A human labor intensity evaluation method and system based on joint force analysis

Abstract

The application discloses a human labor intensity evaluation method and system based on joint stress analysis, which comprises the following steps: firstly, generating human and operation object models and their attributes according to image data based on image recognition, or directly obtaining human and operation object models and their attributes from software based on man-machine engineering software; then, obtaining spatial coordinate information of each moment of human bones changing over time, spatial coordinate information of each moment of the object changing over time which is being operated by the human, and attributes such as geometric size, mass and density of the object being operated by the human; determining the stress direction and size of the human body outside each moment changing over time, estimating the pressure, torque and shear force at part or all of the human joints at each moment changing over time; finally, calculating the human labor intensity by a human labor intensity evaluation module. Compared with the traditional method, the method disclosed by the application can obtain more accurate evaluation results.

Description

Technical Field

[0001] This invention relates to human labor intensity assessment technology, and more particularly to a method and system for assessing human labor intensity based on joint stress analysis. Background Technology

[0002] Currently, existing methods for assessing human labor intensity often employ subjective evaluation, wearable sensors, or video observation of human posture to measure angles. Subjective evaluation is ineffective, highly susceptible to individual differences, and has low accuracy. Wearable sensors can acquire relatively accurate physiological parameters, but require professional operation, are not suitable for large-scale assessments, and are inconvenient to use. Video observation of human posture to measure angles does not consider factors such as task duration, recovery time, or arm vibration, which may affect the load and fatigue of the musculoskeletal system.

[0003] With the development of image recognition and analysis technologies, new systems integrating image recognition and human biomechanics knowledge can acquire human motion information non-contactly, accurately calculate the stress on human joints, and achieve simple and precise assessment of human labor intensity. Similarly, in the field of ergonomic software, there is a need for an effective tool based on ergonomic software data to accurately assess labor intensity.

[0004] Therefore, achieving a simple and accurate assessment of human labor intensity based on human motion information and human biomechanics knowledge has significant research significance and practical value. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to propose a method and system for assessing human labor intensity based on joint stress analysis, which is used to obtain human motion information in a non-contact manner, accurately calculate the stress on human joints, and achieve a simple and accurate assessment of human labor intensity.

[0006] This invention adopts the following technical solution: a method for assessing human labor intensity based on joint stress analysis, comprising the following steps:

[0007] S1. In the data acquisition module, collect and transmit work site data;

[0008] S2. In the data fusion module, data fusion is performed, the above-mentioned field data is stored, and two-dimensional and / or three-dimensional model information of the human body at each moment of time and two-dimensional and / or three-dimensional model information of the object being operated by the human body at each moment of time are generated from the field data. The object being operated by the human body includes tools and / or objects.

[0009] S3. In the human body processing module, identify personnel information, obtain the mass attributes of the human body, and obtain the spatial coordinate information of the human body's skeleton at each moment of time.

[0010] S4. In the object processing module, identify the attributes and motion trajectory information of the object being operated by the human body; the attributes include: the geometric dimensions, mass, and density of the object being operated by the human body; the motion trajectory information is the spatial coordinate information of the object being operated by the human body at each moment of time.

[0011] S5. Based on the human body external force analysis module, determine the direction and magnitude of the external force on the human body at each moment of time as it changes over time.

[0012] S6. Based on the human body internal joint force estimation module, estimate the pressure, torque and shear force at some or all human body joints at each moment of time as the human body changes over time.

[0013] S7. In the human labor intensity assessment module, construct a fatigue assessment function, calculate the instantaneous value of human fatigue, sum a series of instantaneous human fatigue values ​​at a certain time, and assess the human labor intensity based on the summation result and a preset threshold.

[0014] On the one hand, the present invention provides a method for assessing human labor intensity based on image recognition.

[0015] Specifically, in step S1, the on-site video acquisition module is used as a data acquisition module to collect on-site work information. The on-site video acquisition module includes a video acquisition submodule and a video data transmission submodule.

[0016] The video acquisition submodule includes: one or more monocular cameras and / or one or more binocular cameras and / or one or more infrared cameras and / or one or more motion-sensing cameras, for acquiring on-site video information;

[0017] The video data transmission submodule includes a network transmission device and network communication software, used to transmit the acquired video data to the video data fusion module.

[0018] In step S2, a video data fusion module is used as a data fusion module to perform data fusion. The video data fusion module includes: a video data receiving submodule, a video data storage submodule, and a video data preprocessing submodule.

[0019] The video data receiving submodule is used to receive video data from the on-site video acquisition module;

[0020] The video data storage submodule is used to store video data into a storage medium;

[0021] The video data preprocessing submodule is used to learn and identify human body information from video data, and further generate two-dimensional and / or three-dimensional model information of the human body at each moment of continuous temporal change; it is also used to learn and identify information of the object being operated by the human body from video data, and further generate two-dimensional and / or three-dimensional model information of the object at each moment of continuous temporal change.

[0022] In step S3, based on the two-dimensional and / or three-dimensional model information of the human body generated by the video data fusion module at each moment of time, the identification information of the person is obtained, the mass attributes of the human body are estimated, and the spatial coordinate information of the skeleton at each moment of time is generated.

[0023] The spatial coordinate information of the human skeleton at each moment of time varies with the human body includes: obtaining it from a three-dimensional human body model; and / or using monocular vision target recognition and localization technology to estimate the position and posture of the human body from a two-dimensional human body model to determine the spatial coordinate information of the human skeleton at each moment of time varies with the human body.

[0024] In step S4, based on the two-dimensional and / or three-dimensional model information of the object at each moment of time change generated by the video data fusion module, the object processing module obtains the identification information of the object being operated by the human body, and generates the spatial coordinate information of the object at each moment of time change, including the following sub-steps;

[0025] Step S4.1: Obtain the object that the human is currently operating on;

[0026] Step S4.2: Obtain the geometric dimensions, mass, and density attributes of the object being manipulated by the human body;

[0027] Step S4.3: After determining the object being operated on by the human body, if the object can be directly identified in the video, then obtain the spatial coordinate information of the object at each moment of time as the human body is operating on it; if the object cannot be directly identified in the video, then estimate the spatial coordinate information of the object at each moment of time as the human body is operating on it based on the current posture of the human body and the human body's movement pattern on the object being operated on.

[0028] In step S5, the human body external force analysis module, based on the spatial coordinate information of the human body's bones at each moment of time and the spatial coordinate information of the object being manipulated at each moment of time, calculates the direction and magnitude of the external force on the human body at each moment of time. The method includes the following sub-steps:

[0029] Step S5.1: Filter the spatial coordinate information of the object being operated on by the human body at each moment of time to generate smoothed spatial coordinate information of the object being operated on by the human body at each moment of time.

[0030] Step S5.2: Based on the spatial coordinate information of the object being operated on by the smoothed human body at each moment of time, obtain the velocity and acceleration of the object, and combine the geometric size, mass, and density attributes of the object to calculate the direction and magnitude of the force on the human body at each moment of time.

[0031] In step S6, the human body internal joint force estimation module estimates the pressure, torque, and shear force at some or all of the human body joints at each moment of time, based on the human body's mass attributes, the spatial coordinate information of the bones at each moment of time, and the direction and magnitude of the force on the human body's exterior at each moment of time.

[0032] In step S7, the fatigue assessment function is a calculation function that takes the pressure, torque and shear force at some or all of the joints of the human body at a certain moment as parameters and is an increasing function of the above parameters. The calculation result of the function is used as the instantaneous value of human fatigue. A series of instantaneous values ​​of human fatigue at a certain moment are summed, and the labor intensity of the human body is assessed based on the summation result and a preset threshold.

[0033] On the other hand, the present invention provides a method for assessing human labor intensity based on human factors engineering software.

[0034] The data acquisition module and data fusion module are the data acquisition module and data fusion module of the human body engineering software, and the human body processing module and operation object processing module are the human body processing module and object processing module of the human body engineering software.

[0035] Steps S1 to S4 include: directly acquiring the mass and other attributes of the virtual human body in the virtual human body action sequence that has been edited in the human-computer engineering software, the spatial coordinate information of the human body's skeleton at each moment of time, the spatial coordinate information of the object being operated by the human body at each moment of time, and the geometric dimensions, mass, density and other attributes of the object being operated by the human body, the object including tools and / or objects.

[0036] The technical solution of the present invention also includes a human labor intensity assessment system based on joint stress analysis, which uses any of the above-mentioned labor intensity assessment methods to assess human labor intensity, including: a data acquisition module, a data fusion module, a human body processing module, an operation object processing module, a force analysis module for the outside of the human body, a joint stress estimation module for the inside of the human body, and a human labor intensity assessment module.

[0037] The data acquisition module is used to collect and transmit work site data;

[0038] The data fusion module is used to store the above-mentioned field data and generate two-dimensional and / or three-dimensional model information of the human body and the object being operated by the human body at each moment of time as the field data changes over time.

[0039] The human body processing module is used to identify personnel information, human body mass, and obtain human body spatial coordinate information;

[0040] The object processing module is used to obtain the attributes and motion trajectory information of the object being manipulated by the human body;

[0041] The external force analysis module is used to determine the direction and magnitude of the external forces acting on the human body at every moment over time.

[0042] The human body internal joint force estimation module is used to estimate the pressure, torque and shear force at some or all of the human body joints at each moment of time.

[0043] The human labor intensity assessment module is used to calculate the instantaneous value of human fatigue and assess the human labor intensity.

[0044] Compared with the prior art, the present invention, employing the above technical solution, has the following technical effects:

[0045] 1. The non-contact assessment method for human labor intensity based on image recognition and human-computer interaction software involved in this invention can avoid various limitations of actual scenarios by establishing a digital human body model for multi-body kinematic simulation, and is especially suitable for labor intensity assessment of various human labor activities; the system is easy to use; through simulation technology, the system has a strong ability to resist external environmental interference.

[0046] 2. The present invention provides a method for assessing human labor intensity by identifying joint positions on a human body model, obtaining human body mass attributes and skeletal coordinate information, identifying object categories on an object model, obtaining object size, mass and other attributes, calculating external forces on the human body based on time-varying information of the human body and the object, calculating internal forces on the human joints based on the human biomechanical model, designing a fatigue assessment function, and calculating human fatigue values ​​using joint forces as parameters, and finally assessing the level of human labor intensity. Attached Figure Description

[0047] Figure 1 This is a system flowchart of the human labor intensity assessment method of the present invention;

[0048] Figure 2 This invention relates to a human body model in simulation software based on the human labor intensity assessment method. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of the application will be further described in detail below with reference to the accompanying drawings. The described embodiments are only a part of the embodiments involved in this invention. All non-innovative embodiments based on these embodiments by other researchers in the art are within the protection scope of this invention. Furthermore, the step numbers in the embodiments of this invention are only set for ease of explanation and do not limit the order of the steps. The execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0050] The essence of this invention is to acquire video or simulated information of the human body performing labor activities through image recognition algorithms or human-computer interaction software. The video or simulated information is processed to identify the posture and motion parameters of the human body at each moment, as well as the attribute parameters of the object being manipulated. Based on the changes in the motion state of the human body or object, complex actions are divided into multiple simple actions. For each simple action, a simplified human biomechanical model is applied to calculate the labor intensity of the single simple action based on the human posture and object attributes. The labor intensities of multiple simple actions are accumulated to obtain the overall labor intensity of the complex action. The labor intensity level of the complex action is assessed according to a preset labor intensity level. This can evaluate the instantaneous labor intensity of a single action or the average labor intensity of a long-term repetitive action.

[0051] like Figure 1 As shown, the present invention provides a human labor intensity assessment system based on joint stress analysis, comprising: a data acquisition module, a data fusion module, a human body processing module, an operation object processing module, a force analysis module of the human body exterior, a joint stress estimation module of the human body interior, and a human labor intensity assessment module.

[0052] The data acquisition module is used to collect and transmit work site data;

[0053] The data fusion module is used to store the above-mentioned field data and generate two-dimensional and / or three-dimensional model information of the human body and the object being operated by the human body at each moment of time as the field data changes over time.

[0054] The human body processing module is used to identify personnel information, human body mass, and obtain human body spatial coordinate information;

[0055] The object processing module is used to obtain the attributes and motion trajectory information of the object being manipulated by the human body;

[0056] The external force analysis module is used to determine the direction and magnitude of the external forces acting on the human body at every moment over time.

[0057] The human body internal joint force estimation module is used to estimate the pressure, torque and shear force at some or all of the human body joints at each moment of time.

[0058] The human labor intensity assessment module is used to calculate the instantaneous value of human fatigue and assess the human labor intensity.

[0059] Example 1: Assessment of human labor intensity based on image recognition, the implementation process is as follows:

[0060] Step S1: Use the on-site video acquisition module as a data acquisition module to collect on-site labor information.

[0061] Specifically, one or more monocular cameras, and / or one or more binocular cameras, and / or one or more infrared cameras, and / or one or more 3D cameras are used to collect on-site video information;

[0062] The acquired video data is transmitted to the video data fusion module using network transmission equipment and network communication software.

[0063] Step S2: Use the video data fusion module as the data fusion module to perform data fusion.

[0064] The video data storage submodule is used to store video data into a storage medium, including hard drives, optical discs, USB flash drives, and cloud storage.

[0065] The video data preprocessing submodule learns and identifies human information from the video data, and further generates two-dimensional and / or three-dimensional model information of the human body at each moment of continuous temporal change; further, it learns and identifies information of the object being operated on by the human body from the video data, and further generates two-dimensional and / or three-dimensional model information of the object at each moment of continuous temporal change.

[0066] Step S3: Based on the two-dimensional and / or three-dimensional model information of the human body generated by the video data fusion module at each moment of time, obtain the identification information of the person, estimate the mass attributes of the human body, and generate the spatial coordinate information of the human body's skeleton at each moment of time.

[0067] The spatial coordinate information of the human skeleton at each moment of time varies with the human body includes: obtaining it from a three-dimensional human body model; and / or using a monocular vision target recognition and localization method to estimate the position and posture of the human body from a two-dimensional human body model to determine the spatial coordinate information of the human skeleton at each moment of time varies with the human body.

[0068] Step S4: Based on the two-dimensional and / or three-dimensional model information of the object being operated by the human body at each moment of time, generated by the video data fusion module, the object operation processing module obtains the identification information of the object being operated by the human body and generates the spatial coordinate information of the object at each moment of time.

[0069] First, identify the object being manipulated by the human body, including the following scenarios:

[0070] Scenario 1: When a human body touches the object being operated on or a part of the object, or when the position of a movable object near the human body changes, the system determines that a corresponding operational relationship has occurred between the human body and the object, which is the object that the human body is operating on.

[0071] Scenario 2: When the object is occluded, obtain the object that the human was operating on before the current time point. If the human's operation movement at the current time point matches the operation movement movement of the object that the human was operating on before, then the object that the human is operating on is the object that the human was operating on before.

[0072] Scenario 3: When the object is occluded, obtain the object that the human was operating on before the current time point. If the human's operation movement at the current time point does not match the operation movement movement of the object that the human was operating on before, learn and judge the operation movement movement of the human's actions to match the operation movement movement movement of the human to operate on a certain X object. Based on the matching result, further determine the operation relationship between the human and the X object. Then the object that the human is operating on is a certain X object. The X object may also be an object that is not an object.

[0073] Then, the geometric dimensions, mass, and density attributes of the object being manipulated by the human body are obtained;

[0074] Next, after determining the object being operated on by the human body, if the object can be directly identified in the video (i.e., scenario 1 above), the spatial coordinate information of the object being operated on at each moment of time is obtained; if the object cannot be directly identified in the video (i.e., scenario 2 or 3 above), the spatial coordinate information of the object being operated on at each moment of time is estimated based on the current posture of the human body and the human body's movement pattern on the object being operated on.

[0075] Step S5: Based on the spatial coordinate information of the human skeleton at each moment of time and the spatial coordinate information of the object being manipulated at each moment of time, calculate the direction and magnitude of the force on the human body at each moment of time. The method includes the following sub-steps:

[0076] Step S5.1: Filter the spatial coordinate information of the object being operated on by the human body at each moment of time to generate smoothed spatial coordinate information of the object being operated on by the human body at each moment of time.

[0077] Step S5.2: Based on the spatial coordinate information of the object being operated on by the smoothed human body at each moment of time, obtain the velocity and acceleration of the object, and combine the geometric size, mass, and density attributes of the object to calculate the direction and magnitude of the force on the human body at each moment of time.

[0078] Step S6: Based on the mass properties of the human body, the spatial coordinate information of the bones of the human body at each moment of time, and the direction and magnitude of the forces on the human body at each moment of time, estimate the pressure, torque and shear force at some or all of the joints of the human body at each moment of time.

[0079] Step S7 involves a fatigue assessment function. The fatigue assessment function is a calculation function that takes the pressure, torque, and shear force at some or all of the joints of the human body at a certain moment as parameters and is an increasing function of the above parameters. The calculation result of the function is used as the instantaneous value of human fatigue. A series of instantaneous values ​​of human fatigue at a certain moment are summed, and the labor intensity of the human body is assessed based on the summation result and a preset threshold.

[0080] Example 2: Assessment of human labor intensity based on ergonomic software. The implementation process is as follows:

[0081] Step S1: Obtain simulation data information from the edited virtual human motion sequence in the ergonomics software, and obtain the human model in the simulation software, such as... Figure 2 As shown.

[0082] Step S2: Based on the model, directly obtain human body attributes from the human body engineering software, including two-dimensional and / or three-dimensional model information of the human body at each moment of time and two-dimensional and / or three-dimensional model information of the object that the human body is operating at each moment of time, wherein the object includes tools and / or objects.

[0083] Step S3: Obtain the mass attributes of the virtual human body and the spatial coordinate information of the skeleton of the human body at each moment of time from the human-computer interaction software data.

[0084] Step S4: Obtain complex action sequences from the human-machine interface software data, and obtain the spatial coordinate information of the object being operated by the human body at each moment of time; identify the geometric dimensions, mass, and density attributes of the object being operated by the human body.

[0085] Step S5: Using the external force analysis method of the human body in the above embodiment, determine the direction and magnitude of the external force on the human body at each moment of time.

[0086] Step S6: Using the method for estimating the force on the internal joints of the human body in the above embodiment, estimate the pressure, torque, and shear force at some or all of the joints of the human body at each moment of time as the human body changes.

[0087] Step S7: In the human labor intensity assessment module, construct a fatigue assessment function, calculate the instantaneous value of human fatigue, sum a series of instantaneous human fatigue values ​​at a certain time, and assess the human labor intensity based on the summation result and a preset threshold.

[0088] Through experiments, the labor intensity assessment results obtained based on the decomposition and calculation of human body movements in the embodiments of the present invention are more accurate than those obtained by other traditional assessment methods.

[0089] In summary, the non-contact assessment method for human labor intensity based on image recognition and ergonomic software disclosed in this invention avoids various limitations of real-world scenarios by establishing a digital human body model for multi-body kinematics simulation, making it particularly suitable for assessing the labor intensity of various human labor activities. The system is easy to use; through simulation technology, it has strong resistance to external environmental interference; the algorithm model integrates image generation and human biomechanics knowledge to achieve simple and reliable labor intensity assessment; and it has broad application prospects, applicable to multiple fields such as industrial production process optimization in virtual scenarios, human activity task assessment, and athlete training program development.

[0090] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for assessing human labor intensity based on joint stress analysis, characterized in that, Includes the following steps: S1. In the data acquisition module, collect and transmit work site data; S2. In the data fusion module, data fusion is performed, the above-mentioned field data is stored, and two-dimensional and / or three-dimensional model information of the human body at each moment of time and the two-dimensional and / or three-dimensional model information of the object being operated by the human body at each moment of time are generated from the field data; the object being operated by the human body includes objects. S3. In the human body processing module, identify personnel information, obtain the mass attributes of the human body, and obtain the spatial coordinate information of the human body's skeleton at each moment of time. S4. In the object processing module, identify the attributes and motion trajectory information of the object being operated by the human body; The attributes include: the geometric dimensions, mass, and density of the object being manipulated by the human body; the motion trajectory information is the spatial coordinate information of the object being manipulated at each moment over time. Based on the two-dimensional and / or three-dimensional model information of the object at each moment of time change generated by the data fusion module, the object processing module obtains the identification information of the object being operated by the human body, and generates the spatial coordinate information of the object at each moment of time change, including the following sub-steps. Step S4.1: Obtain the object that the human is currently operating on; Step S4.2: Obtain the geometric dimensions, mass, and density attributes of the object being manipulated by the human body; Step S4.3: After determining the object being operated on by the human body, if the object can be directly identified in the video, then obtain the spatial coordinate information of the object at each moment of time as the human body is operating on it; if the object cannot be directly identified in the video, then estimate the spatial coordinate information of the object at each moment of time as the human body is operating on it based on the current posture of the human body and the human body's operation motion on the object being operated on. S5. Based on the human body external force analysis module, determine the direction and magnitude of the external force on the human body at each moment of time as it changes over time. S6. Based on the human body internal joint force estimation module, estimate the pressure, torque and shear force at some or all human body joints at each moment of time as the human body changes over time. Specifically, based on the mass attributes of the human body, the spatial coordinate information of the skeleton at each moment of time, and the direction and magnitude of the forces on the human body at each moment of time, estimate the pressure, torque, and shear force at some or all of the joints of the human body at each moment of time. S7. In the human labor intensity assessment module, construct a fatigue assessment function, calculate the instantaneous value of human fatigue, sum a series of instantaneous human fatigue values ​​at a certain time, and assess the human labor intensity based on the summation result and a preset threshold.

2. The method for assessing human labor intensity based on joint stress analysis according to claim 1, characterized in that, In the human labor intensity assessment based on image recognition, step S1 involves using a field video acquisition module as a data acquisition module to collect labor site information. The field video acquisition module includes a video acquisition submodule and a video data transmission submodule. The video acquisition submodule includes: one or more monocular cameras and / or one or more binocular cameras and / or one or more infrared cameras and / or one or more motion-sensing cameras, for acquiring on-site video information; The video data transmission submodule includes a network transmission device and network communication software, used to transmit the acquired video data to the video data fusion module.

3. The method for assessing human labor intensity based on joint stress analysis according to claim 2, characterized in that, In step S2, a video data fusion module is used as a data fusion module to perform data fusion. The video data fusion module includes: a video data receiving submodule, a video data storage submodule, and a video data preprocessing submodule. The video data receiving submodule is used to receive video data from the on-site video acquisition module; The video data storage submodule is used to store video data into a storage medium; The video data preprocessing submodule is used to learn and identify human body information from video data, and further generate two-dimensional and / or three-dimensional model information of the human body at each moment of continuous temporal change; it is also used to learn and identify information of the object being operated by the human body from video data, and further generate two-dimensional and / or three-dimensional model information of the object at each moment of continuous temporal change.

4. The method for assessing human labor intensity based on joint stress analysis according to claim 3, characterized in that, In step S3, based on the two-dimensional and / or three-dimensional model information of the human body at each moment of time generated by the video data fusion module, the identification information of the person is obtained, the mass attributes of the human body are estimated, and the spatial coordinate information of the human skeleton at each moment of time is generated. The spatial coordinate information of the human skeleton at every moment of time as it changes over time includes: information obtained from a three-dimensional human body model; And / or use monocular vision target recognition and localization technology to estimate the position and posture of the two-dimensional human body model, and determine the spatial coordinate information of the skeleton of the human body at each moment of time as it changes over time.

5. The method for assessing human labor intensity based on joint stress analysis according to claim 4, characterized in that, In step S5, based on the spatial coordinate information of the human skeleton at each moment of time and the spatial coordinate information of the object being manipulated at each moment of time, the direction and magnitude of the force on the human body at each moment of time are calculated. The method includes the following sub-steps: Step S5.1: Filter the spatial coordinate information of the object being operated on by the human body at each moment of time to generate smoothed spatial coordinate information of the object being operated on by the human body at each moment of time. Step S5.2: Based on the spatial coordinate information of the object being operated on by the smoothed human body at each moment of time, obtain the velocity and acceleration of the object, and combine the geometric size, mass, and density attributes of the object to calculate the direction and magnitude of the force on the human body at each moment of time.

6. The method for assessing human labor intensity based on joint stress analysis according to claim 5, characterized in that, In step S7, the fatigue assessment function is a calculation function that takes the pressure, torque and shear force at some or all of the human joints at a certain moment as parameters and is an increasing function of the above parameters. The calculation result of the calculation function is used as the instantaneous value of human fatigue. A series of instantaneous values ​​of human fatigue at a certain moment are summed. The labor intensity of the human body is assessed based on the summation result and a preset threshold.

7. The method for assessing human labor intensity based on joint stress analysis according to claim 6, characterized in that, Human labor intensity assessment is performed based on human factors engineering software. The data acquisition module and data fusion module are the data acquisition module and data fusion module of the human factors engineering software, and the human body processing module and operation object processing module are the human body processing module and object processing module of the human factors engineering software. Steps S1 to S4 include: directly acquiring the mass attributes of the virtual human body in the edited virtual human body action sequence in the human-computer interaction software, the spatial coordinate information of the human body's skeleton at each moment of time, the spatial coordinate information of the object being operated on by the human body at each moment of time, and the geometric dimensions, mass, and density attributes of the object being operated on by the human body.

8. A human labor intensity assessment system based on joint stress analysis, characterized in that, The labor intensity assessment system for assessing human labor intensity using the labor intensity assessment method according to any one of claims 1 to 7 includes: a data acquisition module, a data fusion module, a human body processing module, an operation object processing module, a force analysis module for the external body, a force estimation module for the internal joints of the human body, and a human labor intensity assessment module. The data acquisition module is used to collect and transmit work site data; The data fusion module is used to store the above-mentioned field data and generate two-dimensional and / or three-dimensional model information of the human body and the object being operated by the human body at each moment of time as the field data changes over time. The human body processing module is used to identify personnel information, human body mass, and obtain human body spatial coordinate information; The operation object processing module is used to obtain the attributes and motion trajectory information of the object being operated by the human body; The force analysis module on the outside of the human body is used to determine the direction and magnitude of the forces on the outside of the human body at each moment of time. The human body internal joint force estimation module is used to estimate the pressure, torque and shear force at some or all human joints at each moment of time as the human body changes over time. The human labor intensity assessment module is used to calculate the instantaneous value of human fatigue and assess the human labor intensity.

Images