Information processing device, information processing system, information processing method, and program

Abstract

To provide an information processing device, an information processing system, an information processing method, and a program which can contribute to human capital based management.SOLUTION: An information processing device includes: a first acquisition unit which acquires log information of a person on a cyber space and a physical space; a second acquisition unit which acquires human resource information of the person; a storage unit which stores integrated data of log information of the person and human resource information in association with each other; and a first generation unit which generates a hypothesis and a basis for a problem regarding human capital based management on the basis of the integrated data, and outputs the generated hypothesis and the basis.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing system, an information processing method, and a program. [Background technology]

[0002] In recent years, human capital management, which regards human resources as capital and increases corporate value, has been attracting attention in corporate management. In order to maximize the value of human resources in a company, it is necessary to analyze information about human resources and link it to management strategies.

[0003] As a related technique, for example, Patent Document 1 describes a system that links and analyzes vital sign information, behavioral information, and work quality information of workers. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2022-082304 Summary of the Invention [Problem to be solved by the invention]

[0005] In Patent Document 1, advice on work is generated for workers by analyzing vital signs, behavioral information, work quality information, etc. of workers. In this way, although related technologies such as Patent Document 1 analyze information about people, they do not take human capital management into consideration and therefore cannot contribute to human capital management.

[0006] In view of such problems, one of the objects of the present disclosure is to provide an information processing device, an information processing system, an information processing method, and a program that can contribute to human capital management. [Means for solving the problem]

[0007] An information processing device according to one embodiment of the present disclosure includes a first acquisition means for acquiring log information of a person in cyberspace and physical space, a second acquisition means for acquiring human resource information of the person, a storage means for storing integrated data linking the log information of the person with the human resource information of the person, and a first generation means for generating hypotheses and evidence for problems related to human capital management based on the integrated data and outputting the generated hypotheses and evidence.

[0008] An information processing system according to one embodiment of the present disclosure comprises a first acquisition means for acquiring a person's log information in cyberspace and physical space, a second acquisition means for acquiring the person's human resource information, a storage means for storing integrated data linking the person's log information with the person's human resource information, and a first generation means for generating hypotheses and evidence for issues related to human capital management based on the integrated data and outputting the generated hypotheses and evidence.

[0009] An information processing method according to one aspect of the present disclosure acquires log information of a person in cyberspace and physical space, acquires human resource information of the person, stores integrated data linking the log information of the person with the human resource information of the person, generates hypotheses and evidence for issues related to human capital management based on the integrated data, and outputs the generated hypotheses and evidence.

[0010] A program according to one embodiment of the present disclosure is a program for causing a computer to execute a process of acquiring log information of a person in cyberspace and physical space, acquiring human resource information of the person, storing integrated data linking the log information of the person with the human resource information of the person, generating hypotheses and evidence for problems related to human capital management based on the integrated data, and outputting the generated hypotheses and evidence. [Effects of the Invention]

[0011] The present disclosure can contribute to human capital management. [Brief explanation of the drawings]

[0012] [Figure 1] FIG. 1 is a configuration diagram illustrating an example of the configuration of an information processing device according to some embodiments. [Figure 2] 1 is a configuration diagram illustrating an example configuration of an information processing system according to some embodiments. [Figure 3] 1 is a flowchart illustrating an example of an information processing method according to some embodiments. [Figure 4] 1 is a configuration diagram illustrating an example of the configuration of a management support system according to some embodiments. [Figure 5] 1 is a flowchart illustrating an example of a data integration process according to some embodiments. [Figure 6] FIG. 1 illustrates an example of a data integration process according to some embodiments. [Figure 7] 1 is a flowchart illustrating an example of a problem detection process according to some embodiments. [Figure 8] 10 is a flowchart illustrating an example of a process for generating hypothesis evidence and personnel policy proposals according to some embodiments. [Figure 9] FIG. 1 is a diagram illustrating an example of the hardware configuration of a computer according to some embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0013] Hereinafter, embodiments will be described with reference to the drawings. In the drawings, the same elements are denoted by the same reference numerals, and redundant description will be omitted as necessary.

[0014] (Embodiment 1) First, a description will be given of embodiment 1. In this embodiment, an outline of several embodiments will be described.

[0015] 1 shows an example of the configuration of an information processing device 10 according to some embodiments. For example, the information processing device 10 is a device that analyzes information on employees and outputs the analysis results in order to support human capital management.

[0016] In the example of FIG. 1, the information processing device 10 includes a first acquisition unit 11, a second acquisition unit 12, a storage unit 13, and a first generation unit 14.

[0017] The first acquisition unit 11 acquires log information of a person in cyberspace and physical space. For example, the log information of a person in physical space may include vital information of the person, emotional information of the person, an activity log of the person, etc. The log information of a person in cyberspace may include a system usage log of the person, etc.

[0018] The second acquiring unit 12 acquires the human resource information of the person. For example, the human resource information of the person may include the attribute information of the person, the achievement information of the person, and the awareness information of the person.

[0019] The storage unit 13 stores integrated data linking the log information of the person acquired by the first acquisition unit 11 with the human resource information of the person acquired by the second acquisition unit 12. For example, the storage unit 13 links and stores the time-series data of the log information and the human resource information for each person.

[0020] The first generation unit 14 generates hypotheses and rationales for problems related to human capital management based on the integrated data stored in the storage unit 13, and outputs the generated hypotheses and rationales. Problems related to human capital management are problems that hinder the achievement of human capital management goals, such as KGI (Key Goal Indicators). One example of a problem is that employee stress levels are higher than the standard.

[0021] The information processing device 10 may also include a detection unit that detects problems related to human capital management based on the person's log information acquired by the first acquisition unit 11. For example, the first generation unit 14 may generate a question about the cause of the problem in accordance with the detection result of the problem related to human capital management, and generate a hypothesis and evidence based on the generated question and integrated data. The detection unit may detect problems related to human capital management based on KGI for human capital management. In this case, the detection unit may determine KPI (Key Performance Indicator) related to KGI based on the acquired person's log information, and detect problems related to human capital management.

[0022] Furthermore, the information processing device 10 may include a second generation unit that creates a personnel policy proposal for a problem related to human capital management based on the hypotheses and evidence generated by the first generation unit 14. The personnel policy proposal is a policy proposal for solving the problem, and is a policy proposal related to management strategy and human resources strategy. For example, if an employee's stress level is higher than a standard, the second generation unit generates a policy proposal (such as a process review) for reducing the stress level.

[0023] Note that each unit in the information processing device 10 may be included in one device or multiple devices, or may be included in an information processing system including one device or multiple devices. Fig. 2 shows an example configuration of an information processing system 20 according to some embodiments. In the example of Fig. 2, the information processing system 20 includes the first acquisition unit 11, the second acquisition unit 12, the storage unit 13, and the first generation unit 14 shown in Fig. 1. For example, the first acquisition unit 11, the second acquisition unit 12, the storage unit 13, and the first generation unit 14 may be distributed across multiple devices.

[0024] 3 shows an example of an information processing method according to some embodiments. For example, the information processing method according to some embodiments is executed by the information processing device 10 of FIG. 1 or the information processing system 20 of FIG.

[0025] 3, the first acquisition unit 11 acquires log information of a person in cyberspace and physical space (S11). Next, the second acquisition unit 12 acquires human resource information of the person (S12). Next, the storage unit 13 stores integrated data linking the acquired log information of the person with the acquired human resource information of the person (S13).

[0026] Next, the first generation unit 14 generates a hypothesis and evidence for the problem related to human capital management based on the stored integrated data, and outputs the generated hypothesis and evidence (S14). For example, when a problem is detected based on a person's log information, a question is generated according to the detection result, and a hypothesis and evidence are generated based on the question and the integrated data. Furthermore, the information processing device 10 may create a personnel policy proposal for the problem related to human capital management based on the generated hypothesis and evidence.

[0027] In this way, in this embodiment, hypotheses and evidence for problems related to human capital management are generated based on integrated data linking a person's log information with the person's human resource information. This makes it possible to specifically identify the cause of the problem and further generate personnel policy proposals to solve the problem, thereby contributing to human capital management.

[0028] (Embodiment 2) Next, a description will be given of a second embodiment. In this embodiment, a specific example of the first embodiment will be described.

[0029] 4 shows an example of the configuration of a management support system 1 according to some embodiments. The management support system 1 is a system that links and analyzes digital (cyberspace) and real (physical space) data related to human resources, derives hypotheses and evidence about the causes of problems related to human capital management, and proposes personnel policy proposals based on the hypotheses and evidence.

[0030] 4, the management support system 1 includes a data integration server, an analysis server 200, a physical system 300, a cyber system 400, an HR database 500, and an integrated database 600. Each device and each system is connected to each other via an arbitrary network so that they can communicate with each other.

[0031] The management support system 1 is not limited to the configuration shown in Figure 4 and may have other configurations. For example, the functions of the data integration server 100 and the analysis server 200 may be realized by a single device or any number of devices. The HR database 500 and the integrated database 600 may be combined into a single database. The HR database 500 and the integrated database 600 may be located within the data integration server 100 or the analysis server 200.

[0032] Physical system 300 is a platform capable of collecting personal data in the physical space. The configuration of physical system 300 is not limited as long as it is capable of collecting personal data in the physical space. The personal data in the physical space is data necessary for acquiring log information in the physical space of employees. For example, physical system 300 includes a camera for capturing images of people's faces for facial recognition, a camera for capturing images of people to acquire real-life activity logs, entrance and exit gates, terminals in internal facilities, vending machines, terminals in convenience stores, etc.

[0033] Cyber ​​system 400 is a platform capable of collecting personal data in cyberspace. The configuration of cyber system 400 is not limited as long as it is capable of collecting personal data in cyberspace. Personal data in cyberspace is data necessary for acquiring employee log information in cyberspace. For example, cyber system 400 includes personal computers (PCs), terminals, business systems, etc. used by employees.

[0034] The HR database 500 is a database that stores employee HR (Human Resource) data. HR data is registered and updated as needed by the HR department or each individual. HR data includes employee attribute data, performance data, attitude data, etc. Attribute data is data indicating employee attributes, including, for example, an individual's gender, age, job type, department, work location, qualifications, skills, etc. Performance data is data indicating employee performance, including, for example, performance evaluation data, behavioral evaluation data, 360° evaluation, etc. Attitude data is data indicating employee attitudes, including, for example, the results of employee surveys and various questionnaires. Attitude data may include employee engagement, values, business understanding, goals, etc. Each HR data is stored linked to the employee's ID (common ID).

[0035] The integrated database 600 is a database that stores integrated HR data that is an extension of employee HR data. The integrated HR data is generated and stored by the data integration server 100. The integrated HR data is data that links an employee's HR data with log information in the employee's physical space and cyberspace. For example, the integrated HR data is data that links HR data and log information with a common ID that uses biometric information, including facial recognition, as a key.

[0036] Log information in the physical space is time-series data that indicates an individual's activity (behavior and state) in the real physical space. For example, log information in the physical space includes changes in vital signs and emotions, real-life activity logs, etc. Real-life activity logs include work content and work time, arrival and departure times at work, usage history of company facilities, vending machine usage history, and store payment history. Log information in the cyberspace is time-series data that indicates an individual's activity (behavior and state) in the cyberspace. For example, log information in the cyberspace includes system usage history, PC usage history, web conference history, chat history, email history, etc.

[0037] The data integration server 100 is a server that collects employee HR data and employee log information in physical and cyberspace, and generates integrated HR data. The data integration server 100 may be one or more physical servers, or may be a virtualized server built on a virtualization platform. For example, the data integration server 100 may be a cloud server on a cloud.

[0038] In the example of FIG. 4, the data integration server 100 includes a face authentication unit 110, a vital sign and emotion estimation unit 120, an activity log acquisition unit 130, a system log acquisition unit 140, an HR data acquisition unit 150, and a data integration unit 160. For example, the face authentication unit 110, the vital sign and emotion estimation unit 120, and the activity log acquisition unit 130 are physical log acquisition units that acquire log information in physical space. The system log acquisition unit 140 is a cyberlog acquisition unit that acquires log information in cyberspace. The face authentication unit 110, the vital sign and emotion estimation unit 120, the activity log acquisition unit 130, and the system log acquisition unit 140 are also first acquisition units that acquire log information in physical space and cyberspace. The HR data acquisition unit 150 is also a second acquisition unit that acquires HR data. Note that the data integration server 100 may have other configurations as long as it is capable of performing the processes described below.

[0039] The face authentication unit 110 performs face authentication based on a captured face image of an employee's face. For example, the face authentication unit 110 performs face authentication using a face authentication AI engine generated by machine learning such as deep learning. The face authentication unit 110 extracts a face image of a person from an image of the person captured by a camera of the physical system 300, and performs face authentication using the extracted face image. For example, the face authentication unit 110 compares the captured face image with face images of pre-registered employees, and performs face authentication based on the similarity of the face images, etc. For example, an ID is linked to the pre-registered face image of an employee, and the employee in the captured face image can be identified based on the face authentication result. Note that the method is not limited to face authentication, and other biometric authentication methods may also be used to identify workers.

[0040] The vital sign and emotion estimation unit 120 estimates the vital signs and emotions of an employee based on a facial image of the employee's face. For example, the vital sign and emotion estimation unit 120 estimates the vital signs and emotions using a vital sign and emotion estimation AI engine generated by machine learning such as deep learning. The vital sign and emotion estimation AI engine learns the vital signs and emotions of a person based on the facial image of the person. The face authentication unit 110 extracts a facial image of the person from an image of the person captured by a camera of the physical system 300 and estimates the vital signs and emotions using the extracted facial image. Note that vital sign data is not limited to facial images, and may be acquired from a wearable device or the like. For example, the vital sign and emotion estimation unit 120 may estimate the emotion of a person based on the person's facial expression or estimated vital sign data. For example, the emotion data may be happy, angry, sad, relaxed, etc. For example, the employee whose vital signs and emotions are estimated by the vital signs and emotion estimation unit 120 may be identified through facial recognition by the facial recognition unit 110.

[0041] The activity log acquisition unit 130 acquires real activity logs of employees. For example, the activity log acquisition unit 130 acquires activity logs using a behavior recognition AI engine generated by machine learning such as deep learning. For example, the activity log acquisition unit 130 recognizes a person's behavior from an image of the person captured by a camera in the physical system 300. From the person's behavior, the activity log acquisition unit 130 can recognize the work content, work time, etc. Furthermore, the activity log acquisition unit 130 may acquire arrival and departure times, usage history of in-house facilities, usage history of vending machines, payment history of shops, etc. from entrance and exit gates, terminals in in-house facilities, vending machines, terminals in shops, etc. in the physical system 300. For example, the employees whose activity logs the activity log acquisition unit 130 acquires may be identified by facial recognition by the facial recognition unit 110 or by the employee's ID entered into a terminal, etc.

[0042] The system log acquisition unit 140 acquires the system logs of employees. The system logs are log information in cyberspace. For example, the system log acquisition unit 140 acquires system usage history, PC usage history, web conference history, chat history, email history, etc. from the PCs, terminals, and business systems used by employees in the cyber system 400. For example, the employees whose system logs the system log acquisition unit 140 acquires may be identified by the employee's ID entered into a terminal, etc.

[0043] The HR data acquisition unit 150 acquires HR data stored in the HR database 500. The HR data acquisition unit 150 acquires employee HR data corresponding to the log information acquired by the face authentication unit 110, the vital sign and emotion estimation unit 120, the activity log acquisition unit 130, and the system log acquisition unit 140.

[0044] The data integration unit 160 links the acquired employee's log information in physical space and cyberspace with the acquired HR data to generate the employee's integrated HR data, and stores the generated HR integrated data in the integrated database 600. The data integration unit 160 links the employee's vital signs and emotion data, activity log, and system log identified by facial recognition to the corresponding employee's HR data.

[0045] The analysis server 200 is a server that analyzes the HR integrated data and generates hypotheses and rationales for problems that have occurred, as well as proposed personnel measures. The analysis server 200 may be one or more physical servers, or may be a virtualized server built on a virtualization platform. For example, the analysis server 200 may be a cloud server on a cloud.

[0046] In the example of FIG. 4, the analysis server 200 includes a problem detection unit 210, a hypothesis basis generation unit 220, and a personnel policy proposal generation unit 230. The hypothesis basis generation unit 220 is also a first generation unit that generates hypotheses and basis. The personnel policy proposal generation unit 230 is also a second generation unit that generates personnel policy proposals. For example, the problem detection unit 210, the hypothesis basis generation unit 220, and the personnel policy proposal generation unit 230 may each be located on a separate server. However, the analysis server 200 may have other configurations as long as it is capable of performing the processing described below.

[0047] The problem detection unit 210 detects problems related to human capital management. For example, the problem detection unit 210 detects problems using a problem detection AI engine generated by machine learning such as deep learning. The problem detection AI engine learns the relationship between the goals of human capital management and the factors that achieve or hinder the goals. For example, the problem detection AI engine learns the relationship between the human capital KGI and the KPIs by performing fine tuning. The problem detection unit 210 uses the problem detection AI engine to acquire KPIs related to the human capital KGI. Furthermore, the problem detection AI engine learns measures and monitoring methods for each KPI. The problem detection unit 210 uses the problem detection AI engine to acquire measures and monitoring methods related to the KPIs. The problem detection unit 210 monitors data corresponding to the KPIs based on the monitoring method and detects problems based on the monitoring results. The monitored data may be acquired from any of the physical system 300, the cyber system 400, the HR database 500, and the integrated database 600. The problem detection unit 210 may monitor the employee's physical space log information and cyberspace log information acquired by the data integration server 100. For example, the problem detection unit 210 may monitor the employee's emotions, work content, etc., and determine the stress level.

[0048] When a problem is detected, the hypothesis and evidence generation unit 220 generates a hypothesis and evidence for the problem. The hypothesis and evidence generation unit 220 generates a hypothesis and evidence for the cause of the problem based on the HR integrated data stored in the integrated database 600. For example, the hypothesis and evidence generation unit 220 generates the hypothesis and evidence using a hypothesis and evidence generation AI engine generated by machine learning such as deep learning. The hypothesis and evidence generation AI engine learns the relationship between the question about the problem, the HR integrated data, and the hypotheses and evidence. The hypothesis and evidence generation AI engine may learn using not only the HR integrated data but also internal corporate data, open data, common knowledge data, etc. Internal corporate data is data related to the organization, environment, business, etc. Open data and common knowledge data are generally publicly available data that serve as hypotheses and evidence for the problem. For example, the hypothesis and evidence generation AI engine may be generated by learning using the HR integrated data as Retrieval-Augmented Generation (RAG). The hypothesis and evidence generation unit 220 may output the generated hypothesis and evidence.

[0049] The personnel policy proposal generation unit 230 generates personnel policy proposals for the problem based on the generated hypotheses and evidence. For example, the personnel policy proposal generation unit 230 generates personnel policy proposals using a personnel policy proposal generation AI engine generated by machine learning such as deep learning. For example, the personnel policy proposal generation AI engine learns the relationship between the hypotheses and evidence and the personnel policy proposals. The personnel policy proposal generation unit 230 outputs the generated personnel policy proposals.

[0050] FIG. 5 shows an example of data integration processing according to some embodiments. For example, the processing in FIG. 5 is executed by the data integration server 100. Note that FIG. 5 is just an example, and the order of some of the processing may be changed, some of the processing may be performed consecutively or in parallel, or some of the processing may be omitted. For example, S102 to S104 may be performed in parallel or in any order. Also, only one of S102 to S104 may be performed.

[0051] In the example of FIG. 5, the face authentication unit 110 performs face authentication from a facial image of an employee (S101). For example, the face authentication unit 110 acquires a facial image of the employee from a camera and inputs the acquired facial image into a face authentication AI engine to perform face authentication. The camera may be a camera installed at an entrance gate, a workplace, a work site, etc. If face authentication of the employee is successful, the face authentication unit 110 identifies the employee's ID.

[0052] Next, the vital sign and emotion estimation unit 120 estimates the vital sign and emotion of the employee (S102). For example, the vital sign and emotion estimation unit 120 estimates the vital sign and emotion of the employee by inputting a facial image that has undergone facial recognition into a vital sign and emotion estimation AI engine. That is, the vital sign and emotion of the employee having an ID identified by facial recognition is estimated.

[0053] The activity log acquisition unit 130 also acquires the employee's real activity log (S103). The activity log acquisition unit 130 may acquire the activity log following facial recognition, as necessary. For example, the facial recognition unit 110 may perform facial recognition from an image of the employee captured by a camera, and the activity log acquisition unit 130 may recognize the employee's behavior using a behavior recognition AI engine and acquire the employee's work content, etc. That is, the activity log of an employee whose ID is identified by facial recognition may be acquired. The activity log acquisition unit 130 may also acquire usage history including the employee's ID from a terminal in an in-house facility, a vending machine, a terminal in a convenience store, etc., and acquire the activity log of the employee identified by the ID.

[0054] Furthermore, the system log acquiring unit 140 acquires the system log of the employee (S104). For example, the system log acquiring unit 140 may acquire the usage history including the employee's ID from the PC, terminal, business system, etc. used by the employee, and acquire the system log of the employee identified by the ID.

[0055] Next, the HR data acquisition unit 150 acquires the employee's HR data (S105). For example, in order to link the employee's vital signs and emotions, activity log, and system log acquired in S102 to S104, the HR data of the employee having the same ID as the acquired log, etc. is acquired from the HR database 500.

[0056] Next, the data integration unit 160 integrates the employee's vital signs and emotions, activity log, and system log with the employee's HR data (S106). For example, the data integration unit 160 generates integrated HR data by linking the employee's vital signs and emotions, activity log, and system log acquired in S102 to S104 with the corresponding employee's HR data acquired in S105, and stores the generated integrated HR data in the integrated database 600. Any of the employee's vital signs and emotions, activity log, and system log may be linked to the employee's HR data. The data integration server 100 repeats S101 to S106, linking the acquired data to the HR data each time any of the employee's vital signs and emotions, activity log, and system log is acquired. Logs, etc. may also be linked to the integrated HR data already stored in the integrated database 600.

[0057] Figure 6 shows a specific example of data integration processing according to some embodiments. Figure 6 shows an example in which log information in physical space and cyberspace from the time an employee enters until the time they leave is linked to HR data in chronological order by the data integration processing described in Figure 5.

[0058] In the example of FIG. 6, first, an employee enters a company (S201). For example, when the employee passes through the entrance gate, the face authentication unit 110 acquires a facial image of the employee from a camera at the entrance gate, performs facial authentication, and identifies the employee's ID. The vital sign and emotion estimation unit 120 estimates the vital signs and emotions from the facial image of the employee whose ID has been identified. The activity log acquisition unit 130 acquires the employee's ID and arrival time from the entrance gate. The HR data acquisition unit 150 acquires HR data with the same ID from the HR database 500. The data integration unit 160 links the acquired HR data of the employee with the arrival time, vital signs, and emotions at the time of arrival, and stores the data in the integrated database 600 as the employee's integrated HR data.

[0059] Next, the employee logs on to their own PC (S202). For example, the system log acquisition unit 140 acquires the employee's ID and log-on history from the PC. The data integration unit 160 records the PC log-on history in association with the HR integrated data of the same ID stored in the integrated database 600.

[0060] Next, the employee uses the facilities within the company (S203). For example, the activity log acquisition unit 130 acquires the employee's ID and the usage history of the facilities within the company from a terminal at the facilities within the company. The data integration unit 160 records the usage history of the facilities within the company by linking it to the HR integrated data of the same ID stored in the integrated database 600.

[0061] Next, the employee logs in to the business system (S204). For example, the system log acquisition unit 140 acquires the employee's ID and system login history from the business system. The data integration unit 160 records the system login history in association with the HR integrated data of the same ID stored in the integrated database 600.

[0062] Next, the employee makes a payment at the store (S205). For example, the activity log acquisition unit 130 acquires the employee's ID and the store's payment history from a terminal at the store. The data integration unit 160 records the store's payment history in association with the HR integrated data with the same ID stored in the integrated database 600.

[0063] Next, the employee works at the work site (S206). For example, the face authentication unit 110 performs face authentication on images captured by a camera at the work site to identify the employee's ID. The activity log acquisition unit 130 recognizes the worker's behavior from the identified employee's image and acquires the work content. The vital sign and emotion estimation unit 120 estimates the vital signs and emotions from the identified employee's facial image. The data integration unit 160 records the employee's work start time and work end time, work history including the work content, and vital signs and emotions at the start and end of the work in association with the HR integrated data of the same ID stored in the integrated database 600.

[0064] Next, the employee leaves the company (S207). For example, when the employee passes through the exit gate, the face authentication unit 110 acquires the employee's facial image from the camera at the exit gate, performs facial authentication, and identifies the employee's ID. The vital sign and emotion estimation unit 120 estimates the employee's vital signs and emotions from the facial image of the employee whose ID has been identified. The activity log acquisition unit 130 acquires the employee's ID and time of leaving work from the exit gate. The data integration unit 160 records the employee's time of leaving work, vital signs, and emotions at the time of leaving work in association with the HR integrated data of the same ID stored in the integrated database 600.

[0065] 7 illustrates an example of a problem detection process according to some embodiments. For example, the process of FIG. 7 is performed by the problem detection unit 210.

[0066] In the example of Figure 7, the problem detection unit 210 acquires a human capital KGI as a goal for human capital management (S301). The human capital KGI may be input from an external source or may be set in advance. For example, the human capital KGI is an "engagement score of 50%."

[0067] The problem detection unit 210 inputs the human capital KGI into the problem detection AI engine (S302) and generates an alert (S303). For example, the alert may be generated based on the human capital KGI and HR data, etc. The engagement score can be obtained from awareness data in the HR data. For example, the problem detection AI engine generates an alert "The sales department's engagement score is expected to decrease from the previous time" for the KGI "engagement score 50%." The problem detection unit 210 may output the generated alert to a display device, etc.

[0068] The problem detection AI engine also generates key success factors (KSFs) (S304), KPIs (S305), measures (S306), and monitoring methods (S307) related to the human capital KGI and alerts. For each human capital KGI, the problem detection AI engine generates multiple key success factors (KSFs) for achieving the KGI. For example, for the KGI "engagement score 50%," it generates a KSF such as "achieving work-life balance."

[0069] Furthermore, the problem detection AI engine generates multiple KPIs for achieving each key success factor (KSF) and generates measures and monitoring methods required for each KPI. For example, for the KSF "achieving work-life balance," it generates KPI (1) "20 hours of overtime per month" and KPI (2) "stress level below 50%." For KPI (1) "20 hours of overtime per month," it generates measure (1) "regularly checking overtime hours and following up with the target employee to control overtime hours" and monitoring method (1) "recording attendance records and displaying overtime hours when arriving and leaving work." For KPI (2) "stress level below 50%," it generates measure (2) "stress control by conducting interviews and work adjustments based on the results of stress level monitoring" and monitoring method (2) "monitoring stress levels when arriving and leaving work." The problem detection unit 210 may output the generated KSFs, KPIs, measures, and monitoring methods to a display device or the like.

[0070] The problem detection unit 210 implements the generated monitoring method and detects a problem. The problem detection unit 210 may implement all of the monitoring methods, or may implement a selected monitoring method. For example, the problem detection unit 210 implements monitoring method (2) "stress level monitoring when arriving at and leaving work." The problem detection unit 210 monitors the employee's log information in the physical space and the log information in the cyberspace, and detects a problem when the employee's stress level is higher than a standard. For example, the stress level may be determined from the employee's vital signs or emotions. The problem detection unit 210 may output the detected problem to a display device or the like.

[0071] 8 shows an example of a process for generating assumption grounds and a personnel policy proposal according to some embodiments. For example, the process of FIG. 8 is performed by the assumption grounds generating unit 220 and the personnel policy proposal generating unit 230.

[0072] 8, the hypothesis basis generation unit 220 acquires the KPI (impeding factor) that detected the problem (S401). For example, when a problem is detected as in the example of FIG. 7, the KPI of the detected problem, "the stress level in the sales department is 50%," is acquired.

[0073] Next, the hypothesis evidence generation unit 220 generates a question for the problematic KPI (S402). The question for the problem may be generated by the hypothesis evidence generation AI engine, or may be converted into a format that asks the reason for the problem using a predetermined pattern. For example, for the problematic KPI "The stress level in the sales department is 50%", the question generated is "Why has the stress level increased in the sales department?"

[0074] Next, the hypothesis evidence generation unit 220 inputs the generated question, the HR integrated data, the internal company data, and the open data from the integrated database 600 into the hypothesis evidence generation AI engine (S403), and outputs a hypothesis and evidence for the cause of the problem (S404). The hypothesis evidence generation AI engine generates and outputs a hypothesis about the cause of the problem and evidence supporting the hypothesis in response to the input question. For example, a hypothesis for the question may be generated, and data that forms the basis for the hypothesis may be obtained from the HR integrated data, the internal company data, the open data, etc. The hypothesis evidence generation unit 220 may output the generated hypothesis and evidence to a display device, etc.

[0075] Next, the personnel policy proposal generation unit 230 inputs the generated hypothesis and evidence into the personnel policy proposal generation AI engine (S405), which then proposes a personnel policy proposal (S406). The personnel policy proposal generation AI engine generates and outputs a personnel policy proposal for improving the problem based on the input hypothesis and evidence. The personnel policy proposal generation unit 230 may output the generated personnel policy proposal to a display device or the like.

[0076] Next, a specific example of supporting human capital management by applying the management support system 1 according to some embodiments will be described.

[0077] As a specific example, Company A has adopted human capital management as a management policy. Based on the characteristics of its business, Company A decided to link its management strategy with its human resources strategy and defined its management strategy in its medium-term management plan. Company A also realized that in order to achieve this, it would be necessary to transform its traditional business model.

[0078] Company A identified the challenges it needed to overcome in order to achieve this goal and determined that organizational culture was the biggest issue. The business they were about to launch was a core business that would account for 20% of their company's sales by 2030. However, as their business model changed, they also needed to transform their business processes. However, no one was actively working to change these processes. To achieve this, Company A needed to simultaneously promote change among the people responsible for the change. However, the company's culture was characterized by a strong resistance to change. The company's overall engagement score was 25%, which was quite low by industry standards. For this reason, the company decided that organizational culture should be the top priority in its human resources strategy, even if it meant incurring costs. To change business processes, employees needed to feel motivated and comfortable with change, and perform as a team to achieve better results. They decided to work toward raising their engagement score to 50% by 2030.

[0079] In the above-described background, for example, the management support system 1 can detect a problem through the processing of FIG. 7, generate hypotheses and evidence through the processing of FIG. 8, and propose personnel policy proposals.

[0080] First, Management Support System 1 detects a decline in the engagement score relative to the KGI of "raising the engagement score to 50% by 2030," and detects an alert that "the engagement of employees in their 20s in the sales department is expected to decline significantly." For example, it can be determined from employee logs that the results of engagement, which is the most important part of the human resources strategy, are likely to decline among employees in their 20s in the sales department.

[0081] To gain insight into the likely reasons for the decline in engagement, Management Support System 1 uses its problem detection AI engine to identify KPIs related to the alert, in this example monitoring stress levels. By monitoring stress levels, it can be determined that the stress levels of employees in their twenties in the sales department at the start of work are 10 points higher than last week, indicating a potential decline in engagement.

[0082] The reasons why stress levels lead to decreased engagement are as follows: For example, the management support system 1 detects problems from these relationships. The causal link that contributes to the sales department's engagement score is work-life balance, which is rooted in properly managed working hours. Employees who feel their working hours are well managed tend to experience less stress when they come to work. Employees who do not feel their working hours are being properly managed tend to experience higher levels of stress when they come to work. Regular monitoring of emotions when employees first log on to their PCs and arrive at work shows that stress levels in the sales department remain high compared to last week. The trend of high stress continues, especially among employees in their 20s.

[0083] The management support system 1 uses a hypothesis and evidence generation AI engine to estimate hypotheses and evidence for detected problems based on logs, general knowledge, internal company data, and HR data. For example, the management support system 1 generates the following hypotheses and evidence: <Hypothesis> · Due to the large volume of document entry work occurring in the order management system, long hours of overtime continue and stress levels continue to be high. <Basis> Sales department employees in their 20s spend a lot of time using the order management system. There may be an increase in orders from customers. This is generally a time when orders for equipment and parts tend to be made with excess budget. -As the fiscal year is coming to an end, it is important to ensure that all invoices are entered by the deadline.

[0084] The management support system 1 generates personnel policy proposals from the generated hypotheses and evidence using a personnel policy proposal generation AI engine. For example, the management support system 1 generates and outputs the following personnel policy proposals to reduce stress and achieve efficient work. <Human resources policy proposal> 1. Review your processes: Check for waste and duplication in the process of entering documents into your order management system. Optimizing your work procedures and workflows can reduce work time and stress. 2. Introduction of automation: By utilizing automation tools and functions in the order management system, the burden of entering slips can be reduced. For example, automatic entry of customer and product information, and the use of barcode readers can be considered. 3. Distributing the workload: By distributing the periods and times when invoice entry work is concentrated, you can avoid long hours of overtime. It is also effective to set priorities for work and divide tasks within the team. 4. Improve communication: Smooth communication within the team will enable work coordination and early problem resolution. Establish regular meetings and progress reports to promote information sharing and communication.

[0085] Furthermore, the management support system 1 may use a personnel policy proposal generation AI engine to output currently implemented policies. The currently implemented policies may be acquired from in-house data, etc., and policies related to the personnel policy proposal may be extracted. For example, the management support system 1 may output currently implemented policies related to the personnel policy proposal as follows: <Current measures> 1.Improvement of slip entry work in order management systems There are problems with the usability of the newly introduced order management system when entering documents, and the workload for order processing is high, so we are currently introducing a system to reduce the workload. 2. Providing know-how on inputting slips into order management systems We regularly share know-how on how to enter documents into order management systems.

[0086] As described above, according to this embodiment, the management support system can detect problems with respect to human capital management goals. For example, if there are indicators to be tracked in advance as part of a human resources strategy, problems can be detected by using AI to generate KPIs, measures, and monitoring methods related to those indicators and monitoring the necessary data. Furthermore, the management support system can generate hypotheses and evidence for detected problems and propose proposed human resources measures. For example, AI can derive hypotheses and evidence for the cause of problems from HR data that links digital and real-world behaviors and is stored linked to a common ID, and then propose measures based on those hypotheses and evidence. This can therefore contribute to human capital management.

[0087] The present disclosure is not limited to the above-described embodiment, and can be modified as appropriate within the scope of the present disclosure.

[0088] Each component in the above-described embodiments may be configured with hardware or software, or both, and may be configured with one piece of hardware or software, or may be configured with multiple pieces of hardware or software. Each device and each function (processing) such as the information processing device, data integration server, and analysis server may be realized by a computer 30 having a processor 31 such as a CPU (Central Processing Unit) and a memory 32 serving as a storage device, as shown in FIG. 9. For example, a program for performing the method (information processing method) in the embodiment may be stored in the memory 32, and each function may be realized by the processor 31 executing the program stored in the memory 32.

[0089] These programs include instructions (or software code) that, when loaded into a computer, cause the computer to perform one or more functions described in the embodiments. The programs may be stored on a non-transitory computer-readable medium or a tangible storage medium. By way of example and not limitation, computer-readable media or tangible storage media include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technology, CD-ROM, digital versatile disc (DVD), Blu-ray® disc or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage device. The programs may also be transmitted on a transitory computer-readable medium or communication medium. By way of example and not limitation, transitory computer-readable media or communication media include electrical, optical, acoustic, or other forms of propagated signals.

[0090] Although the present disclosure has been described above with reference to the embodiments, the present disclosure is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present disclosure within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0091] Each drawing is merely an example for describing one or more embodiments. Each drawing may relate not only to one particular embodiment, but also to one or more other embodiments. As will be understood by those skilled in the art, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create, for example, an embodiment not explicitly shown or described. Not all features or steps shown in any one drawing are necessary to describe an exemplary embodiment, and some features or steps may be omitted. The order of steps described in any drawing may be changed as appropriate.

[0092] A part or all of the above-described embodiments can be described as, but not limited to, the following supplementary notes. (Appendix 1) a first acquisition means for acquiring log information of a person in cyberspace and physical space; a second acquiring means for acquiring human resource information of the person; a storage means for storing integrated data linking the person's log information with the person's human resource information; a first generating means for generating hypotheses and evidence for problems related to human capital management based on the integrated data and outputting the generated hypotheses and evidence; An information processing device comprising: (Appendix 2) a detection means for detecting the problem based on the log information of the person; 10. The information processing device according to claim 1. (Appendix 3) the first generation means generates a question regarding a cause of the problem in accordance with the problem detection result, and generates the hypothesis and evidence based on the generated question and the integrated data; 3. The information processing device according to claim 2. (Appendix 4) The detection means detects the problem based on the KGI for the human capital management. 3. The information processing device according to claim 2. (Appendix 5) The detection means determines a KPI related to the KGI based on the log information of the person, and detects the problem. 5. The information processing device according to claim 4. (Appendix 6) a second generation means for generating a personnel policy plan for the problem based on the hypothesis and grounds; 6. An information processing device according to any one of claims 1 to 5. (Appendix 7) The person's log information in cyberspace includes the person's system usage log, the log information in the physical space of the person includes any one of vital information of the person, emotional information of the person, and an activity log of the person; The human resource information of the person includes any one of attribute information of the person, achievement information of the person, and awareness information of the person. 6. An information processing device according to any one of claims 1 to 5. (Appendix 8) a first acquisition means for acquiring log information of a person in cyberspace and physical space; a second acquiring means for acquiring human resource information of the person; a storage means for storing integrated data linking the person's log information with the person's human resource information; a first generating means for generating hypotheses and evidence for problems related to human capital management based on the integrated data and outputting the generated hypotheses and evidence; An information processing system comprising: (Appendix 9) Acquires log information of a person in cyberspace and physical space, obtaining human resource information for said person; storing integrated data linking the person's log information with the person's human resource information; generating hypotheses and evidence for issues related to human capital management based on the integrated data, and outputting the generated hypotheses and evidence; Information processing methods. (Appendix 10) Acquires log information of a person in cyberspace and physical space, obtaining human resource information for said person; storing integrated data linking the person's log information with the person's human resource information; generating hypotheses and evidence for issues related to human capital management based on the integrated data, and outputting the generated hypotheses and evidence; A program that causes a computer to execute a process.

[0093] Some or all of the elements (e.g., configurations and functions) described in Supplementary Notes 2 to 7 that are dependent on Supplementary Note 1 (information processing device) may also be dependent on Supplementary Note 8 (information processing system), Supplementary Note 9 (information processing method), and Supplementary Note 10 (program) in the same dependency relationship as Supplementary Note 2 to Supplementary Note 7. Some or all of the elements described in any Supplementary Note may be applied to various hardware, software, recording means for recording software, systems, and methods. [Explanation of symbols]

[0094] 1 Management Support System 10. Information processing equipment 11 First Acquisition Section 12 Second Acquisition Section 13 Storage area 14 First Generation Section 20 Information Processing Systems 30 Computer 31 processors 32 memory 100 Data Integration Server 110 Face Recognition Unit 120 Vital Signs and Emotion Estimation Unit 130 Activity Log Acquisition Department 140 System Log Acquisition Unit 150 HR data acquisition unit 160 Data Integration Department 200 Analysis Server 210 Problem Detection Unit 220 Hypothesis Evidence Generation Unit 230 Human resources policy generation department 300 Physical System 400 Cyber ​​Systems 500 HR Database 600 Integrated Database

Claims

1. a first acquisition means for acquiring log information of a person in cyberspace and physical space; a second acquiring means for acquiring human resource information of the person; a storage means for storing integrated data linking the person's log information with the person's human resource information; a first generating means for generating hypotheses and evidence for problems related to human capital management based on the integrated data and outputting the generated hypotheses and evidence; An information processing device comprising:

2. a detection means for detecting the problem based on the log information of the person; The information processing device according to claim 1 .

3. the first generation means generates a question regarding a cause of the problem in accordance with the detection result of the problem, and generates the hypothesis and evidence based on the generated question and the integrated data. The information processing device according to claim 2 .

4. The detection means detects the problem based on the KGI for human capital management. The information processing device according to claim 2 .

5. The detection means determines a KPI related to the KGI based on the log information of the person, and detects the problem. The information processing device according to claim 4 .

6. a second generation means for generating a personnel policy plan for the problem based on the hypothesis and grounds; The information processing device according to claim 1 .

7. The person's log information in cyberspace includes the person's system usage log, the log information in the physical space of the person includes any one of vital information of the person, emotional information of the person, and an activity log of the person; The human resource information of the person includes any one of attribute information of the person, achievement information of the person, and awareness information of the person. The information processing device according to claim 1 .

8. a first acquisition means for acquiring log information of a person in cyberspace and physical space; a second acquiring means for acquiring human resource information of the person; a storage means for storing integrated data linking the person's log information with the person's human resource information; a first generating means for generating hypotheses and evidence for problems related to human capital management based on the integrated data and outputting the generated hypotheses and evidence; An information processing system comprising:

9. Acquires log information of a person in cyberspace and physical space, obtaining human resource information for said person; storing integrated data linking the person's log information with the person's human resource information; generating hypotheses and evidence for issues related to human capital management based on the integrated data, and outputting the generated hypotheses and evidence; Information processing methods.

10. Acquires log information of a person in cyberspace and physical space, obtaining human resource information for said person; storing integrated data linking the person's log information with the person's human resource information; generating hypotheses and evidence for issues related to human capital management based on the integrated data, and outputting the generated hypotheses and evidence; A program that causes a computer to execute a process.

Images