Learning assistance device, learning assistance system, and learning assistance method

Abstract

Provided is a technology for proposing an appropriate learning material following update of the learning material.　In this learning assistance device, a storage unit stores: a duty definition document including necessary skills and definitions thereof; learning materials including skills to be learned and definitions thereof; and skill system information obtained by systematizing existing skills, and a processor executes: skill similarity comparison processing of, for each of the necessary skills, identifying a maximum similarity with the existing skill as a first similarity, and identifying a maximum similarity between the necessary skill and the skill to be learned as a second similarity; skill system update processing of updating the skill system information by adding the similar skill to be learned as the existing skill when the second similarity is greater than the first similarity; and learning material recommendation processing of receiving at least one possessed skill and using the skill system information to identify and output a learning material including an unpossessed skill as a recommended learning material.

Description

Learning Support Device, Learning Support System, and Learning Support Method

[0001] The present invention relates to a learning support device, a learning support system, and a learning support method. The present invention claims the priority of Japanese Patent Application No. 2024-192647 filed on November 1, 2024, and for designated countries where incorporation by reference is permitted, the contents described in that application are incorporated into the present application by reference.

[0002] Due to a shortage of human resources caused by the declining birthrate and aging population, and digital technological innovation, the gap between the skills required by companies and the skills possessed by employees has been widening, and investment in reskilling and upskilling has become important. In order to enhance the results of learning, it is necessary to use learning materials at an optimal level and content corresponding to the current objective skills of the learners.

[0003] Therefore, there is a concept of a technology that proposes training based on skill trend information in order to efficiently identify and eliminate skill gaps.

[0004] Patent Document 1 describes a technology related to "an optimal training recommendation device comprising a standard skill trend information database that stores standard skill trend information corresponding to a standard human resource image, a training information database that stores training information corresponding to the standard skill trend information, a skill trend information collection means that collects the skill trend information of the trainee in a question-and-answer format via the Internet, an analysis means that objectively analyzes the skill trend and human resource image of the trainee based on the comparison result between the standard skill trend information and the skill trend information, and a selection means that selects, as optimal training recommendation information, the training information suitable for the trainee from the training information database based on the analysis result of the analysis means."

[0005] JP-A-2002-72848

[0006] However, in the technology described in Patent Document 1, in particular, in rapidly advancing technical fields such as growth fields or niche technical fields, the obsolescence of the standard skill trend information itself occurs, and there are limitations in proposing appropriate training. The object of the present invention is to provide a technology that proposes appropriate learning materials following the update of learning materials.

[0007] The present invention includes several means for solving at least part of the above problems, but an example thereof is as follows. A learning support device according to one aspect of the present invention that solves the above problems comprises one or more processors, an input / output unit, and a storage unit, wherein the storage unit stores at least a job definition document including required skills and definitions of said required skills, learning materials including learning target skills and definitions of said learning target skills, and skill system information that systematizes existing skills recognized as existing in a given technical field, and the processor identifies the similarity of the similar existing skill that has the greatest similarity with the said existing skill as the first similarity for each of the required skills included in the job definition document, and the similarity of the similar learning target skill that has the greatest similarity between the required skill and the learning target skill as the second similarity The system performs the following: a skill similarity comparison process to identify the skills; a skill system update process to update the skill system information by adding the similar target learning skills to the skill system information as existing skills in association with the learning materials if the second similarity is greater than the first similarity; and a learning material recommendation process that receives one or more possessed skills, which are skills possessed by the target person, via the input / output unit, identifies skills among the required skills that do not correspond to the possessed skills as unpossessed skills that the target person does not possess, and uses the skill system information to identify and output the learning materials associated with the target learning skills that correspond to the unpossessed skills as recommended learning materials for the target person.

[0008] According to the present invention, it is possible to provide a technology that proposes appropriate learning materials in response to updates to existing learning materials. Other problems, configurations, and effects will be clarified by the following description of embodiments for carrying out the invention.

[0009] This figure shows an example configuration of the learning support system according to the first embodiment. This figure shows an example of the data structure of the skill system information. This figure shows an example of the data structure of the learning material bibliographic information. This figure shows an example of the data structure of the job definition information. This figure shows an example of the data structure of the possessed skills information. This figure shows an example of the hardware configuration of the learning support device. This figure shows an example of the processing flow of the learning material suggestion process. This figure shows an example of the material suggestion screen. This figure shows an example configuration of the learning support system according to the second embodiment. This figure shows an example of the data structure of the learning material bibliographic information according to the second embodiment. This figure shows an example of the processing flow of the learning material suggestion process according to the second embodiment. This figure shows an example of the material suggestion screen according to the second embodiment. This figure shows an example configuration of the learning support system according to the third embodiment. This figure shows an example of the data structure of the learning material bibliographic information according to the third embodiment. This figure shows an example of the processing flow of the learning material suggestion process according to the third embodiment. This figure shows an example configuration of the learning support system according to the fourth embodiment. This figure shows an example configuration of the learning support system according to the fifth embodiment. This figure shows an example of the data structure of the learning material bibliographic information according to the fifth embodiment. This figure shows an example configuration of the learning support system according to the sixth embodiment.

[0010] <First Embodiment> Embodiments of the present invention will be described below with reference to the drawings. The embodiments are illustrative examples for explaining the present invention, and have been omitted and simplified as appropriate for clarity of explanation. The present invention can also be carried out in various other forms. Unless otherwise specified, each component may be singular or plural.

[0011] The positions, sizes, shapes, and ranges of the components shown in the drawings may not represent their actual positions, sizes, shapes, and ranges in order to facilitate understanding of the invention. Therefore, the present invention is not necessarily limited to the positions, sizes, shapes, and ranges disclosed in the drawings.

[0012] Examples of various types of information may be described using expressions such as "table," "list," and "queue," but these types of information may also be represented by data structures other than these. For example, various types of information such as "XX table," "XX list," and "XX queue" may be referred to as "XX information." When describing identification information, expressions such as "identification information," "identifier," "name," "ID," and "number" are used, but these are interchangeable. Furthermore, the identification information described using these expressions is represented in the examples using symbols, numbers, natural language, or combinations thereof, but the identification information may also be in other formats.

[0013] When there are multiple components with the same or similar function, they may be described using the same symbol but with different subscripts. Furthermore, when it is not necessary to distinguish between these multiple components, the subscripts may be omitted in the description.

[0014] In the embodiments, the processes performed by executing a program may be described. Here, the computer executes the program using a processor (e.g., CPU, GPU) and performs the processing defined in the program using memory resources (e.g., memory) and interface devices (e.g., communication ports). Therefore, the main entity performing the processing by executing the program may be the processor. Similarly, the main entity performing the processing by executing the program may be a controller, device, system, computer, or node having a processor. The main entity performing the processing by executing the program may be an arithmetic unit, and may include a dedicated circuit that performs a specific processing. Here, a dedicated circuit is, for example, an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), or a CPLD (Complex Programmable Logic Device).

[0015] The program may be installed on the computer from the program source. The program source may be, for example, a program distribution server or a storage medium readable by the computer. If the program source is a program distribution server, the program distribution server includes a processor and storage resources for storing the program to be distributed, and the processor of the program distribution server may distribute the program to other computers. In addition, in the embodiment, two or more programs may be implemented as one program, or one program may be implemented as two or more programs.

[0016] Furthermore, while the present invention is typically implemented by an information processing device, it may also be implemented as a platform having the functions of the present invention.

[0017] Figure 1 shows an example configuration of a learning support system according to the first embodiment. The learning support system 1 includes a learning support device 100. The learning support device 100 is also connected to other devices via a network 50 so as to be able to communicate with them.

[0018] For example, the learning support device 100 is an information processing device comprising a storage unit 110, a processing unit 120, a UI (User Interface) device 140, and an NI (Network Interface) device 150.

[0019] [Data Description] The memory unit 110 contains skill system information 111, learning material bibliographic information 112, job definition information 113, possessed skill information 114, personal skill map 115, learning items 116, and recommended learning materials 117.

[0020] Figure 2 shows an example of the data structure of skill system information. Skill system information 111 is information that systematizes existing skills. In particular, in this embodiment, existing skills refer to skills incorporated into skill system information 111, that is, skills that are recognized by engineers or in a given technical field, or skills that are expected to be recognized in the future. Skill system information 111 includes a classification name 111a, a definition 111b, an extracted skill name 111c, an extracted skill definition 111d, a document type 111e, and a document name 111f.

[0021] Classification name 111a is information indicating the classification of the existing skill. Definition 111b is information that defines the existing skill. For example, definition 111b is text information written in natural language that describes the content of the skill. Extracted skill name 111c is the skill name extracted when the existing skill was registered in the skill system. Extracted skill definition 111d is the definition on the learning material from which the existing skill was extracted. For example, extracted skill definition 111d is text information written in natural language that describes the content of the skill in the learning material. Document type 111e is the type of learning material from which the existing skill was extracted. Document name 111f is the name of the learning material from which the existing skill was extracted.

[0022] Figure 3 shows an example of the data structure of learning material bibliographic information. The learning material bibliographic information 112 is management information for the learning material, and it includes the material name 112a and the learning content 112b. The material name 112a is the name of the learning material, for example, the book title or the training name. The learning content 112b is the learning content described in the learning material. The learning content 112b includes at least the target skill and information that defines the target skill. For example, the learning content 112b is the title of the skill in the learning material and text information written in natural language that describes the content of the skill.

[0023] Figure 4 shows an example of the data structure of job definition information. Job definition information 113 is the content of the job definition document. Job definition information 113 includes job 113a and skill requirements 113b. Job 113a is information that defines the job, such as the classification of an engineer. Skill requirements 113b is the content of the skills required for the job. Skill requirements 113b includes at least the required skills and the definition of those required skills. For example, the definition of a required skill is the title of the skill and text information written in natural language that describes the content of the skill in job definition information 113.

[0024] Figure 5 shows an example of the data structure of possessed skills information. Possessed skills information 114 is information about the skills possessed by employees and other persons subject to reskilling. In particular, in this embodiment, possessed skills refer to the skills possessed by individual employees, that is, the skills that individual employees have acquired. Possessed skills information 114 includes employee ID 114a and possessed skills 114b. Employee ID 114a is information that identifies the employee. Possessed skills 114b is information that lists one or more skills possessed by the employee identified by employee ID 114a.

[0025] The processing unit 120 includes a required skills extraction unit 121, a learning item extraction unit 122, a skill similarity comparison unit 123, a skill system update unit 124, a personalized skill map creation unit 125, and a learning material recommendation unit 126.

[0026] The required skills extraction unit 121 extracts the required skills and definitions of those required skills from the job description document (job description information 113) which is written in natural language.

[0027] The learning item extraction unit 122 extracts the learning target skills and the definitions of those learning target skills contained in the learning material bibliographic information 112, which is described in natural language.

[0028] The skill similarity comparison unit 123 identifies, for each required skill included in the job definition document (job definition information 113), the similarity of the existing skill included in the skill system information 111 that has the greatest similarity as the first similarity, and identifies, as the second similarity of the target learning skill included in the learning material bibliographic information 112 that has the greatest similarity between the required skill and the target learning skill.

[0029] If the second similarity identified by the skill similarity comparison unit 123 is greater than the first similarity, the skill system update unit 124 updates the skill system information 111 by adding the similar learning target skill to the skill system information 111 as an existing skill and associating it with the learning material. In other words, if a skill described in the job description is a mismatch with an existing skill included in the skill system and is included in the learning material, the skill system update unit 124 updates the skill system by incorporating that skill and its learning material.

[0030] The individual skill map creation unit 125 creates a skill map for each employee (a mapping of learning materials within the scope of job-defined skills in the skill system). Specifically, the individual skill map creation unit 125 associates the existing skills with the highest degree of similarity with the required skills, and creates an individual skill map 115 that associates the existing skills, updated by the skill system update unit 124, with similar learning target skills and learning materials.

[0031] The learning material recommendation unit 126 identifies necessary skills that do not correspond to the possessed skill information 114 received and stored via the UI device 140 as unpossessed skills, and uses the skill system information 111 to identify and output learning materials associated with the learning target skills corresponding to the unpossessed skills as recommended learning materials.

[0032] The UI (User Interface) device 140 receives various instructions from the user (operator). The input includes information about the skills possessed by employees. For example, the UI device 140 receives information that identifies the skills possessed by each employee via input devices such as a mouse and keyboard.

[0033] The UI device 140 displays recommended learning materials on the screen via a display device. The UI device 140 may be integrated with an input device, such as a touch panel. Furthermore, the UI device 140 may be housed in a separate enclosure from the learning support device 100. In this case, the UI device 140 may be implemented in a separate terminal device, and input and output information may be transferred via a network.

[0034] The NI (Network Interface) device 150 is connected to an external device via a communication path such as a public network like the Internet, a communication network that uses a LAN (Local Area Network), a WAN (Wide Area Network), a VPN (Virtual Private Network), etc., in part or in whole, a mobile phone communication network, etc., or a network 50 that combines these. The network 50 may be a wireless communication network such as Wi-Fi® or 5G (Generation).

[0035] [Explanation of Hardware Configuration] Figure 6 shows an example of the hardware configuration of a learning support device. The learning support device 100 can be realized as a general information processing device 900, which includes a processor 901, hardware memory 902 such as RAM (Random Access Memory), storage 903 such as a hard disk drive (HDD) or SSD (Solid State Drive), a reading device 905 that reads information from a portable storage medium 904 such as a CD (Compact Disk) or DVD (Digital Versatile Disk), an input device 906 such as a keyboard, mouse, barcode reader, or touch panel, an output device 907 such as a display, and a communication device 908 that communicates with other computers via a communication network such as a LAN or the Internet, or as a network system equipped with multiple such information processing devices 900. Furthermore, the reading device 905 may be capable of not only reading but also writing to the portable storage medium 904.

[0036] The processor 901 is, for example, a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). The processor 901 performs various processes by executing predetermined programs loaded from the storage 903 into the memory 902. These programs are, for example, application programs that can be executed on an OS (Operating System) program. These programs may be installed in the storage 903 from a portable storage medium 904 via a reader 905, or they may be downloaded from a network via a communication device 908 and executed by the processor 901.

[0037] For example, the required skills extraction unit 121, the learning item extraction unit 122, the skill similarity comparison unit 123, the skill system update unit 124, the personalized skill map creation unit 125, and the learning material recommendation unit 126 can be implemented by loading programs stored in the storage 903 into the memory 902 and executing them with the processor 901.

[0038] The UI device 140 can be realized by the processor 901 utilizing the input device 906, the output device 907, and the communication device 908. The storage unit 110 can be realized by the processor 901 utilizing the memory 902 or storage 903. The NI device 150 can be realized by the processor 901 utilizing the communication device 908.

[0039] [Explanation of Operation] Figure 7 shows an example of the processing flow for the learning material suggestion process. The learning material suggestion process is started, for example, when the UI device 140 receives an event from the user that includes an instruction to execute the learning material suggestion process.

[0040] First, the required skills extraction unit 121 extracts skill names and definitions from the job definition document (step S001). Specifically, the required skills extraction unit 121 analyzes the natural language description of the skill requirements 113b of the job definition information 113 related to the target employee specified and entered by the user, and extracts the required skills and their definitions. The required skills extraction unit 121 denotes the number of extracted skills as N1. The required skills extraction unit 121 can use an LLM (Large-Scale Language Model) or an existing language analysis processing program to analyze the natural language description.

[0041] The learning item extraction unit 122 then extracts skill names and definitions from the learning materials (step S002). Specifically, the learning item extraction unit 122 analyzes the natural language description of the learning content 112b in the learning material bibliographic information 112 and extracts the skills to be learned and their definitions. The learning item extraction unit 122 determines that the number of extracted skills is N2. The learning item extraction unit 122 can use LLM (Large-Scale Language Model) or existing language analysis processing programs to analyze the natural language description.

[0042] Then, the skill similarity comparison unit 123 loops through the processes of steps S004 to S008 for each skill in the job description (step S003). In other words, the skill similarity comparison unit 123 performs the processes of steps S004 to S008 for each of the N1 skills extracted from the job description.

[0043] Then, the skill similarity comparison unit 123 calculates the similarity between one of the N1 skills extracted from the job definition document and each skill included in the skill system information 111 (step S004). For example, in the process of calculating the skill similarity, the skill similarity comparison unit 123 may vectorize the text of the skill name and the skill definition, obtain the inner product, and calculate the similarity.

[0044] Then, the skill similarity comparison unit 123 calculates the similarity between one of the N1 skills extracted from the job definition document and each learning target skill extracted from the learning material bibliographic information 112 (step S005). For example, in the process of calculating the skill similarity, the skill similarity comparison unit 123 may vectorize the text of the skill name and the skill definition, obtain the inner product, and calculate the similarity.

[0045] Then, the skill system update unit 124 determines whether the highest similarity of the learning material skill exceeds the highest similarity of the skill system skill (step S006). Specifically, the skill system update unit 124 determines whether the similarity of the learning material skill with the highest similarity among the learning material skills whose similarities are calculated in step S005 exceeds the similarity of the existing skill of the skill system with the highest similarity among the existing skills of the skill system whose similarities are calculated in step S004.

[0046] When the highest similarity of the learning material skill exceeds the highest similarity of the skill system skill (in the case of "Yes" in step S006), the skill system update unit 124 adds the learning material skill with the highest similarity to the skill system information 111 (step S007). Specifically, the skill system update unit 124 adds the teaching material name of the learning material to the document name 111f, adds "learning material" to the document type 111e, and adds the learning material skill and its definition to the extracted skill name 111c and the extracted skill definition 111d. The skill system update unit 124 adds the classification and definition to which the learning material skill belongs to the classification name 111a and the definition 111b.

[0047] When the highest similarity of the learning material skills is the same as or lower than the highest similarity of the skill system skills (in step S006, when "No"), the skill system update unit 124 regards it as registered in the skill system without adding the skill to the skill system information 111 (step S008).

[0048] Then, the personal skill map creation unit 125 creates a personal skill map for the target employee (step S009). Specifically, the personal skill map creation unit 125 associates the similar existing skill with the highest similarity with the required skill for the required skill, and creates and stores in the personal skill map 115 a personal skill map 115 that associates the existing skill in the state updated by the skill system update unit 124 with the learning target skill and learning material similar to the existing skill.

[0049] Then, the learning material recommendation unit 126 extracts the unowned skills of the employee (step S010). Specifically, the learning material recommendation unit 126 identifies the required skills that do not correspond to the owned skills 114b of the corresponding employee as the unowned skills of the corresponding employee.

[0050] Then, the learning material recommendation unit 126 selects and displays a combination of learning materials for the unowned skills (step S011). Specifically, the learning material recommendation unit 126 uses the skill system information 111 to identify and output the learning materials associated with the learning target skills corresponding to the unowned skills as the recommended learning materials.

[0051] The above is an example of the processing flow of the learning material proposal process. According to the processing flow of the learning material proposal process, appropriate learning materials can be proposed following the update of the learning materials.

[0052] Figure 8 shows an example of a learning material suggestion screen. The learning material suggestion screen 200 is the screen displayed on the UI device 140 in step S011 of the learning material suggestion process described above. The learning material suggestion screen 200 includes an employee ID display area 210 that displays the employee ID of the employee who is scheduled to learn, and a learning material display area 220 that displays a list of recommended learning materials in order. The learning material display area 220 displays information about the recommended learning materials, including the name of the learning material and the skills to be acquired in that material.

[0053] The above is an example of the learning support system 1 according to the first embodiment of the present invention. According to the learning support system 1 according to the first embodiment, it is possible to suggest appropriate learning materials in accordance with updates to the learning materials.

[0054] It should be noted that the present invention is not limited to the embodiments described above, and various modifications are included. For example, the embodiments described above are described in detail to make the present invention easier to understand, and are not necessarily limited to those having all the configurations described. It is possible to replace some of the configurations of the embodiments with other configurations, and it is also possible to add configurations from other embodiments to the configurations of the embodiments. Furthermore, it is possible to delete some of the configurations of the embodiments.

[0055] For example, in the above embodiment, the learning support device 100 directly references the learning material bibliographic information 112 and the job definition information 113 to extract skills and definitions, etc. However, it is not limited to this, and skills and definitions may also be extracted using a trained model that has been trained by machine learning to extract included skills and their definitions using natural language descriptive text. By doing so, it becomes possible to improve the accuracy of appropriately extracting skills that do not exist in existing skills from learning materials.

[0056] Furthermore, in the process of recommending learning materials, by using a pre-trained model that has undergone reinforcement learning to provide high rewards when it extracts learning materials that employees have actually used and successfully completed, it becomes possible to suggest learning materials that are likely to be selected by those who wish to learn.

[0057] Furthermore, while the first embodiment described above only presents learning materials, it is not limited to this. By further presenting a portion of the learning materials (such as chapters or sections, or other necessary parts), employees can engage in more efficient learning. Such a second embodiment will be explained using Figures 9 to 12.

[0058] <Second Embodiment> The learning support system 2 according to the second embodiment of the present invention has basically the same configuration as the learning support system 1 according to the first embodiment. Therefore, the following description will focus on the differences between it and the learning support system 1 according to the first embodiment.

[0059] Figure 9 is a diagram showing an example configuration of a learning support system according to the second embodiment. As shown in Figure 9, in the learning support system 2 according to the second embodiment, the learning support device 100 has a storage unit 110' which contains learning material bibliographic information 112' in a different format from the learning material bibliographic information 112, and a processing unit 120' which contains a learning section extraction unit 127.

[0060] Figure 10 shows an example of the data structure of learning material bibliographic information according to the second embodiment. The learning material bibliographic information 112' is management information for the learning material, and includes the material name 112a, the learning content 112b', and the available dates and times 112c. The material name 112a is the name of the learning material, for example, the name of the book or the name of the training. The learning content 112b' is the learning content described in the learning material, and includes information such as the chapter structure of the learning content, and in the case of training, the schedule and order of learning. The available dates and times 112c include the date and time of the training in the case of training, the period during which it can be accessed in the case of e-learning, etc., and information on the period during which it can be viewed if there are restrictions on the dates and times in the case of books, etc.

[0061] The learning section extraction unit 127 identifies the chapter number and date / time in which the skill name of the learning material appears. Specifically, the learning section extraction unit 127 reads the learning material bibliographic information 112', reads the chapter number or date / time from the content of the learning content 112b', and reads the date / time in which the learning is possible from the available date / time 112c. The learning material recommendation unit 126 outputs the information of the section or date / time along with the recommended learning material.

[0062] Figure 11 shows an example of the processing flow for the learning material suggestion process according to the second embodiment. The learning material suggestion process according to the second embodiment is basically the same as that according to the first embodiment, but the differences will be explained in detail.

[0063] Between step S002 and step S003, the learning section extraction unit 127 identifies the chapter number and date / time in which the skill name of the learning material appears (step S102). Specifically, the learning section extraction unit 127 reads the learning material bibliographic information 112', reads the chapter number or date / time from the content of the learning content 112b', and reads the date / time in which learning is possible from the available date / time 112c.

[0064] Furthermore, in step S011, the learning material recommendation unit 126 not only selects and displays combinations of learning materials related to unpossessed skills, but also selects combinations of learning materials related to unpossessed skills and displays the chapter number and date and time (step S011').

[0065] Figure 12 shows an example of a teaching material suggestion screen according to the second embodiment. The teaching material suggestion screen 200' according to the second embodiment is a screen displayed on the UI device 140 in step S011' of the learning material suggestion process described above. The teaching material display area 220' of the teaching material suggestion screen 200' displays information about the recommended learning material, including the name of the material, the skills to be acquired in the material, the chapter number, and the date and time.

[0066] The above describes the learning support system 2 according to the second embodiment. According to the learning support system 2 according to the second embodiment, employees can learn more efficiently by further presenting a portion of the learning materials (a more limited range of necessary parts, such as chapters and sections) and the dates and times when the learning materials can be used.

[0067] Furthermore, while the first embodiment described above only presents learning materials, it is not limited to this. By considering the prerequisite knowledge for the learning materials and further presenting the learning sequence, employees can learn more efficiently. Such a third embodiment will be explained using Figures 13 to 15.

[0068] <Third Embodiment> The learning support system 3 according to the third embodiment of the present invention has basically the same configuration as the learning support system 1 according to the first embodiment. Therefore, the following description will focus on the differences from the learning support system 1 according to the first embodiment.

[0069] Figure 13 is a diagram showing an example configuration of a learning support system according to the third embodiment. As shown in Figure 13, in the learning support system 3 according to the third embodiment, the learning support device 100 has a storage unit 110' which contains learning material bibliographic information 112'' in a different format from the learning material bibliographic information 112, and a processing unit 120' which contains a constraint condition extraction unit 128.

[0070] Figure 14 shows an example of the data structure of learning material bibliographic information according to the third embodiment. The learning material bibliographic information 112'' is management information for the learning material, and includes the material name 112a, the learning content 112b'', and the prerequisite knowledge 112d. The material name 112a is the name of the learning material, for example, the name of the book or the name of the training. The learning content 112b'' is the learning content described in the learning material, and includes information such as the chapter structure of the learning content, and in the case of training, the schedule and order of learning. The prerequisite knowledge 112d is information (constraint information) of the skills that are prerequisites for learning as explicitly stated in the material.

[0071] The constraint extraction unit 128 identifies the prerequisite skills of the learning material. Specifically, the constraint extraction unit 128 reads the learning material, identifies and reads the sections in the learning material that indicate prerequisite knowledge and skills described in natural language, and stores them as constraint information in the prerequisite knowledge 112d of the learning material bibliographic information 112''. The constraint extraction unit 128 can use an LLM (Large-Scale Language Model) or an existing language analysis processing program to analyze the descriptive text written in natural language.

[0072] The learning material recommendation unit 126 not only selects and displays combinations of learning materials related to unpossessed skills, but also displays the learning order of the learning materials related to unpossessed skills. Specifically, the learning material recommendation unit 126 constructs and displays the learning order based on constraint information, ensuring that prerequisite skills are learned first.

[0073] Figure 15 shows an example of the processing flow for the learning material suggestion process according to the third embodiment. The learning material suggestion process according to the third embodiment is basically the same as that according to the first embodiment, but the differences will be explained in detail.

[0074] Following step S002, the constraint extraction unit 128 identifies the prerequisite skills of the learning material (step S202). Specifically, the constraint extraction unit 128 reads the learning material, identifies and reads the sections in the learning material that indicate prerequisite knowledge and skills described in natural language, and stores them as constraint information in the prerequisite knowledge 112d of the learning material bibliographic information 112''.

[0075] Furthermore, the loop continuation condition in step S003 is set for each skill in the job definition document and its prerequisite skills (step S203). In this way, prerequisite skills can also be registered in the skill system.

[0076] Furthermore, instead of step S011, the learning material recommendation unit 126 not only selects and displays combinations of learning materials related to unpossessed skills, but also displays the learning order of the learning materials related to unpossessed skills (step S204). Specifically, the learning material recommendation unit 126 constructs and displays the learning order so that prerequisite skills included in the constraint information are learned first. Skills that are not related to the order may be learned in any order.

[0077] The above describes the learning support system 3 according to the third embodiment. According to the learning support system 3 according to the third embodiment, by further presenting the learning sequence while taking into account the prerequisite knowledge of the learning materials, employees will be able to learn more efficiently.

[0078] Furthermore, for example, in the third embodiment described above, the learning order of the learning materials is determined using information on prerequisite skills indicated in the learning materials. However, this is not the only way to do so. By considering prerequisite knowledge not explicitly stated in the learning materials when presenting the learning order, employees can learn more efficiently. Such a fourth embodiment will be explained with reference to Figure 16.

[0079] <Fourth Embodiment> The learning support system 4 according to the fourth embodiment of the present invention has basically the same configuration as the learning support system 1 according to the first embodiment. Therefore, the following description will focus on the differences from the learning support system 1 according to the first embodiment.

[0080] Figure 16 shows an example of the configuration of a learning support system according to the fourth embodiment. As shown in Figure 16, in the learning support system 4 according to the fourth embodiment, the learning support device 100 includes skill dependency information 118 in the storage unit 110'.

[0081] The learning material recommendation unit 126 not only selects and displays combinations of learning materials related to unpossessed skills, but also displays the learning order of the learning materials related to unpossessed skills. Specifically, the learning material recommendation unit 126 constructs and displays the learning order by referring to the skill dependency information 118, ensuring that prerequisite skills are learned first.

[0082] Skill dependency information 118 is information that organizes skills in a hierarchical manner and includes metadata that identifies dependencies (prerequisites, precedence relationships, etc.) between two skills.

[0083] The above describes the learning support system 4 according to the fourth embodiment. According to the learning support system 4 according to the fourth embodiment, employees can learn efficiently by presenting a learning sequence that also takes into account prerequisite knowledge not explicitly stated in the learning materials.

[0084] Furthermore, while the first embodiment described above recommends learning materials related to unpossessed skills, it is not limited to this. By recommending learning materials according to the level of skill proficiency, employees can learn more efficiently. This fifth embodiment will be explained using Figures 17 and 18.

[0085] <Fifth Embodiment> The learning support system 5 according to the fifth embodiment of the present invention has basically the same configuration as the learning support system 1 according to the first embodiment. Therefore, the following description will focus on the differences from the learning support system 1 according to the first embodiment.

[0086] Figure 17 is a diagram showing an example configuration of a learning support system according to the fifth embodiment. As shown in Figure 17, in the learning support system 5 according to the fifth embodiment, the learning support device 100 has a storage unit 110' which contains learning material bibliographic information 112'''' in a different format from the learning material bibliographic information 112, and skill proficiency information 119, and a processing unit 120' which contains a material level extraction unit 129.

[0087] Figure 18 shows an example of the data structure of learning material bibliographic information according to the fifth embodiment. The learning material bibliographic information 112'''' is management information for the learning material, and includes the material name 112a, the learning content 112b', and the material difficulty level 112e. The material name 112a is the name of the learning material, for example, the name of the book or the name of the training. The learning content 112b' is the learning content described in the learning material, and includes information such as the chapter structure of the learning content, and in the case of training, the schedule and order of learning. The material difficulty level 112e is information on the difficulty level of the learning content as explicitly stated in the material.

[0088] The learning material recommendation unit 126 not only selects and displays combinations of learning materials related to unpossessed skills, but also displays recommended learning materials whose difficulty level corresponds to the user's proficiency level for both possessed and unpossessed skills (with the lowest proficiency level for unpossessed skills). Specifically, the learning material recommendation unit 126 refers to the difficulty level of the materials identified by the material level extraction unit 129 and the skill proficiency information 119, and then selects and displays learning materials that exclude unpronounced skills that require a certain level of proficiency above the current proficiency level (i.e., selects learning materials with a difficulty level slightly above the current proficiency level) for learning.

[0089] The material level extraction unit 129 identifies the difficulty level of the learning material. Specifically, the material level extraction unit 129 reads the learning material, identifies the section in the learning material that indicates the difficulty level and is written in natural language, and stores it in the material difficulty level 112e of the learning material bibliographic information 112''''. The material level extraction unit 129 can use an LLM (Large-Scale Language Model) or an existing language analysis processing program to analyze the written text in natural language.

[0090] The skill proficiency information 119 includes additional information on proficiency for each possessed skill 114b, in addition to the possessed skill information 114.

[0091] The above describes the learning support system 5 according to the fifth embodiment. According to the learning support system 5 according to the fifth embodiment, by recommending learning materials according to the level of skill proficiency, employees can avoid highly difficult materials that are incomprehensible or materials that are too easy, and learn efficiently.

[0092] Furthermore, while the first embodiment described above recommends learning materials related to unpossessed skills, it is not limited to this. By recommending learning materials according to future skill needs, employees can learn more efficiently. This sixth embodiment will be explained with reference to Figure 19.

[0093] <Sixth Embodiment> The learning support system 6 according to the sixth embodiment of the present invention has basically the same configuration as the learning support system 1 according to the first embodiment. Therefore, the following description will focus on the differences from the learning support system 1 according to the first embodiment.

[0094] Figure 19 is a diagram showing an example configuration of a learning support system according to the sixth embodiment. As shown in Figure 19, in the learning support system 6 according to the sixth embodiment, the learning support device 100 has job data 160 in the storage unit 110' and a skill demand evaluation unit 130 in the processing unit 120'.

[0095] Job posting data 160 differs from job definition information 113 in that it contains the same information, although it includes the skill requirements that the recruiting organization seeks in the person they want to hire. In other words, job posting data 160 includes the job and the skill requirements. In addition, job posting data 160 also includes information on the timing of the job posting.

[0096] The skill demand evaluation unit 130 evaluates the demand for required skills using the job data 160. More specifically, the skill demand evaluation unit 130 compiles statistics from the job data 160, creates a graph plotting the timing and quantity for each skill, and makes predictions about the trends in the graph to estimate the level of demand for a skill at a predetermined point in time. This allows the skill demand evaluation unit 130 to predict, for example, skills whose demand is expected to increase at a future point in time. The skill demand evaluation unit 130 can use LLM (Large-Scale Language Model) or existing language analysis processing programs to analyze the job data 160.

[0097] The learning material recommendation unit 126 then outputs recommended learning materials according to the skill demand evaluation. Specifically, the learning material recommendation unit 126 displays recommended learning materials for skills with high demand in a higher order, depending on when it is received via the UI device 140. For example, if the learning material recommendation unit 126 is received via the UI device 140 three years from now, it will have the skill demand evaluation unit 130 identify skills with high demand in three years and display recommended learning materials for those skills in a higher order.

[0098] The above describes the learning support system 6 according to the sixth embodiment. According to the learning support system 6 according to the sixth embodiment, employees can learn efficiently by recommending learning materials according to the future demand for skills.

[0099] Each of the above-mentioned parts, configurations, functions, and processing units may be implemented in hardware, in whole or in part, for example, by designing them as integrated circuits. Alternatively, each of the above-mentioned parts, configurations, and functions may be implemented in software by having the processor interpret and execute programs that realize each function. Information such as programs, tables, and files that realize each function can be stored in memory, a recording device such as a hard disk, or a recording medium such as an IC card, SD card, or DVD.

[0100] It should be noted that the control lines and information lines in the embodiments described above are those deemed necessary for explanation and do not necessarily represent all control lines and information lines in the actual product. In practice, it can be assumed that almost all components are interconnected. The present invention has now been described, focusing on its embodiments.

[0101] 1: Learning support system, 50: Network, 100: Learning support device, 110: Memory unit, 111: Skill system information, 112: Learning material bibliographic information, 113: Job definition information, 114: Possessed skill information, 115: Personalized skill map, 116: Learning items, 117: Recommended learning materials, 120: Processing unit, 121: Required skill extraction unit, 122: Learning item extraction unit, 123: Skill similarity comparison unit, 124: Skill system update unit, 125: Personalized skill map creation unit, 126: Learning material recommendation unit, 140: UI device, 150: NI device.

Claims

1. A system comprising one or more processors, an input / output unit, and a storage unit, wherein the storage unit stores at least a job description document including required skills and definitions of said required skills, learning materials including skills to be learned and definitions of said learning materials, and skill system information that systematizes existing skills recognized as existing in a given technical field, and the processor performs a skill similarity comparison process for each of the required skills included in the job description document, which identifies the similarity of the existing skill with the greatest similarity to said existing skill as the first similarity, and identifies the similarity of the learning target skill with the greatest similarity to said required skill as the second similarity, and if the second similarity is greater than the first similarity, a skill system update process which adds the similar learning target skill to the skill system information as an existing skill in association with the learning materials and updates the skill system information, A learning support device that performs a learning material recommendation process, which involves receiving one or more possessed skills, which are skills possessed by the target person, via the input / output unit, identifying skills among the required skills that do not correspond to the possessed skills as unpossessed skills that the target person does not possess, and using the skill system information, identifying and outputting the learning materials associated with the learning target skills that correspond to the unpossessed skills as recommended learning materials for the target person.

2. A learning support device according to claim 1, wherein the processor performs a personal skill map creation process that associates the existing similar skill with the required skill that has the highest degree of similarity with the required skill, and associates the existing skill with the learning target skill that is similar to the learning target skill.

3. A learning support device according to claim 1, wherein the learning material includes information that identifies the portion of the learning material in which the learning target skill is described, and the processor outputs the portion of the learning material together with the recommended learning material in the learning material recommendation process.

4. A learning support device according to claim 1, wherein the learning material includes date and time information that makes the portion of the learning material on which the learning target skill is described available, and the processor outputs the date and time information together with the recommended learning material in the learning material recommendation process.

5. A learning support device according to claim 1, wherein the learning material includes constraint information that identifies skills that are prerequisites for learning the target skill, and the processor, in the learning material recommendation process, outputs the recommended learning material in the order based on the constraint information.

6. A learning support device according to claim 1, wherein the memory unit includes skill dependency information that identifies skills that are prerequisites for learning the target skill, and the processor, in the learning material recommendation process, outputs the recommended learning materials in the order based on the skill dependency information.

7. A learning support device according to claim 1, wherein the learning material includes information that identifies the difficulty level of the learning target skill, the input / output unit receives information indicating the proficiency level of the possessed skill, and the processor, in the learning material recommendation process, outputs the recommended learning material whose proficiency level corresponds to the difficulty level.

8. A learning support device according to claim 1, wherein the storage unit includes job data including required skills, definitions of the required skills, and recruitment periods; the processor performs a skill demand evaluation process to evaluate the demand for the required skills using the job data; and in the learning material recommendation process, outputs recommended learning materials according to the evaluation of the demand for the skills.

9. A learning support system using a computer and a user terminal capable of communicating with the computer via a network, wherein the user terminal transmits user input received via an input / output unit to the computer and outputs output data transmitted from the computer to the input / output unit, the computer comprises a processor, a storage unit, and a communication unit, the storage unit stores at least a job definition document including required skills and definitions of said required skills, learning materials including learning target skills and definitions of said learning target skills, and skill system information systematizing existing skills recognized as existing in a predetermined technical field, the processor, upon receiving the job definition document from the user terminal via the communication unit, performs a skill similarity comparison step in which, for each of the required skills included in the job definition document, the similarity of the similar existing skill that has the greatest similarity with the said existing skill is identified as the first similarity, and the similarity of the similar learning target skill that has the greatest similarity between the required skill and the learning target skill is identified as the second similarity, A learning support system that, when the second similarity is greater than the first similarity, updates the skill system information by adding the similar target learning skills to the skill system information as existing skills in association with the learning materials; and receives one or more possessed skills, which are skills possessed by the target person, via the input / output unit of the user terminal, identifies skills among the required skills that do not correspond to the possessed skills as unpossessed skills that the target person does not possess, and uses the skill system information to identify the learning materials associated with the target learning skills corresponding to the unpossessed skills as recommended learning materials for the target person, generates screen information to output, and displays it on the input / output unit of the user terminal.

10. A learning support method using one or more computers, wherein the computer comprises a processor, an input / output unit, and a storage unit, the storage unit stores at least a job definition document including required skills and definitions of said required skills, learning materials including learning target skills and definitions of said learning target skills, and skill system information systematizing existing skills recognized as existing in a predetermined technical field, the processor performs a skill similarity comparison step, for each of the required skills included in the job definition document, the similarity of the similar existing skill that has the greatest similarity with the said existing skill as the first similarity, and the similarity of the similar learning target skill that has the greatest similarity between the required skill and the learning target skill as the second similarity, and if the second similarity is greater than the first similarity, the skill system update step, which updates the skill system information by adding the similar learning target skill to the skill system information as an existing skill in association with the learning materials, A learning support method that includes a learning material recommendation step, in which the input / output unit receives one or more possessed skills which are skills possessed by the target person, identifies skills among the required skills that do not correspond to the possessed skills as unpossessed skills which the target person does not possess, and uses the skill system information to identify and output the learning materials associated with the learning target skills which correspond to the unpossessed skills as recommended learning materials for the target person.

Images