Learning motivation detection method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of intelligent education, in particular to a learning incentive detection method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a log file of a learner, and carrying out the separation detection of the log file, and obtaining the participation information of the learner; if it is judged that the learner is out of learning according to the participation degree information, dialogue information is generated based on a preset item questionnaire, and the learner is inquired based on the dialogue information to obtain an incentive file of the learner; and generating a personalized intervention scheme for the learner based on the participation degree information and the motivation archive. Therefore, the motivation state of the learner can be recognized more accurately and timely in combination with automatic monitoring and active self-evaluation of the behavior of the learner, the learning process is quickly intervened and optimized, and the teaching efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent educational technology, and in particular to a learning motivation detection method, device, electronic device and storage medium. Background Art

[0002] Intelligent Courseware is an advanced teaching resource that integrates digital and intelligent technologies, and is an important part of the online learning system. It is built based on digital technology, converting traditional textbooks, teaching materials and various educational resources into digital forms that can be processed by computers, which is convenient for storage, management and dissemination. Intelligent Courseware uses multimedia, animation, simulation and other means to provide a highly interactive learning experience, enabling students to understand and master knowledge in a dynamic and visual way, enhancing participation and fun in the learning process. In addition, intelligent courseware combines artificial intelligence and big data analysis technology, and can dynamically adjust and personalize according to learners' learning behaviors, ability levels and personalized needs to achieve adaptive teaching.

[0003] Among them, motivation has always been important for learning. It exists in the learning process and has a great impact on the learning process. In the offline classroom environment, teachers have a variety of sources to infer the motivational state of learners, such as visual clues, imitation, facial expressions, etc. Inactive students will be discovered by teachers and given timely reminders. However, these sources cannot be obtained by online learning systems, resulting in low teaching efficiency. Summary of the invention

[0004] In order to overcome the deficiencies in the prior art, the present application provides a learning motivation detection method, device, electronic device and storage medium, which can accurately judge the learner's motivation state and intervene to improve teaching efficiency.

[0005] In a first aspect, the present application provides a learning motivation detection method, the method comprising the following steps:

[0006] Obtaining a learner's log file, and performing a disengagement test on the log file to obtain the learner's engagement information;

[0007] If it is determined according to the engagement information that the learner is disengaged from learning, generating dialogue information based on a preset project questionnaire, and questioning the learner based on the dialogue information to obtain the learner's motivation profile;

[0008] A personalized intervention plan for the learner is generated based on the engagement information and the motivation profile.

[0009] In a possible implementation manner, performing disengagement detection on the log file to obtain the learner's engagement information includes the following steps:

[0010] Extracting the learner's operation behavior data from the log file;

[0011] Calculating learning motivation-related attributes according to the operation behavior data, and performing motivation prediction on the calculated learning motivation-related attributes based on the constructed disengagement detection decision tree to obtain the motivation state category of the learner; the motivation state category includes disengagement and engagement;

[0012] The motivation state category is incorporated into the learner's engagement information; wherein, if the motivation state category is disengagement, it is determined that the learner is disengaged from learning.

[0013] In a possible implementation manner, performing disengagement detection on the log file to obtain the learner's participation information further includes the following steps:

[0014] Analyzing the change of the learner's participation within a set time according to the operation behavior data, and judging the learner's non-participation mode and the start time and duration of the non-participation period according to the change of the participation; the non-participation mode includes long-term non-participation and rapid non-participation;

[0015] The learner's non-participation pattern and the start time and duration of the non-participation period are incorporated into the learner's engagement information.

[0016] In a possible implementation, the learning motivation related attributes include reading time and test scores, and the disengagement detection decision tree divides the learner's motivation state category according to the reading time and the test scores in the following manner:

[0017] Setting a first time threshold, a first score threshold, and a second score threshold; wherein the first time threshold is greater than the set time for analyzing the change in participation, and the first score threshold is less than the second score threshold;

[0018] If the reading time is less than or equal to the first time threshold, or the reading time is greater than the first time threshold and the test score is between the first score threshold and the second score threshold, classifying the learner's motivation state category as disengagement;

[0019] If the reading time is greater than or equal to the first time threshold and the test score is greater than the second score threshold, or the reading time is greater than or equal to the first time threshold and the test score is less than the first score threshold, the learner's motivation state category is classified as participation.

[0020] In a possible implementation, the project questionnaire is preset in the following manner:

[0021] Determining the motivational characteristics to be measured; the motivational characteristics include self-efficacy, self-regulation, and goal orientation;

[0022] selecting a plurality of preset items from validated questionnaires or created items for each of said motivational characteristics;

[0023] The target items representing each motivation characteristic are screened out from the plurality of preset items by means of expert ranking, the target items are formed into a project questionnaire, and the validity and reliability of the project questionnaire are verified.

[0024] In a possible implementation manner, the step of questioning the learner based on the dialogue information to obtain the learner's motivation profile includes the following steps:

[0025] After obtaining the learner's consent to conduct motivation assessment, each round of dialogue information is sent to the learner, and reply information for each round of dialogue information is obtained;

[0026] According to the dialogue information and response information of each round, motivation characteristic data of the learner is obtained;

[0027] The motivational characteristic data are organized into a motivational profile, and permissions for the learner and / or external intervener are set to update the motivational profile.

[0028] In a possible implementation, generating a personalized intervention plan for the learner includes one or more of adjusting the learning path and content, setting a reward mechanism, and providing learning strategy guidance.

[0029] In a second aspect, the present application provides a learning motivation detection device, the device comprising:

[0030] A monitoring module, used for obtaining a learner's log file and performing a disengagement detection on the log file to obtain the learner's participation information;

[0031] A dialogue module, for generating dialogue information based on a preset project questionnaire if it is determined that the learner is disengaged from learning according to the engagement information, and for questioning the learner based on the dialogue information to obtain the learner's motivation profile;

[0032] An intervention module is used to generate a personalized intervention plan for the learner based on the engagement information and the motivation profile.

[0033] In a third aspect, the present application provides an electronic device comprising: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the learning motivation detection method as described in any one of the first aspects are performed.

[0034] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the learning motivation detection method as described in any one of the first aspects are executed.

[0035] The present embodiment provides a learning motivation detection method, device, electronic device and storage medium, which obtains the learner's log file, and performs disengagement detection on the log file to obtain the learner's engagement information; if the learner is judged to be disengaged from learning based on the engagement information, dialogue information is generated based on a preset project questionnaire, and the learner is questioned based on the dialogue information to obtain the learner's motivation profile; and a personalized intervention plan for the learner is generated based on the engagement information and the motivation profile. Thus, by combining the automatic monitoring of learner behavior with active self-assessment, the learner's motivation status can be identified more accurately and timely, and rapid intervention can be performed to optimize the learning process and improve teaching efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A flow chart of a learning motivation detection method according to an embodiment of the present application is shown;

[0038] Figure 2 A flowchart of performing disengagement detection on the log file to obtain the learner's participation information according to an embodiment of the present application is shown;

[0039] Figure 3 A schematic diagram of the structure of a departure detection decision tree according to an embodiment of the present application is shown;

[0040] Figure 4 A flowchart of a preset item questionnaire according to an embodiment of the present application is shown;

[0041] Figure 5A schematic diagram showing the structure of a learning motivation detection device according to an embodiment of the present application is shown;

[0042] Figure 6 A structural block diagram of an electronic device described in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0043] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0044] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0045] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0046] In view of the technical problems raised by the background technology, the present application provides a learning motivation detection method, device, electronic device and storage medium, which can accurately judge the motivation state of learners and intervene to improve teaching efficiency.

[0047] In one embodiment, see the attached specification Figure 1 The present application provides a learning motivation detection method, which is applied to a digital learning courseware platform, and the method comprises the following steps:

[0048] S1. Obtain a learner's log file, and perform a disengagement test on the log file to obtain the learner's participation information;

[0049] S2. If it is determined according to the engagement information that the learner is disengaged from learning, generate dialogue information based on a preset project questionnaire, and question the learner based on the dialogue information to obtain the learner's motivation profile;

[0050] S3. Generate a personalized intervention plan for the learner based on the engagement information and the motivation profile.

[0051] In step S1, non-intrusive disengagement detection of learners is mainly carried out through log file analysis, so that learning motivation can be automatically monitored without significantly interfering with the learning process. Figure 2 , the step of performing disengagement detection on the log file to obtain the learner's participation information comprises the following steps:

[0052] S101, extracting the learner's operation behavior data from the log file;

[0053] S102, calculating learning motivation-related attributes according to the operation behavior data, and performing motivation prediction on the calculated learning motivation-related attributes based on the constructed disengagement detection decision tree to obtain the motivation state category of the learner; the motivation state category includes disengagement and engagement;

[0054] S103, incorporating the motivation status category into the learner's engagement information; wherein, if the motivation status category is disengagement, determining that the learner is disengaged from learning.

[0055] In step S101, the log files of learners on the digital courseware learning platform are fully collected, and the log files record various operation behavior information of learners on the digital courseware learning platform, including rich event data. For example, the target selected by the learner (selected from multiple targets), parameter settings (including quantity and time spent on selection), reading pages (number of pages and average time to read each page), pre-test (number of times, average time, number of correct answers, number of wrong answers), test (number of times, average time, number of correct answers, number of wrong answers) and access to hyperlinks, manuals, help, terminology, communication, search, notes, statistics, feedback and other functions (number of visits and average time for each visit).

[0056] Furthermore, different types of event data are integrated for subsequent calculation and analysis. For example, data related to reading (reading page number, reading time, etc.) are aggregated, and data related to testing (various indicators of pre-test and test) are organized together. On the one hand, this can ensure the integrity and availability of the data, and on the other hand, it is convenient to create a database with the same indicators for each learner.

[0057] In step S102, the learning motivation related attributes include test scores, reading time, number of visited pages, and time to solve test problems. Among them, the test score calculation is performed, that is, the percentage of correctly answered tests is calculated, which is obtained by dividing the number of correct tests by the total number of tests; the reading time calculation is performed, that is, the time spent on the page in the session is taken as the reading time, and calculated as the sum of the time spent on visiting each page; the number of visited pages is calculated, that is, the number of pages visited by the learner is directly counted; the time to solve the test problem is calculated, that is, the time spent on the test is calculated by the sum of the time spent on each test.

[0058] Furthermore, the calculated learning motivation-related attributes such as test scores, reading time, number of pages visited, and test problem solving time were used as input data to construct a disengagement detection decision tree using the J48 algorithm, which automatically finds the best decision rule that can classify the learner status through data analysis and divides the learners into different categories, such as disengaged learners and engaged learners.

[0059] In one embodiment, the constructed departure detection decision tree is shown in the attached specification. Figure 3 , the most important learning motivation-related attribute for predicting learners' motivational status is reading time. For example, when the reading time is less than 2688 seconds (about 45 minutes), it means that insufficient time is invested in learning, and the learner is preliminarily classified as disengaged; if the reading time exceeds 2688 seconds, it is further classified according to the test scores. If the test score ratio is higher than 63%, it means that the learner has shown high enthusiasm and good learning ability in learning, and the learner is classified as engaged; if the test score ratio is between 49% and 63%, it means that there are certain problems in the degree of concentration or understanding of the learning content, and the learner is classified as disengaged; if the test score ratio is lower than 49%, it means that the learner is in the initial stage of knowledge accumulation and needs more time and help to improve the score, but still maintains a positive learning attitude, and the learner is classified as engaged.

[0060] In addition, the present application also constructs a confusion matrix, as shown in Table 1, where the elements in the matrix represent the number of test examples with actual categories as rows and predicted categories as columns, and the quality of the disengagement detection decision tree is evaluated by calculating the proportion of diagonal elements of the confusion matrix. In this embodiment, the diagonal of the confusion matrix indicates that 75% of the examples are correctly classified and 25% of the examples are misclassified, indicating that the constructed disengagement detection decision tree can accurately classify the learner's disengagement state to a certain extent.

[0061]

[0062] Table 1

[0063] In step S103, the motivation state category obtained by the disengagement detection decision tree is incorporated into the learner's engagement information for subsequent generation of a personalized intervention plan. If the motivation state category is disengagement, the learner is judged to be disengaged from learning, and then step S2 is executed.

[0064] Furthermore, performing disengagement detection on the log file to obtain the learner's participation information also includes the following steps: analyzing the learner's participation changes within a set time based on the operational behavior data, and judging the learner's non-participation mode and the start time and duration of the non-participation period based on the participation changes; the non-participation mode includes long-term non-participation and rapid non-participation; and incorporating the learner's non-participation mode and the start time and duration of the non-participation period into the learner's participation information.

[0065] This is because the classification result obtained based on the disengagement detection decision tree is based on 45 minutes as the boundary, and it is impossible to explain the learner's learning motivation level in the first 45 minutes. Only after 45 minutes can the learner be characterized as disengaged or engaged, and at that time, the learner who has lost motivation is likely to have logged off the digital courseware learning platform. At this time, even if the learner's disengagement state is understood, effective intervention measures cannot be taken to restore their learning enthusiasm. Therefore, this application needs to further analyze the user's operation behavior data in a short time (such as 10-15 minutes), track the changes in the learner's participation in this time period, subdivide its non-participation mode, long-term non-participation or fast non-participation, and obtain the start time and duration of the non-participation period based on the timestamp record of the log file. For example, the long-term non-participation mode is characterized by staying on one or very few pages for a long time; the fast non-participation mode is characterized by quickly browsing pages. Once the motivation level is detected to drop, the system can immediately initiate corresponding intervention measures, such as pushing personalized encouragement messages, providing targeted learning tips, adjusting the difficulty or form of learning content to re-attract learners' attention, etc. In this way, it is possible to seize the opportunity to adjust the user's learning status before he logs out, better meeting the needs of real-time monitoring and intervention of learning motivation in online learning environments.

[0066] The learner's motivation state category, non-participation mode, and the start time and duration of the non-participation period are summarized as the learner's participation information, which will be more perfect for subsequent generation of personalized intervention plans.

[0067] In step S2, mainly when the motivation state category of the learner obtained based on the disengagement detection decision tree is disengagement, the learner's self-assessment needs to be conducted through dialogue. In one embodiment, when starting a dialogue with the learner, the learner's consent to conduct motivation assessment should be obtained first, and the learner should be clearly explained that the reason for interrupting learning is based on the result of the disengagement detection. At the same time, the learner should be clearly informed that the purpose of this dialogue is to obtain his motivation profile for subsequent personalized intervention, and the importance of obtaining motivation profiles for improving his learning experience and effect should be explained. For example, in a clear and easy-to-understand way, the learner is asked whether he agrees to answer a series of questions to obtain his motivation profile. The expression of the questions adopts friendly and non-compulsive language to give the learner full autonomy to choose; if the learner agrees, the subsequent motivation profile acquisition process is entered, and each round of dialogue information is sent to the learner (the dialogue information is generated based on a preset item questionnaire representing the motivation characteristics), and the reply information of each round of dialogue information is obtained; then, according to the dialogue information and reply information of each round, the learner's motivation feature data is obtained, and the motivation feature data is organized into a motivation profile.

[0068] See the instruction manual Figure 4 ,In this application, the project questionnaire is preset in the following way:

[0069] S201, determining the motivational characteristics to be measured; the motivational characteristics include self-efficacy, self-regulation and goal orientation;

[0070] S202, selecting a plurality of preset items from a verified questionnaire or a created item for each of the motivational characteristics;

[0071] S203, selecting target projects representing each motivation characteristic from the plurality of preset projects by means of expert ranking, forming project questionnaires from the target projects, and verifying the validity and reliability of the project questionnaires.

[0072] Specifically, in step S201, self-efficacy, self-regulation and goal orientation are determined as motivational characteristics to be measured because self-efficacy affects learning motivation and persistence. Learners with high self-efficacy believe that they are capable of completing learning tasks, and this belief will inspire them to actively engage in learning. Self-regulation specifically refers to time management and emotional regulation. Learners who are good at self-regulation can reasonably arrange their study time, formulate effective study plans and strictly implement them, and maintain a positive learning attitude, thereby improving their learning efficiency. Clear goal orientation provides learners with learning direction and motivation, and different learning environments and tasks may require different goal orientations. Understanding learners' goal orientations helps provide them with more suitable learning resources and environments, and promotes the improvement of learning effects.

[0073] In step S202, motivational characteristics can be measured starting from a validated questionnaire, or if no validated tool is available, items can be created. For example, the "Pattern of Adaptive Learning (PALS)" questionnaire can be used to measure self-efficacy and goal orientation through a series of questions related to learners' cognition of their ability to complete learning tasks; the IQ Learn tool can be used to measure learners' self-regulation ability by asking them questions about time management, self-management, and persistence; and items (questions or options) can be created for perceived task difficulty, attribution (including control locus and stable / unstable dimensions), and non-participatory goal orientation.

[0074] In step S203, the questionnaire items are finally determined by expert screening. The experts select a certain number of items for motivation characteristics (based on the importance, relevance and effectiveness of learning motivation measurement. For example, for self-efficacy, there are 5 items in the original questionnaire, and according to the requirements, 3 items that they think are the most critical need to be selected as target items.

[0075] In one embodiment, the selection and ranking results of each expert are collected, the selection frequency (i.e., the proportion of times selected by experts) and the average ranking value of each item are calculated, and the selection frequency and the average ranking value are comprehensively considered, for example, a certain weight is given to items with higher selection frequency, while considering items with lower average ranking (i.e., more important), and the comprehensive ranking of each item is obtained through a weighted average algorithm. According to the comprehensive ranking, the top ranked items are selected to determine the final questionnaire content.

[0076] Furthermore, according to the comments of experts, the project questionnaire can be modified and improved accordingly, such as adjusting the question wording to make it more understandable, adding or modifying some items to enhance the validity and reliability of the questionnaire.

[0077] In addition, the present application also conducts reliability experiments and concurrent validity experiments to ensure that the project questionnaire set by the present application can accurately and reliably measure the motivation characteristics of learners. For example, a representative group of learner samples are selected, and they are asked to complete the same motivation assessment questionnaire twice in a similar learning environment at a certain interval (such as one week), and the correlation coefficient between the two measurement results is calculated to evaluate the reliability of the internal consistency of the questionnaire. A high correlation coefficient indicates that the project questionnaire has good stability and reliability when measuring the motivation characteristics of the same learner at different times; another group of learner samples (different from the reliability experiment samples, but with similar characteristic distribution) are selected, and they are evaluated using the project questionnaire set by the present application and the existing, widely recognized complete motivation measurement tool at the same time, and the correlation coefficient between the project questionnaire of the present application and the measurement results of the complete tool is calculated. If the correlation coefficient is high, it means that the project questionnaire set by the present application has good consistency with the existing mature tools when measuring the same or similar motivation characteristics, that is, it has high concurrent validity.

[0078] In practical applications, motivation profiles can be updated to reflect changes in learners’ learning status in real time and used to optimize teaching strategy adjustments. One way is that learners have the authority to update motivation characteristics, whether simply modifying the value or completing the project questionnaire again; another way is that the instructor has the authority to update the learner’s motivation characteristics and fine-tune its value.

[0079] In step S3, based on the obtained engagement information and motivation profile, the detected learner motivation state and motivation characteristics are combined, and a personalized intervention strategy is formulated according to social cognitive learning theory to improve the learner's motivation state and learning behavior, including one or more of adjusting the learning path and content, setting up a reward mechanism, and providing learning strategy guidance.

[0080] For example, intervention measures can be different based on the distinction between long-term and fast-disengagement patterns. For long-term learners, personalized encouragement messages can be pushed to remind them of their learning goals and progress, or additional learning resources can be provided to help them overcome difficulties; for fast-disengagement learners, the presentation of learning content can be adjusted, interactive elements can be added, or more attractive multimedia formats can be used to increase their engagement. Such personalized intervention measures can help increase learners' enthusiasm for re-engagement in learning and improve learning outcomes.

[0081] Alternatively, dynamically adjust the difficulty, sequence, or presentation of learning content based on the learner's motivation profile and engagement information to better match the learner's interest and ability level. For example, if a learner shows low motivation for a topic, the system can automatically adjust to more challenging or interesting content, or provide more background knowledge to increase the learner's interest. Motivate learners by setting various forms of rewards (such as badges, points, virtual rewards, etc.). These rewards can be associated with the learner's engagement and motivation status. For example, when a learner shows high engagement at a certain stage, the system can automatically issue rewards to further enhance their learning motivation. Provide personalized learning strategy suggestions. For example, if a learner performs poorly in time management, the system can provide time management tips or tools; if a learner has difficulty in self-regulation, the system can provide relevant training or suggestions. Improve learner engagement by increasing the interaction between learners and the system, and between learners. For example, the system can automatically arrange for learners to participate in group discussions, online Q&A, and other activities, or provide real-time feedback to help learners understand their learning progress and achievements in a timely manner. Leverage learners’ social networks or learning communities to provide peer support to learners. For example, the system can automatically match learners with similar learning goals or interests to form learning groups to support and encourage each other. Provide personalized feedback and motivational information. For example, the system can provide positive feedback to enhance learners’ self-efficacy based on their sense of self-efficacy; or push relevant learning resources or activity information based on learners’ interests and hobbies. Influence learners’ motivational states by adjusting the settings of the learning environment (such as background music, interface style, etc.). For example, the system can automatically adjust the color matching or background music of the learning interface based on learners’ preferences to create an environment more conducive to learning.

[0082] It can be seen that the learning motivation detection method provided by the present application can automatically monitor the learner's motivation status without obviously interfering with the learning process by analyzing the learner's behavior log, and allow the learner to conduct self-assessment through dialogue. The combination of the two can more accurately and timely identify the learner's motivation status, conduct rapid intervention, optimize the learning process, and improve teaching efficiency.

[0083] Based on the same inventive concept, a learning motivation detection device is also provided in the embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the above-mentioned learning motivation detection method in the embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0084] As the instruction manual Figure 5 As shown, a learning motivation detection device provided in an embodiment of the present application is applied to a digital learning courseware platform, and the device includes:

[0085] The monitoring module 501 is used to obtain the learner's log file and perform a disengagement detection on the log file to obtain the learner's participation information;

[0086] A dialogue module 502 is used for generating dialogue information based on a preset project questionnaire if it is determined that the learner is disengaged from learning according to the engagement information, and questioning the learner based on the dialogue information to obtain the learner's motivation profile;

[0087] The intervention module 503 is used to generate a personalized intervention plan for the learner based on the engagement information and the motivation profile.

[0088] In one embodiment, the engagement monitoring module 501 performs disengagement detection on the log file to obtain the learner's engagement information, including: extracting the learner's operational behavior data from the log file; calculating learning motivation-related attributes based on the operational behavior data, and performing motivation prediction on the calculated learning motivation-related attributes based on a constructed disengagement detection decision tree to obtain the learner's motivation state category; the motivation state category includes disengagement and engagement; incorporating the motivation state category into the learner's engagement information; wherein, if the motivation state category is disengagement, judging that the learner is disengaged from learning.

[0089] In one embodiment, the engagement monitoring module 501 performs disengagement detection on the log file to obtain the learner's engagement information, and also includes: analyzing the learner's engagement changes within a set time based on the operational behavior data, and judging the learner's non-participation mode and the start time and duration of the non-participation period based on the engagement changes; the non-participation mode includes long-term non-participation and rapid non-participation; and incorporating the learner's non-participation mode and the start time and duration of the non-participation period into the learner's engagement information.

[0090] In one embodiment, the learning motivation-related attributes include reading time and test scores, and the device also includes a classification module: used to set a first time threshold, a first score threshold, and a second score threshold; wherein the first time threshold is greater than the set time for analyzing changes in participation, and the first score threshold is less than the second score threshold; if the reading time is less than or equal to the first time threshold, or the reading time is greater than the first time threshold and the test score is between the first score threshold and the second score threshold, the learner's motivation state category is classified as disengagement; if the reading time is greater than or equal to the first time threshold and the test score is greater than the second score threshold, or the reading time is greater than or equal to the first time threshold and the test score is less than the first score threshold, the learner's motivation state category is classified as participation.

[0091] In one embodiment, the device also includes a setting module for determining the motivational characteristics to be measured; the motivational characteristics include self-efficacy, self-regulation and goal orientation; for each of the motivational characteristics, multiple preset items are selected from a verified questionnaire or a created project; and target items representing each of the motivational characteristics are screened out from the multiple preset items using expert ranking to form a project questionnaire.

[0092] In one embodiment, the dialogue module 502 inquires the learner based on the dialogue information to obtain the learner's motivation profile, including: initiating a dialogue with the learner, and after obtaining the learner's consent to conduct a motivation assessment, sending each round of dialogue information to the learner and obtaining reply information for each round of dialogue information; obtaining the learner's motivation characteristic data based on each round of dialogue information and reply information; organizing the motivation characteristic data into a motivation profile, and setting permissions for the learner and / or external intervener to update the motivation profile.

[0093] In one embodiment, the personalized intervention plan includes one or more of adjusting the learning path and content, setting up a reward mechanism, and providing learning strategy guidance.

[0094] The present application provides a learning motivation detection device, which obtains the learner's log file through a monitoring module, and performs a disengagement detection on the log file to obtain the learner's engagement information; if the learner is judged to be disengaged from learning based on the engagement information, a dialogue module generates dialogue information based on a preset project questionnaire, and inquires the learner based on the dialogue information to obtain the learner's motivation profile; an intervention module generates a personalized intervention plan for the learner based on the engagement information and the motivation profile. Thus, by combining the automatic monitoring of learner behavior with active self-assessment, the learner's motivation status can be identified more accurately and timely, and rapid intervention can be performed to optimize the learning process and improve teaching efficiency.

[0095] Based on the same concept of the present invention, the specification is attached Figure 6 As shown, the structure of an electronic device 600 provided in an embodiment of the present application includes: at least one processor 601, at least one network interface 604 or other user interface 603, a memory 605, and at least one communication bus 602. The communication bus 602 is used to realize the connection and communication between these components. The electronic device 600 optionally includes a user interface 603, including a display (for example, a touch screen, LCD, CRT, holographic imaging (Holographic) or projection (Projector), etc.), a keyboard or a pointing device (for example, a mouse, a trackball (trackball), a touch pad or a touch screen, etc.).

[0096] The memory 605 may include a read-only memory and a random access memory, and provides instructions and data to the processor 601. A portion of the memory 605 may also include a non-volatile random access memory (NVRAM).

[0097] In some implementations, the memory 605 stores the following elements, executable modules or data structures, or a subset thereof, or an extended set thereof:

[0098] Operating system 6051, including various system programs for implementing various basic services and processing hardware-based tasks;

[0099] The application module 6052 includes various application programs, such as a launcher, a media player, a browser, etc., which are used to implement various application services.

[0100] In an embodiment of the present application, by calling the program or instructions stored in the memory 605, the processor 601 is used to execute steps in a learning motivation detection method, which can more accurately and timely identify the learner's motivation state, and quickly intervene to optimize the learning process and improve teaching efficiency.

[0101] The present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the learning motivation detection method are executed.

[0102] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is run, the above-mentioned learning motivation detection method can be executed.

[0103] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0106] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0107] Finally, it should be noted that the above embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the aforementioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the aforementioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A learning motivation detection method, characterized in that: Applied to the digital learning courseware platform, the method comprises the following steps: Obtaining a learner's log file, and performing a disengagement test on the log file to obtain the learner's engagement information; If it is determined according to the engagement information that the learner is disengaged from learning, generating dialogue information based on a preset project questionnaire, and questioning the learner based on the dialogue information to obtain the learner's motivation profile; A personalized intervention plan for the learner is generated based on the engagement information and the motivation profile.

2. A learning motivation detection method according to claim 1, characterized in that: The step of performing disengagement detection on the log file to obtain the learner's participation information includes the following steps: Extracting the learner's operation behavior data from the log file; Calculating learning motivation-related attributes according to the operation behavior data, and performing motivation prediction on the calculated learning motivation-related attributes based on the constructed disengagement detection decision tree to obtain the motivation state category of the learner; the motivation state category includes disengagement and engagement; The motivation state category is incorporated into the learner's engagement information; wherein, if the motivation state category is disengagement, it is determined that the learner is disengaged from learning.

3. A learning motivation detection method according to claim 2, characterized in that: The performing of the disengagement detection on the log file to obtain the learner's participation information further includes the following steps: Analyzing the change of the learner's participation within a set time according to the operation behavior data, and judging the learner's non-participation mode and the start time and duration of the non-participation period according to the change of the participation; the non-participation mode includes long-term non-participation and rapid non-participation; The learner's non-participation pattern and the start time and duration of the non-participation period are incorporated into the learner's engagement information.

4. A learning motivation detection method according to claim 2, characterized in that: The learning motivation related attributes include reading time and test scores. The disengagement detection decision tree divides the learner's motivation state category according to the reading time and the test scores in the following manner: Setting a first time threshold, a first score threshold, and a second score threshold; wherein the first time threshold is greater than the set time for analyzing the change in participation, and the first score threshold is less than the second score threshold; If the reading time is less than or equal to the first time threshold, or the reading time is greater than the first time threshold and the test score is between the first score threshold and the second score threshold, classifying the learner's motivation state category as disengagement; If the reading time is greater than or equal to the first time threshold and the test score is greater than the second score threshold, or the reading time is greater than or equal to the first time threshold and the test score is less than the first score threshold, the learner's motivation state category is classified as participation.

5. A learning motivation detection method according to claim 1, characterized in that: Preset the project questionnaire in the following way: Determining the motivational characteristics to be measured; the motivational characteristics include self-efficacy, self-regulation, and goal orientation; selecting a plurality of preset items from validated questionnaires or created items for each of said motivational characteristics; The target items representing each motivation characteristic are screened out from the plurality of preset items by means of expert ranking, the target items are formed into a project questionnaire, and the validity and reliability of the project questionnaire are verified.

6. A learning motivation detection method according to claim 5, characterized in that: The step of querying the learner based on the speech information to obtain the learner's motivation profile comprises the following steps: After obtaining the learner's consent to conduct motivation assessment, each round of dialogue information is sent to the learner, and reply information for each round of dialogue information is obtained; According to the dialogue information and response information of each round, motivation characteristic data of the learner is obtained; The motivational characteristic data are organized into a motivational profile, and permissions for the learner and / or external intervener are set to update the motivational profile.

7. A learning motivation detection method according to claim 1, characterized in that: in, Generating a personalized intervention plan for the learner includes one or more of adjusting the learning path and content, setting a reward mechanism, and providing learning strategy guidance.

8. A learning motivation detection device, characterized in that: Applied to a digital learning courseware platform, the device comprises: A monitoring module, used for obtaining a learner's log file and performing a disengagement detection on the log file to obtain the learner's participation information; A dialogue module, for generating dialogue information based on a preset project questionnaire if it is determined that the learner is disengaged from learning according to the engagement information, and for questioning the learner based on the dialogue information to obtain the learner's motivation profile; An intervention module is used to generate a personalized intervention plan for the learner based on the engagement information and the motivation profile.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the learning motivation detection method as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the learning motivation detection method as described in any one of claims 1 to 7.

Images