Personnel evaluation support device

Abstract

To support objective and fair personnel evaluations that do not require comparison with other members. [Solution] The personnel evaluation support device 1 of the present invention comprises an information acquisition unit 111 that acquires workplace information and subject information related to the subject of personnel evaluation, a provisional goal providing unit 112 that provides the subject's supervisor with a provisional goal related to the subject's personnel evaluation, generated by a process of inputting the workplace information and the subject information into a first machine learning model, a final goal acquisition unit 113 that acquires a final goal related to the personnel evaluation provided by the supervisor, a provisional evaluation providing unit 114 that provides the supervisor with a provisional evaluation related to the subject's personnel evaluation, generated by a process of inputting the achievements related to the final goal and the final goal into a second machine learning model, a final evaluation acquisition unit 115 that acquires a final evaluation related to the personnel evaluation provided by the supervisor, and a machine learning unit 116 that performs machine learning related to the first machine learning model and the second machine learning model.

Description

[Technical field]

[0001] The present invention relates to a personnel evaluation support device. [Background technology]

[0002] With regard to the operational management of an organization exemplified by a company, personnel evaluation is conducted to evaluate the performance of members exemplified by employees, etc. A proper personnel evaluation conveys to members what they should do as members of an organization and increases their motivation.

[0003] However, there is a concern that manual personnel evaluation, such as a personnel evaluation in which a goal is set and the achievement level of the goal is evaluated by a superior, may not be satisfactory to the members being evaluated. For example, members may be dissatisfied with the evaluation due to concerns that the goal setting or the achievement level of the goal in the personnel evaluation is biased based on the subjectivity of the evaluator, or that there is variation in the goals set by humans. Therefore, there is a demand for technology that supports objective personnel evaluation.

[0004] Regarding technologies for supporting objective personnel evaluation in conventional services and conventional technologies, Patent Document 1 discloses a performance evaluation system characterized by including a server and an information terminal, the server including a sales data storage means for storing sales data indicating sales made by a sales representative, an information generation means for tallying up the sales data stored in the sales data storage means for each sales representative and generating the information upon receiving a request for information evaluating the performance of sales activities performed by the sales representative, and an information supply means for supplying the information generated by the information generation means to the information terminal that originated the request. The information generated by the information generation means of the performance evaluation system is, for example, sales data corrected using sales of selected products, a regional economic index, customer satisfaction level, etc.

[0005] The technology described in Patent Document 1 can assist in proper performance evaluation of sales representatives by enabling them to judge the relative merits of their own performance relative to other sales representatives based on the amount of corrected sales data. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] JP 2003-022361 A Summary of the Invention [Problem to be solved by the invention]

[0007] However, such an evaluation using comparisons with other members may cause dissatisfaction among members who are evaluated low because their performance is inferior to that of other members, even if all members have achieved excellent results. In addition, such a relative evaluation using comparisons may function as a proper evaluation in an organization composed only of members who perform similar tasks, as is the case with the organization targeted by Patent Document 1, but it is difficult to apply to an organization in which it is difficult to evaluate performance using the same indicators, as exemplified by an organization that aims to achieve goals by combining a wide variety of tasks.

[0008] Therefore, there is room for further improvement in the technology described in Patent Document 1 in terms of enabling objective and fair personnel evaluation without making comparison with other members a mandatory requirement.

[0009] An object of the present invention is to support objective and fair personnel evaluation that does not require comparison with other members. [Means for solving the problem]

[0010] As a result of intensive research to solve the above problems, the inventors have found that the above object can be achieved by utilizing a machine learning model not only in the evaluation of performance but also in the generation of the performance goal itself that serves as an index of the evaluation. Thus, the inventors have completed the present invention.

[0011] According to one aspect of the present invention, there is provided an information acquisition unit that acquires workplace information and subject information relating to a subject of a personnel evaluation, a provisional goal providing unit that provides a supervisor of the subject with a provisional goal relating to the personnel evaluation of the subject, the provisional goal being generated by a process of inputting the workplace information and the subject information into a first machine learning model, a final goal acquiring unit that acquires a final goal relating to the personnel evaluation provided by the supervisor, a provisional evaluation providing unit that provides the supervisor with a provisional evaluation relating to the personnel evaluation of the subject, the provisional evaluation being generated by a process of inputting performance related to the final goal and the final goal into a second machine learning model, a final evaluation acquiring unit that acquires a final evaluation relating to the personnel evaluation provided by the supervisor, and a machine learning unit that performs machine learning relating to the first machine learning model and the second machine learning model, wherein the machine learning unit performs machine learning relating to the first machine learning model and the second machine learning model using learning data including the workplace information and the subject information as explanatory variables and the final goal as a target variable, Books The present invention provides a support device for personnel evaluation, which performs machine learning related to the second machine learning model using learning data that includes a goal as an explanatory variable and the actual evaluation as a target variable.

[0012] In this aspect of the present invention, a tentative goal related to personnel evaluation is generated by a first machine learning model in which machine learning related to the goal is performed as described below. Since the tentative goal is generated by a machine learning model, it can be said to be an objective goal.

[0013] However, due to circumstances such as insufficient pre-learning of the machine learning model, there is a concern that the provisional target generated in this manner is not an appropriate target that fully reflects the needs of the organization or the like regarding personnel evaluation. Therefore, in this aspect of the present invention, the provisional target is provided to a superior, and the superior obtains a final target revised as necessary. Furthermore, in this aspect of the present invention, machine learning of the first machine learning model is performed using learning data including the final target, so that a more appropriate provisional target is generated.

[0014] In addition, in this aspect of the present invention, a provisional evaluation for the personnel evaluation is generated by a second machine learning model in which machine learning related to the evaluation described below is performed. Since the provisional evaluation is generated by the machine learning model, it can be said to be an objective evaluation.

[0015] However, due to circumstances such as insufficient pre-learning of the machine learning model, there is a concern that the provisional evaluation generated in this manner is not an appropriate evaluation. Therefore, in this aspect of the present invention, the provisional evaluation is provided to a superior, and a final evaluation revised by the superior as necessary is obtained. Furthermore, in this aspect of the present invention, machine learning is performed on a second machine learning model using learning data including the final evaluation, so that a more appropriate provisional evaluation is generated.

[0016] In this way, this aspect of the present invention utilizes machine learning models not only to evaluate performance, but also to generate the performance targets themselves that serve as indicators of the evaluation, and further, by feeding back revised targets or evaluations by supervisors as necessary to each machine learning model, it is possible to assist in providing objective and fair personnel evaluations that do not require comparison with other members. Effect of the Invention

[0017] As described above, the present invention can support objective and fair personnel evaluation that does not require comparison with other members. [Brief description of the drawings]

[0018] [Figure 1]FIG. 1 is a block diagram showing an example of the hardware configuration and software configuration of a system S of the present embodiment. [Diagram 2] FIG. 2 is an example of the workplace information database 131. [Diagram 3] FIG. 3 is a main flowchart showing an example of a preferable flow of the support process executed by the support device 1 of this embodiment. [Figure 4] FIG. 4 is a flow chart continuing from the previous figure. [Diagram 5] FIG. 5 is a flow chart continuing from the previous figure. [Figure 6] FIG. 6 is a flow chart continuing from the previous figure. [Figure 7] FIG. 7 is a flow chart continuing from the previous figure. [Figure 8] FIG. 8 is a flow chart continuing from the previous figure. [Figure 9] FIG. 9 is a flow chart continuing from the previous figure. [Figure 10] FIG. 10 is an example of a display on terminal T. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0019] First, although the following disclosure, diagrams, and / or claims are described as being described alone or in combination with one or more other aspects, the subject matter of the immediate disclosure is not intended to be so limited. That is, the immediate disclosure, diagrams, and claims are intended to encompass the various aspects described herein, each alone or in one or more combinations with each other. For example, even if the immediate disclosure describes and illustrates a first embodiment, a second embodiment, and a third embodiment in such a manner that the first embodiment is described and illustrated in particular with respect to the second embodiment, or the second embodiment is described and illustrated only with respect to the third embodiment, the immediate disclosure and illustrations are not so limited and may include only the first embodiment, only the second embodiment, only the third embodiment, or one or more combinations of the first, second, and / or third embodiments, such as the first and second embodiments, the first and third embodiments, the second and third embodiments, or the first, second, and third embodiments.

[0020] The use of the phrase "or" in this document shall mean a "non-exclusive" arrangement unless expressly specified otherwise. For example, "item x is A or B" shall mean either: (1) item x is either A or B, but not both; or (2) item x is both A and B. In other words, the word "or" is not used to define an "exclusive" arrangement.

[0021] Additionally, as used herein, the phrases "comprising at least one of" and "comprising at least one of the following," when used in conjunction with a system or element, mean that the system or element includes one or more of the elements listed after the phrase. For example, if there are three types of elements, a first element, a second element, and a third element, the phrases "comprising at least one of" and "comprising at least one of the following" are to be interpreted as any of the following structural arrangements: a device including the first element, a device including the second element, a device including the third element, a device including the first and second elements, a device including the first and third elements, a device including the second and third elements, or a device including the first, second, and third elements.

[0022] A similar interpretation is intended when the phrase "used in at least one of the following" is used in this context. Additionally, "and / or" is used in this context as a verbal conjunction to indicate that one or more of the listed elements or conditions are included or occur. For example, a device that includes a first element, a second element, and / or a third element is to be interpreted as any of the following structural arrangements: a device that includes the first element, a device that includes the second element, a device that includes the third element, a device that includes the first element and the second element, a device that includes the first element and the third element, a device that includes the second element and the third element, or a device that includes the first element, the second element, and the third element.

[0023] In addition, the use of the phrase "and / or" in the text means a "non-exclusive" arrangement, as stipulated in the Japanese Industrial Standards (JIS) "JIS Z 8301 - Format and preparation method of standard sheets."

[0024] Hereinafter, an example of an embodiment of the present invention will be described in detail with reference to the drawings.

[0025] <System S> 1 is a block diagram showing an example of the hardware configuration and software configuration of a system S of this embodiment. The following describes an example of a preferred embodiment of the hardware configuration and software configuration of the system S of this embodiment using FIG.

[0026] The system S includes a personnel evaluation support device 1 and a terminal T configured to communicate with the support device 1 via a network N.

[0027] [Support device 1] The support device 1 includes a control unit 11, a storage unit 13, and a communication unit 14. The type of the support device 1 is not particularly limited, and may be, for example, a server device, a cloud server, or the like.

[0028] [Control unit 11] The control unit 11 includes a Central Processing Unit (CPU), a Random Access Memory (RAM), and a Read Only Memory (ROM).

[0029] The control unit 11 cooperates with at least one of the storage unit 13 and the communication unit 14 as necessary. The control unit 11 then realizes the software components of the program of this embodiment executed by the support device 1, such as an information acquisition unit 111, a provisional goal providing unit 112, a final goal acquiring unit 113, a provisional evaluation providing unit 114, a final evaluation acquiring unit 115, a machine learning unit 116, a skill map acquiring unit 117, a curriculum providing unit 118, a workplace specification acquiring unit 119, a personnel system draft providing unit 120, and a grant support information providing unit 121.

[0030] [Storage section 13] The memory unit 13 is a device in which data and / or files are stored, and has a storage unit that non-temporarily stores data using a hard disk, a semiconductor memory, a recording medium, a memory card, etc. The memory unit 13 stores a program executed by a microcomputer, a workplace information database 131, a machine learning model, etc.

[0031] (Workplace Information Database 131) The workplace information database 131 stores workplace information and subject information related to subjects of performance evaluation. This allows the support device 1 to generate and provide a tentative goal related to the performance evaluation of the subject by inputting the workplace information and subject information into the first machine learning model.

[0032] In this example, the workplace information and the target person information are stored in the same workplace information database 131, but the workplace information and the target person information in this embodiment may be stored in independent databases. In order to efficiently execute data processing such as storage, acquisition, and update, it is preferable that the workplace information and the target person information are stored in association with information that identifies the information, such as an information ID.

[0033] The workplace information includes information for each of various hierarchical levels of the workplace to which the subject belongs. Examples of such information for each hierarchy include information including the policies and specifications of the entire company to which the subject belongs, the policies of the department in the company to which the subject belongs, and the policies of the team in the department to which the subject belongs. The policies may include policies associated with a period such as the current month or the current term. The specifications of the entire company are, for example, the industry, sales volume, or employee size of the company. Since the workplace information includes the specifications of the workplace, the support device 1 can generate and provide support information for supporting a draft of the personnel system of the workplace or an application for a subsidy by inputting the specifications of the workplace into the fourth machine learning model.

[0034] The subject information includes, for example, the subject's achievements, the subject's grade (no title, team leader, section chief, department manager, etc.), the subject's skill map, or information related to a previous evaluation of the subject. The achievements or previous evaluations may be associated with a period such as last week, last month, or last term. The achievements include, for example, achievements indicated by numbers or symbols similar to numbers (for example, symbols indicating grades such as "A, B, C"), achievements indicated by sentences, etc. The skill map is, for example, data listing skills that the subject has acquired or mastered among skills exemplified by qualifications related to the workplace. By including the skill map in the subject information, the support device 1 can generate and provide a human resource development curriculum for the subject by inputting the skill map into a third machine learning model.

[0035] 2 is an example of the workplace information database 131. The database of this example stores workplace information related to the entire company identified by an information ID "D0001", workplace information related to the accounting department identified by an information ID "D0011", target person information related to a target person "Tanaka △△ (accounting department)" identified by an information ID "D0111", target person information related to a target person "Suzuki △△ (accounting department)" identified by an information ID "D0112", and the like.

[0036] The workplace information for the entire company identified by the information ID "D0001" includes information such as the industry "manufacturing", sales volume "△△ billion yen", employee size "△△ people", and the company's overall policy "promoting digitalization of operations" and "promoting paperless operations". This allows the support device 1 to generate and provide provisional goals for personnel evaluation that reflect the industry, size, or overall policy of the company. This also allows the support device 1 to determine a subsidy appropriate for the industry or size of the company, and generate and provide support information that supports applications for the subsidy.

[0037] The workplace information for the department (accounting department) identified by the information ID "D0011" includes information on the department's policies such as "renovation of the billing management system," "renovation of the voucher management system," and "establishment of an invoice workflow." This allows the support device 1 to generate and provide tentative goals for personnel evaluation that reflect the department's policies.

[0038] The subject information for the subject "Tanaka △△ (Accounting Department)" identified by the information ID "D0111" includes information such as achievements "Requests for renewal of billing management system compiled", "△△ invoice tasks handled (last month)", grade "Team leader", skill map "△△ qualification (Level 2)", previous evaluation "Leadership in △△ tasks...". This allows the support device 1 to generate and provide provisional goals for personnel evaluation that reflect the achievements, grade, skill map, or previous evaluation of the subject. This also allows the support device 1 to generate and provide a human resources development curriculum that reflects the skill map, etc.

[0039] The subject information for the subject "Suzuki △△ (Accounting Department)" identified by the information ID "D0112" includes information such as achievements "Requests for renewal of billing management system compiled", "△△ invoice cases handled (last month)", grade "no position", skill map "△△ qualification (grade 4)", previous evaluation "make further effort in △△ work...", etc. This allows the support device 1 to generate and provide a tentative goal for personnel evaluation that reflects the achievements, grade, skill map, or previous evaluation of the subject. In addition, this allows the support device 1 to generate and provide a human resource development curriculum that reflects the skill map, etc.

[0040] In this way, the achievements, grade, skill map, previous evaluations, etc., which differ for each subject are stored in the workplace information database 131 and used by the first machine learning model, so that the support device 1 can generate a provisional goal that is even higher than that of "Suzuki △△" for a subject "Tanaka △△" whose achievements, grade, skill map, and previous evaluations are superior to other subjects such as "Suzuki △△" and provide it to the terminal T used by the subject's supervisor. The support device 1 can also generate and provide a more appropriate provisional goal that reflects the policies of the entire workplace, the policies of the department, etc.

[0041] The storage unit 13 stores at least various data necessary for processing using the first machine learning model and processing using the second machine learning model. These data preferably include the machine learning models themselves, but may also be various data (e.g., data related to an Application Programming Interface (API)) necessary for using the machine learning models stored and executed in an external device. The storage unit 13 preferably further stores various data necessary for processing using the third machine learning model, the fourth machine learning model, or the fifth machine learning model.

[0042] (First machine learning model) The first machine learning model is a machine learning model that generates a tentative goal for the personnel evaluation of a subject by inputting workplace information and subject information related to the subject of the personnel evaluation. The first machine learning model may be a model that has a common part with the second machine learning model, the third machine learning model, the fourth machine learning model, or the fifth machine learning model described later.

[0043] In order to generate a provisional goal that appropriately reflects the workplace information and the subject information, the first machine learning model is preferably pre-trained using training data that includes the workplace information and the subject information as explanatory variables and includes a goal based on these information as a target variable. This allows the first machine learning model to deduce and generate an appropriate provisional goal based on the pre-training for inputs having complex correlations such as workplace goals and the subject's achievements, grade, and skill map. An example of such a correlation is a correlation in which achievements and skills unrelated to workplace goals have a small effect on goal setting, and achievements and skills deeply related to workplace goals have a large effect on goal setting.

[0044] In order to enable the use of workplace information and target information written in natural language as input, the first machine learning model preferably includes a language model. In order to enable the use of workplace information and target information written in a wide variety of natural language expressions as input, the language model is preferably a large-scale language model exemplified by ChatGPT (registered trademark) and the like. The large-scale language model understands inputs of workplace information and target information written in a wide variety of natural language expressions, etc., by using emergent abilities related to natural language acquired by a large-scale neural network having a large amount of parameters, for example, more than 100 billion, a huge amount of learning data, for example, more than 100 billion tokens, etc., and contributes to the generation of goals, etc. related to personnel evaluation that reflect this understanding.

[0045] (Second machine learning model) The second machine learning model is a machine learning model that generates a provisional evaluation for the personnel evaluation of a subject by inputting the achievements and goals related to the goals. The second machine learning model may be a model that has a common part with the first machine learning model, or the third, fourth, or fifth machine learning model described below.

[0046] In order to generate a provisional evaluation that appropriately reflects the achievements related to the goal and the goal, the second machine learning model is preferably pre-trained using training data that includes the achievements related to the goal and the goal as explanatory variables and the evaluation based on the achievements and the goal as a response variable. This allows the second machine learning model to deduce and generate an appropriate provisional evaluation based on the pre-training for an input having a complex correlation between the goal, achievements, etc. An example of such a correlation is a correlation in which achievements unrelated to the goal have a small effect on the evaluation, and achievements closely related to the goal have a large effect on the setting of the evaluation.

[0047] The second machine learning model preferably includes a language model so that achievements and goals described in a natural language can be used as inputs. The language model is preferably a large-scale language model, such as ChatGPT (registered trademark), so that achievements and goals described in a wide variety of natural language expressions can be used as inputs.

[0048] (Third machine learning model) The third machine learning model is a machine learning model that generates a human resource development curriculum for a subject by inputting a skill map of the subject. The third machine learning model may be a model that has a common part with the first machine learning model, the second machine learning model, the fourth machine learning model described below, or the fifth machine learning model. In order to reflect other circumstances of the skill map of the subject, when the subject's achievements, grade, or previous evaluation is input in addition to the skill map, the third machine learning model preferably generates a human resource development curriculum that reflects the input.

[0049] In order to generate a human resource development curriculum in which input such as a skill map is appropriately reflected, the third machine learning model is preferably pre-trained using training data including input data such as a skill map as an explanatory variable and including a human resource development curriculum based on the input as a target variable. This allows the third machine learning model to deduce and generate an appropriate human resource development curriculum based on the pre-training for an input having complex correlations such as a skill map including many skills. An example of such a correlation is a correlation in which the priority of developing skills unrelated to currently possessed skills is low and the priority of developing skills closely related to currently possessed skills is high.

[0050] In order to be able to use inputs such as skill maps written in natural language, the third machine learning model preferably includes a language model. In order to be able to use inputs such as skill maps written in a wide variety of natural language expressions, the language model is preferably a large-scale language model, such as exemplified by ChatGPT (registered trademark).

[0051] (4th machine learning model) The fourth machine learning model is a machine learning model that generates a draft of a personnel system for a workplace by inputting workplace specifications related to personnel evaluation. The fourth machine learning model may be a model that has a common part with the first machine learning model, the second machine learning model, the third machine learning model, or the fifth machine learning model described below.

[0052] In order to generate a draft of a personnel system for a workplace, the fourth machine learning model is preferably pre-trained using training data including workplace specifications related to personnel evaluation as explanatory variables and a draft of the personnel system for the workplace related to the specifications as a target variable. This allows the fourth machine learning model to deduce and generate an appropriate draft based on the pre-training for inputs having complex correlations such as specifications including a large number of elements. As an example of such correlation, there is a correlation between increasing the number of grades when the company is small but the industry is one in which the chain of command in the work is important, and decreasing the number of grades when the company is small but the industry is one in which individual autonomy in the work is important.

[0053] The draft personnel system referred to here includes, for example, a draft rank system, an evaluation sheet, and a wage table. This allows the fourth machine learning model to generate a draft personnel system that integrates a rank system, an evaluation sheet used for evaluation of each rank, and a wage table according to the rank, etc.

[0054] In order to be able to use inputs of properties written in natural language, the fourth machine learning model preferably includes a language model, which is preferably a large-scale language model, such as ChatGPT (registered trademark), in order to be able to use inputs of properties written in a wide variety of natural language expressions.

[0055] (5th machine learning model) The fifth machine learning model is a machine learning model that generates support information to support an application for a subsidy to be received by the workplace by inputting specifications of the workplace. The fifth machine learning model may be a model having a common part with the first machine learning model, the second machine learning model, the third machine learning model, or the fourth machine learning model.

[0056] In order to generate support information that supports an appropriate application for a subsidy for the workplace specifications, the fifth machine learning model is preferably pre-trained using training data that includes the workplace specifications as explanatory variables and the support information that supports an appropriate application for a subsidy for the specifications as a target variable. This allows the fifth machine learning model to deduce and generate appropriate support information based on the pre-training for inputs having complex correlations such as specifications including a large number of elements. An example of such a correlation is a correlation that associates a small company in a specific industry with support information related to applications for subsidies for small and medium-sized enterprises in that industry.

[0057] In order to support the application of an appropriate subsidy, the fifth machine learning model preferably generates support information including information indicating an appropriate subsidy for a workplace having the specifications by inputting the specifications of the workplace. In this case, the fifth machine learning model is preferably pre-trained using training data including the specifications of the workplace as explanatory variables and the support information including information indicating an appropriate subsidy for the specifications as a target variable.

[0058] In order to be able to use inputs of properties written in natural language, the fifth machine learning model preferably includes a language model, which is preferably a large-scale language model, such as ChatGPT (registered trademark), in order to be able to use inputs of properties written in a wide variety of natural language expressions.

[0059] [Communications Section 14] The communication unit 14 is not particularly limited as long as it can connect the support device 1 to the network N and communicate with it. Examples of the communication unit 14 include a network card compatible with the Ethernet standard and a communication device compatible with wireless LAN.

[0060] [Network N] The type of the network N is not particularly limited as long as it enables communication with the support device 1, etc. The type of the network N is, for example, the Internet, a mobile phone network, a wireless LAN, etc.

[0061] [Terminal T] The terminal T is used by a superior of an organization that performs personnel evaluation. The terminal T executes a process of instructing the support device 1 to provide a tentative goal or a tentative evaluation, a process of acquiring the generated tentative goal or tentative evaluation from the support device 1 and displaying it, a process of providing the support device 1 with a real goal or real evaluation inputted by referring to the displayed tentative goal or tentative evaluation, a process of instructing the support device 1 to provide a human resource development curriculum, a draft of a personnel system, or support information for grant applications, etc. The types of the terminal T include, for example, a smartphone, a tablet terminal, a portable terminal such as a notebook computer, a fixed terminal such as a desktop computer, etc.

[0062] [Main Flowchart of Support Processing] Fig. 3 is a main flow chart showing an example of a preferred flow of the support process executed by the support device 1 of this embodiment. Figs. 4, 5, 6, 7, 8, and 9 are each a flow chart continuing from the previous figures. Below, an example of a preferred flow of the support process will be described using Figs. 3 to 9.

[0063] The support process executes a series of processes to generate a tentative goal related to a personnel evaluation of a target person, provide the generated tentative goal, obtain a real goal provided by a superior to which the tentative goal was provided, and use the real goal in machine learning of a first machine learning model. Steps S1 to S8 are an example of the process.

[0064] [Step S1: Determine whether to generate a tentative target] The control unit 11, in cooperation with the storage unit 13 and the communication unit 14, executes a process of determining whether to generate a tentative goal related to the personnel evaluation of the subject (a tentative goal generation determination step). If it is determined that a tentative goal should be generated, the control unit 11 shifts the process to step S2. If it is determined that a tentative goal should not be generated, the control unit 11 shifts the process to step S5.

[0065] In the tentative target generation determination step, the control unit 11 determines that a tentative target is to be generated when, for example, a command is issued from the terminal T to instruct the provision of a tentative target, exemplified by a command related to AI target setting, etc.

[0066] [Step S2: Obtain workplace information and target person information] The control unit 11 cooperates with the storage unit 13 and the communication unit 14 to execute the information acquisition unit 111. Then, the control unit 11 executes a process of acquiring workplace information and subject information related to the subject of the personnel evaluation by the information acquisition unit 111 (information acquisition step). The control unit 11 shifts the process to step S3.

[0067] In the information acquisition step, the information acquisition unit 111 acquires, for example, the workplace information and the target person information exemplified in the section on the workplace information database 131 from the workplace information database 131. In order to add data to the workplace information database 131 or update the stored data, the information acquisition unit 111 may acquire a part or all of the workplace information or the target person information from the terminal T.

[0068] [Step S3: Generate a tentative target] The control unit 11 cooperates with the storage unit 13 and the communication unit 14 to execute the provisional goal providing unit 112. Then, the control unit 11 executes a process of generating a provisional goal related to the personnel evaluation of the above-mentioned subject by inputting the workplace information and subject information acquired in the information acquisition step into the first machine learning model by the provisional goal providing unit 112 (provisional goal generating step). The control unit 11 shifts the process to step S4.

[0069] When the first machine learning model includes a language model, the provisional goal providing unit 112 may generate the above-mentioned provisional goal by inputting a prompt including workplace information, subject information, and an instruction to generate a goal into the language model.

[0070] When the number of provisional goals to be generated is specified, the provisional goal providing unit 112 may generate the provisional goal in that number. In order to provide a provisional goal for each policy separately determined for the entire workplace, a department, a group, or the like, the provisional goal providing unit 112 may generate a provisional goal for each policy indicated by the workplace information or the target person information.

[0071] [Step S4: Provide a tentative goal] The control unit 11 executes a process of providing the tentative goal generated in the tentative goal generating step by the tentative goal providing unit 112 (tentative goal providing step). The control unit 11 shifts the process to step S5. The tentative goal providing unit 112 provides the tentative goal to the terminal T, for example.

[0072] Through the series of processes from step S1 to step S4, the supervisor using terminal T can obtain a tentative goal related to the personnel evaluation of the target person. The supervisor can then use the tentative goal as is as a real goal, or modify the tentative goal and use it as a real goal.

[0073] [Step S5: Determine whether to acquire this target] The control unit 11 cooperates with the storage unit 13 and the communication unit 14 to execute the main target acquisition unit 113. Then, the control unit 11 executes a process of determining whether to acquire the main target related to the above-mentioned tentative target by the main target acquisition unit 113 (main target acquisition determination step). If it is determined that the main target is to be acquired, the control unit 11 shifts the process to step S6. If it is determined that the main target is not to be acquired, the control unit 11 shifts the process to step S9.

[0074] In the main target acquisition determination step, when the control unit 11 receives data of the main target transmitted from the terminal T, for example, it determines that the main target is to be acquired.

[0075] [Step S6: Acquire this target] The control unit 11 executes the process of acquiring the above-mentioned final goal by the final goal acquisition unit 113 (final goal acquisition step). The control unit 11 shifts the process to step S7.

[0076] [Step S7: Store this goal] The control unit 11 executes a process of storing the above-mentioned final goal in the memory unit 13 by the final goal acquisition unit 113 (a final goal storage step). The control unit 11 moves the process to step S8.

[0077] [Step S8: Run machine learning for the first machine learning model] The control unit 11 executes the machine learning unit 116 in cooperation with the storage unit 13 and the communication unit 14. Then, the control unit 11 executes a process of executing machine learning of the first machine learning model using learning data including the above-mentioned workplace information and subject information as explanatory variables and including the above-mentioned main goal as a target variable, by the machine learning unit 116 (first machine learning step). The control unit 11 shifts the process to step S9.

[0078] In the first machine learning step, the machine learning unit 116 performs the above-mentioned machine learning to reflect the actual goal set by the superior after modifying the tentative goal as necessary in the first machine learning model. This allows the support device 1 to generate a more appropriate tentative goal that reflects the actual goal modified as necessary.

[0079] After the real goal is provided, the support process of this embodiment executes a series of processes to generate a provisional evaluation based on the performance and the real goal, obtain a final evaluation provided by the superior to whom the provisional evaluation was provided, and use the final evaluation in machine learning of the second machine learning model. Steps S9 to S16 are an example of the process.

[0080] [Step S9: Determine whether to generate a provisional evaluation] The control unit 11, in cooperation with the storage unit 13 and the communication unit 14, executes a process of determining whether to generate a provisional evaluation related to the personnel evaluation of the subject (provisional evaluation generation determination step). If it is determined that a provisional evaluation should be generated, the control unit 11 shifts the process to step S10. If it is determined that a provisional evaluation should not be generated, the control unit 11 shifts the process to step S13.

[0081] In the provisional evaluation generation determination step, the control unit 11 determines that a provisional evaluation should be generated when, for example, an instruction is given from the terminal T to provide a provisional evaluation, such as an instruction related to AI evaluation.

[0082] [Step S10: Obtain results and actual targets] The control unit 11 executes a process of acquiring the achievements and final targets related to the person who is the subject of the personnel evaluation through the information acquisition unit 111 (achievement acquisition step). The control unit 11 shifts the process to step S11.

[0083] In the achievement record acquisition step, the information acquisition unit 111 acquires, for example, achievement records exemplified in the section on the workplace information database 131 from the workplace information database 131. In order to add data to the workplace information database 131 or update the stored data, the information acquisition unit 111 may acquire a part or all of the achievement records from the terminal T.

[0084] [Step S11: Generate a provisional evaluation] The control unit 11 cooperates with the storage unit 13 and the communication unit 14 to execute the provisional evaluation providing unit 114. Then, the control unit 11 executes a process of generating a provisional evaluation related to the personnel evaluation of the subject described above by inputting the above-mentioned achievements and the final goal into the second machine learning model through the provisional evaluation providing unit 114 (provisional evaluation generating step). The control unit 11 shifts the process to step S12.

[0085] If the second machine learning model includes a language model, the provisional evaluation providing unit 114 may generate the provisional evaluation described above by inputting the achievements, the actual goal, and a prompt including an instruction to generate the evaluation into the language model.

[0086] [Step S12: Provide a provisional evaluation] The control unit 11 executes a process of providing the provisional evaluation generated in the provisional evaluation generation step by the provisional evaluation providing unit 114 (provisional evaluation providing step). The control unit 11 shifts the process to step S13. The provisional evaluation providing unit 114 provides the provisional evaluation to the terminal T, for example.

[0087] Through the series of processes from step S9 to step S12, the superior using terminal T can obtain a provisional evaluation of the personnel evaluation of the target person. The superior can then use the provisional evaluation as is as a final evaluation, or can modify the provisional evaluation and use it as a final evaluation.

[0088] [Step S13: Determine whether to obtain a formal evaluation] The control unit 11 cooperates with the storage unit 13 and the communication unit 14 to execute the final evaluation acquisition unit 115. Then, the control unit 11 executes a process of determining whether to acquire a final evaluation related to the above-mentioned provisional evaluation by the final evaluation acquisition unit 115 (a final evaluation acquisition determination step). If it is determined that the final evaluation should be acquired, the control unit 11 shifts the process to step S14. If it is determined that the final evaluation should not be acquired, the control unit 11 shifts the process to step S17.

[0089] In the final evaluation acquisition determination step, the control unit 11 determines that the final evaluation is to be acquired when, for example, data of the final evaluation transmitted from the terminal T is received.

[0090] [Step S14: Obtain this evaluation] The control unit 11 executes the process of acquiring the above-mentioned final evaluation by the final evaluation acquisition unit 115 (final evaluation acquisition step). The control unit 11 moves the process to step S15.

[0091] [Step S15: Store this evaluation] The control unit 11 executes a process of storing the above-mentioned final evaluation in the storage unit 13 by the final evaluation acquisition unit 115 (a final evaluation storage step). The control unit 11 moves the process to step S16.

[0092] [List of evaluations] In order to make it easier for the supervisor to check the evaluations of multiple members, the support process preferably includes a procedure for displaying a list of the above-mentioned provisional evaluations or final evaluations of multiple members (evaluation display step). In order to make it easier to view the evaluation stages, this procedure preferably displays the evaluations in different colors. In order to make it easier to understand the correspondence between the grades and the evaluations, this procedure preferably displays the grades side by side. In order to make it easier to view the grade stages, this procedure preferably displays the grades in different colors. In order to make it easier for the supervisor to view the grade stages, this procedure preferably displays the grades in different colors. It is preferable that these color-coding criteria be customizable.

[0093] [Step S16: Run machine learning on the second machine learning model] The control unit 11 cooperates with the storage unit 13 and the communication unit 14 to execute the machine learning unit 116. Then, the control unit 11 executes a process of executing machine learning of a second machine learning model using learning data including the above-mentioned achievement and the final goal as explanatory variables and including the above-mentioned final evaluation as a response variable, by the machine learning unit 116 (second machine learning step). The control unit 11 shifts the process to step S17.

[0094] In the second machine learning step, the machine learning unit 116 performs the above-mentioned machine learning to reflect the final evaluation, which is set by the superior after correcting the provisional evaluation as necessary, in the second machine learning model. This allows the support device 1 to generate a more appropriate provisional evaluation that reflects the final evaluation corrected as necessary.

[0095] The support process preferably includes a series of processes for generating and providing a human resource development curriculum for the subject based on the subject's skill map, etc. Steps S17 to S20 are an example of the process.

[0096] [Step S17: Determine whether to generate a human resource development curriculum] The control unit 11, in cooperation with the storage unit 13 and the communication unit 14, executes a process of determining whether to generate a human resource development curriculum for the subject (curriculum generation determination step). If it is determined that a curriculum is to be generated, the control unit 11 shifts the process to step S18. If it is not determined that a curriculum is to be generated, the control unit 11 shifts the process to step S21.

[0097] In the curriculum generation determination step, the control unit 11 determines that a human resource development curriculum will be generated when, for example, a command is issued from terminal T instructing the terminal to provide a human resource development curriculum, such as a command related to AI curriculum generation.

[0098] [Step S18: Get skill map] The control unit 11 executes the skill map acquisition unit 117 in cooperation with the storage unit 13 and the communication unit 14. Then, the control unit 11 executes a process of acquiring a skill map related to the above-mentioned subject by the skill map acquisition unit 117 (skill map acquisition step). The control unit 11 shifts the process to step S19.

[0099] In the skill map acquisition step, the skill map acquisition unit 117 acquires, for example, a skill map exemplified in the section on the workplace information database 131 from the workplace information database 131. In order to add data to the workplace information database 131 or update the data stored therein, the skill map acquisition unit 117 may acquire a part or all of the skill map from the terminal T.

[0100] [Skill map display] The support process preferably includes a step of displaying the skill map acquired in the skill map acquisition step (skill map display step). In this case, in order to facilitate comparison between multiple members, the step preferably displays the skill maps related to multiple members in a list format. As an example of such a display, there is a table display in which the members and the skills displayed in the skill map are plotted on different axes vertically and horizontally.

[0101] In the list display, the steps are preferably displayed with the grades written on them so that the correspondence between the grades and the skills can be easily understood. In order to make it easy to see the skill and grade stages at a glance, the steps are preferably displayed with the skills or grades color-coded. In order to provide a display that is easy for the supervisor to see, it is preferable that the color-coding criteria be customizable.

[0102] [Step S19: Generate human resource development curriculum] The control unit 11 cooperates with the storage unit 13 and the communication unit 14 to execute the curriculum providing unit 118. Then, the control unit 11 executes a process of generating a human resource development curriculum for the above-mentioned subject by inputting input data such as the above-mentioned skill map into the third machine learning model through the curriculum providing unit 118 (human resource development curriculum generation step). The control unit 11 shifts the process to step S20.

[0103] In the human resource development curriculum generation step, the curriculum providing unit 118 preferably uses the subject's achievements, grades, or previous evaluations as additional input data for the third machine learning model in addition to the skill map. This allows the curriculum providing unit 118 to generate a human resource development curriculum reflecting the additional input data. If the third machine learning model includes a language model, the curriculum providing unit 118 may generate the above-mentioned human resource development curriculum by a process of inputting a prompt including an instruction to generate the skill map and the human resource development curriculum into the language model.

[0104] [Step S20: Provide a human resource development curriculum] The control unit 11 executes a process of providing the human resource development curriculum generated in the human resource development curriculum generation step by the curriculum providing unit 118 (curriculum providing step). The control unit 11 shifts the process to step S21. The curriculum providing unit 118 provides the human resource development curriculum to the terminal T, for example.

[0105] [On supervisor-initiated revisions and machine learning in human resource development curriculum] In order to allow a supervisor to manually correct any deficiencies in the automatic generation, the series of processes for generating and providing a human resource development curriculum, similar to the series of processes for obtaining an actual goal based on the provided interim goal, preferably includes a procedure for obtaining, after providing the human resource development curriculum generated by the third machine learning model, the human resource development curriculum modified by the supervisor, etc., as necessary, from a terminal T used by the supervisor, etc.

[0106] At this time, it is preferable that the series of processes further includes a procedure of performing machine learning of a third machine learning model using learning data including the skill map as an explanatory variable and including the human resource development curriculum acquired from the terminal T as a target variable. This enables the third machine learning model to generate a more appropriate human resource development curriculum.

[0107] The support process preferably includes a series of processes for generating and providing a draft of a personnel system for the workplace based on the specifications of the workplace, etc. Steps S21 to S24 are an example of the process.

[0108] [Step S21: Determine whether to generate a personnel system] The control unit 11, in cooperation with the storage unit 13 and the communication unit 14, executes a process of determining whether to generate a draft of a personnel system for the workplace (a personnel system draft generation determination step). If it is determined that a draft is to be generated, the control unit 11 shifts the process to step S22. If it is not determined that a draft is to be generated, the control unit 11 shifts the process to step S25.

[0109] In the personnel system draft generation determination step, the control unit 11 determines that a draft will be generated when, for example, a command is issued from terminal T instructing to provide a draft personnel system, as exemplified by commands related to AI personnel system generation.

[0110] [Step S22: Obtain workplace specifications] The control unit 11 executes the workplace specification acquisition unit 119 in cooperation with the storage unit 13 and the communication unit 14. Then, the control unit 11 executes a process to acquire the workplace specifications described above by the workplace specification acquisition unit 119 (first workplace specification acquisition step). The control unit 11 moves the process to step S23.

[0111] In the first workplace specification acquisition step, the workplace specification acquisition unit 119 acquires, for example, the workplace specifications exemplified in the section on workplace information database 131 from the workplace information database 131. In order to add data to the workplace information database 131 or update the data stored therein, the workplace specification acquisition unit 119 may acquire some or all of the workplace specifications from the terminal T.

[0112] [Step S23: Generate personnel system] The control unit 11 cooperates with the storage unit 13 and the communication unit 14 to execute the personnel system draft providing unit 120. The control unit 11 then executes a process of generating a draft of the personnel system of the workplace described above by inputting input data such as the specifications of the workplace described above into a fourth machine learning model through the personnel system draft providing unit 120 (personnel system draft generating step). The control unit 11 shifts the process to step S24.

[0113] In the personnel system draft generation step, the personnel system draft providing unit 120 generates a draft of a personnel system including, for example, a grade system, an evaluation sheet, and a draft of a wage table. This allows the personnel system draft providing unit 120 to generate a draft of a personnel system that integrates a grade system, an evaluation sheet used for evaluation for each grade, and a wage table corresponding to the grade, etc.

[0114] If the fourth machine learning model includes a language model, the personnel system draft providing unit 120 may generate the above-mentioned personnel system draft by inputting a prompt including workplace specifications and instructions for generating a personnel system draft into the language model.

[0115] [Step S24: Provide personnel system] The control unit 11 executes a process of providing the personnel system draft generated in the personnel system draft creation step by the personnel system draft providing unit 120 (personnel system draft providing step). The control unit 11 moves the process to step S25. The personnel system draft providing unit 120 provides the personnel system draft to the terminal T, for example.

[0116] [User-initiated modifications and machine learning in personnel systems] In order to allow the user to manually correct any deficiencies in the automatic generation, it is preferable that the series of processes for generating and providing a draft personnel system includes a procedure for obtaining, after providing the draft personnel system generated by the fourth machine learning model, a personnel system that has been modified by the user as necessary from terminal T, similar to the series of processes for obtaining an actual goal based on the provided interim goal.

[0117] At this time, it is preferable that the series of processes further includes a procedure of performing machine learning of a fourth machine learning model using learning data including workplace specifications as explanatory variables and including the personnel system as a target variable acquired from terminal T. This enables the fourth machine learning model to generate a more appropriate draft personnel system.

[0118] [About salary management] The support process preferably includes a procedure (salary increase assessment step) for automatically assessing the periodic salary increase of the subject based on the personnel system related to the generated draft and the subject's performance. The procedure includes, for example, a procedure for automatically assessing the periodic salary increase of the subject by processing based on the correspondence between performance and periodic salary increase included in the personnel system and the subject's performance.

[0119] In order to realize an objective evaluation of a wide variety of performances, the processing is preferably a processing using a machine learning model. In order to realize an appropriate evaluation, the machine learning model is preferably pre-trained using training data including performances and correspondences as explanatory variables and the assessed regular salary increase as a response variable.

[0120] In addition, the support process preferably includes a step (bonus assessment step) of automatically assessing the bonus of the target person based on the personnel system related to the generated draft and the performance of the target person. The step includes, for example, a step of automatically assessing the bonus of the target person by processing based on the correspondence between performance and bonus included in the personnel system and the performance of the target person.

[0121] In order to realize an objective evaluation for a wide variety of results, the processing is preferably a processing using a machine learning model. In order to realize an appropriate evaluation, the machine learning model is preferably pre-trained using training data including results and corresponding relationships as explanatory variables and including the assessed bonus as a response variable.

[0122] In order to realize cooperation with software for managing salaries, it is preferable that the support process includes a procedure for outputting the above-mentioned assessment results, etc. in a form usable by the software for managing salaries.

[0123] The support process preferably includes a series of processes for generating and providing support information for supporting an application for a subsidy to be received by the workplace based on the specifications of the workplace, etc. Steps S25 to S29 are an example of the process.

[0124] [Step S25: Determine whether to support the grant application] The control unit 11, in cooperation with the storage unit 13 and the communication unit 14, executes a process of determining whether to support the application for a subsidy (support information generation and determination step). If it is determined that support is to be provided, the control unit 11 moves the process to step S26. If it is not determined that support is to be provided, the control unit 11 returns the process to step S1 and repeats the processes from step S1 to step S29.

[0125] In the support information generation determination step, the control unit 11 determines that it will support the grant application when a command is issued from terminal T instructing it to provide support information for the grant application, exemplified by a command related to an AI grant application, for example.

[0126] [Step S26: Obtain workplace specifications] The control unit 11 executes the workplace specification acquisition unit 119 in cooperation with the storage unit 13 and the communication unit 14. Then, the control unit 11 executes a process to acquire the workplace specifications described above by the workplace specification acquisition unit 119 (second workplace specification acquisition step). The control unit 11 moves the process to step S27. The second workplace specification acquisition step may be similar to the first workplace specification acquisition step.

[0127] When the fifth machine learning model is configured to generate support information including information indicating a subsidy appropriate for a workplace having the above-mentioned specifications, the above-mentioned series of processes preferably includes a series of steps for determining whether there is a subsidy appropriate for the workplace having the above-mentioned specifications, and generating and providing support information if there is an appropriate subsidy. Steps S27 to S29 are an example of such steps. Thereby, the support device 1 can determine a subsidy appropriate for the workplace and generate support information that supports an application for such a subsidy.

[0128] [Step S27: Determine whether appropriate subsidies are available] The control unit 11 executes the subsidy support information providing unit 121 in cooperation with the storage unit 13 and the communication unit 14. Then, the control unit 11 inputs the above-mentioned specifications into the fifth machine learning model by the subsidy support information providing unit 121, generates information indicating an appropriate subsidy for the workplace related to the specifications to receive, and executes a process of determining whether or not there is an appropriate subsidy based on the information (subsidy presence / absence determination step). If it is determined that there is, the control unit 11 moves the process to step S28. If it is not determined that there is, the control unit 11 returns the process to step S1 and repeats the processes from step S1 to step S29.

[0129] [Step S28: Generate support information] The control unit 11 executes a process of generating support information for supporting the application for a subsidy to be received by the workplace by inputting the input data such as the above-mentioned workplace specifications into the fifth machine learning model through the subsidy support information providing unit 121 (support information generation step). The control unit 11 shifts the process to step S29.

[0130] When information indicating an appropriate subsidy is generated in the subsidy availability determination step, the subsidy support information providing unit 121 preferably generates support information for supporting the application for the appropriate subsidy by inputting input data further including the information into the fifth machine learning model. This allows the support device 1 to generate support information for supporting the application for the subsidy that is determined to be appropriate for the workplace.

[0131] [Step S29: Provide support information] The control unit 11 executes a process of providing the support information generated in the support information generation step by the subsidy support information providing unit 121 (subsidy support information providing step). The control unit 11 returns the process to step S1, and repeats the processes from step S1 to step S29. The subsidy support information providing unit 121 provides support information to a terminal T, for example.

[0132] [User-generated modifications and machine learning in grant-related support information] In order to allow the user to manually correct any deficiencies in the automatic generation, it is preferable that the series of processes for generating and providing support information includes a procedure for obtaining support information corrected by the user, as necessary, from terminal T after providing the support information generated by the fifth machine learning model, similar to the series of processes for obtaining an actual goal based on the provided tentative goal.

[0133] In this case, it is preferable that the series of processes further includes a procedure of performing machine learning of the fifth machine learning model using learning data including the specifications of the workplace as explanatory variables and the support information acquired from the terminal T as a target variable. This enables the fifth machine learning model to generate even more appropriate support information.

[0134] [Interview Management] In order to support the recording of interviews with subordinates and their utilization, the support process preferably includes a procedure for recording interviews between a superior and a subordinate and making them available for viewing (interview management step). The procedure preferably includes a procedure for recording voice or video calls related to the interviews. In order to alleviate the subordinates' anxieties regarding the interviews, the procedure preferably includes a procedure for sharing notes written by the superior about the interviews with the subordinates.

[0135] [Effects of Support Processing] By executing the above-mentioned support process, the support device 1 of the present embodiment generates a tentative goal related to personnel evaluation by a first machine learning model in which machine learning related to the real goal is performed (steps S1 to S3). Since the tentative goal is generated by a machine learning model, it can be said to be an objective goal.

[0136] However, due to circumstances such as insufficient pre-learning of the machine learning model, there is a concern that the provisional target generated in this manner is not an appropriate target that fully reflects the needs of the organization or the like regarding personnel evaluation. Meanwhile, in the above-mentioned support process, the provisional target is provided to the superior, and the actual target revised by the superior as necessary is obtained (steps S4 to S7). Furthermore, in the above-mentioned support process, machine learning is performed on the first machine learning model using learning data including the actual target, so that a more appropriate provisional target is generated (step S8).

[0137] In addition, in the above-mentioned support process, a provisional evaluation for personnel evaluation is generated by a second machine learning model in which machine learning related to the actual evaluation, which will be described later, is performed. Since the provisional evaluation is generated by a machine learning model, it can be said to be an objective evaluation (steps S9 to S11).

[0138] However, due to circumstances such as insufficient pre-learning of the machine learning model, there is a concern that the provisional evaluation generated in this manner is not an appropriate evaluation. Therefore, in the above-mentioned support process, the provisional evaluation is provided to the superior, and a final evaluation revised by the superior as necessary is obtained (steps S12 to S15). Furthermore, in the above-mentioned support process, machine learning is performed on the second machine learning model using learning data including the final evaluation, so that a more appropriate provisional evaluation is generated (step S16).

[0139] In this way, the support device 1 that executes the above-mentioned support process utilizes machine learning models not only to evaluate performance, but also to generate the performance targets themselves that serve as indicators of the evaluation, and further, by feeding back the targets and evaluations revised by the supervisor as necessary to each machine learning model, it is possible to support objective and fair personnel evaluations that do not require comparison with other members.

[0140] The above-mentioned support process may take the form of generating a human resource development curriculum based on the skill map of the subject (steps S17 to S20). In this form, the support device 1 further includes a skill map acquisition unit 117 that acquires a skill map related to the subject, and a curriculum provision unit 118 that provides the human resource development curriculum of the subject, generated by a process of inputting the skill map into a third machine learning model, and the third machine learning model includes the skill map as an explanatory variable, and is pre-learned using learning data that includes the human resource development curriculum for the human resource related to the skill map as a target variable. As a result, the support device 1 of this embodiment in this form can provide a human resource development curriculum linked to personnel evaluation.

[0141] In addition, the above-mentioned support process may take a form in which a draft personnel system is generated based on the specifications of the workplace (steps S21 to S24). In this form, the support device 1 further includes a workplace specification acquisition unit 119 that acquires the specifications of the workplace related to personnel evaluation, and a personnel system draft provision unit 120 that provides a draft of the personnel system of the workplace generated by a process of inputting the specifications into a fourth machine learning model, and the fourth machine learning model is pre-trained using learning data that includes the specifications of the workplace as explanatory variables and the personnel system related to the workplace as a target variable. As a result, the support device 1 of this embodiment in this form can support the construction of a personnel system linked to personnel evaluation.

[0142] Furthermore, the above-mentioned support process may take a form in which a grant application is supported based on the specifications of the workplace (steps S25 to S29). In this form, the support device 1 further includes a workplace specification acquisition unit 119 that acquires the specifications of the workplace related to the personnel evaluation, and a grant support information provision unit 121 that provides support information that supports the application for a grant received by the workplace, generated by a process of inputting the workplace specifications into a fifth machine learning model, and the fifth machine learning model is pre-trained using learning data that includes the specifications of the workplace as explanatory variables and information that supports the application for a grant received by the workplace as a target variable. As a result, the support device 1 of this embodiment in this form can support the work of the workplace where the personnel evaluation is performed.

[0143] Therefore, the support device 1 that executes the above-mentioned support process can support an objective and proper personnel evaluation that does not require comparison with other members.

[0144] <Example of use of support device 1> The following is an example of how the support device 1 of this embodiment is used.

[0145] [Registering workplace and individual information] The superior and the subject person, etc., register the workplace information and subject information related to the personnel evaluation in the support device 1 via a terminal T, etc. The support device 1 stores the registered workplace information and subject information in the workplace information database 131, etc.

[0146] [AI goal setting directive] Fig. 10 is an example of a display on terminal T. In this example, the boss clicks the "AI goal setting" button displayed in the upper right corner of terminal T, and instructs the support device 1 to display a pop-up menu related to the provision of tentative goals, etc., related to the subordinate "Tanaka △△". The support device 1 displays a pop-up menu on terminal T with the heading "Implementing AI goal setting" that prompts the user to set parameters related to the provision of tentative goals, etc.

[0147] In this example, the supervisor checks the work goal in the goal section of the pop-up menu to instruct the system to provide a tentative goal related to the work. The supervisor also checks the ability goal in the goal section of the pop-up menu to instruct the system to provide a goal related to the abilities. In addition, the supervisor unchecks the behavior goal in the goal section of the pop-up menu to instruct the system not to provide a tentative goal related to the behavior goal.

[0148] Furthermore, the supervisor sets the number of goals for each category to "4" in the pop-up menu.Then, the supervisor specifies in the user interface element of "select reference information" in the pop-up menu that the supervisor will refer to the company-wide goals, department goals, grade, skill map, and previous evaluation sheet.

[0149] Then, the superior enters special notes in "Other special notes" as necessary, and clicks "Execute" at the bottom of the pop-up menu to issue an instruction to the support device 1 to set AI goals. In response to the instruction, the support device 1 generates a provisional goal and a human resource development curriculum by processing using the first machine learning model or the like. Then, the support device 1 provides the generated information to the superior by displaying it on the terminal T. In this example, as the generated provisional goal, a provisional goal "Promote digitalization of business operations and digitalize five or more business operations" corresponding to the theme "digitalization" which is the company-wide goal (the policy of the entire workplace) is displayed. In addition, in this example, corresponding provisional goals are displayed for each of the belonging goals (the policy of the belonging department in the workplace) "Troubleshooting," "Goal setting and quantification," and "Adjustment with related departments."

[0150] [Setting this goal] The supervisor sets a final goal for the subordinate "Tanaka △△" by referring to the provisional goal provided in the above procedure and making appropriate corrections. Because the provisional goal has been provided, the supervisor can set a final goal quickly and easily without having to consider the goal from scratch. The support device 1 acquires the set final goal and stores it in the workplace information database 131 or the like. The support device 1 also performs machine learning using the final goal.

[0151] [Revising the human resources development curriculum] The supervisor sets the human resource development curriculum for the subordinate "Tanaka △△" by referring to the human resource development curriculum provided in the above procedure and making appropriate modifications. Because the curriculum proposed by the support device 1 is provided, the supervisor can set the curriculum quickly and easily without having to consider the curriculum from scratch. The support device 1 acquires the set human resource development curriculum and stores it in the workplace information database 131 or the like. The support device 1 also performs machine learning using the human resource development curriculum.

[0152] [Command to generate provisional evaluation] After the work period related to the actual goal set by the above procedure ends, the supervisor instructs the support device 1 to provide a provisional evaluation based on the performance during that period and the actual goal. The support device 1 generates a provisional evaluation by processing using a second machine learning model that uses the performance and the actual goal as input, and provides the generated provisional evaluation to the supervisor by displaying it on the terminal T.

[0153] [Settings for this evaluation] The supervisor sets a final evaluation for the subordinate "Tanaka △△" by referring to the provisional evaluation provided in the above procedure and making appropriate corrections. Because the provisional evaluation has been provided, the supervisor can quickly and easily set a final evaluation without having to consider the evaluation from scratch. The support device 1 acquires the set final evaluation and stores it in the workplace information database 131 or the like. The support device 1 also performs machine learning using the final evaluation.

[0154] [Drafting the personnel system] The user provides specifications related to the workplace to the support device 1, and instructs the support device 1 to create a draft of the personnel system based on the specifications. The support device 1 generates a draft of the personnel system by inputting the specifications into a fourth machine learning model, and provides the generated draft of the personnel system to the user by displaying it on the terminal T. The user refers to the draft and proceeds with the review of the personnel system.

[0155] [Applying for Grants] The user provides specifications related to the workplace to the support device 1, and commands the support device 1 to provide support information for supporting an application for a grant based on the specifications. The support device 1 generates support information by inputting the specifications into a fifth machine learning model, and provides the generated support information to the user by displaying the support information on the terminal T. The user refers to the support information and proceeds with the application for the grant.

[0156] It should be noted that within the scope of the concept of the present invention, a person skilled in the art may come up with various modifications and alterations. It is understood that such modifications and alterations fall within the scope of the present invention. For example, even if a person skilled in the art appropriately adds, deletes, or modifies the design of the above-described embodiment, or adds, omits, or modifies the conditions of a process, these modifications and alterations are included in the scope of the present invention as long as they include the gist of the present invention. [Explanation of symbols]

[0157] S System 1 Support equipment 11 Control section 111 Information Acquisition Department 112 Provisional Target Providing Department 113 Book Objective Acquisition Department 114 Provisional Evaluation Department 115 This evaluation acquisition department 116 Machine Learning Department 117 Skill Map Acquisition Department 118 Curriculum Department 119 Workplace Specification Acquisition Department 120 Personnel system draft provision department 121 Grant Support Information Section 13 Storage section 131 Workplace Information Database 14 Communications Department N Network T-Terminal

Claims

1. An information acquisition unit that acquires workplace information and subject information related to a subject of personnel evaluation; A provisional goal providing unit that provides a provisional goal related to the personnel evaluation of the subject, which is generated by a process of inputting the workplace information and the subject information into a first machine learning model, to the subject's supervisor; a final goal acquisition unit that acquires a final goal related to the personnel evaluation provided by the superior; A provisional evaluation providing unit that provides a provisional evaluation related to the personnel evaluation of the subject, the provisional evaluation being generated by a process of inputting the achievements related to the real goal and the real goal into a second machine learning model, to the supervisor; a final evaluation acquisition unit that acquires a final evaluation related to the personnel evaluation provided by the superior; a machine learning unit that performs machine learning related to the first machine learning model and the second machine learning model; Equipped with The machine learning unit performs machine learning for the first machine learning model using learning data including the workplace information and the subject information as explanatory variables and including the final goal as a response variable, and performs machine learning for the second machine learning model using learning data including the achievement and the final goal as explanatory variables and including the final evaluation as a response variable. A support device for personnel evaluation.

2. A skill map acquisition unit that acquires a skill map related to the subject; A curriculum providing unit that provides a human resource development curriculum for the subject, the human resource development curriculum being generated by inputting the skill map into a third machine learning model; Further equipped with The third machine learning model includes a skill map as an explanatory variable, and pre-learning is performed using learning data including a human resource development curriculum for the human resource related to the skill map as a target variable. The support device according to claim 1 .

3. A workplace specification acquisition unit that acquires workplace specifications related to the personnel evaluation; A personnel system draft providing unit that provides a draft of a personnel system for the workplace, the draft being generated by a process of inputting the specifications into a fourth machine learning model; Further equipped with The fourth machine learning model is pre-trained using learning data including workplace specifications as explanatory variables and a personnel system related to the workplace as a target variable. The support device according to claim 1 .

4. Further, a subsidy support information providing unit that provides support information for supporting an application for a subsidy to be received by the workplace, the support information being generated by the process of inputting the workplace specifications into a fifth machine learning model, The fifth machine learning model is pre-trained using learning data including workplace specifications as explanatory variables and information supporting the application of subsidies received by the workplace as a target variable. The support device according to claim 3.

Images