Fatigue level estimation system and fatigue level estimation method
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2025-02-03
- Publication Date
- 2026-08-14
AI Technical Summary
【0019】 本開示は、作業者の疲労度の推定精度を向上できる疲労度推定システム及び疲労度推定方法を提供できる。
Smart Images

Figure 2026131298000001_ABST
Abstract
Description
Technical Field
[0003]
[0001] The present disclosure relates to a fatigue degree estimation system and a fatigue degree estimation method.
Background Art
[0002] The system of Patent Document 1 calculates the fatigue degree of a worker when performing a task involving walking (i.e., a walking task). Specifically, when determining the fatigue degree of the worker, the system of Patent Document focuses on the fatigue degree calculated from information such as the moving distance, the means of movement, the weight of the equipment, and the carrying method.
[0003] The system of Patent Document 2 calculates the time-series change in the fatigue degree of a worker when performing a task not involving walking (i.e., a non-walking task). Specifically, the system of Patent Document 2 acquires the posture taken by the worker in the non-walking task and uses the physical load and duration at that time to estimate the time-series change in the fatigue degree of the worker.
[0004] Regarding Non-Patent Documents 1 and Non-Patent Documents 2, they will be described later in the form for implementing the invention.
Prior Art Documents
Patent Documents
[0005]
Patent Document 1
Patent Document 2
Non-Patent Documents
[0006]
Non-Patent Document 1
[0007] When workers walk while carrying objects, they actually adopt various walking postures depending on factors such as the contents, weight, and way they are holding the object. Therefore, it is conceivable that the level of fatigue a worker experiences can vary depending on the walking posture they adopt while moving.
[0008] However, the technologies described in Patent Documents 1 and 2 do not calculate the worker's fatigue level from the walking posture adopted by the worker, so there was room for improvement in the accuracy of estimating the worker's fatigue level.
[0009] This disclosure aims to provide a fatigue estimation system and fatigue estimation method that can improve the accuracy of estimating the fatigue level of workers, in light of such challenges. [Means for solving the problem]
[0010] A fatigue level estimation system relating to one aspect of this disclosure is: A posture acquisition unit that acquires the walking posture adopted by the worker during work, A duration acquisition unit that acquires the duration of the aforementioned walking posture, An external force information acquisition unit that acquires information on the external force that the worker receives when he takes the aforementioned walking posture, A load estimation unit estimates the physical load on the worker due to the walking posture, based on the walking posture and the external force information received by the worker when taking the walking posture. The system includes a fatigue estimation unit that estimates the worker's fatigue level during a walking section, which is the section in which the walking posture is maintained, based on the duration of the walking posture and the physical burden on the worker due to the walking posture.
[0011] The fatigue level estimation system of this disclosure can improve the accuracy of estimating the fatigue level of workers through the configuration described above.
[0012] Other fatigue estimation systems relating to this disclosure are: The unit further comprises a physical characteristics acquisition unit that acquires the physical characteristics of the aforementioned worker, The load estimation unit, Based on the walking posture, the external force information received by the worker when adopting the walking posture, and the physical characteristics, the physical load on the worker due to the walking posture is estimated.
[0013] In other forms of fatigue estimation systems related to this disclosure, The load estimation unit further, The physical load on the worker due to the walking posture is estimated using a pre-trained AI model that takes the walking posture, information on the external forces the worker experiences when taking the walking posture, and the physical characteristics as input.
[0014] The fatigue level estimation system of this disclosure can further improve the accuracy of estimating the fatigue level of workers through the configuration described above.
[0015] Other fatigue estimation systems relating to this disclosure are: The aforementioned work includes a plurality of the aforementioned walking sections, The fatigue degree estimation unit calculates the total fatigue degree of the worker in the plurality of walking intervals, and estimates the total fatigue degree of the worker as the fatigue degree of the worker in the work.
[0016] In work, a worker takes various walking postures, and it is conceivable that the fatigue degree of the worker changes accordingly. The fatigue degree estimation system of the present disclosure can further improve the estimation accuracy of the fatigue degree of the worker with the above-described configuration.
[0017] The fatigue degree estimation method according to one aspect of the present disclosure includes a computer acquiring a walking posture taken by a worker in work, acquiring the duration of the walking posture, acquiring external force information received by the worker when taking the walking posture, estimating the physical load of the worker due to the walking posture based on the walking posture and the external force information received by the worker when taking the walking posture, estimating the fatigue degree of the worker in a walking interval, which is an interval during which the walking posture continues, based on the duration of the walking posture and the physical load of the worker due to the walking posture.
[0018] The fatigue degree estimation method of the present disclosure can improve the estimation accuracy of the fatigue degree of the worker with the above-described configuration.
Advantages of the Invention
[0019] The present disclosure can provide a fatigue degree estimation system and a fatigue degree estimation method that can improve the estimation accuracy of the fatigue degree of a worker.
Brief Description of the Drawings
[0020] [Figure 1] It is a block diagram showing an example of the configuration of a fatigue degree estimation system according to the first embodiment. [Figure 2] It is a flowchart showing an example of the operation of a fatigue degree estimation system according to the first embodiment. [Figure 3]This figure shows an example of the estimation results of the time-series change in the fatigue level of workers in the fatigue level estimation system 10 according to the first embodiment. [Figure 4] This figure shows an example of the estimation results of the time-series change in the worker's remaining physical strength in the fatigue estimation system 10 according to the first embodiment. [Modes for carrying out the invention]
[0021] In the following, specific embodiments to which the present invention is applied will be described in detail with reference to the drawings. In each drawing, the same elements are denoted by the same reference numerals, and redundant explanations will be omitted where necessary for clarity.
[0022] (First Embodiment) First, the configuration of the fatigue level estimation system 10 according to the first embodiment will be described using Figure 1. Figure 1 is a block diagram showing an example of the configuration of the fatigue level estimation system 10 according to the first embodiment.
[0023] As shown in Figure 1, the fatigue estimation system 10 is a system for estimating the fatigue level of a worker performing a task. In the following description, when a worker performs a task, they assume one or more postures involving walking (hereinafter referred to as walking postures) and one or more postures without walking (hereinafter referred to as non-walking postures). Walking postures are, for example, the stance and free-swinging postures taken when performing a task that involves walking while carrying an object. Non-walking postures are, for example, the postures taken when performing standing work, manual work, or machine work in a fixed location.
[0024] The fatigue level estimation system 10 includes a posture acquisition unit 11, a duration acquisition unit 12, an external force information acquisition unit 13, a physical characteristics acquisition unit 14, a load estimation unit 15, and a fatigue level estimation unit 16.
[0025] The posture acquisition unit 11 acquires a predetermined walking posture adopted by the worker during work. The acquired walking posture is a posture maintained for a predetermined period of time or longer. Furthermore, the acquired walking posture is one in which both feet are in contact with the ground. Specifically, the posture acquisition unit 11 acquires a video or image including the worker that has been stored in advance. Then, the posture acquisition unit 11 acquires the worker's walking posture using motion capture or image recognition. This walking posture is indicated by the position and angle of each part of the worker's body (e.g., each joint). Alternatively, the posture acquisition unit 11 may acquire the worker's walking posture from a simulation in which the worker walks in a virtual environment.
[0026] The duration acquisition unit 12 acquires the duration of time the worker maintains a walking posture (hereinafter referred to as the duration). Hereinafter, the period in which the worker maintains a walking posture will be referred to as the walking period.
[0027] The external force information acquisition unit 13 acquires information about the external forces that the worker experiences when assuming a walking posture. Specifically, the external force information includes the magnitude and direction of the external force that the worker experiences from an object they are holding. The external force information acquisition unit 13 uses a pre-stored mechanics simulator to acquire the magnitude and direction of the external force experienced by the worker. In this case, the magnitude of the external force may be a value calculated from information such as the type and size of the object. When the worker is not holding any objects while walking, the magnitude of the external force acting on the hands should be set to 0.
[0028] The physical characteristics acquisition unit 14 acquires the physical characteristics of the worker that have been stored in advance. The physical characteristics of the worker include, for example, the worker's weight and height. The physical characteristics may not be variables, i.e., values tailored to the individual worker, but rather predetermined set values or reference values such as average values.
[0029] The load estimation unit 15 estimates the physical load on the worker due to walking posture based on the walking posture, information on the external forces the worker experiences when taking the walking posture, and the worker's physical characteristics. Specifically, the load estimation unit 15 estimates the physical load on the worker due to walking posture by comparing the walking posture, external force information, and physical characteristics with information pre-stored in a database (not shown). The physical load is the muscle load on each part of the worker's body (for example, each joint of the body). The muscle load on each part is calculated, for example, as a value of %MVC, which is a ratio to MVC (Maximum Voluntary Contraction).
[0030] The load estimation unit 15 may also estimate the physical load on the worker due to their walking posture using a pre-stored model that takes walking posture, external force information, and physical characteristics as input. This model could be, for example, a mechanics simulator or a trained AI model. The load estimation unit 15 can also estimate the physical load on the worker due to their walking posture in real time by using this model.
[0031] Alternatively, the load estimation unit 15 may estimate the physical load on the worker due to their walking posture based on their walking posture and information on the external forces the worker experiences when adopting that posture, without using the physical characteristics of the worker acquired by the physical characteristics acquisition unit 14. In that case, the fatigue level estimation system 10 does not need to include the physical characteristics acquisition unit 14.
[0032] The fatigue estimation unit 16 estimates the worker's fatigue level during a walking period (walking section) based on the duration of the walking posture and the physical load on the worker due to the walking posture. Specifically, the fatigue estimation unit 16 estimates the worker's fatigue level at a given time based on the physical load on the worker due to the walking posture at that time. The fatigue estimation unit 16 accumulates the worker's fatigue level due to the walking posture at each time point from the start to the end of the walking section (i.e., the duration of the walking posture). By doing so, the fatigue estimation unit 16 estimates the time-series change in the worker's fatigue level during the walking section. Note that the estimation result may represent the worker's fatigue level at each time point within the walking section.
[0033] Furthermore, the fatigue estimation unit 16 estimates the worker's remaining physical strength in the walking section based on the worker's remaining physical strength at the start of the walking section and the worker's fatigue level during the walking section. Specifically, the fatigue estimation unit 16 estimates the worker's remaining physical strength at a predetermined time by subtracting the worker's fatigue level at a predetermined time from the worker's remaining physical strength at a time prior to the predetermined time. The fatigue estimation unit 16 estimates the worker's remaining physical strength at each time point from the start to the end of the walking posture (i.e., the duration of the walking posture). By doing so, the fatigue estimation unit 16 estimates the time-series change in the worker's remaining physical strength during the walking section. Note that the estimation result may be the worker's remaining physical strength at each time point within the walking section.
[0034] For example, the fatigue estimation unit 16 uses a muscle fatigue model to estimate at least one of the worker's fatigue level or remaining physical strength at each time point. This muscle fatigue model is disclosed in Patent Document 2, Non-Patent Document 1, and Non-Patent Document 2.
[0035] Next, the operation of the fatigue level estimation system 10 according to the first embodiment will be explained using Figure 2. Figure 2 is a flowchart showing an example of the operation of the fatigue level estimation system 10 according to the first embodiment.
[0036] As shown in Figure 2, in step S101, the posture acquisition unit 11 of the fatigue estimation system 10 acquires the walking posture adopted by the worker during the work. Next, in step S102, the duration acquisition unit 12 acquires the duration of the walking posture. Next, in step S103, the external force information acquisition unit 13 acquires information about the external forces that the worker experiences when taking a walking posture.
[0037] Next, in step S104, the physical characteristics acquisition unit 14 acquires the physical characteristics of the worker. Next, in step S105, the load estimation unit 15 estimates the physical load on the worker due to the walking posture, based on the worker's walking posture, information on the external forces the worker experiences when taking the walking posture, and the worker's physical characteristics.
[0038] Next, in step S106, the fatigue estimation unit 16 estimates the worker's fatigue level during the section in which the walking posture is maintained (walking section), based on the duration of the walking posture and the physical load on the worker due to the walking posture.
[0039] Next, in step S107, the fatigue estimation unit 16 estimates the worker's remaining physical strength in the walking section based on the worker's remaining physical strength at the start of the walking section and the worker's fatigue level in the walking section.
[0040] Furthermore, workers may adopt various walking postures during work, and their fatigue levels may change accordingly. If a worker adopts multiple walking postures during work, or in other words, if the work includes sections in which multiple walking postures are maintained (walking sections), the fatigue level estimation system 10 may repeat the processing of steps S101 to S107 described above to estimate the fatigue level of each worker in each of the multiple walking sections. Alternatively, the fatigue level estimation unit 16 of the fatigue level estimation system 10 may sum the fatigue levels of the workers in the multiple walking sections and estimate the total fatigue level of the workers as the fatigue level of the workers in the work. By doing so, the fatigue level estimation system 10 can improve the accuracy of estimating the fatigue level of the workers.
[0041] Furthermore, the fatigue estimation system 10 may acquire a predetermined non-walking posture adopted by the worker during the work and estimate the worker's fatigue level during the section in which the non-walking posture is maintained (non-walking section). Alternatively, the fatigue estimation system 10 may estimate the worker's remaining physical strength at the end of the non-walking section based on the worker's remaining physical strength at the start of the non-walking section and the worker's fatigue level during the non-walking section. In this case, "walking posture" and "walking section" in steps S101 to S107 should be read as "non-walking posture" and "non-walking section," respectively. Additionally, if the work includes multiple non-walking sections, the fatigue estimation system 10 may estimate the fatigue level of each worker in each of the multiple non-walking sections.
[0042] Next, using Figure 3, we will explain the estimation results of the time-series changes in the fatigue level of workers in the fatigue level estimation system 10 according to the first embodiment.
[0043] Figure 3 shows an example of the estimation results of the time-series change in worker fatigue in the fatigue estimation system 10 according to the first embodiment. In the example in Figure 3, it is assumed that the worker took walking posture A1, non-walking posture B1, walking posture A2, and non-walking posture B2 in sequence during work.
[0044] The fatigue estimation system 10 estimates the time-series changes in the worker's fatigue level during each of the following periods: the period in which walking posture A1 is maintained (walking section a1), the period in which non-walking posture B1 is maintained (non-walking section b1), the period in which walking posture A2 is maintained (walking section a2), and the period in which non-walking posture B2 is maintained (non-walking section b2). The estimation results are shown by the solid (thick) lines in Figure 3.
[0045] Furthermore, as a comparative example of this disclosure, the solid line (thin) in Figure 3 shows the result of estimating the time-series change in worker fatigue in the above-mentioned section using the system described in Patent Document 1. The dotted line (thin) in Figure 3 shows the result of estimating the time-series change in worker fatigue in the above-mentioned section using the system described in Patent Document 2.
[0046] The system described in Patent Document 1 calculates the fatigue level of a worker when they perform work that involves walking (walking work) based on information such as distance traveled, means of transport, weight of equipment, and method of carrying, but does not calculate the fatigue level based on walking posture. Therefore, the system described in Patent Document 1 has room for improvement in the accuracy of the estimated fatigue level of workers in walking sections a1 and a2, and differs from the estimated results of fatigue level estimation system 10. Furthermore, the system described in Patent Document 1 does not have a configuration for estimating the fatigue level of workers based on their non-walking posture when they perform work that does not involve walking (non-walking work). Therefore, the system described in Patent Document 1 cannot estimate the fatigue level of workers in non-walking sections b1 and b2.
[0047] The system described in Patent Document 2 calculates the fatigue level of a worker in a non-walking posture when performing non-walking tasks, but it does not estimate the fatigue level of a worker in a walking posture. Therefore, the system described in Patent Document 2 cannot estimate the time-series change in the fatigue level of a worker in walking sections a1 and a2.
[0048] As described above, the fatigue estimation system 10 can estimate the fatigue level of a worker from the walking posture adopted by the worker, thus improving the accuracy of estimating the fatigue level of workers in tasks that include walking.
[0049] Next, using Figure 4, we will explain the estimation results of the time-series change in the worker's remaining physical strength in the fatigue estimation system 10 according to the first embodiment.
[0050] Figure 4 shows an example of the estimation results of the time-series change in the worker's remaining physical strength in the fatigue estimation system 10 according to the first embodiment. In the example in Figure 4, similar to the example in Figure 3, it is assumed that the worker took walking posture A1, non-walking posture B1, walking posture A2, and non-walking posture B2 in sequence during work.
[0051] As described above using Figure 3, the fatigue estimation system 10 estimates the time-series changes in the worker's fatigue level in each of the following sections: the section in which walking posture A1 continues (walking section a1), the section in which non-walking posture B1 continues (non-walking section b1), the section in which walking posture A2 continues (walking section a2), and the section in which non-walking posture B2 continues (non-walking section b2).
[0052] As shown in Figure 4, the fatigue estimation system 10 estimates the time-series change in the worker's remaining physical strength in each of the walking section a1, non-walking section b1, walking section a2, and non-walking section b2 by subtracting the worker's fatigue level from the worker's physical strength over time. Here, in the example in Figure 4, the worker's total strength is 100% at the start of walking section a1, as this is the start of the work. The estimation results are shown by the solid (thick) line in Figure 4.
[0053] Furthermore, as a comparative example of this disclosure, the solid (thin) line in Figure 4 shows the result of estimating the time-series change in the worker's remaining physical strength in the above-mentioned section using the system described in Patent Document 1. The dotted line in Figure 4 shows the result of estimating the time-series change in the worker's remaining physical strength in the above-mentioned section using the system described in Patent Document 2.
[0054] The fatigue estimation system 10 can improve the accuracy of estimating the fatigue level of workers in tasks that include walking, and therefore can also improve the accuracy of estimating the remaining physical strength of workers.
[0055] <Hardware Configuration> Each component of the fatigue level estimation system 10 in the above-described embodiment is composed of hardware, software, or both, and may consist of one piece of hardware or software, or multiple pieces of hardware or software.
[0056] For example, each component of the fatigue estimation system 10 in the above-described embodiment is comprised of a computer comprising a processor and memory. The processor may be, for example, a microprocessor, an MPU (Micro Processing Unit), or a CPU (Central Processing Unit). The processor may include multiple processors. The memory is comprised of a combination of volatile memory and non-volatile memory. The memory may include storage located away from the processor. In this case, the processor may access the memory via an I / O interface not shown. The processor executes one or more programs containing a set of instructions for causing the computer to perform the algorithm described with reference to the drawings.
[0057] The program, when loaded into a computer, includes a set of instructions (or software code) for causing the computer to perform one or more functions (fatigue estimation methods) as described in the embodiments. The program may be stored on a non-temporary computer-readable medium or a physical storage medium. Examples, but not limited to, include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technologies, CD-ROM, digital versatile disc (DVD), Blu-ray® disc or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices. The program may be transmitted over a temporary computer-readable medium or a communication medium. Examples, but not limited to, include temporary computer-readable medium or a communication medium that includes electrically, optically, acoustically or otherwise propagating signals.
[0058] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure are possible, as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.
[0059] Each drawing is merely illustrative to illustrate one or more embodiments. Each drawing may be associated with one or more other embodiments rather than with only one specific embodiment. As those skilled in the art will understand, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings, for example, to create embodiments not explicitly shown or described. Not all features or steps shown in any one drawing to illustrate an exemplary embodiment are necessarily required, and some features or steps may be omitted. The order of steps shown in any of the drawings may be changed as appropriate. [Explanation of Symbols]
[0060] 10 Fatigue level estimation system, 11 Posture acquisition unit, 12 Duration acquisition unit, 13 External force information acquisition unit, 14 Physical characteristics acquisition unit, 15 Load estimation unit, 16 Fatigue level estimation unit
Claims
1. A posture acquisition unit that acquires the walking posture adopted by the worker during work, A duration acquisition unit that acquires the duration of the aforementioned walking posture, An external force information acquisition unit that acquires information on the external force that the worker receives when he takes the aforementioned walking posture, A load estimation unit estimates the physical load on the worker due to the walking posture, based on the walking posture and the external force information received by the worker when taking the walking posture. The system includes a fatigue estimation unit that estimates the worker's fatigue level during a walking section, which is the section in which the walking posture is maintained, based on the duration of the walking posture and the physical burden on the worker due to the walking posture. Fatigue level estimation system.
2. The unit further comprises a physical characteristics acquisition unit that acquires the physical characteristics of the aforementioned worker, The load estimation unit, Based on the walking posture, the external force information received by the worker when adopting the walking posture, and the physical characteristics, the physical load on the worker due to the walking posture is estimated. The fatigue level estimation system according to claim 1.
3. The aforementioned work includes a plurality of the aforementioned walking sections, The fatigue level estimation unit, The fatigue levels of the worker in multiple walking sections are totaled, and the total fatigue level of the worker is estimated as the fatigue level of the worker in the work. The fatigue level estimation system according to claim 1.
4. The load estimation unit, Using a pre-trained AI model that takes the aforementioned walking posture, information on the external forces the worker experiences when adopting the walking posture, and the aforementioned physical characteristics as input, the physical load on the worker due to the walking posture is estimated. The fatigue level estimation system according to claim 2.
5. Computers The walking posture adopted by the worker during the work is captured. The duration of the aforementioned walking posture is obtained, When the worker assumes the aforementioned walking posture, information on the external force received by the worker is acquired. Based on the walking posture and the information on the external forces the worker experiences when adopting the walking posture, the physical load on the worker due to the walking posture is estimated. Based on the duration of the walking posture and the physical burden on the worker due to the walking posture, the worker's fatigue level during the walking section, which is the section in which the walking posture is maintained, is estimated. Method for estimating fatigue levels.
Citation Information
Patent Citations
Prediction system
JP2024005974A
Work planning device, work planning method, and work planning program
WO2020148876A1