Fatigue feature-based work hour prediction method and device, and electronic device

Abstract

The application relates to a fatigue feature-based work hour prediction method and device and electronic equipment, and the method comprises the following steps: obtaining a data sample set on a selected route, wherein the data sample set comprises a work hour data set and a fatigue feature value data set; constructing a work hour probability prediction model by using the work hour data set and the fatigue feature value data set; determining a first fatigue feature value of a driver before work hour prediction, inputting the first fatigue feature value into the work hour probability prediction model, and predicting a work hour probability of the driver on the selected route. The application improves the accuracy of real-time work hour prediction.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method, apparatus, and electronic device for predicting work hours based on fatigue characteristics. Background Technology

[0002] With the continuous expansion of underground mining depth and scale, and the increasing automation of machinery and equipment, improving the utilization rate of mining and transportation machinery and equipment and achieving efficient operation are key issues that every mining enterprise needs to focus on. Work hour prediction is a crucial foundation for the precise scheduling of transportation equipment, enabling better real-time scheduling and precise control, and providing data support for the construction of intelligent scheduling systems in underground mines.

[0003] Currently, due to the low level of automation in mining equipment, manual operation of machinery will remain the mainstream for a long time to come. However, existing work hour prediction does not take into account the impact of human factors on equipment operation, resulting in low accuracy of real-time work hour prediction and affecting the real-time monitoring of the dispatching system and emergency equipment handling. Summary of the Invention

[0004] In view of this, it is necessary to provide a method, device and electronic equipment for predicting work hours based on fatigue characteristics, so as to take into account human fatigue factors and provide decision-makers with more accurate work hour information.

[0005] To achieve the above objectives, in a first aspect, the present invention provides a method for predicting work hours based on fatigue characteristic values, comprising:

[0006] Obtain a data sample set on the selected route, wherein the data sample set includes a work hour dataset and a fatigue characteristic value dataset;

[0007] A probability prediction model for work hours is constructed using the aforementioned work hour dataset and fatigue feature value dataset.

[0008] Before predicting the work hours, the driver's first fatigue characteristic value is determined, and the first fatigue characteristic value is input into the work hour probability prediction model to predict the driver's work hour probability on the selected route.

[0009] Furthermore, obtaining the data sample set on the selected route includes:

[0010] Within the selected route, obtain samples of the driver's work hours under different continuous working durations;

[0011] Obtain fatigue characteristic data samples of drivers under different continuous working durations.

[0012] Furthermore, the acquisition of driver work hour data samples under different continuous working durations includes:

[0013] The working hours are defined as the time during which a driver works continuously and completes a normal operation on a selected route.

[0014] Acquire multiple first work hours data of the driver over multiple days for each continuous work duration;

[0015] The average of multiple first operation time data under each continuous operation duration is processed to obtain operation time data samples under different continuous operation durations.

[0016] Furthermore, the acquisition of fatigue characteristic data samples of drivers under different continuous working durations includes:

[0017] Define the fatigue characteristic values ​​within a preset time period preceding a specified time as the fatigue characteristic data for that specified time.

[0018] Acquire first fatigue feature data under different continuous working durations within the same working period over multiple days, and use the first fatigue feature data as fatigue feature data samples for different continuous working durations.

[0019] Furthermore, the data sample set also includes the baseline working hours for the selected route;

[0020] Obtain the baseline working hours for the selected route, including:

[0021] Calculate the expected value of the work time data sample and use the expected value as the baseline work time for the selected route.

[0022] Furthermore, the step of constructing a work time probability prediction model using the work time dataset and fatigue feature value dataset includes:

[0023] Fit a two-dimensional curve between the sample of work time data and the duration of continuous work, and determine the average work time data corresponding to each duration of continuous work based on the relationship of the two-dimensional curve;

[0024] The driver's fatigue level is determined based on the average working hours data and the baseline working hours, and the probability distribution of the fatigue level under a certain fatigue characteristic value is determined based on the fatigue characteristic data sample.

[0025] Furthermore, determining the driver's fatigue level for each continuous working period based on the average working hours data and the baseline working hours includes:

[0026] Calculate the fluctuation ratio of the average working hours for each continuous working period to the baseline working hours;

[0027] The driver's fatigue level is determined based on the fluctuation ratio for each continuous working period.

[0028] Furthermore, the step of determining the driver's first fatigue characteristic value before predicting the work hours, inputting the first fatigue characteristic value into the work hour probability prediction model, and outputting the driver's work hour probability on the selected route includes:

[0029] The probability of each fatigue level occurring corresponding to the first fatigue characteristic value is determined based on the probability distribution.

[0030] The probability of each fatigue level is converted into the probability of a fluctuation ratio level; the second working hour data under each level fluctuation ratio is calculated based on the baseline working hour, and the probability of the driver's working hour fluctuation range on the selected route is determined based on the second working hour data.

[0031] Secondly, the present invention also provides a work time prediction device based on fatigue characteristic values, comprising:

[0032] The acquisition module is used to acquire a data sample set on the selected route, wherein the data sample set includes a work time dataset and a fatigue feature value dataset;

[0033] The module is used to construct a probability prediction model for work hours using the work hour dataset and fatigue feature value dataset;

[0034] The prediction module is used to determine the driver's first fatigue characteristic value before predicting the work hours, input the first fatigue characteristic value into the work hour probability prediction model, and output the driver's work hour probability on the selected route.

[0035] Thirdly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps in the above-described method for predicting work hours based on fatigue feature values.

[0036] The beneficial effects of using the above embodiments are:

[0037] This invention, based on actual mine operations, acquires a dataset of working hours and fatigue characteristic values ​​along selected mine routes. By analyzing these datasets, a probabilistic prediction model for working hours is constructed—a probability distribution function of working hours based on baseline working hours. By determining the driver's first fatigue characteristic value before predicting working hours, the working hours of transport equipment can be predicted with relatively high accuracy. Compared to previous prediction models that typically consider the influence of the mine face and machinery, this invention emphasizes the impact of human factors on working hours, better reflecting the randomness of human activity during operations and contributing to improved prediction accuracy. Attached Figure Description

[0038] Figure 1 This is a flowchart illustrating an embodiment of the work time prediction method based on fatigue feature values ​​provided by the present invention.

[0039] Figure 2 This is a flowchart illustrating the process of constructing a job time probability prediction model according to an embodiment of the present invention;

[0040] Figure 3 A fitting curve diagram provided in one embodiment of the present invention;

[0041] Figure 4 This is a flowchart illustrating the probability of predicting job working hours according to an embodiment of the present invention.

[0042] Figure 5 A schematic diagram of an embodiment of the work time prediction device based on fatigue characteristics provided by the present invention;

[0043] Figure 6 This is a schematic diagram of an embodiment of an electronic device provided by the present invention. Detailed Implementation

[0044] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0045] In the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. Furthermore, "a plurality of" means two or more, unless otherwise explicitly specified. The reference to "embodiment" herein means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0046] This invention provides a method for predicting work hours based on fatigue feature values, including: Specific embodiments are described in detail below:

[0047] Please see Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the work time prediction method based on fatigue feature values ​​provided by the present invention. A specific embodiment of the present invention discloses a work time prediction method based on fatigue feature values, comprising:

[0048] Step S101: Obtain the data sample set on the selected route, wherein the data sample set includes the work time dataset and the fatigue feature value dataset;

[0049] Step S102: Construct a probability prediction model for job hours using the job hour dataset and fatigue feature value dataset;

[0050] Step S103: Before predicting the work hours, measure the driver's first fatigue characteristic value, input the first fatigue characteristic value into the work hour probability prediction model, and predict the driver's work hour probability on the selected route.

[0051] This invention, based on actual mine operations, acquires a dataset of working hours and fatigue characteristic values ​​along selected mine routes. By analyzing these datasets, a probabilistic prediction model for working hours is constructed—a probability distribution function of working hours based on baseline working hours. By determining the driver's first fatigue characteristic value before predicting working hours, the working hours of transport equipment can be predicted with relatively high accuracy. Compared to previous prediction models that typically consider the influence of the mine face and machinery, this invention emphasizes the impact of human factors on working hours, better reflecting the randomness of human activity during operations and contributing to improved prediction accuracy.

[0052] In one embodiment of the present invention, obtaining a data sample set on a selected route includes:

[0053] In the selected route, obtain samples of driver work hour data under different continuous working durations;

[0054] Obtain fatigue characteristic data samples of drivers under different continuous working durations.

[0055] First, it should be noted that the prerequisites for obtaining a valid data sample set include: ensuring that the driver has sufficient sleep, is in good spirits, and is not fatigued before the start of the experiment; selecting transportation equipment that has been tested and is in normal working order; selecting a fixed route at the work site and working on the same fixed route at the same time every day; and ensuring that the driver continuously drives the equipment on that route within a shift.

[0056] The time a driver has worked during a normal shift is called the continuous working time t. c This refers to the time already completed before the start of normal operation of a fixed route for data collection experiments.

[0057] In one embodiment of the present invention, obtaining work hour data samples of drivers under different continuous working durations includes:

[0058] The working hours are defined as the time during which a driver works continuously and completes a normal operation on a selected route.

[0059] Acquire multiple first work hours data of the driver over multiple days for each continuous work duration;

[0060] The average of multiple first operation time data under each continuous operation duration is processed to obtain operation time data samples under different continuous operation durations.

[0061] It is understandable that the working hours refer to the time it takes for a driver to complete one normal operation of the fixed route after working continuously for a certain period of time since the start of the test. For example, with 1 minute as the interval between adjacent continuous working hours, starting from time 0, the working hours data of the driver at different continuous working hours each day are collected, and the average is taken as the working hours data sample t0 under different continuous working hours.

[0062] In one embodiment of the present invention, obtaining fatigue characteristic data samples of drivers under different continuous working durations includes:

[0063] Define the fatigue characteristic values ​​within a preset time period preceding a specified time as the fatigue characteristic data for that specified time.

[0064] Obtain the first fatigue feature data under different continuous working durations within the same working period over multiple days, and use the first fatigue feature data as fatigue feature data samples for different continuous working durations.

[0065] First, it should be noted that the fatigue characteristic value can be the heart rate value, which is highly correlated with the degree of fatigue and is easy to collect, and the heart rate value can be used as an indicator to judge the degree of fatigue.

[0066] Fatigue characteristic data samples were collected based on different continuous working durations. For example, heart rate values ​​were collected at the same time on multiple days at 1-minute intervals and averaged. One minute before the start of the experiment, fatigue characteristic values ​​within this time interval were collected as fatigue characteristic data at time 0. Fatigue characteristic values ​​within the time interval [0,1] were collected as fatigue characteristic values ​​at time 1, and so on. The fatigue characteristic data at time t were the fatigue characteristic values ​​within the time interval [t-1,t]. Fatigue characteristic data under different continuous working durations within the same working period on multiple days were collected in this way to obtain fatigue characteristic data samples K with different continuous working durations. t .

[0067] In one embodiment of the present invention, the data sample set also includes the baseline working hours of the selected route;

[0068] Obtain the baseline working hours for the selected route, including:

[0069] Calculate the sample expectation of the work time data sample and use the sample expectation as the baseline work time for the selected route.

[0070] Understandably, when the driver is in good mental condition and not fatigued, multiple samples of working hours data for the selected route can be obtained, and then the expected value of these samples can be used as the baseline working hour t. b It should be noted that the baseline working time t can also be used. b This serves as sample data at time 0 in the job time dataset.

[0071] In one embodiment of the present invention, please refer to Figure 2 , Figure 2 This is a flowchart illustrating the process of constructing a probability prediction model for job hours according to an embodiment of the present invention. The model utilizes a job hour dataset and a fatigue feature value dataset to construct the probability prediction model for job hours, including:

[0072] Step S201: Fit a two-dimensional curve between the sample of work time data and the duration of continuous work, and determine the average work time data corresponding to each duration of continuous work based on the relationship of the two-dimensional curve;

[0073] Step S202: Determine the driver's fatigue level within each continuous working period based on average working hours data and baseline working hours, and determine the probability distribution of fatigue level under a certain fatigue characteristic value based on fatigue characteristic data samples.

[0074] Understandably, based on work hour data samples under different continuous work duration conditions, the Origin software function can be used to perform fitting operations to fit the corresponding two-dimensional curve, thereby obtaining the relationship between continuous work duration and work hours: t0 = f(t c ).

[0075] In a specific embodiment, for example, several sample work hours with a baseline work hour of 14 minutes and a continuous work duration ranging from 1 to 120 minutes are analyzed. The scatter plot of the sample data shows that while the data fluctuations are small, the data points are relatively dispersed. Spline interpolation is then used for interpolation, with a sample data size of 120. Finally, Origin is used for fitting, resulting in the interpolated sample point-line plot, the fitted curve, and the functional relationship. Please refer to [link to relevant documentation]. Figure 3 , Figure 3 This is a fitting curve diagram provided in one embodiment of the present invention.

[0076] It is understandable that when the continuous operation duration is 0, i.e., when the two-dimensional curve represents the moment when the continuous operation duration is 0, the baseline working time is the working time at that moment. The integral average of the working time over the time interval [0,1] is taken as the average working time data for the continuous operation duration [0,1]. Similarly, the working time over the time interval [t-1,t] is the integral average of the continuous operation duration [t-1,t]. This method is then used to determine the average work hours dataset for each minute of continuous operation. In a specific embodiment, MATLAB software can be used to calculate the integral mean of the obtained functional relationship and update it to the average work hours dataset t for each continuous operation duration. m .

[0077] Specifically, when determining the driver's fatigue level within each continuous working period, the average working hours can be compared with the baseline working hours and the average working hours per minute of continuous working time. The driver's fatigue level or excitement level in each minute of continuous working time can be judged and divided. Then, based on the corresponding fatigue characteristic value, the probability distribution of the fatigue level under a certain fatigue characteristic value can be obtained.

[0078] Among these measures, the driver's fatigue level is determined based on average working hours data and baseline working hours, including:

[0079] Calculate the fluctuation ratio of the average working hours for each continuous working period to the baseline working hours;

[0080] The driver's fatigue level is determined based on the fluctuation ratio for each continuous working period.

[0081] Understandably, the continuous changes in average working hours per minute over a sustained working period can reflect different levels of driver fatigue. Therefore, by comparing the average working hours with the baseline working hours and calculating the percentage of fluctuation, we can obtain the following: The fluctuations in this indicator will inform further judgments.

[0082] Specifically, the upper limit threshold of the fluctuation ratio is first defined. For example, if it is greater than 50%, the driver is judged to be overly fatigued. Considering personnel safety and work efficiency, work should be stopped and a certain amount of rest should be given. Within the fluctuation range of [0%, 50%], a fatigue level is set every 10%. If the fluctuation ratio is 10%, it is level one fatigue; 20% is level two fatigue, and so on to classify fatigue levels L. t .

[0083] It should be noted that in actual operation, the fluctuation ratio may be negative. In this case, it is judged that the driver is in an excited state. A lower limit threshold for the fluctuation ratio is defined. For example, if the fluctuation ratio is less than -50%, the driver is judged to be over-excited. Considering personnel safety, the operation should be stopped and the driver given a certain amount of rest. Within the fluctuation range of [-50%, 0%], an excitement level is set every 10%. If the fluctuation ratio is -10%, it is level one excitement; -20% is level two excitement, and so on, dividing the excitement level L. e .

[0084] In a specific embodiment, the fluctuation ratio can be divided according to the average working hours data and the baseline working hours to determine the fatigue level under each continuous working time. The fatigue level table for some continuous working time intervals is shown in Table 1.

[0085] Table 1 Partial Fatigue Level Table

[0086]

[0087] Then, based on the fatigue level and corresponding fatigue characteristic values ​​in each time period, the probability distribution of fatigue level under a certain fatigue characteristic value is analyzed. Specifically, based on the obtained fatigue characteristic value datasets for each continuous work duration and the corresponding fatigue level (i.e., the sum of fatigue level and excitement level), the probability distribution function P(L|K) of fatigue level under this fatigue characteristic data is calculated using MATLAB software. t )=h(L,K t ).

[0088] In one embodiment of the present invention, please refer to Figure 4 , Figure 4 This is a flowchart illustrating the prediction of job time probability according to an embodiment of the present invention, as shown below. Figure 4 As shown, before predicting work hours, the driver's first fatigue characteristic value is measured. This first fatigue characteristic value is input into the work hour probability prediction model, which outputs the driver's work hour probability on the selected route, including:

[0089] Step S401: Determine the probability of each fatigue level occurring corresponding to the first fatigue characteristic value based on the probability distribution;

[0090] Step S402: Convert the probability of each fatigue level occurring into the probability of the fluctuation ratio level occurring;

[0091] Step S403: Calculate the second working hour data under the fluctuation ratio of each level based on the baseline working hour, and determine the probability of the driver's working hour fluctuation range on the selected route based on the second working hour data.

[0092] It is understandable that, according to the above probability distribution function, the fatigue characteristic values ​​at different times may be the same or different, and each fatigue characteristic value may correspond to different fatigue levels at different times. By comprehensively calculating, the probability of each level of fatigue occurring under a certain fatigue characteristic value can be obtained.

[0093] Specifically, each fatigue level corresponds to a different fluctuation ratio. For example, fatigue level one corresponds to a fluctuation ratio of [0%, 10%], and so on. Each fatigue level is converted into a corresponding fluctuation ratio level, and then the probability of each fluctuation ratio level occurring at a certain fatigue characteristic value is obtained.

[0094] Then, based on the average working hours and baseline working hours in the fluctuation ratio formula, each fluctuation ratio level corresponds to a range of working hours. Based on the probability of each fluctuation ratio level occurring under a certain fatigue characteristic value, the probability of the second working hour data corresponding to different fluctuation ratios under the first fatigue characteristic value can be obtained. Thus, the probability of the corresponding second working hour can be predicted based on different fatigue characteristic values, realizing real-time prediction of the driver's working hours on the selected route.

[0095] In a specific embodiment, based on the probability of occurrence of each fluctuation ratio level under each fatigue characteristic value, the probability of predicted working time fluctuation range under each fatigue characteristic value within the continuous working time of 1 to 120 minutes is shown in Table 2.

[0096] Table 2. Probability Prediction Table for Partial Work Hour Intervals

[0097]

[0098] To better implement the fatigue-based work time prediction method in this invention, please refer to the relevant documentation. Figure 5 , Figure 5 This is a schematic diagram of an embodiment of the work time prediction device based on fatigue characteristics provided by the present invention. The embodiment of the present invention provides a work time prediction device 500 based on fatigue characteristics, comprising:

[0099] The acquisition module 501 is used to acquire a data sample set on the selected route, wherein the data sample set includes a work time dataset and a fatigue feature value dataset.

[0100] Module 502 is used to construct a probability prediction model for work hours using the work hour dataset and fatigue feature value dataset;

[0101] The prediction module 503 is used to determine the driver's first fatigue characteristic value before predicting the work hours, input the first fatigue characteristic value into the work hour probability prediction model, and output the driver's work hour probability on the selected route.

[0102] It should be noted that the device 500 provided in the above embodiments can implement the technical solutions described in the above method embodiments. The specific implementation principles of the above modules or units can be found in the corresponding content in the above method embodiments, and will not be repeated here.

[0103] Based on the above-described fatigue-feature-based job time prediction method, this invention also provides an electronic device, including: a processor and a memory, and a computer program stored in the memory and executable on the processor; when the processor executes the computer program, it implements the steps in the fatigue-feature-based job time prediction method of the above embodiments.

[0104] Figure 6 The diagram shows a structural schematic of an electronic device 600 suitable for implementing embodiments of the present invention. The electronic device in the embodiments of the present invention may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of the present invention.

[0105] The electronic device includes a memory and a processor, wherein the processor may be referred to as processing device 601 below, and the memory may include at least one of read-only memory (ROM) 602, random access memory (RAM) 603 and storage device 608 below, as detailed below:

[0106] like Figure 6 As shown, electronic device 600 may include a processing device (e.g., a central processing unit, a graphics processor, etc.) 601, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 602 or a program loaded from storage device 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of electronic device 600. Processing device 601, ROM 602, and RAM 603 are interconnected via bus 604. Input / output (I / O) interface 605 is also connected to bus 604.

[0107] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic device 600 to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 An electronic device 600 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0108] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a storage device 608, or installed from a ROM 602. When the computer program is executed by the processing device 601, it performs the functions defined in the methods of the embodiments of the present invention.

[0109] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0110] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for predicting work hours based on fatigue characteristics, characterized in that, include: Obtain a data sample set on the selected route, wherein the data sample set includes a work hour dataset and a fatigue feature value dataset; A probability prediction model for work hours is constructed using the aforementioned work hour dataset and fatigue feature value dataset. Before predicting the work hours, the driver's first fatigue characteristic value is determined, and the first fatigue characteristic value is input into the work hour probability prediction model to predict the driver's work hour probability on the selected route. The step of constructing a probability prediction model for work hours using the work hour dataset and fatigue feature value dataset includes: Fit a two-dimensional curve between the sample of work time data and the duration of continuous work, and determine the average work time data corresponding to each duration of continuous work based on the relationship of the two-dimensional curve; Calculate the fluctuation ratio between the average working hours data and the baseline working hours for each continuous working period, and determine the driver's fatigue level within each continuous working period based on the fluctuation ratio. And determine the probability distribution of fatigue level under a certain fatigue characteristic value based on the fatigue characteristic data sample; The step of determining the driver's first fatigue characteristic value before predicting work hours, inputting the first fatigue characteristic value into the work hour probability prediction model, and outputting the driver's work hour probability on the selected route includes: The probability of each fatigue level occurring corresponding to the first fatigue characteristic value is determined based on the probability distribution. The probability of each fatigue level occurring is converted into the probability of the fluctuation ratio level occurring. The second working hours data under the fluctuation ratio of each level are calculated based on the baseline working hours, and the probability of the driver's working hours fluctuation range on the selected route is determined based on the second working hours data.

2. The method for predicting work hours based on fatigue characteristics according to claim 1, characterized in that, The process of obtaining the data sample set on the selected route includes: Within the selected route, obtain samples of the driver's work hours under different continuous working durations; Obtain fatigue characteristic data samples of drivers under different continuous working durations.

3. The method for predicting work hours based on fatigue characteristics according to claim 2, characterized in that, The acquisition of driver work hour data samples under different continuous working durations includes: The working hours are defined as the time during which a driver works continuously and completes a normal operation on a selected route. Acquire multiple first work hours data of the driver over multiple days for each continuous work duration; The average of multiple first operation time data under each continuous operation duration is processed to obtain operation time data samples under different continuous operation durations.

4. The method for predicting work hours based on fatigue characteristics according to claim 2, characterized in that, The acquisition of fatigue characteristic data samples of drivers under different continuous working durations includes: Define the fatigue characteristic values ​​within a preset time period preceding a specified time as the fatigue characteristic data for that specified time. Acquire first fatigue feature data under different continuous working durations within the same working period over multiple days, and use the first fatigue feature data as fatigue feature data samples for different continuous working durations.

5. The method for predicting work hours based on fatigue characteristics according to claim 3, characterized in that, The data sample set also includes the baseline working hours for the selected route; Obtain the baseline working hours for the selected route, including: Calculate the expected value of the work time data sample and use the expected value as the baseline work time for the selected route.

6. A fatigue-based work time prediction device, used to perform the steps of the fatigue-based work time prediction method according to any one of claims 1 to 5, characterized in that, include: The acquisition module is used to acquire a data sample set on the selected route, wherein the data sample set includes a work time dataset and a fatigue feature value dataset; The module is used to construct a probability prediction model for work hours using the work hour dataset and fatigue feature value dataset; The prediction module is used to determine the driver's first fatigue characteristic value before predicting the work hours, input the first fatigue characteristic value into the work hour probability prediction model, and output the driver's work hour probability on the selected route.

7. An electronic device, characterized in that, The method includes a memory and a processor, wherein the memory is used to store a program; and the processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the fatigue-based work time prediction method according to any one of claims 1 to 5.

Images