Classroom teaching analysis method, device and equipment and storage medium

Abstract

The invention discloses a classroom teaching analysis method and device, equipment and a storage medium. The method comprises the following steps: acquiring a courseware video stream corresponding to a course to be evaluated, the courseware video stream being a video stream divided according to each page of courseware; counting to obtain the duration of each page of courseware; counting the proportion of the courseware pages with the duration lower than the preset duration of the single page in the total courseware page, and recording the proportion as a first proportion; based on a preset model, a classroom analysis result is obtained, and an input factor of the preset model comprises the first proportion. The analysis process does not need to be carried out offline, and the concentration degree of teachers and students in a classroom cannot be affected.

Description

Technical Field

[0001] The present invention relates to the technical field of multimedia processing, and more specifically, to a classroom teaching analysis method, device, equipment, and storage medium. Background Art

[0002] Classroom teaching analysis can effectively identify problems existing in teachers and help teachers improve their teaching. Traditional teaching analysis usually occurs in the classroom and is analyzed by other offline teachers through listening and recording. However, this offline analysis method often requires sitting on the side of the classroom, which will affect the concentration of the students listening to the class and is not conducive to teachers carrying out teaching. Summary of the Invention

[0003] In order to solve the technical problem of difficult accurate teaching evaluation in the prior art, the present invention provides a classroom teaching analysis method, device, equipment, and storage medium. The technical solutions adopted by the present invention are as follows.

[0004] In a first aspect, the present invention provides a method for classroom analysis, including:

[0005] Obtaining a courseware video stream corresponding to a course to be evaluated, where the courseware video stream is a video stream divided according to each page of the courseware;

[0006] Statistically obtaining the duration of each page of the courseware;

[0007] Statistically obtaining the proportion of the courseware pages with a duration lower than the preset duration per page in the total number of courseware pages, denoted as the first proportion;

[0008] Based on a preset model, obtaining a classroom analysis result, where the input factor of the preset model includes the first proportion.

[0009] In an implementation manner, the process of statistically obtaining the proportion of the courseware pages with a duration lower than the preset duration per page, denoted as the first proportion, includes:

[0010] Calculating the preset duration per page;

[0011] The process of calculating the preset duration per page includes:

[0012] Obtaining a base duration;

[0013] Obtaining the number of page-turning actions during the duration of each courseware page;

[0014] Based on the base duration and the number of page-turning actions, obtaining the preset duration per page of each courseware page.

[0015] In an implementation manner, it further includes:

[0016] The last k pages of the courseware, or the subsequent n% of the pages, are divided into the latter part of the courseware, where both k and n are preset values;

[0017] Calculate the average duration of the pages in the latter part of the courseware, and calculate the average duration of all the pages in the courseware;

[0018] Calculate the ratio between the average duration of the pages in the latter part of the courseware and the average duration of all the pages in the courseware, denoted as the second ratio;

[0019] Among them, the input factor of the preset model further includes the second ratio.

[0020] In one implementation, it further includes:

[0021] Obtain a task duration list, where the task duration list is used to record the duration range of certain pages in the courseware;

[0022] Count the proportion of the pages in the courseware that meet the requirements of the task duration list, denoted as the third ratio;

[0023] Among them, the input factor of the preset model further includes the third ratio.

[0024] In one implementation, it further includes: the process of dividing the courseware video stream,

[0025] The process of dividing the courseware video stream includes:

[0026] Receive the courseware video stream;

[0027] When receiving the page-turning action information, intercept a frame of the courseware image from the video stream, and the timestamp information of the courseware image;

[0028] Extract the page number of the courseware image;

[0029] Judge whether the page number of the newly intercepted courseware image is the same as that of the previous courseware image;

[0030] When the page number of the newly intercepted courseware image is different from that of the previous courseware image, mark the timestamp information corresponding to the page number of the newly intercepted courseware image as the first type of timestamp information;

[0031] Divide the courseware video stream according to the first type of timestamp information to obtain the video stream divided according to each page of the courseware.

[0032] In one implementation, the process of extracting the page number of the courseware image includes:

[0033] Obtain a frame of detection picture from the courseware video stream;

[0034] Intercept candidate specific regions of the detection image, where the candidate specific regions are pre-defined regions and there are multiple candidate specific regions;

[0035] Use the OCR algorithm to detect the text boxes in each candidate specific region and obtain the recognition results of each candidate specific region;

[0036] Determine whether the identifiers in the recognition results of each candidate specific region exist in the pre-set page number identifier list, and determine the candidate specific regions with identifiers in the pre-set page number identifier list as page regions;

[0037] Use the OCR algorithm to detect the region in the courseware image with the same position as the page region, and obtain the recognition result of the page region of the courseware image;

[0038] Obtain the page number of the courseware image according to the recognition result of the page region of the courseware image.

[0039] In one implementation manner, the process of extracting the page number of the courseware image further includes:

[0040] Based on the relationship between the characters included in the recognition result of the page region of the detection image and the pre-set key characters, determine the style of the page annotation;

[0041] The process of obtaining the page number of the courseware image according to the recognition result of the page region of the courseware image includes:

[0042] Confirm the page number of the courseware image according to the numbers in the recognition result of the page region of the courseware image and the style of the page annotation.

[0043] In one implementation manner, it further includes:

[0044] When the page number of the newly intercepted courseware image is the same as the page number of the previous courseware image, mark the timestamp information corresponding to the page number of the newly intercepted courseware image as the second type of timestamp information;

[0045] Mark each piece of the second type of timestamp information in the video stream of each page of the courseware.

[0046] In one implementation manner, it further includes:

[0047] The page turning action information is generated based on receiving a page turning signal triggered by an external device or a situation where the degree of change in the image content of the slide video stream is greater than a threshold range.

[0048] In a second aspect, the present invention provides a device for classroom analysis, including:

[0049] An acquisition module for acquiring the courseware video stream corresponding to the course to be evaluated, where the courseware video stream is a video stream divided according to each page of the courseware;

[0050] A statistical module for statistically obtaining the duration of each page of the courseware; and statistically obtaining the proportion of the courseware pages with a duration lower than the preset duration per page in the total courseware pages, which is denoted as the first proportion.

[0051] An analysis module for obtaining a classroom analysis result based on a preset model, wherein the input factors of the preset model include the first proportion.

[0052] In a third aspect, the present invention provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method of any of the above embodiments is implemented.

[0053] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored. The program is characterized in that when it is executed by a processor, the method of any of the above embodiments is implemented.

[0054] In the present invention, the teaching rhythm of the teacher is obtained by using the teaching time of each page in the courseware, and the classroom teaching situation is analyzed from the side. The analysis process of the present invention does not need to be carried out offline and will not affect the concentration of the teacher and students in the classroom. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a schematic diagram of the overall process of an embodiment of the present invention.

[0056] Figure 2 is a schematic diagram of a partial process of an embodiment of the present invention.

[0057] Figure 3 is a schematic diagram of the detected picture of the first embodiment of the present invention.

[0058] Figure 4 is a schematic diagram of the overall structure of an embodiment of the second embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0059] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be fully conveyed to those skilled in the art.

[0060] It should be noted that the terms "first / second / ..." involved in the embodiments of the present invention are only used to distinguish similar objects and do not represent a specific order for the objects. It can be understood that "first / second / ..." can be interchanged with a specific order or sequence under allowable circumstances. It should be understood that the objects distinguished by "first / second / ..." can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can be implemented in an order other than those illustrated or described here.

[0061] Embodiment 1

[0062] Please refer to Figure 1 , Figure 1 which is a schematic flowchart of a method for classroom analysis provided by Embodiment 1 of the present invention. The method includes steps S110, S120, S130, and S140. It should be noted that steps S110, S120, S130, and S140 are only reference numerals used to clearly explain the correspondence between the embodiments and the Figure 1 drawings and do not represent a limitation on the order of each step in this embodiment.

[0063] Step S110: Obtain the courseware video stream corresponding to the course to be evaluated, where the courseware video stream is a video stream divided according to each page of the courseware;

[0064] Step S120: Statistically obtain the duration of each page of the courseware;

[0065] Step S130: Statistically obtain the proportion of the courseware pages with a duration lower than the preset duration per page in the total number of courseware pages, denoted as the first proportion;

[0066] Step S140: Based on a preset model, obtain the classroom analysis result, where the input factor of the preset model includes the first proportion.

[0067] This embodiment analyzes the teacher's performance in the classroom from the aspects of the process of the teacher using the courseware and the rhythm of the teacher using the courseware.

[0068] Through the process from step S110 to step S120, it can be known how long the teacher spends on each page when using the courseware for teaching. Theoretically, for most pages of the courseware made by the teacher, there is content, and the teacher needs to teach the content on these pages. Based on the above principle, in this method, a single-page preset duration is set, such as 5s. When the duration of a page of the courseware is lower than this single-page preset duration, it means that the teacher is skipping the content of this page. In step S130, the proportion of the skipped pages is counted, and this proportion of the skipped pages is the first proportion. In step S140, this first proportion is used as an input factor of the preset model to obtain the classroom analysis result. For example, in the model, if the proportion of pages with a duration lower than 5s is 10%, then 5 points are obtained; if the proportion of pages with a duration lower than 5s is 20 - 30%, then 4 points are obtained, etc.

[0069] In one implementation, the process of counting the proportion of the courseware pages with a duration lower than the single-page preset duration, denoted as the first proportion, includes: calculating the single-page preset duration;

[0070] The process of calculating the single-page preset duration includes:

[0071] Obtaining the basic duration;

[0072] Obtaining the number of page-turning actions within the continuous time period of each courseware page;

[0073] Based on the basic duration and the number of page-turning actions, the single-page preset duration of each courseware page is obtained.

[0074] For different pages of the courseware, some have more animations and require more page-turning actions to turn to the next page, while some only require one or two page-turning actions to turn to the next page. The more page-turning actions, the longer the time will be. This will result in a situation where although the teacher is also skipping a page of the courseware, the number of page-turning actions is too many, causing the duration to exceed the preset duration, and the resulting result is distorted. Therefore, it is not scientific to use the same single-page preset duration across the board. For this reason, in this implementation, two parts, namely the basic time and the additional time, are set. The additional time is determined according to the number of page-turning actions. The more page-turning actions, the longer the corresponding single-page preset duration, to avoid the above-mentioned distortion problem.

[0075] In one implementation, this method for classroom analysis further includes: step S210, step S220, and step S230.

[0076] Step S210: Divide the last k pages of the courseware, or the last n% of the pages, into the latter part of the courseware, where k and n are both preset values;

[0077] Step S220: Calculate the average duration of the pages in the latter part of the courseware and calculate the average duration of the overall pages of the courseware;

[0078] Step S230: Calculate the ratio between the average duration of the latter part of the courseware pages and the average duration of the overall courseware pages, denoted as the second ratio.

[0079] Among them, the input factor of the preset model also includes the second ratio.

[0080] When a teacher teaches a course, if the rhythm control is not good, it often happens that there is plenty of time in the front, the teaching is slower, and when it is almost time to finish the class, the speed suddenly accelerates, and the rhythm is uneven. In view of this situation, in this embodiment, a value k or n is preset. The latter k pages of the courseware are defined as the latter part of the courseware, or the latter n% of the courseware, such as 25%, is defined as the latter part of the courseware.

[0081] Step S220 calculates the average duration of the entire courseware pages, that is, the average duration of the overall courseware pages. Step S230 calculates the ratio between the average duration of the latter part of the pages and the average duration of the overall courseware pages, denoted as the second ratio. Finally, in the preset model of step S250, this second ratio is also used as an input factor to obtain the classroom analysis result. For example, in the model, if the average time of the content of the latter quarter of the teacher's courseware pages is less than 10% of the average time of the overall page numbers, 5 points are obtained; if it is less than 20% of the average time of the overall page numbers, 4 points are obtained; if it is less than 30% of the average time of the overall page numbers, 3 points are obtained, etc.

[0082] In one embodiment, the method for classroom analysis further includes: step S310 and step S320.

[0083] Step S310: Obtain a task duration list, where the task duration list is used to record the duration range of certain pages in the courseware;

[0084] Step S320: Count the proportion of the pages in the courseware that meet the requirements of the task duration list, denoted as the third ratio;

[0085] Among them, the input factor of the preset model also includes the third ratio.

[0086] For teacher teaching, there is always a part of the page content that is relatively important. Therefore, the lecture duration range of these pages is set in advance, and then these pages and their lecture duration ranges are recorded in a list, that is, the task duration list. Step S310 obtains this list, and step S320 counts how many pages of these pages taught by the teacher in the actual classroom fall within the preset duration range. The proportion of the counted page number to the total number of these pages is denoted as the third ratio. Finally, in the preset model of step S250, this third ratio is also used as an input factor to obtain the classroom analysis result.

[0087] This method uses the teaching time of each page in the courseware to determine whether the teacher's teaching rhythm is reasonable, and analyzes the classroom teaching situation from the side. The analysis process of this method does not need to be carried out offline and will not affect the concentration of teachers and students in the classroom.

[0088] In one implementation, the method for classroom analysis further includes: the process of dividing the courseware video stream;

[0089] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of the process of dividing the courseware video stream provided in Embodiment 1 of the present invention, including: step S410, step S420, step S430, step S440, step S450 and step S460.

[0090] Step S410, receiving the courseware video stream;

[0091] Step S420, when receiving the page-turning action information, intercepting a frame of courseware image from the video stream, and the timestamp information of the courseware image;

[0092] Step S430, extracting the page number of the courseware image;

[0093] Step S440, determining whether the page number of the newly intercepted courseware image is the same as the page number of the previous courseware image;

[0094] Step S450, when the page number of the newly intercepted courseware image is different from the page number of the previous courseware image, marking the timestamp information corresponding to the page number of the newly intercepted courseware image as the first type of timestamp information;

[0095] Step S460, dividing the courseware video stream according to the first type of timestamp information to obtain the video stream divided according to each page of the courseware.

[0096] In the current smart classroom, usually the courseware demonstration process during the teacher's lecture is recorded as a complete video file for later use such as taking screenshots of the courseware, displaying, and analyzing. In step S410, the recorded video stream is obtained. This implementation is used in the scenario of dividing each page of the courseware video during the teacher's lecture process.

[0097] When a page-turning signal triggered by an external device, such as a page-turning pen, a mouse, etc., or the degree of change in the image content of the video stream is greater than the threshold range, a page-turning action information will be generated. In step S420, when the page-turning action information is received, it means that a potential page-turning event has occurred. Why is this page-turning event called potential? Because there are many animations in a slide. During this process, a single page-turning signal from the page-turning pen may only trigger the animations on the same slide page without actually turning the page. Therefore, it is called potential. That is, in this potential page-turning event, it may actually be a real turn from page n to page n + 1, or it may just be an animation on page n. In this embodiment, regardless of whether it is a potential or an actual page turn, a frame of courseware image is intercepted from the video stream, and this intercepted frame of courseware image is the latest frame of courseware image. Since the purpose of this embodiment is to divide the courseware video into segments of video according to each page of the courseware, it is necessary to master the start time and end time of each segment of video (in actual operation, the end time of this page is the start time of the next page). Therefore, in addition to intercepting a frame of courseware image from the video stream, the time stamp corresponding to this frame of courseware image also needs to be saved.

[0098] In step S430, the page number of the courseware image is extracted. Generally, there are page number identifiers in the courseware, such as "page number", "page", etc. The OCR algorithm can be used to perform text recognition on the courseware image to obtain the recognition result of the page number.

[0099] In one embodiment, the process of extracting the page number of the courseware image in step S430 includes: step S431, step S432, step S433, step S434, step S435 and step S436.

[0100] Step S431, obtain a frame of detection picture from the courseware video stream;

[0101] Step S432, intercept the candidate specific regions of the detection picture, where the candidate specific regions are pre-defined regions and there are multiple candidate specific regions;

[0102] Step S433, use the OCR algorithm to detect the text boxes in each candidate specific region to obtain the recognition results of each candidate specific region;

[0103] Step S434, determine whether the recognition results of each candidate specific region exist in the identifiers in the preset page number identifier list, and determine the candidate specific regions with identifiers in the preset page number identifier list as the page regions;

[0104] Step S435, use the OCR algorithm to detect the region in the courseware image with the same position as the page region to obtain the recognition result of the page region of the courseware image;

[0105] Step S436: Obtain the page number of the courseware image according to the recognition result of the page area of the courseware image.

[0106] For the same set of courseware, the position of the page number is usually fixed. Therefore, by detecting a frame of courseware picture, the area of the page number position can be found. When the page number needs to be recognized later, only the text in this area needs to be detected. Based on the above principle, step S431 obtains a frame of detection picture for detecting the area of the page number position of this set of courseware.

[0107] Generally speaking, the page numbers of the courseware are usually marked in several specific areas, such as the lower right corner, the lower left corner, the middle position at the bottom, etc. As Figure 3 shown, Figure 3 is a schematic diagram of the detection picture, Figure 3 and the page number of the detection picture in

[0108] is marked in the lower right corner. Therefore, in steps S432 and S433, only these areas are detected. In steps S432 and S433, taking advantage of the characteristic that the page numbers of the courseware are marked in several specific position areas, several areas are pre-designated as candidate specific areas, and then these several small areas are intercepted. The text boxes of these several small areas are detected by using the OCR algorithm to obtain the recognition results of each candidate specific area. Compared with extracting the text boxes of the entire detection picture, only several small areas are detected in this embodiment, which can greatly save the cost.

[0109] After detecting the recognition results of the text boxes of these several small areas, it is necessary to find out one area that actually marks the page number among these small areas, that is, to find out the actual page area. In step S434, a page number identifier list is preset. This list contains some key characters that can be expressed as page numbers, such as page, page, " / ", "|", and numbers. If an identifier in the preset page number identifier list exists in the candidate specific area, then this area is the actual page area we need to find.

[0110] It should be noted here that these key characters can be used alone or in combination. For example, when using " / " or "|", there must be numbers before and after to trigger the key character.

[0111] As mentioned above, for the same set of courseware, the position of the page number is usually fixed. Steps S435 and S436 use the OCR algorithm to detect the area in the courseware image that is at the same position as the page area, and then obtain the recognition result and extract the page number of the area, which is the page number of the courseware image.

[0112] In this implementation, the page numbers of the courseware are marked in certain specific location areas, and several areas are pre-demarcated as candidate specific areas. Then, the OCR algorithm is used to detect the text boxes of these several small areas, and one of the identifiers in the preset page number identifier list is found in the text boxes of these small areas, and this area is determined as the real page area. Finally, the page number of this page area is extracted as the page number of the courseware image. This implementation can accurately find the page numbers marked in the courseware video, and does not require high computing power, so it is convenient and practical.

[0113] In one implementation, the process of extracting the page number of the courseware image in step S430 further includes: step S437.

[0114] Step S437, determining the style of the page annotation based on the relationship between the characters included in the recognition result of the page area of ​​the detected image and the preset key characters;

[0115] The process of obtaining the page number of the courseware image according to the recognition result of the page area of ​​the courseware image in step S436 includes:

[0116] The page number of the courseware image is confirmed based on the numbers in the recognition result of the page area of ​​the courseware image and the style of the page marking.

[0117] Preset key characters, such as " / ", "|", page, etc. Figure 3 As shown, when " / " is detected, the page marking style is: current page number / total number of pages, then the number before " / " can be confirmed as the page number of the detected image. For another example, if only the word "第" is detected, and no " / " or "|" is detected, then the page marking style is: "第"+current page number+"页". In step S437, the page marking style is obtained through some key characters.

[0118] The specific process of step S436 is to obtain the specific page number through the page annotation style. Continuing with the previous style: "No." + current page number + "page" example, the number after "No." can be confirmed as the page number of the detected image.

[0119] Steps S440 to S460 are to verify whether the process of actually turning from page n to page n + 1 has occurred. At this time, step S430 extracts the page number of the latest page just intercepted, step S440 obtains the page number of the previous page screen, and step S450 compares the page numbers of these two page screens. If the page numbers are different, it means that it has actually turned from page n to page n + 1. At this time, the timestamp information corresponding to the page number of the newly intercepted courseware image is marked as the first type of timestamp information for further use later.

[0120] In fact, the time period experienced by one page of the courseware is between each piece of the first type of timestamp information. Additionally, through the recognized page numbers, the time length occupied by each page of the courseware can be marked. Step S460 divides the courseware video stream in this way to obtain the video stream divided according to each page of the courseware.

[0121] It should be noted here that the page number obtained in step S440 is only the page number of the previous courseware image, and there is no restriction on how the page number is obtained. One can directly take out that picture and recognize it again, or obtain the data obtained when performing step S430 before.

[0122] In this embodiment, by comparing the page number of the new screenshot generated by the suspected page turning action with the previous page number, it is determined whether the suspected page turning action in the video has actually caused the courseware to turn pages. When a page turning action occurs, the corresponding timestamp is recorded, so that the video can be divided according to the pages. The process of dividing the video by this method has low requirements for computing power and is convenient and practical.

[0123] Embodiment 2

[0124] Corresponding to the method of Embodiment 1, as Figure 4 shown, the present invention also provides a classroom analysis device 5, including: an acquisition module 510, a statistics module 520, and an analysis module 530.

[0125] The acquisition module 510 is configured to acquire the courseware video stream corresponding to the course to be evaluated, where the courseware video stream is a video stream divided according to each page of the courseware;

[0126] The statistics module 520 is configured to statistically obtain the duration of each page of the courseware; statistically obtain the proportion of the courseware pages with a duration lower than the single - page preset duration in the total courseware pages, and record it as the first proportion;

[0127] The analysis module 530 is configured to obtain a classroom analysis result based on a preset model, where the input factors of the preset model include the first proportion.

[0128] In one embodiment, the statistics module is further configured to calculate the single - page preset duration;

[0129] The process of calculating the preset duration of a single page includes:

[0130] Obtain the basic duration;

[0131] Obtain the number of page-turning actions within the continuous time period of each courseware page;

[0132] Based on the basic duration and the number of page-turning actions, obtain the preset duration of a single page for each courseware page.

[0133] In one implementation, the statistics module is further configured to divide the last k pages of the courseware, or the subsequent n% of the pages, into the latter part of the courseware, where both k and n are preset values; calculate the average duration of the pages in the latter part of the courseware, calculate the average duration of all the pages in the courseware; calculate the ratio between the average duration of the pages in the latter part of the courseware and the average duration of all the pages in the courseware, denoted as the second ratio;

[0134] Among them, the input factor of the preset model further includes the second ratio.

[0135] In one implementation, the statistics module is further configured to obtain a task duration list, where the task duration list is used to record the duration range of certain pages in the courseware; count the proportion of pages in the courseware that meet the requirements of the task duration list, denoted as the third ratio;

[0136] Among them, the input factor of the preset model further includes the third ratio.

[0137] In one implementation, the device for classroom analysis further includes: a unit for obtaining the page numbers in the video;

[0138] The unit for obtaining the page numbers in the video includes:

[0139] A receiving module, configured to receive the courseware video stream; when receiving the page-turning action information, intercept a frame of the courseware image from the video stream, and the timestamp information of the courseware image;

[0140] An extraction module, configured to extract the page number of the courseware image;

[0141] A comparison module, configured to determine whether the page number of the newly intercepted courseware image is the same as the page number of the previous courseware image;

[0142] An archiving module, configured to, when the page number of the newly intercepted courseware image is different from the page number of the previous courseware image, mark the timestamp information corresponding to the page number of the newly intercepted courseware image as the first type of timestamp information;

[0143] A generation module, configured to divide the courseware video stream according to the first type of timestamp information, and obtain the video stream divided according to each page of the courseware.

[0144] In one implementation, the process of the extraction module extracting the page numbers of the courseware images includes:

[0145] Obtain a frame of detection picture from the courseware video stream;

[0146] Intercept candidate specific regions of the detection picture, where the candidate specific regions are pre-defined regions and there are multiple candidate specific regions;

[0147] Use the OCR algorithm to detect the text boxes in each candidate specific region to obtain the recognition results of each candidate specific region;

[0148] Determine whether the recognition results of each candidate specific region contain identifiers in a preset page number identifier list, and determine the candidate specific regions containing identifiers in the preset page number identifier list as page regions;

[0149] Use the OCR algorithm to detect the regions in the courseware image with the same position as the page region to obtain the recognition result of the page region of the courseware image;

[0150] Obtain the page numbers of the courseware images according to the recognition results of the page regions of the courseware images.

[0151] In one implementation, the process of extracting the page numbers of the courseware images further includes:

[0152] Determine the style of page annotation based on the relationship between the characters included in the recognition result of the page region of the detection picture and the preset key characters;

[0153] The process of obtaining the page numbers of the courseware images according to the recognition results of the page regions of the courseware images includes:

[0154] Confirm the page numbers of the courseware images according to the numbers in the recognition results of the page regions of the courseware images and the style of page annotation.

[0155] In one implementation, the archiving module is further configured to, when the page numbers of newly intercepted courseware images are the same as those of the previous courseware image, mark the timestamp information corresponding to the page numbers of the newly intercepted courseware images as the second type of timestamp information; mark each second type of timestamp information in the video stream of each page of the courseware.

[0156] In one implementation, the page turning action information is generated based on receiving a page turning signal triggered by an external device or a situation where the degree of change in the image content of the slide video stream is greater than a threshold range.

[0157] In this device, by using the teaching time of each page in the courseware, it is possible to determine whether the teacher's teaching rhythm is reasonable, and the classroom teaching situation can be analyzed from the side. The analysis process of this device does not need to be carried out offline and will not affect the concentration of the teacher and students in the classroom.

[0158] Embodiment III

[0159] The embodiment of the present invention also provides a storage medium, on which computer instructions are stored, and when the instructions are executed by a processor, the method for classroom analysis of any of the above embodiments is implemented.

[0160] Those skilled in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: removable storage devices, random access memory (RAM), read-only memory (ROM), magnetic disks or optical disks and other various media that can store program codes.

[0161] Alternatively, if the above integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiment of the present invention essentially or the part that contributes to the related technology can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a terminal, or a network device, etc.) to execute all or part of the methods of the various embodiments of the present invention. And the foregoing storage medium includes: removable storage devices, RAM, ROM, magnetic disks or optical disks and other various media that can store program codes.

[0162] Corresponding to the above computer storage medium, in one embodiment, a computer device is also provided. The computer device includes a memory, an encoder, and a computer program stored on the memory and executable on the encoder. When the encoder executes the program, it implements any one of the classroom analysis methods in the above embodiments.

[0163] The above computer device uses the teaching time of each page in the courseware to determine whether the teacher's teaching rhythm is reasonable, and analyzes the classroom teaching situation from the side. The analysis process of this computer device does not need to be carried out offline and will not affect the concentration of the teacher and students in the classroom.

[0164] The technical features of the above-described embodiments may be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as falling within the scope described in this specification.

[0165] Obviously, the above embodiments of the present invention are merely examples given for clearly illustrating the present invention, rather than limiting the implementation manners of the present invention. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all implementation manners here. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the claims of the present invention.

Claims

1. A method of classroom analysis, characterized in that: include: Obtaining the courseware video stream corresponding to the course to be evaluated, wherein the courseware video stream is a video stream divided according to each page of the courseware; Statistically determine the duration of each page of courseware; Count the proportion of courseware pages that are shorter than the preset single-page duration to the total courseware pages, and record it as the first proportion; Based on a preset model, a classroom analysis result is obtained, wherein the input factors of the preset model include the first ratio.

2. The classroom analysis method according to claim 1, characterized in that: The process of counting the proportion of courseware pages with a duration shorter than the preset single-page duration to the total courseware pages, recorded as the first proportion, includes: Calculate the preset duration of a single page; The process of calculating the preset duration of a single page includes: Get the basic duration; Get the number of page turning actions within the duration of each courseware page; According to the basic duration and the number of page-turning actions, the preset duration of a single page of each courseware page is obtained.

3. The classroom analysis method according to claim 1, characterized in that: Also includes: The last k pages of the courseware, or the last n% of the pages, are divided into the last part of the courseware, wherein k and n are both preset values; Calculate the average duration of the pages at the end of the courseware and the average duration of the entire page of the courseware; Calculate the ratio between the average duration of the pages in the latter part of the courseware and the average duration of the pages in the entire courseware, and record it as the second ratio; Wherein, the input factors of the preset model also include the second ratio.

4. The classroom analysis method according to claim 1, characterized in that: Also includes: Obtaining a task duration list, wherein the task duration list is used to record the duration range of certain pages in the courseware; The percentage of pages in the courseware that meet the requirements of the task duration list is counted as the third ratio; Wherein, the input factors of the preset model also include the third ratio.

5. The classroom analysis method according to any one of claims 1 to 4, characterized in that: Also includes: The process of dividing the courseware video stream, The process of dividing the courseware video stream includes: Receive courseware video stream; When receiving the page turning action information, intercepting a frame of courseware image from the video stream, and the timestamp information of the courseware image; Extracting the page number of the courseware image; Determine whether the page number of the newly captured courseware image is the same as the page number of the previous courseware image; When the page number of the newly captured courseware image is different from the page number of the previous courseware image, the timestamp information corresponding to the page number of the newly captured courseware image is marked as the first type of timestamp information; The courseware video stream is divided according to the first type of timestamp information to obtain the video stream divided according to each page of the courseware.

6. The method for dividing courseware video streams according to claim 5, characterized in that: The process of extracting the page number of the courseware image includes: Get a frame of detection picture from the courseware video stream; Intercepting a candidate specific area of ​​the detection image, wherein the candidate specific area is a pre-demarcated area, and there are multiple candidate specific areas; Using the OCR algorithm, the text box of each candidate specific area is detected to obtain the recognition result of each candidate specific area; Determine whether the recognition result of each candidate specific area contains an identifier in a preset page number identifier list, and determine the candidate specific area containing the identifier in the preset page number identifier list as the page area; Using an OCR algorithm to detect the area in the courseware image that is located at the same position as the page area, and obtaining a recognition result of the page area of ​​the courseware image; According to the recognition result of the page area of ​​the courseware image, the page number of the courseware image is obtained.

7. The method for dividing courseware video streams according to claim 6, characterized in that: The process of extracting the page number of the courseware image also includes: Determine the style of page annotation based on the relationship between the characters included in the recognition result of the page area of ​​the detected image and the preset key characters; The process of obtaining the page number of the courseware image according to the recognition result of the page area of ​​the courseware image includes: The page number of the courseware image is confirmed based on the numbers in the recognition result of the page area of ​​the courseware image and the style of the page marking.

8. The method for dividing courseware video streams according to claim 6, characterized in that: Also includes: When the page number of the newly captured courseware image is the same as the page number of the previous courseware image, the timestamp information corresponding to the page number of the newly captured courseware image is marked as the second type of timestamp information; The second type of timestamp information is marked on the video stream of each page of the courseware.

9. The method for dividing courseware video streams according to claim 6, characterized in that: Also includes: The page turning action information is generated based on receiving a page turning signal triggered by an external device, or a situation where the image content change degree of the slide video stream is greater than a threshold range.

10. A device for classroom analysis, characterized in that: include: An acquisition module is used to acquire the courseware video stream corresponding to the course to be evaluated, wherein the courseware video stream is a video stream divided according to each page of the courseware; The statistical module is used to calculate the duration of each page of courseware; calculate the proportion of courseware pages with a duration shorter than the preset duration of a single page to the total courseware pages, which is recorded as the first proportion; An analysis module is used to obtain classroom analysis results based on a preset model, wherein the input factors of the preset model include the first ratio.

11. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.

Images