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 business support system, executed by a computer system, for supporting business establishments where administrators and those managed by the administrators coexist, comprising: a step of generating countermeasure information in which a video of the managed person is input to a generating AI, the AI ​​analyzes the managed person from observation points in the video image diagnosis, and uses the results of the analysis to generate health measures to be output to the managed person for health management or morale improvement; The process includes a health measures output step in which the health measures generated by the generation AI are output to the person being managed.

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 describes 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 the health information of a user 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 health information of the user mapped to the latent space.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the above technique, the health level of a user is mapped to the latent space of a machine learning model M1 that has been learned in advance. As a result, based on the first health feature information corresponding to the health level 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 level of the user from the health level 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 technique for performing 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. One aspect of the present invention is a business support system executed by a computer system for supporting a business office where an administrator and an administrator-managed person coexist, comprising a step of generating countermeasure information in which a generating AI is instructed to input video images of an administrator, analyze the administrator's walking pattern, body movements, and posture from observation points in the video image diagnosis, and use the results of the analysis to generate health countermeasures to be output to the administrator for health management or morale improvement of the administrator, A health measures output step which outputs the health measures generated by the generation AI to the person being managed, To do so.

[0007] Furthermore, a business support method implemented by a computer system for supporting business establishments where administrators and those managed by such administrators coexist, A step of generating countermeasure information involves inputting an image of the person being managed into a generating AI, analyzing the person's walking pattern, body movements, and posture, and instructing the AI ​​to generate health measures to be output to the person for health management or morale improvement using the results of the analysis. The system includes a health measures output step, which outputs the health measures generated by the generation AI to the person being managed.

[0008] Furthermore, a business support program that operates a computer system to support business establishments where administrators and those managed by such administrators coexist, A step of generating countermeasure information involves inputting an image of the person being managed into a generating AI, analyzing the person's walking pattern, body movements, and posture, and instructing the AI ​​to generate health measures to be output to the person for health management or morale improvement using the results of the analysis. A health measures output step which outputs the health measures generated by the generation AI to the person being managed, Have them do it. [Effects of the Invention]

[0009] According to the present invention, it is possible to provide technology that enables specific interventions for users in order to manage their health or improve their morale.

[0010] Other issues, configurations, and effects not mentioned above will be clarified by the following description of the embodiments. [Brief explanation of the drawing]

[0011] [Figure 1A] This is a diagram illustrating the configuration of the business support system according to the embodiment. [Figure 1B] This is a configuration diagram showing another example of the business support system according to this embodiment. [Figure 2] This figure shows an example of a server device configuration. [Figure 3] This figure shows an example of a data structure for user information. [Figure 4] This figure shows an example of the data structure for attendance record information. [Figure 5] This figure shows an example of the data structure of detection information. [Figure 6] This figure shows an example of the data structure for countermeasure information. [Figure 7] This figure shows an example of the data structure 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]It is a diagram showing an example of a flow of engraving processing. [Figure 11] It is a diagram showing an example of a flow of report creation processing. [Figure 12] It is a diagram showing an example of a countermeasure information display screen. [Figure 13] It is a diagram showing an example of a report information display screen.

Mode for Carrying Out the Invention

[0012] Hereinafter, a business office support system 1 to which an embodiment according to one aspect of the present invention is applied will be described with reference to the drawings. In the following embodiments, when necessary for convenience, they will be divided and described in a plurality of sections or embodiments. However, unless otherwise specified, they are not unrelated to each other, and one is related to a modification example, details, supplementary explanation, etc. of part or all of the other.

[0013] Also, in the following embodiments, when referring to the number of elements, etc. (including the number, numerical value, quantity, range, etc.), unless otherwise specified and in cases where it is clearly limited to a specific number in principle, it is not limited to that specific number, and it may be more than or less than the specific number.

[0014] Furthermore, in the following embodiments, it goes without saying that the constituent elements (including element steps, etc.) are not necessarily essential unless otherwise specified and in cases where they are clearly considered essential in principle.

[0015] Similarly, in the following embodiments, when referring to the shape, positional relationship, etc. of the constituent elements, etc., unless otherwise specified and in cases where it is clearly not considered so in principle, it includes those substantially approximate or similar to the shape, etc. This also applies to the above numerical values and ranges.

[0016] Also, in all the drawings for explaining the embodiments, the same members are basically given the same reference numerals, and the repeated explanations thereof are omitted.

[0017] 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.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] Furthermore, the countermeasure information generation unit 111 instructs the generation AI service 300 to analyze at least one of the voice characteristics (voice tone, volume, pitch, speed) of the voice spoken by the person being managed (e.g., 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 rapidly moving their eyes around. 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.

[0032] Furthermore, the countermeasure information generation unit 111 instructs the generation AI service 300 to analyze the person being managed by video image diagnosis based on walking patterns, movements, posture, etc., using the values ​​from the human body recognition sensor or captured images (video), and to generate health countermeasures using the results of the analysis. The countermeasure information generation unit 111 acquires the person being managed's body information from the human body recognition sensor installed in the attendance recording device 200.

[0033] 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.

[0034] In video image diagnosis, the countermeasure information generation unit 111 can instruct the generation AI service 300 to diagnose at least one item described in the "Video Diagnosis Observation Point Overview" below, for example, and output an "Overview of Observation Points and Symptoms / Disorders," and obtain the output results. By obtaining these observation points, specific examples, examples of operating phenomena, and suspected symptoms / disorders, the generation AI service can be made to perform diagnoses with greater accuracy.

[0035] Alternatively, when performing video image diagnosis, the countermeasure information generation unit 111 can input at least one item from the "Overview of Video Diagnosis Observation Points" and at least one item from the "Overview of Observation Points and Symptoms / Discomforts" into the generation AI service 300 to perform the diagnosis. By inputting these observation points, specific examples, examples of behavioral phenomena, and suspected symptoms / discomforts, the generation AI service can be made to perform the diagnosis with greater accuracy.

[0036] [Table 1]

[0037] [Table 2]

[0038] Here, we have compiled examples of symptoms and physical ailments that can be inferred from the phenomena (movemental characteristics) and observed in videos and images based on walking and movement. However, it is also possible to add body parts, symptoms, and specific diseases from the perspectives of "orthopedics, neurology, gastroenterology" or "respiratory medicine, cardiology."

[0039] 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.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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.

[0046] 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.

[0047] 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.

[0048] 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.

[0049] The communication unit 250 communicates with the server device 100 via a data communication network and the internet, etc.

[0050] 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 it. In this case, a robot that walks and speaks, or a robot speaker that travels on rails, may accompany or walk alongside the unit and output the conversation, with the health management output unit 260 controlling its operation.

[0051] 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.

[0052] 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.

[0053] The processor 101 is a computing device such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit).

[0054] Memory 102 is a memory device such as RAM (Random Access Memory).

[0055] 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.

[0056] The communication device 104 is a network interface card (NIC) or the like that communicates with other devices via the data communication network 50.

[0057] 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.

[0058] 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.

[0059] 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.

[0060] 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.

[0061] 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.

[0062] 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.

[0063] 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.

[0064] 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.

[0065] 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.

[0066] The above is an example of the hardware configuration of the attendance recording device 200.

[0067] 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.

[0068] 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.

[0069] Next, the operation of the business support system 1 in this embodiment will be described.

[0070] 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.

[0071] 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).

[0072] 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.

[0073] 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.

[0074] 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.

[0075] 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.

[0076] 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.

[0077] 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.

[0078] Furthermore, instructions for generating countermeasures information may also involve analyzing at least one of the following aspects of the managed person's speech: voice characteristics (tone, volume, pitch, speed) and footstep patterns, to evaluate stress and emotional changes, and then using the results of this evaluation to generate health countermeasures. Alternatively, instructions for generating countermeasures information may involve presenting the managed person with facial expressions or voices generated from images or videos, analyzing the results to obtain either the managed person's facial expression or the facial expression of their response, identifying the type of facial expression from a range of expressions including stress, fatigue, joy, sadness, anger, surprise, fear, disgust, contempt, interest, confusion, relief, and anticipation, evaluating emotional changes, and then using the results of this evaluation to generate the aforementioned health countermeasures. Because facial expressions, gait, body movements, and voice production are inherently influenced by individual differences, regional variations, and culture, it may not be possible to judge them using the same criteria as others. Therefore, regularly collecting information on an individual managed person basis and analyzing their emotional expressions will improve accuracy. Therefore, it is desirable that the countermeasure information generation unit 111 analyzes and accumulates emotional fluctuations as data. Alternatively, the generation AI service 300 may be entrusted with the analysis and accumulation of this data.

[0079] 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.

[0080] 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.

[0081] 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.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] Furthermore, instructions for creating countermeasure information may include instructing users to discuss topics such as work or household finances during conversations. Additionally, instructions for creating countermeasure information may include instructing users to transform negative expressions from those conversations into positive ones, encouraging confirmation and creating a more positive or uplifting atmosphere. Furthermore, when discussing negative topics, instead of forcing a cheerful tone, consciously following a flow of "empathy → positive perspective → encouragement and appreciation → future-oriented and positive conclusion" will result in more natural and uplifting responses. Therefore, instructions for creating countermeasures information may include the following points, advice, specific substitution examples, and key phrases. 1. First, empathize. Before jumping straight into a positive response, acknowledging the other person's feelings by saying things like, "That must have been tough," or "That must have been difficult," can build trust. 2. Subtly point out and communicate the positive aspects and areas of progress. Even in negative situations, we pick out the "efforts we made," "lessons learned," and "positive elements." 3. Add words that specifically acknowledge the other person's existence and efforts. Examples include "Thanks to you," "It wouldn't be possible without you," and "You've been a great help." 4. Let's think about and support the future together. The conversation ends with a phrase that leaves the impression of looking ahead, such as, "We're just one step away from here," "Today will surely be the day," or "Let's take it easy."

[0086] Specific replacement examples Example 1: If the work is not finished Employee: "I couldn't finish my work yesterday, so I stayed late and I'm exhausted." Administrator (example): "You've truly worked so hard. I think it's amazing that you were able to tackle such a difficult job! Are you almost finished? Please don't push yourself too hard today. If you have any problems, please don't hesitate to let me know." Example 2: In case of injury Employee: "I tripped on the stairs at the station yesterday and scraped my right leg, so it hurts." Administrator (example): "That must have been terrible. But I'm so glad you weren't seriously injured. Please take it easy and walk carefully today. This will serve as a reminder to everyone! Thank you for letting me know." Example 3: When you lack motivation or feel exhausted Employee: "Lately, I just don't feel very motivated..." Administrator (example): "Everyone has days like that, right? But I think it's important to go at your own pace without pushing yourself too hard. Let's start with what you can do at your own pace, [Name]. Thank you for always working so hard!" The above is an example of what happens when work is finished. Employee: "I somehow managed to finish my work yesterday." Administrator (example): "Great job! Your ability to see things through to the end is definitely one of your strengths, [Name]." "This is the result of your hard work, even staying late. You must feel relieved now that you've reached a milestone, right?" "I'm so glad it all went smoothly. Please relax a little today as you prepare for the next step." "You've completed a very demanding job so well, that's impressive. Seeing the results is very encouraging!" Key points of the phrase: Specific praise for "what was accomplished" Appreciation for "hard work" and "process" Expectations for the future and suggestions for refreshing oneself

[0087] Furthermore, to ensure that the words are naturally internalized as if they were spoken by the employee themselves, the generating AI can be instructed to rephrase the statements as if the employee were speaking them. In other words, by giving the person being managed the feeling that they themselves spoke positive words (rewriting their self-talk), it is possible to enhance memory retention and the effect of shifting their mood. Therefore, the instructions for creating countermeasures against the generating AI may include the following: Techniques and innovations: Express it in "your own words" →When the AI ​​responds, it will rephrase the response in the first person, as if the employee themselves were speaking. Make it short and concise. → Not redundant, but makes you think, "I could say that too." It ends with confirmation or prompting. → This naturally leads to feelings like, "I can definitely do it," and "Okay, let's do our best." Actual conversation examples Employee (negative comments): "I have to finish this job by the end of this week. What a pain." AI (Self-talk rewritten version): "Now that I think about it, there are still three days left this week, and I'm sure everything will be alright if I talk to someone. Let's start with what we can do!" Employee (negative comments): "I've been having trouble finding motivation lately..." AI (Self-talk rewritten version): "These things happen. Don't push yourself too hard. Today, let's do what we can at our own pace. Don't blame yourself, and take it one step at a time." Employee (negative comments): "I couldn't finish my work yesterday. I'm so tired." AI (Self-talk rewritten version): "You really did a great job yesterday. We're almost there, so let's take it easy today too. I'm not so bad for what I've accomplished!" Implementation image The AI ​​not only speaks in the second person, but also reconstructs positive words as first-person self-talk. Promoting smooth "self-dialogue" → Employees naturally internalize positive ways of speaking. Continuing this will have a positive effect on the employees' own "thinking patterns" and self-image. Additional advice Example guidance for employees: "Please read the words the AI ​​returned to you again in your head. It's okay to say them aloud softly." This approach will improve retention! 1. Self-reflection style arrangement Self-reflection is the process of looking back on one's own actions, emotions, and events. This method aims to lead to "awareness" and "positive interpretation." Specific example Employee (negative comments) "I have to finish this job by the end of this week. What a pain." AI (Self-Reflection Transformation) "I just realized I'm feeling anxious. But I still have three days, and if I can find a better way to approach it, I might be able to get through it. These kinds of experiences are what help me grow." Employee (negative comments) "I've been having trouble finding motivation lately..." AI (Self-Reflection Transformation) "There will be times when you just don't feel motivated. There's no need to be too hard on yourself for that. Just start with something small, and it'll be okay if you gradually get back into the swing of things." Employee (negative comments) "I couldn't finish my work yesterday. I'm so tired." AI (Self-Reflection Transformation) "I really worked hard yesterday. I didn't finish everything, but being able to get this far is proof of my efforts. Let's try to make a little more progress today." Furthermore, the instructions for creating countermeasures against the generating AI may include the following: Other “self-transforming” methods • Affirmations (positive self-declarations) By verbally encouraging and affirming yourself with phrases like "I can do it" and "I've overcome challenges before," you can form a positive self-image. Example: "I've overcome every difficulty up until now. I'm sure I can overcome this one too." • Reframing (framework transformation) It changes your perspective on things, allowing you to reinterpret the same facts in a more positive light. Example: "I fell behind on my work" → "There's still an opportunity to find areas for improvement." Solution-focused approach Instead of focusing on the problem, we should focus on "what should happen next" and "what can be done." Example: "How can we make this situation even a little bit better?" "So, what should we start with?" Gratitude & Mindfulness Even for the small things we have now, we can say "thank you" and "that's good," and express our gratitude. Acknowledge your feelings and efforts in the "here and now." Example: "Thank you to myself for being able to come to work today." "I was really grateful that my colleague helped me out."

[0088] Furthermore, the instructions for generating countermeasures information to the AI ​​may also include instructions to guide the user toward correct posture and walking by displaying images of correct posture and walking over the image of the person being managed, if the posture or walking is poor. In this process, you could, for example, slowly move the image from the current posture to the correct walking posture, or indicate areas for improvement with lines or arrows. Furthermore, you could provide examples showing how continuing with the current posture and walking style will eventually lead to such deterioration.

[0089] 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).

[0090] 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).

[0091] Then, the output generation unit 112 transmits the countermeasure information to the attendance record device 200 (step S010).

[0092] The health countermeasure output unit 260 displays the countermeasure information (step S011).

[0093] 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.

[0094] 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).

[0095] 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.

[0096] 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).

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] Furthermore, instructions for generating countermeasures information to the AI ​​may include instructions to convert the responses into a style that "sounds like a personal tweet" or "sounds like a diary or memo." Instructions for generating countermeasures information to the AI ​​may also include instructions to output questions that encourage deeper thinking, such as "How did you reconsider this time?" In addition, the AI ​​may generate conversations like the ones described above during internal company activities, and a server terminal may be installed in the company to communicate about work progress, opinions, complaints, and grievances through conversations or text, or communication may be conducted using APIs on the managed person's own mobile phone, PC, or wearable device.

[0108] Furthermore, regarding the business support system 1, we will describe an embodiment that focuses on the walking patterns and body movements of the person being managed. The business support system 1 acquires image and voice data of the person being managed (e.g., an employee), and based on this data, it analyzes various physical and emotional characteristics such as walking patterns, body movements, posture, arm swing, balance of both hands, facial expressions, tone of voice, and even footsteps produced while walking, thereby comprehensively evaluating the health status of the person being managed. This makes it possible to detect early signs that tend to be overlooked in conventional health management and to take early preventive measures.

[0109] For example, if analyzing an employee's posture from images reveals a hunched posture, rounded shoulders, or shoulder asymmetry, it may indicate modern occupational ailments such as stiff shoulders, lower back pain, straight neck, or VDT syndrome (Visual Display Terminal syndrome) caused by prolonged computer work. These signs can also serve as indicators of excessive strain on the musculoskeletal system.

[0110] Furthermore, if imbalances in left-right balance, limping, or sluggishness in movement are observed in gait patterns obtained from images and audio, it may be a sign of decreased motor function, physical fatigue, or an early sign of neuromuscular disease. In particular, the business support system 1 acquires footsteps (walking sounds) as audio and analyzes characteristics such as intervals, rhythm, variations in intensity, and left-right differences in the footsteps. This allows for the detection of lower limb motor disorders, joint pain, and gait unsteadiness, which are difficult to judge visually. This makes it applicable to assessing the risk of falls and supporting rehabilitation for elderly employees and those in the recovery phase.

[0111] Furthermore, by analyzing the speech-related components of the audio data, abnormalities in voice tone, speech speed, and pauses during speech can be used as mental health indicators, such as mental stress, sleep deprivation, and decreased concentration. This makes it possible to detect depressive symptoms and burnout early.

[0112] Thus, multifaceted analysis using image and audio data enables more objective and continuous monitoring of health management, which previously relied on regular checkups and self-reporting. In particular, this invention is extremely useful in that it can detect symptoms such as cervical spondylosis, straight neck, VDT syndrome, and chronic shoulder and lower back strain, which tend to become apparent in modern workplace environments, at an early stage, and propose and implement appropriate health measures.

[0113] The generation AI used in the business support system 1 is configured to process multimodal inputs and comprehensively analyzes image data, audio data, and associated metadata (e.g., identification information of the person being managed, time of day, type of work, etc.). For example, the following information is input to the generating AI: Image data (including full-body video or still images) of the person under management while walking or working, Audio data of the person being managed (speech, footsteps, coughing, etc.), Metadata such as the date and time, location, and duration of acquisition of the image / audio, Analysis history for the same person under management in the past, This information will be used for training and inference in the AI ​​model to assess health status and generate proposed countermeasures.

[0114] Furthermore, in this embodiment, prompts (instructions) are used to clearly specify the analysis purpose and output format in order to guide and optimize the analysis by the generating AI. The following is an example. <Prompt Example 1: Assessment of Walking Condition> "The following video shows employee A walking. Analyze the walking pattern, balance between the left and right feet, arm swing, and postural stability. If any physical ailments or risks are estimated, generate health measures including suggestions for improvement." <Prompt Example 2: Posture Assessment and Detection of PC Work-Related Diseases> "This image shows the person being managed working at a desk. Evaluate whether there is any forward head posture, hunched back, or rounded shoulders. If there is a possibility of straight neck or VDT syndrome, qualitatively assess the degree and suggest appropriate stretches and break frequencies as countermeasures." <Prompt Example 3: Evaluation of Voice Tone and Speech Content> "The following audio is a recording of a manager giving a work report. Analyze the tone of voice, intonation, speaking speed, and any hesitations to assess whether there are signs of mental stress or fatigue, and suggest refreshing methods or mental health measures as needed." <Prompt Example 4: Physical Function Assessment through Footstep Sound Analysis> "The following audio data is a recording of footsteps made while the person being monitored was walking. Pay attention to the interval between the left and right footsteps, the volume of the sounds, and the rhythm to evaluate whether there is any decline in motor function or risk of falling. If there is a risk, please indicate the reason and recommend exercises or rehabilitation."

[0115] Based on the prompts described above, the generating AI assesses the health status and generates customized countermeasures based on the input multimodal data. The resulting output is provided as health measures appropriate for each person being managed, contributing to improved health management and workplace performance.

[0116] Furthermore, the business support system 1 according to the present invention may be configured to capture an image of the hand of the person being managed and to estimate their health status from the hand image. The appearance of the hand, the condition of the wrinkles (number of wrinkles, depth, branching, fineness, overlap, and prominence), distribution, skin tone, visible blood vessels, and the condition of the nails are effective indicators that reflect the overall health status, aging, circulatory condition, and lifestyle habits.

[0117] Specifically, if the number and depth of wrinkles on the back of the hands are remarkably prominent, it may indicate dry skin, dehydration, or malnutrition. Pale skin may also be a sign of anemia or peripheral circulatory insufficiency. Furthermore, the color, luster, thickness, brittleness, and presence or absence of a lunula (half-moon) of the fingernails suggest the state of blood flow quality, liver function, and metabolic function related to nail formation.

[0118] Furthermore, changes in the overall shape of the hand, particularly swelling or asymmetry in the joints, and finger deformities may indicate early signs of conditions such as rheumatic diseases, tenosynovitis, or osteoarthritis. To obtain this image information with high accuracy, it is recommended to acquire high-resolution images under appropriate lighting conditions.

[0119] Based on this visual information, the generating AI will formulate health measures using prompts such as the following: <Prompt Example 5: Health Estimation Based on Hand Images> "The following is an image of the person being managed. Based on the condition of the wrinkles on the back of the hand, skin tone, nail shape, color, thickness, and degree of breakage, the visibility of blood vessels, joint swelling, etc., please list the estimated health conditions and suggest recommended health measures for each."

[0120] For example, the following health measures could be devised by generative AI: If dryness is severe: Promote hydration, provide guidance on moisturizing care, and recommend vitamin A and E intake. If anemia is suspected: Suggestions for a diet containing iron and folic acid, and recommendations for blood tests at a medical institution. If your nails are dull and brittle: Recommendation of protein and zinc intake, and guidance on nail care. If joint swelling is observed: Consult an orthopedic specialist and suggest reducing the physical strain of manual work. If you notice a sudden increase in wrinkles: This may be due to a decrease in metabolism associated with aging, so we advise you to promote blood circulation through exercise, bathing, etc.

[0121] Thus, health status estimated from hand image information is a powerful and supplementary means of detecting early signs of overall physical ailments. It is also highly compatible with image AI analysis and is superior in that it is non-invasive and easily obtainable. Therefore, by combining it with other body movement information and voice information, more multifaceted and highly accurate health monitoring can be realized.

[0122] In the business support system 1 according to the present invention, the system may be configured to estimate health status by focusing on changes over time (temporal changes) by comparing multiple data acquired at different times for the same person under management, in addition to estimating static image and audio data at a single point in time.

[0123] Specifically, for example, image and audio data is acquired from the person being managed a total of three times (multiple times): before the start of work (morning), after the morning work (noon), and at the end of work (evening). At each time, posture, gait, facial expressions, voice condition (voice tone, speech clarity, balance of footsteps, and even hand position) are analyzed, and the temporal changes are comprehensively evaluated by a generative AI.

[0124] By focusing on these changes over time, it becomes possible to estimate health conditions such as the following: If your posture becomes more hunched over in the evening compared to the morning, and your facial expression becomes less expressive: This may indicate physical fatigue or the accumulation of mental stress. If your voice is quieter and less expressive compared to the morning: This may indicate decreased concentration, drowsiness, or a tendency towards depression. If you experience difficulty lifting your feet while walking in the afternoon or notice inconsistencies in the sound of your footsteps: This may indicate lower limb fatigue or a temporary decline in balance function. If wrinkles and discoloration on your hands become more noticeable in the afternoon: This could indicate poor circulation, dehydration, or environmental stress.

[0125] To perform this kind of analysis based on temporal changes, the following prompts are used for the generative AI. <Prompt Example 6: Assessment of Health Changes by Time Comparison> "The following is data on the same employee's posture, facial expressions, voice, footsteps, etc., in the morning, noon, and evening. Based on these temporal changes, please analyze and estimate changes in their physical and mental state, and propose appropriate health measures as needed."

[0126] By analyzing these temporal changes, the generating AI can analyze not only short-term fluctuations (e.g., daily fatigue levels) but also long-term trends (e.g., chronic fatigue, changes in motivation, accumulation of health risks). Therefore, this embodiment realizes more advanced health support based on the visualization and prediction of changes, rather than merely recording the state.

[0127] In the business support system 1 according to the present invention, the system may be configured to collect and store image and audio data relating to multiple managers and to analyze them across the entire business. That is, the generating AI can not only individually estimate the health status of each manager, but also perform a cross-sectional trend analysis on the data of multiple managers to extract health issues common to the entire business.

[0128] This configuration suggests that, for example, if many employees in a particular workplace exhibit a tendency towards hunching over, it may be due to the work environment (such as the height of desks and chairs, or the placement of screens), and that implementing comprehensive improvement measures related to posture correction would be effective. Furthermore, if there is a general tendency for walking balance to worsen towards the evening, it will be necessary to review organizational health management policies, such as reallocating work assignments or optimizing break times. Furthermore, if the time periods and types of work in which signs of mental stress (such as a drop in voice tone or rigid facial expression) are concentrated among multiple individuals can be identified, measures such as reducing the workload of those tasks or improving management methods can be derived.

[0129] This configuration allows for the visualization of trends across the entire workplace, rather than simply addressing individual issues, and enables the proposal and implementation of comprehensive health measures for common challenges. This makes the present invention extremely useful in realizing organizational health management, including improving the work environment, preventing occupational accidents, and increasing productivity.

[0130] In the business support system 1 according to the present invention, the generating AI derives collective trends using image data and audio data acquired for multiple managed persons. At this time, the information input to the generating AI is provided as multidimensional and time-series structured data, as exemplified below. (1) Image information (for all managed users) Image acquisition date and time (e.g., Month Day, AM / PM / Evening) The ID or anonymized identifier of the person being managed. Posture data (angle of forward lean, difference in shoulder position, head position, degree of arm and leg spread, etc.) Skeletal estimation parameters during walking (stride length, left-right balance, speed variation) Facial features (corners of the mouth, eyebrow position, degree of eye opening, etc.) (2) Audio information Audio recording time, administrator ID Voice tone, intonation, speech rate, sound pressure level Left-right intensity, rhythm difference, and landing sound waveform of footsteps Frequency of non-verbal sounds such as coughs and sighs (3) Temporal and environmental metadata Data acquisition time (morning / afternoon / evening) Job title and type of duties of the person being managed Time elapsed since last acquisition, details of the most recent work performed. Environmental sensor data such as temperature, humidity, and illuminance

[0131] These input data are supplied to the generating AI in a chronologically ordered manner for each managed entity, and are then converted into a format that allows for comparison between managed entities (normalized or feature extracted). Cross-sectional analysis and clustering processes are then performed to conduct the following analyses: "What percentage of employees experience a worsening of their posture in the afternoon?" "Is there a statistically significant difference in the degree of facial rigidity between employees in Department A and employees in Department B?" "Among employees performing the same duties, is there a uniform decrease in voice tone between the morning and afternoon?" Thus, the input information is not merely images or audio itself, but includes extracted data on physical and emotional characteristics, as well as associated work and environmental metadata. The generating AI utilizes this data to enable the understanding of health trends and the development of improvement guidelines at the workplace level.

[0132] Embodiments of the present invention include the following aspects. <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 to generate countermeasure information involves inputting a video of the person being managed, along with observation points in the video image diagnosis (examples of actions / phenomena, suspected symptoms / ailments), analyzing the person being managed, and using the results of the analysis to generate health measures that should be output to the person being managed for health management or morale improvement. A health measures output step which outputs the health measures generated by the generation AI to the person being managed, A business support system that performs the following tasks. <2> <1> The business support system described above, The instructions given to the AI ​​in the aforementioned countermeasure information generation step include: A business support system that includes analyzing audio acquired from the vicinity of the person being managed, and analyzing at least one of the following: speech content, voice condition (voice tone, speaking speed, pauses), and footstep patterns. <3> <2> The business support system described above, The instructions given to the AI ​​in the aforementioned countermeasure information generation step include: A workplace support system that includes cross-sectional analysis of negative statements based on the text-based speech content obtained from the aforementioned managed personnel, and proposing health measures to improve morale through positive, text-based communication. <4> <1> The business support system described above, The instructions given to the AI ​​in the aforementioned countermeasure information generation step include: A business support system that includes analyzing at least one of the left-right balance, intensity, rhythm, and interval of the foot sounds of the person being managed, and evaluating the state of motor function. <5> <1> The business support system described above, The instructions given to the AI ​​in the aforementioned countermeasure information generation step include: A business support system that receives an image of the hand of the person being managed as input, and includes analyzing at least one of the following from the image: the condition of the wrinkles on the hand, the depth of the wrinkles, the skin tone, the condition of the nails, and the swelling of the joints. <6> <5> The business support system described above, The instructions given to the AI ​​in the aforementioned countermeasure information generation step include: A workplace support system that includes analyzing the health status of the person under management, based on information analyzed from images of the person under management, including at least one of the following: dryness / dehydration, malnutrition, peripheral circulatory insufficiency, nail malformation, and signs of joint disease. <7> <1> The business support system described above, The instructions given to the AI ​​in the aforementioned countermeasure information generation step include: A business support system that includes acquiring images or audio of the person under management at multiple time periods (around the start of work, around noon, and around the end of work) and evaluating their health status based on changes over time. <8> <7> The business support system described above, The instructions given to the AI ​​in the aforementioned countermeasure information generation step include: A business support system that includes estimating at least one of the following based on changes over time: the degree of fatigue accumulation, decreased concentration, the progression of mental stress, and changes in physical balance, and generating health measures based on these results. <9> <1> The business support system described above, The instructions given to the AI ​​in the aforementioned countermeasure information generation step include: A business support system that includes generating individually optimized health measures, taking into account past health analysis results associated with the aforementioned person under management. <10> <1> The business support system described above, The instructions given to the AI ​​in the aforementioned countermeasure information generation step include: A workplace support system that includes cross-sectional analysis of images and audio obtained from multiple persons under management, extracting health risks common to the entire group, and proposing a health guidance policy for the entire workplace. <11> A method for supporting a business establishment that is implemented by a computer system, for supporting a business establishment in which an administrator and an employee managed by the administrator coexist, A step of generating countermeasure information involves inputting an image of the person being managed into a generating AI, analyzing the person's walking pattern, body movements, and posture, and instructing the AI ​​to generate health measures to be output to the person for health management or morale improvement using the results of the analysis. A health measures output step which outputs the health measures generated by the generation AI to the person being managed, Business support methods including those mentioned above. <12> 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 involves inputting an image of the person being managed into a generating AI, analyzing the person's walking pattern, body movements, and posture, and instructing the AI ​​to generate health measures to be output to the person for health management or morale improvement using the results of the analysis. A health measures output step which outputs the health measures generated by the generation AI to the person being managed, A support program for businesses that implements this.

[0133] 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.

[0134] 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.

[0135] The present invention has been described above, focusing on its embodiments. [Explanation of Symbols]

[0136] 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

1. A business support system that operates a computer system including a generation AI service (including those provided via a network) to support business establishments where administrators and those managed by said administrators coexist, The steps include acquiring images of the person being managed at multiple times, including the start and end of the workday, A step of generating countermeasure information, instructing the AI ​​service to input images of the person being managed, analyze the person being managed by video image diagnosis of predetermined observation points including the person's walking and movements, and use the results of the analysis to generate health measures to be output to the person being managed for the purpose of health management or morale improvement of the person being managed; A health measures output step which outputs the health measures generated by the AI ​​generation service to the person being managed, Perform In the aforementioned countermeasure information generation step, A business support system that includes having the AI ​​generation service evaluate the health status of the managed person's image based on the temporal changes at multiple time points.

2. A business support system according to claim 1, In the aforementioned countermeasure information generation step, A business support system that includes having the aforementioned AI generation service estimate the degree of fatigue accumulation, decrease in concentration, progression of mental stress, or changes in physical balance based on changes over time, and generating health measures based on the results.

3. A business support system that operates a computer system including a generation AI service (including those provided via a network) to support business establishments where administrators and those managed by said administrators coexist, A step to generate countermeasure information involves inputting images and audio obtained from the multiple persons under management into the AI ​​service, and instructing it to extract health risks based on statistical information obtained by cross-analyzing the images or audio as health risks that may be common to the entire group, and to propose a health guidance policy for the entire workplace. An output step which outputs the health guidance policy for the entire business establishment proposed by the aforementioned AI generation service, A business support system that performs the following tasks.

4. A method for supporting a business establishment that includes a generating AI service (including one provided via a network) and is implemented by a computer system, for supporting a business establishment where an administrator and an administrator who manages such an administrator coexist, The steps include acquiring images of the person being managed at multiple times, including the start and end of the workday, A step of generating countermeasure information, instructing the AI ​​service to input images and audio of the person being managed, analyze the person's walking pattern, body movements, and posture, and use the results of the analysis to generate health measures to be output to the person being managed for the purpose of health management or morale improvement. A health measures output step which outputs the health measures generated by the AI ​​generation service to the person being managed, Perform In the aforementioned countermeasure information generation step, A business support method comprising having the generating AI service evaluate the health status of the person under management based on the temporal changes in the image or voice at multiple time points.

5. A method for supporting a business establishment as described in claim 4, In the aforementioned countermeasure information generation step, A method for supporting a business establishment, which includes having the aforementioned generation AI service estimate the degree of fatigue accumulation, the decline in concentration, the progression of mental stress, or the change in physical balance based on changes over time, and generating health measures based on the results.

6. A method for supporting a business establishment that includes a generating AI service (including one provided via a network) and 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 to generate countermeasure information involves inputting images and audio obtained from the multiple persons under management into the AI ​​service, and instructing it to extract health risks based on statistical information obtained by cross-analyzing the images or audio as health risks that may be common to the entire group, and to propose a health guidance policy for the entire workplace. An output step which outputs the health guidance policy for the entire business establishment proposed by the aforementioned AI generation service, A method of supporting businesses.

7. A business support program that operates a computer system including a generation AI service (including those provided via a network) to support business establishments where administrators and those managed by said administrators coexist, The steps include acquiring images of the person being managed at multiple times, including the start and end of the workday, A step of generating countermeasure information, instructing the AI ​​service to input images of the person being managed, analyze the person being managed by video image diagnosis of predetermined observation points including the person's walking and movements, and use the results of the analysis to generate health measures to be output to the person being managed for the purpose of health management or morale improvement of the person being managed; A health measures output step which outputs the health measures generated by the AI ​​generation service to the person being managed, Perform In the aforementioned countermeasure information generation step, A business support program that includes having the AI ​​generation service evaluate the health status of the managed person based on the temporal changes at multiple time points.

8. A business support program according to claim 7, In the aforementioned countermeasure information generation step, A business support program that includes having the aforementioned AI generation service estimate the degree of fatigue accumulation, decrease in concentration, progression of mental stress, or changes in physical balance based on changes over time, and generating health measures based on the results.

9. A business support program that operates a computer system including a generation AI service (including those provided via a network) to support business establishments where administrators and those managed by said administrators coexist, A step to generate countermeasure information involves inputting images and audio obtained from the multiple persons under management into the AI ​​service, and instructing it to extract health risks based on statistical information obtained by cross-analyzing the images or audio as health risks that may be common to the entire group, and to propose a health guidance policy for the entire workplace. An output step which outputs the health guidance policy for the entire business establishment proposed by the aforementioned AI generation service, A business support program that implements these measures.

Images