JP7854672B2 - Engagement estimation method, program, and engagement estimation system - Google Patents

Description

This disclosure generally relates to engagement estimation methods, programs, and engagement estimation systems, and more particularly to engagement estimation methods, programs, and engagement estimation systems for estimating worker engagement with their work.

A known indicator related to workers' work is engagement (also called work engagement or employee engagement). According to Non-Patent Document 1, engagement is defined by the following two points: (1) commitment to the organization, specifically emotional commitment (emotional attachment to the organization) and continued commitment (desire to remain with the organization); and (2) extra-role behavior (any behavior that enables the organization to function effectively).

Increasing employee engagement can lead to improvements in productivity, sales, customer satisfaction, and employee retention within the organization, for example.

Traditionally, employee engagement has been quantified by conducting surveys of workers and analyzing their responses (for example, Patent Document 1).

However, responses to surveys are not always objective data. Therefore, to improve the reliability of engagement estimations, the development of more objective engagement estimation methods is desirable.

Japanese Patent Publication No. 2018-185680

Arnold B. Bakker and Michael P. Reiter (eds.), "Work Engagement: A Handbook of Basic Theory and Research," Seiwa Shoten, 2014, p. 23.

This disclosure aims to provide an engagement estimation method, program, and system that can estimate engagement more objectively.

An engagement estimation method according to one aspect of the present disclosure is an engagement estimation method in an engagement estimation system. The engagement estimation method comprises a first acquisition step, a second acquisition step, a feature determination step, and an estimation step. In the first acquisition step, a first acquisition unit acquires information about a worker. In the second acquisition step, a second acquisition unit acquires the worker's engagement with work over a predetermined period. In the feature determination step, a feature determination unit determines at least one feature from the worker's information based on the coefficient of determination of a regression equation obtained using the worker's information as an explanatory variable and the engagement over the predetermined period as the dependent variable . In the estimation step, an estimation unit substitutes the at least one feature into the regression equation to estimate the worker's engagement at a point in time different from the predetermined period. The worker's information includes the worker's biometric information, the worker's location information at the worker's workplace, and relationship information relating to the relationship between the worker and other workers in the workplace. The aforementioned biological information is measured by a biological information measurement terminal .

A program according to one aspect of this disclosure is a program for causing one or more processors of a computer system to execute the engagement estimation method.

An engagement estimation system according to one aspect of this disclosure comprises a first acquisition unit, a second acquisition unit, a feature determination unit, and an estimation unit. The first acquisition unit acquires information about a worker. The second acquisition unit acquires the worker's engagement with their work over a predetermined period. The feature determination unit determines at least one feature from the worker's information based on the coefficient of determination of a regression equation obtained using the worker's information as an explanatory variable and the engagement over the predetermined period as the dependent variable . The estimation unit substitutes the at least one feature into the regression equation to estimate the worker's engagement at a point in time different from the predetermined period. The worker's information includes the worker's biometric information, the worker's location information at their workplace, and relationship information relating to the relationship between the worker and other workers in the workplace. The biometric information is measured by a biometric information measurement terminal .

Figure 1 is a block diagram of an engagement estimation system and related configuration according to one embodiment. Figure 2 is a graph illustrating one process in the engagement estimation system described above. Figure 3 is an explanatory diagram illustrating the engagement estimation process using the same engagement estimation system as described above.

(Embodiment)
The following describes the engagement estimation method, program, and engagement estimation system 1 according to the embodiments, with reference to the drawings. However, the embodiments described below are only one of many embodiments of this disclosure. The embodiments described below can be modified in various ways depending on the design, etc., as long as the objectives of this disclosure are achieved.

(overview)
Figure 1 schematically shows the configuration of the engagement estimation system 1 of this embodiment. The engagement estimation system 1 is used to estimate the engagement of workers. In this disclosure, "worker" refers to all persons who perform work. In this disclosure, "worker" differs from the general meaning of "worker" in that it includes not only those who receive compensation for their work but also those who work without compensation. However, in the following, we will describe the case in which the engagement of those who receive compensation for their work is estimated as a representative example. Therefore, the engagement estimation system 1 is used, for example, in companies, government offices, or organizations. In the following, we will describe the case in which the engagement estimation system 1 is used in a company as a representative example.

As shown in Figure 1, the engagement estimation system 1 of this embodiment comprises a first acquisition unit 21, a second acquisition unit 22, a feature determination unit 23, and an estimation unit 24. The first acquisition unit 21 acquires worker information. The second acquisition unit 22 acquires the worker's engagement to work over a predetermined period. The feature determination unit 23 determines at least one feature from the worker information based on the relationship between the worker information and the engagement over the predetermined period. The estimation unit 24 estimates the worker's engagement at a point in time other than the predetermined period based on at least one feature. The worker information includes the worker's biometric information, the worker's location information at the worker's workplace, and relationship information regarding the relationship between the worker and other workers in the workplace. The biometric information is measured by a biometric information measurement terminal 3.

According to this embodiment, compared to estimating engagement based solely on questionnaire responses, using workers' biometric information, location information, and relationship information allows for a more objective estimation of engagement. Furthermore, using workers' biometric information, location information, and relationship information makes it possible to reduce the number of questionnaire items or even estimate engagement without conducting a questionnaire. Therefore, the burden on those answering the questionnaire (workers, etc.) can be reduced. Additionally, using the engagement estimation system 1 allows for an increased frequency of engagement estimation.

Furthermore, functions similar to those of the Engagement Estimation System 1 can be realized in the Engagement Estimation Method. The Engagement Estimation Method of this embodiment is the Engagement Estimation Method in the Engagement Estimation System 1. The Engagement Estimation Method comprises a first acquisition step, a second acquisition step, a feature determination step, and an estimation step. In the first acquisition step, the first acquisition unit 21 acquires worker information. In the second acquisition step, the second acquisition unit 22 acquires the worker's engagement to the job over a predetermined period. In the feature determination step, the feature determination unit 23 determines at least one feature from the worker's information based on the relationship between the worker's information and the engagement over the predetermined period. In the estimation step, the estimation unit 24 estimates the worker's engagement at a point in time different from the predetermined period based on at least one feature. The worker's information includes the worker's biometric information, the worker's location information at the worker's workplace, and relationship information regarding the relationship between the worker and other workers in the workplace. Biological information is measured by the biological information measurement terminal 3.

Furthermore, the engagement estimation method can be implemented in a program. The program in this embodiment is a program that causes one or more processors in a computer system to execute the engagement estimation method. The program may be recorded on a non-temporary recording medium readable by the computer system.

(detail)
(1) Overall Structure The engagement estimation system 1 and its related components will be described in more detail below.

In this embodiment, there are multiple workers. The engagement estimation system 1 estimates the engagement of each of the multiple workers.

The engagement estimation system 1 is used, for example, in conjunction with a biometric information measurement terminal 3, a location measurement system 4, a data server 5, an operation terminal 6, an information processing server 7, a PC (personal computer) 8, an attendance management system 9, and an exercise measurement terminal 10.

(2) Biometric Information Measurement Terminal The biometric information measurement terminal 3 measures the biometric information of each of the multiple workers. The biometric information includes, for example, at least one of heart rate, blood pressure, skin temperature, sweat amount, and voice information. Multiple types of biometric information (for example, heart rate and blood pressure) may be measured by one biometric information measurement terminal 3. Alternatively, there may be multiple biometric information measurement terminals 3, and each of the multiple biometric information measurement terminals 3 may measure different types of biometric information.

The biometric information measurement terminal 3 is, for example, a wearable device worn by a worker. The wearable device is equipped with, for example, an optical heart rate sensor, which measures the worker's heart rate and blood pressure. The wearable device is also equipped with, for example, a temperature sensor, which measures the worker's skin temperature. Furthermore, the wearable device is also equipped with, for example, a sweat sensor, which measures the amount of sweat the worker produces.

As another example, the biometric information measurement terminal 3, for instance, uses a camera (such as a near-infrared camera) to capture images of the worker over a certain period of time to generate image data, and then measures the worker's heart rate based on the image data.

As another example, the biometric information measurement terminal 3 is, for example, a blood pressure monitor with a cuff, which measures the worker's blood pressure while the cuff is wrapped around the worker's arm.

As another example, the biometric information measurement terminal 3 may be equipped with a microphone, which converts the worker's voice into audio information in the form of electrical signals. The microphone may also be provided on a wearable device.

(3) Location measurement system The location measurement system 4 measures the location information of each of the multiple workers. The location information includes, for example, the coordinate information of each of the multiple workers.

For example, each of the multiple workers carries a mobile device such as a smartphone or wearable device. Multiple beacon devices are installed at the workplace of the multiple workers (e.g., an office building, a store, or a factory).

The following section describes an example of measuring the location information of one worker out of several. The location information of other workers can also be measured in a similar manner.

Each of the multiple beacon devices emits a beacon signal. The mobile terminal carried by the worker measures the received signal strength of the beacon signal. The received signal strength information is transmitted from the mobile terminal to the location measurement system 4. Based on the received signal strength, the location measurement system 4 calculates the distance between the mobile terminal and each of the multiple beacon devices. Furthermore, based on the distance between the mobile terminal and each of the multiple beacon devices, and the location information of each of the multiple beacon devices, the location measurement system 4 measures the location information of the mobile terminal using tripoint positioning. The location measurement system 4 transmits the location information of the mobile terminal to the engagement estimation system 1 as the location information of the worker carrying the mobile terminal.

Furthermore, the mobile device that receives the beacon signal (for example, a wearable device) may also serve as the biometric information measurement terminal 3.

(4) Data Server The data server 5 stores relationship information. Relationship information is information about the relationships between multiple workers in the workplace (company, government office, or organization, etc.) of multiple workers. More specifically, relationship information includes, for example, information about the hierarchical relationships between multiple workers. Information about the hierarchical relationships between multiple workers includes, for example, information about the job title of each of the multiple workers. Job title refers to the position in the workplace. Job title is a position or rank, etc. Relationship information also includes, for example, organizational information about the organization (department or division, etc.) to which each of the multiple workers belongs. Departments or divisions are distinguished by names such as XX Department, XX Section, or XX Center. Relationship information also includes, for example, work information about the work (projects, etc.) that each of the multiple workers is involved in.

Furthermore, data server 5 stores area information. This area information includes, for example, map information of the workplaces of multiple workers. It also includes, for example, information on the location of each room and the purpose of each room.

(5) Operating terminal The operating terminal 6 is, for example, a personal computer or a mobile terminal. The mobile terminal is, for example, a mobile phone such as a smartphone, a wearable device, or a tablet device.

The operation terminal 6 generates worker declaration information related to work in response to human operation. To generate worker declaration information using the operation terminal 6, the worker themselves may operate the operation terminal 6, or another person may operate the operation terminal 6.

The operating terminal 6 includes, for example, a touch panel display, which displays questionnaire items. The person answers the questionnaire items by operating the touch panel display. The operating terminal 6 then generates declaration information that includes the answers obtained from the person.

People, for example, select an answer from multiple options in response to a question presented as part of a survey. These options might include five choices: "Agree," "Somewhat agree," "Neither agree nor disagree," "Somewhat disagree," and "Disagree."

The survey items include, for example, questions for estimating engagement over a predetermined period on the information processing server 7. Such questions will be referred to as "first questions" below, and the answers to first questions will be referred to as "first answers" below. First questions are, for example, questions that inquire about the worker's thoughts and feelings regarding their workplace, job content, and colleagues.

Furthermore, the questionnaire items include, for example, questions for estimating engagement at a point in time other than a predetermined period using the engagement estimation system 1. Such questions will be referred to as "second questions" below, and the answers to the second questions will be referred to as "second answers" below. At least one of the second questions may be the same as the first question.

(6) Information Processing Server The information processing server 7 estimates the engagement of workers over a predetermined period. More specifically, the information processing server 7 first obtains declared information from the operation terminal 6. The declared information includes at least one first response. Based on at least one first response, the information processing server 7 estimates the engagement of workers over a predetermined period.

As a method for estimating engagement by the information processing server 7, a known method such as that disclosed in Patent Document 1 can be employed. For example, a score for the first answer is determined based on which of several options the employee selected as their first answer. The information processing server 7 estimates the employee's engagement over a predetermined period by summing the scores for each of the multiple first answers.

(7) PC
Workers use PCs (Personal Computers) 8 for their work. More specifically, multiple workers are assigned, for example, one or more PCs 8 by their workplace. Each of the multiple workers uses one or more PCs 8 assigned to them.

PC8 is equipped with a storage device that stores its usage history. The storage device is a hard disk drive (HDD) or solid-state drive (SSD), etc. Software for acquiring and storing PC8's usage history in the storage device may be installed on PC8.

PC8 is an example of a computer system used by workers for their work. A computer system includes one or more computers. The computer system used by workers for their work is not limited to PC8; for example, it could be a mobile phone such as a smartphone, a tablet device, or a host computer. Furthermore, the computer system used by workers for their work could be, for example, a computer system for operating an object such as a vehicle or machine tool, and the usage history may include the operation history of the object being operated.

(8) Attendance Management System The attendance management system 9 generates attendance information for each of the multiple workers. For example, each of the multiple workers carries a mobile terminal (smartphone or wearable device, etc.) or a reading device such as an IC card, and holds the reading device over the reader of the attendance management system 9 when arriving at and leaving work. The attendance management system 9 then reads the identification information stored in the reading device from the reading device. As a result, the attendance management system 9 generates attendance information for each of the multiple workers, and the attendance information includes information on arrival time and departure time.

(9) Exercise Measurement Terminal The exercise measurement terminal 10 obtains the exercise index of the worker. The exercise index represents at least one of the quality and quantity of exercise. The exercise index includes, for example, activity level and movement level. Activity level is expressed, for example, in METs (Metabolic equivalents). Movement level is, for example, the number of steps.

The exercise measurement terminal 10 is, for example, a wearable device. The worker carries the wearable device. The wearable device is equipped with, for example, a pedometer and measures the worker's steps. The wearable device also measures, for example, the worker's biometric information (heart rate, blood pressure, skin temperature, or sweating amount, etc.) as described above. Based on the biometric information, the wearable device determines the worker's activity level.

(10) Engagement estimation system The engagement estimation system 1 comprises a processing unit 2, a storage unit 11, and a communication unit 12.

The storage unit 11 is a storage device composed of a hard disk drive (HDD) or a solid-state drive (SSD), etc. The storage unit 11 stores information. The storage unit 11 stores information acquired from external devices, such as biological information acquired from the biological information measurement terminal 3, location information acquired from the location measurement system 4, and relationship information acquired from the data server 5.

The communication unit 12 includes a communication interface device. The communication unit 12 can communicate with external devices (for example, a biometric information measurement terminal 3, a location measurement system 4, and a data server 5) via the communication interface device. In this disclosure, "communication possible" means that signals can be sent and received directly or indirectly via a network or repeater, etc., by an appropriate communication method such as wired communication or wireless communication.

The processing unit 2 includes a computer system having one or more processors and memory. The functions of the processing unit 2 are realized when the processor of the computer system executes a program stored in the computer system's memory. The program may be stored in memory, provided via telecommunication lines such as the Internet, or provided on a non-temporary recording medium such as a memory card.

The processing unit 2 includes a first acquisition unit 21, a second acquisition unit 22, a feature quantity determination unit 23, an estimation unit 24, a presentation content generation unit 25, and a communication processing unit 26. Note that these merely represent the functions implemented by the processing unit 2 and do not necessarily represent an actual physical configuration.

(10.1) First acquisition unit The first acquisition unit 21 acquires worker information (information for each of multiple workers) via the communication unit 12. The worker information includes the worker's biometric information measured by the biometric information measurement terminal 3, the worker's location information measured by the location measurement system 4, and relationship information stored in the data server 5.

Furthermore, the worker information also includes declared information generated by the operation terminal 6. The declared information is information related to work and is generated in response to operations on the operation terminal 6. The declared information may be, for example, one or both of the first and second responses described above.

Furthermore, the worker information includes the usage history of the computer system used by the worker for their work. In this embodiment, the computer system is PC8. That is, the worker information includes the usage history of PC8.

Furthermore, the worker information includes worker attendance information. Worker attendance information is generated by the attendance management system 9.

Furthermore, the worker information also includes the worker's exercise indicators. The worker's exercise indicators are generated by the exercise measurement terminal 10.

(10.2) Second acquisition unit The second acquisition unit 22 acquires the worker engagement for a predetermined period, which is estimated by the information processing server 7.

(10.3) Feature determination unit The feature determination unit 23 determines at least one feature from the worker information based on the relationship between the worker information and engagement over a predetermined period. For example, the feature determination unit 23 extracts multiple parameters from the worker information. These multiple parameters may include, for example, the conversation time between the worker and a specific person, the worker's activity level, and the worker's overtime hours.

A parameter may correspond to certain information about a worker. In other words, worker information can be used directly as a parameter. For example, a worker's overtime hours are one example of worker information. A worker's overtime hours can be used as a parameter.

Alternatively, a parameter may be determined based on certain information about the worker. In other words, worker information may be processed and used as a parameter. For example, the worker's location information measured by the location measurement system 4 and the relationship information stored in the data server 5 are examples of worker information. Based on these, the conversation time between a worker and a specific person may be determined as a parameter. More specifically, the (face-to-face) conversation time between a worker and their supervisor can be determined, for example, from the location information of both the worker and the supervisor. That is, the time during which the distance between the worker and the supervisor is within a predetermined distance (e.g., 1 meter) can be used as the conversation time between the worker and the supervisor. Furthermore, whether or not a worker is a supervisor can be identified based on the relationship information.

The feature determination unit 23 may determine at least one feature for each individual worker. That is, in order to determine at least one feature corresponding to a particular worker, information about that worker and the worker's engagement over a predetermined period may be referenced.

Alternatively, the feature determination unit 23 may determine at least one feature common to two or more workers. That is, in order to determine at least one feature corresponding to two or more workers, the information of each of those two or more workers and their engagement over a predetermined period may be referenced.

The feature determination unit 23 selects a parameter from among several parameters that has a strong correlation with engagement over a predetermined period as a feature. The feature determination unit 23 calculates the strength of the correlation, for example, by multiple regression analysis. That is, the feature determination unit 23 uses engagement over a predetermined period as the dependent variable and several parameters over a predetermined period as several independent variables to obtain a multiple regression equation, and then calculates the coefficient of determination of the multiple regression equation. The coefficient of determination is a value between 0 and 1. The larger the coefficient of determination, the stronger the correlation. For example, the feature determination unit 23 selects several independent variables when the coefficient of determination is greater than a threshold as several features. Alternatively, the feature determination unit 23 may obtain a simple regression equation instead of a multiple regression equation and calculate the strength of the correlation (coefficient of determination) from the simple regression equation. In short, the feature determination unit 23 only needs to determine the correlation between at least one feature and engagement by regression analysis or the like.

Figure 2 illustrates an example of a simple linear regression equation (line L1) obtained by using engagement over a specified period as the dependent variable and one parameter over a specified period as the independent variable. Specifically, the independent variable is the number of conversations with the second-level supervisor (the immediate supervisor's immediate supervisor). Both the dependent and independent variables are determined at multiple time points. In Figure 2, the pairs of dependent and independent variables for each time point are plotted as points. The simple linear regression equation is derived based on these multiple points.

When determining at least one feature corresponding to a specific worker, Figure 2 is a plot of the data (pair of dependent and independent variables) for that specific worker. Similarly, when determining at least one feature common to two or more workers, Figure 2 is a plot of the data (pair of dependent and independent variables) for each of those two or more workers.

Furthermore, when the predetermined period includes a first time point and a second time point, the feature determination unit 23 may determine at least one feature based on the difference between the engagement at the first time point and the engagement at the second time point. In other words, the feature determination unit 23 may determine at least one feature based on the change in engagement. For example, the feature determination unit 23 may obtain a multiple regression equation with multiple parameters as multiple explanatory variables and the change in engagement as the dependent variable, and then select the parameter among the multiple parameters that has a strong correlation with the change in engagement as the feature.

Furthermore, the feature determination unit 23 may use the difference between a predetermined parameter and a baseline value as the explanatory variable. The baseline value may be, for example, the average value of the predetermined parameter over a specific period. For example, the predetermined parameter may be the activity level of workers during a predetermined period. In this case, the baseline value may be, for example, the average activity level of the workers during the same period in the year prior to the predetermined period. Alternatively, the baseline value may be, for example, the average activity level of the workers from a predetermined number of days (for example, 6 months) before the predetermined period up to the predetermined period. By taking the difference between the predetermined parameter and the baseline value, the possibility that differences in baseline values for each worker will affect the engagement estimation results can be reduced.

(10.4) Estimation Unit The estimation unit 24 performs an estimation step. That is, the estimation unit 24 estimates the worker's engagement at a point in time other than the predetermined period (here, as an example, the most recent point in time) based on at least one feature determined by the feature determination unit 23. For example, suppose that the feature determination unit 23 has determined two parameters as features: the conversation time between the worker and their second supervisor, and the worker's overtime hours. In this case, the estimation unit 24 obtains the most recent engagement that reflects the parameters from the previous month by substituting the two parameters from the previous month into a multiple regression equation (obtained by the feature determination unit 23) in which each of the two parameters is an explanatory variable and engagement is the dependent variable.

Furthermore, if parameters are obtained at multiple points in time during a period other than the specified period, the engagement may be calculated by substituting the mean value of the parameters at multiple points in time into the multiple regression equation. Alternatively, multiple engagements may be calculated by substituting each of the parameters at multiple points in time into the multiple regression equation. In addition, a simple linear regression equation may be used instead of a multiple regression equation.

(10.5) Content Generation Unit The content generation unit 25 performs the content generation step. That is, the content generation unit 25 generates content to be presented to the viewer based on the estimation result of the estimation step by the estimation unit 24. The content presented to the viewer includes, for example, a numerical value representing the engagement obtained in the estimation step. The viewer may be the worker who is the subject of the engagement request, or another person (for example, the worker's supervisor).

The content generation unit 25 generates, for example, a list of the engagement of multiple workers for each survey period (for example, every month), as content to be presented to the viewer.

Furthermore, the content generation unit 25 generates, for example, a list of a worker's engagement for each survey period, as content to be presented to that worker.

(10.6) Communication Processing Unit The communication processing unit 26 controls the transmission and reception of information by the communication unit 12. The communication processing unit 26 executes the transmission step by controlling the communication unit 12. The transmission step is the step of sending the content generated in the presentation content generation step to a terminal. The terminal is, for example, a PC 8. The terminal is equipped with a display that displays the received content. The viewer views the content generated in the presentation content generation step via the terminal's display.

For example, in the transmission step, the content generated in the presentation content generation step is sent to the terminal at regular intervals. These regular intervals could be, for example, one week, two weeks, one month, or two months.

(11) Specific Examples Below, we will describe specific examples of engagement estimation using the Engagement Estimation System 1 with reference to Figure 3.

Worker information, including biometric data, location information, and relationship information, is collected periodically or irregularly through measurements and questionnaires to workers. This worker information is then compiled monthly. For example, Figure 3 shows the compilation of worker information for January, worker information for February, and so on.

Furthermore, the information processing server 7 estimates engagement based on the first response included in the declared information. Here, a survey is conducted with workers every month, and a first response is obtained as a response to the survey. The information processing server 7 then estimates the engagement for each month based on the first response. For example, in Figure 3, the information processing server 7 estimates the engagement for January based on the first response in January, the engagement for February based on the first response in February, and the engagement for March based on the first response in March.

Once a certain amount of engagement data estimated by the information processing server 7 has been accumulated, engagement estimation becomes possible using the engagement estimation system 1. In Figure 3, engagement estimation by the engagement estimation system 1 begins after three months' worth of engagement data estimated by the information processing server 7 has been accumulated. Hereafter, the engagement data estimated by the information processing server 7 will be referred to as "reference engagement data".

The engagement estimation system 1 first determines the multiple regression equation and features in order to estimate engagement. For example, when estimating engagement in April (the target period), the engagement estimation system 1 refers to worker information and reference engagement data for periods other than April (the target period). In Figure 3, the engagement estimation system 1 refers to worker information and reference engagement data for January to March. Based on this, the engagement estimation system 1 determines the multiple regression equation and features. More specifically, the engagement estimation system 1 uses engagement from January to March (a predetermined period) as the dependent variable and multiple parameters extracted from worker information for January to March (a predetermined period) as multiple independent variables to obtain a multiple regression equation, and then uses multiple independent variables for which the coefficient of determination of the multiple regression equation is greater than a threshold as multiple features.

Next, the engagement estimation system 1 estimates the engagement for April (the target period) from the multiple regression equation and the features. More specifically, the engagement estimation system 1 calculates the engagement for April (the target period) by substituting the features obtained from the worker information for April (the target period) into the multiple regression equation.

Next, the engagement estimation system 1 generates content to present to the viewer based on the calculated engagement and sends the content to the terminal (PC 8). For example, the engagement estimation system 1 generates content every month and sends the content to the terminal.

By following the same procedure as in April, it is possible to estimate engagement at points in time after April. For example, by substituting the features obtained from the worker information in May into a multiple regression equation, it is possible to determine engagement in May. In this case, it is not necessary to recalculate the multiple regression equation; the same multiple regression equation obtained when calculating engagement in April can be used.

Conducting a survey to obtain initial responses after April is not mandatory. If a survey to obtain initial responses is not conducted after April, the burden on respondents (workers, etc.) will be reduced, as they will no longer need to dedicate time to completing the survey. Furthermore, regardless of whether or not a survey to obtain initial responses is conducted after April, engagement after April will be estimated after verifying the correlation between engagement and information other than the initial responses (such as workers' location information). Therefore, Engagement Estimation System 1 can estimate engagement more objectively.

The process of determining the multiple regression equation and features does not need to be performed every time the engagement estimation system 1 estimates engagement; it only needs to be performed once (i.e., only when estimating engagement in April).

Alternatively, the process of determining (updating) the multiple regression equation and features may be performed at intervals longer than the engagement estimation interval (1 month) by the engagement estimation system 1 (for example, every 6 months). In this case as well, there is the advantage of reducing the burden, for example, by reducing the frequency of conducting questionnaires to obtain first responses.

For the Engagement Estimation System 1 to estimate engagement during a target period (for example, April), it is not essential for the system to collect information other than features from the worker information for that period. For example, suppose the conversation time between the worker and their secondary supervisor and the worker's overtime hours are determined as features by the Feature Determination Unit 23. In this case, it is not essential for the Engagement Estimation System 1 to collect information other than features from the worker information for that period (for example, the worker's activity level).

Furthermore, in order to estimate engagement in April (the target period), the engagement estimation system 1 may determine the multiple regression equation and features by referring to worker information and reference engagement data from a period later than April (for example, May to June).

(12) Details of Features Features may be related to, for example, "job resources,""individualresources," or "job requirements" as defined in the "job requirements-resource model," i.e., the "JD-R model." Features may also be related to empathy or acceptance of at least one of the vision, mission, and philosophy of the group (company, etc.) to which the worker belongs for work. Alternatively, features may be related to two or more of the above.

For example, "work resources" relate to at least one of the following: "support from others," "relationships with others," "autonomy in work," "coaching from colleagues," "feedback from colleagues," "diversity in relationships," and "opportunities for career development."

For example, "personal resources" relate to at least one of the following: "optimism," "resilience," and "recovery ability."

For example, "job requirements" relate to at least one of the following: "quantitative workload," "qualitative workload," and "physical workload."

As described above, the feature determination unit 23 extracts multiple parameters from, for example, worker information and uses at least one of them as a feature. The parameters (features) are, for example, the conversation time between the worker and a specific person, the worker's activity level, and the worker's overtime hours. The at least one feature determined by the feature determination unit 23 is not particularly limited. Therefore, the feature determination unit 23 may, for example, use only the parameters extracted from biometric information as features, or only the parameters extracted from declared information as features, or a combination of the parameters extracted from biometric information and the parameters extracted from declared information as features.

The following are examples of features. However, features are not limited to those listed below.

(12.1) Work Resources The conversation time between a worker and a specific person, as a feature, is related to "support from the surroundings" and "relationships with the surroundings" in "work resources". The conversation time between a worker and a specific person (face-to-face) can be determined, for example, from the location information and voice information of each of multiple workers. That is, the conversation time between a worker and a specific person can be defined as the time during which voice information is being output from microphones present around the conversation area, provided that the distance between the worker and the specific person is within a predetermined distance (e.g., 1 meter). The microphone may, for example, be carried by the worker or installed near the worker's workplace.

Furthermore, the duration of a (face-to-face) conversation between a worker and a specific person can also be determined, for example, solely from the location information of each individual worker. That is, the conversation time can be determined by conveniently assuming that the workers and the specific person are in close proximity to each other for the purpose of conversation. For example, the time during which the distance between the worker and the specific person is within a predetermined distance can be considered the conversation time between the worker and the specific person.

Furthermore, the conversation time between a worker and a specific person is not limited to face-to-face conversation time, but may also include non-face-to-face (e.g., online) conversation time. Online conversation time can be extracted, for example, from the usage history of PC8.

Furthermore, separate requirements may be set for the amount of time spent in face-to-face conversations between workers and specific individuals, as well as for the amount of time spent in non-face-to-face conversations.

Furthermore, the conversation time between a worker and a specific person may be extracted from the declared information entered into the operating terminal 6. In other words, the engagement estimation system 1 may obtain the conversation time between a worker and a specific person based on declarations from the respondent (worker, etc.).

Furthermore, as mentioned above, the relationship information is information about the relationships between the multiple workers in the workplace. The feature determination unit 23 may determine the conversation time of the multiple workers for each relationship based on the relationship information. In other words, the feature determination unit 23 may determine the conversation time between a worker and a worker in a specific position. For example, the feature determination unit 23 may determine the conversation time between a worker and their superior, the conversation time between a worker and their subordinate, and the conversation time between workers who hold the same position. The relationships may also be further subdivided. For example, the feature determination unit 23 may determine the conversation time between a worker and their primary superior (immediate supervisor), and the conversation time between a worker and their secondary superior (the immediate supervisor's immediate supervisor). Also, for example, the feature determination unit 23 may determine the conversation time between workers who belong to the same organization (department, etc.), or the conversation time between workers who belong to different organizations (departments, etc.). Alternatively, for example, the feature determination unit 23 may determine the conversation time between workers who are assigned the same tasks (projects, etc.).

Furthermore, the number of conversations between a worker and a specific person may be determined as a feature. The number of face-to-face conversations can be determined, for example, from the location information of multiple workers. That is, the number of times the distance between a worker and a specific person changes from beyond a predetermined distance (e.g., 1 meter) to within that predetermined distance can be used as the number of conversations between the worker and the specific person.

As features, the overtime hours, number of overtime shifts, night shift hours, and holiday shift hours of workers are related to the "discretionary power in work" as a "work resource." These are extracted, for example, from attendance information output from the attendance management system 9, or from declared information entered into the operation terminal 6. Alternatively, these can be determined, for example, from the start and end times of PC 8, extracted from the usage history of PC 8.

As a feature, the mood at the end of the workday is related to "work resources," specifically "coaching from colleagues" and "feedback from colleagues." The mood at the end of the workday is extracted, for example, from the declared information entered into the operation terminal 6.

The number of communications within a department and the number of people communicating within a department, as features, are related to "relationship diversity" in "work resources." The number of face-to-face communications within a department and the number of people communicating face-to-face within a department can be obtained, for example, from the location information of each of multiple workers, or from location information and voice information, or from the declared information entered into the operation terminal 6. The number of non-face-to-face (e.g., online) communications within a department and the number of people communicating non-face-to-face within a department can be extracted, for example, from the usage history of PC 8, or from the declared information entered into the operation terminal 6.

The number of spaces used and the number of times specialized tools were used, as features, are related to "career development opportunities" within "work resources." The number of spaces used and the number of times specialized tools were used can be obtained, for example, from the worker's location information, or extracted from the usage history of PC 8, or from the declared information entered into the operating terminal 6.

(12.2) Personal Resources The change in mood between morning and evening, as a feature, is related to "optimism" in "personal resources". The change in mood between morning and evening is extracted, for example, from the declared information entered into the operating terminal 6.

The features of break time, time spent without PC input, and number of times PC input was not performed (the number of times the input state continued for a predetermined period of time or longer) are related to "resilience" as a "personal resource." Break time, time spent without PC input, and number of times PC input was not performed are extracted, for example, from the usage history of PC 8 or from the declared information entered into the operation terminal 6.

As a feature, the amount of movement within the office is related to "resilience" as a "personal resource." The amount of movement within the office can be determined, for example, from the worker's location information, or measured by a pedometer (exercise measurement terminal 10) carried by the worker.

The PC usage time and number of times the PC is used, as features, before the start of work, after the end of work, during late-night hours, and on holidays, are related to the "recovery status" of "individual resources." The PC usage time and number of times the PC is used before the start of work, after the end of work, during late-night hours, and on holidays are extracted, for example, from the usage history of PC 8, attendance information output from the attendance management system 9, or declaration information entered into the operation terminal 6.

The work interval (the length of time from the end of work on a given day to the start of work on the following day), as a feature, is related to the "recovery status" of "individual resources." The work interval is extracted, for example, from the usage history of PC 8, attendance information output from the attendance management system 9, or declaration information entered into the operation terminal 6.

The volume of the worker's voice, as a feature, is related to the "recovery status" of "individual resources." The volume of the worker's voice is measured, for example, by a microphone equipped on the biometric information measurement terminal 3.

(12.3) Degree of Work Demand As a feature, working hours (the length of time from the time of entering the workplace to the time of leaving) is related to the "quantitative burden of work" in the "degree of work demand". Working hours can be obtained, for example, from the worker's location information or attendance information output from the attendance management system 9.

As a feature, PC usage time after the end of the workday is related to the "quantitative burden of work" in the "level of work requirements." PC usage time after the end of the workday can be extracted, for example, from the usage history of PC8.

The features of rest area usage time and rest area usage frequency are related to the "quantitative workload" of "work demands." Rest area usage time and rest area usage frequency are obtained, for example, from a combination of worker location information and area information related to rest areas. Area information is obtained, for example, from data server 5.

The features that indicate no PC input between the start and end of the workday, and the number of times (the number of times the input state continued for a predetermined period of time or longer), are related to the "quantitative burden of work" in the "level of work requirement." The time and number of times no PC input between the start and end of the workday can be extracted, for example, from the usage history of PC 8.

As a feature, the amount of conversation in the workplace is related to the "quantitative burden of work" in the "level of job requirements." The amount of conversation in the workplace can be determined, for example, from the output (voice information) of the microphone equipped on the biometric information measurement terminal 3.

The features, namely the number of keyboard operations per unit time and the amount of mouse cursor movement per unit time, are related to the "qualitative burden of work" under "work requirements." The number of keyboard operations per unit time and the amount of mouse cursor movement per unit time are extracted, for example, from the usage history of PC8.

As a feature, PC operation time is related to the "qualitative burden of work" and the "level of work requirements." PC operation time is extracted, for example, from the usage history of PC8.

As a feature, the time spent on tasks with a high qualitative burden is related to the "qualitative burden of the work" in the "level of work requirements." The time spent on tasks with a high qualitative burden can be determined, for example, from biometric information measured by the biometric information measurement terminal 3. Specifically, the engagement estimation system 1 assumes that a state where the heart rate, as biometric information, is greater than a corresponding threshold is a state of high qualitative burden, and calculates the cumulative time of this state as the time spent on tasks with a high qualitative burden.

As a feature, the worker's activity level is related to the "physical burden of work" in the "job requirements." The worker's activity level is expressed, for example, in METs. The worker's activity level is determined, for example, from biometric information (heart rate, blood pressure, skin temperature, or sweating) measured by the biometric information measurement terminal 3.

As a feature, the number of steps taken by a worker is related to the "physical burden at work" in the "level of job requirements." The number of steps taken by a worker can be determined, for example, from the worker's location information. Alternatively, the number of steps taken by a worker can be measured, for example, by a pedometer (exercise measurement terminal 10) carried by the worker.

As a feature, the worker's maximum heart rate is related to the "physical burden of work" within the "job requirements." The worker's maximum heart rate can be extracted, for example, from heart rate measurement data as biometric information.

(12.4) Empathy with the Philosophy The features related to the empathy with the philosophy (empathy or acceptance of at least one of the vision, mission, and philosophy of the group to which a worker belongs for work) are extracted, for example, from the declared information entered into the operating terminal 6. The features related to the empathy with the philosophy are, for example, indicators that show how well the worker understands the meaning of their work.

(13) Modifications of the Embodiments The following are modifications of the embodiments. The following modifications may be implemented by combining them as appropriate.

The engagement estimation system 1 may include a display device that displays the information generated in the presentation content generation step.

The engagement estimation system 1 includes an operation unit that accepts operations for generating declared information, and may also serve as an operation terminal 6.

The feature determination unit 23 may refer to the correlation coefficient instead of the coefficient of determination in order to determine the strength of the correlation between multiple parameters and engagement over a predetermined period.

In the embodiment described above, the estimation unit 24 performs a regression step to obtain a regression equation that represents the relationship between at least one feature and engagement over a predetermined period. In this disclosure, the process of "obtaining a regression equation" may be a process in which the estimation unit 24 obtains a regression equation obtained by an external configuration of the engagement estimation system 1 from the external configuration, or it may be a process in which the estimation unit 24 obtains a regression equation stored in the storage unit 11 of the engagement estimation system 1. Alternatively, the process of "obtaining a regression equation" may be a process of determining a regression equation.

The entity that executes the engagement estimation system 1 or engagement estimation method in this disclosure includes a computer system. The computer system mainly consists of a processor and memory as hardware. At least a part of the functions of the entity that executes the engagement estimation system 1 or engagement estimation method in this disclosure is realized by the processor executing a program recorded in the memory of the computer system. The program may be pre-recorded in the memory of the computer system, provided via a telecommunications line, or provided on a non-temporary recording medium such as a memory card, optical disk, or hard disk drive that can be read by the computer system. The processor of the computer system is composed of one or more electronic circuits including semiconductor integrated circuits (ICs) or large-scale integrated circuits (LSIs). The integrated circuits such as ICs or LSIs referred to here are named differently depending on the degree of integration, and include integrated circuits called system LSIs, VLSIs (Very Large Scale Integrations), or ULSIs (Ultra Large Scale Integrations). Furthermore, FPGAs (Field-Programmable Gate Arrays) programmed after the LSI is manufactured, or logic devices capable of reconfiguring internal junctions or circuit compartments within the LSI, can also be used as processors. Multiple electronic circuits may be integrated onto a single chip or distributed across multiple chips. Multiple chips may be integrated into a single device or distributed across multiple devices. The computer system referred to here includes a microcontroller having one or more processors and one or more memories. Therefore, the microcontroller also consists of one or more electronic circuits, including semiconductor integrated circuits or large-scale integrated circuits.

Furthermore, it is not essential for the engagement estimation system 1 to have multiple functions integrated into a single device; the multiple components of the engagement estimation system 1 may be distributed across multiple devices. Moreover, at least some of the functions of the engagement estimation system 1 may be implemented by a server or cloud (cloud computing), etc.

Conversely, in the embodiment, multiple functions that are distributed across multiple devices may be consolidated into a single device. For example, at least two of the data server 5, the information processing server 7, and the engagement estimation system 1 may be consolidated into a single device. Also, for example, the PC 8 may also function as the operation terminal 6. Also, for example, the biometric information measurement terminal 3 may also function as the exercise measurement terminal 10.

At least some of the functions of the engagement estimation system 1 may be implemented by a computational model generated by machine learning. For example, a feature determination step of determining at least one feature may be implemented by the computational model. Also, for example, an estimation step of estimating worker engagement based on at least one feature may be implemented by the computational model.

(summary)
Based on the embodiments described above, the following aspects are disclosed.

The engagement estimation method according to the first embodiment is an engagement estimation method in the engagement estimation system (1). The engagement estimation method comprises a first acquisition step, a second acquisition step, a feature determination step, and an estimation step. In the first acquisition step, the first acquisition unit (21) acquires worker information. In the second acquisition step, the second acquisition unit (22) acquires the worker's engagement to work over a predetermined period. In the feature determination step, the feature determination unit (23) determines at least one feature from the worker's information based on the relationship between the worker's information and the engagement over the predetermined period. In the estimation step, the estimation unit (24) estimates the worker's engagement at a point in time different from the predetermined period based on at least one feature. The worker's information includes the worker's biometric information, the worker's location information at the worker's workplace, and relationship information regarding the relationship between the worker and other workers in the workplace. The biometric information is measured by a biometric information measurement terminal (3).

According to the above configuration, engagement can be estimated more objectively by using workers' biometric information, location information, and relationship information.

Furthermore, in the engagement estimation method relating to the second embodiment, in the first embodiment, the worker's information further includes declared information related to work. The declared information is generated in response to operations on the operation terminal (6).

According to the above configuration, the accuracy of engagement estimation can be improved by using the declared information.

Furthermore, in the engagement estimation method relating to the third embodiment, in the second embodiment, the declared information includes answers to questions for estimating engagement over a predetermined period.

According to the above configuration, the accuracy of engagement estimation can be improved by using the answers to the questions.

Furthermore, in the engagement estimation method relating to the fourth aspect, in the second aspect, the declared information includes a first answer to a first question for estimating engagement during a predetermined period, and a second answer to a second question for estimating engagement at a point in time other than the predetermined period.

According to the above configuration, the accuracy of engagement estimation can be improved by using the answers to the questions.

Furthermore, in the engagement estimation method relating to the fifth aspect, in any one of the first to fourth aspects, the worker's information further includes the usage history of the computer system (PC8) that the worker uses for work.

According to the above configuration, the accuracy of engagement estimation can be improved by using usage history.

Furthermore, in the engagement estimation method relating to the sixth aspect, in any one of the first to fifth aspects, the worker information further includes the worker's attendance information.

According to the above configuration, the accuracy of employee engagement estimation can be improved by using attendance data.

Furthermore, in the engagement estimation method relating to the seventh aspect, in any one of the first to sixth aspects, at least one feature is related to at least one of the following: "job resources," "personal resources," and "job requirements" as defined in the "job requirements-resource model," i.e., the "JD-R model"; or empathy and acceptance of at least one of the vision, mission, and philosophy of the group to which the worker belongs for work.

According to the above structure, elements that have a relatively strong correlation with engagement can be used as features.

Furthermore, in the engagement estimation method relating to the eighth aspect, in the seventh aspect, "work resources" relate to at least one of "support from others," "relationships with others," "autonomy in work," "coaching from colleagues," "feedback from colleagues," "diversity of relationships," and "opportunities for career development." "Personal resources" relate to at least one of "optimism," "resilience," and "recovery status." "Job demands" relate to at least one of "quantitative workload," "qualitative workload," and "physical workload."

According to the above structure, elements that have a relatively strong correlation with engagement can be used as features.

Furthermore, the engagement estimation method according to the ninth embodiment further includes a content generation step in any one of the first to eight embodiments. In the content generation step, content to be presented to the viewer is generated based on the estimation results of the estimation step.

According to the above configuration, viewers can see the estimated results.

Furthermore, the engagement estimation method according to the tenth embodiment further includes a transmission step in the ninth embodiment. In the transmission step, the content generated in the presentation content generation step is transmitted to the terminal.

According to the above configuration, viewers can see the estimated results.

Furthermore, in the engagement estimation method according to the eleventh embodiment, in the tenth embodiment, the transmission step transmits the content generated in the presentation content generation step to the terminal at regular intervals.

According to the above configuration, viewers can periodically learn the estimated results.

Furthermore, the engagement estimation method according to the twelfth embodiment further includes, in any one of the first to eleventh embodiments, a regression step in the estimation unit (24) that obtains a regression equation representing the relationship between at least one feature and the engagement over a predetermined period. In the estimation step, the engagement at a point in time different from the predetermined period is estimated based on at least one feature and the regression equation.

With the above configuration, engagement can be estimated using a regression equation.

Furthermore, in the engagement estimation method relating to the 13th embodiment, in any one of the first to 12 embodiments, in the feature determination step, at least one feature is determined based on the coefficient of determination of a regression equation that represents the relationship between worker information and engagement over a predetermined period.

According to the above configuration, at least one feature can be determined using the coefficient of determination.

Configurations other than those in the first embodiment are not essential to the engagement estimation method and can be omitted as appropriate.

Furthermore, the program relating to the 14th embodiment is a program that causes one or more processors of a computer system to execute the engagement estimation method relating to any one of the first to 13 embodiments.

According to the above configuration, engagement can be estimated more objectively by using workers' biometric information, location information, and relationship information.

Furthermore, the engagement estimation system (1) according to the 15th embodiment comprises a first acquisition unit (21), a second acquisition unit (22), a feature determination unit (23), and an estimation unit (24). The first acquisition unit (21) acquires worker information. The second acquisition unit (22) acquires the worker's engagement to work over a predetermined period. The feature determination unit (23) determines at least one feature from the worker information based on the relationship between the worker information and the engagement over the predetermined period. The estimation unit (24) estimates the worker's engagement at a point in time other than the predetermined period based on at least one feature. The worker information includes the worker's biometric information, the worker's location information at the worker's workplace, and relationship information regarding the relationship between the worker and other workers in the workplace. The biometric information is measured by a biometric information measurement terminal (3).

According to the above configuration, engagement can be estimated more objectively by using workers' biometric information, location information, and relationship information.

Not limited to the above embodiments, various configurations (including modifications) of the engagement estimation system (1) according to the embodiment can be realized in an engagement estimation method, a (computer) program, or a non-temporary recording medium on which the program is recorded.

1. Engagement estimation system 3. Biometric information measurement terminal 6. Operation terminal 8. PC (computer system)
21 First acquisition unit 22 Second acquisition unit 23 Feature determination unit 24 Estimation unit

Claims (13)

An engagement estimation method in an engagement estimation system,
In the first acquisition section, there is a first acquisition step of acquiring worker information,
In the second acquisition section, a second acquisition step is performed to acquire the worker's engagement with the work over a predetermined period,
A feature determination step in which, in the feature determination unit, the worker's information is used as an explanatory variable and the engagement over a predetermined period is used as the dependent variable in a regression equation, and at least one feature is determined from the worker's information based on the coefficient of determination of the regression equation obtained,
The estimation unit includes an estimation step of substituting the at least one feature quantity into the regression equation to estimate the worker's engagement at a point in time different from the predetermined period,
The aforementioned worker's information is
The biometric information of the worker measured by the biometric information measurement terminal,
The worker's location information at the worker's place of employment,
Relationship information regarding the relationship between the aforementioned worker and another worker in the workplace,
including,
Engagement estimation methods. The worker's information further includes declaration information regarding the work, which is generated in response to operations on the operating terminal.
The engagement estimation method according to claim 1. The declared information includes answers to questions for estimating the engagement during the specified period.
The engagement estimation method according to claim 2. The declared information includes a first answer to a first question for estimating the engagement during the predetermined period, and a second answer to a second question for estimating the engagement at a point in time other than the predetermined period.
The engagement estimation method according to claim 2. The information of the worker further includes the usage history of the computer system used by the worker for the work.
The engagement estimation method according to any one of claims 1 to 4. The aforementioned worker information further includes the worker's attendance information.
The engagement estimation method according to any one of claims 1 to 4. The at least one feature is,
The "Job Requirement-Resource Model," or "JD-R Model," defines "job resources,""individualresources," and "job requirements."
The worker's sense of empathy and acceptance of at least one of the visions, missions, and principles of the group to which he belongs for the work,
Including at least one of the following:
The engagement estimation method according to any one of claims 1 to 4. The aforementioned "work resources" relate to at least one of the following: "support from others,""relationships with others,""autonomy in work,""coaching from colleagues,""feedback from colleagues,""diversity in relationships," and "opportunities for career development."
The aforementioned "personal resources" relate to at least one of the following: "optimism,""resilience," and "recovery ability."
The aforementioned "level of work requirements" relates to at least one of the following: "quantitative workload,""qualitativeworkload," and "physical workload."
The engagement estimation method according to claim 7. The system further includes a content generation step that generates content to be presented to the viewer based on the estimation results of the estimation step.
The engagement estimation method according to any one of claims 1 to 4. The system further includes a transmission step of transmitting the content generated in the aforementioned presentation content generation step to a terminal.
The engagement estimation method according to claim 9. In the transmission step, the content generated in the presentation content generation step is transmitted to the terminal at regular intervals.
The engagement estimation method according to claim 10. To cause one or more processors of a computer system to execute the engagement estimation method according to any one of claims 1 to 4,
Program. The first acquisition unit acquires worker information,
A second acquisition unit for acquiring the worker's engagement with the work during a predetermined period,
A feature determination unit determines at least one feature from the worker's information based on the coefficient of determination of a regression equation obtained using the worker's information as an explanatory variable and the engagement over a predetermined period as the dependent variable.
The system includes an estimation unit that substitutes the at least one feature into the regression equation to estimate the worker's engagement at a point in time different from the predetermined period,
The aforementioned worker's information is
The biometric information of the worker measured by the biometric information measurement terminal,
The worker's location information at the worker's place of employment,
Relationship information regarding the relationship between the aforementioned worker and another worker in the workplace,
including,
Engagement estimation system.