Education support system and education support method

Abstract

To provide an education support system capable of providing personnel education information that meets potential needs of a customer.SOLUTION: An education support device that is an education support system: stores, in relation to needs data about needs of a customer, solution data about personnel education to be proposed to the customer; stores attribute data for identifying an application range of a solution in association with the solution data; identifies a first similarity degree which is a degree of similarity between the needs data and input data; identifies a keyword corresponding to the attribute data from the input data; identifies a second similarity degree which is a degree of similarity between the attribute data and the keyword; identifies solution data associated with the attribute data corresponding to the identified second similarity degree from the solution data related to the needs data corresponding to the identified first similarity degree; and provides information that is generated on the basis of the identified needs data, the attribute data and the solution data as personnel education information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an education support system and an education support method. [Background technology]

[0002] Designing educational curricula for companies and other organizations is important in developing the human resources they need. Patent Document 1 below discloses a system that creates and presents a curriculum for classes in in-company training and other events. This system estimates the difficulty and dependency of classes based on the class syllabus as well as information from encyclopedias and specialized books obtained from the Internet, and creates and presents a curriculum for classes so that there are no excessive jumps in difficulty between classes and the class content transitions from general concepts to specialized concepts.

[0003] Patent Document 2 below discloses a system that presents recommended courses that are deemed appropriate for a student. This system extracts educational courses based on personal information such as course history, grades, affiliated organizations, and work experience, training information such as skills acquired in training, and weighting information determined by attributes such as the organization, and creates and presents educational training curricula that are important to the student. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6963935 [Patent Document 2] Patent No. 4823509 Summary of the Invention [Problem to be solved by the invention]

[0005] The system in Patent Document 1 presents a curriculum for classes that is created based on the difficulty and dependencies of classes estimated from the class syllabus, etc., and does not present an educational curriculum that meets the latent needs of companies.

[0006] Furthermore, the system in Patent Document 2 presents an educational training curriculum consisting of educational courses extracted based on the student's previous attendance record and the capabilities required by the organization, and does not present an educational curriculum that meets the potential needs of companies.

[0007] An object of the present invention is to provide an education support system and an education support method that can provide personnel education information that meets the potential needs of customers. [Means for solving the problem]

[0008] An education support system according to one embodiment of the present invention comprises: means for associating known data related to customer needs with hierarchical needs data, storing hierarchical solution data of known data related to human resource training to be proposed to a customer as a solution, and storing attribute data for identifying the scope of application of the solution in association with the solution data; means for identifying a first similarity which is the similarity between the stored needs data and input data entered as a target for searching for needs; means for identifying a keyword corresponding to the attribute data from the input data and identifying a second similarity which is the similarity between the stored attribute data and the keyword; means for identifying solution data linked to attribute data corresponding to the second similarity identified by the second similarity identifying means from solution data associated with needs data corresponding to the first similarity identified by the first similarity identifying means; and means for providing information generated based on the needs data corresponding to the first similarity identified by the first similarity identifying means, the attribute data corresponding to the second similarity identified by the second similarity identifying means, and the solution data identified by the solution data identifying means as human resource training information.

[0009] An education support method according to another aspect of the present invention is a method executed by a processor, and includes the steps of: associating known data related to customer needs with hierarchical needs data, storing hierarchical solution data of known data related to human resource training to be proposed to the customer as a solution, and storing attribute data for identifying the scope of application of the solution in association with the solution data; identifying a first similarity which is the similarity between the stored needs data and input data entered as a target for searching for needs; identifying a keyword corresponding to the attribute data from the input data and identifying a second similarity which is the similarity between the stored attribute data and the keyword; identifying solution data linked to the attribute data corresponding to the second similarity identified in the second similarity identifying step from solution data associated with the needs data corresponding to the first similarity identified in the first similarity identifying step; and providing information generated based on the needs data corresponding to the first similarity identified in the first similarity identifying step, the attribute data corresponding to the second similarity identified in the second similarity identifying step, and the solution data identified in the solution data identifying step as human resource training information.

[0010] According to these aspects, known solution data can be stored in association with known needs data, attribute data can be stored linked to solution data, a first similarity between the needs data and input data can be identified, and a second similarity between the attribute data and a keyword corresponding to the attribute data included in the input data can be identified. Then, from solution data associated with the needs data corresponding to the identified first similarity, solution data linked to the attribute data corresponding to the identified second similarity can be identified, and further human resource training information generated based on the needs data corresponding to the identified first similarity, the attribute data corresponding to the identified second similarity, and the identified solution data can be provided.

[0011] This makes it possible to identify needs that are latent in the input data and provide, as human resource training information, solutions that address the identified needs and that correspond to keywords contained in the input data. [Effects of the Invention]

[0012] According to the present invention, it is possible to provide an education support system and an education support method that can provide personnel education information that meets the potential needs of customers. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a block diagram illustrating a configuration of an education support device according to an embodiment. [Figure 2] FIG. 2 is a conceptual diagram illustrating an example of the data structure of needs data and solution data. [Figure 3] FIG. 2 is a conceptual diagram illustrating an example of the data structure of attribute data. [Figure 4] FIG. 2 is a process flow diagram illustrating the operation of the education support device according to the embodiment. [Figure 5] FIG. 10 is a conceptual diagram for explaining the importance of solution data. [Figure 6] FIG. 10 is a schematic diagram illustrating an example of proposal information. DETAILED DESCRIPTION OF THE INVENTION

[0014] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS A preferred embodiment of the present invention will be described with reference to the accompanying drawings. In the drawings, components with the same reference numerals have the same or similar configurations.

[0015] [Configuration of educational support device] An example of the configuration of an education support device 1 according to an embodiment will be described with reference to Fig. 1. The education support device 1 has, as its physical configuration, for example, a processor 11, a storage device 12, and a communication interface 13. Note that it is not necessary for the education support device 1 to have all of the components; for example, part or all of the storage device 12 may be provided in a device separate from the education support device 1, resulting in an education support system including the education support device 1 and the separate device.

[0016] The processor 11 is, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit), etc. The processor 11 executes a program 121 stored in the storage device 12, thereby functioning as a control unit 111 that executes processes for realizing various functions described below.

[0017] The communication interface 13 functions as a communication unit that connects to a network and communicates with other devices on the network.

[0018] The storage device 12 is a computer-readable recording medium such as a disk drive or a semiconductor memory. The storage device 12 functions as a storage unit that stores a program 121 for realizing various functions of the education support device 1 and various data 122 used by the program 121.

[0019] The various data 122 include, for example, needs data that is a hierarchical structure of known data related to the needs (issues) of customers such as companies, solution data that is a hierarchical structure of known data related to human resource training proposed to customers as solutions, attribute data for specifying the scope of application of the solution, course offering data related to courses to be offered to customers, etc. Each type of data will be explained in turn below.

[0020] The needs data and solution data are managed, for example, by a tree structure consisting of a plurality of nodes. As the tree structure, for example, a first tree structure consisting of a plurality of first nodes that store needs data and a second tree structure consisting of a plurality of second nodes that store solution data can be provided. Note that the management of the needs data and solution data is not limited to a tree structure, and other hierarchical structures such as a graph structure, a network structure, a hierarchical clustering structure, a pyramid structure, etc. may also be used.

[0021] An example of the data structure of needs data and solution data is shown in Figure 2. Needs data A and solution data B shown in Figure 2 are respectively excerpts from the needs data and solution data managed in a tree structure.

[0022] In the needs data A, the higher the hierarchy, the more abstract the content of the human resource issues assigned to the nodes, and the lower the hierarchy, the more specific the content of the human resource issues assigned to the nodes. In Figure 2, the human resource issues (higher) hierarchy Aa has the most abstract content, the human resource issues (lower) hierarchy Ac has the most specific content, and the human resource issues (middle) hierarchy Ab has content somewhere in between.

[0023] In the solution data B shown in FIG. 2, a subject Ba indicating the field of human resource training is assigned to a node in the upper layer, and one or more courses Bb provided in the subject Ba in the upper layer are assigned to a node in the lower layer.

[0024] A degree of association indicating the strength of the association is set between a node of needs data A and a node of solution data B. Specifically, FIG. 2 illustrates that the node with the highest degree of association with node Ac1 of needs data A is node Ba1 of solution data B. Similarly, the node with the highest degree of association with node Ac2 of needs data A is node Ba2 of solution data B, and the node with the second highest degree of association is node Ba1 of solution data B. Similarly, the two nodes with the highest degree of association with node Ac3 of needs data A are node Ba1 and node Ba3 of solution data B.

[0025] By associating as shown in Figure 2, for example, if a customer has needs for nodes Aa1, Ab1, and Ac1 in needs data A, taking each course in the "Introduction to Automation" section of node Ba1, which is most closely related to node Ac1, can be identified as a potential solution for the customer.

[0026] FIG. 3 shows an example of the data structure of attribute data. The attribute data C shown in FIG. 3 includes, as data items, attribute categories Ca, which are categories for specifying the scope of application of a solution, and attribute labels Cb, which indicate the breakdown of the attribute categories Ca. In FIG. 3, the attribute categories Ca are exemplified as "Affiliation," "Target Process," "Proficiency Level," and "Language." Furthermore, the attribute labels Cb indicating the breakdown of "Affiliation" are exemplified as "Maintenance," "Production Technology," "Production Management," "Quality Maintenance," and "Design / Development." Similarly, the attribute labels Cb indicating the breakdown of "Target Process" are exemplified as "Robot Process" and "XX Process." The attribute labels Cb indicating the breakdown of "Proficiency Level" are exemplified as "Introduction," "Basic," "Applied," and "Advanced." The attribute labels Cb indicating the breakdown of "Language" are exemplified as "Japanese," "English," and "Chinese."

[0027] As shown in Fig. 3, attribute data C is linked to solution data B. For example, "Maintenance" in the attribute label Cb of attribute data C is linked to "Introduction to Automation," "Safety Engineer," and "Maintenance Engineer" in the subject Ba of solution data B.

[0028] By linking in this way, for example, if the attribute corresponding to input data described below is "maintenance," the courses provided for "Introduction to Automation," "Safety Engineer," and "Maintenance Engineer," which are linked to "maintenance," can be used to narrow down and prioritize the courses to be proposed to the customer. Note that course provision data that predetermines the order in which courses provided for each department are to be taken may also be stored, and when departments and courses are proposed to the customer, the order in which the courses are to be taken may also be proposed.

[0029] 4, various functions realized by the control unit 111 will be described. The processing procedure shown in this processing flow diagram is an example of the operation of the education support device 1, and the operation of the education support device 1 is not limited to this processing procedure.

[0030] First, the control unit 111 executes a division process for the input data (step S101). The division process will be described below.

[0031] Input data is data that is the target of identifying customer needs. For example, text information such as minutes containing content that may be needs or voice of the customer (VOC) can be used as input data. Note that input data is not limited to text information. For example, images or videos can also be used as target data. In this case, it is preferable to extract characteristic elements from the images or videos and convert them into text information.

[0032] In the division process, the control unit 111 divides a sentence included in the input data into a plurality of divided input data by using, for example, morphological analysis or a rule base. The divided input data is data obtained by dividing a sentence included in the input data into, for example, punctuation marks or phrases. Note that the divided input data may be data obtained by dividing the input data into elements that represent a single unit of meaning.

[0033] In addition, in the splitting process, the control unit 111 inputs multiple split input data into a natural language processing (NLP) model such as Bert (Bidirectional Encoder Representations from Transformers), and obtains a sequence of vectors (hereinafter also referred to as "first vectors") output from the model.

[0034] Following step S101, the control unit 111 executes a weighting process for the needs data A (step S102). The weighting process for the needs data A will be described below.

[0035] In the weighting process for the needs data A, the control unit 111 inputs the data stored in each node of the needs data A into a natural language processing model such as Bert, and obtains a sequence of vectors (hereinafter also referred to as "second vectors") output from the model. That is, the control unit 111 obtains a second vector for each node of the needs data A.

[0036] Next, the control unit 111 calculates the similarity between the first vector and each second vector (hereinafter also referred to as "first similarity") using the first vector corresponding to the input data and the second vector corresponding to each node of the needs data A. That is, the control unit 111 calculates the first similarity between each node of the needs data A and the first vector corresponding to the input data. It is preferable to calculate the similarity using, for example, cosine similarity.

[0037] Next, the control unit 111 assigns the first similarity as a weight to each node of the needs data A. This first similarity can express the strength of the association between each node of the needs data A and the input data. Therefore, the weighted needs data A can be regarded as a system that represents the importance of the customer's needs. This makes it possible to identify, among the nodes of the needs data A, nodes with a large weight (first similarity) as data that the customer needs highly.

[0038] In parallel with step S102, the control unit 111 executes a weighting process for the attribute label Cb (step S103). The weighting process for the attribute label Cb will be described below.

[0039] In the weighting process for the attribute label Cb, the control unit 111 identifies a keyword corresponding to the data of the attribute label Cb of the attribute data C from the input data.

[0040] Next, the control unit 111 inputs the keyword identified from the input data into a natural language processing model such as Bert, and acquires a vector (hereinafter also referred to as a "third vector") output from the model.

[0041] Next, the control unit 111 inputs the data of the attribute label Cb of the attribute data C into a natural language processing model such as Bert, and obtains a vector (hereinafter also referred to as a "fourth vector") output from the model.

[0042] Next, the control unit 111 calculates the similarity between each third vector and each fourth vector (hereinafter also referred to as "second similarity") using the third vector corresponding to each keyword of the input data and the fourth vector corresponding to each attribute label Cb. That is, the control unit 111 calculates the second similarity between the third vector corresponding to each keyword of the input data for each attribute label Cb of the attribute data C. It is preferable to calculate the similarity using, for example, cosine similarity.

[0043] Next, the control unit 111 assigns the second similarity as a weight to each attribute label Cb of the attribute data C. This second similarity can express the strength of association between each attribute label Cb of the attribute data C and the input data. Therefore, the weighted attribute data C can be used as an important factor for narrowing down solutions to customer needs. This makes it possible to identify, among the attribute labels Cb of the attribute data C, attribute labels Cb with a large weight (second similarity) as data with a high degree of association with the input data.

[0044] Here, the control unit 111 may list a predetermined number of attribute labels Cb with large weights for each attribute category Ca.

[0045] Following step S102, the control unit 111 executes weight propagation processing from the needs data A to the solution data B (step S104). The weight propagation processing from the needs data A to the solution data B will be described below.

[0046] In the weight propagation process from needs data A to solution data B, the control unit 111 calculates the weight to be assigned to each node of solution data B using the weight assigned to each node of needs data A. At this time, it is preferable to use a propagation matrix. When using a propagation matrix, the weight of the node placed at the lowest layer of needs data A and the propagation matrix are used to calculate the weight of the node placed at the lowest layer of solution data B.

[0047] The propagation matrix is ​​a matrix whose rows are the number of nodes at the lowest level of the needs data A and whose columns are the number of nodes at the lowest level of the solution data B. It is preferable to set the strength of the association (degree of association) between the corresponding nodes in each element of the propagation matrix.

[0048] After assigning weights to each node in the lowest hierarchy of solution data B using the propagation matrix, the weights of the linked lower nodes are added to the nodes above each node in the lowest hierarchy, and this process is repeated from the lower hierarchy to the top hierarchy. This allows the weights of needs data A to be propagated to solution data B.

[0049] Following step S103, the control unit 111 executes weight propagation processing from the attribute label Cb to the solution data B (step S105). The weight propagation processing from the attribute label Cb to the solution data B can be performed in the same manner as the weight propagation processing from the needs data A to the solution data B described above.

[0050] Following the above steps S104 and S105, the control unit 111 executes a course identification process (step S106). The course identification process will be described below.

[0051] In the course identification process, the control unit 111 determines the importance (hereinafter also referred to as "first importance") of the solution data B based on the weight assigned in the above step S102. Then, the control unit 111 arranges the solution data B in descending order of the determined first importance.

[0052] Here, the first importance of solution data B can be determined, for example, using the weight assigned to each node in needs data A and the strength of association (degree of association) between each node in needs data A and each node in solution data B. Specifically, it can be determined by identifying nodes in needs data A whose weight is equal to or greater than a first predetermined value, and then using the weight of the identified node and nodes in solution data B whose strength of association with the identified node is equal to or greater than a second predetermined value. This will be described with reference to Fig. 5.

[0053] For example, suppose the weights of node A1 and node A2 in needs data A are "0.9" and "0.7", which are greater than or equal to a first predetermined value. Also, suppose that nodes B1 and B2 in solution data B have a relationship strength with node A1 greater than or equal to a second predetermined value, and node B2 has a relationship strength with node A2 greater than or equal to the second predetermined value. Furthermore, suppose that the relationship strength between node A1 and node B1 is "0.9", the relationship strength between node A1 and node B2 is "0.5", and the relationship strength between node A2 and node B2 is "0.4".

[0054] In this case, the first importance of node B1 in solution data B is determined as "0.81" by multiplying the weight of node A1, "0.9", by the strength of its relationship with node B1, "0.9". On the other hand, the first importance of node B2 in solution data B is determined as "0.73" by adding the product of the weight of node A1, "0.9", by the strength of its relationship with node B2, "0.5", and the product of the weight of node A2, "0.7", by the strength of its relationship with node B2, "0.4". The first importance of other nodes in solution data B can be determined in a similar manner.

[0055] Furthermore, the control unit 111 determines the importance of solution data B (hereinafter also referred to as "second importance") based on the weight assigned in step S103. The second importance of solution data B can be determined in the same manner as the procedure for determining the first importance of solution data B described above.

[0056] Next, the control unit 111 identifies solution data B from among the solution data B arranged in descending order of first importance by using attribute data C that has a high second importance relative to the solution data B. Specifically, it identifies solution data B that has a high first importance and a high second importance relative to the solution data B. The solution data B to be identified may be one or more.

[0057] Next, the control unit 111 lists the identified course Bb of the solution data B as a course to be proposed to the customer.

[0058] Following step S106, control unit 111 executes a curriculum construction process (step S107). The curriculum construction process will be described below.

[0059] In the curriculum configuration process, the control unit 111 determines the order of the courses Bb to be provided to the customer based on the courses Bb listed in step S105. When determining the order of the courses Bb, course provision data that predetermines the order of the courses to be provided may be referenced. In this embodiment, a collection of courses whose order of provision is determined is called a curriculum.

[0060] Following step S107, the control unit 111 executes a suggested information providing process (step S108). The suggested information providing process will be described below.

[0061] In the proposed information providing process, the control unit 111 provides the customer with information generated based on the needs data A identified in step S102, the attribute label Cb identified in step S103, and the course Bb of the solution data B identified in step S106 as proposed information (human resource training information). When generating the proposed information, various pieces of information managed (stored) in association with each piece of data may be added as additional items as appropriate.

[0062] An example of proposed information is shown in Fig. 6. The proposed information 6a in Fig. 6 exemplarily presents a proposed course 6b, which is an item based on the course Bb in the solution data B, a learning subject 6c, which is an item based on the attribute label Cb, a human resources task 6d, which is an item based on the needs data A, and other additional items.

[0063] When providing the proposed information, the proposed information may be displayed on a display device, may be output from a printing device, or may be provided to an external device as electronic data. The display device and the printing device may be provided in the education support device 1, or may be connected to the education support device 1 via a network.

[0064] As described above, the education support device 1 according to the embodiment can store known solution data B in association with known needs data A, and store attribute data C linked to the solution data B, identify needs data A that has a high similarity to input data, and identify attribute data C that has a high similarity to a keyword corresponding to attribute data C included in the input data. Then, from solution data B associated with the identified needs data A, it can identify solution data B linked to the identified attribute data C, and further provide proposal information 5a generated based on the identified needs data A, attribute data C, and solution data B to a customer as human resource training information.

[0065] This allows the needs latent in the input data to be identified, and solutions that address the identified needs and that correspond to the keywords contained in the input data to be provided to the customer as human resource training information.

[0066] Therefore, the education support device 1 according to the embodiment can provide personnel education information that meets the potential needs of the customer.

[0067] The present invention is not limited to the above-described embodiment, and can be embodied in various other forms without departing from the spirit of the present invention. Therefore, the above-described embodiment is merely an example in all respects and should not be interpreted as being limiting. For example, the order of the above-described processing steps can be arbitrarily changed or executed in parallel as long as no contradiction occurs in the processing content.

[0068] In the above-described embodiment, the needs data A with a high first similarity is identified from the needs data A, the attribute data C with a high second similarity is identified from the attribute data C, and then the solution data B linked to the identified attribute data C is identified from the solution data B associated with the identified needs data A, but the method of identifying the solution data B is not limited to this. For example, the first similarity may be calculated to identify the first similarity, the second similarity may be calculated to identify the second similarity, and then the solution data B linked to the attribute data C corresponding to the identified second similarity may be identified from the solution data B associated with the needs data A corresponding to the identified first similarity.

[0069] [Note] Aspects of this embodiment include the following disclosure.

[0070] (Appendix 1) a means for associating known data relating to customer needs with hierarchical needs data, storing known data relating to human resource training to be proposed to the customer as a solution in hierarchical solution data, and storing attribute data for specifying the scope of application of the solution in association with the solution data; means for identifying a first similarity which is a similarity between the stored needs data and input data input as a target for searching for the needs; a means for identifying a keyword corresponding to the attribute data from the input data and identifying a second similarity between the stored attribute data and the keyword; a means for identifying the solution data linked to the attribute data corresponding to the second similarity identified by the means for identifying the second similarity from among the solution data associated with the needs data corresponding to the first similarity identified by the means for identifying the first similarity; a means for providing, as human resource training information, information generated based on the needs data corresponding to the first similarity identified by the means for identifying the first similarity, the attribute data corresponding to the second similarity identified by the means for identifying the second similarity, and the solution data identified by the means for identifying the solution data; An educational support system equipped with:

[0071] (Appendix 2) When specifying the first similarity, the means for specifying the first similarity vectorizes the needs data and the input data, respectively, and calculates the first similarity using the vector of the needs data and the vector of the input data, thereby specifying the first similarity. 1. An educational support system as described in Appendix 1.

[0072] (Appendix 3) the means for specifying the second similarity, when specifying the second similarity, vectorizes the attribute data and the keyword, respectively, and calculates the second similarity using the vector of the attribute data and the vector of the keyword, thereby specifying the second similarity. 3. An educational support system according to claim 1 or 2.

[0073] (Appendix 4) the means for identifying solution data arranges the solution data associated with the needs data in descending order of first importance based on the first importance of the solution data determined using the first similarity identified by the means for identifying first similarity, and identifies the solution data from the arranged solution data using the second importance of the solution data determined using the second similarity. 4. An educational support system according to any one of appendices 1 to 3.

[0074] (Appendix 5) The storage unit storing the needs data in a first tree structure consisting of a plurality of nodes in which the more abstract the needs data is assigned to a higher hierarchy and the more concrete the needs data is assigned to a lower hierarchy; the solution data is stored in a second tree structure consisting of a plurality of nodes in which departments representing the fields of human resource training are assigned to a higher level and courses provided in the departments are assigned to a lower level; 5. An educational support system according to any one of appendices 1 to 4.

[0075] (Appendix 6) A method executed by a processor (11), comprising: a step of associating known data on customer needs with hierarchical needs data, storing known data on human resource training to be proposed to the customer as a solution in hierarchical solution data, and storing attribute data for identifying the scope of application of the solution in association with the solution data; A step of identifying a first similarity which is a similarity between the stored needs data and input data input as a target for searching for the needs; a step of identifying a keyword corresponding to the attribute data from the input data, and identifying a second similarity which is a similarity between the stored attribute data and the keyword; identifying the solution data linked to the attribute data corresponding to the second similarity identified in the step of identifying the second similarity from among the solution data associated with the needs data corresponding to the first similarity identified in the step of identifying the first similarity; providing, as human resource training information, information generated based on the needs data corresponding to the first similarity identified in the step of identifying the first similarity, the attribute data corresponding to the second similarity identified in the step of identifying the second similarity, and the solution data identified in the step of identifying the solution data; Educational support methods, including: [Explanation of symbols]

[0076] 1...Education support device, 11...Processor, 12...Storage device, 13...Communication interface, 111...Control unit, 121...Program, 122...Data, A...Needs data, B...Solution data, C...Attribute data

Claims

1. a means for associating known data relating to customer needs with hierarchical needs data, storing known data relating to human resource training to be proposed to the customer as a solution in hierarchical solution data, and storing attribute data for specifying the scope of application of the solution in association with the solution data; a means for identifying a first similarity between the stored needs data and input data input as a target for searching for the needs; a means for identifying a keyword corresponding to the attribute data from the input data and identifying a second similarity between the stored attribute data and the keyword; a means for identifying the solution data linked to the attribute data corresponding to the second similarity identified by the means for identifying the second similarity from among the solution data associated with the needs data corresponding to the first similarity identified by the means for identifying the first similarity; a means for providing, as human resource training information, information generated based on the needs data corresponding to the first similarity identified by the means for identifying the first similarity, the attribute data corresponding to the second similarity identified by the means for identifying the second similarity, and the solution data identified by the means for identifying the solution data; An educational support system equipped with:

2. the means for specifying the first similarity specifies the first similarity by vectorizing the needs data and the input data, respectively, and calculating the first similarity using the vector of the needs data and the vector of the input data. The education support system according to claim 1.

3. the means for specifying the second similarity, when specifying the second similarity, vectorizes the attribute data and the keyword, respectively, and calculates the second similarity using the vector of the attribute data and the vector of the keyword, thereby specifying the second similarity. The education support system according to claim 1.

4. the means for identifying solution data arranges the solution data associated with the needs data in descending order of first importance based on the first importance of the solution data determined using the first similarity identified by the means for identifying first similarity, and identifies the solution data from the arranged solution data using the second importance of the solution data determined using the second similarity. The education support system according to claim 1.

5. The storage means comprises: storing the needs data in a first tree structure consisting of a plurality of nodes in which the more abstract the needs data is assigned to a higher hierarchy and the more concrete the needs data is assigned to a lower hierarchy; the solution data is stored in a second tree structure consisting of a plurality of nodes in which departments representing the fields of human resource training are assigned to a higher level and courses provided in the departments are assigned to a lower level; The education support system according to claim 1.

6. 1. A processor-implemented method comprising: a step of associating known data on customer needs with hierarchical needs data, storing known data on human resource training to be proposed to the customer as a solution in hierarchical solution data, and storing attribute data for identifying the scope of application of the solution in association with the solution data; A step of identifying a first similarity which is a similarity between the stored needs data and input data input as a target for searching for the needs; a step of identifying a keyword corresponding to the attribute data from the input data, and identifying a second similarity which is a similarity between the stored attribute data and the keyword; identifying the solution data linked to the attribute data corresponding to the second similarity identified in the step of identifying the second similarity from among the solution data associated with the needs data corresponding to the first similarity identified in the step of identifying the first similarity; providing, as human resource training information, information generated based on the needs data corresponding to the first similarity identified in the step of identifying the first similarity, the attribute data corresponding to the second similarity identified in the step of identifying the second similarity, and the solution data identified in the step of identifying the solution data; Educational support methods, including:

Images