Learning motivation determination method and device, equipment and medium

Abstract

The invention provides a learning motivation determination method and device, equipment and a medium. The method comprises the steps of obtaining a current learning behavior of a target student and at least one first feature related to a learning motivation in response to a learning motivation determination instruction of a user, determining the first feature according to the current learning behavior and a preset first feature type, and determining a learning motivation of the target student according to the at least one first feature and a first sample set; a first probability of each learning motivation category under the condition of all the first features is determined, the first sample set comprises a plurality of first samples, each first sample comprises at least one first feature of a sample student and a sample label, and the sample label is used for indicating that the learning motivation category of the sample student is an active learning category or a passive learning category; and determining the learning motivation category with the maximum first probability in each learning motivation category as the learning motivation category of the current learning behavior of the target student. According to the method, the accuracy of determining the learning motivation is improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, device and medium for determining learning motivation. Background Technology

[0002] With the widespread adoption and deep integration of the internet, corporate online learning platforms have become an important channel for internal education and knowledge sharing. To better recommend courses and enhance learners' interest, it is necessary to determine their learning motivations.

[0003] Existing methods for determining learning motivation suffer from poor effectiveness. Summary of the Invention

[0004] This application provides a method, apparatus, device, and medium for determining learning motivation, in order to solve the problem that the determination of learning motivation in the prior art is not effective.

[0005] Firstly, this application provides a method for determining learning motivation, including:

[0006] In response to the user's instruction to determine learning motivation, the current learning behavior of the target learner and at least one first feature related to learning motivation are obtained, and the first feature is determined based on the current learning behavior and a preset first feature type.

[0007] Based on at least one first feature and a first sample set, determine the first probability of each learning motivation category under all the first features. The first sample set includes multiple first samples, each of which includes at least one first feature of the sample learner and a sample label. The sample label is used to indicate whether the learning motivation category of the sample learner is an active learning category or a passive learning category.

[0008] The learning motivation category with the highest probability in each learning motivation category is determined as the learning motivation category of the target learner's current learning behavior.

[0009] In this application, determining the first probability of each learning motivation category under all conditions of the first feature, based on at least one first feature and a first sample set, includes:

[0010] For each learning motivation category, based on at least one first feature and a first sample set, determine the second probability of all first features under the condition of the learning motivation category;

[0011] Based on the second probability, the first proportion of the learning motivation category in the first sample set, and the second proportion of at least one first feature in the first sample set, the first probability of the learning motivation category under all first features is determined.

[0012] In this application, for each learning motivation category, based on at least one first feature and a first sample set, a second probability of all first features under the condition of the learning motivation category is determined, including:

[0013] For each learning motivation category, based on at least one first feature and a first sample set, determine the third probability of each first feature under the condition of the learning motivation category;

[0014] The second probability of all first features under the condition of learning motivation category is determined by multiplying all third probabilities of the learning motivation category.

[0015] In this application, the first probability of the learning motivation category under all first features is determined based on the second probability, the first proportion of the learning motivation category in the first sample set, and the second proportion of at least one first feature in the first sample set, satisfying:

[0016]

[0017] Among them, X i For at least one first feature, C m For the category of learning motivation, P(C) m |X i Let P(X) be the first probability of the learning motivation category given all the first features. i |C m P(C) represents the second probability of all first features given the learning motivation category. m P(X) represents the first proportion of the learning motivation category in the first sample set. i () is the second proportion of at least one first feature in the first sample set.

[0018] In this application, the method also includes:

[0019] Determine multiple second feature types, and the second feature of each of the multiple second feature types, where the second feature types include student basic feature types and student learning behavior feature types;

[0020] Based on the second sample set, determine the fourth probability of each second feature under each learning motivation category. The second sample set includes multiple second samples, and each second sample includes multiple second features of the sample learners and sample labels.

[0021] Based on the fourth probability of each second feature type, multiple second feature types are filtered to obtain at least one first feature type.

[0022] In this application, based on a second sample set, the fourth probability of each second feature under each learning motivation category is determined, including:

[0023] For each second feature and each learning motivation category, determine the third proportion of samples in the second sample set that simultaneously include the second feature and the learning motivation category;

[0024] The fourth probability of the second feature under the learning motivation category is determined based on the ratio of the third proportion to the fourth proportion of the learning motivation category in the second sample set.

[0025] Based on the fourth probability of the second feature under each learning motivation category, the fourth probability of each second feature under each learning motivation category is obtained.

[0026] In this application, multiple second feature types are filtered based on the fourth probability of each second feature type to obtain at least one first feature type, including:

[0027] For each second feature type, determine the probability threshold for that second feature type;

[0028] If at least one of the fourth probabilities of the second feature type is greater than the probability threshold, then the second feature type is determined as the first feature type.

[0029] In this application, for each second feature type, a probability threshold for the second feature type is determined, including:

[0030] For each second feature type, determine the number of possible values ​​for the second feature of that second feature type;

[0031] The probability threshold for the second feature type is determined based on the ratio of a preset adjustment coefficient to the number of values, and the adjustment coefficient is not greater than the number of values.

[0032] Secondly, this application provides a learning motivation determination device, comprising:

[0033] The acquisition module is used to acquire the target learner's current learning behavior and at least one first feature related to the learning motivation in response to the user's instruction to determine the learning motivation. The first feature is determined based on the current learning behavior and a preset first feature type.

[0034] The first determining module is used to determine the first probability of each learning motivation category under all the first features based on at least one first feature and a first sample set. The first sample set includes multiple first samples, each of which includes at least one first feature of the sample learner and a sample label. The sample label is used to indicate whether the learning motivation category of the sample learner is an active learning category or a passive learning category.

[0035] The second determination module is used to determine the learning motivation category with the highest probability among each learning motivation category as the learning motivation category of the target learner's current learning behavior.

[0036] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0037] The memory stores the instructions that the computer executes;

[0038] The processor executes computer execution instructions stored in memory to implement the method provided in this application.

[0039] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method provided in this application.

[0040] The learning motivation determination method, apparatus, device, and medium provided in this application, in response to a user's learning motivation determination instruction, acquire the current learning behavior of the target learner and at least one first feature related to the learning motivation, then determine the first probability of each learning motivation category under all the first features based on the at least one first feature and a first sample set, and finally determine the learning motivation category with the highest first probability among each learning motivation category as the learning motivation category of the target learner's current learning behavior, thereby improving the accuracy of learning motivation determination. Attached Figure Description

[0041] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0042] Figure 1 A schematic diagram illustrating a scenario for determining learning motivation, provided as an embodiment of this application;

[0043] Figure 2 A flowchart illustrating a method for determining learning motivation provided in an embodiment of this application;

[0044] Figure 3 This is a schematic diagram of the structure of a learning motivation determination device provided in an embodiment of this application;

[0045] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0046] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0047] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0048] To clearly understand the technical solution of this application, the solutions of the prior art will be described in detail first.

[0049] With the widespread adoption and deep integration of the internet, online learning platforms have become an important channel for internal education and knowledge sharing. Learner behavior data is one of the main bases for guiding platform operations, and how to conduct effective data analysis is a major challenge for platform operation.

[0050] Corporate online learning platforms provide learning services to all employees. While learning through video courses and other content resources, learners generate corresponding learning data. Platform operations managers can analyze this data to uncover potential learning behaviors, thereby improving platform operational efficiency. Learning motivation is a key aspect of learning behavior analysis. Since the users of corporate online learning platforms are primarily company employees, their learning behaviors vary. Some learners passively engage in course learning to complete specific tasks, such as required courses or talent development modules. Others learn spontaneously to enhance their domain knowledge. Therefore, from a motivational perspective, learning behaviors can be categorized as passive or active learning. Effectively identifying the learning motivation category helps optimize learning recommendations, improving their accuracy and enhancing the platform's precise operational effectiveness.

[0051] In response to the above situation, the inventors discovered in their research that by determining at least one first feature of the target learner, and then based on the magnitude of the posterior probability of each learning motivation category in the first sample set under all first features, the learning motivation category of the target learner's current learning behavior can be obtained, thereby improving the recognition effect of learning motivation.

[0052] The following describes the application scenarios of the learning motivation determination method provided in the embodiments of this application.

[0053] Figure 1 This application provides a schematic diagram of a scenario for determining learning motivation, as illustrated in the embodiments of this application. Figure 1As shown, the scenario includes a course platform and a server. In response to the user's instruction to determine learning motivation, the server obtains the target learner's current learning behavior and at least one first feature related to learning motivation from the course platform. Then, based on the at least one first feature and a first sample set, it determines the first probability of each learning motivation category under all the first features. Finally, the learning motivation category with the highest first probability among each learning motivation category is determined as the learning motivation category of the target learner's current learning behavior.

[0054] A course platform can refer to a platform where students take courses. The course platform can record each student's basic characteristics and learning behavior characteristics. The basic characteristics of students can include their age, gender, department, and major, while the learning behavior characteristics can include the number of times students have taken courses, the duration of their courses, the courses they have taken, and the keywords they have used.

[0055] Figure 2 This is a flowchart illustrating a method for determining learning motivation provided in an embodiment of this application, as shown below. Figure 2 As shown, the method includes:

[0056] S201. In response to the user's instruction to determine learning motivation, obtain the target learner's current learning behavior and at least one first feature related to learning motivation, wherein the first feature is determined based on the current learning behavior and a preset first feature type.

[0057] In this embodiment, when a user needs to determine the learning motivation of a target learner, the user can send a learning motivation determination instruction to the server. This instruction can include the target learner's personal information, which may refer to information uniquely identifying the target learner, such as name, employee ID, email address, phone number, or combinations thereof. Upon receiving the learning motivation determination instruction, the server reads the target learner's personal information from the instruction and retrieves the target learner's current learning behavior from the course platform based on this information. Current learning behavior can refer to the target learner's learning behavior in a particular course. Alternatively, this embodiment can also determine learning motivation based on the target learner's past learning behavior in a particular course; here, current learning behavior is used as an example. Current learning behavior can include the target learner's basic characteristics and learning behavior characteristics in this course. Since the target learner's current learning behavior contains a large amount of information, a preset first feature type needs to be determined to filter the information and obtain key information. At least one first feature is then retrieved from the target learner's current learning behavior based on this preset first feature type, thus facilitating the determination of the target learner's learning motivation based on the first feature. For example, the first feature type includes the number of times of learning and the duration of learning. The first feature of the target learner is the number of times of learning is the first time and the duration of learning is 1 hour.

[0058] S202. Based on at least one first feature and a first sample set, determine the first probability of each learning motivation category under all the first features. The first sample set includes multiple first samples, each of which includes at least one first feature of the sample learner and a sample label. The sample label is used to indicate whether the learning motivation category of the sample learner is an active learning category or a passive learning category.

[0059] In this embodiment, after obtaining at least one first feature of the target learner, in order to determine the probabilistic relationship between at least one first feature of the target learner and the learning motivation category, it is necessary to determine a first sample set with a certain number of samples. The first sample set needs to include multiple first samples. Each first sample may include at least one first feature of the sample learner and the sample label of the sample learner. The at least one first feature of the sample learner is determined according to the current learning behavior of the sample learner and the preset first feature type.

[0060] Furthermore, methods for determining sample tags for student learners can directly obtain pre-defined student learning motivations from the course platform. Methods for determining student learning motivations on the course platform can include: Firstly, determining motivation based on student evaluations of their current learning motivation. For example, the course platform can include a self-assessment module displayed when a student closes the course page after completing their learning session. This module can determine whether the student's motivation for this learning session was active or passive. Secondly, learning motivation can be determined using a learning behavior determination model. This model is obtained by training a pre-defined neural network model based on learning motivation samples. These learning motivation samples can include student learning characteristics, historical data characteristics, course characteristics, and learning motivation tags.

[0061] In this embodiment, after obtaining at least one first feature and a first sample set, a first probability can be obtained for each learning motivation category in the first sample set under all the first features. The first probability can also be called the posterior probability.

[0062] Specifically, based on at least one first feature and a first sample set, determine the first probability of each learning motivation category under all conditions of the first feature, including:

[0063] For each learning motivation category, based on at least one first feature and a first sample set, determine the second probability of all first features under the condition of the learning motivation category;

[0064] Based on the second probability, the first proportion of the learning motivation category in the first sample set, and the second proportion of at least one first feature in the first sample set, the first probability of the learning motivation category under all first features is determined.

[0065] In this embodiment, in order to obtain the first probability of each learning motivation category under all the first features, for a certain learning motivation category, such as the active learning category, it is necessary to first obtain the second probability of all the first features under the active learning category, the first proportion of the active learning category in the first sample set, and the second proportion of all the first features in the first sample set, and then obtain the first probability of the active learning category under all the first features based on the aforementioned three parameters.

[0066] The "first proportion" of the active learning category in the first sample set can be defined as the ratio of the number of samples in the first sample set whose label is the active learning category to the total number of all first samples. For example, if the number of first samples in the first sample set is 10, and the number of samples whose label is the active learning category is 5, then the first proportion is 5 / 10.

[0067] The second proportion of at least one first feature in the first sample set can refer to the number of samples in the first sample set that simultaneously include all first features. For example, if the first sample set has 10 samples and the first features include first feature A and first feature B, and there are 4 first samples in the first sample set that include both first feature A and second feature B, then the second proportion of all first features in the first sample set is 4 / 10.

[0068] Based on the method described above for obtaining the first probability of the first feature under the active learning category, the first probability of the first feature under the passive learning category is obtained, and finally the first probability of each learning motivation category under all the first features is obtained.

[0069] Furthermore, the first probability of the learning motivation category under all conditions of the first feature satisfies:

[0070]

[0071] Among them, X i For at least one first feature, C m For the category of learning motivation, P(C) m |X i Let P(X) be the first probability of the learning motivation category given all the first features. i |C m P(C) represents the second probability of all first features given the learning motivation category. m P(X) represents the first proportion of the learning motivation category in the first sample set. i () is the second proportion of at least one first feature in the first sample set.

[0072] Specifically, for each learning motivation category, based on at least one first feature and a first sample set, determine the second probability of all first features under the condition of the learning motivation category, including:

[0073] For each learning motivation category, based on at least one first feature and a first sample set, determine the third probability of each first feature under the condition of the learning motivation category;

[0074] The second probability of all first features under the condition of learning motivation category is determined by multiplying all third probabilities of the learning motivation category.

[0075] In this embodiment, taking the active learning category as an example, when at least one first feature contains many first features, calculating the second probability of all first features under the active learning category condition is very costly. To reduce the computational cost, it is assumed that the first features are conditionally independent of each other, that is, there is no dependency between the first features. First, the third probability of each first feature under the active learning category condition is obtained. Then, based on the product of all third probabilities corresponding to the active learning category, the second probability of all first features under the active learning category condition is obtained. Using the same method, the second probability of all first features under the passive learning category condition can be obtained.

[0076] S203. Determine the learning motivation category with the highest probability in each learning motivation category as the learning motivation category of the target learner's current learning behavior.

[0077] In this embodiment, after obtaining the first probability of each learning motivation category under all the first features, it represents the probability of each learning motivation category occurring in the first sample set given that all the first features occur. Therefore, the learning motivation category with the highest first probability among all learning motivation categories is determined as the learning motivation category of the target learner's current learning behavior. For example, if the first probability of the active learning category under all the first features is 0.5, and the first probability of the passive learning category under all the first features is 0.7, then the passive learning category is taken as the learning motivation category of the target learner's current learning behavior.

[0078] In one possible implementation, the method for determining at least one preset first feature type may include:

[0079] Determine multiple second feature types, and the second feature of each of the multiple second feature types, where the second feature types include student basic feature types and student learning behavior feature types;

[0080] Based on the second sample set, determine the fourth probability of each second feature under each learning motivation category. The second sample set includes multiple second samples, and each second sample includes multiple second features of the sample learners and sample labels.

[0081] Based on the fourth probability of each second feature type, multiple second feature types are filtered to obtain at least one first feature type.

[0082] In this embodiment, to determine the feature types related to learning motivation types, a large number of second feature types are summarized. Due to the large number of second feature types, to reduce computational complexity and errors in determining learning motivation, it is necessary to identify first feature types strongly correlated with learning motivation types from these second feature types. This allows for the filtering of learner learning behavior information to obtain key information, thereby facilitating a more accurate determination of learner learning motivation. Specifically, firstly, multiple second feature types and second features for each second feature type are determined. The second feature of a second feature type can refer to all values ​​of the second feature type. For example, if the second feature type is learning time, and the values ​​of learning time include morning (8:00-12:00), afternoon (12:00-18:00), evening (18:00-22:00), and other time periods, then the second feature includes four features: morning (8:00-12:00), afternoon (12:00-18:00), evening (18:00-22:00), and other time periods.

[0083] Furthermore, a second sample set is constructed. Using this second sample set, the correlation between each second feature type and the learning motivation type is determined. The second sample set includes multiple second samples, each containing multiple second features of the student and a sample label. The student's multiple second features correspond to the second feature type. For example, if the second feature type includes learning frequency, learning duration, learning time, and learning course, then the student's second features would correspond to: learning frequency 1st time, learning duration 1 hour, learning time in the morning, and learning course A. The sample label indicates whether the student's learning motivation category is active learning or passive learning. The first and second sample sets can contain features from the same student or features from different students; this embodiment does not impose such limitations.

[0084] After obtaining the second sample set, it is necessary to determine the fourth probability of each second feature under each learning motivation category, thereby obtaining the fourth probability of each second feature type. Based on the fourth probability of each second feature type, the second feature types are filtered to obtain at least one first feature type. The fourth probability can also be called the confidence level.

[0085] Specifically, methods for determining the fourth probability may include:

[0086] For each second feature and each learning motivation category, determine the third proportion of samples in the second sample set that simultaneously include the second feature and the learning motivation category;

[0087] The fourth probability of the second feature under the learning motivation category is determined based on the ratio of the third proportion to the fourth proportion of the learning motivation category in the second sample set.

[0088] Based on the fourth probability of the second feature under each learning motivation category, the fourth probability of each second feature under each learning motivation category is obtained.

[0089] In this embodiment, the fourth probability can represent the probability of the second feature occurring in the second sample set for each learning motivation category. Taking the active learning category as an example, when the second feature is learning time (morning), first determine the proportion of target samples in the second sample set whose label is active learning category; for distinction, this is referred to as the third proportion. Then determine the proportion of active learning category in the second sample set; this is referred to as the fourth proportion. Finally, the ratio of the third proportion to the fourth proportion is used as the fourth probability of learning time (morning) under the active learning category condition. According to the above method, the fourth probability of learning time (morning) under the passive learning category condition can be obtained, thereby obtaining the fourth probability of any second feature in the second feature type under each passive learning category condition.

[0090] Specifically, based on the fourth probability of each second feature type, multiple second feature types are filtered to obtain at least one first feature type, which may include:

[0091] For each second feature type, determine the probability threshold for that second feature type;

[0092] If at least one of the fourth probabilities of the second feature type is greater than the probability threshold, then the second feature type is determined as the first feature type.

[0093] In this embodiment, the probability threshold of each second special type is compared with the fourth probability of each second feature type. If any fourth probability of the second feature type is greater than the probability threshold, the second feature type is determined as the first feature type.

[0094] Specifically, the method for determining the probability threshold of the second feature type may include:

[0095] For each second feature type, determine the number of possible values ​​for the second feature of that second feature type;

[0096] The probability threshold for the second feature type is determined based on the ratio of a preset adjustment coefficient to the number of values, and the adjustment coefficient is not greater than the number of values.

[0097] For example, the second feature type is learning time, and the values ​​of learning time include morning (8:00-12:00), afternoon (12:00-18:00), evening (18:00-22:00), and other time periods. The number of possible values ​​for the second feature is 4, and the adjustment coefficient is preset to 3. Therefore, the probability threshold for learning time is 3 / 4, meaning that the fourth probability of learning time needs to reach 3 times the average probability. If the third probability of learning time in the morning under the passive learning category is 4 / 5, then learning time can be determined as the first feature type.

[0098] This application provides a method for determining learning motivation. In response to a user's instruction to determine learning motivation, the method acquires the current learning behavior of the target learner and at least one first feature related to the learning motivation. Then, based on the at least one first feature and a first sample set, it determines the first probability of each learning motivation category under all the first features. Finally, it determines the learning motivation category with the highest first probability among each learning motivation category as the learning motivation category of the target learner's current learning behavior, thereby improving the accuracy of learning motivation determination.

[0099] Figure 3 This is a schematic diagram of the structure of a learning motivation determination device provided in an embodiment of this application, as shown below. Figure 3 As shown, the device includes:

[0100] The acquisition module 301 is used to acquire the current learning behavior of the target learner and at least one first feature related to the learning motivation in response to the user's instruction to determine the learning motivation. The first feature is determined based on the current learning behavior and a preset first feature type.

[0101] The first determining module 302 is used to determine the first probability of each learning motivation category under all the first features based on at least one first feature and a first sample set. The first sample set includes multiple first samples, each first sample including at least one first feature of the sample learner and a sample label, the sample label being used to indicate whether the learning motivation category of the sample learner is an active learning category or a passive learning category.

[0102] The second determining module 303 is used to determine the learning motivation category with the highest probability among each learning motivation category as the learning motivation category of the target learner's current learning behavior.

[0103] In some embodiments, the first determining module 302 is further configured to:

[0104] For each learning motivation category, based on at least one first feature and a first sample set, determine the second probability of all first features under the condition of the learning motivation category;

[0105] Based on the second probability, the first proportion of the learning motivation category in the first sample set, and the second proportion of at least one first feature in the first sample set, the first probability of the learning motivation category under all first features is determined.

[0106] In some embodiments, the first determining module 302 is further configured to:

[0107] For each learning motivation category, based on at least one first feature and a first sample set, determine the third probability of each first feature under the condition of the learning motivation category;

[0108] The second probability of all first features under the condition of learning motivation category is determined by multiplying all third probabilities of the learning motivation category.

[0109] In some embodiments, the first determining module 302 is further configured to satisfy:

[0110]

[0111] Among them, X i For at least one first feature, C m For the category of learning motivation, P(C) m |X i Let P(X) be the first probability of the learning motivation category given all the first features. i |C m P(C) represents the second probability of all first features given the learning motivation category. m P(X) represents the first proportion of the learning motivation category in the first sample set. i () is the second proportion of at least one first feature in the first sample set.

[0112] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 4 As shown, the electronic device 40 includes:

[0113] The electronic device 40 may include a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a communication component 403, and other components. The processor 401, memory 402, and communication component 403 are connected via a bus 404.

[0114] In the specific implementation process, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to execute the learning motivation determination method described above.

[0115] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0116] In the above Figure 4 In the illustrated embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0117] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0118] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0119] In some embodiments, a computer program product is also provided, comprising a computer program or instructions that, when executed by a processor, implement the steps in any of the above-described methods for determining learning motivation.

[0120] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0121] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0122] Therefore, embodiments of this application provide a computer-readable storage medium storing a plurality of instructions that can be loaded by a processor to execute the steps in any of the learning motivation determination methods provided in embodiments of this application.

[0123] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0124] According to one aspect of this application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium.

[0125] Since the instructions stored in the storage medium can execute the steps in any of the learning motivation determination methods provided in the embodiments of this application, the beneficial effects that any of the learning motivation determination methods provided in the embodiments of this application can achieve can be realized, as detailed in the preceding embodiments, and will not be repeated here.

[0126] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0127] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for determining learning motivation, characterized in that, include: In response to a user's instruction to determine learning motivation, the system acquires the target learner's current learning behavior and at least one first feature related to learning motivation, wherein the first feature is determined based on the current learning behavior and a preset first feature type. Based on the at least one first feature and the first sample set, determine the first probability of each learning motivation category under all the first features. The first sample set includes a plurality of first samples, each first sample including at least one first feature of the sample learner and a sample label, the sample label being used to indicate whether the learning motivation category of the sample learner is an active learning category or a passive learning category. The learning motivation category with the highest probability in each learning motivation category is determined as the learning motivation category of the target learner's current learning behavior.

2. The method according to claim 1, characterized in that, Determining the first probability of each learning motivation category under all the first features based on the at least one first feature and the first sample set includes: For each learning motivation category, based on the at least one first feature and the first sample set, determine the second probability of all first features under the condition of the learning motivation category; Based on the second probability, the first proportion of the learning motivation category in the first sample set, and the second proportion of the at least one first feature in the first sample set, the first probability of the learning motivation category under all first features is determined.

3. The method according to claim 2, characterized in that, For each learning motivation category, determining the second probability of all first features under the condition of the learning motivation category, based on the at least one first feature and the first sample set, includes: For each learning motivation category, based on the at least one first feature and the first sample set, determine the third probability of each first feature under the condition of the learning motivation category; The second probability of all first features under the condition of the learning motivation category is determined by multiplying all third probabilities of the learning motivation category.

4. The method according to claim 2, characterized in that, The first probability of the learning motivation category under all first features is determined based on the second probability, the first proportion of the learning motivation category in the first sample set, and the second proportion of the at least one first feature in the first sample set, satisfying: Among them, X i For the at least one first feature, C m For the aforementioned learning motivation category, P(C) m |X i P(X) represents the first probability of the learning motivation category under all conditions of the first feature. i |C m P(C) represents the second probability of all first features given the learning motivation category. m P(X) represents the first proportion of the learning motivation category in the first sample set. i ) represents the second proportion of the at least one first feature in the first sample set.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: Determine multiple second feature types, and a second feature of each of the multiple second feature types, wherein the second feature types include student basic feature types and student learning behavior feature types; Based on the second sample set, determine the fourth probability of each second feature under each learning motivation category. The second sample set includes multiple second samples, and each second sample includes multiple second features of the sample learners and sample labels. Based on the fourth probability of each second feature type, the plurality of second feature types are filtered to obtain at least one first feature type.

6. The method according to claim 5, characterized in that, The step of determining the fourth probability of each second feature under each learning motivation category based on the second sample set includes: For each second feature and each learning motivation category, determine the third proportion of samples in the second sample set that simultaneously include the second feature and the learning motivation category; The fourth probability of the second feature under the learning motivation category is determined based on the ratio of the third proportion to the fourth proportion of the learning motivation category in the second sample set. Based on the fourth probability of the second feature under the learning motivation category, the fourth probability of each second feature under the condition of each learning motivation category is obtained.

7. The method according to claim 5, characterized in that, The step of filtering the plurality of second feature types according to the fourth probability of each second feature type to obtain at least one first feature type includes: For each second feature type, determine the probability threshold for the second feature type; If at least one of the fourth probabilities of the second feature type is greater than the probability threshold, then the second feature type is determined as the first feature type.

8. The method according to claim 7, characterized in that, Determining the probability threshold for each second feature type includes: For each second feature type, determine the number of values ​​for the second feature of that second feature type; The probability threshold of the second feature type is determined based on the ratio of a preset adjustment coefficient to the number of values, wherein the adjustment coefficient is not greater than the number of values.

9. A learning motivation determination device, characterized in that, include: The acquisition module is used to acquire the current learning behavior of the target learner and at least one first feature related to the learning motivation in response to the user's instruction to determine the learning motivation. The first feature is determined based on the current learning behavior and a preset first feature type. The first determining module is configured to determine the first probability of each learning motivation category under all the first features based on the at least one first feature and the first sample set. The first sample set includes a plurality of first samples, each first sample including at least one first feature of the sample learner and a sample label, the sample label being used to indicate whether the learning motivation category of the sample learner is an active learning category or a passive learning category. The second determination module is used to determine the learning motivation category with the highest probability among each learning motivation category as the learning motivation category of the target learner's current learning behavior.

10. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-8.

Images