Job generation method and device, equipment and storage medium
By obtaining and analyzing students' learning status data at specific knowledge points, determining students' mastery level and generating personalized homework, the problem of unreasonable homework in the existing teaching model is solved and teaching efficiency is improved.
Patent Information
- Application Number
- CN202311129216.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-09-01
- Publication Date
- 2025-03-11
AI Technical Summary
In the existing teaching model, it is difficult for teachers to understand each student's learning situation, resulting in the assignments assigned are not reasonable enough and inefficient.
By obtaining the target knowledge point and the user status data of the target user in the target period corresponding to the knowledge point, the user's degree of mastery of the knowledge point is determined, and personalized homework is generated based on this degree.
It realizes personalization of homework, fits the user's mastery, reduces the time and energy of teachers when assigning homework, and improves teaching efficiency.
Smart Images
Figure CN119597965A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of educational technology, and in particular to a homework generation method, apparatus, device and storage medium. Background Art
[0002] In the current teaching model, the generation of homework mainly relies on teachers to complete it manually. After the class, the teacher will select questions corresponding to the course content based on the course content taught in class and his or her own evaluation, organize them into homework, and then distribute them to students through various means (such as paper printing, email, teaching management system, etc.).
[0003] Since all students have to complete the same homework, it is difficult for teachers to understand the learning situation of all students when assigning homework. The assigned homework is not suitable for all students, resulting in unreasonable assignments for individual students. If teachers understand the learning situation of each student and assign homework to each student separately, it will waste a lot of teachers' time and be inefficient. Summary of the invention
[0004] The present application provides a homework generation method, apparatus, device and storage medium to solve the technical problem of low efficiency caused by teachers assigning homework to each student individually.
[0005] In a first aspect, a method for generating a job is provided, comprising:
[0006] Acquire user status data of a target knowledge point and a target user in a target time period corresponding to the target knowledge point, wherein the user status data is used to reflect the user status of the target user in the target time period;
[0007] Determining the target user's mastery of the target knowledge point according to the user status data;
[0008] Based on the mastery level, a homework corresponding to the target knowledge point is generated for the target user.
[0009] In this technical solution, the target knowledge point and the user status data of the target user in the target time period corresponding to the target knowledge point are first obtained, and then the target user's mastery of the target knowledge point is determined based on the user status data; finally, based on the user's mastery of the target knowledge point, an assignment corresponding to the target knowledge point is generated for the target user, so that the assignment generated for the user can fit the user's mastery of the knowledge point and meet the user's personalized needs; in addition, the user status data is automatically obtained to determine the user's mastery of the knowledge point and then generate personalized assignments for the user, without the need for teacher participation, which can save teachers' time in assigning homework and improve efficiency.
[0010] In conjunction with the first aspect, in a possible implementation, obtaining the user status data of the target user in the target time period corresponding to the target knowledge point includes: obtaining target video data of the target user in the target time period; performing behavior recognition and / or facial expression recognition on each frame of the target video data to obtain the user status data. Obtaining the user status data by image recognition can accurately obtain the user status data.
[0011] In combination with the first aspect, in a possible implementation, the user status data is used to reflect the behavior status of the target user in the target time period; the determination of the target user's mastery of the target knowledge point based on the user status data includes: determining the target behavior status of the target user in the target time period and the first status score corresponding to the target behavior status based on the user status data, the first status score is used to reflect the target user's concentration on the knowledge point under the target behavior status; determining the target user's mastery of the target knowledge point based on the first status score, the mastery is positively correlated with the first status score. By converting the user status data reflecting the user's behavior status into a concentration score, and then determining the user's mastery of the knowledge point, the user's mastery of the knowledge point can be accurately evaluated.
[0012] In combination with the first aspect, in a possible implementation method, determining the target user's mastery of the target knowledge point based on the first state score includes: calculating the ratio between the duration of each target behavior state within the target time period and the total duration of the target time period, and obtaining the behavior time ratio corresponding to each target behavior state; using the behavior time ratio corresponding to each target behavior state as the weight coefficient corresponding to each target behavior state, and performing weighted summation on the first state scores corresponding to each target behavior state to obtain the target user's total behavior state score within the target time period; determining the ratio between the behavior state total score and the maximum behavior state total score as the target user's mastery score of the target knowledge point.
[0013] In combination with the first aspect, in a possible implementation, the user status data is used to reflect the emotional state of the target user in the target time period; the determination of the target user's mastery of the target knowledge point based on the user status data includes: determining the target emotional state of the target user in the target time period and a second state score corresponding to the target emotional state based on the user status data, the second state score is used to reflect the target user's understanding of the knowledge point in the target emotional state; determining the target user's mastery of the target knowledge point based on the second state score, the mastery being positively correlated with the second state score. By converting the user status data reflecting the user's emotional state into an understanding score, and then determining the user's mastery of the knowledge point, the user's mastery of the knowledge point can be accurately evaluated.
[0014] In combination with the first aspect, in a possible implementation method, determining the target user's mastery of the target knowledge point based on the second state score includes: calculating the ratio between the duration of each target emotional state within the target time period and the total duration of the target time period, and obtaining the emotional duration ratio corresponding to each target emotional state; using the emotional duration ratio corresponding to each target emotional state as the weight coefficient corresponding to each target emotional state, and performing weighted summation on the second state scores corresponding to each target emotional state to obtain the target user's total emotional state score within the target time period; determining the ratio between the emotional state total score and the maximum emotional state total score as the target user's mastery score of the target knowledge point.
[0015] In combination with the first aspect, in a possible implementation, the user status data is used to reflect the behavior state and emotional state of the target user in the target time period; the determination of the target user's mastery of the target knowledge point based on the user status data includes: determining the target behavior state of the target user in the target time period and a first state score corresponding to the target behavior state, and the target emotional state of the target user in the target time period and a second state score corresponding to the target emotional state according to the user status data, the first state score is used to reflect the target user's concentration on the knowledge point in the target behavior state, and the second state score is used to reflect the target user's understanding of the knowledge point in the target emotional state; the target user's mastery of the target knowledge point is determined according to the first state score and the second state score. By converting the user status data reflecting the user's behavior state into a concentration score, and converting the user status data reflecting the user's situation state into an understanding score, the user's mastery of the knowledge point can be accurately evaluated.
[0016] In combination with the first aspect, in a possible implementation method, determining the target user's mastery of the target knowledge point based on the first state score and the second state score includes: taking a weighted sum of the first state score and the second state score to obtain a total state score corresponding to the target knowledge point; and determining the ratio between the total state score and the maximum total state score as the target user's mastery score of the target knowledge point.
[0017] In combination with the first aspect, in a possible implementation, generating the homework corresponding to the target knowledge point for the target user according to the mastery level includes: determining a target mastery level, the target mastery level being the mastery level to which the target user's mastery of the target knowledge point belongs; and extracting homework titles belonging to the target knowledge point and corresponding to the target mastery level from a preset homework title library as the homework corresponding to the target knowledge point. By extracting homework titles corresponding to the mastery level to which the user's mastery level belongs as the corresponding homework, the homework can be made to meet the user's learning situation.
[0018] In a second aspect, a job generation device is provided, comprising:
[0019] A data acquisition module, used to acquire user status data of a target knowledge point and a target user in a target period corresponding to the target knowledge point, wherein the user status data is used to reflect the user status of the target user in the target period;
[0020] A mastering degree determination module, used to determine the mastering degree of the target user on the target knowledge point according to the user status data;
[0021] The topic generation module is used to generate homework corresponding to the target knowledge point for the target user according to the mastery level.
[0022] In a third aspect, a computer device is provided, comprising a memory and one or more processors, wherein the memory is connected to the one or more processors, and the one or more processors are used to execute one or more computer programs stored in the memory, and when the one or more processors execute the one or more computer programs, the computer device implements the job generation method of the first aspect.
[0023] According to a fourth aspect, a computer-readable storage medium is provided, 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 job generation method according to the first aspect.
[0024] The present application can achieve the following technical effects: the homework generated for the user can be in line with the user's mastery of the knowledge points and meet the user's personalized needs; in addition, by automatically obtaining user status data to determine the user's mastery of the knowledge points and then generating personalized homework for the user, no teacher participation is required, which can save teachers' time in assigning homework and improve efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0025] Figure 1 A schematic diagram of the system architecture of an operating system provided in an embodiment of the present application;
[0026] Figure 2 A flowchart of a method for generating a job provided in an embodiment of the present application;
[0027] Figure 3 A schematic diagram of a convolutional neural network provided in an embodiment of the present application;
[0028] Figure 4 It is a structural schematic diagram of a job generation device provided in an embodiment of the present application;
[0029] Figure 5 It is a structural diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0030] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.
[0031] The technical solution of the present application is applicable to teaching scenarios, and the technical solution of the present application is applicable to generating personalized homework for students in teaching scenarios.
[0032] For ease of understanding, the operating system of this application is first introduced.
[0033] See also Figure 1 , Figure 1 A schematic diagram of the system architecture of an operating system provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the homework system 10 includes a data acquisition device 101 and a data processing device 102, wherein the data acquisition device 101 is arranged in a specific teaching space for conducting teaching, and is used to collect various data related to the teaching scene, and send the collected data to the data processing device 102. The data acquisition device 101 can be used to collect teacher data, such as the teacher's voice and behavior in the classroom, the knowledge points taught by the teacher in the classroom, etc.; the data acquisition device 101 can also be used to collect student data, such as the student's voice and behavior, facial expressions, etc. in the classroom.
[0034] Teaching scenes can be divided into offline teaching scenes and online teaching scenes according to different teaching spaces. When the teaching scene is an offline teaching scene, the data acquisition device 101 can be arranged in the classroom. The data acquisition device 101 can specifically include audio and video equipment and cameras in the classroom, wherein the audio and video equipment can include a display screen, a microphone, etc. in the classroom, and there can be multiple cameras, which can be respectively arranged in multiple positions in the classroom for shooting video images in the classroom; in a specific implementation scheme, there can be two cameras, which are respectively arranged in the front and back positions of the classroom. When the teaching scene is an offline teaching scene, the data acquisition device 101 can be respectively arranged in the space where the teacher and the user are located. The data acquisition device 101 can specifically include cameras, microphones, and computer equipment used by teachers in class, etc.
[0035] The data processing device 102 is connected to the data acquisition device 101, and is used to analyze various data collected by the data acquisition device 101, determine the knowledge points taught by the teacher in class and the status of the students in class, and generate personalized homework for the students according to the status of the students in class. The data processing device 102 may include a remote server, a homework topic database, etc.
[0036] based on Figure 1 The operating system shown can implement the technical solution of the present application, and the technical solution of the present application can be specifically applied to the data processing device 102.
[0037] The technical solution of this application is described in detail below.
[0038] See also Figure 2 , Figure 2 A flowchart of a method for generating a job provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the method comprises the following steps:
[0039] S201, obtaining user status data of a target knowledge point and a target user in a target time period corresponding to the target knowledge point.
[0040] Here, the target knowledge point is the knowledge point taught by the teacher in the classroom. The target knowledge point can be the knowledge point taught by the teacher in the online classroom or the knowledge point taught by the teacher in the offline classroom. When the teaching scene is an online teaching scene, the audio data of the teacher's lecture can be obtained through the microphone arranged in the space where the teacher is located, and the courseware content of the teacher's lecture can be obtained through the computer used by the teacher to teach, and the target knowledge point can be obtained by combining the audio data and courseware content of the teacher's lecture. When the teaching scene is an offline teaching scene, the audio data of the teacher's lecture can be obtained through the microphone arranged in the classroom, and the courseware content of the teacher's lecture can be obtained through the display screen in the classroom, and the target knowledge point can be obtained by combining the audio data and courseware content of the audio teacher's lecture.
[0041] For example, when a teacher is giving a lecture in an offline class, by obtaining the courseware content displayed on the display screen in the classroom, it is determined that the courseware content displayed on the display screen in the classroom during the period of 10:00:00-10:25:00 is related to Newton's third law. By obtaining the audio data of the teacher in the classroom, it is determined that Newton's third law frequently appears in the teacher's audio data during the period of 10:00:00-10:25:00. Then, the target knowledge point can be determined to be Newton's third law, and the target time period corresponding to the target knowledge point can be determined to be 10:00:00-10:25:00.
[0042] The target user can be any student who is learning the target knowledge point in the classroom. The user status data of the target user in the target time period corresponding to the target knowledge point is used to reflect the user status of the target user in the target time period. The target time period can be determined according to the target knowledge point, and the user status of the target user in the target time period may include the behavior status, emotional state, etc. of the target user in the target time period.
[0043] The user status data of the target user in the target time period corresponding to the target knowledge point can be obtained through the following steps A1-A2:
[0044] A1. Obtain target video data of a target user in a target time period corresponding to a target knowledge point.
[0045] Here, when the teaching scene is an online teaching scene, the target video data of the target user in the target time period corresponding to the target knowledge point can be obtained through the camera deployed in the space where the target user is located; when the teaching scene is an offline teaching scene, the target video data of the target user in the target time period corresponding to the target knowledge point can be obtained through the camera deployed in the classroom. Among them, the video data of the target user can be obtained in real time through the camera deployed in the space where the target user is located or in the classroom; the video data belonging to the target time period is determined from the video data of the target user as the target video data.
[0046] A2. Performing behavior recognition and / or facial expression recognition on each frame of the target video data to obtain user status data of the target user in a target time period corresponding to the target knowledge point.
[0047] Here, the behavior recognition model and / or facial expression recognition model obtained by pre-training can be used to perform behavior recognition and / or facial expression recognition on each frame of the target video data to obtain the user status data of the target user in the target time period corresponding to the target knowledge point. The user status data of the target user in the target time period corresponding to the target knowledge point includes the behavior status data of the target user in each frame of the target video data and / or the emotional state data of the target user in each frame of the target video data. The behavior status data is used to reflect the behavior status of the target user, and the behavior status of the target user can be divided into raising hands, sitting upright, lowering the head, sleeping, and sideways. The behavior status can be used to reflect the user's concentration on the knowledge point. For example, the behavior status includes five behavior states: raising hands, sitting upright, lowering the head, sleeping, and sideways. Then, the concentration level corresponding to raising hands>the concentration level corresponding to sitting upright>the concentration level corresponding to lowering the head>the concentration level corresponding to sideways>the concentration level corresponding to sleeping. The emotional state data is obtained based on the recognition of the facial expression of the target user, and is used to reflect the emotional state of the target user. The emotional state of the target user can be divided into seriousness, doubt, surprise, and sadness. The emotional state can be used to reflect the user's understanding of the knowledge point. For example, if the emotional states include seriousness, doubt, surprise and sadness, then the degree of understanding corresponding to seriousness > the degree of understanding corresponding to surprise > the degree of understanding corresponding to doubt > the degree of understanding corresponding to sadness.
[0048] The target user's behavior state data in each frame of the target video data and / or the target user's emotional state data in each frame of the target video data can be saved according to the frame sequence of the image, and different frame sequences correspond to different time points. For example, a total of 1000 frames of images are acquired in the target time period, and the frame sequences of the images are 1 to 1000, respectively. Then the target user's behavior state data in each frame of the target video data and / or the target user's emotional state data in each frame of the target video data can be expressed as {image 1: behavior state 1, emotional state 1}, {image 2: behavior state 2, emotional state 2}, ..., {image 1000: behavior state 1000, emotional state 1000}.
[0049] In some possible situations, when there are multiple users in the image in the target video data, the position of the target user in each frame of the image can be first identified based on identity recognition technology (such as face recognition, etc.), and behavior recognition and / or facial expression recognition can be performed on each frame of the image according to the position of the target user in each frame of the image.
[0050] In some possible situations, when a large number of frames of images are obtained in the target video data during the target time period, the target video data can be first extracted, and then behavior recognition and / or facial recognition can be performed on each frame of the image obtained by extraction to obtain the user status data of the target user during the target time period corresponding to the target knowledge point.
[0051] In some possible cases, in the process of performing behavior recognition on each frame of the target video image data, the skeleton feature points of the target user in each frame of the image can be extracted by the OpenPose algorithm, and then the extracted skeleton feature points are input into the convolutional neural network for behavior state recognition to obtain the behavior state of the target user in each frame of the target video image data. The convolutional neural network can include three layers of convolutional layers connected in sequence and three layers of fully connected layers connected in sequence. The structure of the convolutional neural network can be as follows: Figure 3 As shown in the figure, by combining OpenPose with a convolutional neural network to identify the user's behavior state, the accuracy of behavior state recognition can be improved.
[0052] In the above steps A1-A2, the user status data is obtained by image recognition, which can accurately obtain the user status data, and then the user's mastery of the knowledge points can be accurately determined according to the user status data.
[0053] S202, determining the target user's mastery of the target knowledge point according to the target user's state data in the target time period corresponding to the target knowledge point.
[0054] In the case where the user status data includes the behavior status data of the target user in each frame of the target video data, the user status data is used to reflect the behavior status of the target user in the target time period; the mastery degree of the target user on the target knowledge point can be determined through the following steps B1-B2:
[0055] B1. Determine the target behavior state of the target user in the target period and the first state score corresponding to the target behavior state according to the user state data of the target user in the target period corresponding to the target knowledge point.
[0056] Here, the first state score is used to reflect the degree of concentration of the target user on the knowledge point in the target behavior state. The state score can be set for each behavior state in advance according to the types of behavior states that may occur in the class and the degree of concentration corresponding to each behavior state. The higher the degree of concentration corresponding to the behavior state, the higher the state score set for the behavior state; then a first corresponding relationship between the behavior state and the state score is established. After obtaining the target behavior state, the first state score corresponding to the target behavior state can be determined according to the first corresponding relationship.
[0057] For example, the behavior states are respectively raising hands, sitting upright, lowering the head, sleeping, and lying sideways. The concentration level corresponding to raising hands>the concentration level corresponding to sitting upright>the concentration level corresponding to lowering the head>the concentration level corresponding to lying sideways>the concentration level corresponding to sleeping. Then, the state scores can be set in advance for the five behavior states of raising hands, sitting upright, lowering the head, sleeping, and lying sideways to indicate the concentration level on the knowledge points in these five behavior states, and the first corresponding relationship between the behavior states and the state scores shown in Table 1 is established:
[0058] Behavioral state Status score Raise your hand 100 Sitting upright 80 Bow your head 70 sideways 60 sleep 20
[0059] Table 1
[0060] If it is determined that the target behavior state of the target user in the target time period is raising the hand, then the first state score corresponding to the target behavior state is determined to be 100 points.
[0061] It should be noted that Table 1 is only an example of the first corresponding relationship between the behavior state and the state score for the present application, and does not limit the present application. The behavior state and the state score corresponding to the behavior state can be set based on actual needs.
[0062] B2. Determine the target user's mastery of the target knowledge point based on the first state score corresponding to the target behavior state.
[0063] Here, the target user's mastery of the target knowledge point is positively correlated with the first state score corresponding to the target behavior state.
[0064] In a feasible implementation, the cumulative duration of each target behavior state of the target user within the target time period can be counted; the ratio between the first state score of the target behavior state corresponding to the maximum cumulative duration and the maximum behavior state score is determined as the mastery score of the target user for the target knowledge point.
[0065] For example, the maximum behavior state score is 100 points, the target time period is 10:00:00-10:25:00, a total of 25 minutes, and the target behavior states of the target user in the target time period are raising hands and sitting upright. The cumulative duration of raising hands is 3 minutes, and the cumulative duration of sitting upright is 22 minutes. The state scores corresponding to raising hands and sitting upright are shown in Table 1. The maximum cumulative duration is 22 minutes, and the target behavior state corresponding to the maximum cumulative duration is sitting upright. The state score corresponding to sitting upright is 80 points, and 80 / 100=80% is determined as the target user's mastery score of the target knowledge point.
[0066] In another feasible implementation, the ratio between the duration of each target behavior state of the target user within the target time period and the total duration of the target time period can also be calculated to obtain the behavior duration ratio corresponding to each target behavior state within the target time period; then the behavior duration ratio corresponding to each target behavior state within the target time period is used as the weight coefficient corresponding to each target behavior state within the target time period, and the first state scores corresponding to each target behavior state within the target time period are weighted and summed to obtain the total behavior state score of the target user within the target time period; finally, the ratio between the total behavior state score of the target user within the target time period and the maximum behavior state total score is determined as the target user's mastery score of the target knowledge point.
[0067] For example, the maximum behavior state score is 100 points, the target period is 10:00:00-10:25:00, a total of 25 minutes, and the target behavior states of the target user in the target period are: raising hands (10:00:00-10:03:00) → sitting upright (10:03:00-10:15:00) → leaning sideways (10:15:00-10:20:00) → sitting upright (10:20:00-10:24:00) → bowing head (10:24:00-10:25:00). The state scores corresponding to various behavior states are shown in Table 1, so it can be determined The duration of each target behavior state within the target time period is 3 minutes, 12 minutes, 5 minutes, 4 minutes, and 1 minute, respectively; the proportion of behavior duration corresponding to each target behavior state within the target time period is 3 / 25, 12 / 25, 1 / 5, 4 / 25, and 1 / 25, respectively; the weighted sum of the first state scores corresponding to each target behavior state within the target time period is 100*3 / 25+80*12 / 25+60*1 / 5+80*4 / 25+70*1 / 25=78; 78 / 100=78% is determined as the target user's mastery score of the target knowledge point.
[0068] By converting user status data reflecting the user's behavior status into a score of the user's concentration on the knowledge point, and then determining the user's mastery of the knowledge point, the user's mastery of the knowledge point can be accurately evaluated.
[0069] In the case where the user status data includes the emotional state data of the user in each frame of the target video data, the user status data is used to reflect the emotional state of the target user in the target period; the mastery degree of the target user on the target knowledge point can be determined by the following steps C1-C2:
[0070] C1. Determine the target emotional state of the target user in the target time period and the second state score corresponding to the target emotional state based on the user state data of the target user in the target time period corresponding to the target knowledge point.
[0071] Here, the second state score is used to reflect the target user's understanding of the knowledge point in the target emotional state. A score can be set for each emotional state in advance according to the type of emotional state that the user may have in class and the degree of understanding corresponding to each emotional state. The higher the degree of understanding corresponding to the emotional state, the higher the state score set for the emotional state; then a second corresponding relationship between the emotional state and the state score is established. After obtaining the target emotional state, the second state score corresponding to the target emotional state can be determined according to the second corresponding relationship.
[0072] For example, there are four emotional states: serious, doubtful, surprised, and sad. The degree of understanding corresponding to serious > the degree of understanding corresponding to surprise > the degree of understanding corresponding to doubt > the degree of understanding corresponding to sadness. Then, state scores can be set in advance for the four emotional states of serious, doubtful, surprised, and sad to indicate the degree of understanding of the knowledge points under these four emotional states, and the second corresponding relationship between the emotional states and the state scores shown in Table 2 is established:
[0073] Emotional state Status score serious 100 surprise 90 Confuse 70 sad 40
[0074] Table 2
[0075] If it is determined that the target emotional state of the target user in the target time period is surprise, then the second state score corresponding to the target emotional state is determined to be 90 points.
[0076] It should be noted that Table 2 is only an example of the second corresponding relationship between emotional state and status score for the present application, and does not limit the present application. The status scores corresponding to the emotional state and situation state can be set based on actual needs.
[0077] C2. Determine the target user's mastery of the target knowledge point based on the second state score corresponding to the target emotional state.
[0078] Here, the target user's mastery of the target knowledge point is positively correlated with the second state score corresponding to the target emotional state.
[0079] In a feasible implementation, the cumulative duration of each target emotional state of the target user within the target time period can be counted; the ratio between the second state score of the target emotional state corresponding to the maximum cumulative duration and the total score of the maximum emotional state is determined as the target user's mastery score of the target knowledge point.
[0080] For example, the maximum emotional state score is 100 points, the target time period is 10:00:00-10:25:00, a total of 25 minutes, and the state scores corresponding to each emotional state are shown in Table 2. The target emotional states of the target user in the target time period are serious and surprised. The cumulative duration of seriousness is 10 minutes, and the cumulative duration of surprise is 15 minutes. The maximum cumulative duration is 15 minutes. The target emotional state corresponding to the maximum cumulative duration is surprise. The second state score corresponding to surprise is 90 points, so 90 / 100=90%.
[0081] In another feasible implementation, the ratio between the duration of each target emotional state of the target user within the target time period and the total duration of the target time period can also be calculated to obtain the emotional duration ratio corresponding to each target emotional state within the target time period; then, the emotional proportion duration corresponding to each target emotional state within the target time period is used as the weight coefficient corresponding to each target emotional state within the target time period, and the weighted sum of the second state scores corresponding to each target emotional state within the target time period is performed to obtain the total emotional state score of the target user within the target time period; finally, the ratio between the total behavioral state score of the target user within the target time period and the maximum emotional state total score is determined as the target user's mastery score of the target knowledge point.
[0082] For example, the maximum behavior state score is 100 points, the target period is 10:00:00-10:25:00, a total of 25 minutes, and the target emotional states of the target user in the target period are: serious (10:00:00-10:06:00) → confused (10:06:00-10:20:00) → surprised (10:20:00-10:25:00). The state scores corresponding to each emotional state are shown in Table 2. Then, the target user in the target period can be determined. The duration of each target emotional state is 6 minutes, 14 minutes and 5 minutes respectively; the proportion of emotional duration corresponding to each target emotional state within the target period is 6 / 25, 14 / 25 and 1 / 5 respectively; the weighted sum of the second state scores corresponding to each target emotional state within the target period is 100*6 / 25+70*14 / 25+90*1 / 5=78; 79.2 / 100=79.2% is determined as the target user's mastery score of the target knowledge point.
[0083] By converting user status data reflecting the user's emotional state into a score of the user's understanding of the knowledge point, and then determining the user's mastery of the knowledge point, the user's mastery of the knowledge point can be accurately evaluated.
[0084] In the case where the user status data includes the behavior status data and emotional status data of the target user in each frame of the target video data, the user status data is used to reflect the behavior status and emotional status of the target user in the target period; the mastery degree of the target user on the target knowledge point can be determined through the following steps D1-D3:
[0085] D1. Determine the target behavior state of the target user in the target period and the first state score corresponding to the target behavior state according to the user state data of the target user in the target period corresponding to the target knowledge point.
[0086] Here, the specific implementation method of step D1 can refer to the description of the aforementioned step B1, which will not be repeated here.
[0087] D2. Determine the target emotional state of the target user in the target period and the second state score corresponding to the target emotional state based on the user state data of the target user in the target period corresponding to the target knowledge point.
[0088] Here, the specific implementation method of step D2 can refer to the description of the aforementioned step C1, which will not be repeated here.
[0089] D3. Determine the target user's mastery of the target knowledge point based on the first state score corresponding to the target behavior state and the second state score corresponding to the target emotional state.
[0090] In a feasible implementation, the cumulative duration of each target behavior state and each target emotional state of the target user within the target time period can be counted; the target behavior state corresponding to the maximum cumulative duration and the target emotional state corresponding to the maximum cumulative duration can be determined; the target behavior state corresponding to the maximum cumulative duration and the target emotional state corresponding to the maximum cumulative duration can be determined as the behavior state of the target user in the entire target time period and the emotional state of the target user in the entire target time period; then a weighted sum is taken of the first state score corresponding to the behavior state of the target user in the entire target time period and the second state score corresponding to the emotional state of the target user in the entire target time period to obtain the total state score corresponding to the target knowledge point; the ratio between the total state score corresponding to the target knowledge point and the maximum total state score can be determined as the score of the target user's mastery of the target knowledge point.
[0091] For example, the maximum state total score is 100 points, the state scores corresponding to each behavioral state and the state scores corresponding to each emotional state are shown in Table 1 and Table 2, the target behavioral state corresponding to the maximum cumulative duration is sitting upright, the target emotional state corresponding to the maximum cumulative duration is surprised, and the weight of the behavioral state and the emotional state is 0.5 respectively. Then, the total state score corresponding to the target knowledge point can be determined as: 0.5*80+0.5*90=85, and 85 / 100=85% is determined as the target user's mastery score of the target knowledge point.
[0092] In another feasible implementation, the weighted sum of the first state score corresponding to the target behavior state and the second state score corresponding to the target emotional state of the target user in each frame of the image can also be determined to obtain the total state score of the target user in each frame of the image; the average of the total state score of the target user in each frame of the image is determined as the total state score corresponding to the target knowledge point; the ratio between the total state score corresponding to the target knowledge point and the maximum total state score is determined as the mastery score of the target user for the target knowledge point. The state score corresponding to the target knowledge point is: Where a1 and a2 are the weights of the behavioral state and emotional state, respectively; N is the number of frames contained in the target video data or the number of frames obtained by extracting the target video data; S1 i and S2 i They are respectively a first state score corresponding to the target behavior state of the target user in the i-th frame image and a second state score corresponding to the target emotional state of the target user in the i-th frame image.
[0093] By converting user status data reflecting the user's behavior status into a score of the user's concentration on the knowledge point, and converting user status data reflecting the user's situation status into a score of the user's understanding of the knowledge point, the user's mastery of the knowledge point can be accurately evaluated.
[0094] S203, generating a homework corresponding to the target knowledge point for the target user according to the target user's mastery of the target knowledge point.
[0095] In some possible situations, homework questions with different mastery levels can be set in advance for each knowledge point. For example, the mastery level can be divided into 5 mastery levels in advance, namely mastery level 1 (0, 20%], mastery level 2 (20%, 40%], mastery level 3 (40%, 60%], mastery level 3 (60%, 80%], and mastery level 5 (80%, 100%). The homework can be set according to the mastery level of the target user's mastery of the knowledge point. The homework corresponding to the target knowledge point can be generated for the target user through the following steps E1-E2:
[0096] E1. Determine the level of mastery of the goal.
[0097] Here, the target mastering degree level is the mastering degree level to which the target user's mastering degree of the target knowledge point belongs. For example, if the target user's mastering degree of the target knowledge point is 85%, then the target mastering degree level can be determined to be the mastering degree level 5 introduced above.
[0098] E2. From the preset homework question library, extract the homework questions that belong to the target knowledge points and correspond to the target mastery level as the homework corresponding to the target knowledge points.
[0099] Here, homework questions that belong to the target knowledge points and correspond to the target mastery level can be randomly selected as the homework corresponding to the target knowledge points.
[0100] By extracting the homework title corresponding to the mastery level level to which the user's mastery level belongs as the corresponding homework, the homework can be made to suit the user's learning situation.
[0101] In the above Figure 2 In the corresponding technical solution, the target knowledge point and the user status data of the target user in the target time period corresponding to the target knowledge point are first obtained, and then the target user's mastery of the target knowledge point is determined based on the user status data; finally, based on the user's mastery of the target knowledge point, an assignment corresponding to the target knowledge point is generated for the target user, so that the assignment generated for the user can fit the user's mastery of the knowledge point and meet the user's personalized needs; in addition, by automatically obtaining user status data to determine the user's mastery of the knowledge point and then generating personalized assignments for the user, no teacher participation is required, which can save teachers' time in assigning homework and improve efficiency.
[0102] The method of the present application is introduced above, and the device of the present application is introduced below.
[0103] See also Figure 4 , Figure 4 It is a structural schematic diagram of a job generation device provided in an embodiment of the present application.
[0104] like Figure 3 As shown, the job generating device 30 includes:
[0105] A data acquisition module 301 is used to acquire user status data of a target knowledge point and a target user in a target period corresponding to the target knowledge point, wherein the user status data is used to reflect the user status of the target user in the target period;
[0106] A mastering degree determination module 302 is used to determine the mastering degree of the target user on the target knowledge point according to the user status data;
[0107] The topic generating module 303 is used to generate the homework corresponding to the target knowledge point for the target user according to the mastery level.
[0108] In a possible design, the data acquisition module 301 is specifically used to: acquire the target video data of the target user within the target time period; perform behavior recognition and / or facial expression recognition on each frame of the target video data to obtain the user status data.
[0109] In one possible design, the user status data is used to reflect the behavior status of the target user in the target time period; the above-mentioned mastery level determination module 302 is specifically used to: determine the target behavior status of the target user in the target time period and the first status score corresponding to the target behavior status according to the user status data, the first status score is used to reflect the focus of the target user on the knowledge point in the target behavior state; determine the mastery level of the target user on the target knowledge point according to the first status score, and the mastery level is positively correlated with the first status score.
[0110] In a possible design, the mastery degree determination module 302 is specifically used to: calculate the ratio between the duration of each target behavior state within the target time period and the total duration of the target time period to obtain the behavior duration ratio corresponding to each target behavior state; use the behavior duration ratio corresponding to each target behavior state as the weight coefficient corresponding to each target behavior state, and perform weighted summation on the first state scores corresponding to each target behavior state to obtain the total behavior state score of the target user within the target time period; determine the ratio between the total behavior state score and the maximum behavior state total score as the mastery degree score of the target user for the target knowledge point.
[0111] In one possible design, the user status data is used to reflect the emotional state of the target user during the target time period; the above-mentioned mastery level determination module 302 is specifically used to: determine the target emotional state of the target user during the target time period and the second state score corresponding to the target emotional state based on the user status data, the second state score is used to reflect the target user's understanding of the knowledge point under the target emotional state; determine the target user's mastery of the target knowledge point based on the second state score, and the mastery level is positively correlated with the second state score.
[0112] In a possible design, the mastery level determination module 302 is specifically used to: calculate the ratio between the duration of each target emotional state within the target time period and the total duration of the target time period to obtain the emotional duration ratio corresponding to each target emotional state; use the emotional duration ratio corresponding to each target emotional state as the weight coefficient corresponding to each target emotional state, and perform weighted summation on the second state scores corresponding to each target emotional state to obtain the total emotional state score of the target user within the target time period; determine the ratio between the total emotional state score and the maximum emotional state total score as the mastery level score of the target user for the target knowledge point.
[0113] In one possible design, the user state data is used to reflect the behavioral state and emotional state of the target user in the target time period; the above-mentioned mastery level determination module 302 is specifically used to: determine the target behavioral state of the target user in the target time period and the first state score corresponding to the target behavioral state, as well as the target emotional state of the target user in the target time period and the second state score corresponding to the target emotional state according to the user state data, the first state score is used to reflect the target user's concentration on the knowledge point in the target behavioral state, and the second state score is used to reflect the target user's understanding of the knowledge point in the target emotional state; determine the target user's mastery of the target knowledge point according to the first state score and the second state score.
[0114] In a possible design, the above-mentioned mastery degree determination module 302 is specifically used to: perform weighted summation of the first state score and the second state score to obtain the total state score corresponding to the target knowledge point; and determine the ratio between the total state score and the maximum total state score as the mastery degree score of the target user for the target knowledge point.
[0115] In a possible design, the above-mentioned question generation module 303 is specifically used to: determine the target mastery level, which is the mastery level of the target user's mastery of the target knowledge point; extract homework questions belonging to the target knowledge point and corresponding to the target mastery level from a preset homework question library as the homework corresponding to the target knowledge point.
[0116] It should be noted that Figure 4 For the contents not mentioned in the corresponding embodiments, please refer to the description of the aforementioned method embodiments, which will not be repeated here.
[0117] The above-mentioned device first obtains the target knowledge point and the user status data of the target user in the target time period corresponding to the target knowledge point, and then determines the target user's mastery of the target knowledge point based on the user status data; finally, based on the user's mastery of the target knowledge point, generates homework corresponding to the target knowledge point for the target user, so that the homework generated for the user can fit the user's mastery of the knowledge point and meet the user's personalized needs; in addition, by automatically obtaining user status data to determine the user's mastery of the knowledge point and then generating personalized homework for the user, no teacher participation is required, which can save teachers' time in assigning homework and improve efficiency.
[0118] See also Figure 5 , Figure 5 4 is a schematic diagram of a computer device provided in an embodiment of the present application, wherein the computer device 40 includes a processor 401 and a memory 402. The memory 402 is connected to the processor 401, for example, via a bus.
[0119] The processor 401 is configured to support the computer device 40 to perform the corresponding functions in the method in the above method embodiment. The processor 401 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.
[0120] The memory 402 is used to store program codes, etc. The memory 402 may include a volatile memory (VM), such as a random access memory (RAM); the memory 402 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 402 may also include a combination of the above-mentioned types of memories.
[0121] The processor 401 may call the program code to perform the following operations:
[0122] Acquire user status data of a target knowledge point and a target user in a target time period corresponding to the target knowledge point, wherein the user status data is used to reflect the user status of the target user in the target time period;
[0123] Determining the target user's mastery of the target knowledge point according to the user status data;
[0124] Based on the mastery level, a homework corresponding to the target knowledge point is generated for the target user.
[0125] 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.
[0126] 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.
[0127] 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 generating a job, characterized in that: include: Acquire user status data of a target knowledge point and a target user in a target time period corresponding to the target knowledge point, wherein the user status data is used to reflect the user status of the target user in the target time period; Determining the target user's mastery of the target knowledge point according to the user status data; Based on the mastery level, a homework corresponding to the target knowledge point is generated for the target user.
2. The method according to claim 1, characterized in that: The acquiring of user status data of the target user in the target time period corresponding to the target knowledge point includes: Acquire target video data of the target user within the target time period; Behavior recognition and / or facial expression recognition are performed on each frame of the target video data to obtain the user status data.
3. The method according to claim 1, characterized in that: The user status data is used to reflect the behavior status of the target user within the target time period; Determining the target user's mastery of the target knowledge point according to the user status data includes: Determine, according to the user status data, a target behavior state of the target user in the target time period and a first status score corresponding to the target behavior state, wherein the first status score is used to reflect the degree of concentration of the target user on the knowledge point in the target behavior state; The target user's mastery of the target knowledge point is determined according to the first status score, and the mastery is positively correlated with the first status score.
4. The method according to claim 3, characterized in that: The determining, according to the first status score, the target user's mastery of the target knowledge point includes: Calculating the ratio between the duration of each target behavior state within the target time period and the total duration of the target time period to obtain the behavior duration ratio corresponding to each target behavior state; The behavior duration ratio corresponding to each target behavior state is used as the weight coefficient corresponding to each target behavior state, and the first state score corresponding to each target behavior state is weighted and summed to obtain the total behavior state score of the target user in the target time period; The ratio between the total score of the behavior state and the maximum total score of the behavior state is determined as the mastery degree score of the target user on the target knowledge point.
5. The method according to claim 1, characterized in that The user status data is used to reflect the emotional state of the target user during the target period; Determining the target user's mastery of the target knowledge point according to the user status data includes: Determining, according to the user state data, a target emotional state of the target user in the target time period and a second state score corresponding to the target emotional state, wherein the second state score is used to reflect the target user's degree of understanding of the knowledge point in the target emotional state; The target user's mastery of the target knowledge point is determined according to the second status score, and the mastery is positively correlated with the second status score.
6. The method according to claim 5, characterized in that Determining the target user's mastery of the target knowledge point according to the second status score includes: Calculating the ratio between the duration of each target emotional state within the target time period and the total duration of the target time period to obtain the emotional duration ratio corresponding to each target emotional state; The emotional duration ratio corresponding to each target emotional state is used as the weight coefficient corresponding to each target emotional state, and the second state score corresponding to each target emotional state is weighted and summed to obtain the total emotional state score of the target user in the target time period; The ratio between the total score of the emotional state and the maximum total score of the emotional state is determined as the mastery score of the target user on the target knowledge point.
7. The method according to claim 1, characterized in that The user status data is used to reflect the behavior status and emotional state of the target user during the target period; Determining the target user's mastery of the target knowledge point according to the user status data includes: Determine, according to the user status data, a target behavior state of the target user in the target time period and a first status score corresponding to the target behavior state, as well as a target emotional state of the target user in the target time period and a second status score corresponding to the target emotional state, wherein the first status score is used to reflect the degree of concentration of the target user on the knowledge point in the target behavior state, and the second status score is used to reflect the degree of understanding of the target user on the knowledge point in the target emotional state; The mastery degree of the target user on the target knowledge point is determined according to the first status score and the second status score.
8. The method according to claim 7, characterized in that The determining, according to the first status score and the second status score, the mastery degree of the target user of the target knowledge point includes: Performing a weighted summation on the first state score and the second state score to obtain a total state score corresponding to the target knowledge point; The ratio between the state total score and the maximum state total score is determined as the mastery degree score of the target user on the target knowledge point.
9. The method according to any one of claims 1 to 8, characterized in that: Generating, for the target user, a homework corresponding to the target knowledge point according to the mastery level, includes: determining a target mastery level, the target mastery level being the mastery level to which the mastery level belongs; From a preset homework question library, homework questions that belong to the target knowledge point and correspond to the target mastery level are extracted as the homework corresponding to the target knowledge point.
10. A job generating device, characterized in that: include: A data acquisition module, used to acquire user status data of a target knowledge point and a target user in a target period corresponding to the target knowledge point, wherein the user status data is used to reflect the user status of the target user in the target period; A mastering degree determination module, used to determine the mastering degree of the target user on the target knowledge point according to the user status data; The topic generation module is used to generate homework corresponding to the target knowledge point for the target user according to the mastery level.
11. 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 9.
12. 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 9.