Business support system, business support method, and business support program

Abstract

This technology provides techniques for taking specific actions to engage users for health management or morale improvement. [Solution] A computer-based business support system for supporting business establishments where administrators and those managed by the administrators coexist, comprising: a countermeasure information generation step instructing an AI to input images of those managed and generate health measures to be output to those managed for the purpose of health management or morale improvement; and a health measure output step in which the health measures generated by the AI ​​are output to the managers.

Description

【Technical Field】 【0001】 The present invention relates to an office support system, an office support method, and an office support program. 【Background Art】 【0002】 Patent Document 1 discloses an information processing apparatus including: an acquisition unit that acquires a machine learning model learned to estimate health information indicating a health state from biological information; a mapping unit that maps a user's health information to a latent space of the machine learning model, and an estimation unit that estimates ideal biological information, which is biological information corresponding to desired health information indicating a desired health state of the user, based on first health feature information corresponding to the user's health information mapped to the latent space. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2023-180124 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In the above technology, the health degree of a user is mapped to the latent space of a pre-learned machine learning model M1. Thus, based on the first health feature information corresponding to the health degree of the user mapped to the latent space, by gradually changing the value of the latent variable in the latent space from the first health feature information, it becomes possible to generate the first health feature information corresponding to the health degree of the user from the health degree of the user. However, since it does not perform a specific action on the user for health management or morale improvement, a practical effect cannot be directly obtained. 【0005】 An object of the present invention is to provide a technology that performs a specific action on a user for health management or morale improvement. [Means for solving the problem] 【0006】 The present invention includes several means for solving at least some of the above problems, but an example is as follows. A business support system according to one aspect of the present invention is a business support system executed by a computer system for supporting a business where an administrator and an administrator-managed person coexist, and includes a countermeasure information generation step of inputting an image of an administrator-managed person and instructing the AI ​​to generate health measures to be output to the administrator-managed person for the purpose of health management or morale improvement of the administrator-managed person, and a health measure output step of outputting the health measures generated by the AI ​​to the administrator-managed person. 【0007】 Furthermore, the above-mentioned business support system may also include the step of acquiring images of the person being managed from a camera installed in a device that records attendance. 【0008】 Furthermore, in the above-described business support system, the countermeasure information generation step may also include instructing the AI ​​to analyze the facial expressions of the person being managed using an image of the person being managed, to identify the type of facial expression from a plurality of types including stress, fatigue, joy, and sadness, and to determine the health or mental state of the person being managed based on the type of facial expression and generate health countermeasures. 【0009】 Furthermore, the above-described business support system may also include a voice acquisition step that acquires the voice of the person being managed, and in the countermeasure information generation step, it may instruct the AI ​​to analyze at least one of the tone, volume, pitch, and speed of the voice to evaluate stress and emotional changes, and to generate the health countermeasures using the results of the evaluation. 【0010】 Furthermore, the above-described business support system may also include a facial expression and voice acquisition step that acquires the facial expressions and voices of the person being managed, and in the countermeasure information generation step, the facial expressions and voices obtained as a result of outputting predetermined facial expressions and voices to be seen and heard by the person being managed are acquired in the facial expression and voice acquisition step, and the AI ​​is instructed to analyze any of the facial expressions or voices to identify the type of facial expression from a plurality of facial expression types including stress, fatigue, joy, sadness, anger, surprise, fear, disgust, contempt, interest, confusion, relief, and expectation, evaluate the change in emotion, and use the results of the evaluation to generate the health countermeasures. 【0011】 Furthermore, in the above-described business support system, the countermeasure information generation step may also include instructing the AI ​​to analyze the walking pattern or posture of the person being managed using the values ​​of the human body recognition sensor, and to generate the health countermeasures using the results of the analysis. 【0012】 Furthermore, in the above-described business support system, the countermeasure information generation step may also instruct the AI ​​to generate health measures, including providing positive messages or fun jokes to the person being managed. 【0013】 Furthermore, the above-mentioned business support system may also store the past health status and warning history of the person being managed, and in the countermeasure information generation step, it may instruct the AI ​​to input the past health status and the history of health countermeasures of the person being managed, and to generate health countermeasures that include a thoughtful message for the person being managed who has been the target of a warning in the past. 【0014】 Furthermore, in the above-described business support system, the countermeasure information generation step may also be instructed to generate health measures that include information to attempt to instill positive expressions in the person being managed, such as displaying an image of the person being managed with a brighter expression to those who are being managed with a negative expression, outputting a positive voice message to make them stop, and so on. 【0015】 Furthermore, the above-mentioned business support system may also include a report creation step in which the system stores the past health status and warning history of the person being managed, and instructs the AI ​​to generate a report indicating the health status of the person being managed. 【0016】 Furthermore, the above-mentioned business support system may also include a step in which the countermeasure information generation step is instructed to analyze changes in the employee's facial expressions and posture in response to being spoken to, predict the possibility of business or financial misconduct, and generate countermeasures. 【0017】 Furthermore, another aspect of the present invention relates to a business support method for a business establishment where an administrator and an administrator who is managed by the administrator coexist, and is performed by a computer system, comprising: a countermeasure information generation step of inputting an image of an administrator to an AI and instructing the AI ​​to generate health measures to be output to the administrator for the purpose of health management or morale improvement of the administrator; and a health measure output step of outputting the health measures generated by the AI ​​to the administrator. 【0018】 Moreover, a workplace support program according to another aspect of the present invention is a workplace support program for operating a computer system for supporting a workplace where an administrator and subordinates managed by the administrator coexist. The program causes an AI to perform a countermeasure information generation step of inputting an image of a subordinate and instructing the AI to generate health countermeasures to be output to the subordinate for health management or morale improvement of the subordinate, and a health countermeasure output step of outputting the health countermeasures generated by the AI to the subordinate. Here, subordinates include external contractors (consultants, repair inspections, security, etc.) and temporary employees (seasonal workers, part-time workers, etc.). 【Advantages of the Invention】 【0019】 According to the present invention, it is possible to provide a technology for performing a specific approach to a user for health management or morale improvement. 【0020】 Problems, configurations, and effects other than those described above will be clarified by the description of the following embodiments. 【Brief Description of the Drawings】 【0021】 [Figure 1A] It is a configuration diagram of a workplace support system according to an embodiment. [Figure 1B] It is a configuration diagram showing another configuration example of the workplace support system according to the present embodiment. [Figure 2] It is a diagram showing a configuration example of a server device. [Figure 3] It is a diagram showing a data structure example of user information. [Figure 4] It is a diagram showing a data structure example of attendance record information. [Figure 5] It is a diagram showing a data structure example of detection information. [Figure 6] It is a diagram showing a data structure example of countermeasure information. [Figure 7] It is a diagram showing a data structure example of report information. [Figure 8]This figure shows an example of the hardware configuration of a server device. [Figure 9] This figure shows an example of the hardware configuration of an attendance recording device. [Figure 10] This diagram shows an example of the time clocking process flow. [Figure 11] This diagram shows an example of the report creation process flow. [Figure 12] This figure shows an example of a countermeasure information display screen. [Figure 13] This figure shows an example of a report information display screen. [Modes for carrying out the invention] 【0022】 Below, a business support system 1 applying an embodiment according to one aspect of the present invention will be described with reference to the drawings. In the following embodiments, when necessary for convenience, the description will be divided into multiple sections or embodiments. Unless otherwise specified, these are not unrelated, and one may be a modification, detail, or supplementary explanation of part or all of the other. 【0023】 Furthermore, in the following embodiments, when referring to the number of elements (including the number of elements, numerical values, quantities, ranges, etc.), unless specifically stated or clearly limited in principle to a particular number, it is not limited to that particular number, and may be greater than or less than that number. 【0024】 Furthermore, it goes without saying that in the following embodiments, the constituent elements (including elemental steps, etc.) are not necessarily essential, except in cases where they are specifically indicated or where they are clearly essential in principle. 【0025】 Similarly, in the following embodiments, when referring to the shape, positional relationship, etc., of components, unless otherwise specifically stated or when it is clearly not the case in principle, it shall include those that substantially approximate or resemble such shapes, etc. The same applies to the numerical values ​​and ranges mentioned above. 【0026】 Furthermore, in all the drawings used to illustrate the embodiments, the same reference numerals are generally used for identical components, and repeated explanations of them are omitted. 【0027】 Figure 1A is a diagram illustrating the configuration of the business support system according to this embodiment. The business support system 1 is a system that supports business establishments where managers and those managed by the manager coexist. For example, a manager is a person in a position to manage employees, such as the head of the business establishment or the management team. Those managed are, for example, employees, part-time workers, and sometimes employees or contractors of business partners or subcontractors. The business support system 1 includes a server device 100, an attendance recording device 200, and a generation AI service 300. Those managed, such as employees, use the attendance recording device 200 to perform actions for managing working hours when they arrive at or leave work, such as clocking in or clocking out. The server device 100 communicates with the attendance recording device 200 and controls the operation of the attendance recording device 200. 【0028】 The Generative AI Service 300 is a service that provides the functions of so-called Generative AI, such as GPT and Gemini, via an API (Application Programming Interface). The Generative AI Service 300 obtains desired results such as text, images, audio, and video by giving commands (prompts) in natural language to the Generative AI. The Generative AI Service 300 may utilize publicly available services such as ChatGPT, which are published on the internet. Furthermore, the Generative AI Service 300 may also be AGI (Artificial General Intelligence) or ASI (Artificial Superintelligence). 【0029】 In this embodiment, the generation AI service 300, upon receiving instructions, for example via an API, causes the generation AI to generate information and sends the result to the source of the instructions as a return value of the API. At that time, the generation AI receives various detection information of the person being managed (mainly image information such as videos and still images, and audio information such as speech) detected by the attendance recording device 200, and outputs, for example, health measure information that should be output to the person being managed for health management or morale improvement in accordance with instructions from the source (for example, health measures including providing positive messages or fun jokes to the person being managed). Alternatively, regardless of instructions from the source, the generation AI outputs health measure information according to predetermined settings. The generation AI has been trained through deep learning and machine learning to output health measure information that should be output to the person being managed for health management or morale improvement, using various detection information of the person being managed detected by the attendance recording device 200 as input information. 【0030】 Furthermore, the generation AI service 300, upon receiving instructions for report creation along with past health status and warning history, generates a report indicating the health status of the person being managed. The generation AI has been trained through deep learning and machine learning to output a report indicating the health status of the person being managed, using the various health statuses and warning history of the person being managed detected by the attendance record device 200 as input information. However, it is not limited to this, and the generation AI service 300 may also obtain health information by searching for it from other devices via the internet or other means at runtime. 【0031】 The server device 100 responds to various requests from the attendance recording device 200 via a data transmission protocol. For example, when the server device 100 receives a request from the attendance recording device 200 to record attendance times, it identifies the person to be recorded and stores the information in attendance record information 122. The server device 100 also receives imaging data and sound data from the attendance recording device 200, identifies the person to be recorded, and stores the information in detection information 123. After storing the detection information 123, the server device 100 passes the past detection information of the person to the generating AI and instructs it to create countermeasure information. The server device then displays the created countermeasure information on the attendance recording device 200. Figure 1B shows another example of the configuration of the business support system according to this embodiment, where the business support system 1A includes the server device 100A, the attendance recording device 200A, the generating AI service 300A, and the user terminal 400A. Employees and other managed personnel use the attendance recording device 200A to perform tasks such as clocking in and out or entering the gate for work time management purposes. The server device 100A communicates with the attendance recording device 200A and controls its operation. The attendance recording device 200A exchanges information with each device, such as the imaging unit 210A, sound collection unit 220A, human body recognition unit 230A, and clocking unit 240A, either directly or through communication. The attendance recording device 200A may also be equipped with a backup system of the server device 100A's processing unit 110A and storage unit 120A, for example, to enable simplified operation in case communication with other devices via the data communication network 50 is not possible. Furthermore, the user terminal 400A communicates with other devices via the data communication network 50 and can connect to the attendance recording device 200A as appropriate even if communication with other devices via the data communication network 50 is not possible. This enables emergency responses in the event of system failures or other emergencies to be carried out from the user terminal 400A. Furthermore, the health monitoring output unit 260A can also be installed on the user terminal 400A. Additionally, the generated AI service 300A may encompass the functions and configuration of the server device 100, and may also encompass the attendance recording device 200A, or it may control the processing performed by each processing unit of the attendance recording device 200A.Furthermore, the attendance recording device 200A may be equipped with an AI processing circuit equivalent to that of the generation AI service 300A. In addition, the attendance recording device 200A can connect to expert AIs (e.g., legal consultation AI) or other business AIs (e.g., employee health management AI) via the data communication network 50. Alternatively, the generation AI service 300 may be included within the attendance recording device 200A. Also, the user terminal 400A and the attendance recording device 200A may be connected to communicate without going through a data communication network 50 such as the internet. The data communication network 50 may be configured as an internal LAN. Furthermore, the business support system 1A may be made operational even in the event of problems such as internet line errors. In addition, it is possible to operate using only the internal system's AI without using external generation AI services, ignoring or excluding other expert AIs. 【0032】 Figure 2 shows an example of the configuration of a server device. The server device 100 comprises a processing unit 110, a storage unit 120, and a communication unit 130. The storage unit 120 includes user information 121, attendance record information 122, detection information 123, countermeasure information 124, and report information 125. The processing unit 110 includes a countermeasure information generation unit 111, an output generation unit 112, an attendance record unit 113, and a report creation unit 114. 【0033】 Figure 3 shows an example of the data structure of user information. User information 121 includes user ID 121a and identification feature information 121b. User ID 121a is information that identifies the user (employee, etc.) from other managed persons. Identification feature information 121b is the features that distinguish a managed person from other managed persons when identifying them. For example, this could be various types of information such as a facial image, appearance, or voice. Note that user ID 121a may be coded information such as a QR code (registered trademark) or a URL. 【0034】 Figure 4 shows an example of the data structure for attendance record information. Attendance record information 122 includes user ID 122a, attendance date and time 122b, and departure date and time 122c. User ID 122a is information that identifies the user (employee, etc.) from other managed persons. Attendance date and time 122b is information that identifies the date and time when the managed person arrived at work. Departure date and time 122c is information that identifies the date and time when the managed person left work. In addition, although not shown in this example, attendance records may be recorded multiple times on the same day, such as for business trips within working hours from the start to the end of work. 【0035】 Figure 5 shows an example of the data structure of detection information. Detection information 123 includes user ID 123a, date and time 123b, and detection information 123c. User ID 123a is information that identifies the user (employee, etc.) from other managed persons. Date and time 123b is information that identifies the date and time when the managed person was detected. Detection information 123c is various detection information of the managed person (mainly image information such as videos and still images, and audio information such as speech) obtained when the managed person was detected. Although not shown in this example, it may be possible to record detection information multiple times on the same day. 【0036】 Figure 6 shows an example of the data structure of the countermeasure information. Countermeasure information 124 includes user ID 124a, date and time 124b, and countermeasure information 124c. User ID 124a is information that identifies the user, who is a person under management (employee, etc.), from other persons under management. Date and time 124b is information that identifies the date and time when the server device 100 obtained the person's health countermeasure information from the generation AI service 300. Countermeasure information 124c is the person's health countermeasure information obtained by the server device 100 from the generation AI service 300. Although not shown here, it is also possible to record the output of countermeasure information multiple times on the same day. 【0037】 Figure 7 shows an example of the data structure of report information. Report information 125 includes user ID 125a, analysis period 125b, and report data 125c. User ID 125a is information that identifies the user (employee, etc.) from other managed persons. Analysis period 125b is information that specifies the period to be analyzed in the report that analyzes the health information of the managed persons. Report data 125c is report data on the health of the managed persons obtained by the server device 100 from the generated AI service 300. 【0038】 The countermeasure information generation unit 111 is a processing unit that instructs the generation AI service 300 to input images of the person being managed (especially their face, gait, body movements, facial expressions, etc.) and to generate health measures to be output to the person being managed for the purpose of health management or morale improvement. The countermeasure information generation unit 111 acquires images of the person being managed from a camera installed in the attendance recorder 200. Although not shown here, it is also possible to generate countermeasure information multiple times on the same day. 【0039】 Furthermore, the countermeasure information generation unit 111 instructs the generation AI service 300 to analyze the facial expressions of the person being managed using an image of the person being managed, identify the type of facial expression from among several types including stress, fatigue, joy, and sadness, and then determine the person's health or mental state based on the type of facial expression to generate health countermeasures. In addition, other emotions such as anger, surprise, fear, disgust, contempt, interest, confusion, relief, and expectation may also be added to health countermeasures if ethical issues are resolved. 【0040】 In this embodiment, the emotional circle model (also known as Russell's circle model) is adopted as the type of emotion or facial expression. The emotional circle model is a dimension on which various emotions are arranged, with emotions represented by mutually independent two-dimensional axes (Arousal: degree of arousal and Valence: emotional valence (pleasant / unpleasant)). Various emotions such as happy, excited, tense, stressed, sad, calm, and relaxed are arranged on the circle of the emotional circle model. Therefore, in this embodiment, the generating AI service 300 identifies the type of emotion or facial expression based on Russell's circle model described above. However, it is not limited to this, and other types of emotions or facial expressions may be adopted. 【0041】 Furthermore, the countermeasure information generation unit 111 instructs the generation AI service 300 to analyze at least one of the tone, volume, pitch, and speed of the voice spoken by the person being managed (for example, greetings or introductions) to evaluate stress and emotional changes, and to generate health countermeasures using the results of the evaluation. The countermeasure information generation unit 111 acquires the voice spoken by the person being managed from a microphone installed in the attendance recording device 200. In addition, the countermeasure information generation unit 111 may instruct the generation AI service 300 to determine if the person is suffering from a physical ailment, such as back or knee pain, based on the image of the person being managed, including their gait and behavior leading up to the imaging device, for example, the movement of their left and right feet. Not limited to physical ailments, the countermeasure information generation unit 111 may also instruct the generation AI service 300 to determine if the person is experiencing psychological stress, such as worries, if they are moving their eyes around restlessly. To this end, for example, it is preferable to provide space so that the person being monitored walks a certain distance (for example, 5 meters, preferably around 8 meters) in front of the camera. Furthermore, it is even more desirable to image the person being monitored from the side, diagonally in front, and behind. 【0042】 Furthermore, the countermeasure information generation unit 111 instructs the generation AI service 300 to analyze the gait pattern or posture of the person being managed using the values ​​from the human body recognition sensor, and to generate health countermeasures using the results of the analysis. The countermeasure information generation unit 111 acquires the person's body information from the human body recognition sensor installed in the attendance recording device 200. 【0043】 Furthermore, the countermeasure information generation unit 111 instructs the generation AI service 300 to analyze the posture of the person being managed using data from the motion capture system, and to generate health countermeasures, including messages that warn of prolonged poor posture and suggest improvements, using the results of the analysis. The countermeasure information generation unit 111 acquires the motion capture data of the person being managed from a camera installed in the attendance recording device 200. 【0044】 Furthermore, the countermeasure information generation unit 111 instructs the generation AI service 300 to generate health measures, including providing positive messages or fun jokes to the person being managed. 【0045】 Furthermore, the countermeasure information generation unit 111 inputs the past health status and health countermeasure history of the person being managed, and instructs the generation AI service 300 to generate health countermeasures, including thoughtful messages for those who have been subject to warnings in the past. 【0046】 Furthermore, the countermeasure information generation unit 111 instructs the generation AI service 300 to generate health countermeasures that include information to display an image of the person being managed with a brighter expression to those who are being managed with a negative expression, output a positive message voice to make them stop, and attempt to instill a positive expression in the person being managed. 【0047】 Furthermore, the countermeasure information generation unit 111 instructs the generation AI service 300 to analyze changes in the employee's facial expressions and posture in response to being spoken to, predict the possibility of work-related or financial misconduct, and generate countermeasures. 【0048】 The output generation unit 112 is a processing unit that outputs the health measures generated by the generation AI service 300 to the person being managed. 【0049】 When the attendance recording unit 113 receives an instruction from the attendance recording device 200 to record an attendance or departure date, it records the date and time the person being managed arrived at work and the date and time they left work. 【0050】 The report generation unit 114 instructs the generation AI service 300 to generate a report showing the changes in the health status of the person under management over a predetermined period. 【0051】 The communication unit 130 communicates with the attendance record device 200 and the generation AI service 300 via a data communication network and the internet, etc. 【0052】 Returning to the explanation of Figure 1A, the attendance recording device 200 comprises an imaging unit 210, a sound collection unit 220, a human body recognition unit 230, a time stamping unit 240, a communication unit 250, and a health measures output unit 260. The imaging unit 210 captures video or still images at a predetermined field of view. For example, the imaging unit 210 captures the figure of the person being managed who is operating the attendance recording device 200, including their facial expression. The sound collection unit 220 collects sound within a predetermined range. For example, the sound collection unit 220 collects the speech of the person being managed who is operating the attendance recording device 200. The human body recognition unit 230 captures video or still images at a predetermined field of view. For example, the human body recognition unit 230 acquires the person's body information using a human body recognition sensor. 【0053】 The time stamping unit 240 identifies the date and time when the employee arrives at work and the date and time when the employee leaves work, and requests the server device 100 to record this information. The time stamping unit 240 also uses the imaging unit 210, the sound collection unit 220, and the human body recognition unit 230 to detect information about the employee when they arrive at or leave work. 【0054】 The communication unit 250 communicates with the server device 100 via a data communication network and the internet, etc. 【0055】 The health management output unit 260 receives instructions from the server device 100, receives health management and report data, and outputs it. If the output content includes voice output (such as greetings or verbal encouragement), the health management output unit 260 outputs the voice; if it includes image display, the health management output unit 260 displays the image (including still images and videos). For example, the health management output unit 260 outputs voice messages such as greetings and everyday conversations with the person being managed (e.g., "It's a nice day today," or "You worked hard until late yesterday"). It may not be limited to simple conversations, but may also include questions about the progress of work, or, after a holiday, questions about places visited during the holiday and whether they enjoyed themselves. In this case, a robot that speaks while walking or a robot speaker that travels on rails may be responsible for outputting the conversation, and the health management output unit 260 may control its operation. 【0056】 Furthermore, instead of a walking path in front of the camera, the system may be equipped with moving walkways, escalators, elevators, or other mobility devices, and a robot may run alongside the user at a speed appropriate to their movement speed and engage in conversation. In addition, to make it easier for the managed individual to speak, privacy may be respected, and guidance may be provided to maintain a distance between the managed individual and those in front of them on moving walkways and escalators, and elevators may be limited to one person at a time. Furthermore, a system may be provided in which the managed individual is transported in a cart. These mobility devices may be equipped with imaging devices and conversation devices, and may also be equipped with biometric information acquisition devices that measure body temperature, pulse, blood pressure, blood alcohol concentration, and facial color. In addition, during activities within the company, the user may be encouraged to wear a wearable terminal that can measure, for example, body temperature, pulse, and blood pressure. This is particularly effective in high-temperature work, work at height, and hazardous work environments. The measurement results may also be collected in a timely manner on the server device 100. 【0057】 Figure 8 shows an example of the hardware configuration of the server device 100. The server device 100 has a hardware configuration that is realized by the casing of a so-called server device, workstation, personal computer, smartphone, or tablet terminal. The server device 100 includes a processor 101, memory 102, storage 103, communication device 104, and a bus connecting each device. 【0058】 The processor 101 is a computing device such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit). 【0059】 Memory 102 is a memory device such as RAM (Random Access Memory). 【0060】 Storage 103 is a non-volatile storage device capable of storing digital information, such as a hard disk drive, solid state drive (SSD), or flash memory. 【0061】 The communication device 104 is a network interface card (NIC) or the like that communicates with other devices via the data communication network 50. 【0062】 The countermeasure information generation unit 111, output generation unit 112, attendance record unit 113, and report creation unit 114 of the server device 100 described above are implemented by a program that causes the processor 101 to perform processing. This program is stored in memory 102, storage 103, or a ROM device (not shown), and is loaded into memory 102 for execution and executed by the processor 101. 【0063】 Furthermore, the storage unit 120 of the server device 100, user information 121, attendance record information 122, detection information 123, countermeasure information 124, and report information 125 are realized by the memory 102 and storage 103. The above is an example of the hardware configuration of the server device 100. 【0064】 The configuration of the server device 100 can be further classified into many components depending on the processing content. Alternatively, it can be classified so that a single component performs even more processing. 【0065】 Furthermore, each processing unit (countermeasure information generation unit 111, output generation unit 112, attendance record unit 113, report creation unit 114) may be constructed using dedicated hardware (ASIC, GPU, etc.) to realize its respective function. Also, the processing of each processing unit may be executed on a single piece of hardware or on multiple pieces of hardware. The information processing device that realizes the generation AI service 300 is envisioned as a cloud service, but is not limited to this, and may have a hardware configuration that is basically the same as that of the server device 100. 【0066】 Figure 9 shows an example of the hardware configuration of the attendance recording device. The attendance recording device 200 also has basically the same hardware configuration as the server device 100. The attendance recording device 200 includes a processor 101, memory 102, storage 103, communication device 104, input / output device 205, camera 206, microphone 207, and a bus connecting each device. 【0067】 The input / output device 205 is a device that combines a display device such as a liquid crystal display or an organic EL display with various input devices such as a touch panel, hardware buttons, a keyboard, and a mouse. The time stamping unit 240 and the health monitoring output unit 260 are realized by the input / output device 205, the processor 101, the memory 102, the storage 103, and the communication device 104. 【0068】 Camera 206 captures video or still images at a predetermined angle of view. The imaging unit 210 is implemented by camera 206, processor 101, memory 102, storage 103, and communication device 104. The human body recognition unit 230 is implemented by camera 206, processor 101, memory 102, storage 103, and communication device 104. 【0069】 The microphone 207 collects sound within a predetermined range. The sound collection unit 220 is realized by the microphone 207, processor 101, memory 102, storage 103, and communication device 104. 【0070】 Furthermore, the processing of each component of the attendance recording device 200 may be performed on one piece of hardware or on multiple pieces of hardware. Also, the processing of each component of the attendance recording device 200 may be implemented by one program or by multiple programs. 【0071】 The above is an example of the hardware configuration of the attendance recording device 200. 【0072】 Each component of the attendance recording device 200 can be further classified into many more components depending on the processing content. Alternatively, each component can be classified to perform even more processing. 【0073】 Furthermore, each processing unit (imaging unit 210, sound collection unit 220, human body recognition unit 230, time stamping unit 240, communication unit 250, health countermeasure output unit 260) may be constructed using dedicated hardware (ASIC, GPU, etc.) to realize its respective function. Also, the processing of each processing unit may be executed on a single piece of hardware or on multiple pieces of hardware. 【0074】 Next, the operation of the business support system 1 in this embodiment will be described. 【0075】 Figure 10 shows an example of the time clocking process flow. When the attendance recording device 200 is activated, it enters a standby state and starts when the person being managed makes an operation to the attendance recording device 200. 【0076】 First, the time stamping unit 240 of the attendance recording device 200 receives user ID information read from the managed person's ID card, such as a magnetic card or IC card, and an attendance / departure classification indicating whether the managed person is recording their attendance or departure (step S001). 【0077】 The attendance recording device 200 then performs imaging and sound collection (step S002). Specifically, the imaging unit 210, sound collection unit 220, and human body recognition unit 230 acquire video or still images including facial expressions, speech audio data, and human body information of the person being managed, respectively. However, it is not limited to this, and the imaging unit 210 and human body recognition unit 230 may also treat the walking and standing postures of the person being managed as they approach the attendance recording device 200 as human body information by taking images of them in advance. 【0078】 Then, the time-stamping unit 240 of the attendance recording device 200 transmits the attendance record to the server device 100 (step S003). Specifically, the time-stamping unit 240 transmits the user ID and the attendance category to the server device 100. 【0079】 The attendance record unit 113 of the server device 100 authenticates and stores the information in the attendance record (step S004). Specifically, when the attendance record unit 113 receives a user ID, it authenticates it and stores the attendance record information 122 with the attendance date and time or the departure date and time according to the attendance category. 【0080】 Then, the time-stamping unit 240 of the attendance recording device 200 transmits the detection information to the server device 100 (step S005). Specifically, the time-stamping unit 240 transmits the user ID and the detection information detected in step S002 to the server device 100. 【0081】 The attendance record unit 113 of the server device 100 authenticates and stores the detection information in the detection information 123 (step S006). Specifically, when the attendance record unit 113 receives a user ID, it authenticates and stores the detection information in the detection information 123 for each person managed. 【0082】 Then, the countermeasure information generation unit 111 instructs the generation of countermeasure information to be displayed (step S007). Specifically, the countermeasure information generation unit 111 extracts detection information of the person under management from the detection information 123 for a predetermined period in the past (for example, the most recent month), transmits the detection information of the person under management and the past detection information of the person under management to the generation AI service 300, and instructs the generation of countermeasure information to be displayed. The instruction to generate countermeasure information is based on the instruction to create health countermeasure information to be output to the person under management, but may also include specifying a type of facial expression from a plurality of types of facial expressions that include stress, fatigue, joy, or sadness, and instructing the system to determine the health or mental state of the person under management based on the type of facial expression and generate health countermeasures. 【0083】 Furthermore, the instruction to generate countermeasure information may also involve analyzing at least one of the tone, volume, pitch, and speed of the managed person's speech to evaluate stress and emotional changes, and then using the results of this evaluation to generate health countermeasures. Moreover, the instruction to generate countermeasure information may also involve presenting the managed person with facial expressions or voices generated from images or videos, analyzing the results of either the managed person's facial expression or the facial expression of their response, identifying the type of facial expression from a plurality of types including stress, fatigue, joy, sadness, anger, surprise, fear, disgust, contempt, interest, confusion, relief, and expectation, evaluating emotional changes, and then using the results of this evaluation to generate the aforementioned health countermeasures. In reality, facial expressions, gait, body movements, and voice production are easily influenced by individual differences, regional variations, and culture, making it difficult to judge them using the same standards as others. Therefore, collecting information on an individual managed person basis and analyzing the emotional expressions of each managed person on a regular basis will improve accuracy. For this reason, it is desirable for the countermeasure information generation unit 111 to analyze and accumulate emotional changes as data. Alternatively, the data analysis and aggregation can be performed by the generation AI service 300. 【0084】 Furthermore, instructions for creating countermeasures information may also include instructions to analyze the walking patterns or posture of the person being managed using the values ​​from a human body recognition sensor, and to generate health countermeasures using the results of that analysis. 【0085】 Furthermore, instructions for creating countermeasures information may also include instructions to analyze the posture of the person being managed using data from the motion capture system, and to generate health measures that include messages warning of prolonged poor posture and suggestions for improvement using the results of that analysis. 【0086】 Furthermore, instructions for creating countermeasures information may also include instructions for generating health measures that include providing positive messages or lighthearted jokes to those being managed. 【0087】 Furthermore, instructions for creating countermeasure information may also include instructions to generate health measures that include thoughtful and considerate messages for managers who have previously been subject to warnings, based on their past health status and history of health measures. 【0088】 Furthermore, instructions for creating countermeasures information may also include instructions to generate health measures that include information to attempt to instill positive expressions in the person being managed, such as displaying an image of the person with a brighter expression to those with negative expressions, outputting positive audio messages that speak to the person, or making them stop and stand still. 【0089】 Furthermore, instructions to create countermeasures information may also include instructing employees to analyze changes in their facial expressions and posture in response to verbal cues, predict the possibility of work-related or financial misconduct, and generate countermeasures accordingly. 【0090】 The generation AI service 300 creates countermeasure information in response to the generation instruction and sends the countermeasure information to the server device 100 (step S008). 【0091】 Then, the countermeasure information generation unit 111 stores the countermeasure information transmitted from the generation AI service 300 in the countermeasure information 124 (step S009). 【0092】 Then, the output generation unit 112 transmits the countermeasure information to the attendance record device 200 (step S010). 【0093】 The health countermeasure output unit 260 displays the countermeasure information (step S011). 【0094】 The above is an example of a time clock processing flow. The time clock processing allows for the display of health measures that should be output to the employee in question for health management or morale improvement, enabling specific actions to be taken. 【0095】 Figure 11 shows an example of the report creation process flow. The report creation process starts when the server device 100 receives an operation from an administrator (such as the head of the business or management, or any person in a position to manage employees). 【0096】 First, the report generation unit 114 accepts the specification of the reporting period and the target individuals (step S401). Then, the report generation unit 114 acquires attendance records, detection information, and countermeasure information for each target individual for the reporting period (step S402). Specifically, the report generation unit 114 extracts attendance records for the reporting period from the attendance record information 122 in the storage unit 120, detection information from the detection information 123 in the storage unit 120, and countermeasure information from the countermeasure information 124 in the storage unit 120, as RAG information. 【0097】 Then, the report creation unit 114 prompts the generation AI service 300 to create a report (step S403). Specifically, for each subject, the report creation unit 114 analyzes the attendance records, detection information, and countermeasure information for the reporting period extracted as RAG information, and uses the results of the analysis to create a prompt instructing the generation AI service 300 to create a report, and passes it to the generation AI service 300. Then, the report creation unit 114 receives the report data from the generation AI service 300 (step S404). Then, the report creation unit 114 stores it in the report information 125 (step S405). 【0098】 The above is an example of the report generation process flow. This report generation process allows for an objective analysis of the health and mental state of the person being managed, based on monitoring data over a specified period. 【0099】 Figure 12 shows an example of a countermeasure information display screen. The countermeasure information display screen 700 is the screen on which countermeasure information is displayed in step S011 of the time clock process. The countermeasure information display screen 700 displays an image 701 of the person under management whose negative expression in the captured image has been changed to a brighter expression. In addition, the countermeasure information display screen 700 displays a positive message 702 for the person under management. 【0100】 Figure 13 shows an example of a report information display screen. The report information display screen 800 is an example of a screen used to display the stored report information in step S405 of the report creation process. 【0101】 The report information display screen 800 includes a user ID display area 801, an image of the person being managed 802, an analysis graph 810, and a message display 820. The analysis graph 810 uses time on the horizontal axis 811 and a measured quantity on the vertical axis 812, plotting, for example, an index of mental health 813, the number of abnormal movements 814, an index of emotional information 815, and the number of poor postures 816, visualizing the trends of change. The message display 820 describes warning information and the analysis results of health trends in natural language. 【0102】 The above describes the Business Support System 1. As demonstrated in the above embodiment, the Business Support System 1 allows for specific actions to be taken with users for health management or morale improvement. However, it is important to ensure transparency and consent regarding the means, timing, and content of acquiring information on those under management, to protect privacy, to conduct regular health checkups, to establish a mental health support desk (creating an environment where employees can consult if they are experiencing stress or mental health problems), and to formulate ethical guidelines (implemented with transparency for employees). Furthermore, it is considered important to raise awareness throughout the organization by implementing education and training (education and training on ethics and compliance for employees). In light of these points, it is desirable to adopt programs, support systems, and operating methods that combine these functions. In addition, it may be beneficial to connect with other expert AIs and exchange information. 【0103】 Furthermore, emotions, states, and facial expressions at that time can be associated as follows. Therefore, the countermeasure information generation unit 111 can instruct the generation AI service 300 to identify emotions from the facial expressions contained in the captured image according to the following correspondence. Joy: Expresses feelings of happiness and satisfaction: a smile, sparkle in the eyes Sadness: Shows disappointment or a sense of loss: Corners of the mouth droop, eyes well up with tears. Anger: Expresses frustration or hostility: Frowning, pursed lips Surprise: Reaction to an unexpected event: Eyes widen, mouth agape Fear: A reaction to danger or threat: Eyes widen, eyebrows raised. Disgust: A gesture of displeasure or rejection, such as frowning or twisting the mouth. Contempt: Expresses feelings of looking down on others: Raises one corner of the mouth. Interest / Attention: To show that you are paying attention: widen your eyes and slightly raise your eyebrows. Confusion: A reaction to an incomprehensible situation: furrowing brows and slightly opening the mouth. Relief: Represents a state of release of tension; facial muscles are relaxed, and the expression is calm. Expectation: A state of anticipation for good things: eyes sparkling, a smile on one's lips Fatigue: Describes a tired state: eyes half-closed, corners of the mouth drooping. Doubt: To show that you doubt something: Raise one eyebrow and pucker your lips. Satisfaction: Expresses a feeling of contentment: A gentle smile, relaxed eyes. Tension: A state of feeling stressed or under pressure: Facial muscles become rigid, and the eyes become sharp. 【0104】 Furthermore, emotions and voices are associated as follows. Therefore, the countermeasure information generation unit 111 can instruct the generation AI service 300 to identify emotions from the acquired voices according to the following correspondence. Emotions: Voice characteristics Joy: A bright, high-pitched tone, a rhythmic way of speaking. Sadness: Low, slow tone, weakened voice. Anger: Strong voice, rapid speech, sometimes trembling voice Surprise: The voice suddenly gets higher, and the words break. Fear: Trembling voice, speaking quickly Nervousness: Voice becomes stiff, words get stuck, speaking speed is irregular. Excitement: High tone of voice, fast speaking, increased volume Boring: monotonous tone, slow speech, little intonation. Confidence: Clear pronunciation, stable tone and rhythm Anxiety: voice trembling, frequent hesitation of words, rapid speech Contempt: A sarcastic tone, a cold-sounding voice. 【0105】 Furthermore, emotions and walking patterns are associated as follows. Therefore, the countermeasure information generation unit 111 can instruct the generation AI service 300 to identify emotions from the acquired walking patterns according to the following correspondence. Joy: A light and rhythmic way of walking, a skipping motion, and long strides. Sadness: Slow gait, slumped shoulders. A heavy impression, downward gaze. Anger: A strong, fast walk, loud footsteps, and large arm swings. Surprise: Walking stops for a moment, movements are irregular, sudden stops. Fear: Small steps, walking cautiously, careful movements, occasionally looking back. Tension: Awkward walking, stiff movements, raised shoulders, limited arm swing. Excitement: Fast walking, active movement, energetic, long strides Boredom: Slow walking, lack of energy in movement, unfocused gaze, looking around. Confidence: Stand tall, walk with a firm gait, maintain a steady stride, and keep your gaze forward. Anxiety: Irregular gait, restless movements, frequent stopping, looking around. Contempt: A slow gait, condescending movements, occasionally stopping to look down on others. 【0106】 Furthermore, emotions and "body movements" are associated as follows. Therefore, the countermeasure information generation unit 111 can instruct the generation AI service 300 to identify emotions from the "body movements" of the person being managed, which are identified from the acquired images, in accordance with the following correspondence. Joy: Smiling, jumping, clapping. Light and cheerful movements, energetic impression. Sadness: Leaning forward, shoulders slumped. A heavy, subdued impression, slow movements. Anger: Shaking hands forcefully, frowning. Intense movements, a tense impression. Surprise: Eyes widen, mouth agape. Sudden movement, instantaneous reaction. Fear: Shrinking the body, being wary of the surroundings. A defensive posture, cautious movements. Tension: Rubbing hands together, shaking feet. Awkward movements, an unstable impression. Excitement: Swinging arms widely, moving quickly. Lively and energetic movements. Boredom: Crossing legs, averting gaze. Giving an impression of indifference, monotonous movements. Confidence: Standing tall with a straight back, a firm gait. A dignified appearance, stable movements. Anxiety: Frequently looking around, rubbing hands together. Restless movements, giving an impression of being wary. Contempt: Narrowing eyes, raising one eyebrow. A cold impression, slow movements. 【0107】 Furthermore, "physical condition" and "characteristics" are associated as follows. Therefore, the countermeasure information generation unit 111 can instruct the generation AI service 300 to identify the physical condition from the "characteristics" of the person being managed, according to the following correspondence. Physical condition: characteristics Fatigue: Expressionless face = eyes half-closed Poor posture = rounded back, drooping shoulders Movement = slower actions, shorter strides Voice tone = weak voice, increased sighing Energy levels decrease, making you easily fatigued. High stress: Facial expressions = furrowed brow, squinting eyes Poor posture = raised shoulders, clenched chin Movement = shaking feet, snapping fingers Voice tone = shallow, rapid breathing, increased sighing Energy = restless movement, a cautious impression Joy: Expression = smiling, eyes sparkling Posture = a relaxed posture with a straight spine. Movement = light and rhythmic movement, lively movement Voice tone = bright, clear voice, often laughter Energy = having vitality and acting proactively Sadness: Facial expression = corners of the mouth droop, eyes watery. Poor posture = hunched over, drooping shoulders Movement = slow movement, decreased activity Voice tone = weak, low voice, speaking less frequently Energy levels decrease, making you easily fatigued. 【0108】 The present invention is not limited to the embodiments described above. The embodiments described above can be modified in various ways within the scope of the technical idea of ​​the present invention. For example, the functions of the server device 100 may be realized by a system consisting of one or more computers. 【0109】 Furthermore, the technical elements of the embodiments described above may be applied individually, or they may be divided into multiple parts, such as program components and hardware components, and applied accordingly. 【0110】 The present invention has been described above, focusing on its embodiments. [Explanation of symbols] 【0111】 1...Business office support system, 50...Data communication network, 100...Server device, 110...Processing unit, 111...Countermeasure information generation unit, 112...Output generation unit, 113...Attendance record unit, 114...Report creation unit, 120...Storage unit, 121...User information, 122...Attendance record information, 123...Detection information, 124...Countermeasure information, 125...Report information, 130...Communication unit, 200...Attendance record device, 210...Imaging unit, 220...Sound collection unit, 230...Human body recognition unit, 240...Time stamping unit, 250...Communication unit, 260...Health countermeasure output unit, 300...Generating AI service.

Claims

[Claim 1] A business support system implemented by a computer system to support business establishments where administrators and those managed by said administrators coexist, A step of generating countermeasure information in which an image of the person to be managed is input to the AI, and the AI ​​is instructed to generate health measures to be output to the person to manage their health or improve their morale, A health measures output step which outputs the health measures generated by the AI ​​to the person being managed, A business support system that performs the following tasks. [Claim 2] A business support system according to claim 1, further, The steps include: acquiring an image of the person being managed from a camera installed in a device that records attendance times; A business support system that performs the following tasks. [Claim 3] A business support system according to claim 1, further, In the aforementioned countermeasure information generation step, The AI ​​is instructed to analyze the facial expressions of the person being managed using an image of the person being managed, to identify the type of facial expression from among several types including stress, fatigue, joy, and sadness, and to determine the health or mental state of the person being managed based on the type of facial expression, and to generate the health measures described above. Business support system. [Claim 4] A business support system according to claim 1, further, The voice acquisition step is performed to acquire the voice of the person being managed, In the aforementioned countermeasure information generation step, The AI ​​is instructed to analyze the voice, at least one of its tone, volume, pitch, and speed, to evaluate stress and emotional changes, and to use the results of the evaluation to generate the health measures. Business support system. [Claim 5] A business support system according to claim 1, further, The facial expression and voice acquisition step is performed to acquire the facial expressions and voice of the person being managed. In the aforementioned countermeasure information generation step, In the facial expression and voice acquisition step, the facial expressions and voices obtained as a result of outputting predetermined facial expressions and voices to be seen and heard by the person being managed are acquired, and the AI ​​is instructed to analyze any of the facial expressions or voices to identify the type of facial expression from among multiple types including stress, fatigue, joy, sadness, anger, surprise, fear, disgust, contempt, interest, confusion, relief, and expectation, evaluate the change in emotion, and use the results of the evaluation to generate the health measures. Business support system. [Claim 6] A business support system according to claim 1, further, In the aforementioned countermeasure information generation step, The AI ​​is instructed to analyze the walking pattern, body movements, and posture of the person being managed using the values ​​from the human body recognition sensor, and to generate the health measures using the results of the analysis. Business support system. [Claim 7] A business support system according to claim 1, further, In the aforementioned countermeasure information generation step, The AI ​​is instructed to generate health measures, including providing positive messages or humorous jokes to the person being managed. Business support system. [Claim 8] A business support system according to claim 1, further, The system stores the past health status and warning history of the person being managed. In the aforementioned countermeasure information generation step, The AI ​​is instructed to input the past health status and health measures history of the person being managed, and to generate health measures that include thoughtful and considerate messages for the person being managed who has previously been subject to warnings. Business support system. [Claim 9] A business support system according to claim 1, further, In the aforementioned countermeasure information generation step, The AI ​​is instructed to generate health measures that include information to attempt to instill positive facial expressions in the person being managed, such as displaying an image of the person being managed with a brighter expression to those who are being managed with a negative expression, and outputting a positive voice message. Business support system. [Claim 10] A business support system according to claim 1, further, The system stores the past health status and warning history of the person being managed. A report creation step in which the AI ​​is instructed to generate a report showing the health status of the person being managed, A business support system that implements this functionality. [Claim 11] A business support system according to claim 1, further, In the aforementioned countermeasure information generation step, the AI ​​is instructed to analyze changes in the employee's facial expressions and posture in response to being spoken to, predict the possibility of work-related or financial misconduct, and generate countermeasures. Business support system. [Claim 12] A method for supporting a business establishment that is implemented by a computer system, for supporting a business establishment where an administrator and an administrator who manages such an administrator coexist, A step of generating countermeasure information in which an image of the person to be managed is input to the AI, and the AI ​​is instructed to generate health measures to be output to the person to manage their health or improve their morale, A health measures output step which outputs the health measures generated by the AI ​​to the person being managed, A method of supporting businesses that implement this. [Claim 13] A business support program that operates a computer system to support business establishments where administrators and those managed by said administrators coexist, A step of generating countermeasure information in which an image of the person to be managed is input to the AI, and the AI ​​is instructed to generate health measures to be output to the person to manage their health or improve their morale, A health measures output step which outputs the health measures generated by the AI ​​to the person being managed, A support program for businesses that implements this.

Images