Human resource management systems, human resource management methods and programs

Abstract

This invention provides a human resource management system, human resource management method, and program that facilitate the management of output information generated by machine learning models. [Solution] In the generation step (S12-S13), the control unit generates first output information from one or more source information using a trained model. The trained model is a model that has been trained to take input information, which includes at least a portion of the source information, as input and output first output information, which includes at least a portion of the source information. In the determination step (S14), the control unit determines the attributes of the generated first output information based on the attributes of one or more source information.

Description

Technical Field

[0001] The present disclosure relates to a human resource management system, a human resource management method, and a program.

Background Art

[0002] In recent years, technologies for generating new information by utilizing machine learning models such as generative AI (Artificial Intelligence) have attracted attention. For example, in Patent Document 1, a text creation support system is disclosed that causes artificial intelligence to create the approach text from a source text including profile information related to either an organization or an individual.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, while the spread of generative AI has made it easier to generate new information, it has become difficult to appropriately manage the generated new information. Particularly in a human resource management system that manages information related to human resources, since the information serving as materials often includes personal information and privacy information, careful handling is required for the output of the machine learning model. Therefore, it is required to facilitate the management of output information by the machine learning model.

[0005] An object of the present disclosure is to provide a human resource management system, a human resource management method, and a program capable of facilitating the management of output information by a machine learning model in view of the above-described problems.

Means for Solving the Problems

[0006] In one aspect of the present disclosure, the human resource management system comprises one or more processors capable of performing a generation step and a determination step. In the generation step, the one or more processors generate first output information from one or more source information using a trained model. The trained model takes input information, which includes at least a portion of the source information, as input and outputs first output information, which includes at least a portion of the source information. In the determination step, the one or more processors determine the attributes of the generated first output information based on the attributes of the one or more source information.

[0007] A human resource management method according to one aspect of this disclosure is implemented by one or more processors. The human resource management method comprises a generation step and a determination step. The generation step is a step of generating first output information from one or more source information using a trained model. The trained model takes input information including at least a portion of the source information as input and outputs first output information including at least a portion of the source information. The determination step is a step of determining the attributes of the generated first output information based on the attributes of the one or more source information.

[0008] A program according to one aspect of this disclosure operates a computer comprising one or more processors and memory. The program causes the one or more processors to perform a generation step and a determination step. In the generation step, the one or more processors generate first output information from one or more source information using a trained model. The trained model takes input information including at least a portion of the source information as input and outputs first output information including at least a portion of the source information. In the determination step, the one or more processors determine the attributes of the generated first output information based on the attributes of the one or more source information. [Effects of the Invention]

[0009] This disclosure provides a human resource management system, a human resource management method, and a program that facilitate the management of output information generated by machine learning models. [Brief explanation of the drawing]

[0010] [Figure 1] This is a block diagram showing the overall configuration of the human resource management system according to Embodiment 1. [Figure 2] This is a block diagram showing the hardware configuration of a registered user terminal according to Embodiment 1. [Figure 3] This is a block diagram showing the hardware configuration of the personnel management device according to Embodiment 1. [Figure 4] This is a block diagram showing the functional configuration of the personnel management device according to Embodiment 1. [Figure 5] This is a flowchart showing the human resource management method according to Embodiment 1. [Figure 6] This figure shows an example of the data structure of a material attribute table. [Figure 7] This figure shows an example of the data structure of the material output table. [Figure 8] This figure shows an example of the data structure of an output attribute table. [Figure 9] This is a block diagram showing the overall configuration of the human resource management system according to Embodiment 2. [Figure 10] This is a block diagram showing the functional configuration of the personnel management device according to Embodiment 2. [Figure 11] This is a flowchart showing the flow of the attribute determination method according to Embodiment 2. [Figure 12] This is a diagram showing an example of the screen. [Figure 13] This is a diagram showing an example of the screen. [Figure 14] This is a diagram showing an example of the screen. [Figure 15] This is a flowchart showing the flow of the search processing method according to Embodiment 2. [Figure 16] This is a diagram showing an example of the screen. [Figure 17] This is a diagram showing an example of the screen. [Figure 18] This is a diagram showing an example of the screen. [Figure 19]It is a diagram showing an example of a screen.

Mode for Carrying Out the Invention

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

[0012] <Embodiment 1> First, Embodiment 1 of the present disclosure will be described. 1. Hardware Configuration In this section, the hardware configuration of the human resource management system 1 according to this embodiment will be described. FIG. 1 is a block diagram showing the overall configuration of the human resource management system 1 according to Embodiment 1.

[0013] 1.1 Human Resource Management System 1 The human resource management system 1 is a computer system that manages information related to human resources. In particular, the human resource management system 1 manages information related to the members of an organization. The organization is a company, a government agency, an arbitrary group, or other organization. Also, the members are employees, officers, or other members of the organization. The human resource management system 1 includes a human resource management device 2 and a registrant terminal 3. The human resource management device 2 and the registrant terminal 3 are communicably connected via a network NW such as the Internet.

[0014] 1.2 Registrant Terminal 3 The registrant terminal 3 is a computer terminal operated by a registrant who registers material information related to a member. For example, the registrant is the member himself / herself, a personnel or general affairs person in the organization, or a person in a position to manage the members. For example, the registrant terminal 3 is a smartphone, a tablet terminal, a personal computer, or other communication terminal capable of input and output. The registrant terminal 3 transmits the material information related to the member received by the operation of the registrant to the human resource management device 2 via the network NW. The material information related to the member is the personnel information of the member. The material information will be described in detail later.

[0015] Figure 2 is a block diagram showing the hardware configuration of the registrant terminal 3 according to Embodiment 1. The registrant terminal 3 comprises a control unit 31, a communication unit 35, a storage unit 36, an input unit 37, and a display unit 38, and these components are electrically connected within the registrant terminal 3 via a communication bus. The control unit 31 comprises a processor 32, a ROM 33, and a RAM 34. The hardware configuration of the control unit 31, the communication unit 35, and the storage unit 36 ​​is substantially the same as that of the control unit 21, the communication unit 25, and the storage unit 26 in the personnel management device 2 described later, so a detailed explanation is omitted.

[0016] The input unit 37 may be included in the casing of the registered user terminal 3, or it may be an external component. For example, the input unit 37 may be integrated with the display unit 38 to function as a touch panel. Of course, a switch button, mouse, QWERTY keyboard, etc., may be used instead of a touch panel. In other words, the input unit 37 receives operation inputs made by the registered user. These inputs are transmitted as command signals to the control unit 31 via the communication bus, and the control unit 31 can perform predetermined controls and calculations as needed.

[0017] The display unit 38 may be included in the casing of the registrant terminal 3, for example, or it may be an external component. The display unit 38 displays a graphical user interface (GUI) screen that can be operated by the registrant. It is preferable to use a display device such as a CRT display, liquid crystal display, organic EL display, and plasma display, depending on the type of registrant terminal 3.

[0018] 1.3 Human Resources Management System 2 The personnel management device 2 is a computer such as a server. For example, the personnel management device 2 is managed by an administrator who is in a position to manage the members of an organization. The personnel management device 2 stores the raw information acquired from the registered user terminal 3 in the member database (not shown) of the storage unit 26 (described later) or in an external storage area accessible to the personnel management device 2. Then, the personnel management device 2 uses a trained model to acquire first output information about the members of the organization from the raw information and manages this first output information. The trained model will be described in detail later.

[0019] Figure 3 is a block diagram showing the hardware configuration of the personnel management device 2 according to Embodiment 1. The personnel management device 2 comprises a control unit 21, a communication unit 25, a storage unit 26, and an input unit 27, and these components are electrically connected within the personnel management device 2 via a communication bus.

[0020] The control unit 21 comprises a processor 22, a ROM 23, and a RAM 24. The processor 22 implements each function by executing programs stored in the ROM 23 or the storage unit 26. Each function will be described in detail in the next section. The ROM 23 is a non-temporary storage medium such as ROM (Read-only memory), and various programs or data for the processor 22 to perform various controls or calculations are stored in it in advance. The RAM 24 is a volatile storage medium such as RAM (Random Access Memory), and is a storage area for temporarily holding information when the processor 22 is operating. An area for performing the various processing according to this embodiment can be secured in this RAM 24.

[0021] The communication unit 25 is a communication interface for connecting to the network NW. The storage unit 26 is a storage device that includes a non-temporary computer-readable medium or a physical storage medium. The hardware configuration of the input unit 27 is substantially the same as that of the input unit 37 described above. Note that the input unit 27 is not essential in the personnel management device 2.

[0022] 2. Functional Configuration This section describes the functional configuration of Embodiment 1, particularly the functional configuration of the personnel management device 2. The personnel management method described later is performed by the personnel management device 2.

[0023] Figure 4 is a block diagram showing the functional configuration of the personnel management device 2 according to Embodiment 1. The control unit 21 realizes the functions of the acquisition unit 211, the generation unit 212, and the determination unit 213 by executing a program.

[0024] The acquisition unit 211 acquires one or more material information items relating to the target member (hereinafter referred to as the target member) as an acquisition step. For example, the acquisition unit 211 reads one or more material information items relating to the target member from the member database of the storage unit 26 or from an external storage area.

[0025] The generation unit 212 generates first output information from one or more source information using a trained model as a generation step. The trained model is a model that takes input information, which includes at least a portion of the source information, as input and outputs first output information. The first output information is different from the input information but is configured to include at least a portion of the source information. In other words, the first output information is newly constructed information that includes at least information about the target members. The input information and first output information will be described in detail later.

[0026] The determination unit 213, as a determination step, determines the attributes of the generated first output information based on the attributes of one or more source information. Attributes are categories that classify the range of users who can use the information, the time the information was created, the expiration date of the information, or the characteristics of the information from a predetermined perspective. Here, "use of information" refers to at least one of the following: viewing, editing, publishing, sharing, or processing the information.

[0027] 3. Operation of the personnel management device 2 Section 3 will explain the flow of the personnel management method performed by the personnel management device 2, with reference to the diagram.

[0028] 3.1 Overview of Human Resource Management Methods Figure 5 is a flowchart showing the flow of the personnel management method according to Embodiment 1. The order of processes can be rearranged as appropriate, and multiple processes may be executed simultaneously. Some processes may also be omitted. The same applies to subsequent flowcharts.

[0029] First, the acquisition unit 211 acquires one or more source information items related to the target member (S11: acquisition step). For example, the acquisition unit 211 reads one or more source information items from the member database in the storage unit 26 or from an external storage area. Next, the generation unit 212 inputs the input information, including the acquired one or more source information items, into the trained model (S12). Next, the generation unit 212 acquires first output information from the trained model (S13). Next, the determination unit 213 determines the attributes of the first output information based on the attributes of the one or more source information items (S14). Next, the determination unit 213 stores information in the storage unit 26 that associates the first output information acquired in S13 with the attributes determined in S14 (S15).

[0030] [effect] Until now, it has been necessary to properly manage the output information generated from trained models, especially generative AI, by appropriately setting the range of users who can use it and the expiration date, or by appropriately assigning categories that represent the characteristics of the information. However, manually performing these actions each time a trained model is generated has been time-consuming. However, according to Embodiment 1, the personnel management device 2 automatically assigns attributes to the first output information output from the trained model based on the attributes of the source information. Therefore, the management of the output information generated from trained models, especially generative AI, becomes easier.

[0031] 3.2 Details of Human Resource Management Methods Next, I will explain the details of the human resource management methods mentioned above.

[0032] [Material Information] The raw information concerning members is their personnel information. The raw information may include at least one of the following: career information showing the member's history, skills information showing the member's skills, and goal information showing the member's goals. For example, raw information may include the member's basic personal information, work history, transfer history, skills, goals set by the member within the organization, information about the member before joining the organization (such as the results of pre-employment tests and other recruitment information), evaluations of the member by superiors, engagement, aptitude test results, information on inner characteristics, attendance information, or interview history. Basic personal information may include the member's name, gender, age, employee code, contact information, department, employment type, work location, or current job.

[0033] [Pre-trained model] A trained model is a model that takes input information as input and outputs first output information. For example, a trained model is a Large Language Model (LLM), which is an example of generative AI (Artificial Intelligence). Note that the trained model is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> The model may be a general-purpose model such as those disclosed in [publication name], or a dedicated model tuned for the personnel management system 1. In the latter case, the trained model may be trained to take input information as input and output first output information using a training dataset that includes training prompts containing training material information and first output information which is the correct answer. Training may be performed in the control unit 21 of the personnel management device 2, or by an external device (not shown).

[0034] [Input Information] The input information provided to the trained model is configured to include at least a portion of the source information. For example, the input information is a prompt that includes at least a portion of the source information. The prompt may include other information in addition to the source information. Other information may include conditions for the data size of the first output information (e.g., number of characters), conditions for the absolute or relative importance of each type of source information (e.g., prioritizing work experience over skills), conditions for the characteristics desired in the first output information (e.g., conciseness or clarity), or a combination thereof. In particular, by specifying a small number of characters or conciseness, in S13 the generation unit 212 can generate as the first output information a summary text obtained by combining one source information or multiple source information, or a text newly constructed from these. When the amount of data in the source information is large, or when the source information used as input information is distributed across multiple tables, integrating the source information into a single concise piece of information makes it easier to grasp the characteristics of the members. It also makes it easier to manage. Alternatively, instead of including the other information in the prompt, the parameters of the trained model may be adjusted through training to satisfy the above conditions.

[0035] [First Output Information] The first output information of a trained model is information about the characteristics of its members. In particular, the first output information may be information about the members' careers, skills, or internal characteristics. The first output information is structured to include at least a portion of the source information, but it is different from the input information. For example, the first output information may be a summary text of the source information, or a newly constructed text combining information (keywords or phrases, etc.) contained in the source information. The first output information may be a summary text of one source information, or a newly constructed text combining information contained in one source information. However, the first output information may instead be a text that summarizes multiple source information by concatenating them, or a newly constructed text combining information contained in each of multiple source information. Furthermore, the first output information is not limited to text, but may also be in other data formats such as numbers, vectors, or matrices.

[0036] [Attribute determination process: S14] In S14, the determination unit 213 determines the attributes of the first output information based on the attributes of one or more material information. At this time, the determination unit 213 may generate an output attribute table T3 using the material attribute table T1 and material output table T2 stored in the storage unit 26.

[0037] (Material Attribute Table T1) Figure 6 shows an example of the data structure of the material attribute table T1. The material attribute table T1 is a table that shows the correspondence between material information and attributes. For example, the material attribute table T1 associates material information T11 with attributes T12. More specifically, as shown in Figure 6, the material attribute table T1 shows which of the multiple types of attributes T12 (group a to group c) each of the multiple types of material information T11 (material A to material F) possesses. Note that one type of material information T11 may have only one type of attribute T12, or it may have multiple types of attributes T12.

[0038] In the example in Figure 6, materials A to C have the attribute of group a, material D has the attributes of group a and b, material E has the attributes of group a, b and c, and material F has the attribute of group c.

[0039] (Material output table T2) Figure 7 shows an example of the data structure of the material output table T2. The material output table T2 is a table that shows the correspondence between material information and first output information. For example, the material output table T2 associates material information T21 with first output information T22. More specifically, as shown in Figure 7, the material output table T2 shows the combination of material information T11 used as input information when each first output information T22 (output A, B, or C) is generated.

[0040] In the example in Figure 7, output A is generated from materials A to E, output B from materials D and E, output C from materials E and F, and output D from materials A and F. Although Figure 7 shows an example where the first output information T22 is generated from input information using multiple types of material information T21, it may also be generated from input information using only one type of material information T21.

[0041] (Output attribute table T3) Figure 8 shows an example of the data structure of the output attribute table T3. The output attribute table T3 is a table that shows the correspondence between the first output information and its attributes. For example, the output attribute table T3 associates the first output information T31 with attribute T32. More specifically, as shown in Figure 8, the output attribute table T3 shows which of the multiple types of attribute T32 (group a to group d) each of the multiple types of first output information T31 (output A to output D) has. Note that one type of first output information T31 may have only one type of attribute T32, or it may have multiple types of attribute T32.

[0042] Here, the generation unit 212 identifies the underlying material information for each first output information from the material output table T2, and identifies the attributes of the identified material information from the material attribute table T1. Then, the generation unit 212 determines the attributes of the first output information based on the attributes of the underlying material information.

[0043] For example, if the first output information is based on a single material information or on multiple material information with the same attributes, the generation unit 212 may determine the same attributes as those of the material information as the attributes of the first output information. As an example, since output A is generated based on materials A to E, the attributes of output A may be group a, which consists of the attributes of materials A to E.

[0044] Furthermore, for example, if the generation unit 212 is based on multiple material information with different attributes, it may determine the range (AND) where the attributes of the multiple material information overlap as the attributes of the first output information. For example, output C is generated based on materials E and F, where material E has attributes of groups a to c, and material F has attributes of group c. In this case, the attributes of output C may be group c, which is the overlapping attribute.

[0045] Furthermore, for example, if the first output information is based on multiple material information with different attributes, the generation unit 212 may determine the attributes of the first output information as a range (OR) that encompasses some or all of the attributes of the multiple material information. As an example, output D is generated based on materials A and F, and material A has the attribute of group a, and material F has the attribute of group c. In this case, the attributes of output D may be group d, which encompasses group a and group c.

[0046] The rules for determining the attributes of the first output information can be set flexibly, not limited to the method described above, as long as they are based on the attributes of the underlying material information.

[0047] Furthermore, determining the attributes may mean determining them regardless of the registrant's actions, or it may mean proposing the attributes to the registrant and determining them after obtaining their consent. Also, the determined attributes may be made unmodifiable, or they may be modifiable by the registrant.

[0048] <Embodiment 2> Next, Embodiment 2 of this disclosure will be described. Embodiment 2 is a specific example of Embodiment 1. In Embodiment 2, the attribute of the material information is the range of users who can use the material information (hereinafter referred to as the usable range), and in particular the range of users who can view it (hereinafter referred to as the viewable range). The attribute of the first output information is the range of use of the first output information, and in particular the viewable range. In other words, the personnel management device 2 automatically determines the usable range of the material information based on the usable range of the first output information. This prevents users who are not supposed to be able to use the material information from being able to use the output of the trained model. It also eliminates the need to manually set the usable range of the output of the trained model.

[0049] Furthermore, the human resource management system according to Embodiment 2 is used to manage information about company employees, which are an example of members of an organization, and the first output information is employee characteristic text, which is text that represents the characteristics of the employee.

[0050] 4. Overall structure 4.1 Human Resources Management System 1a Figure 9 is a block diagram showing the overall configuration of the personnel management system 1a according to Embodiment 2. The personnel management system 1a is basically the same as the personnel management system 1 in terms of configuration and function, but differs from the personnel management system 1 in that it includes a personnel management device 2a instead of the personnel management device 2, and a viewer terminal 4.

[0051] 4.2 Human resources management device 2a The personnel management device 2a is basically the same as the personnel management device 2 in terms of configuration and function, but differs from the personnel management device 2 in that it presents first output information, which is information about personnel, to the viewer terminal 4. Specifically, the personnel management device 2a presents employee characteristic text to the viewer terminal 4 according to the viewer's viewing permission. For example, when the personnel management device 2a receives a search request regarding an employee from the viewer terminal 4, it presents employee characteristic text that matches the search criteria and is according to the viewer's viewing permission as search results to the viewer terminal 4. Note that for a viewer to have viewing permission for the first output information means that the viewer is within the scope of being able to view the employee characteristic text.

[0052] 4.3 Viewer terminal 4 Viewer terminal 4 is a computer terminal operated by the viewer. For example, the viewer may be an employee, human resources or general affairs staff member belonging to a company, or a person in a position to manage employees. For example, viewer terminal 4 may be a smartphone, tablet, personal computer, or other communication terminal capable of input / output. The hardware configuration of viewer terminal 4 is substantially the same as that of registrant terminal 3, so the explanation is omitted. Viewer terminal 4 receives employee characteristic text according to the viewer's viewing authority from the personnel management device 2a and displays it on the display unit (not shown).

[0053] 5. Functional Configuration Figure 10 is a block diagram showing the functional configuration of the personnel management device 2a according to Embodiment 2. The control unit 21a executes a program to realize the functions of the acquisition unit 211a, the generation unit 212a, the determination unit 213a, the search processing unit 214a, and the display control unit 215a.

[0054] The acquisition unit 211a, the generation unit 212a, and the determination unit 213a have basically the same functions as the acquisition unit 211, the generation unit 212, and the determination unit 213 of Embodiment 1. However, the material information is information about employees, and the first output information is employee feature text.

[0055] The search processing unit 214a performs the following as a search processing step. First, upon receiving a search request from the viewer terminal 4, the search processing unit 214a obtains employee characteristic text corresponding to the employee and which the viewer has permission to view. For example, the search processing unit 214a obtains employee characteristic text for each employee that corresponds to that employee and which the viewer has permission to view. Then, based on the obtained employee characteristic text and the search conditions included in the search request, the search processing unit 214a generates search results to present to the viewer. In this embodiment 2, the search conditions are, but are not limited to, search conditions related to the desired personnel or job type.

[0056] The display control unit 215a controls the system so that the results of various processing performed by the control unit 21 can be displayed on the display unit of the operator's terminal, such as the registrant terminal 3 or the viewer terminal 4. This control may involve the display control unit 214 sending images showing the various processing results to the operator's terminal, or the operator's terminal sending information necessary to generate images showing the various processing results to the operator's terminal. The operator's terminal, upon receiving the necessary information, displays the images on its display unit. For example, the display control unit 215a controls the system so that the search results generated by the search processing unit 214a can be displayed on the display unit of the viewer terminal 4. In other words, the display control unit 215a causes the viewer terminal 4 to display information generated based on the search conditions and employee characteristic text included in the search request.

[0057] 6. Operation of the personnel management device 2a This section describes the flow of the personnel management method performed by the personnel management device 2a with reference to the figures. In Embodiment 2, the personnel management method includes an attribute determination method and a search processing method.

[0058] 6.1 Overview of Attribute Determination Method Figure 11 is a flowchart showing the flow of the attribute determination method according to Embodiment 2. First, the acquisition unit 211a receives and sets a group indicating the viewable range (viewable group) for each piece of material information from the registrant terminal 3 (S21). The viewable group is an example of the attributes in Embodiment 1. The viewable group is determined in correspondence with the user attribute. Next, the acquisition unit 211a receives the user attribute of the viewer from the registrant terminal 3 (S22).

[0059] Next, the acquisition unit 211a identifies and acquires one or more pieces of material information corresponding to a specified user attribute, which are the material information of the target employee that will be used to generate employee feature text (S23). Next, the generation unit 212a inputs a prompt containing one or more pieces of material information to the first trained model (S24). The first trained model is an example of the trained model of Embodiment 1. Next, the generation unit 212a acquires employee feature text representing the characteristics of the target employee from the first trained model (S25).

[0060] Next, the determination unit 213a determines the viewable group of employee feature text based on the viewable group of material information used in S24 (S26). Then, the determination unit 213a stores information relating the employee feature text to the viewable group determined in S26 in the storage unit 26 (S27). Note that each of S23 to S27 in Figure 11 corresponds to each of S11 to S15 in Figure 5.

[0061] Thus, the same effects as in Embodiment 1 can be obtained in Embodiment 2 as in Embodiment 1.

[0062] 6.2 Details of the attribute determination method Next, we will explain the details of the attribute determination method described above.

[0063] [Settings for groups that can view material information: S21] In S21, the acquisition unit 211a sets the viewable groups for material information. At this time, the display control unit 215a may display a screen 6 for setting the viewable groups for material information on the display unit of the registrant terminal 3.

[0064] Figure 12 shows an example of screen 6. Screen 6 includes a material attribute table 60 for setting viewable groups for each material information. The material attribute table 60 includes material information 61, a corresponding viewable group 62, and an input area 63 for entering the correspondence between them.

[0065] The material information 61 shown in Figure 12 indicates the identification information of the material information, specifically its name. In Figure 12, the material information includes "personal basic information," "transfer history," "career history," "career design sheet," "skills," "pre-employment test results," and "evaluation results." Each piece of material information may be stored in a different memory area (e.g., a table).

[0066] The "Viewable Group 62" indicates the identification information of the viewable group, specifically its name. Here, the viewable groups for the material information are determined in relation to the viewer's user attributes, particularly their job title. Figure 12 shows three types of viewable groups: "Supervisor," "General Employee," and "Self." "Supervisor" refers to the group of users who hold the position of supervisor of the target employee. "Self" refers to the user who is the target employee. "General Employee" refers to the group of users who are neither "Supervisor" nor "Self," such as colleagues. By simplifying the types of viewable scope in this way, the management of viewable scope can be made easier.

[0067] The input area 63 is an area for inputting information to associate each material information 61 with each viewable group 62. In the example shown in Figure 12, "Personal Basic Information" is viewable by users belonging to "Supervisor," "General Employee," and "Self." Also, "Evaluation Results" are viewable by users belonging to "Supervisor" and "Self," but not by users belonging to "General Employee."

[0068] Screen 6 may have an operation area 64 for registering the material attribute table 60 that reflects the input. When the user clicks the operation area 64, the acquisition unit 211a registers the material attribute table 60 as material attribute table T1. The display control unit 215a then transitions the display screen from screen 6 to screen 7.

[0069] Figure 13 shows an example of screen 7. Screen 7 is a screen for setting material information used as input information when employee characteristic text is generated. Screen 7 includes a material output table 70. The material output table 70 includes material information 61, employee characteristic text 72, and their corresponding relationships.

[0070] Employee characteristic text 72 indicates the identification information of the employee characteristic text, specifically its name. In Figure 13, the number of employee characteristic texts is the same as the number of viewable group types for the source information. For example, employee characteristic text 72 shows three types of employee characteristic text: "For Supervisors," "For General Employees," and "For the Employee Themselves." "For Supervisors" indicates employee characteristic text for users who hold the position of supervisor of the target employee. "For the Employee Themselves" indicates employee characteristic text for the target employee themselves. "For General Employees" indicates employee characteristic text for users who are neither supervisors nor the employee themselves, such as colleagues.

[0071] The display control unit 215a may display the material information associated with the employee characteristic text for "Supervisor" registered on screen 6 as corresponding material information. Screen 7 may include an operation area 74 for modifying the correspondence. If the registrant clicks the operation area 74, the display control unit 215a may display a screen on the registrant terminal 3 that accepts modifications to the correspondence between the material information and the viewable group or between the material information and the employee attribute text.

[0072] Screen 7 may have an operation area 75 for registering the material output table 70. When the user clicks the operation area 75, the acquisition unit 211a registers the material output table 70 as material output table T2.

[0073] [Determination of the group that can view employee characteristics text: S26] In S26, the determination unit 213a may determine the same range as the viewable group for material information as the viewable group for employee characteristic text. If the display control unit 215a has determined the viewable group for employee characteristic text, it may display a screen 8 showing the viewable group on the display unit of the registrant terminal 3.

[0074] Figure 14 shows an example of screen 8. Screen 8 includes an output attribute table 80. The output attribute table 80 includes employee characteristic text 72, viewable groups 82, and their corresponding relationships. In the example shown in Figure 14, the viewable groups for employee characteristic text are determined in association with the viewer's user attributes, particularly the viewer's job title, similar to the viewable groups for source information. Figure 14 shows three types of viewable groups: "Supervisor," "General Employee," and "Self." Employee characteristic text for "Supervisors" can be viewed by users belonging to the "Supervisor" category. Similarly, employee characteristic text for "Self" can be viewed by users belonging to the "Self" category. Employee characteristic text for "General Employees" can be viewed by users who are neither "Supervisors" nor "Self," such as colleagues.

[0075] Screen 8 may include an operation area 84 for modifying the correspondence. If the registrant clicks the operation area 84, the display control unit 215a may display a screen on the registrant terminal 3 that accepts modifications to the correspondence between employee characteristic text and viewable groups. The control unit 215a can ensure flexibility in attribute determination by automatically determining the viewable groups for employee characteristic text while leaving room for later modification.

[0076] Screen 8 may have an operation area 85 for registering the output attribute table 80. When the user clicks the operation area 85, the determination unit 213a registers the output attribute table 80 as output attribute table T3.

[0077] In the attribute determination method of Embodiment 2, the display control of screens 7 to 8 may be omitted.

[0078] 6.3 Overview of Search Processing Methods Figure 15 is a flowchart showing the flow of the search processing method according to Embodiment 2. First, when the control unit 21a receives a search request regarding an employee from the viewer terminal 4 (S31), the search processing unit 214a generates search text from the search conditions included in the search request (S32). Next, the search processing unit 214a identifies the viewer's user attributes and identifies the viewable group based on the user attributes (S33). Next, the search processing unit 214a uses the output attribute table 80 to obtain, for each employee, the employee feature text included in the viewable group corresponding to the viewer's user attributes, i.e., the employee feature text that the viewer can view (S34). Next, the search processing unit 214a matches the employee feature text with the search text for each employee and calculates the degree of match (S35). Next, the search processing unit 214a identifies employee candidates to be presented to the viewer based on the degree of match (S36). Next, the search processing unit 214a generates information regarding employee candidates to be presented to the viewer (S37). The display control unit 215a then causes the generated information regarding employee candidates to be displayed on the display unit of the viewer terminal 4 (S38).

[0079] [effect] In this way, the control unit 21 uses the newly constructed employee feature text, which is created by integrating or summarizing the material information, for employee searches. This makes the search process easier even when the amount of material information is large or when the material information is distributed across multiple tables.

[0080] 6.4 Details of the search processing method Next, we will explain the details of the search processing method described above.

[0081] [Search request received: S31] In S31, the control unit 21a may display an input screen for searching on the display unit of the viewer terminal 4 and receive a search request including search conditions via the input screen. There may be two methods for the viewer to input search conditions. One is to input the search conditions in free text format, and the other is to input the search conditions in selection format.

[0082] Figure 16 shows an example of screen 9, which is one of the input screens for searching. Screen 9 includes an operation area 91 for free text input and an operation area 92 for selection input. In other words, the viewer can choose between free text input and selection input as their search method. When the viewer clicks on operation area 91 in Figure 16, the control unit 21a transitions the displayed screen from screen 9 to screen 10.

[0083] Figure 17 shows an example of screen 10. Screen 10 is a screen that includes an input area 101 for entering the characteristics of the employee to be searched for in free text format as search criteria. In the example shown in this figure, the text "Has leadership experience and is internationally minded" is entered in the input area 101. In response to this input, the control unit 21a receives a search request.

[0084] In Figure 16, when the viewer clicks on the operation area 92, the control unit 21a transitions the displayed screen from screen 9 to screen 11.

[0085] Figure 18 shows an example of screen 11. Screen 11 is a screen that includes an operation area 111 for inputting the characteristics of the employee to be searched for in a selection format as search criteria. In the example shown in this figure, the items "Leadership" and "Overseas experience" are selected in the operation area 111. Based on this selection, the control unit 21a receives a search request.

[0086] [Generating searchable text: S32] In S32, the search processing unit 214a generates search text based on the search conditions included in the search request. The method for generating the search text may be substantially the same as the method for generating the employee feature text. That is, the search processing unit 214a may generate the search text from the input search conditions using a second trained model. The second trained model is a model that has been trained to output search text, taking input information that includes at least a part of the search conditions as input. The second trained model is not limited to this, but may include an LLM. If the search conditions are input in free text format, the step of generating the search text may be omitted. That is, the search text may be the input text.

[0087] [Identifying viewer access groups and obtaining employee characteristic text: S33-S34] In S33, the search processing unit 214a identifies the user attributes of the viewer and identifies the viewable group based on the user attributes. At this time, the search processing unit 214a may identify the viewable group by identifying the relationship of job titles between each employee and the viewer. Then, in S34, the search processing unit 214a uses the output attribute table 80 to obtain the employee feature text that can be viewed by the viewable group to which the viewer belongs for each employee. At this time, if employee feature text for each group is prepared in advance, the search processing unit 214a may obtain the above employee feature text by selecting the employee feature text that corresponds to the relationship (i.e., group) from among the multiple employee feature texts corresponding to that employee. Note that the employee feature text may be generated in S34. That is, the attribute determination process shown in Figure 11 may be performed in S34.

[0088] [Matching process: S35~S36] In S35, the search processing unit 214a matches the employee characteristic text with the search text for each employee and calculates the degree of match. The degree of match corresponds to the degree of match between the employee and the search conditions corresponding to the search text. Here, "matching" indicates that there is a correlation between the two, and the degree of match indicates the degree of correlation. For example, "matching" includes not only the state in which the meaning of the entire text or the words or phrases contained therein is similar between the texts, but also the state in which the meanings are not similar between the texts but are recognized as being correlated based on past experience.

[0089] In calculating the match score, known methods for analyzing correlations can be used. For example, analytical methods include performing co-occurrence analysis using a corpus or dataset, extracting similar concepts through clustering, or performing regression analysis with a correlation matrix. The objects of analysis may be words, phrases, the entire text, or features extracted from these. The search processing unit 214a may then calculate the match score based on the above correlations. Alternatively, the search processing unit 214a may calculate the match score using a pre-trained model for calculating the match score. For example, the pre-trained model may be trained to output the match score using features extracted from the employee feature text and the search text for training as input.

[0090] Next, in S36, the search processing unit 214a identifies employees to be presented to the viewer as employee candidates based on the match score. For example, the search processing unit 214a may identify the top N employees (where N is a natural number) with the highest match scores as employee candidates. Alternatively, the search processing unit 214a may identify employees with a match score equal to or above a predetermined threshold as employee candidates.

[0091] [Generation and display control of information regarding candidate employees: S37~S38] In S37, the search processing unit 214a generates search results containing information about potential employee candidates to be presented to the viewer. Then, in S38, the display control unit 215a displays the generated information about potential employee candidates on the display unit of the viewer terminal 4.

[0092] Figure 19 shows an example of screen 12. Screen 12 includes candidate information 121 and 122 as search results. Each of the candidate information 121 and 122 is information about each employee candidate. Candidate information 121,122 includes personal basic information RG1,RG2 of the identified employee candidate, such as name, gender, age, affiliation, or current job. Candidate information 121,122 also includes information DC1 indicating the reason for the match. Information DC1 may include at least a portion of the employee feature text used in the matching process, or the material information that formed the basis for generating the employee feature text, or a combination thereof. Information DC1 may also be text newly generated from the employee feature text used in the matching process. For example, information DC1 may be text further summarized using a first trained model, etc., from the employee feature text used in the matching process, or it may be text newly generated based on the employee feature text used in the matching process and the search text. For example, the search processing unit 214a may identify a portion between the employee feature text and the search text that had a particularly high degree of match and generate information DC1 based on that portion. For example, the search processing unit 214a may identify combinations of words or phrases contained in the employee characteristic text and words or phrases contained in the search text whose match degree is equal to or greater than a predetermined threshold, and generate information DC1 based on such combinations.

[0093] Candidate information 121 and 122 may further include information indicating the degree of match calculated in S35, such as an image IM showing the degree of match. The image IM is positioned at a location corresponding to the employee candidate's personal basic information RG1 and RG2. The length of the bar represented by the image IM indicates the magnitude of the degree of match. This allows viewers to quantitatively and immediately grasp how well the employee candidate matches the search criteria. The image IM may also show the magnitude of the difference between the degree of match and the specified maximum score (100%).

[0094] In this diagram, two candidate information items, 121 and 122, are presented in order from the highest match score. The display order of information regarding employee candidates is determined by the display control unit 215a based on the match score, but it is not limited to this and may be determined based on other information in addition to or instead of the match score. This allows for a change in the emphasis between identifying employee candidates and determining the display order. For example, the suitability to the search criteria may be emphasized for employee candidates, while the display order may emphasize how easily it attracts the interest of the viewer or employee candidate, or the employee candidate's preferences. In this case, the display control unit 215a may determine the display order based on other material information not used in the matching process. For example, if skill information and career information are used in the matching process, the display control unit 215a may determine the display order of employee candidates based on the match score and goal information. In this way, the control unit 215a selects employee candidates based on their current or past characteristics, but presents them to the viewer in a way that aligns with the employee candidate's desired future state. This ensures relevance to search criteria while also allowing for presentations that are more likely to attract the viewer's interest or align with the preferences of potential employees.

[0095] Furthermore, the display control unit 215a may determine the display order based on the information with relatively higher importance among the material information used in the matching process, in addition to the match score. For example, suppose skill information and career information are used in the matching process. In this case, if the career information is more important than the skill information, the display control unit 215a may determine the display order of employee candidates based on the match score and career information. This makes it possible to adjust the weighting between the selection of employee candidates and the determination of the display order.

[0096] Candidate information 121 and 122 may include newly generated information DC2 from other material information not used in the matching process. The material information used in the matching process may be excluded from the material information used in information DC2. For example, if skill information and career information were used in the matching process, information DC2 may be text generated based on the employee candidate's goal information.

[0097] 7. Variations Embodiments 1 and 2 have been described above, but Embodiments 1 and 2 can be modified as follows.

[0098] For example, in Embodiments 1 and 2, a series of processes were executed in the personnel management devices 2 and 2a, but some of the processes may be executed in an external device. For example, in the step of generating first output information (employee feature text in Embodiment 2), the generation unit 212 of the personnel management devices 2 and 2a may generate a prompt that includes at least a part of the first input information and transmit the prompt to an external device via a network NW. In this case, the external device is a computer that holds a trained model such as an LLM (first trained model in Embodiment 2). The trained model is the same as in Embodiments 1 and 2, so its description is omitted. The generation units 212 and 212a may then receive the first output information generated by the external device using the trained model via a network NW. By executing part of the process through an external service in this way, the same effects as in Embodiments 1 and 2 can be obtained while suppressing development resources.

[0099] Furthermore, in Embodiment 2, for example, the material information and the first output information were information about the members of the organization. However, the material information and the first output information may also be information about persons who do not belong to the organization, or persons who currently belong to other organizations, such as job seekers.

[0100] In Embodiment 2, the search processing unit 214a of the personnel management device 2a identifies the relationship between the viewer and each employee of the organization in the search processing step, obtains the employee characteristic text for each employee, and matches these with the search text. However, the scope of employees to be searched (search scope) is not limited to all employees, but may be only some employees. For example, the search processing unit 214a may divide the search scope in advance, and sequentially identify the relationship between the viewer and each employee included in each search scope, obtain the employee characteristic text for each employee, and perform matching. The search processing unit 214a may then terminate the search processing step when the number of matched employees becomes M or more (where M is a natural number). Note that the search processing unit 214a obtains employee characteristic text for all employees, but may perform matching only for some employees. The search processing unit 214a may also pre-set the search range according to the search conditions. For example, suppose a viewer enters the text "personnel with leadership experience and an international orientation" along with the search condition "currently working in the human resources department." In this case, the search processing unit 214a may identify employees tagged as currently working in the human resources department using the employee database or the like, and set those employees as the search range.

[0101] In Embodiments 1 and 2, the case where the personnel management device 2 and 2a is a single device was described, but some or all of the components of the personnel management device 2 and 2a may be realized by multiple information processing devices or circuits. In this case, the multiple information processing devices or circuits may be centrally located or distributed. For example, the information processing devices or circuits may be realized in a form in which each is connected via a communication network, such as a client-server system or a cloud computing system. Furthermore, the functions of the personnel management device 2 and 2a may be provided in SaaS (Software as a Service) format.

[0102] While the present disclosure has been described above with reference to embodiments, it is not limited thereto. Various modifications to the structure and details of the present disclosure are possible, which can be understood by those skilled in the art within the scope of the invention.

[0103] Some or all of the above embodiments may also be described as follows, but are not limited to the following: (Note 1) A human resources management system comprising one or more processors and memory, The one or more processors described above are capable of performing the generation step and the determination step, The aforementioned processor 1 or more In the generation step described above, a first output information is generated from one or more source information using a trained model. The trained model takes input information, which includes at least a portion of the material information, as input and outputs first output information, which includes at least a portion of the material information. In the determination step, the attributes of the generated first output information are determined based on the attributes of the one or more material information. Human resource management system. (Note 2) The aforementioned one or more pieces of material information include at least one of the following: career information indicating the history of the organization's members, skill information indicating the skills of the members, and goal information indicating the goals of the members. The first output information is information relating to the characteristics of the member. The human resource management system described in Appendix 1. (Note 3) The attribute of the one or more material information is the range of users who can use the one or more material information. The attribute of the first output information is the range of users who can use the first output information. The aforementioned use includes at least one of the following: viewing, editing, sharing, and processing the information in question. The personnel management system described in Appendix 1 or 2. (Note 4) The attributes of the one or more pieces of material information are determined in correspondence with the user attributes of the viewer. The personnel management system described in Appendix 3. (Note 5) The one or more processors described above are capable of further executing the first display control step, In the first display control step, a screen is displayed on the registrant terminal operated by the registrant that accepts modifications to the attributes of the one or more material pieces of information, or to the attributes of the determined first output information. A human resource management system as described in any one of the items 1 to 4 of the appendix. (Note 6) The input information further includes conditions for the data size of the first output information, conditions for the absolute or relative importance of each of the one or more types of material information, and conditions for the characteristics to be obtained for the first output information. A human resource management system as described in any one of the items 1 to 5 of the appendix. (Note 7) The one or more processors described above are further capable of performing a search processing step and a second display control step. In the search processing step, upon receiving a search request from a viewer terminal operated by the viewer, the system obtains the first output information corresponding to the member and which the viewer has access to. In the second display control step, information generated based on the search conditions included in the search request and the first output information is displayed on the viewer terminal. The personnel management system described in Appendix 2. (Note 8) The aforementioned processor 1 or more In the search processing step, for each member, the relationship between the member's job title and the viewer is identified, and from among a plurality of first output pieces of information corresponding to that member, the first output piece of information corresponding to the relationship is selected. In the second display control step, the information generated based on the search conditions and the selected first output information is displayed on the viewer terminal. The personnel management system described in Appendix 7. (Note 9) A human resource management method implemented by one or more processors, The aforementioned personnel management method comprises a generation step and a decision step, In the generation step described above, a first output information is generated from one or more source information using a trained model. The trained model takes input information, which includes at least a portion of the material information, as input and outputs first output information, which includes at least a portion of the material information. In the determination step, the attributes of the generated first output information are determined based on the attributes of the one or more material information. Human resource management methods. (Note 10) A program for operating a computer comprising one or more processors and memory, wherein the program causes the one or more processors to perform a generation step and a determination step. In the generation step described above, a first output information is generated from one or more source information using a trained model. The trained model takes input information, which includes at least a portion of the material information, as input and outputs first output information, which includes at least a portion of the material information. In the determination step, the attributes of the generated first output information are determined based on the attributes of the one or more material information. program. [Explanation of Symbols]

[0104] 1,1a Human Resource Management System 2,2a Human resources management device 3. Registered user terminal 4 Viewer terminals Screens 6, 7, 8, 9, 10, 11, 12 21 Control Unit 22 processors 23 ROM 24 RAM 25 Communications Department 26 Memory section 27 Input section 31 Control Unit 32 processors 33 ROM 34 RAM 35 Communications Department 36 Memory section 37 Input section 38 Display section 60 Material Attribute Table 61 Material Information 62,82 Viewable Groups 63,101 Input Area 64,74,75,84,85,91,92,111 Operation area 70 Material Output Table 72 Employee Characteristics Text 80 Output Attribute Table 121,122 Candidate Information 211,211a Acquisition Department 212,212a generation part 213,213a Decision section 214a Search Processing Unit 215a Display Control Unit T1 Material Attribute Table T11, T21 Material Information T12,T32 attributes T2 Material Output Table T22, T31 First Output Information T3 Output Attribute Table

Claims

1. A human resources management system comprising one or more processors and memory, The one or more processors described above are capable of performing the generation step and the determination step, The one or more processors mentioned above are: In the generation step described above, a first output information is generated from one or more source information using a trained model. The trained model takes input information including at least a portion of the material information as input and outputs first output information including at least a portion of the material information. In the determination step, the attributes of the generated first output information are determined based on the attributes of the one or more material information. Human resource management system.

2. The aforementioned material information includes at least one of the following: career information indicating the career history of the organization's members, skill information indicating the skills of the members, and goal information indicating the goals of the members. The first output information is information relating to the characteristics of the member. The human resource management system according to claim 1.

3. The attribute of the one or more material information is the range of users who can use the one or more material information. The attribute of the first output information is the range of users who can use the first output information. The aforementioned use includes at least one of the following: viewing, editing, sharing, and processing the information in question. The human resource management system according to claim 1.

4. The attributes of the one or more pieces of material information are determined in correspondence with the user attributes of the viewer. The human resource management system according to claim 3.

5. The one or more processors described above are capable of further executing the first display control step, In the first display control step, a screen is displayed on the registrant terminal operated by the registrant that accepts modifications to the attributes of the one or more material pieces of information, or the attributes of the determined first output information. The human resource management system according to claim 1.

6. The input information further includes conditions for the data size of the first output information, conditions for the absolute or relative importance of each of the one or more types of material information, and conditions for the characteristics to be obtained for the first output information. The human resource management system according to claim 1.

7. The one or more processors described above are further capable of performing a search processing step and a second display control step. In the search processing step, upon receiving a search request from a viewer terminal operated by the viewer, the system obtains the first output information corresponding to the member and which the viewer has access to. In the second display control step, information generated based on the search conditions included in the search request and the first output information is displayed on the viewer terminal. The human resource management system according to claim 2.

8. The one or more processors mentioned above are: In the search processing step, the relationship between the member and the viewer's job titles is identified, and from among a plurality of first output pieces of information corresponding to the member, the first output piece of information corresponding to the relationship is selected. In the second display control step, the information generated based on the search conditions and the selected first output information is displayed on the viewer terminal. The human resource management system according to claim 7.

9. A human resources management method implemented by one or more processors, The aforementioned personnel management method comprises a generation step and a decision step, In the generation step described above, a first output information is generated from one or more source information using a trained model. The trained model takes input information including at least a portion of the material information as input and outputs first output information including at least a portion of the material information. In the determination step, the attributes of the generated first output information are determined based on the attributes of the one or more material information. Human resource management methods.

10. A program for operating a computer comprising one or more processors and memory, wherein the program causes the one or more processors to perform a generation step and a determination step. In the generation step described above, a first output information is generated from one or more source information using a trained model. The trained model takes input information including at least a portion of the material information as input and outputs first output information including at least a portion of the material information. In the determination step, the attributes of the generated first output information are determined based on the attributes of the one or more material information. program.

Images