Message generation device, method, and program

Abstract

A message generation device according to an embodiment of the present invention includes: a first calculation unit that calculates a second evaluation value for each of a plurality of types of psychological factors of a plurality of users, the second evaluation value being the average of a first evaluation value for each of the factors and based on outcome information indicating large outcomes and satisfying a prescribed condition, which is stored in a storage device in which the first evaluation value is accumulated and stored, the first evaluation value being an evaluation value pertaining to each of the factors and based on outcome information indicating the size of an outcome arising from the actions of the plurality of users; a second calculation unit that calculates a third evaluation value for each of the factors obtained by correcting the first evaluation value on the basis of the ratio of the first evaluation value to the second evaluation value calculated by the first calculation unit; and a generation unit that generates a message prompting the users associated with the first evaluation value to act in accordance with the third evaluation value calculated by the second calculation unit.

Description

Message generating device, method and program

[0001] FIELD Embodiments of the present invention relate to a message generating device, method, and program.

[0002] In recent years, due to changes in the world, such as diversification, work style reform, and the COVID-19 pandemic, well-being has been attracting attention as a desirable concept for employee satisfaction. The World Health Organization (WHO) defines well-being as "a state of complete physical, mental, and social satisfaction." The constituent factors of subjective well-being, which is one type of well-being, can be determined using Perma theory.

[0003] For example, the strength of each factor of an employee's well-being at work, consisting of Positive Emotion, Engagement, Relationships, Meaning, and Achievement, can be calculated from the answers to the Workplace Perma Profiler, a questionnaire consisting of multiple questions, and this strength can be used to evaluate well-being satisfaction.To support employees based on the perspective of well-being evaluated using the above perma indicators, support tools are used that enable care according to the evaluated state.

[0004] "The Japanese Workplace PERMA-Profiler: A validation study among Japanese workers <https: / / onlinelibrary.wiley.com / doi / epdf / 10.1539 / joh.2018-0050-OA> "Questionnaires Overview" <https: / / www.peggykern.org / questionnaires.html> "Early detection can prevent 52% of absences. Wellday, which uses AI to detect 'hidden illnesses,' begins Japan's first joint research project on prediction with Kitasato University" <https: / / prtimes.jp / main / html / rd / p / 000000020.000047158.html>

[0005] On the other hand, when making a comprehensive evaluation of well-being based on the strength of the constituent factors, each factor is treated as having the same weight. However, in reality, each employee will place different importance on which factor, and there is a considerable discrepancy between this and the above treatment.

[0006] Furthermore, when providing behavioral support to employees based on the perspective of well-being, the characteristic aspects that indicate which elements the employee values ​​are not evaluated, and the goal is to ensure satisfaction with all elements. If the evaluated level of satisfaction with well-being deviates from the actual situation, behavioral support based on the above perspective will be inappropriate and will not be sufficiently effective. Therefore, it is necessary to conduct an evaluation that is tailored to the individual's personality so as to be closer to the actual situation, and use the results of this evaluation as material for appropriate behavioral support.

[0007] The present invention has been made in light of the above-mentioned circumstances, and its purpose is to provide a message generation device, method, and program that can generate appropriate messages that encourage action in response to evaluations related to multiple types of psychological factors.

[0008] A message generation device according to one aspect of the present invention includes a first calculation unit that calculates a second evaluation value for each factor, which is an average of the first evaluation values ​​based on achievement information that satisfies predetermined conditions and indicates a great achievement, stored in a storage device in which first evaluation values ​​for each factor are accumulated and stored, the first evaluation values ​​being evaluation values ​​for each of multiple types of psychological factors of the user based on achievement information that indicates the magnitude of achievement due to the actions of the multiple users; a second calculation unit that calculates a third evaluation value for each factor by correcting the first evaluation value based on the ratio of the first evaluation value to the second evaluation value calculated by the first calculation unit; and a generation unit that generates a message that encourages the user to take action related to the first evaluation value, in accordance with the third evaluation value calculated by the second calculation unit.

[0009] A message generation method according to one aspect of the present invention is a method performed by a message generation device, and includes the steps of: calculating, by a first calculation unit of the message generation device, a second evaluation value for each factor, which is an average of the first evaluation values ​​based on achievement information that satisfies predetermined conditions and indicates a significant achievement, stored in a storage device in which first evaluation values ​​for each factor are accumulated and stored, the first evaluation values ​​being evaluation values ​​for each of multiple types of psychological factors of the user based on achievement information that indicates the magnitude of achievement due to the actions of multiple users; calculating, by a second calculation unit of the message generation device, a third evaluation value for each factor, correcting the first evaluation value based on the ratio of the first evaluation value to the second evaluation value calculated by the first calculation unit; and generating, by a generation unit of the message generation device, a message that encourages the user to take action related to the first evaluation value, in accordance with the third evaluation value calculated by the second calculation unit.

[0010] According to the present invention, it is possible to generate an appropriate message that encourages action in response to an evaluation relating to multiple types of psychological factors.

[0011] FIG. 1 is a diagram showing an example of evaluation values ​​of factors related to well-being. FIG. 2 is a diagram showing an example of maximum intrinsic evaluation values ​​and corrections of factors related to well-being. FIG. 3 is a diagram showing an example of calculations related to correction of evaluation values ​​of factors related to well-being. FIG. 4 is a diagram showing an example of calculations related to correction of evaluation values ​​of factors related to well-being. FIG. 5 is a diagram showing an example of determinations regarding transmission of a support message to a user. FIG. 6 is a diagram showing an example of the relationship between the level of a user's performance and evaluation values. FIG. 7 is a diagram showing an example of calculations of the degree of potential exertion. FIG. 8 is a diagram showing an application example of a message generation device according to an embodiment of the present invention. FIG. 9 is a flowchart showing an example of the procedure of processing operations of a message generation device according to an embodiment of the present invention. FIG. 10 is a block diagram showing an example of the hardware configuration of a message generation device according to an embodiment of the present invention.

[0012] An embodiment of the present invention will be described below with reference to the drawings. In this embodiment, AI (artificial intelligence) is trained to learn the communication tool logs and the strength of each factor related to the user employees, and the strength of each factor can be dynamically estimated from the communication log. The importance of the unique perma factors possessed by various employees is not necessarily roughly equal, and there may be some differences in the weight of each factor.

[0013] Furthermore, there is a correlation between employee well-being satisfaction and their job performance. Job performance can be estimated from the increase or decrease in the amount of work output (hereinafter referred to as job output or output).

[0014] Therefore, in this embodiment, the factor evaluation value of each type when the amount of work output to date related to the assigned task is near its maximum value (hereinafter sometimes referred to as the maximum intrinsic evaluation value) is close to the state in which the employee's intrinsic well-being is at its maximum level of satisfaction. Also, the factor evaluation value of each type when the amount of work output is near its minimum value (hereinafter sometimes referred to as the minimum intrinsic evaluation value) is a state in which the employee's well-being is not at all satisfied. However, the factor evaluation values ​​of all types generally do not reach 0, and are less than the factor evaluation value in the state in which the employee's well-being is at its maximum level of satisfaction.

[0015] In this embodiment, the amount of work performance is routinely acquired, and an evaluation value for each factor according to the Perma theory is calculated and stored in a database. FIG. 1 is a diagram showing an example of the evaluation values ​​of factors for well-being. The example shown in FIG. 1 shows the estimated evaluation values ​​for each type of well-being factor, "Positive Emotion," "Engagement," "Relationship," "Meaning," "Achievement" (sometimes written as "P," "E," "R," "M," and "A"), and "Happy," based on the amount of work performance, with the maximum value set to 10, as well as the evaluation value "Overall (:E)," which is the average of these evaluation values.

[0016] Of these accumulated work results, the evaluation value of each factor when, for example, the top 5% of results are produced is interpreted as the employee's inherent level of importance placed on each factor, and the average of these values ​​is taken as the employee's inherent standard for best performance when carrying out their work, i.e., the maximum inherent evaluation value.

[0017] Fig. 2 is a diagram showing an example of maximum intrinsic evaluation values ​​and corrections of factors related to well-being. Fig. 3 is a diagram showing an example of calculations related to correction of evaluation values ​​of factors related to well-being. Fig. 4 is a diagram showing an example of calculations related to correction of evaluation values ​​of factors related to well-being. In the example shown in Figs. 2 to 4, the average evaluation values ​​(before correction) of each factor when the top 5% of the accumulated work output amounts shown in Fig. 3 (symbol a in Fig. 3) were created are shown as the maximum intrinsic evaluation values ​​of each factor shown in Fig. 2: "8.0", "8.0", "6.0", "10.0", "7.0", and "10.0".

[0018] By correcting the accumulated evaluation values ​​for each factor based on this maximum unique evaluation value, a more realistic level of well-being satisfaction can be estimated, and the content and sending criteria of messages that support the improvement of employee performance can be optimized.

[0019] Next, the correction of the Perma factor evaluation will be described. In this embodiment, the maximum intrinsic evaluation value is updated and optimized as needed. Then, to perform a comprehensive evaluation of well-being, the evaluation value of each factor is corrected (symbol b in FIG. 2 ) using, for example, the following formula (1) so that the maximum evaluation value of each factor is 10 (symbol a in FIG. 2 ), and an evaluation value is calculated for each type of factor.

[0020] Factor evaluation value (after correction) = Factor evaluation value (before correction) × (10 / Maximum intrinsic evaluation value of factor) Formula (1) Figure 2 shows the "corrected evaluation," which is the evaluation value (after correction) for each type of factor calculated based on the evaluation value (before correction) for each type of factor and the maximum intrinsic evaluation value shown in Figure 2. The range of business performance when calculating the maximum intrinsic evaluation value does not have to be within the top 5% range described above, and can be changed depending on the situation.

[0021] Furthermore, when a user is responsible for multiple types of work, the amount of work accomplished for each type can be quantified as the amount of work accomplished for all types of work that the employee is responsible for, based on the importance of the amount of work accomplished for the target work in the organization to which the user belongs.

[0022] Figure 4 shows an example of an employee-specific evaluation range updated by the above update. In this example, before the update, factor "R" in Figure 2, which has the lowest pre-correction evaluation value of "5.3," is the target of priority support (symbol a in Figure 4). However, after calculating the corrected evaluation value, factor "M" with the lowest evaluation value of "5.6" (symbol c in Figure 2) becomes the target of priority support, as the evaluation value of factor "R" increases to "8.8."

[0023] Next, the criteria for sending a support message to a user to improve the user's well-being satisfaction level will be described. FIG. 5 is a diagram illustrating an example of a determination as to whether to send a support message to a user. FIG. 6 is a diagram illustrating an example of the relationship between the level of a user's performance and the evaluation value. In this embodiment, the criterion for sending the support message is whether the overall evaluation value of well-being after the evaluation values ​​of each factor have been corrected as described above falls within the range of the performance evaluation level "low" or "very low" within the range of the evaluation values ​​(after correction) of each of the five performance evaluation levels (performance levels) shown in FIG. 6 . That is, in the example shown in FIG. 6 , the criterion for sending a support message is that the overall evaluation value is less than 6.5. As indicated by symbol a in FIG. 5 , when the overall evaluation value is 6.4, the sending criterion is met.

[0024] When this sending criterion is met, the support message will contain information about factors whose corrected evaluation values ​​fall within the range of "low" or "very low" performance levels. In other words, the support message will contain information about factors "E" and "R" whose corrected evaluation values ​​are less than 6.5, as shown by symbols b and c in Figure 5.

[0025] 7 is a diagram showing an example of calculation of the degree of potential exertion. In this embodiment, the average of the evaluation values ​​of each factor related to the top 5% of the accumulated work performance (symbol a in FIG. 7) is calculated as the maximum intrinsic evaluation value for each type of factor, and the average of the evaluation values ​​of each factor related to the bottom 5% of the accumulated work performance (symbol b in FIG. 7) is calculated as the minimum intrinsic evaluation value for each type of factor. This minimum intrinsic evaluation value is the factor evaluation value when the user is performing work near the minimum limit.

[0026] In this embodiment, the difference between the maximum and minimum intrinsic evaluation values ​​for each factor (sometimes referred to as the first difference) (symbol c in Figure 7) is interpreted as the potential for improving the user's well-being satisfaction, i.e., the amount of support effect that can be expected.

[0027] In addition, in this embodiment, the degree of support effect exerted by each factor is calculated for each type of factor as the difference (sometimes referred to as the second difference) between the pre-correction factor evaluation value and the above-mentioned minimum intrinsic evaluation value for the same factors (symbol d in Figure 7), and the value obtained by dividing this second difference by the above-mentioned first difference is calculated for each type of factor as the degree of exertion relative to the potential.

[0028] For example, for factors "E" and "R" that fall within the range of "low" or "very low" performance levels shown in Figure 5, if the evaluation values ​​before correction are "3" and "2", the maximum intrinsic evaluation values ​​of factors "E" and "R" are "8" and "6", and the minimum intrinsic evaluation values ​​of factors "E" and "R" are "5" and "2", as shown in Figure 7, the calculated result of the performance level of factor "E" relative to its potential is approximately -0.6 (= (3-5 / (8-5))), and the calculated result of the performance level of factor "R" relative to its potential is 0 (= (2-2 / (6-1))).

[0029] In this embodiment, the calculation results of the above-mentioned performance levels for all types of factors are sorted in ascending order, and the elements with the highest support effect for the user are prioritized based on the order of the factors, and the content of the support message is emphasized and a final support message is generated. As described above, if the calculation result of the performance level of factor "E" relative to its potential is approximately -0.6 and the calculation result of the performance level of factor "R" relative to its potential is 0, the highest priority for message generation is assigned to factor "E," and the second highest priority for message generation is assigned to factor "R."

[0030] The content conditions for support messages include the following four, for example: - Comply with the above transmission criteria - The content must be such that it evokes the necessary elements of support that will improve the user's satisfaction with well-being, and induces an increase in the factor evaluation value - When there are multiple elements of support required, the support message with the higher priority must be emphasized - The content must include examples of recommended actions for the user, making it easier for them to actually take action.

[0031] A specific example of a support message is as follows. This example is an example in which, as described above, the highest priority for message generation is assigned to factor "E," and the second highest priority for message generation is assigned to factor "R." Note that the message with the highest priority may be emphasized compared to messages with other priorities, for example by underlining it.

[0032] (Supportive message for the "Engagement" factor) - "You are seriously lacking in engagement. Find a job that you are good at and can use your strengths to your advantage. First, think about your strengths."

[0033] (Supportive message for the factor "Relationship") - "You lack relationships. Try to build friendships with people you know. First, ask questions to people you are interested in and get to know them better."

[0034] In this embodiment, the effect of the support message to the user is expected to be, for example, that, based on the user's actual, optimized well-being, the user will recognize elements that require support from the provided support message and will autonomously take action in accordance with the example actions described in the support message or the actions that the user has independently considered based on the support message. Furthermore, by repeating this action, the user's well-being satisfaction level is expected to approach a state in which it is sufficiently improved.

[0035] 8 is a diagram illustrating an application example of a message generation device according to an embodiment of the present invention. As illustrated in FIG. 8, the message generation device 100 according to this embodiment includes a survey result acquisition unit 11, a communication log acquisition unit 12, a first factor evaluation value calculation unit 13, a second factor evaluation value calculation unit 14, a business performance amount acquisition unit 15, a business performance amount / factor evaluation value DB 21, a factor maximum inherent evaluation value update unit 22, a factor evaluation value correction unit 23, a message transmission determination unit 24, a message content determination unit 25, a potential utilization degree calculation unit 26, a message emphasis unit 27, a message generation unit 28, and a message transmission unit 29.

[0036] The survey result acquisition unit 11 acquires the results of a survey to evaluate the employee's level of satisfaction with well-being. The communication log acquisition unit 12 acquires a log of messages in a chat tool that is used daily during work.

[0037] The first factor evaluation value calculation unit 13 calculates an evaluation value for each factor of PERMA of well-being in the employee's current state based on the survey results acquired by the survey result acquisition unit 11.

[0038] The second factor evaluation value calculation unit 14 calculates an evaluation value for each factor of PERMA of well-being using AI based on, for example, the most recent communication log acquired by the communication log acquisition unit 12.

[0039] Hereinafter, an example will be described in which both the calculation of the evaluation value when using the questionnaire result acquisition unit 11 and the first factor evaluation value calculation unit 13 and the calculation of the evaluation value when using the communication log acquisition unit 12 and the second factor evaluation value calculation unit 14 are performed, but in order to reduce the workload of employees, for example, only the calculation of the evaluation value when using the communication log acquisition unit 12 and the second factor evaluation value calculation unit 14 may be performed. Furthermore, when it is desired to improve the accuracy of the calculation results during a learning promotion period of AI after introducing the system according to this embodiment, as described above, both the calculation of the evaluation value when using the questionnaire result acquisition unit 11 and the first factor evaluation value calculation unit 13 and the calculation of the evaluation value when using the communication log acquisition unit 12 and the second factor evaluation value calculation unit 14 may be performed.

[0040] The business result amount acquisition unit 15 acquires the amount of work performed on a daily basis. The business result amount / factor evaluation value DB 21 stores and accumulates the factor evaluation values ​​calculated by the first factor evaluation value calculation unit 13 or the second factor evaluation value calculation unit 14, and the business result amounts acquired by the business result amount acquisition unit 15, and the accumulated contents are overwritten and updated every time a calculation is performed by the first factor evaluation value calculation unit 13 or the second factor evaluation value calculation unit 14, or every time an acquisition is performed by the business result amount acquisition unit 15.

[0041] The factor maximum inherent evaluation value update unit 22 calculates the average value for each factor of the factor evaluation values ​​for, for example, the top 5% of the data of the work performance amounts accumulated in the work performance amount / factor evaluation value DB 21, thereby calculating the factor maximum inherent evaluation value, i.e., a value between 0 and 10 that indicates a state in which each factor of the employee's unique well-being is fully satisfied. This value indicates the degree of importance placed on each factor unique to the employee.

[0042] The factor evaluation value correcting unit 23 corrects the factor evaluation values ​​for the factor maximum intrinsic evaluation value for each factor calculated by the factor maximum intrinsic evaluation value updating unit 22 so that the maximum value of all factor evaluation values ​​becomes 10.

[0043] The message transmission determination unit 24 calculates a comprehensive evaluation value as a degree of satisfaction with well-being from the factor evaluation values ​​corrected by the factor evaluation value correction unit 23. The message transmission determination unit 24 determines whether the performance level associated with this comprehensive evaluation value corresponds to the above-mentioned "very high," "high," "normal," "low," or "very low," and determines whether to send a support message based on this performance level. If the determined performance level corresponds to "very high," "high," or "normal," it is determined that sending a support message is unnecessary, and the process ends.

[0044] When the determined performance level corresponds to "low" or "very low," the message content determination unit 25 determines that a support message needs to be sent, determines the performance level for each factor related to the factor evaluation value for each factor corrected by the factor evaluation value correction unit 23, and determines the text of the support message for each factor for the factors whose performance level corresponds to "low" or "very low."

[0045] The potential utilization degree calculation unit 26 calculates the potential utilization degree for each factor whose determined performance level is "low" or "very low" from the minimum factor intrinsic evaluation value, which is the average value of the factor evaluation values ​​for, for example, the bottom 5% of the business performance data stored in the business performance amount / factor evaluation value DB 21, the factor evaluation value before correction stored in the business performance amount / factor evaluation value DB 21, and the maximum factor intrinsic evaluation value calculated by the factor maximum intrinsic evaluation value update unit 22.

[0046] The message emphasis unit 27 adds a difference by emphasis processing to the content of the support message for each factor in ascending order of the potential exertion degree for the factor calculated by the potential exertion degree calculation unit 26. The emphasis processing can be, for example, decoration such as underlining. For example, the message emphasis unit 27 emphasizes the support message so that the degree of emphasis for the support message for a factor with a relatively high potential exertion degree is higher than the degree of emphasis for the support message for a factor with a relatively low potential exertion degree.

[0047] The message generating unit 28 generates a support message based on the content of the message processed by the message emphasizing unit 27. The message sending unit 29 sends the support message generated by the message generating unit 28 to the employee.

[0048] 9 is a flowchart showing an example of a procedure for the processing operation of a message generation device according to an embodiment of the present invention. The business performance amount acquisition unit 15 acquires the performance amount of the assigned business (S11). The first factor evaluation value calculation unit 13 calculates (acquires) an evaluation value for each factor of PERMA based on the survey results acquired by the survey result acquisition unit 11, and the second factor evaluation value calculation unit 14 calculates an evaluation value for each factor of PERMA using AI based on the communication log acquired by the communication log acquisition unit 12 (S12).

[0049] The business performance amount acquisition unit 15 writes the results acquired in S11 into the business performance amount / factor evaluation value DB 21, and the first factor evaluation value calculation unit 13 and the second factor evaluation value calculation unit 14 write the results calculated in S12 into the business performance amount / factor evaluation value DB 21. As a result, the contents stored in the business performance amount / factor evaluation value DB 21 are updated (S13).

[0050] The factor maximum inherent evaluation value update unit 22 calculates the factor maximum inherent evaluation value, i.e., a value indicating the degree of importance attached to each factor that is unique to the employee, for the factor evaluation values ​​for, for example, the top 5% of data of the business performance amount accumulated in the business performance amount / factor evaluation value DB 21 (S14).

[0051] The factor evaluation value correcting unit 23 corrects the factor evaluation values ​​for the factor maximum intrinsic evaluation value for each factor calculated by the factor maximum intrinsic evaluation value updating unit 22 so that the maximum value of all factor evaluation values ​​becomes 10 (S15).

[0052] The message transmission determination unit 24 calculates a comprehensive evaluation value from the factor evaluation values ​​corrected by the factor evaluation value correction unit 23 (S16). The message transmission determination unit 24 determines a performance level related to this comprehensive evaluation value (S17), and determines whether this performance level corresponds to any of the above-mentioned "very high," "high," "normal," "low," and "very low," thereby determining whether it is necessary to send a support message (S18).

[0053] If the result of this determination indicates that a support message needs to be sent, the message content determination unit 25 determines the performance level for each factor related to the factor evaluation value corrected by the factor evaluation value correction unit 23, and determines the text of the support message for each factor for factors whose performance level corresponds to "low" or "very low" (S19).

[0054] The potential utilization calculation unit 26 calculates the potential utilization degree for factors whose determined performance level corresponds to "low" or "very low" from the minimum factor intrinsic evaluation value, the factor evaluation value before correction, and the maximum factor intrinsic evaluation value (S20).

[0055] The message highlighting unit 27 performs a process of highlighting the support message for each factor in ascending order of the potential demonstration degree for the factor calculated by the potential demonstration degree calculation unit 26 (S21).

[0056] The message generating unit 28 generates a support message based on the content of the message processed by the message emphasizing unit 27, and the message sending unit 29 sends this generated support message to the employee (S22).

[0057] In the embodiment described above, in order to utilize the correlation between employee well-being satisfaction and performance and to set a scale for employee-specific evaluation values ​​based on performance, the data that can be defined as high performance from the accumulated data on the employee's work output is set as the maximum unique evaluation value, which is the maximum evaluation value unique to the employee. Below this value, the actual evaluation value is corrected so that the maximum value of the evaluation value becomes the maximum evaluation value of the Perma theory, and the value that is closest to the actual well-being state is evaluated.

[0058] Furthermore, in this embodiment, data that can be defined as "low performance" is defined as a minimum inherent evaluation value, which is the minimum evaluation value specific to the employee, the maximum inherent evaluation value and the minimum inherent evaluation value are defined as potential, and the ratio of the difference between the actual evaluation value and the minimum inherent evaluation value relative to this potential is defined as the potential performance level. The order of these performance levels, arranged in ascending order, is set as the priority order for factors requiring support. In this way, by evaluating well-being that is tailored to each employee, it is possible to determine whether support is needed based on actual conditions and provide appropriate support.

[0059] 10 is a block diagram showing an example of the hardware configuration of a message generation device according to an embodiment of the present invention. In the example shown in FIG. 10, the message generation device 100 according to the embodiment is configured, for example, by a server computer or a personal computer, and has a hardware processor 111A such as a CPU (Central Processing Unit). A program memory 111B, a data memory 112, an input / output interface 113, and a communication interface 114 are connected to this hardware processor 111A via a bus 115.

[0060] The communication interface 114 includes, for example, one or more wireless communication interface units, and enables transmission and reception of information to and from a communication network NW. As the wireless interface, for example, an interface that adopts a low-power wireless data communication standard such as a wireless LAN (Local Area Network) is used.

[0061] An input device 300 and an output device 400, which are attached to the message generation device 100 and used by a user or the like, are connected to the input / output interface 113. The input / output interface 113 receives operation data input by a user or the like through the input device 300, such as a keyboard, a touch panel, a touchpad, or a mouse, and outputs output data to the output device 400, which may include a display device using a liquid crystal or an organic electroluminescence (EL) display, for display. The input device 300 and the output device 400 may be devices built into the message generation device 100, or may be input devices and output devices of other information terminals that can communicate with the message generation device 100 via the network NW.

[0062] The program memory 111B is a non-transitory tangible storage medium that is a combination of a non-volatile memory that can be written to and read from at any time, such as a hard disk drive (HDD) or a solid state drive (SSD), and a non-volatile memory such as a read only memory (ROM), and stores programs necessary to execute various control processes, etc., according to one embodiment.

[0063] The data memory 112 is a tangible storage medium that is a combination of, for example, the above-mentioned non-volatile memory and a volatile memory such as RAM (Random Access Memory), and is used to store various data acquired and created during various processes performed by the message generation device 100.

[0064] A message generation device 100 according to an embodiment of the present invention may be configured as a data processing device having software-based processing function units. Storage areas used as work memory or the like by each unit of the message generation device 100 may be configured using the data memory 112 shown in FIG. 10. However, these configured storage areas are not essential components within the message generation device 100, and may be areas provided in, for example, an external storage medium such as a USB (Universal Serial Bus) memory, or a storage device such as a database server located in the cloud.

[0065] The processing function unit can be realized by having the hardware processor 111A read and execute a program stored in the program memory 111B, but the processing function unit may also be realized in various other forms, including an integrated circuit such as an application specific integrated circuit (ASIC) or a field-programmable gate array (FPGA).

[0066] The methods described in the embodiments may be stored as a program (software means) that can be executed by a computer on a recording medium such as a magnetic disk (e.g., a floppy disk, a hard disk, etc.), an optical disk (e.g., a CD-ROM, a DVD, an MO, etc.), or a semiconductor memory (e.g., a ROM, a RAM, a flash memory, etc.), or may be transmitted and distributed via a communication medium. The program stored on the medium also includes a configuration program that configures the software means (including not only executable programs but also tables and data structures) that the computer executes. The computer that implements this device reads the program stored on the recording medium and, in some cases, configures the software means using the configuration program, and executes the above-described processing by having the operation controlled by this software means. The term "recording medium" as used herein is not limited to a storage medium for distribution, but also includes a storage medium such as a magnetic disk or semiconductor memory installed inside the computer or in a device connected via a network.

[0067] The present invention is not limited to the above-described embodiments, and various modifications can be made in the implementation stage without departing from the spirit of the invention. Furthermore, the embodiments may be implemented in appropriate combinations, in which case the combined effects can be obtained. Furthermore, the above-described embodiments include various inventions, and various inventions can be extracted by combining selected elements from the disclosed elements. For example, if the problem can be solved and the desired effect can be obtained even if some elements are deleted from all elements shown in the embodiments, the configuration from which these elements are deleted can be extracted as an invention.

[0068] 100... Message generation device 11... Questionnaire result acquisition unit 12... Communication log acquisition unit 13... Factor evaluation value first calculation unit 14... Factor evaluation value second calculation unit 15... Business result amount acquisition unit 21... Business result amount / factor evaluation value DB 22... Factor maximum inherent evaluation value update unit 23... Factor evaluation value correction unit 24... Message transmission determination unit 25... Message content determination unit 26... Potential utilization degree calculation unit 27... Message emphasis unit 28... Message generation unit 29... Message transmission unit

Claims

1. A storage device that stores, for each factor, a first evaluation value that is an evaluation value for each of a plurality of psychological factors of the user based on achievement information indicating the magnitude of achievements by the actions of a plurality of users. A first calculation unit that calculates, based on the achievement information indicating a large achievement that satisfies a predetermined condition, a second evaluation value that is the average of the first evaluation values for each factor; A second calculation unit that calculates a third evaluation value for each factor, which corrects the first evaluation value based on the ratio of the first evaluation value to the second evaluation value calculated by the first calculation unit; A message generation device comprising: a generation unit that generates a message for prompting the user's action related to the first evaluation value according to the third evaluation value calculated by the second calculation unit.

2. The message generation device according to claim 1, further comprising a fourth calculation unit that calculates, for each factor, a fourth evaluation value that is the average of the first evaluation values based on the achievement information indicating a small achievement that satisfies a predetermined condition, wherein the generation unit generates a message for prompting the user's action based on the content based on the ratio of the difference between the first evaluation value and the fourth evaluation value to the difference between the second evaluation value and the fourth evaluation value.

3. The message generation device according to claim 1, wherein the generation unit generates a message for prompting the user's action when the third evaluation value calculated by the second calculation unit satisfies a predetermined condition and is small.

4. A method performed by a message generation device, comprising: calculating, by a first calculation unit of the message generation device, a second evaluation value for each factor, which is an average of the first evaluation values for each factor, based on achievement information indicating the magnitude of achievements by the actions of a plurality of users, and stored in a storage device that stores the first evaluation values for each of a plurality of psychological factors of the user; calculating, by a second calculation unit of the message generation device, a third evaluation value for each factor, which is the first evaluation value corrected based on the ratio of the first evaluation value to the second evaluation value calculated by the first calculation unit; and generating, by a generation unit of the message generation device, a message that prompts the user to take an action related to the first evaluation value according to the third evaluation value calculated by the second calculation unit.

5. The message generation method according to claim 4, further comprising calculating, by a fourth calculation unit of the message generation device, a fourth evaluation value for each factor, which is an average of the first evaluation values based on the achievement information indicating a small achievement satisfying a predetermined condition, wherein the generation unit generates a message that prompts the user to take an action based on the content based on the ratio of the difference between the first evaluation value and the fourth evaluation value to the difference between the second evaluation value and the fourth evaluation value.

6. The message generation method according to claim 4, wherein the generation unit generates a message that prompts the user to take an action when the third evaluation value calculated by the second calculation unit satisfies a predetermined condition and is small.

7. A message generation processing program that causes a processor to function as each unit of the message generation device according to any one of claims 1 to 3.

Images