Education support device, education support method, and program

Abstract

To provide an education support device, an education support method, and a program which can support a user with education according to a request attribute of user's goal.SOLUTION: In an education support device 10 according to the present disclosure, an acquisition unit 11 acquires information of a user and information of user's goal. An attribute analysis unit 12 uses a language model to analyze an attribute of the user and a request attribute of the user's goal in accordance with the information of the user and the information of the user's goal. An attribute gap analysis unit 13 analyzes an attribute difference between the attribute of the user and the request attribute of the user's goal. An educational content proposal unit 14 generates at least one educational content for a first goal for adding an attribute to the user on the basis of the attribute difference and proposes the generated educational content to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an education support device, an education support method, and a program. [Background technology]

[0002] Patent Document 1 discloses a technology for matching job seekers with recruiters by comparing the attributes of the job seeker with the attributes that the recruiter requires of the job seeker. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7299663 Summary of the Invention [Problem to be solved by the invention]

[0004] A user (e.g., a job seeker) may wish to become the target of a user (e.g., a recruiter) who was not able to be matched with the user. However, in order for the user to easily achieve their wish, it is necessary to support the user in receiving education according to the required attributes of the user's goal. However, Patent Document 1 does not provide such educational support.

[0005] In consideration of such problems, the present disclosure aims to provide an education support device, an education support method, and a program that can support a user in education according to the required attributes of the user's goals. [Means for solving the problem]

[0006] The educational support device of the present disclosure includes: an acquisition unit that acquires information about a user and information about a first goal of the user; an attribute analysis unit that analyzes attributes of the user and required attributes of the user's first goal using a language model based on information about the user and information about the user's first goal; an attribute gap analysis unit that analyzes a difference between the attribute of the user and the required attribute of the first goal of the user; and an educational content suggestion unit that generates at least one educational content for the first goal to allow the user to add an attribute based on the difference in the attribute, and suggests the generated educational content to the user.

[0007] The educational support method of the present disclosure includes: Acquire information about a user and information about a first goal of the user; Analyzing attributes of the user and required attributes of the user's first goal using a language model based on information about the user and information about the user's first goal; Analyzing an attribute difference between the attribute of the user and the desired attribute of the first goal of the user; At least one educational content for the first goal is generated based on the attribute difference to prompt the user to add the attribute, and the generated educational content is suggested to the user.

[0008] The program of the present disclosure is Acquire information about a user and information about a first goal of the user; Analyzing attributes of the user and required attributes of the user's first goal using a language model based on information about the user and information about the user's first goal; Analyzing an attribute difference between the attribute of the user and the desired attribute of the first goal of the user; The computer is caused to execute a process of generating at least one educational content for the first goal to prompt the user to add an attribute based on the difference in the attribute, and proposing the generated educational content to the user. [Effects of the Invention]

[0009] The present disclosure makes it possible to provide an education support device, an education support method, and a program that can support education by adding user attributes so as to satisfy the required attributes of the user's goals. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram showing an example of an education support device 10 according to the present embodiment. [Figure 2] 1 is a block diagram showing an example of an education support device 20 according to the present embodiment. [Figure 3] 4 is a flowchart showing an example of the operation of the education support device 20 according to the embodiment. [Figure 4] 10 is a flowchart showing an example of the process of step S103 of the education support device 20 according to the present embodiment. [Figure 5] FIG. 10 is a diagram showing an example of an attribute gap between the attributes of a job seeker analyzed by the education support device 20 according to the present embodiment and the required attributes of a recruiter Y1. [Figure 6] 10 is a diagram showing an example of an educational content proposal screen displayed on the job seeker terminal 100 by the educational support device 20 according to the present embodiment. FIG. [Figure 7] FIG. 2 is a diagram showing an example of a feedback screen displayed on the job seeker terminal 100 by the education support device 20 according to the present embodiment. [Figure 8] 10 is a flowchart showing an example of the operation of the education support device 30 according to the present embodiment. [Figure 9] FIG. 2 is a diagram showing an example of a feedback screen displayed on the job seeker terminal 100 by the education support device 30 according to the present embodiment. [Figure 10] FIG. 2 is a diagram showing an example of a learning plan proposed by the education support device 40 according to the present embodiment. [Figure 11] FIG. 5 is a block diagram showing an example of the hardware configuration of a computer 500 according to the present embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are designated by the same reference numerals, and for clarity of explanation, duplicate explanations will be omitted as necessary.

[0012] (First embodiment) First, the configuration of an education support device 10 according to the first embodiment will be described with reference to FIG. 1 is a block diagram showing an example of the configuration of an education support device 10 according to this embodiment. As shown in FIG. 1, the education support device 10 includes an acquisition unit 11, an attribute analysis unit 12, an attribute gap analysis unit 13, and an education content proposal unit 14.

[0013] The acquisition unit 11 acquires information about the user and information about the user's goal. The attribute analysis unit 12 analyzes the user's attributes and the required attributes of the user's goals from the user information and the user's goal information using a language model. The attribute gap analysis unit 13 analyzes the difference in attributes between the user's attributes and the required attributes of the user's goals. The educational content suggestion unit 14 generates at least one educational content for the first goal to prompt the user to add the attribute based on the difference in the attribute, and suggests the generated educational content to the user.

[0014] Therefore, the education support device 10 according to the first embodiment can support the user in education according to the required attributes of the user's goal. Even if the user desires a goal of a user who could not be matched because the required attributes are not met, the education support device 10 makes it easier for the user to achieve the desire by receiving education support.

[0015] (Second embodiment) Next, the configuration of the education support device 20 according to the second embodiment will be described with reference to FIG.

[0016] FIG. 2 is a block diagram showing an example of the configuration of an education support device 20 according to the second embodiment. As shown in FIG. 2, the education support device 20 is a specific example of the education support device 10 according to the first embodiment. The "user" in the first embodiment will be described as a "job seeker" in the second embodiment, and the "user's goal" will be described as a "recruiter." Note that the "user" and the "user's goal" are not limited to the above example. For example, the "user" may be a "student" and the "user's goal" may be a "university." Furthermore, the "user" may be an "employee" and the "user's goal" may be an "employer."

[0017] The education support device 20 is, for example, a server. The education support device 20 is a device that supports job seekers in providing education for employers that the job seekers desire. The education support device 20 communicates with a job seeker terminal 100, which is a terminal used by the job seeker. The job seeker terminal 100 is, for example, a smartphone, tablet, or PC (Personal Computer). The job seeker terminal 100 may have an application dedicated to the education support device 20 installed.

[0018] Specifically, the education support device 20 includes an acquisition unit 21, an attribute analysis unit 22, an attribute gap analysis unit 23, an educational content proposal unit 24, a feedback unit 25, and a storage unit 26. The acquisition unit 21, the attribute analysis unit 22, the attribute gap analysis unit 23, and the educational content proposal unit 24 correspond to the acquisition unit 11, the attribute analysis unit 12, the attribute gap analysis unit 13, and the educational content proposal unit 14 in the first embodiment, respectively.

[0019] The acquisition unit 21 acquires information about the job seeker (hereinafter referred to as job search information). The acquisition unit 21 also acquires information about the recruiter Y1 selected by the job seeker (hereinafter referred to as job search information). The attribute analysis unit 22 analyzes the attributes of the job seeker and the attributes required by the recruiter (hereinafter referred to as required attributes) from the job search information of the job seeker and the recruitment information of the recruiter using a language model.

[0020] Here, we will explain the definition of attributes. Attributes refer to the skills, knowledge, experience, etc. that a job seeker possesses. As an example, attributes can be classified into three categories: technical skills (hard skills), soft skills, and business skills. Technical skills are specialized knowledge and techniques required for a specific job or task. Examples of technical skills include programming, data analysis, and machine operation. Soft skills are skills related to interpersonal relationships and how work is carried out. For example, soft skills include communication skills, teamwork, and problem-solving skills. Business skills are basic business knowledge and skills required to carry out work. For example, business skills include project management, marketing, and financial knowledge.

[0021] We will also explain the definition of a language model. A language model is a machine learning model that learns the relationships between words in a sentence and generates related strings from a target string. By using a language model that has been trained on sentences and paragraphs from various contexts, it is possible to generate related strings with appropriate content that are related to the target string.

[0022] For example, a case where a language model is used in question answering will be described. The language model receives an input of a question such as "What kind of country is Japan?" as a target string. The language model generates a string such as "Japan is an island country in the Northern Hemisphere..." as an answer to the question. Note that the learning method of the language model is not particularly limited, and as an example, the language model may be trained to output at least one sentence including the input string.

[0023] As a specific example, a language model is a Generative Pre-trained Transformer (GPT) that outputs a sentence containing an input string by predicting a string that is likely to follow the input string. Other examples of language models include T5 (Text-to-Text Transfer Transformer), BERT (Bidirectional Encoder Representations from Transformers), RoBERTa (Robustly optimized BERT approach), and ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately).

[0024] Furthermore, the character strings generated by the language model are not limited to natural languages. For example, the language model may output an artificial language (such as program source code) for a character string input in a natural language. For example, the language model may accept an input question such as "How do I retrieve data containing a specific character string from a database?" as a target character string. The language model may output program source code for performing database processing. Alternatively, the language model may output a natural language corresponding to a character string input in an artificial language. Furthermore, the content generated by the language model is not limited to character strings. For example, the language model may generate image data, video data, audio data, or other data formats corresponding to the input character string.

[0025] The attribute gap analysis unit 23 analyzes the difference in attributes (hereinafter referred to as the attribute gap) between the job seeker's attributes and the required attributes of the recruiter Y1. The attribute gap is expressed by at least one of cosine similarity, Euclidean distance, and similarity based on a pre-trained language model including BERT (Bidirectional Encoder Representations from Transformers).

[0026] The educational content proposal unit 24 generates at least one educational content for the recruiter Y1 based on the attribute gap between the job seeker's attributes and the required attributes of the recruiter Y1. Specifically, the educational content proposal unit 24 generates at least one educational content for the recruiter Y1 so as to reduce the attribute gap between the job seeker's attributes and the required attributes of the recruiter Y1. The educational content proposal unit 24 then proposes the generated educational content to the job seeker.

[0027] The feedback unit 25 provides the job seeker with feedback information including information indicating how the attribute gap between the job seeker's attributes and the attributes required by the employer Y1 changes before and after taking at least one educational content. For example, the feedback unit 25 provides the feedback information to the job seeker terminal 100.

[0028] The storage unit 26 stores various types of information. The storage unit 26 stores the acquired job search information of job seekers, the job information of recruiter Y1, the analyzed attributes of job seekers, the required attributes and attribute gaps of recruiter Y1, the generated educational content, feedback information, etc.

[0029] Next, the operation of the education support device 20 according to the second embodiment will be described with reference to FIGS.

[0030] FIG. 3 is a flowchart showing an example of the operation of the education support device 20 according to the embodiment. As shown in FIG. 3, first, in step S101, the acquisition unit 21 of the education support device 20 acquires job search information of a job seeker. The job search information of the job seeker includes information such as name, date of birth, gender, educational background, work history, reason for leave of absence, self-promotion, job search status, desired job type, desired work location, desired annual salary, qualifications, language skills, etc. The acquisition unit 21 accepts the job search information input by the job seeker from the job seeker terminal 100.

[0031] Next, in step S102, the acquisition unit 21 acquires the job information of the recruiter Y1 selected by the job seeker. The recruitment information of recruiters includes basic information (e.g., company name, job type, work location, salary), skills and requirements (e.g., required skills, desirable skills, necessary experience and qualifications), job content (e.g., main job duties, technologies and tools used), and other information (e.g., full-time, contract, part-time, etc., employee benefits, corporate culture, and mission). The acquisition unit 21 collects the recruitment information of recruiters from the Internet. Web crawling technology, APIs, databases, and the like that provide recruitment information are used for collection. Specifically, when using web crawling technology, the acquisition unit 21 automatically collects recruitment information from specific recruitment information sites or company career pages using Python libraries (e.g., Beautiful Soup or Scrapy). Furthermore, if a major recruitment information provider or employment placement service provides an API or database, the acquisition unit 21 may collect recruitment information using such API or database. Note that because some recruitment information may be difficult to collect automatically, the acquisition unit 21 may manually input recruitment information from the recruiter via the recruiter's terminal.

[0032] Next, in step S103, the attribute analysis unit 22 analyzes the attributes of the job seeker and the required attributes of the recruiter Y1 using a language model based on the job search information of the job seeker and the recruitment information of the recruiter Y1.

[0033] Attributes refer to the skills, knowledge, experience, etc. that a job seeker possesses. For example, attributes can be classified into three categories: technical skills (hard skills), soft skills, and business skills. Technical skills are specialized knowledge and techniques required for a specific job or task. For example, technical skills include programming, data analysis, and machine operation. Soft skills are skills related to interpersonal relationships and how work is carried out. For example, soft skills include communication skills, teamwork, and problem-solving skills. Business skills are basic business knowledge and skills required to carry out work. For example, business skills include project management, marketing, and financial knowledge.

[0034] Required skills also vary depending on the job type and industry. For example, engineers are required to have knowledge of programming languages, system design skills, knowledge and skills in database management, knowledge and skills in debugging and testing, experience using version control systems, and experience with agile development. Specifically, programming language knowledge refers to in-depth knowledge of specific languages such as Java, Python, and C++. System design skills refer to the ability to understand and plan the overall system design and the interaction between modules. Database management knowledge and skills refer to knowledge of database languages such as SQL and the ability to manage and manipulate data. Debugging and testing knowledge and skills refer to the ability to find and fix software bugs and knowledge of testing methods such as test-driven development. Experience using version control systems refers to experience using version control tools such as Git. Agile development experience refers to experience managing projects based on agile development methodologies such as Scrum and Kanban.

[0035] In the processing of step S103, the attribute analysis unit 22 analyzes the attributes of the job seeker using a language model from the job search information of the job seeker, for example, by the processing of steps S1031 to S1032 shown in Fig. 4. Note that the attribute analysis unit 22 analyzes the required attributes of recruiter Y1 using a language model from the recruitment information of recruiter Y1 in the same way as for the attributes of the job seeker.

[0036] FIG. 4 is a flowchart showing an example of the process of step S103 of the education support device 20 according to this embodiment. 4, first, in step S1031, the attribute analysis unit 22 acquires the basic attributes of the job seeker included in the job search information of the job seeker. For example, the basic attributes are "'Name': 'Tanaka', 'Occupation': 'Engineer'".

[0037] Next, in step S1032, the attribute analysis unit 22 expands the basic attributes using a language model. Specifically, the attribute analysis unit 22 submits the acquired occupation of the job seeker to the language model as a query. The query is "What are the user attributes associated with {'Occupation': 'Engineer'}?" Next, the attribute analysis unit 22 receives attributes related to the prompt from the language model in text format. The received data is "'Programming', 'Software development', 'System design'." In other words, the attribute analysis unit 22 uses the language model to expand the basic attribute of the job seeker, "'Occupation': 'Engineer'," to the attributes "'Programming', 'Software development', 'System design'."

[0038] Returning to the explanation of Fig. 3, next, in step S104, the attribute gap analysis unit 23 analyzes the attribute gap between the job seeker's attributes and the required attributes of the recruiter Y1. The result of the attribute gap analysis is shown in Fig. 5.

[0039] FIG. 5 is a diagram illustrating an example of an attribute gap between the attributes of a job seeker and the required attributes of a recruiter Y1, analyzed by the education support device 20 according to this embodiment. As shown in FIG. 5, the attribute gap is expressed by at least one of cosine similarity, Euclidean distance, and similarity using a pre-trained language model such as BERT. Specifically, the attribute gap analysis unit 23 represents attribute text as vectors and calculates the cosine similarity between them. This method is particularly commonly used in learning methods known as word2vec and other embedded representations. The attribute gap analysis unit 23 also represents attribute text as vectors and calculates the Euclidean distance. This method is useful when the text embedding vectors reflect semantic distances in Euclidean space. The attribute gap analysis unit 23 also embeds attribute text in a pre-trained language model such as BERT and calculates the similarity between the vectors.

[0040] Returning to the explanation of Figure 3, next, in step S105, the educational content proposing unit 24 generates at least one educational content for the recruiter Y1 so as to reduce the attribute gap between the job seeker's attributes and the attributes required by the recruiter Y1, and proposes the educational content to the job seeker. Here, the educational content is content for adding predetermined attributes to the job seeker.

[0041] For example, the educational content proposal unit 24 proposes educational content A, B, and C to a job seeker as educational content for recruiter Y1. Here, educational content A, B, and C are generated so that there is no attribute gap between the job seeker's attributes after taking all of these contents and the attributes required by recruiter Y2. Assume that attributes #1 to #6 are the main factors behind the attribute gap between the job seeker's attributes and the attributes required by recruiter Y1. Educational content A is generated as content that allows the job seeker to add attributes #1, #2, and #3 to the job seeker's attributes after taking educational content A. Educational content B is generated as content that allows the job seeker to add attributes #4 and #5 to the job seeker's attributes after taking educational content B. Educational content C is generated as content that allows the job seeker to add attribute #6 to the job seeker's attributes after taking educational content C. The educational content proposing unit 24 may generate educational content so that the attribute gap between the job seeker's attributes and the required attributes of the recruiter Y1 is eliminated by taking a single educational content (for example, only educational content A).

[0042] Furthermore, the educational content proposal unit 24 displays the educational content on the job seeker terminal 100 on an educational content proposal screen shown in FIG. 6. FIG. 6 is a diagram showing an example of an educational content proposal screen displayed on the job seeker terminal 100 by the education support device 20 according to this embodiment. As shown in FIG. 6, screen S1 is an educational content proposal screen. When a job seeker presses "My Library" on screen S1, educational content A, B, and C for recruiter Y1 are displayed on the job seeker terminal 100. Screen S2 is a recruiter selection screen on which the job seeker selects a target recruiter from among recruiters Y1 to Yn. When a job seeker presses "My Goal" on screen S1, screen S2 is displayed on the job seeker terminal 100. In this way, the educational content proposal unit 24 can propose to the job seeker optimal educational content for the recruiter Yn selected by the job seeker. The job seeker can study effectively toward his or her goal, the recruiter Yn.

[0043] In step S105, the educational content proposal unit 24 is not limited to generating educational content that reduces the attribute gap between the job seeker's attributes and the required attributes of the employer Y1, but may also generate educational content that does not change the attribute gap or that increases the attribute gap.

[0044] Next, in step S106, the feedback unit 25 provides the job seeker with feedback information including information on the change in the attribute gap before and after attending the educational content for recruiter Y1. In other words, the feedback information includes information indicating how the attribute gap between the job seeker's attributes before attending each educational content and the attributes required by recruiter Y1 has changed compared to the attribute gap between the job seeker's attributes after attending each educational content and the attributes required by recruiter Y1.

[0045] For example, the feedback unit 25 displays a screen (feedback screen) including feedback information shown in FIG. 7 on the job seeker terminal 100. FIG. 7 is a diagram showing an example of a feedback screen displayed on the job seeker terminal 100 by the education support device 20 according to this embodiment. As shown in FIG. 7, the feedback screen displays the job seeker's attributes, the required attributes of the recruiter Y1 selected by the job seeker, and the attribute gap between them. The feedback screen also displays the job seeker's attributes after taking educational content A, the job seeker's attributes after taking educational content A and B, and the job seeker's attributes after taking educational content A, B, and C. Here, the job seeker's attributes after taking educational content A, B, and C match the required attributes of the recruiter Y1. From this feedback information, the job seeker can know how much the attribute gap between his or her own attributes and the target required attributes of the recruiter Y1 is narrowing as he or she takes educational content A, B, and C. This makes it easier for the job seeker to make a plan to achieve his or her goal. Furthermore, the job seeker can sense his or her own growth. Job seekers can also determine which educational content they should prioritize in order to achieve their goals.

[0046] As described above, the education support device 20 according to the second embodiment can support a job seeker in receiving education according to the required attributes of the user, i.e., the recruiter. The education support device 10 makes it easier for a job seeker to fulfill their wish by receiving education support, even if the job seeker desires an employer who is unable to match them because they do not satisfy the required attributes. For example, by receiving education support, the job seeker is more likely to be hired by the desired recruiter.

[0047] Furthermore, in order to adapt to the rapidly changing market environment, modern companies are required to update the skill sets of their employees and reskill them (reskilling). For this reason, in-house training and education for adults are becoming increasingly important. As described above, the education support device 30 can be used by "job seekers" as "employees" and "employers" as "employers." In this case, the education support device 30 can provide effective education support during in-house training and education for adults, such as by adding the attributes that employers require to employees.

[0048] In addition, the education support device 20 according to the second embodiment does not need to include an attribute analysis unit 22 that uses a language model to analyze the attributes of the job seeker and the required attributes of the employer from the job search information of the job seeker and the employment information of the employer acquired by the acquisition unit 21. In this case, the acquisition unit 21 of the education support device 20 acquires job search information of the job seeker and job information of the recruiter Y1. The attribute gap analysis unit 23 analyzes the attribute gap between the job seeker's attributes included in the job search information and the required attributes of the recruiter Y1 included in the job information. The educational content proposal unit 24 generates at least one educational content for the recruiter Y1 to allow the job seeker to add attributes based on the attribute gap, and proposes the generated educational content to the job seeker.

[0049] 3, the operation of the education support device 20 does not perform the process of step S103 described above. Instead, in the process of step S104 described above, the attribute gap analysis unit 23 analyzes the attribute gap between the job seeker's attributes included in the job seeker information and the required attributes of the recruiter Y1 included in the recruiter's information. By doing so, for example, efficient processing can be achieved in cases where there is no attribute expansion using a language model in the job information of a job seeker and the job information of a recruiter.

[0050] Furthermore, the job information of the employer may be "ideal job information" set by the job seeker. For example, the acquisition unit 21 of the education support device 20 acquires the ideal job information through manual input by the job seeker from the job seeker terminal 100. By doing so, the job seeker can add ideal attributes through educational content.

[0051] (Third embodiment) Next, the configuration of the education support device 30 according to the third embodiment will be described. The education support device 30 further includes a configuration that can support education that allows flexibility in the goal options of the user, a job seeker. The education support device 30 basically includes the same configuration as the education support device 20 according to the second embodiment (see FIG. 2). However, the education support device 30 further includes the following configuration.

[0052] The educational content suggestion unit 24 of the education support device 30 suggests to the job seeker a recruiter Y2 that is different from the recruiter Y1 and that satisfies a predetermined condition. The predetermined condition is that the recruiter Y2 has a required attribute such that the attribute gap between the recruiter Y2 and the job seeker's attribute during the course of taking at least one educational content aimed at the recruiter Y1 is equal to or smaller than a predetermined value.

[0053] The educational content proposal unit 24 generates at least one educational content for the recruiter Y2 to allow the job seeker to add attributes, based on an attribute gap between the job seeker's attributes in the process of receiving at least one educational content for the recruiter Y1 and the attributes required by the recruiter Y2. Specifically, the educational content proposal unit 24 generates at least one educational content for the recruiter Y2 so as to reduce the attribute gap between the job seeker's attributes in the process of receiving at least one educational content for the recruiter Y1 and the attributes required by the recruiter Y2. The educational content proposal unit 24 then proposes the generated educational content to the job seeker.

[0054] The feedback unit 25 proposes to the job seeker as feedback information information indicating how the attribute gap between the job seeker's attributes and the required attributes of the employer Y2 changes before and after taking at least one educational content for the employer Y2.

[0055] Next, the operation of the education support device 30 according to the third embodiment will be described with reference to Fig. 8. Fig. 8 is a flowchart showing an example of the operation of the education support device 30 according to this embodiment.

[0056] 8, the education support device 30 executes the processes from step S101 to step S106 described above (see FIG. 3), and then executes the processes from step S201 to step S203.

[0057] First, in step S201, the attribute gap analysis unit 23 searches for a recruiter Y2 having required attributes such that the attribute gap between the required attributes and the attributes of a job seeker in the process of taking educational content for recruiter Y1 is equal to or less than a predetermined value. The required attributes of recruiter Yn are analyzed from the recruitment information of recruiter Yn as in step S103 described above. The recruitment information of recruiter Yn is acquired as in step S102 described above. For example, the recruiter Y2 to be searched for has required attributes such that the attribute gap between the required attributes and the attributes of a job seeker after taking educational content A and B is equal to or less than a predetermined value.

[0058] Next, in step S202, the educational content proposal unit 24 generates at least one educational content for the recruiter Y2 so as to reduce the attribute gap between the job seeker's attributes in the process of taking the educational content for the recruiter Y1 and the attributes required by the recruiter Y2, and proposes the educational content to the job seeker. For example, the educational content proposal unit 24 generates educational content A, educational content B, and educational content G as educational content for the recruiter Y2. Here, educational content G is generated so as to eliminate the attribute gap between the job seeker's attributes after taking the educational content A and B and the attributes required by the recruiter Y2.

[0059] Next, in step S203, the feedback unit 25 provides the job seeker with feedback information including information on the change in the attribute gap before and after taking the educational content for recruiter Y2.

[0060] For example, the feedback unit 25 displays a screen (feedback screen) including feedback information shown in FIG. 9 on the job seeker terminal 100. FIG. 9 is a diagram showing an example of a feedback screen displayed on the job seeker terminal 100 by the education support device 30 according to this embodiment. As shown in FIG. 9, the feedback screen displays the job seeker's attributes, the required attributes of the recruiter Y1 selected by the job seeker, and the attribute gap between them. The feedback screen also displays the job seeker's attributes after attending educational content A, the job seeker's attributes after attending educational contents A and B, and the job seeker's attributes after attending educational contents A, B, and C (similar to FIG. 7). In addition, the feedback screen displays the required attributes of the newly proposed recruiter Y2. The feedback screen also displays the attributes of the job seeker after attending educational contents A, B, and G, which are educational contents aimed at recruiter Y2. Here, the job seeker's attributes after attending educational contents A, B, and G match the required attributes of recruiter Y2. From this feedback information, the job seeker can select another target recruiter. Furthermore, if a job seeker takes educational content G instead of educational content C after taking educational content A and B, they can aim to become employer Y2 instead of employer Y1. Even if a job seeker aims to become employer Y1, it is easy for them to change their goal depending on the situation at the time.

[0061] Therefore, the education support device 30 according to the third embodiment can support education that allows the job seeker, who is the user, to have flexibility in the options for goals.

[0062] (Fourth embodiment) Next, the configuration of an education support device 40 according to a fourth embodiment will be described. The education support device 40 further includes a configuration for proposing to the job seeker a study plan in which a combination of educational contents is optimized for the job seeker. The education support device 40 basically has the same configuration as the education support device 20 according to the second embodiment. However, the education support device 40 has the following additional configuration.

[0063] The educational content proposing unit 24 of the education support device 40 further generates a study plan for the educational content and proposes the study plan to the job seeker. In the study plan, the combination of educational content proposed to the job seeker is optimized.

[0064] FIG. 10 is a diagram showing an example of a learning plan proposed by the education support device 40 according to this embodiment. As shown in Figure 10, in the learning plan, training #1 to training #3 are conducted every day from Monday to Sunday. Each training employs one of educational contents A to D.

[0065] In the learning plan, a combination of educational contents A to D that satisfies the constraints and maximizes the objective function is adopted. The objective function is calculated, for example, as "objective function = α × (learning situation) + β × (learning style) + ...". The learning situation and learning style are individual to the job seeker and are quantified. When calculating the objective function, weighting from past data may be performed using inverse reinforcement learning. Constraints can be set, for example, as follows: (1) The study time must be more than the set amount of time per day. (2) The study time must be within the set budget. (3) The load must be evenly distributed across the attributes of job seekers to be added within one week. The educational content proposing unit 24 optimizes the combination of educational contents by performing mathematical optimization based on the above-mentioned objective function and constraint conditions.

[0066] The education support device 40 according to the fourth embodiment has the same effects as the education support device 20 according to the second embodiment. Furthermore, the education support device 40 proposes to the job seeker a study plan in which a combination of educational content is optimized for the job seeker. Therefore, the education support device 40 allows the job seeker to study more effectively.

[0067] The present invention is not limited to the above-described embodiment, and can be modified as appropriate within the scope of the invention.

[0068] <Example of hardware configuration> Each functional component of the education support device 10, education support device 20, education support device 30, and education support device 40 may be realized by hardware that realizes each functional component (e.g., a hardwired electronic circuit, etc.), or may be realized by a combination of hardware and software (e.g., a combination of an electronic circuit and a program that controls it, etc.). Below, a case where each functional component of the above devices is realized by a combination of hardware and software will be further described.

[0069] Fig. 11 is a block diagram showing an example of the hardware configuration of a computer 500 according to this embodiment. The education support device 10, education support device 20, education support device 30, and education support device 40 can all be realized by a computer 500 having the hardware configuration shown in Fig. 11. The computer 500 may be a portable computer such as a smartphone or tablet terminal, or may be a stationary computer such as a PC (Personal Computer). The computer 500 may be a dedicated computer or a general-purpose computer.

[0070] For example, a desired function can be provided to the computer 500 by installing a predetermined application on the computer 500. By installing an application that realizes each function of the device on the computer 500, each function is realized on the computer 500.

[0071] The computer 500 has a bus 501, a processor 502, a memory 503, a storage device 504, an input / output interface (I / F) 505, and a network interface (I / F) 506. The bus 501 is a data transmission path for the processor 502, the memory 503, the storage device 504, the input / output interface 505, and the network interface 506 to transmit and receive data to and from each other. However, the method for connecting the processor 502 and the like to each other is not limited to bus connection.

[0072] The processor 502 is one of various processors such as a central processing unit (CPU), a graphics processing unit (GPU), or a field-programmable gate array (FPGA). The memory 503 is a main storage device realized using a random access memory (RAM) or the like. The storage device 504 is an auxiliary storage device realized using a hard disk, a solid state drive (SSD), a memory card, or a read-only memory (ROM) or the like.

[0073] The input / output interface 505 is an interface for connecting the computer 500 to an input / output device. For example, the input / output interface 505 is connected to an input device such as a keyboard and an output device such as a display device.

[0074] The network interface 506 is an interface for connecting the computer 500 to a network. This network may be a LAN (Local Area Network) or a WAN (Wide Area Network).

[0075] Programs for realizing desired functions are stored in the storage device 504. For example, programs for realizing each function of the device are stored in the storage device 504 of the computer 500. The processor 502 reads the programs into the memory 503 and executes them to realize each function.

[0076] These programs include instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The programs may be stored on a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray® disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The programs may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0077] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes. (Appendix 1) an acquisition unit that acquires information about a user and information about a first goal of the user; an attribute analysis unit that analyzes attributes of the user and required attributes of the user's first goal using a language model based on information about the user and information about the user's first goal; an attribute gap analysis unit that analyzes a difference between the attribute of the user and the required attribute of the first goal of the user; an educational content suggestion unit that generates at least one educational content for the first goal to prompt the user to add an attribute based on the difference in the attribute, and suggests the generated educational content to the user. Educational support equipment. (Appendix 2) The educational content suggestion unit generating at least one educational content for the first goal to prompt the user to add attributes so as to reduce a difference in attributes between the attributes of the user and the required attributes of the first goal of the user; 10. The educational support device according to claim 1. (Appendix 3) the user is a job seeker; The user's primary goal is to recruit 10. The educational support device according to claim 1. (Appendix 4) The system further includes a feedback suggestion unit that suggests to the user, as feedback information, information indicating how a difference in an attribute between the user's attribute and a required attribute of the user's first goal changes before and after taking at least one educational content aimed at the first goal. 10. The educational support device according to claim 1. (Appendix 5) The educational content suggestion unit Proposing to the user a second goal that is different from the user's first goal and that satisfies a predetermined condition; The predetermined condition is: The second goal has a required attribute such that the difference between the attribute of the user and the second goal in the course of receiving at least one educational content aimed at the first goal is equal to or less than a predetermined value. 10. The educational support device according to claim 1. (Appendix 6) The educational content suggestion unit Based on the difference between the attributes of the user in the process of receiving at least one educational content for the first goal and the attributes required for the user's second goal, generate at least one educational content for the second goal for the user to add attributes, and suggest the educational content to the user. 6. An educational support device according to claim 5. (Appendix 7) The educational system further includes a feedback suggestion unit that suggests to the user, as feedback information, information indicating how a difference in an attribute between the user's attribute and a required attribute of the user's second goal changes before and after taking at least one educational content aimed at the second goal. 7. An educational support device according to claim 6. (Appendix 8) The attribute difference is: It is expressed by at least one of cosine similarity, Euclidean distance, and similarity using a pre-trained language model including BERT. 10. The educational support device according to claim 1. (Appendix 9) Acquire information about a user and information about a first goal of the user; Analyzing attributes of the user and required attributes of the user's first goal using a language model based on information about the user and information about the user's first goal; Analyzing an attribute difference between the attribute of the user and the desired attribute of the first goal of the user; generating at least one educational content for the first goal to prompt the user to add an attribute based on the difference in the attribute, and suggesting the generated educational content to the user; Educational support methods. (Appendix 10) generating at least one educational content for the first goal to prompt the user to add attributes so as to reduce a difference in attributes between the attributes of the user and the required attributes of the first goal of the user; The educational support method described in Appendix 9. (Appendix 11) the user is a job seeker; The user's primary goal is to recruit The educational support method described in Appendix 9. (Appendix 12) Providing the user with information indicating how a difference in an attribute between the user's attribute and a required attribute of the user's first goal changes before and after taking at least one educational content aimed at the first goal as feedback information. The educational support method described in Appendix 9. (Appendix 13) Proposing to the user a second goal that is different from the user's first goal and that satisfies a predetermined condition; The predetermined condition is: The second goal has a required attribute such that the difference between the attribute of the user and the second goal in the course of receiving at least one educational content aimed at the first goal is equal to or less than a predetermined value. The educational support method described in Appendix 9. (Appendix 14) Based on the difference between the attributes of the user in the process of receiving at least one educational content for the first goal and the attributes required for the user's second goal, generate at least one educational content for the second goal for the user to add attributes, and suggest the educational content to the user. The educational support method described in Appendix 13. (Appendix 15) Providing to the user, as feedback information, information indicating how a difference in attributes between the user's attributes and the required attributes of the user's second goal changes before and after taking at least one educational content aimed at the second goal. 14. The educational support method described in Appendix 14. (Appendix 16) The attribute difference is: It is expressed by at least one of cosine similarity, Euclidean distance, and similarity using a pre-trained language model including BERT. The educational support method described in Appendix 9. (Appendix 17) Acquire information about a user and information about a first goal of the user; Analyzing attributes of the user and required attributes of the user's first goal using a language model based on information about the user and information about the user's first goal; Analyzing an attribute difference between the attribute of the user and the desired attribute of the first goal of the user; generating at least one educational content for the first goal to prompt the user to add an attribute based on the difference in the attribute, and suggesting the generated educational content to the user; program. (Appendix 18) The computer further executes a process of generating at least one educational content for the first goal to prompt the user to add an attribute so as to reduce a difference between the attribute of the user and a required attribute of the first goal of the user. 17. The program described in Appendix 17. (Appendix 19) the user is a job seeker; The user's primary goal is to recruit 17. The program described in Appendix 17. (Appendix 20) and further causing the computer to execute a process of suggesting to the user, as feedback information, information indicating how a difference in an attribute between the attribute of the user and a required attribute of the first goal of the user changes before and after taking at least one educational content aimed at the first goal. 17. The program described in Appendix 17. (Appendix 21) further causing the computer to perform a process of suggesting to the user a second goal that is different from the first goal of the user and that satisfies a predetermined condition; The predetermined condition is: The second goal has a required attribute such that the difference between the attribute of the user and the second goal in the course of receiving at least one educational content aimed at the first goal is equal to or less than a predetermined value. 17. The program described in Appendix 17. (Appendix 22) and generating at least one educational content for the second goal for the user to add an attribute based on a difference between the attribute of the user in the process of receiving at least one educational content for the first goal and a required attribute of the second goal of the user, and further causing the computer to perform a process of suggesting the educational content to the user. 21. The program described in Appendix 21. (Appendix 23) and further causing the computer to execute a process of suggesting to the user, as feedback information, information indicating how a difference in an attribute between the attribute of the user and a required attribute of the second goal of the user changes before and after taking at least one educational content aimed at the second goal. 22. The program of claim 1. (Appendix 24) The attribute difference is: It is expressed by at least one of cosine similarity, Euclidean distance, and similarity using a pre-trained language model including BERT. 17. The program described in Appendix 17. [Explanation of symbols]

[0078] 10, 20, 30, 40 Educational support equipment 11, 21 Acquisition Department 12, 22 Attribute analysis department 13, 23 Attribute Gap Analysis Section 14, 24 Educational Content Proposal Department 25 Feedback section 26 Memory section 100 job seeker terminals 500 computers 501 Bus 502 processor 503 memory 504 Storage Devices 505 Input / Output Interface (I / F) 506 Network Interface (I / F)

Claims

1. an acquisition unit that acquires information about a user and information about a first goal of the user; an attribute analysis unit that analyzes attributes of the user and required attributes of the user's first goal using a language model based on information about the user and information about the user's first goal; an attribute gap analysis unit that analyzes a difference between the attribute of the user and the required attribute of the first goal of the user; an educational content suggestion unit that generates at least one educational content for the first goal to prompt the user to add an attribute based on the difference in the attribute, and suggests the generated educational content to the user. Educational support equipment.

2. The educational content suggestion unit generating at least one educational content for the first goal to prompt the user to add attributes so as to reduce a difference in attributes between the attributes of the user and the required attributes of the first goal of the user; The educational support device according to claim 1 .

3. the user is a job seeker; The user's primary goal is to be a recruiter The educational support device according to claim 1 .

4. a feedback suggestion unit that suggests to the user, as feedback information, information indicating how a difference in an attribute between the attribute of the user and an attribute required for the first goal of the user changes before and after taking at least one educational content aimed at the first goal; The educational support device according to claim 1 .

5. The educational content suggestion unit Proposing to the user a second goal that is different from the first goal of the user and that satisfies a predetermined condition; The predetermined condition is: The second goal has a required attribute such that a difference between the second goal and the user's attribute during the course of receiving at least one educational content aimed at the first goal is equal to or less than a predetermined value. The educational support device according to claim 1 .

6. The educational content suggestion unit Based on the difference between the attributes of the user in the process of receiving at least one educational content for the first goal and the attributes required for the user's second goal, at least one educational content for the second goal is generated to allow the user to add attributes, and the educational content is proposed to the user. The educational support device according to claim 5 .

7. The educational system further includes a feedback suggestion unit that suggests to the user, as feedback information, information indicating how a difference in an attribute between the attribute of the user and an attribute required for the second goal of the user changes before and after taking at least one educational content aimed at the second goal. The educational support device according to claim 6.

8. The attribute difference is: The similarity is expressed by at least one of cosine similarity, Euclidean distance, and similarity based on a pre-trained language model including BERT. The educational support device according to claim 1 .

9. Acquire information about a user and information about a first goal of the user; Analyzing attributes of the user and required attributes of the user's first goal using a language model based on information about the user and information about the user's first goal; Analyzing an attribute difference between the attribute of the user and the desired attribute of the first goal of the user; generating at least one educational content for the first goal to prompt the user to add an attribute based on the difference in the attribute, and suggesting the generated educational content to the user; Educational support methods.

10. Acquire information about a user and information about a first goal of the user; Analyzing attributes of the user and required attributes of the user's first goal using a language model based on information about the user and information about the user's first goal; Analyzing an attribute difference between the attribute of the user and the desired attribute of the first goal of the user; generating at least one educational content for the first goal to prompt the user to add an attribute based on the difference in the attribute, and suggesting the generated educational content to the user; program.

Images