JP2022037892A - Program, method and system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To check and manage mental states of employees by hearing real feelings on the work of an employee whose mental disorder is worried.

SOLUTION: A program causes a computer including a processor and a memory to execute the following steps. The program causes the processor to execute the steps of: acquiring first information relating to the work state of a user; determining whether or not the user is an object person based on the acquired first information and second information relating to the work states of other users whose mental disorder has been worried in the past; when the user is the object person, creating a question text for the user on the basis of the first information; transmitting the created question text to the user; and responding to the user's reply to the question text.

SELECTED DRAWING: Figure 3

COPYRIGHT: (C)2022,JPO&INPIT

Description

Application for application of Article 30, Paragraph 2 of the Patent Act Applicable to Article 30, Paragraph 2 of the Patent Act, in order to be subject to the provisions of the exception to the loss of novelty of the invention submitted on September 24, 2 Announced on the website listed in "Certificate"

The present invention relates to programs, methods, and systems.

In recent years, flexible working styles that do not limit time and place, such as telework, have become widespread. On the other hand, it has become difficult for managers to grasp the actual working conditions (work load, etc.) of employees, and there is a risk that employees will develop health problems due to overwork or the like. Therefore, there is a need to confirm and manage the mental state of employees from the actual working conditions of employees. For example, in the technique disclosed in Patent Document 1, employees who may have mental health problems are extracted based on the actual working conditions of employees and the working conditions of persons with mental health problems, and the extracted employees and the extracted employees. It is stated that an interview with the boss etc. will be set up.

Japanese Unexamined Patent Publication No. 2016-151979

Patent Document 1 describes that employees who may have mental health problems can be efficiently connected to interviews, but the schedule of the interviewee is not always open, and some interviewees consult with each other. It can be difficult.

The purpose of this disclosure is to confirm and manage the mental state of employees by listening to their true intentions regarding the work of employees who are concerned about their mental disorders.

It is a program to be executed by a computer equipped with a processor and a memory. The program is based on the step of acquiring the first information about the user's work status from the processor, the acquired first information, and the second information about the work status of other users who have been concerned about mental disorders in the past. A step of determining whether or not the user is the target person, a step of creating a question text for the user based on the first information when the user is the target person, and a step of transmitting the created question text to the user. A program that executes a step and a step that responds to a user's response to a question.

According to the program of the present invention, it is possible to confirm and manage the mental state of an employee by listening to the true intentions of the work of the employee who is concerned about mental disorders.

It is a figure which shows the whole structure of the system of this embodiment. It is a block diagram which shows the structure of the terminal apparatus included in the system of this embodiment. It is a block diagram which shows the functional configuration of the server included in the system of this embodiment. It is a figure which shows the data structure of the employee information DB. It is a figure which shows the data structure of the log information DB. It is a figure which shows the data structure of the work information DB. It is a figure for demonstrating an example of the flow which manages the mental state of an employee. It is a schematic diagram which shows the display example of the terminal apparatus which concerns on this embodiment.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. In the drawings for explaining the embodiments, the same components are designated by the same reference numerals in principle, and the repeated description thereof will be omitted.

<Overview>
The system 1 according to the present embodiment manages the working status of employees of the company. The working status represents, for example, the time of commuting of an employee, information on attendance such as absenteeism, late arrival, or early leaving, work content, work volume, overtime hours, holiday work, and the like. Then, the system 1 determines whether or not the employee has a mental disorder based on the work situation, and if it is presumed to have occurred, the system 1 takes care of the employee.

<Overall configuration>
FIG. 1 is a diagram showing an overall configuration of the system 1 of the present embodiment. As shown in FIG. 1, the system 1 includes a terminal device 10 used by employees and a server 20. The terminal device 10 and the server 20 are connected to each other so as to be able to communicate with each other via the network 80 by using a wired or wireless communication standard.
In the illustrated example, the system 1 includes a plurality of terminal devices 10. The quantity of the terminal device 10 can be arbitrarily changed according to the number of employees.

The terminal device 10 is a general-purpose computer used by employees for business. The terminal device 10 is realized by, for example, a stationary PC (Personal Computer), a laptop PC, a head-mounted display, or the like. Further, the terminal device 10 may be a portable computer such as a smartphone or a tablet terminal.

As shown in FIG. 1, the terminal device 10 includes a communication IF (Interface) 12, an input device 13, an output device 14, a memory 15, a storage unit 16, and a processor 19.

The communication IF 12 is an interface for transmitting and receiving signals because the terminal device 10 communicates with an external device. The input device 13 is an input device for receiving an input operation from a user (employee). The input device 13 includes, for example, a touch panel, a touch pad, a pointing device such as a mouse, a keyboard, and the like.

The output device 14 is an output device for presenting information to the user. The output device 14 includes, for example, a display, a speaker, and the like. The memory 15 is for temporarily storing a program, data processed by the program or the like, and is realized by, for example, a volatile memory such as a DRAM (Dynamic Random Access Memory). The storage unit 16 is a storage device for storing data, and is realized by, for example, a flash memory or an HDD (Hard Disc Drive). The processor 19 is hardware for executing an instruction set described in a program, and is composed of an arithmetic unit, registers, peripheral circuits, and the like.

The server 20 is a device that manages employee information. The server 20 is a computer connected to the network 80.

As shown in FIG. 1, the server 20 includes a communication IF 22, an input / output IF 23, a memory 25, a storage 26, and a processor 29.

The communication IF 22 is an interface for transmitting and receiving signals because the server 20 communicates with an external device. The input / output IF 23 functions as an interface with an input device for receiving an input operation from the user and an output device for presenting information to the user. The memory 25 is for temporarily storing a program, data processed by the program, or the like, and is realized by, for example, a volatile memory such as a DRAM. The storage 26 is a storage device for storing data, and is realized by, for example, a flash memory or an HDD. The processor 29 is hardware for executing an instruction set described in a program, and is composed of an arithmetic unit, registers, peripheral circuits, and the like.

<Configuration of terminal device>
FIG. 2 is a block diagram showing a configuration of a terminal device 10 included in the system 1 of the present embodiment. As shown in FIG. 2, the terminal device 10 includes a communication unit 121, an operation input unit 130 (including a touch sensitive device 131 and a display 132), a voice processing unit 140, a microphone 141, and a speaker 142. A position information sensor 150, a camera 160, a storage unit 170, and a control unit 180 are provided. Further, the terminal device 10 also includes functions and configurations (for example, a battery for holding electric power, a power supply circuit for controlling the supply of electric power from the battery to each circuit, and the like) which are not shown in FIG. Each block included in the terminal device 10 is electrically connected by, for example, a bus or the like.

The communication unit 121 performs a process for the terminal device 10 to communicate with another device. The communication unit 121 performs transmission processing on the signal generated by the control unit 180, and transmits the signal to the outside (for example, the server 20). The communication unit 121 performs reception processing on the signal received from the outside and outputs the signal to the control unit 180.

The operation input unit 130 has a mechanism for receiving an input operation from a user who owns the terminal device 10. Specifically, for example, when the operation input unit 130 is a touch screen, the touch sensitive device 131 and the display 132 are included. The operation input unit 130 may include a mouse, a keyboard, and the like.

The touch-sensitive device 131 detects the user's contact position with respect to the touch panel, for example, by using a capacitive touch panel. The touch-sensitive device 131 outputs a signal indicating the contact position of the user detected by the touch panel to the control unit 180 as an input operation.

The display 132 displays data such as images, moving images, and texts according to the control of the control unit 180. The display 132 is realized by, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display.

The voice processing unit 140 performs modulation / demodulation of the voice signal. The voice processing unit 140 is realized by, for example, a processor for voice processing.
The voice processing unit 140 modulates the voice signal given from the microphone 141 and outputs the modulated signal to the control unit 180. Further, the voice processing unit 140 demodulates the voice signal given from the control unit 180, and gives the demodulated signal to the speaker 142.

The microphone 141 receives the voice input and outputs the voice signal corresponding to the voice input to the voice processing unit 140. The speaker 142 converts the voice signal given from the voice processing unit 140 into voice and outputs the voice to the outside of the terminal device 10.

The position information sensor 150 is a sensor that detects the position of the terminal device 10, and is, for example, a GPS (Global Positioning System) module. The GPS module is a receiving device used in a satellite positioning system. The satellite positioning system receives signals from at least three or four satellites and detects the current position of the terminal device 10 on which the GPS module is mounted based on the received signals.

The camera 160 is a device that receives light by an image sensor and outputs it as an image signal. The camera 160 is arranged, for example, at a position facing the user who uses the terminal device 10. The camera 160 captures the user and outputs an image signal.

The storage unit 170 is composed of, for example, a flash memory or the like, and stores data and programs used by the terminal device 10. For example, the storage unit 170 stores employee information 171.

Employee information 171 is information about an employee who owns the terminal device 10. The employee information 171 includes, for example, identification information (employee ID), name, identification information of the terminal device 10 (terminal ID), employee attributes, and the like. The attribute represents the affiliation of the employee. Attributes include, for example, department, job title, project, work style, and the like.

The control unit 180 is realized by the processor 19 reading a program stored in the storage unit 170 and executing an instruction included in the program. The control unit 180 controls the operation of the terminal device 10. Specifically, for example, the control unit 180 exerts functions as an operation reception unit 181, a transmission / reception unit 182, an acquisition unit 183, and a presentation unit 184.

The operation receiving unit 181 performs a process for receiving the user's operation input from the input device 13. For example, the operation reception unit 181 may perform a flick operation, a tap operation, or a drag (drag) based on the information of the coordinates when the user touches the touch sensitive device 131 with a finger or the like. Swipe) Determines the type of operation, such as whether it is an operation, and accepts the operation.

The transmission / reception unit 182 performs a process for the terminal device 10 to transmit / receive data to / from an external device such as a server 20 according to a communication protocol.

The acquisition unit 183 acquires information that can grasp the working status of the user who uses the terminal device 10. Examples of the acquired information include information input by the user for a predetermined application, information on the operation history of the user operating the terminal device 10, information based on the user's image signal taken by the camera 160, and the like. .. The information acquired by the acquisition unit 183 is transmitted to the server 20 via the transmission / reception unit 182.

The information entered for a given application includes, for example, information entered by the user in the attendance management application indicating that the user has gone to work, finished work, or took a break, information indicating that paid leave has been obtained, or information regarding various reasons. Etc. are included. Further, the information includes, for example, information about a schedule entered by the user in the schedule management application. Information about the schedule includes, for example, the content of the business task, such as how much time the meeting is, how long the business trip is, and the amount of the business task.

Specifically, the information regarding the operation history includes a log in which the user operates the input device 13 (hardware) of the terminal device 10, a log in which the application is operated, a log in which the OS (Operating System) is operated, and the like.

The log of operating the hardware includes, for example, information indicating which key is input by the keyboard, the number of times the key is input, and the like. Further, in the log of operating the hardware, information on the position detected by the pointing device such as a mouse, a touch pad, and a touch-sensitive device, and information on the operation content of the user determined based on the information on the position (for example,). , Click, drag, swipe, flick, long tap, etc.), number of operations, etc. are included. In addition, the log of operating the hardware includes voice information input by the microphone, the number of remarks, and the like.

The log of operating the application includes the log of the operation input by the user when the application for performing the business is used. Specifically, for example, if the application is presentation material creation software, the application name, file name, item name in the file, information indicating which function was used, input character information, error information, and slides are displayed. Various information such as information on newly added operations. If the application is mail software, it is information on the header of the sent / received mail, setting information, and the like. If the application is document creation software, the number of characters entered, the number of times characters have been converted, the number of pages created, the contents entered (characters have been entered, characters have been modified, images or videos have been inserted, etc.), etc. included.

In the log of operating the OS, information on the activation of the application, information on changing the setting of the OS, information on putting the terminal device 10 to sleep, information on waking up from the sleep state, and information on the usage status of hardware resources ( For example, CPU usage rate, memory usage rate, network usage status, etc.) are included.

Information based on the user's image signal taken by the camera is characterized by extracting, for example, information on an operation in which the user starts the camera, information on an image showing the orientation and facial expression of the user's face, or facial composition by image analysis. Information about feature points represented as movement of points is included. The information based on the image signal may include information other than these, or may include a part of such information.
The presentation unit 184 presents various information to the user.

<Functional configuration of the server>
FIG. 3 is a block diagram showing a functional configuration of the server 20 included in the system 1 of the present embodiment. As shown in FIG. 3, the server 20 functions as a communication unit 201, a storage unit 202, and a control unit 203.

The communication unit 201 performs a process for the server 20 to communicate with an external device.

The storage unit 202 stores data and programs used by the server 20. For example, the storage unit 202 stores an employee information database (DB) 281, a log information database (DB) 282, and a work information database (DB) 283.

The employee information DB 281 is a database for holding information about employees. Details will be described later.

The log information DB 282 is a database for holding information regarding the operation history in which the user operates the terminal device 10. Details will be described later.

The work information DB 283 is a database for holding the business contents of the user. Details will be described later.

Further, the storage unit 202 stores, for example, a plurality of trained models generated by machine learning. The first trained model 284 is, for example, a model used for determining whether or not the user is a person who is concerned about mental disorders. The second trained model 285 is a model used, for example, when creating a question sentence for a person who is concerned about mental disorders. The third trained model 286 is a model for realizing a chatbot that carries out a chat with a person who is concerned about mental disorders. The first trained model 284 to the third trained model 286 are stored in the storage unit 202, for example, before the provision of the corresponding service is started. In the present embodiment, for example, the following are assumed as persons who are concerned about mental disorders.
・ Persons who are concerned about mental health problems ・ Persons who are concerned about decreased motivation

The first trained model 284 to the third trained model 286 are obtained by causing the machine learning model to perform machine learning according to the model learning program based on the training data.

For example, in the present embodiment, the first trained model 284 is trained to output whether or not there is a concern about mental upset with respect to the input information about the user. At this time, for the learning data, for example, information on the past work status of the employee is used as input data, and the judgment as to whether or not the person is concerned about mental disorders with respect to this input data is used as correct output data. Judgment as to whether or not a person is at risk of mental illness is made, for example, based on the opinion of an expert. That is, the first trained model 284 is trained based on information on the working conditions of employees who have been feared to have mental disorders in the past. Information about the past work status of the employee is acquired from, for example, the employee information DB 281, the log information DB 282, or the work information DB 283. As the learning data, for example, the determination of whether or not the person is mentally ill may be used as the correct answer output data. Judgment as to whether or not a person is mentally ill is made, for example, based on the opinion of an expert.

Further, the second trained model 285 is trained to output a question according to the state of the user with respect to the input information about the user, for example. For example, when a person who is concerned about mental health disorder is a person who is concerned about mental health disorder, the second trained model 285 is trained to output a question for relieving anxiety or stress. ing. At this time, as the learning data, the information on the working status of the employee who has been feared to have a mental disorder in the past is used as the input data, and the question text based on the input information is used as the correct answer output data. The question text as the correct answer output data is created so as to alleviate anxiety, stress, etc. by extracting a predetermined wording from information on the work situation, for example. The question text may be paraphrased, for example, to be generated based on information about the user's work situation. Further, the question text may be paraphrased as being assumed from information on the work situation of the user, for example. Questions to relieve anxiety or stress alleviate the causes of a user's mental health problems, such as work content, relationships, personal circumstances, daily feelings of anxiety, or worries. Is a question for.

In addition, when the person who is concerned about mental illness is a person who is concerned about declining motivation, the second trained model 285 outputs a question for clarifying the reason why the motivation is lowered. Is being learned. At this time, as the learning data, the information on the working status of the employee who has been feared to have a mental disorder in the past is used as the input data, and the question text based on the input information is used as the correct answer output data. The interrogative text as correct answer output data is created, for example, to extract a predetermined wording from information on the work situation and clarify the reason why the motivation is lowered. Questions to clarify the reason why motivation is low are, for example, the content of work, relationships, personal circumstances, daily feelings of dissatisfaction, or whether there are any worries, etc. This is a question to clarify the cause of the decline.

Further, the third trained model 286 is trained to output a predetermined response to the input response and the information regarding the work status of the user. At this time, the learning data is, for example, input data regarding an assumed response pattern and information regarding the work status of an employee who has been feared to have a mental disorder in the past, and is used as input data regarding the input response pattern and work status. The response pattern based on this is used as the correct output data. The response to the response from the user may include, for example, a proposal for an interview with an industrial physician, a proposal for lifestyle-related improvement, a proposal for taking (long-term) leave, and the like.

The machine learning model according to the present embodiment is, for example, a synthetic function with parameters in which a plurality of functions are synthesized. A parameterized composition function is defined by a plurality of adjustable functions and a combination of parameters. The machine learning model according to the present embodiment may be a synthetic function with any parameter that satisfies the above requirements, but is a multi-layered network model (hereinafter referred to as a multi-layered network). A trained model using a multi-layered network has an input layer, an output layer, and at least one intermediate layer or hidden layer provided between the input layer and the output layer. The trained model is expected to be used as a program module that is part of artificial intelligence software.

As the multi-layered network according to the present embodiment, for example, a deep neural network (DNN), which is a multi-layered neural network targeted for deep learning, can be used. As the DNN, for example, a convolutional neural network (CNN) for an image may be used.

The control unit 203 is realized by the processor 29 reading the program stored in the storage unit 202 and executing the instruction included in the program. The control unit 203 controls the operation of the server 20. Specifically, for example, the control unit 203 functions as a transmission / reception unit 2031, an acquisition unit 2032, a determination unit 2033, a dialogue processing unit 2034, and an execution unit 2035.

The transmission / reception unit 2031 controls a process in which the server 20 transmits / receives data to / from an external device such as a terminal device 10 according to a communication protocol. The received data is stored in the storage unit 202. For example, information transmitted from the terminal device 10 and input by the user to a predetermined application, information on the operation history of the user operating the terminal device 10, information based on the user's image signal taken by the camera 160, and the like can be obtained. It is stored in the employee information DB 281, the log information DB 282, or the work information DB 283 of the storage unit 202.

The acquisition unit 2032 acquires the information required for determination among the information stored in the storage unit 202. For example, the acquisition unit 2032 acquires information on the work status of the user in a predetermined period from the employee information DB 281, the log information DB 282, or the work information DB 283. The information on the work status includes, for example, information on attendance, information on the schedule, information on the operation history, information based on the image signal, or business content inferred from the information on the operation history and the information based on the image signal. .. The acquisition unit 2032 acquires, for example, the information required for determination at a predetermined timing.

The determination unit 2033 executes a process of determining whether or not the user is a monitoring target who is concerned about mental disorders. Specifically, for example, the determination unit 2033 inputs the information acquired by the acquisition unit 2032 into the first trained model 284, and outputs whether or not the person is concerned about mental disorders.

The dialogue processing unit 2034 creates a question sentence using the second trained model 285 stored in the storage unit 202, and automatically responds to the answer from the user using the third trained model 286 in an interactive manner. .. The dialogue processing unit 2034 is realized by using, for example, a chat system used in the business of a company.

Specifically, for example, the dialogue processing unit 2034 inputs information on the work status of the user who is determined to be at risk of mental disorder into the second learned model 285, in order to relieve anxiety, stress, or the like. Output the question text of. The dialogue processing unit 2034 transmits the output question text from the communication unit 201 to the terminal device 10. At this time, the dialogue processing unit 2034 transmits, for example, a question sentence at a timing that makes it easy for the user to answer. As the timing at which the user can easily answer, for example, the timing at which the concentration is not high while operating the terminal device 10 is preferable. The timing at which the concentration is not high is determined based on, for example, information on the operation history, that is, information such as slow input speed and many erroneous conversions. Further, the timing at which the concentration is not high is determined based on, for example, the orientation of the user's face determined by the image signal or the behavior of the line of sight. The timing at which the user can easily answer is determined based on, for example, information on the work situation, and includes immediately after the work is switched, immediately after the break, immediately before the end of the lunch break, and the like.

The dialogue processing unit 2034 receives the response text transmitted from the terminal device 10 via the communication unit 201. The answer sentence can be obtained in the form of a natural sentence. By making it possible to answer in the form of natural sentences, the user can chat as if he / she is chatting with a person.

The dialogue processing unit 2034 inputs the acquired answer sentence and information on the working situation into the third trained model 286, and outputs a response sentence corresponding to the input answer. The dialogue processing unit 2034 transmits the output response text from the communication unit 201 to the terminal device 10.

The execution unit 2035 executes a procedure according to the content of the chat with the user. For example, the execution unit 2035 executes the attendance procedure by the attendance application when the user approves the vacation or the proposal such as early leaving sent by the dialogue processing unit 2034.

<Data structure>
4 to 6 are diagrams showing the data structure of the database stored in the server 20. It should be noted that FIGS. 4 to 6 are examples, and data not described is not excluded.
FIG. 4 is a diagram showing a data structure of the employee information DB 281. As shown in FIG. 4, each of the records of the employee information DB 281 includes an item "employee ID", an item "employee name", an item "attribute" and the like.

The item "employee ID" stores an ID for identifying an employee.

The item "employee name" stores the name of the employee.

The item "attribute" stores the attribute of the employee. Attributes include various systems to which employees belong. For example, the item "attribute" includes sub-items such as the item "department", the item "position", the item "project", and the item "working style".

The item "department" stores the department to which the user belongs, for example, the department. The item "position" stores the user's position in the organization to which the user belongs, for example, the position. If there are multiple job titles, multiple job titles may be registered. The item "project" stores the information of the collective work to which the user is assigned, for example, the project. If there are multiple projects, multiple projects may be registered. The item "working style" stores the working style set for the user.

In the item "working style", for example, presentation work that works on a regular basis, flex that works with a time difference, discretionary work in which working hours are left to the discretion of the user, etc. are stored. Further sub-items (for example, year of joining the company, employment form, etc.) may be added to the item "attribute" as needed.

Information other than the information shown in FIG. 4 may be stored in the employee information DB 281. For example, the employee information DB 281 may include quotas and the like imposed within a predetermined period. Further, the employee information DB 281 may include information on the place of work, information on the business partner company, information on the boss or subordinates, and the like.

Further, the employee information DB 281 may store information indicating the health condition of the user. The information indicating the health condition includes, for example, information related to the fear of mental disorder or the diagnosis result in a general health examination.

FIG. 5 is a diagram showing a data structure of the log information DB 282. As shown in FIG. 5, each record of the log information DB 282 includes an item "employee ID", an item "date", an item "operation log", and the like.

The item "date" stores the date when the operation log was acquired.

The item "operation log" stores a log of information related to the operation history. The item "operation log" includes sub-items such as the item "time", the item "terminal ID", and the item "log" as information related to the operation history.

The item "time" stores the time (time stamp) when the operation by the user occurs. Specifically, the item "time" includes, for example, the time when the hardware is operated, the time when the application is operated, or the time when the OS is operated.

The item "terminal ID" stores the ID of the terminal device 10 operated by the user.

The item "log" stores the contents of the operation by the user. Specifically, in the item "log", for example, the content of operating the hardware, the content of operating the application, the content of operating the OS, and the like are stored.

FIG. 6 is a diagram showing a data structure of the work information DB 283. As shown in FIG. 6, each of the records of the work information DB 283 includes an item “employee ID”, an item “date”, an item “business content”, an item “time”, and the like.

The item "date" stores the date when the user performed the business.

The item "business content" stores the content of the business performed by the user. The item "business content" is specified and stored by, for example, the control unit 203 based on the information input to the application. For example, the control unit 203 specifies attendance, termination, break, late arrival, early leaving, absenteeism, etc. based on the information on attendance such as attendance, termination, or break entered by the user for the attendance application, and the item "business content". Remember. Further, the control unit 203 specifies, for example, a meeting, a business trip, etc. based on the information about the schedule input by the user to the schedule management application, and stores it in the item “business content”.

Further, the item "business content" is specified and stored by, for example, the control unit 203 based on the information regarding the operation history. For example, the control unit 203 specifies mail, document creation, work, investigation, etc. based on the application used by the user, the file name created by the application used, the content operated on the file, and the like, and the item "business". Remember in "Contents".

The item "time" stores the time when the work described in the item "business content" is performed. The work information DB 283 is not limited to the item “time”, and the time when the work was performed may be stored. Further, the time is not limited to the time when the predetermined business is started, and the time when the predetermined business is started and the time when the predetermined business is completed may be stored.

Information other than the information shown in FIG. 6 may be stored in the work information DB 283. For example, the work information DB 283 may include an evaluation of the work status. For example, the work information DB 283 may include an evaluation for each business content. The evaluation for each business content is evaluated by, for example, the control unit 203 based on the information related to the operation history, the information based on the image signal of the user, and the like. For example, the control unit 203 estimates the processing speed of the work, the degree of concentration in the work, the degree of participation in the meeting, etc. based on the information related to the operation history or the information based on the image signal of the user, and determines the work content of the user. evaluate. Further, the work information DB 283 may include an evaluation for each predetermined period. The evaluation for each predetermined period represents the user's evaluation for each day, week, month, etc., for example. The evaluation for each predetermined period is evaluated by, for example, the control unit 203 based on the accumulation of evaluations for each business content.

In addition, the total working hours for each predetermined period may be stored in the working information DB 283. The total working hours for each predetermined period represents, for example, the total working hours for each day, week, month, or the like.
good.

<Operation>
Hereinafter, the process of managing the mental state of the employee by the system 1 will be described with reference to FIG. 7. In the description of FIG. 7, for example, a case where a person who is concerned about mental health disorder is a person who is concerned about mental health disorder will be described as an example.

FIG. 7 is a diagram for explaining an example of a flow of managing the mental state of an employee by the system 1.
As shown in FIG. 7, the terminal device 10 transmits information that can grasp the work status of the user to the server 20. Specifically, for example, when the user inputs an input to a predetermined application, the terminal device 10 transmits the input information to the server 20. Further, for example, when the terminal device 10 is operated by the user, the terminal device 10 transmits information regarding the operation history to the server 20. Further, the terminal device 10 transmits information based on the user's image signal taken by the camera 160 to the server 20 at a predetermined cycle.

The transmission / reception unit 2031 of the server 20 receives information about a plurality of employees transmitted from the terminal device 10, and stores the received information in a new record of the database stored in the storage unit 202.

The acquisition unit 2032 of the server 20 acquires information necessary for determination from the database of the storage unit 202 at a predetermined timing (step S201). Specifically, for example, the acquisition unit 2032 determines from the employee information DB 281, the log information DB 282, or the work information DB 283 of the storage unit 202 whether or not the employee P1 is concerned about mental disorders. Get the information you need. The predetermined timing is, for example, as follows when there is no concern about the mental disorder of the employee P1.
-When you go to work on a preset day (when you press the attendance object in the attendance management app)
-Preset time on a preset day-When data suspected of being mentally ill is acquired Data that is suspected of being mentally ill is, for example, variations in work hours or long hours. Overtime work is continuous, or there is no vacation.

Further, the predetermined timing is, for example, as follows when there is a concern about the mental disorder of the employee P1.
-When going to work-Preset time In this explanation, the processing for employee P1 will be described, but processing may be performed in parallel for other employees.

When the information necessary for the determination is acquired, the determination unit 2033 determines whether or not the employee P1 is concerned about a mental disorder (step S202). Specifically, the determination unit 2033 inputs the acquired information on the working status into the first trained model 284, and outputs whether or not the person is concerned about mental disorders. In the following, a person who is concerned about mental illness will be referred to as a person to be monitored for health management. When the determination unit 2033 determines that the employee P1 is the target person, the determination unit 2033 stores the determination result in, for example, the employee information DB 281 of the storage unit 202, and executes the subsequent processing. In addition, when it is determined to be a target person, there are cases where it is determined to be a target person from a state without concern, and there are cases where the determination to be a target person is maintained.

On the other hand, when the determination unit 2033 determines that the employee P1 is not the target person, the determination unit 2033 ends the process. If it is determined that the person is not the target person, the state of concern may be resolved or the state of concern may be maintained.

When it is determined that the employee P1 is the target person, the dialogue processing unit 2034 creates a question sentence to the employee P1 (step S203). Specifically, the dialogue processing unit 2034 inputs information on the working status of the employee P1 who is determined to be at risk of mental illness into the second learned model 285, and relieves the anxiety or stress of the employee P1. Output the question text for. The interrogative text for relieving the anxiety or stress of the employee P1 is created based on the information regarding the working status of the employee P1.

For example, if yesterday's closing time for employee P1 was late, a question was created to work for employee P1 such as "You worked late last night. Did you take a rest after returning?" Will be done.

Also, for example, if the work time of employee P1 who should normally be regular suddenly becomes irregular, such as "Recently, the work time is irregular, are you worried?" A question that cares for employee P1 is created.

Also, for example, if the employee P1 who should normally go to work on time suddenly becomes late, such as "I've been late a lot lately, are you worried?" A question that cares for employee P1 is created.

Also, for example, if a meeting with the same person is held many times over a long period of time, such as "Long meeting is difficult. Isn't the meeting said to be painful?" , A question that cares for employee P1 is created.

The dialogue processing unit 2034 transmits the output question text from the communication unit 201 to the terminal device 10 (step S204). At this time, the dialogue processing unit 2034 transmits, for example, a question sentence at a timing that makes it easy for the user to answer. As the timing at which the user can easily answer, for example, the timing at which the concentration is not high while operating the terminal device 10 is preferable. The dialogue processing unit 2034 refers to the information on the work situation and determines the timing at which the employee P1 can easily answer the question. The dialogue processing unit 2034 transmits the created question text from the communication unit 201 to the terminal device 10 at the determined timing. The dialogue processing unit 2034 transmits the created question text to the terminal device 10 in a format of inserting it into a part of the chat message.

When the question text is transmitted from the server 20, the presentation unit 184 of the terminal device 10 displays the received question text on the display 132 (step S101). The operation reception unit 181 receives a response from the employee P1 who operates the terminal device 10. The presentation unit 184 displays the input response text on the display 132. The transmission / reception unit 182 transmits the input response text to the server 20 (step S102).

FIG. 8 is a schematic diagram showing a display example of the terminal device 10 according to the present embodiment. As shown in FIG. 8, the chat area 1321 is displayed on the display 132 of the terminal device 10. The question sentence 1321A from the server 20 is displayed in the left column of the chat area 1321, and the answer sentence 1321B input from the employee P1 is displayed in the right column. When the presentation unit 184 receives the question text from the server 20, it displays an object indicating that the reception is received at a predetermined position (for example, a bar) of the display 132, and the employee P1 presses the object. The chat area 1321 may be displayed according to the above.

Upon receiving the response sentence from the terminal device 10, the dialogue processing unit 2034 creates a response sentence to the employee P1 (step S205). Specifically, the dialogue processing unit 2034 inputs the received response sentence and information on the working status into the third trained model 286, and outputs a response sentence corresponding to the input answer. The dialogue processing unit 2034 transmits the output response text from the communication unit 201 to the terminal device 10 (step S206).

When the response text is transmitted from the server 20, the presentation unit 184 of the terminal device 10 displays the received response text on the display 132 (step S103). The operation reception unit 181 receives a response from the employee P1 who operates the terminal device 10. The presentation unit 184 displays the input response text on the display 132. The transmission / reception unit 182 transmits the input response text to the server 20 (step S104). The chat between the employee P1 and the server 20 is continued, for example, until the answer from the employee P1 is no longer input. The contents of the chat between the employee P1 and the server 20 (question text, response text, and answer text) are stored in the storage unit 202. The content of the chat between the employee P1 and the server 20 is stored after the content related to the personal information is processed (for example, deleted) so that it is not determined that the chat is with the employee P1. For example, if the boss of the department to which employee P1 belongs responds that he / she is overstressed through his / her work, this answer is in the state where the information such as the name that identifies the boss is hidden. It is stored in the storage unit 202. The stored information is statistically used, for example, as work style improvement data.

Further, for example, when the employee P1 does not have a meeting or the like on the next day, the server 20 may give a response such as "Why don't you take a day off tomorrow?". When the employee P1 responds to such a response, such as "That's right. I will take a day off.", The execution unit 2035 of the server 20 executes the next day's leave request to the attendance application.

Not limited to the above processing, the steps of each processing can be arbitrarily changed as long as the flow of each processing does not contradict. For example, employee P1 may not reply to the automatic response.

As described above, in the present embodiment, the acquisition unit 2032 of the server 20 acquires the first information regarding the work status of the user. The determination unit 2033 determines whether or not the user is the target person based on the acquired first information and the second information regarding the work status of another user who has been feared to have a mental disorder in the past. When the user is the target person, the dialogue processing unit 2034 creates a question sentence for the user based on the first information. The dialogue processing unit 2034 sends the created question text to the user. Then, the dialogue processing unit 2034 responds to the response from the user to the question sentence. As a result, the server 20 can accurately grasp that the user is concerned about a mental disorder. In addition, the server 20 can hear the true intention of the user's anxiety or stress.
Therefore, according to the system 1 according to the present embodiment, it is possible to confirm and manage the mental state of the employee by listening to the true intention of the work of the employee who is concerned about the mental disorder.

Further, in the present embodiment, the determination unit 2033 inputs the first information to the first trained model 284 learned using the second information, and determines whether or not the user is the target person. I am trying to judge. This makes it possible to quickly and accurately determine whether or not the user is the target person, based on the first information about the user.

Further, in the present embodiment, the dialogue processing unit 2034 inputs the first information to the second trained model 285 learned by using the second information and the question sentence assumed from the second information. By doing so, I try to create a question sentence. This makes it possible to quickly and accurately create a question sentence that can alleviate the user's anxiety or stress based on the first information about the user.

Further, in the present embodiment, the execution unit 2035 executes the attendance procedure in response to the response from the user to the question text. As a result, even if the user does not perform the procedure, the attendance procedure is automatically performed, and it is possible to solve the situation that the user cannot take a rest even if he / she wants to take a rest.

Further, in the present embodiment, the dialogue processing unit 2034 refers to the first information and sends a question sentence at a timing when the user can easily answer. This makes it possible to increase the probability of getting an answer from the user.

Further, in the present embodiment, the control unit 203 processes and stores the contents related to the personal information in the question text to the user and the response from the user. This makes it possible to appropriately protect the personal information of the user himself / herself and the employees around him / her. In addition, it is possible to avoid a disadvantageous situation due to the content input by the user in the chat.

Further, in the present embodiment, the dialogue processing unit 2034 is a third trained model 286 learned by using the second information, the assumed response sentence, and the response sentence and the response sentence assumed from the second information. In response to the above, a new response to the user is created by inputting the first information and the response from the user. This makes it possible to quickly and accurately create a response sentence in response to a response from the user.

<Modification example>
In the above embodiment, an example has been described in which the first trained model 284 is trained to output whether or not the input information about the user is a person who is concerned about a mental disorder. However, the training of the first trained model 284 is not limited to this.

For example, the first trained model 284 may be trained to output the degree of mental upset with respect to the input information about the user. The degree of mental illness includes, for example, fear of mental illness, mild mental illness, severe mental illness, and the like. At this time, for the learning data, for example, information on the past work status of the employee is used as input data, and the degree of mental upset with respect to this input data is used as correct output data.

In step S202, the determination unit 2033 inputs information regarding the work status to the first trained model 284, and outputs the degree of mental disorder. When it is output that the mental disorder is feared, the mental disorder is mild, or the mental disorder is severe, it indicates that the user is the target person. When the determination unit 2033 determines that the user is the target person, the determination unit 2033 stores the determination result including the degree of mental disorder in the storage unit 202, for example, the employee information DB 281. By determining the degree of mental illness, it becomes possible to manage the mental state of the employee in more detail.

Further, the first trained model 284 may be trained to output a stress factor as well as output whether or not the person is concerned about mental disorders with respect to the input information about the user. The stress factor is a factor that causes stress, and includes, for example, a large amount of overtime hours, a boss, a subordinate, a customer, a life rhythm, and the like. At this time, for the learning data, for example, information on the past work status of the employee is used as input data, and for this input data, it is judged whether or not the person is concerned about mental disorders, and the stress factor is output correctly. Let it be data.

In step S202, the determination unit 2033 inputs information on the work status into the first trained model 284, and outputs a stress factor together with whether or not the person is concerned about mental disorders. When the determination unit 2033 determines that the user is the target person, the determination unit 2033 stores the determination result including the stress factor in, for example, the employee information DB 281 of the storage unit 202. By determining the stress factor in addition to the mental disorder, it becomes possible to understand the cause of the mental disorder of the employee.

Further, in the above embodiment, an example has been described in which the second trained model 285 is trained to output a question for relieving anxiety, stress, or the like with respect to the input information about the user. However, the training of the second trained model 285 is not limited to this.

For example, the second trained model 285 may be trained to output a question for relieving anxiety, stress, or the like in response to input of information about the user and the degree of mental upset. At this time, as the learning data, information on the past work status of the user for each degree of mental disorder is used as input data, and the question text created according to the degree is used as correct answer output data. The question text as the correct answer output data is created so as to, for example, extract a predetermined wording from the information on the working situation, consider the degree of mental disorder, and relieve anxiety or stress.

In step S203, the dialogue processing unit 2034 inputs information on the work status of the employee whose degree of mental disorder is determined into the second learned model 285, and asks a question to relieve the anxiety or stress of the employee. Is output. Since the question text will be created considering the degree of mental upset, it will be possible to more effectively relieve the anxiety or stress of the employee.

Further, for example, the second trained model 285 may be trained to output a question for relieving anxiety, stress, or the like in response to the input of information about the user and the stress factor. At this time, as the learning data, the information about the work situation and the stress factor of the user who has been feared to have a mental disorder in the past are used as input data, and the question text based on the input information is used as the correct answer output data. The question text as the correct answer output data is created so as to relieve anxiety or stress by extracting a predetermined wording from, for example, information on the work situation and a stress factor.

In step S203, the dialogue processing unit 2034 transfers information on the work status of the determined employee who is at risk of mental illness and the stress factor estimated by the determination unit 2033 into the second trained model 285. Enter and output a question to relieve employee anxiety or stress. Since the question text that considers the stress factor is created, it becomes possible to more effectively relieve the anxiety or stress of the employee.

In the above embodiment, the first trained model 284 to the third trained model 286 may be retrained based on the feedback information. For example, the control unit 203 acquires feedback information for the determination result by the determination unit 2033. The feedback information may be, for example, an evaluation from the user for the determination, or an evaluation based on the content of the chat constructed between the user and the server 20. The control unit 203 relearns the first trained model 284 by using the weighted work status information based on the feedback information and the determination result. As a result, new teacher data will be added, and the accuracy of the determination using the first trained model 284 can be improved with the lapse of the usage period.

Further, for example, the control unit 203 acquires feedback information for the question text created by the dialogue processing unit 2034. The feedback information may be, for example, an evaluation from the user for the created question text, or an evaluation based on the content of the chat constructed between the user and the server 20. The control unit 203 relearns the second trained model 285 by using the weighted work status information based on the feedback information and the created question sentence. As a result, new teacher data will be added, and the content of the question text created using the second trained model 285 will become more suitable as the usage period elapses.

Further, for example, the control unit 203 acquires feedback information about the response to the response sentence from the user created by the dialogue processing unit 2034. The feedback information may be, for example, an evaluation from the user regarding the response to the response sentence, or an evaluation based on the content of the chat constructed between the user and the server 20. The control unit 203 relearns the third trained model 286 by using the weighted work status information based on the feedback information, the input response sentence, and the created response sentence. As a result, new teacher data will be added, and the content of the response sentence created using the third trained model 286 will become more suitable as the usage period elapses.

Further, in the above embodiment, the degree of mental disorder of the user is not determined based on the content of the chat between the user and the server 20. However, the degree of mental upset of the user may be determined based on the content of the chat between the user and the server 20. At this time, the storage unit 202 stores, for example, the fourth trained model. The fourth trained model is a model used for determining the degree of mental upset of a user based on, for example, the content of a chat between the user and the server 20. The fourth trained model is trained to output the degree of mental upset in response to the answer input from the user. At this time, for the learning data, for example, the past answer pattern input from the employee who is feared to have a mental disorder is used as the input data, and the judgment of the degree of the mental disorder with respect to the input data is used as the correct answer output data. do. By determining the degree of mental disorder of the user from the content of the chat, it is possible to respond according to the determined degree.

Further, the fourth trained model may be trained to determine that there is no mental disorder in addition to the degree of the user's mental disorder. At this time, for the learning data, for example, the past answer pattern input from the employee who is feared to have a mental disorder is used as the input data, and the judgment that there is no mental disorder for this input data is the correct answer output data. And.

The control unit 203 may relearn the fourth trained model using the feedback information.

Further, in the above embodiment, the case where the storage unit 202 stores a plurality of trained models has been described as an example, but the storage unit 202 does not have to store the trained model. A predetermined calculation table or a predetermined function may be stored in the storage unit 202, and these data may be used in the processing in the control unit 203.

Further, in the above embodiment, the case where the determination unit 2033 uses the first trained model 284 to determine whether or not the user is a monitoring target who is concerned about mental disorders has been described as an example. However, in the present embodiment, the determination unit 2033 uses the first trained model 284 to determine whether or not the person is concerned about mental health problems and whether or not the person is concerned about a decrease in motivation. You may.

At this time, for example, the first trained model 284 outputs, for example, a numerical value indicating that there is a concern about mental health problems and a numerical value indicating that there is a concern about a decrease in motivation for the input information regarding the user. Have been learned. For the learning data, for example, information on the past work status of the employee is used as input data, and it is judged whether or not the person is concerned about mental health problems and whether or not the person is concerned about a decrease in motivation for this input data. This judgment is used as the correct output data.

The determination unit 2033 is based on, for example, a numerical value indicating that the mental health disorder is feared and a numerical value indicating that the motivation is feared to be lowered, and the user is a person who has no mental disorder or the mental health disorder. Is a person who is concerned about, or a person who is concerned about a decrease in motivation.

When the determination unit 2033 determines whether the user has no mental disorder, is concerned about mental health disorder, or is concerned about decreased motivation, the dialogue processing unit 2034 determines. Creates a question sentence according to the judgment result. Specifically, for example, using the second trained model 285 for those who are concerned about mental health problems, a question is created for those who are concerned about mental health problems, and for those who are concerned about declining motivation. Using the second trained model 285, a question sentence is created for those who are concerned about a decrease in motivation.

Further, in the above embodiment, the case where the dialogue processing unit 2034 sends a question sentence according to the target person to the target person based on the determination result of the determination unit 2033 has been described. However, in the present embodiment, a predetermined notification may be transmitted to the manager of the target person based on the determination result of the determination unit 2033. The manager is, for example, the subject's boss, specialist, or a predetermined person in charge. The predetermined notification is, for example, a notification of being a target person or a notification of predetermined information. The notification of predetermined information includes, for example, a notification that a face-to-face meeting is necessary, a notification of information on working hours, a notification that overtime should be reduced, and the like.

Although the preferred embodiments of the present disclosure have been described above, the present disclosure is not limited to such specific embodiments, and the present disclosure includes the inventions described in the claims and the equivalent scope thereof. Is done. Further, the configurations of the devices described in the above-described embodiments and modifications can be appropriately combined as long as there is no technical contradiction.

<Additional Notes>
The matters described in each of the above embodiments will be added below.

(Appendix 1)
A program for causing a computer having a processor and a memory to execute the program, wherein the program causes the processor to execute the program.
The step of acquiring the first information regarding the work status of the user (step S201) and
A step of determining whether or not the user is a target person based on the acquired first information and the second information regarding the working status of another user who has been feared to have a mental disorder in the past (step S202). When,
When the user is the target person, a step (step S203) of creating a question sentence for the user based on the first information, and
A step (step S204) of transmitting the created question text to the user, and
A step (step S206) of responding to a response from the user to the question text,
A program to execute.

(Appendix 2)
By inputting the first information to the first trained model learned using the second information in the determination step (step S202), whether or not the user is the target person is determined. Judgment, the program according to (Appendix 1).

(Appendix 3)
The first trained model is trained using stress factors that other users who have been concerned about mental disorders in the past feel stressed.
In the determination step (step S202),
The program according to (Appendix 2), which estimates a stress factor by inputting the first information to the first trained model.

(Appendix 4)
The program according to (Appendix 2) or (Appendix 3), which causes the processor to perform a step of re-learning the first trained model using the information fed back from the user who is determined to be the target person. ..

(Appendix 5)
In the step of creating the question sentence (step S203),
By inputting the first information into the second trained model trained using the second information and the question sentence assumed from the second information, the question sentence is created (( The program described in any of Appendix 1) to (Appendix 4).

(Appendix 6)
The second trained model is trained using stress factors that other users who have been concerned about mental disorders in the past feel stressed.
In the step of creating the question sentence (step S203),
The program according to (Appendix 5), wherein the question sentence is created by inputting the first information and the stress factor estimated in the determination step into the second trained model.

(Appendix 7)
The program according to (Appendix 5) or (Appendix 6), which causes the processor to perform a step of re-learning the second trained model using the information returned from the user to the question sentence.

(Appendix 8)
The program according to any one of (Appendix 1) to (Appendix 7), which causes the processor to execute a step of estimating the degree of mental disorder of the user based on the response from the user to the question text.

(Appendix 9)
The program according to any one of (Appendix 1) to (Appendix 8), which causes the processor to execute a step of executing an attendance procedure in response to a response from the user to the question text.

(Appendix 10)
In the step (step S204) of transmitting the created question text to the user.
The program according to any one of (Appendix 1) to (Appendix 9), which refers to the first information and transmits the question sentence at a timing when the user can easily answer.

(Appendix 11)
The program according to (Appendix 10), wherein the timing at which the user can easily answer is a timing at which the user does not have high concentration while operating the terminal.

(Appendix 12)
The program according to any one of (Appendix 1) to (Appendix 11), which causes the processor to execute a step of processing and storing the contents related to personal information in a question text to the user and a response from the user.

(Appendix 13)
For the third trained model trained using the second information, the assumed response sentence, and the response sentence and the response sentence assumed from the second information in the response step (step S206). The program according to any one of (Appendix 1) to (Appendix 12), which creates a new response to the user by inputting the first information and the response from the user.

(Appendix 14)
The step of acquiring the first information regarding the work status of the user (step S201) and
A step of determining whether or not the user is a target person based on the acquired first information and the second information regarding the working status of another user who has been feared to have a mental disorder in the past (step S202). When,
When the user is the target person, a step (step S203) of creating a question sentence for the user based on the first information, and
A step (step S204) of transmitting the created question text to the user, and
A step (step S206) of responding to a response from the user to the question text,
How to carry out.

(Appendix 15)
The means to obtain the first information about the user's work status,
A means for determining whether or not the user is a target person based on the acquired first information and the second information regarding the work status of another user who has been feared to have a mental disorder in the past.
When the user is a target person, a means for creating a question sentence for the user based on the first information, and
A means of transmitting the created question text to the user,
A system provided with means for responding to a response from the user to the question text.

1 ... System 10 ... Terminal device 121 ... Communication unit 13 ... Input device 130 ... Operation input unit 131 ... Touch sensitive device 132 ... Display 1321 ... Chat area 1321A ... Question text 1321B ... Answer text 14 ... Output device 140 ... Voice processing Unit 141 ... Mike 142 ... Speaker 15 ... Memory 150 ... Position information sensor 16 ... Storage unit 160 ... Camera 170 ... Storage unit 171 ... Employee information 180 ... Control unit 181 ... Operation reception unit 182 ... Transmission / output unit 183 ... Acquisition unit 184 ... Presentation unit 19 ... Processor 20 ... Server 201 ... Communication unit 202 ... Storage unit 203 ... Control unit 2031 ... Transmission / output unit 2032 ... Acquisition unit 2033 ... Judgment unit 2034 ... Dialogue processing unit 2035 ... Execution unit 25 ... Memory 26 ... Storage 281 ... Employee Member information DB
282 ... Log information DB
283 ... Work information DB
284 ... 1st trained model 285 ... 2nd trained model 286 ... 3rd trained model 29 ... Processor

Claims (15)

A program for causing a computer having a processor and a memory to execute the program, wherein the program causes the processor to execute the program.
The step to acquire the first information about the user's work status,
A step of determining whether or not the user is a target person based on the acquired first information and the second information regarding the work status of another user who has been feared to have a mental disorder in the past.
When the user is a target person, a step of creating a question sentence for the user based on the first information, and
The step of sending the created question text to the user, and
A step of responding to a response from the user to the question text,
A program to execute. A claim for determining whether or not the user is the target person by inputting the first information to the first trained model learned using the second information in the determination step. The program according to Item 1. The first trained model is trained using stress factors that other users who have been concerned about mental disorders in the past feel stressed.
In the determination step
The program according to claim 2, wherein the stress factor is estimated by inputting the first information to the first trained model. The program according to claim 2 or 3, wherein the processor is made to perform a step of re-learning the first trained model using the information fed back from the user who is determined to be the target person. In the step of creating the question text,
A claim for creating the question text by inputting the first information to the second trained model trained using the second information and the question text assumed from the second information. The program according to any one of Items 1 to 4. The second trained model is trained using stress factors that other users who have been concerned about mental disorders in the past feel stressed.
In the step of creating the question text,
The program according to claim 5, wherein the question sentence is created by inputting the first information and the stress factor estimated in the determination step into the second trained model. The program according to claim 5 or 6, wherein the processor is made to perform a step of re-learning the second trained model using the information returned from the user to the question sentence. The program according to any one of claims 1 to 7, wherein the processor executes a step of estimating the degree of mental disorder of the user based on the response from the user to the question text. The program according to any one of claims 1 to 8, wherein the processor executes a step of executing an attendance procedure in response to a response from the user to the question text. In the step of sending the created question text to the user
The program according to any one of claims 1 to 9, which refers to the first information and transmits the question text at a timing when the user can easily answer. The program according to claim 10, wherein the timing at which the user can easily answer is a timing at which the user does not have high concentration while operating the terminal. The program according to any one of claims 1 to 11, wherein the processor executes a step of processing and storing the contents related to personal information in a question text to the user and a response from the user. With respect to the third trained model trained using the second information, the expected response sentence, the response sentence, and the response sentence assumed from the second information in the response step, the first step is made. 1. The program according to any one of claims 1 to 12, which creates a new response to the user by inputting information and a response from the user. The step to acquire the first information about the user's work status,
A step of determining whether or not the user is a target person based on the acquired first information and the second information regarding the work status of another user who has been feared to have a mental disorder in the past.
When the user is a target person, a step of creating a question sentence for the user based on the first information, and
The step of sending the created question text to the user, and
A step of responding to a response from the user to the question text,
How to carry out. The means to obtain the first information about the user's work status,
A means for determining whether or not the user is a target person based on the acquired first information and the second information regarding the work status of another user who has been feared to have a mental disorder in the past.
When the user is a target person, a means for creating a question sentence for the user based on the first information, and
A means of transmitting the created question text to the user,
A system provided with means for responding to a response from the user to the question text.

Images