Learning support system and learning support method

Abstract

To provide a learning support system and learning support method that can appropriately maintain learning motivation. [Solution] The learner information acquisition unit 11 acquires future image information, which represents the learner's desired future self. The teacher data acquisition unit 12 acquires teacher data from a posting site where multiple posters post, using posting data from model posters who have a similar self-image to the future self. The learning unit 13 constructs a diary generation model that generates a fictional diary based on the teacher data. The future diary generation unit 14 generates a future diary, which is a fictional diary of the learner's future, using the diary generation model. The presentation unit 15 presents the future diary to the learner terminal 2.

Description

Technical Field

[0001] The present disclosure relates to a learning support system and a learning support method.

Background Art

[0002] In order to pass official examinations such as national examinations and entrance examinations, learners need to continue learning over a long period of time. However, it is not easy for learners to maintain their motivation for learning during that time.

[0003] In contrast, Non-Patent Document 1 discloses a technique for presenting the future schedule of a user who has made a life choice such as quitting work and becoming independent by using a large language model (LLM) that has learned past data of the user such as calendar data and information related to the user's life values. By using this technique, it becomes possible to show a successful future of oneself, etc., and there is a possibility that the motivation of the learner for learning can be maintained.

Prior Art Documents

Non-Patent Documents

[0004]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, in the technique described in Patent Document 1, since the future schedule of the user is presented based on the past data of the user himself / herself, there is a possibility that a schedule reflecting the results of past non-study is presented, etc., and an appropriate schedule is not always presented to maintain motivation.

[0006] The purpose of this disclosure is to provide a learning support system and learning support method that can appropriately maintain learning motivation. [Means for solving the problem]

[0007] A learning support system according to one aspect of the present disclosure is a learning support system connected to a learner terminal used by a learner performing predetermined learning, comprising: a learner information acquisition unit that acquires future image information indicating the learner's desired future self; a teacher data acquisition unit that acquires posting data to a posting site where multiple posters post, from the site by a model poster who is a poster with a similar self-image to the future self, as teacher data; a learning unit that constructs a diary generation model for generating a fictional diary based on the teacher data; a generation unit that generates a future diary, which is the learner's fictional future diary, using the diary generation model; and a presentation unit that presents the future diary to the learner terminal. [Effects of the Invention]

[0008] According to the present invention, it becomes possible to appropriately maintain motivation for learning. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows a learning support system according to one embodiment of the present disclosure. [Figure 2] This figure shows an example of the hardware configuration of a learning support system. [Figure 3] This is a flowchart illustrating an example of the future diary generation process. [Modes for carrying out the invention]

[0010] The embodiments of this disclosure will be described below with reference to the drawings.

[0011] Figure 1 shows a learning support system according to one embodiment of the present disclosure. The learning support system 1 shown in Figure 1 is interconnected with a learner terminal 2 via a network 10 such as the Internet, and provides learning support information to the learner terminal 2 to support predetermined learning. In this embodiment, predetermined learning is learning for a predetermined main examination, such as a national examination, a skills proficiency test, an entrance examination, or an academic ability test. The main examination may consist of multiple subject-specific main examinations, each corresponding to a different subject.

[0012] The learner terminal 2 is an information terminal used by learners performing predetermined learning. The learner terminal 2 receives learning support information provided by the learning support system 1 and processes it according to the received learning support information. Processing according to the learning support information includes, for example, processing to display the learning support information and processing to transmit the information entered according to the learning support information to the learning support system 1. The learning support information includes, for example, lecture information, which is video data showing a lecture, and problem information, which includes a problem statement and an input form for entering the answer. The learning support information may also be transmitted in accordance with a learning curriculum determined according to the learner's living situation and wishes. The learner terminal 2 may also send various requests to the learning support system 1. Requests include, for example, a request for the provision of learning support information.

[0013] Learner terminal 2 may be a dedicated information terminal for receiving learning support information, or it may be a general-purpose information terminal such as a PC (Personal Computer), smartphone, or tablet. A single learner may have multiple learner terminals 2, or multiple learners may share one learner terminal 2. Alternatively, by logging the information terminal into the learning support system 1 using the learner's ID, the information terminal may be designated as learner terminal 2 while logged in.

[0014] As shown in Figure 1, the learning support system 1 includes a learner information acquisition unit 11, a teacher data acquisition unit 12, a learning unit 13, a future diary generation unit 14, and a presentation unit 15.

[0015] The learner information acquisition unit 11 acquires learner information, which is information about the learner. The learner information includes future image information, which shows the learner's desired future self (the person the learner wants to become). The future image includes attributes related to the self as items, such as future occupation, future position, future family structure, future annual income, and future lifestyle. The future image information may also include information indicating the time period from the present to the future image (for example, how many years from now). The learner information may also include present information, which shows the learner's current self. The present information includes attributes as items, such as gender, current age, current occupation, current family structure, current annual income, and current lifestyle. Note that the above attributes are merely examples, and any one of them, any combination of them, or other attributes may be included. Lifestyle includes, for example, the amount and proportion of working hours, sleep habits such as bedtime and wake-up time and whether or not naps are taken, and how holidays are spent.

[0016] The method for acquiring learner information is not particularly limited. For example, the learner information acquisition unit 11 may send information that prompts learner input, such as a questionnaire about future aspirations, to the learner terminal 2, and acquire learner information based on the response from the learner terminal 2 or the user to that information (such as a questionnaire response).

[0017] Based on the learner information acquired by the learner information acquisition unit 11, the teacher data acquisition unit 12 identifies posters with similar profiles (model posters) that are similar to the learner's future profile from posting sites where multiple posters post. The teacher data acquisition unit 12 then acquires posting data indicating posts made by the mentors on those posting sites as teacher data. Posting sites include, for example, SNS (Social Networking Service), blogs, and community sites. The teacher data acquisition unit 12 may collect teacher data from multiple posting sites.

[0018] Specifically, the training data acquisition unit 12 first acquires attributes related to the personality of each poster on the posting site. For example, the training data acquisition unit 12 uses an API (Application Programming Interface) provided by the posting site to acquire attributes related to the personality of the poster from the poster's profile. Next, for each poster, the training data acquisition unit 12 calculates the similarity between the attribute value of the poster and the attribute value of the learner's future image for each of several predetermined attributes, and identifies mentors based on these similarities. For example, the training data acquisition unit 12 determines a poster as a mentor if the statistical value of the similarity of each attribute is above a threshold. The algorithm for calculating similarity is not particularly limited. The statistical value of similarity may be, for example, a sum or a weighted sum. The weight values ​​of the weighted sum may be determined, for example, according to the importance of the items. The importance may be predetermined, or it may be determined according to the items that the learner considers important as their future image. Furthermore, it is desirable to have multiple mentors, and the training data acquisition unit 12 may identify a predetermined number of mentors or more, for example, by gradually lowering the threshold until the number of mentors exceeds a predetermined number.

[0019] Furthermore, the above method for identifying mentors is merely an example and is not limited to this example. For example, the training data acquisition unit 12 may estimate the attribute values ​​of the poster's attributes from the poster's posted data. Also, if the training data acquisition unit 12 cannot obtain the poster's attributes, such as the poster's profile, it may estimate the attribute values ​​of the poster's attributes from the posted data. In addition, if the training data acquisition unit 12 cannot obtain the poster's attributes, such as the poster's profile, it may set the similarity to that attribute to 0.

[0020] The learning unit 13 constructs a diary generation model, which is a model for generating fictional diaries, based on the teacher data acquired by the teacher data acquisition unit 12. The diary generation model is, for example, a generative AI (Artificial Intelligence) model such as a large language model. The diary generation model may be one obtained by newly fine-tuning the above-described teacher data as additional learning data (fine-tuning data) for generating fictional diaries for an existing generative AI model. Note that the existing generative AI model and the diary generation model may be provided in an external device (not shown) connected via the network 10, or may be provided in the learning unit 13.

[0021] The future diary generation unit 14 generates future diary information indicating a future fictional diary of the learner using the diary generation model constructed by the learning unit 13. For example, the future diary generation unit 14 causes the diary generation model to generate information indicating a future fictional diary of the mentor, and converts the attributes of the mentor included in the information into the attributes of the future learner, thereby generating future diary information. The future diary generation unit 14 may cause the diary generation model to assume the mentor as the future image of the learner and generate future diary information.

[0022] The format of the future diary information is not particularly limited. For example, the future diary information may be in the same format as the posting data to a predetermined posting site, may be in a predetermined format different from the format of the posting data, or the format may be generated or selected by the diary generation model.

[0023] The prompting unit 15 prompts the learner with the future diary by sending the future diary information generated by the future diary generation unit 14 to the learner terminal 2. Specifically, the prompting unit 15 regularly (in this embodiment, daily, but it may also be weekly, etc.) prompts the learner with future diaries with different contents. Note that the future diary generation unit 14 may generate the future diary information for a certain period (for example, for one year) in a batch, and the prompting unit 15 may extract and transmit the future diary information for the current day from the future diary information for a certain period, or the future diary generation unit 14 may generate the future diary information to be prompted on that day every day. The future diary to be prompted is, for example, a diary for a date after a predetermined period from the current time. The predetermined period may be a relatively near future such as one year, but a future such as five to ten years, where the grand dreams of the learner can be realized, is desirable.

[0024] Note that instead of regularly prompting the future diary information, the prompting unit 15 may transmit the learning support information to the learner terminal 2 according to a request from the learner terminal 2, and transmit the future diary information along with the learning support information. For example, the prompting unit 15 may transmit the future diary information before or after transmitting the lecture information or the problem information.

[0025] FIG. 2 is a diagram showing an example of the hardware configuration of the learning support system 1. As shown in FIG. 2, the learning support system 1 includes a storage device 21, a processor 22, a main memory 23, an input device 24, and a display device 25, which are connected via a bus 26.

[0026] The storage device 21 is a device that records data so that writing and reading are possible, and stores various information such as programs that define the operations of the processor 22, learning support information, learner information and teacher data acquired by the learner information acquisition unit 11 and the teacher data acquisition unit 12. The processor 22 reads the program stored in the storage device 21 into the main memory 23, and uses the main memory 23 to execute processing according to the program. Each part 11 - 15 of the learning support system 1 shown in FIG. 1 is realized by the processor 22.

[0027] The input device 24 is a device that receives various information from the operator of the learning support system 1 and external devices (not shown), and this information is used for processing by the processor 22. For example, learning support information is recorded in the storage device 21 via the input device 24. The display device 25 is a device that displays various information.

[0028] Figure 3 is a flowchart illustrating an example of the future diary generation process by the learning support system 1.

[0029] In the future diary generation process, the learner information acquisition unit 11 sends a questionnaire to the learner terminal 2 prompting the input of learner information, and acquires response information from the learner terminal 2 indicating the answers to the questionnaire (step S101). The timing of sending the questionnaire is, for example, when the learning curriculum is decided. The questionnaire may also be included in the information used to determine the learning curriculum.

[0030] The learner information acquisition unit 11 acquires learner information based on the response information (step S102). For example, if the questionnaire prompts learners to write questions such as, "In how many years, what kind of job / position do you want to have, how much do you want to earn annually, and where and what kind of life do you want to live?", the learner information acquisition unit 11 acquires learner information by extracting the necessary items for learner information from the questionnaire responses or by predicting the necessary items for future vision information from the questionnaire responses using an AI model or the like. Also, if the questionnaire requires learners to select each item of future vision information from a multiple-choice format, the learner information acquisition unit 11 acquires learner information based on the selections.

[0031] Based on the learner information acquired by the learner information acquisition unit 11, the teacher data acquisition unit 12 identifies posters with similar profiles (personal profiles similar to the learner's future aspirations) from posting sites where multiple posters post, and acquires the posting data of those mentors as teacher data (step S103).

[0032] The learning unit 13 constructs a diary generation model, which is a model that generates a fictional diary, based on the training data acquired by the training data acquisition unit 12 (step S104).

[0033] The future diary generation unit 14 uses the diary generation model constructed in the learning unit 13 to generate future diary information that represents a fictional diary of the learner's future (step S105).

[0034] The presentation unit 15 presents the future diary to the learner by transmitting the future diary information generated by the future diary generation unit 14 to the learner terminal 2 (step S106). Upon receiving the future diary information, the learner terminal 2 presents the future diary to the learner by displaying the information.

[0035] As described above, according to this embodiment, the learner information acquisition unit 11 acquires future image information that represents the learner's desired future self. The teacher data acquisition unit 12 acquires as teacher data data posted to a posting site by mentors, who are posters with a similar self-image to the learner's future self-image, from a posting site where multiple posters post. The learning unit 13 constructs a diary generation model that generates a fictional diary based on the teacher data. The future diary generation unit 14 generates a future diary, which is a fictional diary of the learner's future, using the diary generation model. The presentation unit 15 presents the future diary to the learner terminal 2. Therefore, since a future diary based on posting data by a person similar to the learner's desired future self-image is presented, it is possible to present the learner with a diary that aligns with the future self they want to become. Consequently, learners can virtually experience their successful future by continuing to learn, making it possible to appropriately maintain their motivation to learn.

[0036] Furthermore, in this embodiment, the learning unit 13 constructs a diary generation model by additionally training an existing generative AI model with training data. In this case, it becomes possible to easily construct a diary generation model.

[0037] Furthermore, in this embodiment, the display unit 15 periodically transmits future diary information with different content each time. In this case, by reading the future diary little by little, learners can gradually form the person they want to become, which makes it possible to more effectively maintain their motivation to learn.

[0038] Furthermore, in this embodiment, the display unit 15 transmits future diary information for a date a predetermined period after the present time. In this case, learners can relive their desired daily lives in the future, thereby more effectively maintaining their motivation to learn.

[0039] Furthermore, in this embodiment, the predetermined period is 5 to 10 years. In this case, it becomes possible to read a diary of the future in which the learner's grand dreams have been fulfilled, thereby more effectively maintaining motivation for learning.

[0040] Furthermore, in this embodiment, the training data acquisition unit 12 calculates the similarity between the future image and the poster's image for each of several attributes related to the person's profile, and selects a mentor based on the similarity of each attribute. In this case, it becomes possible to identify an appropriate mentor.

[0041] Furthermore, in this embodiment, the training data acquisition unit 12 identifies multiple mentors and acquires the posted data from each mentor as training data. In this case, it becomes possible to construct a future diary generation model using the posted data from multiple people as training data, thereby enabling the generation of engaging future diary information.

[0042] The embodiments of the Disclosure described above are illustrative for illustrative purposes and are not intended to limit the scope of the Disclosure to those embodiments only. Those skilled in the art can implement the Disclosure in various other forms without departing from the scope of the Disclosure. [Explanation of symbols]

[0043] 1: Learning support system 11: Learner information acquisition unit 12: Teacher data acquisition unit 13: Learning unit 14: Future diary generation unit 15: Presentation unit

Claims

1. A learning support system connected to a learner's terminal used by a learner performing a prescribed learning task, A learner information acquisition unit acquires future vision information that represents the desired future self of the learner, A training data acquisition unit acquires training data from a posting site where multiple posters post, using posting data from a model poster who has a similar profile to the aforementioned future image as training data. A learning unit constructs a diary generation model that generates fictional diaries based on the aforementioned training data, Using the diary generation model, a generation unit generates a future diary, which is a fictional diary of the learner's future. A learning support system comprising a display unit that displays the aforementioned future diary to the learner's terminal.

2. The learning support system according to claim 1, wherein the learning unit constructs the diary generation model by additionally training an existing generative AI model with the training data.

3. The learning support system according to claim 1, wherein the display unit periodically displays the future diary with different contents each time.

4. The learning support system according to claim 3, wherein the display unit displays the future diary with a date set a predetermined period after the present time.

5. The learning support system according to claim 4, wherein the predetermined period is 5 to 10 years.

6. The learning support system according to claim 1, wherein the teacher data acquisition unit calculates the similarity between the attribute value of each poster and the attribute value of the future image for each attribute relating to the person's profile for each of the multiple posters, and identifies the model poster based on the similarity of each attribute for each poster.

7. The learning support system according to claim 6, wherein the teacher data acquisition unit identifies multiple exemplary contributors.

8. The learning support system according to claim 6, wherein the aforementioned attributes include occupation, family structure, annual income, and lifestyle.

9. A learning support method using a learning support system connected to a learning terminal used by a learner performing a predetermined learning task, We obtain future vision information that represents the desired future self of the learner. From a posting site where multiple users post, we obtain posting data from model users who have a similar profile to the aforementioned future image, as training data. Based on the aforementioned training data, a diary generation model is constructed to generate fictional diaries. Using the diary generation model described above, a future diary, which is a fictional diary of the learner's future, is generated. A learning support method that presents the aforementioned future diary to the learner's terminal.

Images