Fatigue estimation system, fatigue estimation method, and program recording medium

Abstract

A fatigue estimation system (200) includes an information output device (e.g., a camera (101)) that outputs information about the position of a body part of a subject (11), and an estimation device (100) that counts the number of specific movements that occur in correspondence with fatigue accumulation based on information output from the information output device within a prescribed period, thereby estimating the degree of fatigue of the subject (11) accumulated within the prescribed period and outputting the same.

Description

Technical Field

[0001] This disclosure relates to a fatigue estimation system, fatigue estimation method, and program recording medium for estimating the fatigue level of an individual. Background Technology

[0002] In recent years, due to the accumulation of fatigue, cases of injuries and accidents caused by poor physical condition have become increasingly common. In response, technologies that estimate the degree of fatigue to prevent such injuries and accidents have attracted attention. For example, as a fatigue estimation system for estimating the degree of fatigue equivalent to the aforementioned fatigue, a fatigue determination device has been disclosed that determines the presence and type of fatigue based on force measurement and bioelectrical impedance measurement (see Patent Document 1).

[0003] Existing technical documents

[0004] Patent documents

[0005] Patent Document 1: Japanese Patent Application Publication No. 2017-023311 Summary of the Invention

[0006] The problem that the invention aims to solve

[0007] However, the aforementioned estimation of fatigue level is sometimes inadequate. Therefore, this disclosure provides a fatigue estimation system that can more appropriately estimate the fatigue level of a subject.

[0008] Methods used to solve problems

[0009] A fatigue estimation system according to the present disclosure includes: an information output device that outputs information related to the position of a body part of a subject; and an estimation device that, based on the information output from the information output device within a specified period, counts the number of specific actions that occur corresponding to fatigue accumulation, thereby estimating and outputting the fatigue level of the subject accumulated within the specified period.

[0010] Furthermore, a fatigue estimation method for a technical solution disclosed herein includes: an acquisition step of acquiring information related to the position of a body part of a subject; and an estimation step of counting the number of specific actions that occur corresponding to fatigue accumulation within a specified period based on the output information, thereby estimating the fatigue level of the subject accumulated within the specified period.

[0011] Furthermore, the technical solution disclosed herein can be implemented as a computer-readable, non-transitory recording medium containing a program for causing a computer to execute the fatigue estimation method described above.

[0012] Invention Effects

[0013] The fatigue estimation system and other technical solutions disclosed herein can more appropriately estimate the fatigue level of the subject. Attached Figure Description

[0014] Figure 1 This is a schematic diagram illustrating the outline of the fatigue prediction system for implementing the method.

[0015] Figure 2 This is a block diagram illustrating the functional structure of the fatigue prediction system in the implementation method.

[0016] Figure 3 It is a diagram used to illustrate specific actions of the implementation method.

[0017] Figure 4 This is a diagram used to illustrate personal fatigue information in the implementation method.

[0018] Figure 5 This is a diagram used to illustrate the method for constructing personal fatigue information in the implementation method.

[0019] Figure 6 This is a diagram used to illustrate the estimated fatigue level of the implementation method.

[0020] Figure 7 This is a diagram used to illustrate the blank period of the implementation method.

[0021] Figure 8 This is a diagram used to illustrate the correction of fatigue in the implementation method.

[0022] Figure 9 Figure 1 illustrates the information output by the fatigue estimation system from the implementation method.

[0023] Figure 10 Figure 2 illustrates the information output by the fatigue prediction system from the implementation method.

[0024] Figure 11 This is a flowchart illustrating the operation of the fatigue prediction system in the implementation method. Detailed Implementation

[0025] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. Furthermore, the embodiments described below are inclusive or specific examples. The numerical values, shapes, materials, constituent elements, arrangement and connection methods of constituent elements, steps, and order of steps shown in the following embodiments are examples and are not intended to limit this disclosure. In addition, any constituent elements in the following embodiments that are not described in the independent claims will be described as arbitrary constituent elements.

[0026] Furthermore, the figures are schematic diagrams and not necessarily rigorous representations. Additionally, in each figure, substantially identical components are assigned the same labels, and repetitive explanations are sometimes omitted or simplified.

[0027] (Implementation Method)

[0028] [System Architecture]

[0029] First, refer to Figure 1 and Figure 2 The overall structure of the fatigue prediction system of the implementation method is described. Figure 1 This is a schematic diagram illustrating the general outline of the fatigue prediction system for the implementation method. Figure 1 The text indicates the status of estimating the fatigue level of the subject 11 using the fatigue estimation system 200. Figure 1 In the scene shown, the subject 11 is sitting in a chair 12 and operating a computer 100a placed on a table 13.

[0030] In this embodiment, the fatigue estimation system 200 estimates the fatigue level of the subject 11 based on images captured by the camera device 101. The images captured by the camera device 101 are transmitted to the estimation device 100 via a network such as the Internet. The estimation device 100 is, for example, a computing processing unit installed in a server device such as a cloud server, and estimates the fatigue level of the subject 11 contained in the images. The estimation results are transmitted, for example, via the network to a computer 100a operated by the subject 11, displayed on the screen of the computer 100a, or stored in a storage device (such as the storage unit 24 described later).

[0031] In this case, the user 11 can confirm the prediction results displayed on the same computer 100a during the operation using the computer 100a. Furthermore, this embodiment describes an example where the prediction device 100 is implemented by a server device as described above, but the structure of the fatigue prediction system 200 is not limited to this. For example, the prediction device 100 may also be built into the computer 100a. That is, the computer 100a is a prediction device as in other embodiments.

[0032] When using computer 100a as the estimation device, no network or server device is required, so the fatigue estimation system 200 can be implemented with a simple structure of camera device 101 and computer 100a. Furthermore, sometimes a camera is placed at the location of the object 11 that can be photographed on the computer 100a, and by using this camera as the aforementioned camera device 101, the fatigue estimation system 200 can be implemented using only computer 100a.

[0033] In this disclosure, in the estimation device 100, when estimating the fatigue level of the subject 11 based on the subject 11's posture, the fatigue level accumulated during the specified period can be estimated through simple calculation by counting the number of specific actions that occur corresponding to the subject 11's accumulated fatigue within a specified period. The specified period is set by the user of the fatigue estimation system 200, such as the subject 11 or a manager overseeing the subject 11's fatigue, and can be set to any period such as 1 hour, 8 hours, 1 day, 3 days, 1 week, or 1 month. In this embodiment, a fatigue estimation system 200 is described that estimates the fatigue level accumulated in the subject 11 within one day by setting the specified period to 1 day.

[0034] Furthermore, the relationship between the number of such specific actions and the accumulated fatigue level sometimes differs for each individual subject 11. Therefore, in this embodiment, by using pre-constructed individual fatigue information matched to the individual subject 11, it is possible to obtain a fatigue level prediction suitable for the individual subject 11. With the above configuration, the fatigue level of the individual subject 11 can be predicted using simple calculations, thereby enabling the prediction of fatigue level suitable for each individual subject 11.

[0035] Figure 2 This is a block diagram illustrating the functional structure of the fatigue prediction system implemented in this way. For example... Figure 2 As shown, the fatigue prediction system 200 of this embodiment includes a prediction device 100, a camera device 101, a receiving device 102, an acquisition device 103, an external device 104, and a display device 105.

[0036] As described above, the estimation device 100 is a processing device that estimates the accumulated fatigue of the subject 11, and is implemented by installing it on a server device. The estimation device 100 includes a first acquisition unit 21, a second acquisition unit 22, a third acquisition unit 23, a storage unit 24, a posture estimation unit 25, a determination unit 26, a fatigue estimation unit 27, and an output unit 28.

[0037] The first acquisition unit 21 is a communication module that acquires images of the subject 11. For example, the first acquisition unit 21 acquires images captured by the camera device 101 by communicating with the camera device 101 via a network.

[0038] The imaging device 101 is a device that outputs images containing the subject 11 by capturing them. Examples include cameras mounted on a facility such as surveillance cameras, cameras built into the computer 100a or portable terminals, and dedicated cameras for the fatigue estimation system 200. Furthermore, the images output by the imaging device 101 and acquired by the first acquisition unit 21 are so-called moving images, captured continuously along a time sequence. The first acquisition unit 21 acquires these moving images in parallel with the capturing operations performed by the imaging device 101. The first acquisition unit 21 outputs the acquired images to the posture estimation unit 25.

[0039] The posture estimation unit 25 is a processing unit that estimates the posture of the subject 11 based on the image output from the first acquisition unit 21. The posture estimation unit 25 is implemented by executing a predetermined program by a processor and memory. As described above, since the image is a moving image composed of consecutive frames in a time sequence, the posture estimation unit 25 estimates the posture of the subject 11 with respect to each frame of the moving image. Thus, the estimated posture of the subject 11 is output from the posture estimation unit 25 throughout the entire predetermined period during which fatigue estimation is performed. However, the posture estimation unit 25 may also stop estimating the posture of the subject 11 when the subject 11 leaves the field of view of the camera device 101.

[0040] The posture estimation unit 25 determines the joint positions within the image of the subject 11 by performing image processing according to a prescribed procedure. The posture estimation unit 25 outputs a joint position model, represented by connecting two joints with bones of a predetermined length based on the relative positions of the joints, as the result of posture estimation. Furthermore, since the joint position model corresponds one-to-one with the relative positions of the bones connecting the joints, it can also be referred to as a skeletal position model. In the estimation device 100, based on the posture of the subject 11 output here, the number of specific movements corresponding to the accumulation of fatigue in the subject 11 is counted, thereby enabling the estimation of the subject 11's fatigue level.

[0041] Furthermore, personal fatigue information is stored in storage unit 24 as information related to a specific action. Storage unit 24 is a storage device implemented using semiconductor memory, magnetic storage medium, and optical storage medium, etc. Storage unit 24 stores various types of information used in the estimation device 100, including personal fatigue information. Each processing unit of the estimation device 100 reads the required information from storage unit 24 and uses the information, and writes new information generated by each processing unit into storage unit 24 as needed. For information on specific actions and personal fatigue information, please refer to [reference needed]. Figures 3-5 To be described later.

[0042] The determination is made by counting the number of specific actions based on the posture of the subject 11 predicted by the posture prediction unit 25, and by determining whether the action of the subject 11 caused by the change in the predicted posture of the subject 11 conforms to the specific action. This determination is made by the determination unit 26. The determination unit 26 is a processing unit with the above-described functions, implemented by executing a prescribed program by a processor and memory. As described above, the determination unit 26 determines whether the specific action has been performed by judging whether the action based on the predicted posture of the subject 11 conforms to the specific action. If the determination unit 26 determines that the action of the subject 11 conforms to the specific action, it increments the count of the specific action by 1.

[0043] The fatigue estimation unit 27 is a processing unit that estimates the fatigue level of the subject 11 based on the number of specific actions performed. The fatigue estimation unit 27 is implemented by executing a prescribed program using a processor and memory. Detailed operation of the fatigue estimation unit 27 will be described later.

[0044] When estimating the fatigue level of the subject 11, the fatigue estimation unit 27 makes a more accurate estimation by correcting the fatigue level calculated based on the number of specific actions. In addition to the fatigue estimation unit 27, the second acquisition unit 22 and the third acquisition unit 23 also participate in the fatigue level correction. The second acquisition unit 22 is a communication module that acquires the subject 11's subjective feeling of fatigue. For example, the second acquisition unit 22 acquires the fatigue level input by the subject 11 by communicating with the receiving device 102 via a network.

[0045] The receiving device 102 is a device for receiving input from the subject 11, and is implemented by an interface device or similar device. In the fatigue estimation system 200, the subject 11 inputs the degree of subjective fatigue, and the fatigue level is corrected using the input fatigue level. The correction using fatigue level will be described later. In addition, the fatigue level includes information that can be compared with the fatigue level.

[0046] The third acquisition unit 23 is a communication module that acquires the personal information of the subject 11. For example, the third acquisition unit 23 acquires health diagnosis results containing the personal information of the subject 11 by communicating with the acquisition device 103 via a network. The acquisition device 103 acquires health diagnosis results containing the personal information of the subject 11 by communicating with an external device 104 storing the health diagnosis results via a network. The external device 104 here could be, for example, a server of a facility such as a hospital that performs health diagnoses, a server of an operator that intermediaries the implementation of health diagnoses, or a server within a company that stores health diagnosis results including those of the subject 11's employees. Alternatively, the third acquisition unit 23 may also acquire only the personal information entered by the subject 11 himself via the receiving device 102, etc.

[0047] Here, the personal information of subject 11 includes at least one of the following: age, gender, height, weight, muscle mass, level of mental stress, body fat percentage, and proficiency in sports. Subject 11's age can be a specific numerical value, or an age range divided into 10-year intervals such as 10–19, 20–29, and 30–39, or an age range divided into two categories with a specified age boundary such as under 59 or over 60, or other information.

[0048] Furthermore, the gender of the subject 11 is selected from both male and female, choosing the one most suitable for the subject 11. Additionally, the subject 11's height and weight are measured numerically. Furthermore, the muscle mass is measured using a body composition analyzer or similar device, representing the subject 11's subjective experience of mental stress, determined by the subject 11 through a selection of high, moderate, and low levels.

[0049] Furthermore, the subject's proficiency in the sport can be quantified either by the score achieved when performing a prescribed exercise program, or by the subject's usual exercise performance. The former can be quantified, for example, by the time required to perform 10 back muscle exercises, the time required to run 50 meters, or the flight distance of a long throw. The latter can be quantified, for example, by how many days or how many hours of exercise are performed per week. Additionally, since personal information is used to improve the accuracy of fatigue estimation, the fatigue estimation system 200 can be implemented without the third acquisition unit 23, the acquisition device 103, and the external device 104, provided sufficient accuracy is ensured.

[0050] The fatigue estimation unit 27 corrects the fatigue level calculated based on the number of times a specific action is performed, using the acquired personal information, and ultimately estimates the fatigue level to be output from the estimation device 100. In correcting the fatigue level using personal information, for example, the closer the subject 11's age is to the peak age for muscle development, the lower the fatigue level; the further away from that peak age, the higher the fatigue level. This peak age can also be determined based on the subject 11's gender. Alternatively, if the subject 11 is male, the fatigue level may be lower; if female, the fatigue level may be higher. Furthermore, the lower the subject 11's height and weight, the lower the fatigue level; the higher the height and weight, the higher the fatigue level.

[0051] Alternatively, a higher muscle mass ratio in subject 11 may reduce fatigue, while a lower muscle mass ratio may increase fatigue. Furthermore, lower levels of mental stress in subject 11 may reduce fatigue, while higher levels of mental stress may increase fatigue. Additionally, higher body fat percentage in subject 11 may increase fatigue, while lower body fat percentage may reduce fatigue. Moreover, higher proficiency in the exercise may reduce fatigue, while lower proficiency may increase fatigue.

[0052] The fatigue estimation unit 27 further refines the fatigue level corresponding to the number of times a specific action is performed, as described above, to make a more accurate estimation of the fatigue level for each subject 11. The fatigue estimation unit 27 outputs the estimated fatigue level to the output unit 28.

[0053] Output unit 28 is a processing unit that outputs a prompt message to the user 11, including the predicted fatigue level. Output unit 28 is implemented by executing a predetermined program using a processor and memory. Output unit 28 generates image data as prompt message, which includes the fatigue level of the user 11 predicted in fatigue prediction unit 27 plus other information, and sends it to display device 105 via a network. Alternatively, output unit 28 can also generate sound data as prompt message; in this case, the sound data is sent to a speaker (not shown).

[0054] The display device 105 is a device for displaying received image data. The display device 105 includes a liquid crystal panel or the like, and has a display module 105a (described later). Figure 9 The display module 105a drives the display module to display the image data received from the output unit 28.

[0055] The following is for reference Figures 3-5 Provide details about specific actions and individual fatigue information. Figure 3 This is a diagram used to illustrate specific actions in the implementation method. In Figure 3 The diagram shows a person performing a specific action. Furthermore, in... Figure 3 In this embodiment, four examples are shown as specific actions, but there is no particular limitation on the number of specific actions used.

[0056] As explained above, a specific action is an action that a person might take when fatigue accumulates. For example, one example of a specific action represented by action A in the diagram is the action of changing a posture from a backward leaning position to a forward leaning position. If a certain task is performed in a backward leaning position, fatigue accumulates in the lower back, so the person performs action A, changing the posture from a backward leaning position to a forward leaning position, in order to alleviate the accumulated fatigue.

[0057] Furthermore, for example, one example of a specific action represented by action B in the diagram is the action of a person rubbing their shoulder. If a person continuously uses their shoulder muscles due to tasks such as continuously raising their arms, they will be in a state of muscle stiffness, known as shoulder stiffness. To relax the stiff muscles, a person performs action B as an action to relax the shoulder muscles.

[0058] Furthermore, for example, one example of a specific action represented by action C in the diagram is the action of stretching the back muscles by extending the arms. If a person performs work continuously in a sitting or standing position with little body movement, the back muscles become stiff and contract. In order to stretch the contracted back muscles, the person performs the specific action C, which involves extending the arms connected to the back muscles.

[0059] Furthermore, for example, one example of a specific action represented as specific action D in the diagram is the action of a person pressing their head. Similarly, when blood flow deteriorates due to conditions such as shoulder stiffness, headaches may occur, and a person performs a specific action D by pressing their painful head. Moreover, regarding these specific actions, in order to compare them with the posture of the subject 11 predicted by the posture prediction unit 25, equivalent information comparable to the joint position model is used. However, since specific actions are defined by continuous changes in multiple postures, comparisons are made with the predicted posture in terms of both multiple joint position models and the order in which these joint position models change. Furthermore, since it is rare for a specific action to completely match the predicted posture, allowable ranges are set in both the temporal and spatial domains for postures deemed to conform to a specific action.

[0060] The specific action corresponds to the action that a person would take when fatigue (or the load on joints and muscles, etc.) accumulates. The specific action is not limited to the four actions described above; it can be any action that occurs during fatigue accumulation. Furthermore, the specific action may also include actions unique to the subject 11. That is, it may include actions that are rare for a typical person during fatigue accumulation but are frequent for the subject 11. In this embodiment, by appropriately structured the specific actions included in the personal fatigue information, the fatigue estimation in the estimation device 100 can be tailored to the subject 11.

[0061] In subsequent embodiments, an example of estimating the fatigue level of subject 11 using the four specific actions described above will be explained. These specific actions are those that typically occur when fatigued, thus realizing a estimation device 100 applicable to estimating fatigue in all ordinary people. Furthermore, in the following descriptions, specific actions A through D will sometimes be used without specific explanation; details of each specific action can be found by referring to the above descriptions. Figure 3 The explanation is omitted.

[0062] Figure 4 This is a graph used to illustrate individual fatigue information in the implementation method. Figure 4 The figure shows the personal fatigue information stored in the storage unit 24. As shown in the figure, the personal fatigue information is associated with information corresponding to the subject 11 as a defined individual for each specific action. That is, in the case of estimating the fatigue level of multiple subjects 11 using the fatigue estimation system 200, multiple pieces of personal fatigue information are prepared in a one-to-one correspondence with the number of multiple subjects 11.

[0063] As shown in the figure, in the individual fatigue information, each specific action is associated with its maximum and minimum frequency (daily maximum and minimum) within a specified period of day. For example, the daily maximum frequency associated with specific action A is 12 times, and the daily minimum frequency is 3 times. Here, we explain the method for determining the daily maximum and minimum frequency. Figure 5 This diagram illustrates a method for constructing personal fatigue information in an implementation scheme. Figure 5 The text describes the method used to determine the maximum and minimum number of fatigue events within a day when constructing personal fatigue information.

[0064] When a day is set as a defined period, as in this embodiment, the number of times the subject 11 performs a specific action within that day is counted. For example, in the figure, on the first day, specific action A is counted 3 times, specific action B is counted 3 times, specific action C is counted 2 times, and specific action D is counted 0 times. Similarly, on the second day, specific action A is counted 3 times, specific action B is counted 3 times, specific action C is counted 1 time, and specific action D is counted 1 time. Similarly, on the third day, specific action A is counted 3 times, specific action B is counted 2 times, specific action C is counted 1 time, and specific action D is counted 2 times.

[0065] By repeatedly counting the number of times the specific action described above is performed over multiple days corresponding to multiple specified periods, the number of times the specific action is performed on the day with the most and the number of times on the day with the fewest results can be obtained. The number of times the specific action is performed on the day with the most and the number of times on the day with the fewest results are determined as the maximum number of times and the minimum number of times within a day, respectively.

[0066] Based on the count of the number of times a specific action is performed within a specified period (i.e., how many days), the accuracy and correctness of the maximum and minimum number of times performed within a day vary. Therefore, users of the fatigue prediction system 200 can construct personal fatigue information by simply counting the number of times a specific action is performed until the maximum and minimum number of times performed within a day can be obtained with the desired accuracy and correctness.

[0067] Refer again Figure 4 Based on the maximum and minimum number of repetitions per day as determined above, the first fatigue level accumulated by subject 11 each time a specific action A is performed is calculated. More specifically, using the maximum and minimum number of repetitions per day associated with each specific action, the first fatigue level for each specific action is calculated using the formula 10 / {(maximum number of repetitions per day) - (minimum number of repetitions per day)}. The first fatigue level is a value representing the magnitude of fatigue accumulated each time a specific action is counted, and is uniquely determined by the maximum and minimum number of repetitions per day.

[0068] As shown in the figure, the personal fatigue information includes a first fatigue level and related information used to determine the first fatigue level (here, the maximum and minimum number of times per day). Furthermore, as mentioned above, the first fatigue level is a value uniquely determined based on the information related to the first fatigue level; therefore, if the personal fatigue information includes information related to the first fatigue level, the first fatigue level itself may not be included. Additionally, the formula described above is the one used in this embodiment, which fractionates the fatigue level into 10 points. When fractionating with other values, simply change the value of the numerator, 10.

[0069] In the diagram, the first fatigue level for specific action A is 10 / (12-3)≈1.1, the first fatigue level for specific action B is 10 / (4-1)≈3.3, the first fatigue level for specific action C is 10 / (6-0)≈1.7, and the first fatigue level for specific action D is 10 / (8-4)=2.5. These first fatigue levels, for other subjects 11, are, for example, 2.4 for specific action A, 1.0 for specific action B, 5.0 for specific action C, and 3.3 for specific action D (none are shown). Thus, the accumulated fatigue level differs for each subject 11 until the specific action is performed. In this embodiment, by constructing individual fatigue information for each subject 11, it is possible to infer the fatigue level reflecting the individual's habitual fatigue level for the specific action performed.

[0070] Furthermore, as shown in the figure, the personal fatigue information in this embodiment includes fatigue location information for each specific action. This fatigue location information is information that associates the body part of the subject 11 to which the first fatigue level is accumulated, i.e., the fatigue location, with the specific action. For example, the fatigue location information associates a specific action A with the waist as the fatigue location corresponding to specific action A. That is, when the subject 11 performs specific action A, the first fatigue level of 1.1 is accumulated in the waist. Similarly, when the subject 11 performs specific action B, the first fatigue level of 3.3 is accumulated in the shoulder; when performing specific action C, the first fatigue level of 1.7 is accumulated in the back; and when performing specific action D, the first fatigue level of 2.5 is accumulated in the shoulder.

[0071] Here, specific movements B and D are associated with the same shoulder area as fatigue sites. In this case, either the average fatigue level accumulated in each of specific movements B and D can be calculated, or the fatigue level in specific movements B and D can be calculated as a whole at a ratio corresponding to a pre-set weighting factor. The weighting factor is determined based on the frequency and number of times each specific posture was performed when constructing individual fatigue information.

[0072] Next, refer to Figures 6-8 The study provides an explanation of the estimation of the fatigue level of subject 11. Figure 6 This is a diagram used to illustrate the estimated fatigue level of the implementation method. In Figure 6 The diagram illustrates the timing of the subject 11's posture and specific actions during the specified period, from the middle to the end of the specified period. Specifically, during the illustrated period, after performing work in a forward-leaning posture (hereinafter referred to as fatigue posture A) for 30 minutes, subject 11 performs specific action D, returning to fatigue posture A. Then, after performing work in fatigue posture A for another 30 minutes, subject 11 performs specific action B, resulting in a two-minute blank period as subject 11 leaves the field of view of camera device 101. After performing work in a backward-leaning posture (hereinafter referred to as fatigue posture B) for 45 minutes, subject 11 performs specific action A, returning to fatigue posture A. Finally, after performing work in fatigue posture A for another 30 minutes, the specified period ends. Furthermore, it is assumed that specific action C is performed 5 times for illustration.

[0073] In this case, the determination unit 26 counts specific actions A as 8 times, specific actions B as 3 times, specific actions C as 5 times, and specific actions D as 6 times. Here, when calculating fatigue based on the counted number of specific actions, the minimum number of times within a day is set as the fatigue level of 0 for standardization. Therefore, the fatigue estimation unit 27 calculates fatigue by multiplying the difference obtained by subtracting the minimum number of times within a day from the number of specific actions by the first fatigue level. For example, since specific action A is 8 times, the result is 1.1 × (8-3) = 5.5. Based on the number of times the specific actions are counted, the fatigue estimation unit 27 calculates that 5.5 fatigue levels have accumulated in the waist area of ​​the subject 11.

[0074] Similarly, the fatigue estimation unit 27 calculates that specific action B accumulated 6.6 fatigue in the shoulder, specific action C accumulated 8.5 fatigue in the back, and specific action D accumulated 5.0 fatigue in the shoulder. Here, specific action B and specific action D represent the fatigue in the shoulder, which are the same fatigue site, and the fatigue estimation unit 27 calculates the average fatigue in the shoulder as the shoulder fatigue. Specifically, the shoulder fatigue is 5.8.

[0075] Next, refer to Figure 7 The correction of the fatigue level of subject 11 during the blank period is explained. Figure 7 This is a diagram used to illustrate the blank period of the implementation method. For example... Figure 7 As shown, if the subject 11 leaves the field of view of the camera device 101, a blank period is formed during which fatigue estimation based on the image cannot be performed. Therefore, in this embodiment, when such a blank period is formed, the fatigue estimation unit 27 accumulates a preset fill fatigue value according to the length of the blank period, and adds the accumulated value to the previously calculated fatigue value.

[0076] For example, Figure 6 In the example where subject 11 takes a two-minute break, the fatigue estimation unit 27 accumulates -0.05 fatigue points per minute as a replenishment of fatigue. Therefore, subject 11's fatigue partially recovers, calculated as 5.7 fatigue points in the shoulders, 8.4 in the back, and 5.4 in the waist. Furthermore, if other tasks are performed outside the field of view of camera device 101 during the break, the fatigue points corresponding to those tasks are accumulated, increasing subject 11's overall fatigue. Subject 11's actions during such breaks can be automatically determined by obtaining action plans from an external schedule management server (not shown), or subject 11 can input them into the fatigue estimation system 200 themselves.

[0077] Next, in this embodiment, the fatigue estimation unit 27 performs a process to consider factors such as fatigue rate and fatigue intensity. Figure 6The fatigue level is corrected for the accumulated fatigue posture A after the 8th specific action A. Specifically, the posture of the subject 11 after a predetermined time within a specified period and before the subject 11 performs the specific action, along with the accumulated fatigue per unit time, is saved to the storage unit 24, etc. The fatigue estimation unit 27 uses this data to estimate the fatigue level of the subject 11 after the last specific action. In addition, the predetermined time is the beginning of the specified period, immediately after the specific action, or immediately after a blank period, etc. In other words, the duration of a fatigue posture is sandwiched between the predetermined time and the time of the specific action. The fatigue estimation unit 27 calculates the accumulated fatigue per unit time of the fatigue posture sandwiched between the predetermined time and the time of the specific action.

[0078] For example, in the example shown in the figure, fatigue posture A lasted for 30 minutes before the 6th specific action D, leading to the performance of fatigue posture D. It can be assumed that the fatigue causing the performance of specific action D is due to the 30 minutes of fatigue posture A. Therefore, the fatigue estimation unit 27 calculates the accumulated fatigue level (i.e., the second fatigue level) of fatigue posture A per minute as 0.08 by dividing the first fatigue level of specific action D (2.5) by 30 minutes. Furthermore, since the fatigue location for specific action D is set to the shoulder, the fatigue posture A here is also set to accumulate 0.08 fatigue level in the shoulder per minute and saved to the storage unit 24.

[0079] Furthermore, the fatigue estimation unit 27 also calculates the second fatigue level of the shoulder as 3.3 / 30 minutes = 0.11 for fatigue posture A after the 6th specific action D and before the 3rd specific action B in the figure, and saves it to the storage unit 24. Here, in the two calculation examples above, the second fatigue level accumulated in the shoulder due to fatigue posture A is calculated, but the calculated values ​​differ. Therefore, the fatigue estimation unit 27 determines that fatigue posture A accumulates 0.10 fatigue level in the shoulder every minute by taking their average value, and updates the information saved in the storage unit 24. The fatigue estimation unit 27 also saves the second fatigue level to the storage unit 24 for other fatigue postures using the same calculation.

[0080] Then, fatigue prediction section 27 regarding such Figure 6During the period when the fatigue level cannot be estimated due to the fatigue posture A after the 8th specific action A, the fatigue level of the subject 11 is estimated by referring to the second fatigue level stored in the storage unit 24, including the fatigue level during that period. For example, in the example shown in the figure, the subject 11 adopts the fatigue posture A during the period when the fatigue level cannot be estimated. Therefore, assuming that 0.10 fatigue level is accumulated in the shoulder every minute, it is calculated as 30 minutes × 0.10 = 3.0. Therefore, the fatigue estimation unit 27 estimates, together with the previously calculated fatigue level, that 8.7 fatigue level has been accumulated in the shoulder, 8.4 fatigue level has been accumulated in the back, and 5.4 fatigue level has been accumulated in the waist.

[0081] Furthermore, the above-described estimation results are based solely on the captured images, and therefore may not always align with the actual fatigue felt by the subject 11. If the estimation of fatigue level deviates from the subject 11's subjective feeling of fatigue, the subject 11 may experience a sense of disharmony. In this embodiment, the fatigue estimation unit 27 performs a fatigue-based correction to estimate the fatigue level taking into account the subject 11's subjective feeling of fatigue. Specifically, the fatigue estimation unit 27 receives fatigue-related information from the subject 11 and performs fatigue level correction based on the received information.

[0082] For example, the fatigue estimation system 200, through the output unit 28 and the display device 105, displays a question to the subject 11, such as "How much fatigue do you feel?", after a specified period, and obtains the subject 11's fatigue level as a response. The input from the subject 11 is received by the receiving device 102 and obtained by the second acquisition unit 22. The obtained fatigue level includes fatigue levels corresponding to the shoulders, back, and waist, respectively. The fatigue estimation unit 27 outputs the obtained fatigue level and the average of the calculated fatigue level as an estimated fatigue level value.

[0083] Here, as an example, suppose the user 11 inputs a fatigue level of 7.0 in the shoulder, 7.0 in the back, and 6.0 in the waist. The fatigue estimation unit 27 calculates the average of the obtained fatigue levels and the calculated fatigue degree. The fatigue estimation unit 27 calculates that the accumulated fatigue degree is 7.9 in the shoulder, 7.7 in the back, and 5.7 in the waist, and outputs the estimation result to the output unit 28.

[0084] Furthermore, if multiple datasets of calculated fatigue levels and perceived fatigue are accumulated in this way, correlations can be established. For example, Figure 8This is a graph used to illustrate the correction of fatigue level in the implementation method. The graph shows a curve depicting the accumulated dataset, with the obtained fatigue sensation plotted on the X-axis and the calculated fatigue level plotted on the Y-axis. In the example in the graph, since the calculated fatigue level is a higher value than the obtained fatigue level, for example, when a correlation function is obtained through regression analysis (refer to the dashed line in the figure), the slope is less than 1.

[0085] Therefore, by substituting the calculated fatigue level into the aforementioned function, the fatigue level that reduces the sense of incoordination can be inferred without receiving input from the subject 11.

[0086] The output unit 28 outputs an image to the display device 105. (See reference...) Figure 9 and Figure 10 Explain the output results. Figure 9 Figure 1 illustrates the information output by the fatigue estimation system from the implementation method. Furthermore, Figure 10 Figure 2 illustrates the information output by the fatigue prediction system from the implementation method.

[0087] like Figure 9 As shown, image data representing the fatigue level of the subject 11 is displayed on the display module 105a of the display device 105 via output from the output unit 28. The display device 105 uses the monitor provided with the computer 100a of the subject 11, but other displays may also be used. For example, the display device 105 may also be a dedicated monitor for the fatigue estimation system 200.

[0088] As shown in the figure, the fatigue level of subject 11 is represented by each body part in the image data. Specifically, the image data separately displays "shoulder stiffness" (representing shoulder fatigue), "back pain" (representing back fatigue), and "lower back pain" (representing lower back fatigue). In addition, as supplementary information, the image data also shows the location of each fatigued body part on the doll, a comprehensive evaluation of fatigue, and explanations and suggestions regarding the predicted fatigue levels.

[0089] In addition, such as Figure 10 As shown, suggestions can also be made regarding postures where fatigue tends to accumulate. For example, in... Figure 10 In the example, fatigue posture A, which has the second highest fatigue level, is selected and displayed along with a statement indicating that fatigue is particularly easy to accumulate.

[0090] [action]

[0091] Next, refer to Figure 11The operation of the fatigue prediction system 200 described above will be explained. Figure 11 This is a flowchart illustrating the operation of the fatigue prediction system in the implementation method.

[0092] In the fatigue estimation system 200 of this embodiment, firstly, the fatigue estimation unit 27 reads the personal fatigue information stored in the storage unit 24 (step S101). The personal fatigue information read here is information that establishes a correlation between a specific action, the fatigued part, and information related to the first degree of fatigue.

[0093] The camera device 101 starts working in advance and continuously outputs multiple images constituting a motion image. The first acquisition unit 21 begins to acquire the output images (acquisition step S102), and then continues to acquire multiple images continuously until the fatigue prediction system 200 stops.

[0094] Here, the posture estimation unit 25 estimates the posture of the subject 11 based on the acquired image (step S103). The determination unit 26 determines whether the subject 11 performed a specific action by judging whether the action of the subject 11, obtained from the changes in the posture of the subject 11 estimated by the posture estimation unit 25, matches a specific action contained in the personal fatigue information (step S104). In addition, if multiple specific actions are included, the determination of whether the subject 11's action matches each of the multiple specific actions is performed sequentially.

[0095] If it is determined that the target 11 has performed a specific action ("Yes" in step S104), the determination unit 26 counts the number of specific actions by adding +1 (step S105). Then, proceed to step S106. On the other hand, if it is not determined that the target 11 has performed a specific action ("No" in step S104), skip step S105 and proceed to step S106.

[0096] In step S106, the determination unit 26 determines whether a predetermined period has elapsed. If it is determined that the predetermined period has not elapsed ("No" in step S106), the process returns to step S103, and the estimation of the subject 11's posture and the determination of whether there is a specific action are repeated. On the other hand, if it is determined that the predetermined period has elapsed ("Yes" in step S106), the fatigue estimation unit 27 estimates the subject 11's fatigue level based on the number of specific actions counted (estimate step S107). Then, the estimation device 100 prepares for the next fatigue level estimation by initializing the number of specific actions and ending the process.

[0097] In this embodiment, as described above, the fatigue level of the subject 11 can be estimated simply by determining whether a specific action has been performed. Furthermore, it is possible to improve the accuracy of the estimated fatigue level of the subject 11, and by combining multiple correction mechanisms applicable to individual subjects 11, a fatigue estimation system 200 that meets the accuracy requirements of the subject 11 or managers who manage the fatigue level of the subject 11 can be easily constructed. Thus, the fatigue estimation system 200 of this embodiment can more appropriately estimate the fatigue level of the subject 11.

[0098] [Effects, etc.]

[0099] As described above, the fatigue estimation system 200 of this embodiment includes: an information output device (e.g., a camera device 101) that outputs information related to the position of a body part of the subject 11; and an estimation device 100 that, based on the information output from the information output device within a specified period, counts the number of specific actions that occur corresponding to fatigue accumulation, thereby estimating and outputting the fatigue level of the subject 11 accumulated within the specified period.

[0100] In this fatigue estimation system 200, the number of times the subject 11 performs a specific action is counted based on whether the predicted changes in the subject 11's posture correspond to a specific action resulting from accumulated fatigue. Since there is a correlation between the accumulated fatigue of the subject 11 and the counted number of specific actions, the subject 11's fatigue level can be estimated simply by counting the number of such specific actions. This simplifies the calculation process used to estimate the subject 11's fatigue level. Therefore, in the fatigue estimation system 200 of this embodiment, the fatigue level of the subject 11 can be estimated more appropriately.

[0101] Alternatively, the fatigue estimation system 200 may also include a receiving device 102 that receives fatigue input, which is fatigue corresponding to the fatigue level of the subject 11 and is accumulated within a specified period based on the subject 11's subjective fatigue. The estimation device 100 corrects the subject 11's fatigue level based on the fatigue and outputs it.

[0102] Therefore, the subjective fatigue experienced by the subject 11 can be reflected in the estimated fatigue level, enabling the estimation of fatigue level that reduces the sense of disharmony for the subject 11. Thus, in the fatigue estimation system 200 of this embodiment, the fatigue level of the subject 11 can be estimated more appropriately.

[0103] Alternatively, the fatigue estimation system 200 may also include a storage device (e.g., storage unit 24) storing personal fatigue information of the subject 11, which includes information related to the accumulated fatigue level, i.e., the first fatigue level, whenever a specific action is counted. The estimation device 100 estimates the fatigue level of the subject 11 by accumulating the number of times the first fatigue level corresponds to the specific action.

[0104] Therefore, based on the habits revealed by the number of specific actions performed by each subject 11, a more suitable estimation of the subject 11's fatigue level can be made. Consequently, it is possible to estimate fatigue level that reduces the sense of incoordination for the subject 11. Therefore, in the fatigue estimation system 200 of this embodiment, the fatigue level of the subject 11 can be estimated more appropriately.

[0105] Alternatively, for example, the personal fatigue information may include fatigue location information that associates fatigued parts with specific actions, where the fatigued parts are the body parts of the subject 11 whose first fatigue level is accumulated each time a specific action is counted.

[0106] Therefore, it is possible to infer the fatigue level of each body part of the subject 11. Thus, it is possible to infer the fatigue level of each body part in greater detail, and therefore, it is possible to infer the fatigue level of the subject 11 more appropriately.

[0107] Alternatively, for example, if the estimation device 100 sets the posture of the subject 11, which is estimated based on information after a predetermined time within a specified period and before the specific action of the subject 11 is counted, as a fatigue posture, it can calculate the first fatigue degree, i.e., the second fatigue degree, accumulated per unit time through the fatigue posture by dividing the first fatigue degree by the duration of the fatigue posture, and use the calculated second fatigue degree to correct the fatigue degree of the subject 11 and output it.

[0108] Therefore, by using a second degree of fatigue based on the posture during the period from the predetermined time to the performance of a specific action, a more accurate estimation of the fatigue level of the subject 11 can be made. Thus, a more accurate estimation of fatigue level can be achieved, and the fatigue level of the subject 11 can be estimated more appropriately.

[0109] Alternatively, for example, the estimation device 100 may estimate the posture of the subject 11 based on the information output after the last count of a specific action, determine whether the estimated posture of the subject 11 after the last count of a specific action is a posture that conforms to a fatigue posture, add the calculated value obtained by accumulating the second fatigue degree corresponding to the duration of the posture that conforms to the fatigue posture to the fatigue degree of the subject 11 and output it.

[0110] Therefore, it is possible to estimate fatigue level based on a second fatigue level, including periods during which fatigue level cannot be estimated by counting the number of specific actions. Thus, more accurate fatigue level estimation is possible, and the fatigue level of the subject 11 can be estimated more appropriately.

[0111] Alternatively, for example, the estimation device 100 may output a prompt message to the subject 11 to indicate a fatigue posture.

[0112] Therefore, it is possible to provide the subject 11 with information on postures that are more likely to accumulate fatigue, which can help the subject 11 understand postures that are more likely to accumulate fatigue.

[0113] Alternatively, for example, it may also include a device 103 for obtaining personal information of the subject 11, which includes at least one of age, gender, height, weight, muscle mass, level of mental stress, body fat percentage, and proficiency in sports. The device 100 uses the obtained personal information to correct the fatigue level of the subject 11 and output it.

[0114] Therefore, by refining the data based on various personal information, a more accurate estimation of fatigue levels can be made. Consequently, the fatigue level of subject 11 can be estimated more appropriately.

[0115] Alternatively, for example, the acquiring device 103 may acquire personal information by connecting to an external device 104 that stores health diagnostic results containing personal information.

[0116] Therefore, personal information can be obtained all at once based on health diagnosis results that manage a large amount of personal information. Thus, by modifying various personal information, it is easy to achieve a more accurate estimation of fatigue levels, and to more appropriately estimate the fatigue level of subject 11.

[0117] Alternatively, for example, the estimation device 100 may use a calculated value obtained by accumulating a pre-set fatigue level corresponding to the length of the blank period to correct and output the fatigue level of the object 11 during the blank period, whereby the information output device cannot output information within a specified period.

[0118] Therefore, even when the image does not contain the subject 11 and fatigue cannot be estimated, it is possible to fill in the gaps by pre-set fatigue levels, thus more accurately estimating the accumulated fatigue over a specified period. Consequently, the fatigue level of the subject 11 can be estimated more appropriately.

[0119] Furthermore, the fatigue estimation method of this embodiment includes: an acquisition step S102, acquiring information related to the position of a body part of the subject 11; and an estimation step S107, based on the output information, counting the number of specific actions that occur within a specified period corresponding to fatigue accumulation, thereby estimating the fatigue level of the subject 11 accumulated within the specified period.

[0120] Therefore, it can achieve the same effect as the fatigue prediction system 200 mentioned above.

[0121] Furthermore, this embodiment can also be implemented as a computer-readable, non-transitory recording medium containing a program for causing a computer to execute the fatigue estimation method described above.

[0122] Therefore, computers can achieve the same effect as the fatigue prediction methods mentioned above.

[0123] (Other implementation methods)

[0124] The implementation methods have been described above, but this disclosure is not limited to the above-described implementation methods.

[0125] For example, in the above embodiments, the processing to be performed by a specific processing unit may be performed by other processing units. Furthermore, the order of multiple processes may be changed, or multiple processes may be executed in parallel.

[0126] Furthermore, the fatigue prediction system or device of this disclosure can be implemented by multiple devices, each having a portion of one of the multiple constituent elements, or by a single device having all of the multiple constituent elements. Additionally, a portion of the function of a constituent element can be implemented as the function of another constituent element; the allocation of functions among the constituent elements is arbitrary. Any configuration that substantially enables the full realization of all the functions of the fatigue prediction system or device of this disclosure is included in this disclosure.

[0127] Furthermore, in the above embodiments, each component can also be implemented by executing a software program suitable for each component. Each component can also be implemented by reading and executing a software program recorded on a recording medium such as a hard disk or semiconductor memory by a program execution unit such as a CPU or processor.

[0128] Furthermore, each component can also be implemented in hardware. For example, each component can be a circuit (or integrated circuit). These circuits can either form a single circuit as a whole or be separate circuits. Moreover, these circuits can be either general-purpose circuits or special-purpose circuits.

[0129] Furthermore, the overall or specific technical solutions disclosed herein can also be implemented by systems, devices, methods, integrated circuits, computer programs, or recording media such as computer-readable CD-ROMs, or by any combination of systems, devices, methods, integrated circuits, computer programs, and recording media.

[0130] Furthermore, in addition to using a camera device structure, the present disclosure can also be implemented as a method for inferring the subject's posture using a position sensor structure. Specifically, a sensor module including a position sensor and a potential sensor is used to infer the subject's posture. Here, it is assumed that the subject is wearing multiple sensor modules, but the number of sensor modules worn by the subject is not particularly limited. It is also possible for the subject to wear only one sensor module.

[0131] Furthermore, there are no particular restrictions on the style of wearing the sensor modules; any style is acceptable as long as they can measure the location of specified body parts on the subject. For example, the subject can wear clothing equipped with multiple sensor modules.

[0132] A sensor module is a device installed on a designated body part of a subject and linked to that designated body part to output information indicating the result of detection or measurement. Specifically, the sensor module has a position sensor that outputs position information related to the spatial position of the designated body part of the subject, and a potential sensor that outputs potential information indicating the electrical potential of the designated body part of the subject. The figure shows a sensor module that has both a position sensor and a potential sensor, but a potential sensor is not necessary if the sensor module has a position sensor. The position sensor in such a sensor module is an example of an information output device that outputs position information as information related to the position of the subject's body part. Therefore, the output information is position information, which includes information about the relative or absolute position of the designated body part of the subject. Furthermore, the output information may also include, for example, potential information. Potential information includes information about the value of the potential measured at the designated body part of the subject. Position information and potential information will be explained in detail below along with the position sensor and potential sensor.

[0133] A position sensor is a detector that detects the relative or absolute spatial position of a specified body part of a person wearing a sensor module, and outputs information related to the spatial position of the specified body part as a detection result. The spatial position-related information includes information that can determine the position of the body part in space, as described above, and information that can determine changes in the position of the body part accompanying body movement. Specifically, the spatial position-related information includes the position of joints and bones in space and information indicating changes in that position.

[0134] A position sensor is composed of various sensors, including accelerometers, angular velocity sensors, magnetometers, and distance sensors. The position information output by the position sensor can approximate the spatial position of a specified body part of a person, so the person's posture can be inferred based on the spatial position of the specified body part.

[0135] A potential sensor is a detector that measures the potential at a specified body part of a person wearing a sensor module and outputs information representing the potential of that specified body part as the measurement result. A potential sensor is a measuring device with multiple electrodes, and a potentiometer measures the potential generated between these electrodes. The potential information output by the potential sensor represents the potential generated at the specified body part of the person, which corresponds to the activity potential of muscles at that specified body part, thus improving the accuracy of the inference of the person's posture based on the activity potential of the specified body part.

[0136] In one embodiment of the fatigue estimation system described here, the estimated posture of the subject is used to estimate the subject's fatigue level, as described above. Furthermore, the processing following the estimation of the subject's posture is the same as in the above embodiment, so descriptions are omitted.

[0137] In addition to the method for estimating the subject's fatigue level described in the above embodiments, there are other methods, such as: estimating the subject's fatigue level based on the subject's posture using the formula a × muscle load + b × joint load + c × blood flow, with coefficients a, b, and c as coefficients (in other words, weighted coefficients). Here, muscle load and joint load are unitless indicators within the range of 0 to 1, standardized from quantities having Newton units to a predetermined maximum value of 1. Furthermore, blood flow is a unitless indicator within the range of 0 to 1, obtained as the ratio of a measured value below the initial value to the initial value. By setting the relationship between the coefficients in the above formula to a + b + c = 1, the fatigue level calculated using the above formula is also calculated as a value within the range of 0 to 1.

[0138] Furthermore, the above formula is an example using three indicators, but it is possible to estimate the fatigue level of the subject by using at least one of the three indicators. In this case, by setting the sum of the weighting coefficients multiplied by each indicator to 1, the fatigue level of the subject can be calculated as a value in the range of 0 to 1, just as above.

[0139] However, in these other methods, it is difficult to make the estimation of fatigue levels suitable for each individual as described above. Furthermore, it is difficult to adjust the various parameters to estimate the fatigue levels for each individual. Therefore, in other methods, the fatigue levels are calculated multiple times for a period equivalent to the single specific action calculated in the above-described embodiment. Since these multiple calculations are equivalent to the single specific action described above, the same fatigue levels can be obtained. That is, by adjusting the various parameters to make all these multiple calculations consistent, even with other methods, parameters suitable for estimating fatigue levels for each individual can be determined.

[0140] As described above, the aforementioned estimation device can also be another method for estimating the fatigue level of the subject. Based on the formula with coefficients a, b, and c, namely a × muscle load + b × joint load + c × blood flow, the fatigue level of the subject is estimated. The fatigue level is calculated multiple times for a period equivalent to one specific action based on the formula, and a, b, and c are corrected based on the results of the multiple calculations.

[0141] Therefore, for another method of estimating fatigue level based on the formula a × muscle load + b × joint load + c × blood flow, the coefficients of a, b, and c can be corrected to estimate the fatigue level suitable for each individual as described in the above embodiment. That is, other fatigue estimation methods can be modified based on the fatigue level calculated in this embodiment to make them suitable for each individual, and can also be used to expand the universality of other fatigue estimation methods.

[0142] Furthermore, this disclosure can also be implemented as a fatigue estimation method executed by a fatigue estimation system or device. This disclosure can also be implemented as a program for causing a computer to execute such a fatigue estimation method, or as a computer-readable, non-transitory recording medium containing such a program.

[0143] In addition, this disclosure also includes various modifications to the embodiments that can be conceived by those skilled in the art, or embodiments that are achieved by arbitrarily combining the constituent elements and functions of each embodiment without departing from the spirit of this disclosure.

[0144] Label Explanation

[0145] 11. Object

[0146] 24. Storage Unit (Storage Device)

[0147] 100 Speculation Device

[0148] 101 Camera device (information output device)

[0149] 102 Acceptance Device

[0150] 103 Acquisition Device

[0151] 104 External Devices

[0152] 200 Fatigue Prediction System

Claims

1. A fatigue prediction system, wherein, have: An information output device that outputs information related to the location of a part of the subject's body; The estimation device, based on the information output from the information output device within a specified period, counts the number of specific actions that occur corresponding to fatigue accumulation, thereby estimating and outputting the fatigue level of the subject accumulated within the specified period. as well as The storage device stores the personal fatigue information of the aforementioned subject, including information related to the accumulated fatigue level (i.e., the first fatigue level) each time the aforementioned specific action is counted. The aforementioned estimation device accumulates the first degree of fatigue corresponding to the number of times the specific action is performed, thereby estimating the fatigue level of the subject. In the aforementioned speculative device, If the posture of the subject, inferred from the aforementioned information, is defined as a fatigue posture after a predetermined time within the aforementioned period and before the aforementioned specific action of the subject is counted, then a second fatigue degree is calculated by dividing the first fatigue degree by the duration of the fatigue posture. This second fatigue degree is the first fatigue degree accumulated per unit time through the fatigue posture. The calculated second fatigue level is used to correct and output the fatigue level of the subject.

2. The fatigue prediction system as described in claim 1, wherein, It also includes a device for receiving input of fatigue, which is fatigue corresponding to the fatigue level of the subject and is accumulated within the specified period based on the subject's subjective fatigue. The aforementioned estimation device, based on the aforementioned feeling of fatigue, corrects and outputs the fatigue level of the subject.

3. The fatigue prediction system as described in claim 1, wherein, The aforementioned personal fatigue information includes fatigue location information that associates fatigued parts with the aforementioned specific actions, where the fatigued parts are the body parts of the subject that accumulate the aforementioned first degree of fatigue each time the aforementioned specific action is counted.

4. The fatigue prediction system as described in claim 1, wherein, In the aforementioned speculative device, Based on the information output after the last count of the aforementioned specific actions, the posture of the subject is inferred. Determine whether the posture of the subject, inferred after the last count of the aforementioned specific actions, conforms to the aforementioned fatigue posture. The calculated value is added to the fatigue level of the subject and output. This calculated value is obtained by accumulating the second fatigue level corresponding to the duration of the posture that conforms to the above fatigue posture.

5. The fatigue prediction system as described in claim 1, wherein, The aforementioned prediction device outputs a prompt message to the subject indicating the aforementioned fatigue posture.

6. The fatigue prediction system as described in claim 1, wherein, It also has a device for obtaining the personal information of the aforementioned individuals, including at least one of the following: age, gender, height, weight, muscle mass, level of mental stress, body fat percentage, and proficiency in sports. The aforementioned estimation device uses the acquired personal information to correct and output the fatigue level of the aforementioned subject.

7. The fatigue prediction system as described in claim 6, wherein, The aforementioned acquiring device acquires the aforementioned personal information by connecting to an external device, which stores health diagnostic results containing the aforementioned personal information.

8. The fatigue prediction system according to any one of claims 1 to 7, wherein, During the blank period, the aforementioned estimation device uses a calculated value obtained by accumulating a pre-set fatigue level corresponding to the length of the blank period to correct and output the fatigue level of the subject. The blank period is the period during which the aforementioned information output device cannot output the aforementioned information within the specified period.

9. The fatigue prediction system as described in claim 1, wherein, In the aforementioned speculative device, Another method for estimating the fatigue level of the aforementioned subjects is based on a formula that uses at least one of the following indicators—muscle load, joint load, and blood flow—and a weighted coefficient multiplied by each of these indicators to estimate the fatigue level of the subjects. The weighting is adjusted based on the results of multiple calculations of fatigue levels over a period equivalent to one of the aforementioned specific actions.

10. The fatigue prediction system as described in claim 1, wherein, In the aforementioned speculative device, Another method for estimating the fatigue level of the aforementioned subjects is based on a formula with coefficients a, b, and c. This formula is a × muscle load + b × joint load + c × blood flow. Based on the above formula, the fatigue level is calculated multiple times for a period equivalent to one specific action described above. Based on the above calculation results, a, b, and c are corrected.

11. A fatigue prediction method, wherein, include: The acquisition step involves obtaining information related to the location of the subject's body parts; The estimation step involves counting the number of specific actions that occur within a specified period, corresponding to the accumulation of fatigue, based on the information output above, thereby estimating the fatigue level of the subject accumulated within the specified period. as well as The storage step involves saving the individual's fatigue information, which includes information related to the accumulated fatigue level (i.e., the first fatigue level) each time the specific action is counted. The above estimation steps correspond to the number of times the specific action is performed, and the first level of fatigue is accumulated to estimate the fatigue level of the subject. In the above inference steps, If the posture of the subject, inferred from the aforementioned information, is defined as a fatigue posture after a predetermined time within the aforementioned period and before the aforementioned specific action of the subject is counted, then a second fatigue degree is calculated by dividing the first fatigue degree by the duration of the fatigue posture. This second fatigue degree is the first fatigue degree accumulated per unit time through the fatigue posture. The calculated second fatigue level is used to correct and output the fatigue level of the subject.

12. A program recording medium having a program for causing a computer to execute the fatigue estimation method of claim 11.

Images