Teaching level evaluation method and system based on local account

Abstract

The invention relates to the technical field of intelligent evaluation, and particularly discloses a teaching level evaluation method and system based on a local account, and the method comprises the steps: obtaining the use process and face data of each student based on the granted authority, determining the concentration degree according to the use process, and synchronously training the face data to a neural network model of the concentration degree; face data of each student is collected regularly, and the concentration degree of each student is determined based on the trained neural network model; receiving a teaching scheme input by a teacher, identifying the teaching scheme, determining importance degrees of different time periods, and determining an evaluation score according to the importance degrees of different moments and the concentration degree of each student at different moments; according to the method, the importance degree of each stage in the teaching process is determined based on the information of the teacher, the concentration degree of the student in each stage is determined based on the information of the student, the process is performed in real time, the evaluation score of the teaching process is jointly determined by combining the concentration degree and the importance degree, the globality is high, and the objectivity is high.

Description

Technical Field

[0001] The present invention relates to the field of intelligent assessment technology, and in particular to a teaching level assessment method and system based on a local account. Background Art

[0002] With the advancement of science and technology and the development of society, people have more and more desires and ways to acquire knowledge, and the forms and numbers of classrooms are also increasing. Smart classrooms are a kind of teaching interaction method based on smart devices, including both online and offline methods.

[0003] There is a very important behavior in the teaching interaction process, that is, the teaching level evaluation behavior. The existing evaluation method is still based on manual human evaluation, and the students' memory is limited. The data source of the evaluation is often only some teaching fragments in the final stage. In fact, based on the sufficient popularity of existing smart devices, it is not complicated to introduce a global and objective teaching level evaluation scheme. How to build a global and objective teaching level evaluation architecture is the technical problem that the technical solution of the present invention wants to solve. Summary of the invention

[0004] The purpose of the present invention is to provide a teaching level assessment method and system based on a local account to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: A teaching level evaluation method based on a local account, the method comprising: Sending a permission acquisition request to a user, and receiving the permission granted by the user; wherein the user includes a student and a teacher; Based on the granted permissions, the usage progress and facial data of each student are obtained, the concentration is determined according to the usage progress, and a neural network model of facial data to concentration is trained synchronously; wherein one student corresponds to one neural network model; Collect facial data of each student regularly and determine the concentration of each student based on the trained neural network model; The teaching plan input by the instructor is received, the teaching plan is identified, the importance of different time periods is determined, and the evaluation score is determined according to the importance at different times and the concentration of each student at different times.

[0006] As a further solution of the present invention: the steps of obtaining the usage process and facial data of each student based on the granted authority, determining the concentration according to the usage process, and synchronously training the facial data to the neural network model of the concentration include: Based on the granted authority, the browsing content and operation parameters of the user at each moment are obtained in real time, and the concentration at each moment is determined according to the browsing content and operation parameters; Obtain the student image based on the granted permissions, identify the student image, and extract facial data; The facial data and the concentration are aligned in time domain, and a neural network model is trained based on the facial data and the concentration after the temporal alignment as samples; the input of the neural network model is the facial data, and the output is the concentration.

[0007] As a further solution of the present invention: the step of obtaining the browsing content and operation parameters of the user at each moment in real time based on the granted authority, and determining the concentration at each moment according to the browsing content and operation parameters includes: Based on the granted permissions, the user's browsing content and operation parameters at each moment are obtained in real time; Reading the serial number corresponding to the operation parameter at each moment in a preset parameter conversion table; the parameter conversion table contains an operation type item and a serial number item; Aggregate the time according to the browsing content to obtain the time period corresponding to each browsing content; Based on the time sequence, the serial numbers corresponding to the operation parameters in the time period are counted and arranged to obtain the actual operation serial number group; The preset standard serial number group of each browsing content is read, the practical serial number group and the standard serial number group are compared, the similarity is calculated, and the concentration is determined according to the similarity; wherein the concentration is proportional to the similarity.

[0008] As a further solution of the present invention: the steps of receiving the teaching plan input by the teacher, identifying the teaching plan, determining the importance of different time periods, and determining the evaluation score according to the importance at different times and the concentration of each student at different times include: Receiving the teaching plan input by the teacher, identifying the teaching plan, and determining the importance of different time periods; identifying the teaching plan includes a keyword matching process, different keywords correspond to different importance, and the keywords and their importance are both preset parameters; Read each student's concentration at different times and insert them into the same timeline; According to a preset time step, a matching point is intercepted on the time axis, and the number of people whose concentration at the matching point is less than a preset concentration threshold is read; the matching point is a time point; Query the importance of the matching points and determine the evaluation score based on the importance and number of people.

[0009] As a further solution of the present invention: the step of receiving the teaching plan input by the teacher, identifying the teaching plan, and determining the importance of different time periods includes: Receive teaching keywords and their importance for each time period input by the teacher; Based on the granted permissions, the audio information of the teacher is obtained, the teaching keywords are located, and the teaching keywords and their importance in each time period are modified according to the location results.

[0010] As a further solution of the present invention: the importance of the query matching point and the step of determining the evaluation score according to the importance and the number of people include: Querying the number threshold of each importance, calculating the ratio of the number of people to the number threshold, and determining the score of each matching point according to the ratio; wherein the score is inversely proportional to the ratio; The weight is determined according to the importance of each matching point, and all scores are accumulated based on the weight to obtain the final evaluation score; among which, the weight is proportional to the importance.

[0011] The technical solution of the present invention also provides a teaching level evaluation system based on a local account, the system comprising: The authority acquisition module is used to send an authority acquisition request to a user and receive the authority granted by the user; wherein the user includes a student and a teacher; A model training module is used to obtain the usage process and facial data of each student based on the granted permissions, determine the concentration according to the usage process, and synchronously train the facial data to the neural network model of concentration; wherein one student corresponds to one neural network model; The concentration recognition module is used to collect facial data of each student at regular intervals and determine the concentration of each student based on the trained neural network model; The evaluation score determination module is used to receive the teaching plan input by the teacher, identify the teaching plan, determine the importance of different time periods, and determine the evaluation score according to the importance at different times and the concentration of each student at different times.

[0012] As a further solution of the present invention: the model training module includes: A concentration initial determination unit, used to obtain the browsing content and operation parameters of the user at each moment in real time based on the granted authority, and determine the concentration at each moment according to the browsing content and operation parameters; A facial data extraction unit, used to obtain a student image based on the granted authority, identify the student image, and extract facial data; The training execution unit is used to perform time domain registration on facial data and concentration, and train a neural network model based on the facial data and concentration after time domain registration as samples; the input of the neural network model is facial data, and the output is concentration.

[0013] As a further solution of the present invention: the concentration initial determination unit includes: The data acquisition subunit is used to acquire the browsing content and operation parameters of the user at each moment in real time based on the granted authority; A sequence number query subunit is used to read the sequence number corresponding to the operation parameter at each moment in a preset parameter conversion table; the parameter conversion table contains an operation type item and a sequence number item; The time aggregation subunit is used to aggregate the time according to the browsing content to obtain the time period corresponding to each browsing content; The sequence number arrangement subunit is used to count and arrange the sequence numbers corresponding to the operation parameters in the time period based on the time sequence to obtain the actual operation sequence number group; The comparison subunit is used to read the preset standard serial number group of each browsing content, compare the practical serial number group and the standard serial number group, calculate the similarity, and determine the concentration according to the similarity; wherein the concentration is proportional to the similarity.

[0014] As a further solution of the present invention: the evaluation score determination module includes: A scheme identification unit is used to receive the teaching scheme input by the teacher, identify the teaching scheme, and determine the importance of different time periods; the identification of the teaching scheme includes a keyword matching process, different keywords correspond to different importance, and the keywords and their importance are both preset parameters; The concentration statistics unit is used to read the concentration of each student at different times and insert it into the same timeline; A number query unit, used to intercept matching points on the time axis according to a preset time step, and read the number of people whose concentration at the matching point is less than a preset concentration threshold; the matching point is a time point; The data application unit is used to query the importance corresponding to the matching points and determine the evaluation score based on the importance and the number of people.

[0015] Compared with the prior art, the beneficial effects of the present invention are: the present invention determines the importance of each stage in the teaching process based on the teacher's information, and determines the student's concentration at each stage based on the student's information. This process is carried out in real time, and the evaluation score of the teaching process is determined by combining concentration and importance. It has high globality and objectivity. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention.

[0017] Figure 1 This is a flowchart of the teaching level evaluation method based on local accounts.

[0018] Figure 2 This is a structural diagram of the teaching level evaluation system based on local accounts. DETAILED DESCRIPTION

[0019] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] Figure 1 The flowchart of the teaching level evaluation method based on the local account is as follows. In an embodiment of the present invention, a teaching level evaluation method based on the local account includes: Step S100: sending a permission acquisition request to a user, and receiving the permission granted by the user; wherein the user includes a student and a teacher; The application scenario of the present application is very clear, that is, a smart classroom equipped with electronic devices. Each student is equipped with a tablet computer, and the teacher also has his own computer equipment. In the technical solution of the present invention, the permission acquisition process is a necessary process, including obtaining the permissions granted by the students and the permissions granted by the teacher. The acquired permissions include camera acquisition permissions and operation information recording permissions. The camera acquisition permission is used to obtain videos of the students or teachers, and the operation information recording permission is used to obtain the operation behaviors of the students or teachers on the device, including touch screen signals and keyboard and mouse signals. In the application scenario of the present application, the audio signal used for operation, that is, the audio control method is relatively rare.

[0021] Step S200: Based on the granted authority, the usage process and facial data of each student are obtained, the concentration is determined according to the usage process, and a neural network model of facial data to concentration is synchronously trained; wherein one student corresponds to one neural network model; After receiving the permission granted by the user, the usage process and facial data of each student are obtained based on the granted permission. The usage process indicates what operations the student has performed on his tablet computer. By analyzing the usage process, the student's concentration level in the teaching process can be calculated, which is called concentration. At the same time, the application also obtains facial data. There is a mapping relationship between facial data and concentration. Based on the facial data and concentration, the facial data is used as a feature (input) and the concentration is used as a label (output). A sample set can be constructed, and a neural network model can be trained based on the sample set. After the training is completed, the concentration can be obtained by inputting facial data.

[0022] It should be noted that in the technical solution of the present invention, the training process of each student is independent, one student corresponds to one neural network model, and the types of facial data of a student are very limited. The training process is very simple and a simple regression model can be used.

[0023] Step S300: collecting facial data of each student at regular intervals, and determining the concentration of each student based on the trained neural network model; In actual applications, during a teaching activity, the facial data of each student is collected at a regular interval, and the facial data is input into a trained neural network model to obtain the concentration of each student. Regarding the concept of timing in this application, this application takes the beginning of the teaching activity as time zero. For example, a teaching activity has 72 classes, so the beginning is time zero, and facial data is collected once every minute. The result of the first collection is the result corresponding to one minute, and the result of the second collection is the result corresponding to two minutes, and so on, to obtain multiple results containing time.

[0024] It is worth mentioning that in order to improve the accuracy of the assessment, a shorter timing interval can be used. At this time, the detection granularity is larger and more data is collected. For example, from one minute to thirty seconds, the amount of data obtained is almost twice the original amount of data.

[0025] Step S400: receiving the teaching plan input by the teacher, identifying the teaching plan, determining the importance of different time periods, and determining the evaluation score according to the importance at different times and the concentration of each student at different times; The teacher can input the teaching plan of the entire teaching process at the beginning of teaching (suitable for recorded teaching activities), or input the teaching plan of the current class before each class (suitable for real-time teaching activities), and identify the teaching plan (mainly text recognition of the lesson plan). According to the identification result, the importance of each moment in the entire teaching activity can be determined, which is represented by the parameter of importance; in step S300, the concentration of the students at each moment has been calculated, and the teaching process is evaluated based on the importance of different moments and the concentration of each student at different moments to obtain an evaluation score; the evaluation score indicates how many students focus on the contents of different importance in the teaching process and how much they focus. Its practical significance lies in how much important content attracts students with what degree of concentration, which is a very suitable parameter for evaluating teaching effectiveness.

[0026] Regarding step S100, the steps of obtaining the usage process and facial data of each student based on the granted authority, determining the concentration according to the usage process, and synchronously training the facial data to the neural network model of the concentration include: Based on the granted authority, the browsing content and operation parameters of the user at each moment are obtained in real time, and the concentration at each moment is determined according to the browsing content and operation parameters; Obtain the student image based on the granted permissions, identify the student image, and extract facial data; The facial data and the concentration are aligned in time domain, and a neural network model is trained based on the facial data and the concentration after the temporal alignment as samples; the input of the neural network model is the facial data, and the output is the concentration.

[0027] In an example of the technical solution of the present invention, the browsing content and operating parameters of the students at each moment are obtained in real time based on the granted permissions. The browsing content indicates what kind of content the students are watching on the tablet computer, and the operating parameters indicate what operations are performed. The browsing content and operating parameters at each moment are analyzed to determine the student's concentration on the class, which is represented by the parameter of concentration. At the same time, the student's image is obtained based on the granted permissions, the student image is recognized, and facial data is extracted. This process belongs to the existing facial recognition process and will not be repeated. Both the concentration and facial data contain time information. Only the concentration and facial data at the same moment (with a small enough time difference) can be used as the same sample. The facial data and concentration are time-domain aligned, and the neural network model is trained based on the facial data and concentration after time-domain alignment as samples. Among them, the process of time-domain alignment is to group the concentration and facial data at the same moment together.

[0028] Specifically, the step of obtaining the browsing content and operation parameters of the user at each moment in real time based on the granted authority, and determining the concentration at each moment according to the browsing content and operation parameters includes: Based on the granted permissions, the user's browsing content and operation parameters at each moment are obtained in real time; Reading the serial number corresponding to the operation parameter at each moment in a preset parameter conversion table; the parameter conversion table contains an operation type item and a serial number item; Aggregate the time according to the browsing content to obtain the time period corresponding to each browsing content; Based on the time sequence, the serial numbers corresponding to the operation parameters in the time period are counted and arranged to obtain the actual operation serial number group; The preset standard serial number group of each browsing content is read, the practical serial number group and the standard serial number group are compared, the similarity is calculated, and the concentration is determined according to the similarity; wherein the concentration is proportional to the similarity.

[0029] In an example of the technical solution of the present invention, a specific concentration calculation solution is provided, which obtains the user's browsing content and operation parameters at each moment in real time based on the granted permissions. The browsing content is generally the courseware sent in advance by the teacher, which is known data. Regarding operation parameters, there are only a few existing operation parameters, including zooming, sliding, page turning and marking, etc. They can all be counted in advance in a parameter conversion table and numbered so that each operation is quantified into a serial number, and one operation corresponds to a unique serial number; that is, the parameter conversion table contains operation type items and serial number items.

[0030] For the registration process of browsing content and operation parameters, browsing content generally corresponds to a time period. Obtaining the pinned content on the tablet computer based on the granted permissions is browsing content. Since the moment corresponding to each browsing content is continuous, it is necessary to aggregate the moments according to the browsing content to obtain the time period corresponding to each browsing content.

[0031] Furthermore, regarding the operation information, the time period for each browsing content is determined, and the operation information within the time period is the student's operation process on the browsing content. The serial numbers corresponding to the operation parameters within the time period are counted and arranged based on the time sequence to obtain the practical operation serial number group, which reflects the student's quantified operation process during this period of time; for each browsing content, since it is known data, its standard operation can be determined in advance. Compared with reading text, it is almost intermittent sliding and page turning operations. Its standard operation is counted in advance (it can receive the teacher's input and use the teacher's input as a limitation) and expressed in the form of a standard serial number group. At this time, the operation information corresponds to the practical operation serial number group, and the standard operation corresponds to the standard serial number group. The practical operation serial number group and the standard serial number group are compared to calculate the similarity, and the concentration can be determined based on the similarity.

[0032] Regarding the process of comparing the practical serial number group and the standard serial number group and calculating the similarity, the simplest way is to calculate the maximum intersection of the two and determine the similarity based on the length of the maximum intersection. The longer the length of the maximum intersection, the higher the similarity.

[0033] Regarding step S400, the steps of receiving the teaching plan input by the teacher, identifying the teaching plan, determining the importance of different time periods, and determining the evaluation score according to the importance at different times and the concentration of each student at different times include: Receiving the teaching plan input by the teacher, identifying the teaching plan, and determining the importance of different time periods; identifying the teaching plan includes a keyword matching process, different keywords correspond to different importance, and the keywords and their importance are both preset parameters; Read each student's concentration at different times and insert them into the same timeline; According to a preset time step, a matching point is intercepted on the time axis, and the number of people whose concentration at the matching point is less than a preset concentration threshold is read; the matching point is a time point; Query the importance of the matching points and determine the evaluation score based on the importance and number of people.

[0034] In an example of the technical solution of the present invention, the evaluation process is specifically limited, a teaching plan input by a teacher is received, the teaching plan is identified, the identification of the teaching plan includes a keyword matching process, different keywords correspond to different importance, keywords and their importance are preset parameters, teaching content of different time periods is intercepted in the teaching plan, keyword matching is performed on the teaching content, the importance of the matched keywords is read, and then the importance of the matched keywords is accumulated to obtain the final importance; it should be noted that teaching content of different time periods is intercepted in the teaching plan, and the different time periods can be preset time periods, such as two minutes or three minutes, etc., and the importance determination process is carried out in segments.

[0035] Read the concentration of each student at different moments and insert them into the same timeline. The concentration is the concentration at each moment. For example, the concentration is collected once every thirty seconds. All students have a concentration. In order to facilitate analysis and processing, they are inserted into the same timeline. Furthermore, the concentration recognition moment of each student may be a little different. For example, a difference of a few tenths of a second is caused by the data transmission process. Therefore, when analyzing the concentration, first intercept matching points on the timeline. The intercepted matching points are intercepted every thirty seconds (the same as the guide cycle of the concentration analysis process, that is, the cycle of the image acquisition and recognition process). Query the concentration of each student at the matching point (moment) and compare it with the preset concentration threshold. When the concentration is less than the preset concentration threshold, it means that the student is lacking attention at the current matching point. By obtaining the number of people who lack attention at the matching point (the concentration is small enough), it can be obtained how many students are distracted at the corresponding moment.

[0036] Finally, query the time period where the matching point is located, read the corresponding importance, and combine the importance and the number of people to determine the evaluation score.

[0037] Furthermore, the steps of receiving the teaching plan input by the teacher, identifying the teaching plan, and determining the importance of different time periods include: Receive teaching keywords and their importance for each time period input by the teacher; Based on the granted permissions, the audio information of the teacher is obtained, the teaching keywords are located, and the teaching keywords and their importance in each time period are modified according to the location results.

[0038] The above content provides a new teaching plan determination process. The teaching plan itself is the information uploaded by the teacher, and the teacher knows the most about it. Therefore, the importance of each time period input by the teacher can be received. At the same time, the teaching keywords of each time period are also received. The purpose of receiving the teaching keywords is to verify the importance. For example, if the corresponding teaching keywords do not appear in a certain time period, the time period is divided into two sections and merged into the two previous and next time periods respectively, that is, the time period is corrected.

[0039] In addition, the importance of the query matching point and the step of determining the evaluation score according to the importance and the number of people include: Querying the number threshold of each importance, calculating the ratio of the number of people to the number threshold, and determining the score of each matching point according to the ratio; wherein the score is inversely proportional to the ratio; The weight is determined according to the importance of each matching point, and all scores are accumulated based on the weight to obtain the final evaluation score; among which, the weight is proportional to the importance.

[0040] Specifically, the calculation process of the evaluation score is as follows: ; In the formula, Indicates the evaluation score, represents the total number of matching points, Indicates The ratio of the matching points, Indicates The score corresponding to each matching point.

[0041] A small detail in the above calculation process is that importance has a greater impact, so it uses an exponential basis.

[0042] The above content describes the evaluation process in detail. The evaluation score is determined by the number of people and importance. For each importance, a number threshold is determined in advance. The number threshold indicates how many students at this importance are in a state of inattention at most. The number is the number of people who lack attention at the current matching point. The number threshold is generally a large value. The ratio of the number of people to the number threshold is calculated. The ratio is generally less than 1. The smaller the ratio, the fewer people lack attention, and a higher score is given to them. On this basis, a weight is determined by the importance. The weight can also be understood as a unit score. The higher the importance, the larger the unit score. Finally, all scores are accumulated based on the weight to obtain the final evaluation score. The higher the score, the higher the teaching level.

[0043] Figure 2 1 is a structural diagram of a teaching level evaluation system based on a local account. In an embodiment of the present invention, a teaching level evaluation system based on a local account, the system 10 includes: The authority acquisition module 11 is used to send an authority acquisition request to a user and receive the authority granted by the user; wherein the user includes a student and a teacher; The model training module 12 is used to obtain the usage process and facial data of each student based on the granted authority, determine the concentration according to the usage process, and synchronously train the facial data to the neural network model of the concentration; wherein one student corresponds to one neural network model; A concentration recognition module 13 is used to collect facial data of each student at regular intervals and determine the concentration of each student based on a trained neural network model; The evaluation score determination module 14 is used to receive the teaching plan input by the teacher, identify the teaching plan, determine the importance of different time periods, and determine the evaluation score according to the importance at different times and the concentration of each student at different times.

[0044] Furthermore, the model training module 12 includes: A concentration initial determination unit, used to obtain the browsing content and operation parameters of the user at each moment in real time based on the granted authority, and determine the concentration at each moment according to the browsing content and operation parameters; A facial data extraction unit, used to obtain a student image based on the granted authority, identify the student image, and extract facial data; The training execution unit is used to perform time domain registration on facial data and concentration, and train a neural network model based on the facial data and concentration after time domain registration as samples; the input of the neural network model is facial data, and the output is concentration.

[0045] Specifically, the concentration initial determination unit includes: The data acquisition subunit is used to acquire the browsing content and operation parameters of the user at each moment in real time based on the granted authority; A sequence number query subunit is used to read the sequence number corresponding to the operation parameter at each moment in a preset parameter conversion table; the parameter conversion table contains an operation type item and a sequence number item; The time aggregation subunit is used to aggregate the time according to the browsing content to obtain the time period corresponding to each browsing content; The sequence number arrangement subunit is used to count and arrange the sequence numbers corresponding to the operation parameters in the time period based on the time sequence to obtain the actual operation sequence number group; The comparison subunit is used to read the preset standard serial number group of each browsing content, compare the practical serial number group and the standard serial number group, calculate the similarity, and determine the concentration according to the similarity; wherein the concentration is proportional to the similarity.

[0046] Furthermore, the evaluation score determination module 14 includes: A scheme identification unit is used to receive the teaching scheme input by the teacher, identify the teaching scheme, and determine the importance of different time periods; the identification of the teaching scheme includes a keyword matching process, different keywords correspond to different importance, and the keywords and their importance are both preset parameters; The concentration statistics unit is used to read the concentration of each student at different times and insert it into the same timeline; A number query unit, used to intercept matching points on the time axis according to a preset time step, and read the number of people whose concentration at the matching point is less than a preset concentration threshold; the matching point is a time point; The data application unit is used to query the importance corresponding to the matching points and determine the evaluation score based on the importance and the number of people.

[0047] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A teaching level evaluation method based on a local account, characterized in that: The method comprises: Sending a permission acquisition request to a user, and receiving the permission granted by the user; wherein the user includes a student and a teacher; Based on the granted permissions, the usage progress and facial data of each student are obtained, the concentration is determined according to the usage progress, and a neural network model of facial data to concentration is trained synchronously; wherein one student corresponds to one neural network model; Collect facial data of each student regularly and determine the concentration of each student based on the trained neural network model; The teaching plan input by the instructor is received, the teaching plan is identified, the importance of different time periods is determined, and the evaluation score is determined according to the importance at different times and the concentration of each student at different times.

2. The teaching level evaluation method based on local accounts according to claim 1 is characterized in that: The steps of obtaining the usage process and facial data of each student based on the granted authority, determining the concentration according to the usage process, and synchronously training the facial data to the neural network model of the concentration include: Based on the granted authority, the browsing content and operation parameters of the user at each moment are obtained in real time, and the concentration at each moment is determined according to the browsing content and operation parameters; Obtain the student image based on the granted permissions, identify the student image, and extract facial data; The facial data and the concentration are aligned in time domain, and a neural network model is trained based on the facial data and the concentration after the temporal alignment as samples; the input of the neural network model is the facial data, and the output is the concentration.

3. The teaching level evaluation method based on local accounts according to claim 2 is characterized in that: The step of obtaining the browsing content and operation parameters of the user at each moment in real time based on the granted authority, and determining the concentration at each moment according to the browsing content and operation parameters comprises: Based on the granted permissions, the user's browsing content and operation parameters at each moment are obtained in real time; Reading the serial number corresponding to the operation parameter at each moment in a preset parameter conversion table; the parameter conversion table contains an operation type item and a serial number item; Aggregate the time according to the browsing content to obtain the time period corresponding to each browsing content; Based on the time sequence, the serial numbers corresponding to the operation parameters in the time period are counted and arranged to obtain the actual operation serial number group; The preset standard serial number group of each browsing content is read, the practical serial number group and the standard serial number group are compared, the similarity is calculated, and the concentration is determined according to the similarity; wherein the concentration is proportional to the similarity.

4. The teaching level evaluation method based on local accounts according to claim 1 is characterized in that: The steps of receiving the teaching plan input by the teacher, identifying the teaching plan, determining the importance of different time periods, and determining the evaluation score according to the importance at different times and the concentration of each student at different times include: Receiving the teaching plan input by the teacher, identifying the teaching plan, and determining the importance of different time periods; identifying the teaching plan includes a keyword matching process, different keywords correspond to different importance, and the keywords and their importance are both preset parameters; Read each student's concentration at different times and insert them into the same timeline; According to a preset time step, a matching point is intercepted on the time axis, and the number of people whose concentration at the matching point is less than a preset concentration threshold is read; the matching point is a time point; Query the importance of the matching points and determine the evaluation score based on the importance and number of people.

5. The teaching level evaluation method based on local accounts according to claim 4 is characterized in that: The steps of receiving the teaching plan input by the teacher, identifying the teaching plan, and determining the importance of different time periods include: Receive teaching keywords and their importance for each time period input by the teacher; Based on the granted permissions, the audio information of the teacher is obtained, the teaching keywords are located, and the teaching keywords and their importance in each time period are modified according to the location results.

6. The teaching level evaluation method based on local accounts according to claim 4 is characterized in that: The importance of querying matching points and determining the evaluation score according to the importance and the number of people include: Querying the number threshold of each importance, calculating the ratio of the number of people to the number threshold, and determining the score of each matching point according to the ratio; wherein the score is inversely proportional to the ratio; The weight is determined according to the importance of each matching point, and all scores are accumulated based on the weight to obtain the final evaluation score; among which, the weight is proportional to the importance.

7. A teaching level evaluation system based on local accounts, characterized in that: The system comprises: The authority acquisition module is used to send an authority acquisition request to a user and receive the authority granted by the user; wherein the user includes a student and a teacher; A model training module is used to obtain the usage process and facial data of each student based on the granted permissions, determine the concentration according to the usage process, and synchronously train the facial data to the neural network model of concentration; wherein one student corresponds to one neural network model; The concentration recognition module is used to collect facial data of each student at regular intervals and determine the concentration of each student based on the trained neural network model; The evaluation score determination module is used to receive the teaching plan input by the teacher, identify the teaching plan, determine the importance of different time periods, and determine the evaluation score according to the importance at different times and the concentration of each student at different times.

8. The teaching level evaluation system based on local accounts according to claim 7 is characterized in that: The model training module includes: A concentration initial determination unit, used to obtain the browsing content and operation parameters of the user at each moment in real time based on the granted authority, and determine the concentration at each moment according to the browsing content and operation parameters; A facial data extraction unit, used to obtain a student image based on the granted authority, identify the student image, and extract facial data; The training execution unit is used to perform time domain registration on facial data and concentration, and train a neural network model based on the facial data and concentration after time domain registration as samples; the input of the neural network model is facial data, and the output is concentration.

9. The teaching level evaluation system based on local accounts according to claim 8, characterized in that: The concentration preliminary determination unit includes: The data acquisition subunit is used to acquire the browsing content and operation parameters of the user at each moment in real time based on the granted authority; A sequence number query subunit is used to read the sequence number corresponding to the operation parameter at each moment in a preset parameter conversion table; the parameter conversion table contains an operation type item and a sequence number item; The time aggregation subunit is used to aggregate the time according to the browsing content to obtain the time period corresponding to each browsing content; The sequence number arrangement subunit is used to count and arrange the sequence numbers corresponding to the operation parameters in the time period based on the time sequence to obtain the actual operation sequence number group; The comparison subunit is used to read the preset standard serial number group of each browsing content, compare the practical serial number group and the standard serial number group, calculate the similarity, and determine the concentration according to the similarity; wherein the concentration is proportional to the similarity.

10. The teaching level evaluation system based on local accounts according to claim 7, characterized in that: The evaluation score determination module comprises: A scheme identification unit is used to receive the teaching scheme input by the teacher, identify the teaching scheme, and determine the importance of different time periods; the identification of the teaching scheme includes a keyword matching process, different keywords correspond to different importance, and the keywords and their importance are both preset parameters; The concentration statistics unit is used to read the concentration of each student at different times and insert it into the same timeline; A number query unit, used to intercept matching points on the time axis according to a preset time step, and read the number of people whose concentration at the matching point is less than a preset concentration threshold; the matching point is a time point; The data application unit is used to query the importance corresponding to the matching points and determine the evaluation score based on the importance and the number of people.

Images