment of the present application, and the computer device may be a display. Figure 5 As shown, the computer device 50 includes a processor 501 and a memory 502. The memory 502 is connected to the processor 501, for example, via a bus.

[0160] The processor 501 is configured to support the computer device 50 to perform the corresponding functions in the method in the above method embodiment. The processor 501 can be a central processing unit (CPU), a network processor (NP), a hardware chip or any combination thereof. The above hardware chip can be an application specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The above PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0161] Specifically, the processor 501 may include a sending card, a receiving card and a driving chip.

[0162] The memory 502 is used to store program codes, etc. The memory 502 may include a volatile memory (VM), such as a random access memory (RAM); the memory 502 may also include a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD) or a solid-state drive (SSD); the memory 502 may also include a combination of the above-mentioned types of memories.

[0163] The processor 501 may call the program code to perform the following operations:

[0164] Acquire a panoramic image captured by a camera in a learning area, wherein the learning area includes a plurality of work clamps, and the work clamps are used to clamp work pages to be checked;

[0165] Extracting a region image corresponding to the working clamping plate according to the panoramic image as a working region image;

[0166] generating operation acquisition data according to the operation area image;

[0167] Send each of the homework collection data to the server, so that the server generates homework learning information according to each of the homework collection data.

[0168] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a computer, the computer executes the method described in the above embodiment.

[0169] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0170] The above disclosure is only the preferred embodiment of the present application, which certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application are still within the scope covered by the present application.

Claims

1. A method for collecting homework learning information, characterized in that: A terminal device applied to a homework learning information collection system, wherein the homework learning information collection system comprises a camera, a server and the terminal device; the method comprises: Acquire a panoramic image captured by the camera in a learning area, wherein the learning area includes a plurality of work clamps, and the work clamps are used to clamp work pages to be checked; Extracting a region image corresponding to the working clamping plate according to the panoramic image as a working region image; generating operation acquisition data according to the operation area image; Send each of the homework collection data to the server, so that the server generates homework learning information according to each of the homework collection data.

2. The method according to claim 1, characterized in that The generating of the operation acquisition data according to the operation area image comprises: extracting the operation writing information contained in the operation area image; Scanning the homework area image to obtain student identity information; The homework writing information and the student identity information are combined to obtain homework collection data.

3. The method according to claim 1, characterized in that The step of extracting the area image corresponding to the work clamping plate as the work area image according to the panoramic image comprises: Performing contour recognition on the panoramic image to obtain a contour area, wherein the contour of the contour area is the contour of the work clamping plate; Gaussian blur is performed on the area except the outline area in the panoramic image to obtain a working area image.

4. The method according to any one of claims 1 to 3, characterized in that: Before generating the operation acquisition data according to the operation area image, the method further includes: Determining whether the working area image is in an abnormal state; If so, mark the work area image and output prompt information; If not, generate operation acquisition data according to the operation area image.

5. The method according to claim 4, characterized in that The determining whether the working area image is in an abnormal state includes: extracting a plurality of keywords according to the work area image; Matching the multiple keywords with the preset first information to obtain a target matching value; If the target matching value is lower than a first preset threshold, it is determined that the working area image is in an abnormal state; If the target matching value is higher than a first preset threshold, it is determined that the working area image is in a normal state.

6. The method according to claim 4, characterized in that The panoramic image is configured with a reference line, and the determining whether the working area image is in an abnormal state includes: Determining an angle between a designated line of the work area image and the reference line; If the angle is greater than or equal to a second preset threshold, it is determined that the working area image is in an abnormal state; If the angle is smaller than the second preset threshold, it is determined that the working area image is in a normal state.

7. The method according to claim 4, characterized in that The determining whether the working area image is in an abnormal state includes: Determining whether a label area can be scanned in the working area image; If it is scanned, it is determined that the image of the working area is in a normal state; If it is not scanned, it is determined that the working area image is in an abnormal state.

8. A device for collecting homework learning information, characterized in that: A terminal device applied to a homework learning information collection system, wherein the homework learning information collection system comprises a camera, a server and the terminal device; the method comprises: An acquisition unit, used for acquiring a panoramic image captured by the camera in a learning area, wherein the learning area includes a plurality of work clamps, and the work clamps are used for clamping work pages to be checked; An extraction unit, configured to extract a region image corresponding to the working clamping plate as a working region image according to the panoramic image; A generating unit, configured to generate operation acquisition data according to the operation area image; The sending unit is used to send each of the homework collection data to the server, so that the server generates homework learning information according to each of the homework collection data.

9. A homework learning information collection system, characterized in that: It includes a camera, a terminal device and a server, wherein the terminal device is respectively connected to the camera and the server for communication; The camera is used to respond to the acquisition command sent by the terminal device to acquire a panoramic image of the learning area, wherein the learning area includes a plurality of work clamps, and the work clamps are used to clamp the work pages to be checked; The terminal device is used to receive the panoramic image sent by the camera, extract the area image corresponding to the work clamping plate as the work area image according to the panoramic image, generate work collection data according to the work area image, and send each of the work collection data to the server; The server is used to receive the homework collection data sent by the terminal device, and generate homework learning information according to the homework collection data.

10. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory is connected to the processor, and the processor is used to execute one or more computer programs stored in the memory. When the processor executes the one or more computer programs, the computer device implements the method according to any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 7.

Images