JP7207825B2 - Engagement estimation device, estimation method, program, and recording medium - Google Patents

Description

The present invention relates to an estimation device, an estimation method, a program, and a recording medium for estimating engagement in a group such as a company.

In an organization such as a company, it is extremely important to grasp the engagement of the organization as information for improving the performance of the organization. Therefore, in the above organization, for example, data related to personnel affairs is grasped, periodic questionnaires are conducted for employees, and engagement is grasped.

However, grasping engagement based on questionnaires involves, for example, the subjectivity of the person in charge of summarizing the results of the questionnaire. Moreover, even if the questionnaire is periodically conducted, it is difficult to estimate the change in engagement after the questionnaire until the next questionnaire result is obtained, that is, it is difficult to estimate the engagement in real time.

Accordingly, an object of the present invention is to provide a new system capable of estimating engagement without requiring a questionnaire.

In order to achieve the above object, the engagement estimation device of the present invention includes:
Including an information acquisition unit, an input unit, a similar network extraction unit, a similar attribute extraction unit, and an engagement calculation unit,
The information acquisition unit
Acquiring the group information from a database in which the group information is linked and stored for each group,
the group information includes attribute information, network information, and engagement information;
In the attribute information, attribute items and attribute values are linked,
The network information is information indicating a network between members of the group based on log information of a communication application that transmits and receives messages within the group,
The engagement information is associated with an engagement factor item, an engagement value, and a significance probability of the engagement value with respect to the number of transmissions and receptions of the communication application,
The input unit
Entering the attribute information and the network information for the target group,
The similarity network extraction unit includes:
Based on the group information of each group acquired from the database, select a group showing network information with a feature amount similar to the feature amount of the network information of the target group, and extract the engagement information X of the selected group,
The similar attribute extraction unit includes:
Based on the group information of each group acquired from the database, select a group showing attribute information similar to the attribute information of the target group, extract the engagement information Y of the selected group,
The engagement calculation unit
Based on the engagement information X and the engagement information Y, an average of engagement values for the items of the engagement factor is calculated, and the average value is estimated as the engagement value Z of the target group.

The engagement estimation method of the present invention includes:
Including an information acquisition process, an input process, a similar network extraction process, a similar attribute extraction process, and an engagement calculation process,
The information acquisition step includes:
Acquiring the group information from a database in which the group information is linked and stored for each group,
the group information includes attribute information, network information, and engagement information;
In the attribute information, attribute items and attribute values are linked,
The network information is information indicating a network between members of the group based on log information of a communication application that transmits and receives messages within the group,
The engagement information is associated with an engagement factor item, an engagement value, and a significance probability of the engagement value with respect to the number of transmissions and receptions of the communication application,
The input step includes:
Entering the attribute information and the network information for the target group,
The step of extracting the similar network includes:
Based on the group information of each group acquired from the database, select a group showing network information with a feature amount similar to the feature amount of the network information of the target group, and extract the engagement information X of the selected group,
The similar attribute extraction step includes:
Based on the group information of each group acquired from the database, select a group showing attribute information similar to the attribute information of the target group, extract the engagement information Y of the selected group,
The engagement calculation step includes:
Based on the engagement information X and the engagement information Y, an average of engagement values for the items of the engagement factor is calculated, and the average value is estimated as the engagement value Z of the target group.

A program of the present invention causes a computer to execute the engagement estimation method of the present invention.

A recording medium of the present invention is a computer-readable recording medium recording the program of the present invention.

According to the present invention, by using log information of a communication application that transmits and receives messages between members in a group, it is possible to estimate the engagement of the group, for example, regardless of the presence or absence of questionnaire information. In addition, since log information is used, real-time estimation of engagement becomes possible, for example.

FIG. 1 is a block diagram showing an example of an estimation device according to Embodiment 1. FIG. 2 is a block diagram illustrating an example of the hardware configuration of the estimation device according to the first embodiment; FIG. FIG. 3 is an example of a flowchart showing the procedure of the estimation method according to the first embodiment. FIG. 4 is a table showing an example of group information in the database according to the first embodiment. FIG. 5 is a table showing an example of input information of the target group Z according to the first embodiment. FIG. 6 is a schematic diagram showing an outline of selection of similar groups based on network information in the first embodiment. FIG. 7 shows a calculation formula for calculating the value of the engagement factor of the target group by weighted average in the first embodiment.

In the present invention, the type of "communication application" is not particularly limited, and is an application that allows messages to be sent and received between members belonging to a group. The message type is not particularly limited. The format of the message is not particularly limited, and may be a sentence, a word, an illustration representing the content, a combination thereof, or the like.

In the present invention, the type of communication application is not limited as described above, but among others, since it is an estimate of engagement that affects the performance of the group as described above, it is possible to send and receive thank-you messages between members in the group. A communication app that works is preferred. Hereinafter, the communication application that transmits and receives the thank-you message will also be referred to as a “thank-you app”. For the gratitude application, for example, Japanese Patent Application Laid-Open No. 2018-147494 can be referred to. Hereinafter, in the embodiments of the present invention, a thank you app will be described as an example of the communication app, but the present invention is not limited to this example.

In the present invention, the unit of "group" is not particularly limited, and may be a unit containing a plurality of constituent members. The group may be, for example, an organizational unit such as a company, an association, a school, or an administrative unit, or may be a unit such as a sports team or a club.

An embodiment of the present invention will be described. In addition, this invention is not limited to the following embodiment. In addition, in the following figures, the same reference numerals are given to the same parts. Also, the descriptions of the respective embodiments can be referred to each other's description unless otherwise specified. Furthermore, the configuration of each embodiment can be combined unless otherwise specified.

[Embodiment 1]
FIG. 1 is a block diagram showing the configuration of an example of the estimation device 10 of this embodiment. The estimation device 10 includes, for example, an information acquisition unit 11, an input unit 12, a similar network extraction unit 14, a similar attribute extraction unit 15, and an engagement calculation unit 16, as shown in FIG. The estimating device 10 may further include a feature extraction unit 13, for example. The estimating device 10 is also called an estimating system, for example. The estimating device 10 may be, for example, one device including the above units, or may be a device in which the above units can be connected via a communication network. The communication network is, for example, the same as the examples given later.

For example, in order to obtain various information from a database, the estimating device 10 can be connected to a database 30 via a communication network 20 as shown in FIG. 1(B). Note that the estimating device 10 may, for example, acquire information from the database 30 each time, or have a storage unit (eg, the storage device 107 in FIG. 2). You may store the information Information estimated by the estimation device 10, for example, is output to the user who uses the estimation device 10. Therefore, as shown in FIG. 20 can be connected. In the present embodiment, a user is a user of the estimation device 10, and specifically means, for example, an administrator who estimates engagement in a group or an organization that is above the group. Further, in the present embodiment, users using the communication application are referred to as members of the group.

The communication network 20 is not particularly limited, and a known communication network can be used, and may be wired or wireless. Examples of the communication network include Internet lines, telephone lines, LANs (Local Area Networks), WiFis (Wireless Fidelity), and the like.

First, information stored in the database 30 will be described. In the database 30, group information is described in group units, for example, in association with group identification information. The number of groups stored in database 30 is unlimited. The group identification information is, for example, information specifying the group, such as an ID number and group name. The group information includes attribute information, network information, and engagement information.

In the attribute information, attribute items and attribute values are associated with each other. The item is not particularly limited, and is, for example, information that characterizes the group. The items include, for example, the number of people in the organization, the male/female ratio, the average length of service, the turnover rate, etc., and may be one or two or more. The unit of the attribute value is not particularly limited, and is set according to the type of the item. The unit of the organizational scale is, for example, the number of people, the number of stores, or the like.

The network information is information indicating a network between group members based on the log information of the communication application. The network information may include, for example, network feature amounts in advance.

In the engagement information, an item of engagement factor, an engagement value, and a significance probability of the engagement value with respect to the number of transmissions and receptions of the communication application are linked. The above items are not particularly limited, and examples include work fulfillment, teamwork, trust in colleagues, trust in groups, trust in organization, teamwork, convincingness of work, convincingness of evaluation, and the like. , may be one, or two or more. The engagement value is not particularly limited, and can be represented by any relative value. As a specific example, a relative value with a maximum value of 1 can be mentioned, and it can also be represented by a rate. The significance probability is the significance probability of the engagement value with respect to the number of transmissions and receptions of the communication application in the group, and for example, a p-value calculated from the correlation between the number of transmissions and receptions and the engagement value.

For example, the database 30 may further include log information of the communication application (for example, the gratitude application) as the group information. The log information may be stored as the attribute information, for example. The log information includes, for example, message reception histories and message transmission histories, which are linked to identification information of members who have sent and received messages. The reception history and the transmission history include, for example, recipients, senders, and their times (transmission/reception times). The log information may be, for example, the number of messages sent and received in the entire group over a predetermined period of time, and the predetermined period of time may be, for example, daily, weekly, or monthly. The identification information of the member is, for example, information specifying the user, such as an ID number, name, nickname, address for transmission and reception, and the like.

In the estimation device 10 , the information acquisition unit 11 acquires stored various group information from the database 30 .

In the estimating device 10, the input unit 12 inputs the attribute information and the network information for the target group whose engagement is to be estimated. Specifically, for example, the user inputs the information via the input unit 12 .

Based on the group information of each group acquired from the database 30, the similar network extraction unit 14 selects a group indicating network information with a feature amount similar to the feature amount of the network information of the target group, and extracts the selected group. extract the engagement information X of

The estimating device 10 may further include a feature extraction unit 13, for example. A feature quantity extraction unit 13 extracts a feature quantity of the network information based on the network information. The extracted feature amount can be used as information in the similarity network extraction unit 14, for example. The type of feature quantity is not particularly limited, and examples thereof include feature quantities in general network analysis, and specific examples thereof include betweenness centrality and degree centrality in a network. In general, the betweenness centrality can be represented by a larger numerical value as the number of paths (lines) passing through points in a network connecting points with lines increases. In general, degree centrality can be represented by a larger numerical value as the number of lines connecting points to other nodes increases in a network in which points are connected by lines.

A similar attribute extraction unit 15 selects a group indicating attribute information similar to the attribute information of the target group based on the group information of each group acquired from the database 30, and extracts the engagement information Y of the selected group. do.

Based on the engagement information X and the engagement information Y, the engagement calculation unit 16 calculates an average engagement value for the item of the engagement factor, and estimates the average value as the engagement value Z of the target group.

The estimating device 10 may, for example, further have an output unit, and the output unit outputs the estimation result. For example, when the estimation device 10 has a display, the output unit may output to the display to present the estimation result to the user, or may output to the user's terminal to provide the user with the estimation result. You can present the results.

Next, FIG. 2 illustrates a block diagram of the hardware configuration of the estimation device 10. As shown in FIG. The estimation device 10 has, for example, a CPU (Central Processing Unit) 101, a memory 102, a bus 103, an input device 104, a display 105, a communication device 106, a storage device 107, and the like. Each part of the estimating device 10 is interconnected via a bus 103 by each interface (I/F).

The CPU 101 is a processor responsible for overall control of the estimating device 10, and is not limited to a CPU, and may be another processor. In the estimation device 10, the CPU 101 executes, for example, the program of the present invention and other programs, and reads and writes various types of information.

The estimating apparatus 10 can be connected to a communication network through, for example, a communication device 106 connected to the bus 103, and can also be connected to an external device via the communication network. The external device is not particularly limited, and is, for example, the database 30, the terminal 40, etc. as described above. The terminal 40 is, for example, a terminal or the like, and the terminal is, for example, a PC (personal computer), a tablet, a smart phone, a mobile phone, or the like. A connection method between the estimation device 10 and the external device is not particularly limited, and may be a wired connection or a wireless connection, for example. The wired connection may be, for example, a cord connection or a cable connection for using a communication network. The wireless connection may be, for example, a connection using a communication network or a connection using wireless communication. The communication network is not particularly limited, and for example, a known communication network can be used, which is the same as described above.

The memory 102 includes, for example, a main memory, which is also referred to as main memory. When the CPU 101 performs processing, the memory 102 reads various operating programs 108 such as the program of the present invention stored in an auxiliary storage device described later, and the CPU 101 receives data from the memory 102. , executes the program 108 . The main memory is, for example, RAM (random access memory). Memory 102, for example, further includes a ROM (Read Only Memory).

The storage device 107 is also called a so-called auxiliary storage device, for example, in contrast to the main memory (main storage device). The storage device 107 includes, for example, a storage medium and a drive that reads from and writes to the storage medium. The storage medium is not particularly limited, and may be, for example, a built-in type or an external type, and includes HD (hard disk), CD-ROM, CD-R, CD-RW, MO, DVD, flash memory, memory card, and the like. and the drive is not particularly limited. The storage device 107 can also be exemplified by a hard disk drive (HDD) in which a storage medium and a drive are integrated, for example. For example, the storage device 107 stores the program 108 as described above, and the memory 102 reads the operation program 108 from the storage device 107 when the CPU 101 is executed as described above. Further, the storage device 107 may include, for example, the storage unit, and store information accumulated in the database 30 as described above.

The estimating device 10 may further have an input device 104 and a display 105, for example. The input device 104 is, for example, a scanner, touch panel, keyboard, or the like. Examples of the display 105 include an LED display and a liquid crystal display.

Next, the estimation method of this embodiment will be described using a flow chart of an example of FIG. 3 and an example of group information. The estimation method of this embodiment includes an information acquisition step, an input step, a similar network extraction step, a similar attribute extraction step, and an engagement calculation step, and may further include, for example, a feature amount calculation step. The estimation method of this embodiment can be implemented, for example, using the estimation device 10 shown in FIGS. Note that the estimation method of this embodiment is not limited to the use of the estimation device 10 .

In the database 30, for example, group information as shown in FIG. 1 is stored for each group. Groups 1-5 are illustrated in FIG. 4, but are not limited to these. In the column of network information in FIG. 4, "Data1" is network information based on the log information of group 1 (identification information ID=1), and furthermore, the log information is linked as shown in the balloon column. may be stored. The log information includes, for example, the ID of the sending member of the message, the ID of the receiving member, the date of transmission/reception, and the like. The network information may include, for example, the feature quantity in advance, or may be extracted from the network information in a feature quantity extraction step, which will be described later.

In the input step, the attribute information A and the network information A are input for the target group Z (S101). The input step can be performed by the input unit 12 of the estimation device 10, for example. The input information of the target group Z includes, for example, attribute information and network information as illustrated in FIG. Network information Z is network information based on group Z log information. The network information may include, for example, the feature quantity in advance, or may be extracted from the network information in a feature quantity extraction step, which will be described later.

If the network information does not include the feature quantity, the feature quantity extraction step extracts the feature quantity Z of the network information based on the network information of the target group A (S102). The feature quantity extraction step can be executed by the feature quantity extraction unit 13 of the estimation device 10, for example.

On the other hand, the group information of each group stored is obtained from the database 30 (S103). This information acquisition step can be executed by the information acquisition unit 11 of the estimation device 10, for example. Then, if the network information in the group information does not include the feature amount, the feature amount of the network information is similarly extracted for each group based on the network information (S104). The feature quantity extraction step can be executed by the feature quantity extraction unit 13 of the estimation device 10, for example.

Then, based on the group information of each group acquired from the database 30, a group X indicating network information having a feature amount similar to the feature amount Z of the network information of the target group Z is selected (S105), and the selected group X is extracted (S106). These steps can be executed, for example, by the similarity network extraction unit 14 of the estimation device 10 .

Here, the outline of the selection of the group X and the extraction of the engagement information X is shown in FIG. As shown in FIG. 6, rankings from the top and rankings from the worst are arranged for each of betweenness centrality and degree centrality based on the network information of the target group Z, and differences between them are shown. In this case, the behavior of the 1st to 3rd difference in betweenness centrality (0.5→0.39→0.34) and the behavior of the 1st to 3rd difference in degree stop centrality (0.54→ 0.47→0.34) is the feature amount of the network information of the group Z. Similarly, by extracting feature amounts for each group in the database 30 and comparing them, the group 4 similar to the feature amount of the target group Z can be selected as the group Y. FIG. Then, the engagement information Y can be extracted from the group information of group 4 .

Next, as the similar attribute extraction step, based on the group information of each group acquired from the database 30, a group Y indicating attribute information similar to the attribute information of the target group Z is selected (S107). Engagement information Y of group Y is extracted (S108). These steps can be executed by the similar attribute extraction unit 15 of the estimation device 10, for example.

Here, the outline of the selection of the group Y and the extraction of the engagement information Y is shown in FIG. As shown in FIG. 4, when the attribute information of the group consists of three items of size, gender ratio, and average length of service, a similar group Y is selected for each item. That is, as shown in FIG. 7, with respect to the item "scale" of the attribute information, Group 1 is selected as a group similar to the attribute information of the target group Z, and its engagement information is extracted. Group 2 is selected as a group similar to the attribute information of the target group Z, and its engagement information is extracted. , whose engagement information is extracted.

More specifically, selection of a group of items may be performed as follows. In the case of the item "size", first, a group whose size is similar to the target group Z is selected. In this case, similar conditions can be set as appropriate. For example, as a first step, a group with a range of ±50 people is extracted from the number of people in the target group Z, and the number of people close to the number of people in the target group Z is extracted. , are selected as similar groups. If there is no group with a range of ±50 people, or if the number is less than n, for example, a group with a range of ±100 people is further extracted, and the number of people close to the number of people in the target group Z is higher. groups as similar groups. Next, for the selected n groups, multiple engagement factors (e.g., work fulfillment, teamwork, trust in colleagues, trust in group, trust in organization, teamwork, satisfaction of work, evaluation ), the group with the largest number of factors whose engagement value is an arbitrary number or more (e.g. 0.4 or more) and whose p is an arbitrary number or more (e.g. 0.01 or less) , and finally select as a group related to the item "scale". Groups can also be selected in the same way for the item "Male/Female ratio" and the item "Average length of service".

Next, as the engagement calculation step, based on the engagement information X and the engagement information Y, the average of the engagement values for the items of the engagement factor is calculated (S109), and the average value is used as the engagement value Z of the target group. (S110). These steps can be executed by the engagement calculator 16 of the estimation device 10, for example. Then, the estimation result is output (S111), and the process ends (END). The output step can be performed by the output unit of the estimating device 10, for example.

The average value may be, for example, a simply calculated average value or a weighted average value obtained by weighting the average value. An example of the weighted average will be described below.

As shown in FIG. 7A, (S106) extracts the engagement information X of group 4 based on the feature amount of the network information, and (S108) extracts the item "scale" based on the attribute information. Engagement information Y1 of group 1, engagement information Y2 of group 2 regarding the item "male-to-female ratio", and engagement information Y3 of group 3 regarding the item 3 "average length of service" are extracted, respectively. Each piece of engagement information includes an engagement value and a significance probability (p-value). A low significance probability means that it is preferable to reduce the influence of the engagement value of the engagement item with a low significance probability on the estimated value. For this reason, regarding the engagement information Y1, Y2, and Y3 obtained based on the attribute information, for example, the smaller the significance probability is, the larger the value is set, and the relatively larger the significance probability is, the smaller the value is set. weighting. Then, it is preferable to obtain a weighted average value from the weighted engagement values and estimate it as the engagement value Z of the target group Z. FIG.

Calculation of the engagement value Z by the weighted average can be exemplified by the formula of FIG. 7(B), for example. Based on this formula, when the value of each engagement factor is calculated from FIG. 7(A) by weighted average, as shown in FIG. , that is, "work fulfillment" is calculated as "0.36", and "confidence in colleagues" is calculated as "0.39". These are presumed to be the engagement values of the engagement factors of the target group Z.

[Embodiment 2]
A program of the present embodiment is a program capable of executing the estimation method of the present invention on a computer. Alternatively, the program of this embodiment may be recorded on a computer-readable recording medium, for example. The recording medium is not particularly limited, and includes, for example, the above-described storage medium.

Although the present invention has been described with reference to the embodiments, the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

<Appendix>
Some or all of the above-described embodiments and examples can be described as in the following appendices, but are not limited to the following.
(Appendix 1)
Including an information acquisition unit, an input unit, a similar network extraction unit, a similar attribute extraction unit, and an engagement calculation unit,
The information acquisition unit
Acquiring the group information from a database in which the group information is linked and stored for each group,
the group information includes attribute information, network information, and engagement information;
In the attribute information, attribute items and attribute values are linked,
The network information is information indicating a network between members of the group based on log information of a communication application that transmits and receives messages within the group,
The engagement information is associated with an engagement factor item, an engagement value, and a significance probability of the engagement value with respect to the number of transmissions and receptions of the communication application,
The input unit
Entering the attribute information and the network information for the target group,
The similarity network extraction unit includes:
Based on the group information of each group acquired from the database, select a group showing network information with a feature amount similar to the feature amount of the network information of the target group, and extract the engagement information X of the selected group,
The similar attribute extraction unit includes:
Based on the group information of each group acquired from the database, select a group showing attribute information similar to the attribute information of the target group, extract the engagement information Y of the selected group,
The engagement calculation unit
An engagement estimating device that calculates an average of engagement values for the items of the engagement factor based on the engagement information X and the engagement information Y, and estimates the average value as the engagement value Z of the target group.
(Appendix 2)
Furthermore, including a feature extraction unit,
The estimating device according to supplementary note 1, wherein the feature quantity extraction unit extracts the feature quantity of the network information based on the network information.
(Appendix 3)
The attribute information includes a plurality of items,
The similar attribute extraction unit includes:
The estimating device according to appendix 1 or 2, wherein, for each item of the attribute information, a group indicating attribute information similar to the attribute information of the target group is selected, and engagement information Y of each of the selected groups is extracted.
(Appendix 4)
The engagement calculation unit weights the engagement value according to the superiority probability for the extracted engagement information Y, and estimates the weighted average value as the engagement value Z of the target group,
4. The estimation apparatus according to any one of appendices 1 to 3, wherein the weight of the weighting is set larger as the significance probability is relatively smaller, and is set smaller as the significance probability is relatively larger.
(Appendix 5)
5. The estimation device according to any one of appendices 1 to 4, wherein the attribute information includes log information of the communication application.
(Appendix 6)
6. The estimation device according to any one of appendices 1 to 5, wherein the item of attribute information is at least one selected from the group consisting of size, ratio of men and women, average length of service, and turnover rate.
(Appendix 7)
The items of the engagement factor were selected from the group consisting of work fulfillment, teamwork, trust in colleagues, trust in the group, trust in the organization, teamwork, satisfaction of work, and satisfaction of evaluation. 7. The estimating device according to any one of appendices 1 to 6, which is at least one.
(Appendix 8)
Including an information acquisition process, an input process, a similar network extraction process, a similar attribute extraction process, and an engagement calculation process,
The information acquisition step includes:
Acquiring the group information from a database in which the group information is linked and stored for each group,
the group information includes attribute information, network information, and engagement information;
In the attribute information, attribute items and attribute values are linked,
The network information is information indicating a network between members of the group based on log information of a communication application that transmits and receives messages within the group,
The engagement information is associated with an engagement factor item, an engagement value, and a significance probability of the engagement value with respect to the number of transmissions and receptions of the communication application,
The input step includes:
Entering the attribute information and the network information for the target group,
The step of extracting the similar network includes:
Based on the group information of each group acquired from the database, select a group showing network information with a feature amount similar to the feature amount of the network information of the target group, and extract the engagement information X of the selected group,
The similar attribute extraction step includes:
Based on the group information of each group acquired from the database, select a group showing attribute information similar to the attribute information of the target group, extract the engagement information Y of the selected group,
The engagement calculation step includes:
An engagement estimation method, comprising: calculating an average of engagement values for the items of the engagement factors based on the engagement information X and the engagement information Y, and estimating the average value as the engagement value Z of the target group.
(Appendix 9)
Furthermore, including a feature extraction step,
The estimation method according to appendix 8, wherein the feature quantity extraction step extracts the feature quantity of the network information based on the network information.
(Appendix 10)
The attribute information includes a plurality of items,
The similar attribute extraction step includes:
The estimation method according to appendix 8 or 9, wherein, for each item of the attribute information, a group indicating attribute information similar to the attribute information of the target group is selected, and engagement information Y of each selected group is extracted.
(Appendix 11)
In the engagement calculation step, for the extracted engagement information Y, the engagement value is weighted according to its superiority probability, and the weighted average value is estimated as the engagement value Z of the target group,
11. The estimation method according to any one of appendices 8 to 10, wherein the weight of the weighting is set larger as the significance probability is relatively smaller, and is set smaller as the significance probability is relatively larger.
(Appendix 12)
12. The estimation method according to any one of attachments 8 to 11, wherein the attribute information includes log information of the communication application.
(Appendix 13)
13. The estimation method according to any one of attachments 8 to 12, wherein the item of attribute information is at least one selected from the group consisting of size, ratio of men and women, average length of service, and turnover rate.
(Appendix 14)
The items of the engagement factor were selected from the group consisting of work fulfillment, teamwork, trust in colleagues, trust in the group, trust in the organization, teamwork, satisfaction of work, and satisfaction of evaluation. 14. The estimation method according to any one of appendices 8 to 13, which is at least one.
(Appendix 15)
A program for causing a computer to execute the estimation method according to any one of appendices 8 to 14.
(Appendix 16)
A computer-readable recording medium recording the program according to appendix 15.

According to the present invention, by using log information of a communication application that transmits and receives messages between members in a group, it is possible to estimate the engagement of the group, for example, regardless of the presence or absence of questionnaire information. In addition, since log information is used, real-time estimation of engagement becomes possible, for example.

10 estimation device 11 information acquisition unit 12 input unit 13 feature quantity extraction unit 14 similar network extraction unit 15 similar attribute extraction unit 16 engagement calculation unit

Claims (10)

Including an information acquisition unit, an input unit, a similar network extraction unit, a similar attribute extraction unit, and an engagement calculation unit,
The information acquisition unit
Acquiring the group information from a database in which the group information is linked and stored for each group,
the group information includes attribute information, network information, and engagement information;
In the attribute information, attribute items and attribute values are linked,
The network information is information indicating a network between members of the group based on log information of a communication application that transmits and receives messages within the group,
The engagement information is associated with an engagement factor item, an engagement value, and a significance probability of the engagement value with respect to the number of transmissions and receptions of the communication application,
The input unit
Entering the attribute information and the network information for the target group,
The similarity network extraction unit includes:
Based on the group information of each group acquired from the database, select a group showing network information with a feature amount similar to the feature amount of the network information of the target group, and extract the engagement information X of the selected group,
The similar attribute extraction unit includes:
Based on the group information of each group acquired from the database, select a group showing attribute information similar to the attribute information of the target group, extract the engagement information Y of the selected group,
The engagement calculation unit
An engagement estimating device that calculates an average of engagement values for the items of the engagement factor based on the engagement information X and the engagement information Y, and estimates the average value as the engagement value Z of the target group. Furthermore, including a feature extraction unit,
The estimation device according to claim 1, wherein the feature quantity extraction unit extracts the feature quantity of the network information based on the network information. The attribute information includes a plurality of items,
The similar attribute extraction unit includes:
The estimation device according to claim 1 or 2, wherein, for each item of the attribute information, a group indicating attribute information similar to that of the target group is selected, and engagement information Y of each of the selected groups is extracted. The engagement calculation unit weights the engagement value of the extracted engagement information Y according to the significance probability of the engagement value, and estimates the weighted average value as the engagement value Z of the target group,
The estimation device according to any one of claims 1 to 3, wherein the weight of said weighting is set larger as said significance probability is relatively smaller, and set smaller as said significance probability is relatively larger. The estimation device according to any one of claims 1 to 4, wherein the attribute information includes log information of the communication application. 6. The estimation device according to any one of claims 1 to 5, wherein the item of attribute information is at least one selected from the group consisting of size, gender ratio, average length of service, and turnover rate. The items of the engagement factor were selected from the group consisting of work fulfillment, teamwork, trust in colleagues, trust in the group, trust in the organization, teamwork, satisfaction of work, and satisfaction of evaluation. 7. An estimating device according to any one of claims 1 to 6, which is at least one. Including an information acquisition process, an input process, a similar network extraction process, a similar attribute extraction process, and an engagement calculation process,
The information acquisition step includes:
Acquiring the group information from a database in which the group information is linked and stored for each group,
the group information includes attribute information, network information, and engagement information;
In the attribute information, attribute items and attribute values are linked,
The network information is information indicating a network between members of the group based on log information of a communication application that transmits and receives messages within the group,
The engagement information is associated with an engagement factor item, an engagement value, and a significance probability of the engagement value with respect to the number of transmissions and receptions of the communication application,
The input step includes:
Entering the attribute information and the network information for the target group,
The step of extracting the similar network includes:
Based on the group information of each group acquired from the database, select a group showing network information with a feature amount similar to the feature amount of the network information of the target group, and extract the engagement information X of the selected group,
The similar attribute extraction step includes:
Based on the group information of each group acquired from the database, select a group showing attribute information similar to the attribute information of the target group, extract the engagement information Y of the selected group,
The engagement calculation step includes:
Based on the engagement information X and the engagement information Y, the average of the engagement values for the items of the engagement factor is calculated, and the average value is estimated as the engagement value Z of the target group ,
An engagement estimation method, wherein each of the steps is executed by a computer . A program that causes a computer to execute the estimation method according to claim 8 . A computer-readable recording medium recording the program according to claim 9 .

Images