A method and system for evaluating human attention levels under high-temperature conditions

Abstract

This invention belongs to the field of human attention assessment technology in high-temperature environments. It provides a method and system for evaluating human attention levels in high-temperature environments. The system divides the ambient temperature range into multiple temperature ranges according to the order of temperature from low to high. Feature extraction is performed on near-infrared (fNIRS) data within these multiple temperature ranges to obtain feature data for each temperature range. By dividing the ambient temperature into ranges, feature extraction and filtering of the corresponding near-infrared (fNIRS) data within different temperature ranges are performed. This approach helps to reflect the performance characteristics of near-infrared (fNIRS) data in different high-temperature ranges. Furthermore, in high-temperature environments, different attention performance value calculation models are used to calculate attention performance values ​​in different temperature segments. This avoids the influence of significant differences in the human brain's metabolic rate within high-temperature ranges, better expresses the coupling relationship between fNIRS blood oxygenation signals and neural activity, and improves the accuracy of the assessment.

Description

Technical Field

[0001] This invention belongs to the field of human attention assessment technology in high-temperature environments, and particularly relates to a method and system for evaluating human attention levels in high-temperature environments. Background Technology

[0002] With global warming and frequent heat waves, the impact of sustained high temperatures on human health and work efficiency is becoming increasingly prominent. High temperatures not only affect physical and mental health but also cause cognitive decline, particularly attention deficit, leading to work errors and even accidents. Therefore, evaluating human attention performance during high-temperature exposure is of great significance.

[0003] Functional near-infrared spectroscopy (fNIRS), a non-invasive brain imaging technique, reflects neural activity by measuring changes in hemoglobin concentration in the cerebral cortex, making it suitable for attention assessment in dynamic environments. However, current fNIRS cognitive assessments are mostly based on ambient temperature environments. In high-temperature environments, the human brain's metabolic rate varies significantly, and this variation becomes particularly pronounced across different temperature ranges. This causes the coupling relationship between fNIRS blood oxygenation (HbO / HbR) and neural activity to deviate from the ambient temperature model, leading to inaccurate assessments. Summary of the Invention

[0004] To address the aforementioned problems, this invention proposes a method and system for evaluating human attention levels under high-temperature conditions. This invention divides the ambient temperature into ranges and then extracts and filters features from near-infrared (fNIRS) data corresponding to different temperature ranges. This facilitates the reflection of the characteristics of near-infrared fNIRS data within different high-temperature ranges. Furthermore, within high-temperature environments, different attention performance value calculation models are used to calculate attention performance values ​​in different temperature zones, avoiding the impact of significant variations in human brain metabolic rate within high-temperature ranges. This approach better expresses the coupling relationship between fNIRS blood oxygenation signals and neural activity, improving the accuracy of the assessment.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solution:

[0006] In a first aspect, the present invention provides a method for evaluating human attention levels under high-temperature conditions, comprising:

[0007] Acquire ambient temperature data and near-infrared fNIRS data of the left frontal lobe of the human brain;

[0008] The ambient temperature range was divided into multiple temperature ranges according to the order of temperature values ​​from low to high; feature extraction was performed on the near-infrared fNIRS data in multiple temperature ranges to obtain the feature data of each temperature range.

[0009] The temperature range to which the ambient temperature data belongs is determined. Based on the characteristic data within the corresponding temperature range and the preset attention performance value calculation model within the corresponding temperature range, the attention performance value is obtained. The attention performance value calculation model is a polynomial that includes characteristic data, exposure time, and corresponding coefficients.

[0010] Evaluation is based on attention performance scores.

[0011] Furthermore, the ambient temperature range is divided into multiple temperature ranges, including: a near-high temperature range when the temperature is greater than or equal to a first preset temperature value and less than a second preset temperature value; a high temperature range when the temperature is greater than or equal to a second preset temperature value and less than a third preset temperature value; an extreme high temperature range when the temperature is greater than or equal to a third preset temperature value and less than a fourth preset temperature value; and a range where the first preset temperature value is less than the second preset temperature value, the second preset temperature value is less than the third preset temperature value, and the third preset temperature value is less than the fourth preset temperature value.

[0012] Furthermore, during feature extraction, the extracted features include time-domain indicators and frequency-domain indicators.

[0013] Furthermore, the time-domain indicators include mean, standard deviation, skewness, kurtosis, peak-to-peak value, root mean square value, entropy, and area under curve; the frequency-domain indicators include spectral centroid, spectral standard deviation, spectral skewness, and spectral kurtosis.

[0014] Furthermore, the calculation models for attention performance values ​​in the near-high temperature range, the high temperature range, and the extreme high temperature range are as follows:

[0015] ;

[0016] ;

[0017] ;

[0018] in, a 1 、b 1 、c 1 、d 1. e 1. a 2 、b 2 、c 2. d 2. , a 3 、b 3 、c3. d 3 and X represents the coefficient; X represents the feature data; t represents the exposure time. This is a preset unit of time.

[0019] Furthermore, a low attention level is defined as an attention performance value greater than or equal to the first attention performance value and less than the second attention performance value; a medium attention level is defined as an attention performance value greater than or equal to the second attention performance value and less than the third attention performance value; and a high attention level is defined as an attention performance value greater than or equal to the third attention performance value and less than the fourth attention performance value. Wherein, the first attention performance value is less than or equal to the second attention performance value, the second attention performance value is less than or equal to the third attention performance value, and the third attention performance value is less than or equal to the fourth attention performance value.

[0020] Secondly, the present invention also provides a human attention level evaluation system under high temperature conditions, comprising:

[0021] The data acquisition module is configured to acquire ambient temperature data and near-infrared fNIRS data of the left frontal lobe of the human brain.

[0022] The feature extraction module is configured to: divide the ambient temperature range into multiple temperature ranges according to the temperature values ​​from low to high; extract features from the near-infrared fNIRS data in multiple temperature ranges to obtain feature data for each temperature range;

[0023] The calculation module is configured to: determine the temperature range to which the ambient temperature data belongs, and obtain the attention performance value based on the feature data within the corresponding temperature range and the preset attention performance value calculation model within the corresponding temperature range; wherein, the attention performance value calculation model is a polynomial including feature data, exposure time and corresponding coefficients;

[0024] The evaluation module is configured to evaluate based on attention performance scores.

[0025] Thirdly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for evaluating human attention levels under high-temperature conditions as described in the first aspect.

[0026] Fourthly, the present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to implement the steps of the method for evaluating human attention levels under high temperature conditions as described in the first aspect.

[0027] Fifthly, the present invention also provides a computer program product, the computer program product comprising a computer program, which, when executed by a processor, implements the steps of the method for evaluating human attention levels under high temperature conditions as described in the first aspect.

[0028] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0029] 1. In this invention, firstly, the ambient temperature range is divided into multiple temperature ranges according to the temperature value order from low to high; feature extraction is performed on near-infrared fNIRS data within multiple temperature ranges to obtain feature data for each temperature range; then, the temperature range to which the ambient temperature data belongs is determined, and attention performance values ​​are obtained based on the feature data within the corresponding temperature range and the preset attention performance value calculation model within the corresponding temperature range; by dividing the ambient temperature into ranges, feature extraction and screening of near-infrared fNIRS data corresponding to different ambient temperature ranges are performed, which is beneficial to reflecting the performance of near-infrared fNIRS data characteristics in different high-temperature ranges, and calculating attention performance values ​​using different attention performance value calculation models in different temperature segments within a high-temperature environment, avoiding the influence of significant changes in the human brain's metabolic rate within high-temperature ranges, and better expressing the coupling relationship between fNIRS blood oxygenation signals and neural activity, thus improving the accuracy of assessment.

[0030] 2. This invention collects fNIRS data only from the left frontal lobe, making the acquisition method simple, portable, and highly stable. It is less affected by user activity levels and has multiple application scenarios, enabling rapid deployment and flexible detection. It adjusts in real-time according to changes in high-temperature environments, flexibly assessing human attention levels under high temperatures with high accuracy, meeting real-world work requirements. It provides objective, data-driven real-time attention evaluation, avoiding bias from subjective evaluations and significantly improving assessment accuracy. Attached Figure Description

[0031] The accompanying drawings, which form part of this embodiment, are used to provide a further understanding of this embodiment. The illustrative embodiments and their descriptions are used to explain this embodiment and do not constitute an improper limitation of this embodiment.

[0032] Figure 1 This is a schematic diagram of the method flow of Embodiment 1 of the present invention. Detailed Implementation

[0033] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0034] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of this application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0035] With global warming and frequent heat waves, high-temperature records are constantly being broken, and heat waves are increasingly characterized by longer durations, wider areas, higher intensity, and higher frequency. The impact of sustained high temperatures during heat waves on human health and work efficiency is becoming increasingly prominent. High temperatures not only affect physical and mental health but also cause cognitive decline, especially attention deficit, leading to work errors and even accidents. Therefore, maintaining a high level of attention is crucial for human safety during high-temperature exposure, and achieving objective and real-time evaluation of human attention performance during high-temperature exposure is of great significance.

[0036] Methods for assessing attention performance are mainly divided into two categories: subjective and objective. Subjective methods rely on user self-reporting, are easily influenced by subjective factors, and have lower reliability. Objective methods include behavioral measurements and neurophysiological measurements. While behavioral measurements can reflect attention performance, they cannot provide real-time information on brain activity. Neurophysiological measurements, such as electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS), can directly reflect brain neural activity, providing new approaches to assessing attention performance. fNIRS, as a non-invasive brain imaging technique, reflects neural activity by measuring changes in hemoglobin concentration in the cerebral cortex. It has advantages such as high spatial resolution, strong resistance to motion interference, and portability, making it more suitable for attention assessment in dynamic environments.

[0037] As described in the background section, current cognitive assessments of fNIRS are mostly focused on normal temperature environments. However, the metabolic rate of the human brain varies significantly under high temperature conditions, causing the coupling relationship between fNIRS blood oxygenation signals (HbO / HbR) and neural activity to deviate from the normal temperature model, resulting in inaccurate assessments.

[0038] To address at least one of the aforementioned problems, this invention provides a method for evaluating human attention levels under high-temperature conditions, which is of great significance for the accurate evaluation of human attention in high-temperature environments and for ensuring the health and safety of outdoor populations.

[0039] This invention provides a method for evaluating human attention levels under high-temperature environments, addressing the technical problems of inaccurate assessment results and insufficient coverage caused by inadequate data application, complex integration algorithms, and poor real-time performance in existing technologies. It also fills a gap in current methods for assessing human attention under high-temperature conditions. By accurately identifying ambient temperature and integrating fNIRS data, the real-time performance and coverage of the assessment are enhanced, thereby improving the accuracy and reliability of the assessment results. Figure 1 As shown, the method includes:

[0040] S1. Parameter Acquisition:

[0041] Optionally, ambient temperature data can be acquired using a temperature sensor attached to a portable device, while simultaneously collecting near-infrared fNIRS data of the left frontal lobe of the human brain under high-temperature conditions. In this embodiment, "high temperature" can refer to a temperature exceeding a preset value, such as above 30°C; the near-infrared fNIRS data of the left frontal lobe can be detected using devices such as a near-infrared brain imaging system.

[0042] S2. Feature parameter selection:

[0043] S2.1. Based on the ambient temperature data, determine the ambient temperature range where the user is located. Divide the ambient temperature range into three temperature ranges: near-high temperature, high temperature, and extreme high temperature, according to the temperature values ​​from low to high. For example, a temperature greater than or equal to the first preset temperature value T1 and less than the second preset temperature value T2 is considered near-high temperature, denoted as [T1, T2); a temperature greater than or equal to the second preset temperature value T2 and less than the third preset temperature value T3 is considered high temperature, denoted as [T2, T3); a temperature greater than or equal to the third preset temperature value T3 and less than the fourth preset temperature value T4 is considered extreme high temperature, denoted as [T3, T4); the first preset temperature value T1 is less than the second preset temperature value T2, the second preset temperature value T2 is less than the third preset temperature value T3, and the third preset temperature value T3 is less than the fourth preset temperature value T4.

[0044] By dividing the ambient temperature into ranges, and then extracting and filtering features from the near-infrared fNIRS data corresponding to different ambient temperature ranges, it is beneficial to reflect the performance of near-infrared fNIRS data characteristics in different high temperature ranges and solve the problem of assessment impact caused by the large variation in human brain metabolic rate in high temperature ranges.

[0045] S2.2 The raw near-infrared fNIRS data within the above different temperature ranges are preprocessed using the built-in data processor, and feature extraction methods are used to extract features X from the near-infrared fNIRS data, and sensitive features X are selected. n .

[0046] As shown in Table 1, features X include, but are not limited to, eight time-domain indicators (Mean, Std, Skewness, Kurtosis, Peak2Peak, RMS, AUC, Entropy) and four frequency-domain indicators (Spectral Centroid, Spectral Std, Spectral Skewness, Spectral Kurtosis). Since the activation level of the brain varies at different temperatures, the resulting changes in fNIRS signals also vary. Therefore, different high-temperature environments have different effects on different features. Based on the extracted signal features, sensitive features Xn, such as mean and / or standard deviation, are further screened.

[0047] Table 1 Feature Indicators

[0048]

[0049] S3. Set attention evaluation criteria:

[0050] Optionally, different attention intervals can be set to distinguish different levels of attention. The interval [Y', Y'') where the performance value is greater than or equal to the first attention performance value Y' and less than the second attention performance value Y'' is defined as low attention level; the interval [Y'', Y''') where the performance value is greater than or equal to the second attention performance value Y'' and less than the third attention performance value Y''' is defined as medium attention level; and the interval [Y''', Y'''') where the performance value is greater than or equal to the third attention performance value Y''' and less than the fourth attention performance value Y'''' is defined as high attention level. Specifically, the first attention performance value Y' is less than or equal to the second attention performance value Y'', the second attention performance value Y'' is less than or equal to the third attention performance value Y''', and the third attention performance value Y''' is less than or equal to the fourth attention performance value Y''''.

[0051] S4. Attention Evaluation Model and Evaluation:

[0052] An evaluation model is constructed for different high-temperature environments. Different attention evaluation models are established for different temperature ranges to calculate the real-time attention performance value Y. Specifically:

[0053] The attention performance calculation models Y1, Y2, and Y3 for the near-high temperature range [T1, T2), the high temperature range [T2, T3), and the extreme high temperature range [T3, T4] are respectively:

[0054] ;

[0055] ;

[0056] ;

[0057] in, a 1 、b 1 、c 1 、d 1. e 1. a 2 、b 2 、c 2. d 2. , a 3 、b 3 、c 3. d 3 and is a coefficient that can be obtained through experiments; X is characteristic data; t is the exposure time, which can refer to the duration of human exposure to a high-temperature environment; The preset unit time is used to eliminate the dimensions of corresponding terms in the model. Based on the ambient temperature of the household tested in step S1, the ambient temperature range is determined, and calculations are performed according to the corresponding calculation models. The results are then evaluated in conjunction with the evaluation criteria in step S3, and the real-time attention evaluation results are output.

[0058] Within high-temperature environments, different attention performance values ​​are calculated using different models across different temperature ranges. This avoids the impact of significant variations in the human brain's metabolic rate within high-temperature zones, better representing the coupling relationship between blood oxygenation signals and neural activity in the fNIRS, and improving assessment accuracy. Specifically, compared to near-high-temperature ranges, the time effect is greater in high-temperature ranges (the index corresponding to time is 2.2), and the brain is more strongly affected by the environment in extreme high-temperature ranges, with feature changes having a greater impact on attention performance (the index corresponding to the feature is 2.4). By using the index changes of the model corresponding to different temperatures, local features of the data can be captured more flexibly, improving the model's accuracy.

[0059] S5. Real-time display on the user's display terminal:

[0060] Optionally, the display device can be combined with the user terminal to output the user's attention performance in real time via Bluetooth to the display device, such as a mobile phone or tablet, and display the user's real-time attention level using different data levels and colors.

[0061] Based on fNIRS technology, this invention also provides a human attention level evaluation system under high temperature conditions, including a data acquisition and preprocessing module, an attention performance calculation module, a logic judgment module, and a user display module.

[0062] The data acquisition and preprocessing module performs the steps in S1 of the method. Optionally, it acquires the ambient temperature, confirms the temperature range using a temperature sensor, and simultaneously acquires raw fNIRS data from the left frontal lobe in real time and performs preprocessing. Then, it extracts the time-domain and frequency-domain features of the fNIRS data signal, selects sensitive feature indicators based on these features, and matches them with the attention calculation model at the corresponding temperature.

[0063] The attention performance calculation module performs the steps in step S2 of the method. Optionally, it calculates the user's real-time attention performance using a built-in attention calculation model.

[0064] The logic judgment module executes the steps in step S3 of the method. Optionally, the real-time attention level is obtained for judgment.

[0065] The user display module performs the steps in step S4 of the method. Optionally, the aforementioned real-time attention level data will be displayed in real time through the user display module. This display module can be combined with user terminals, such as mobile phones and tablets, to display the user's real-time attention level using different data levels and colors.

[0066] The method and system in this invention can monitor and provide feedback on the user's attention level in real time. Once a decline in attention is detected, measures can be taken immediately, such as adjusting the difficulty of the task or providing other physical stimuli (such as cooling), to prevent a rapid decline in attention.

[0067] Example 1:

[0068] This embodiment provides a method for evaluating human attention levels in high-temperature environments, which evaluates and provides feedback on a user's attention after 30 minutes of exposure to high temperatures at 33°C.

[0069] S1, Synchronously collect ambient temperature T a Based on the user's fNIRS data and the collected parameters, the temperature range was determined (near-high temperature: [30℃, 35℃), high temperature: [35℃, 40℃), extreme high temperature: [40℃, 50℃). In this case, the ambient temperature T was monitored in real time. a The temperature is 33℃, which is considered a near-high temperature environment. The built-in data processing module preprocesses the user's fNIRS data, then extracts the fNIRS data features X1, X2, X3, X4, X5…X… n The features X represent mean, standard deviation, etc., and n is the number of features extracted. The extracted features are then selected using a built-in machine learning model to determine the feature index Xn that is most sensitive to changes under high temperatures.

[0070] S2. Set attention evaluation criteria. This embodiment sets different attention intervals to distinguish different levels of attention: low attention level [0, 0.6), medium attention level [0.6, 1), and high attention level [1, 1.5]. Then, the real-time acquired feature data X or sensitive features Xn are input into the built-in attention performance calculation model Y1 under near-high temperature conditions, while considering the time variable t, according to the binary quadratic attention evaluation model under near-high temperature conditions: ( a 1 ，b 1 ，c 1 ，d 1 and e 1. All results were obtained from experiments, such as a 1 = 1.6 b 1 = -0.00011 c 1 = 0.21 d 1 = -0.002, e 1 = 0.5 In this case, Y1 = 1.6X. 2 -0.00011 2 +0.21X -0.002X +0.5, calculate the user's real-time attention performance Y; in this case, the feature X1 obtained at the 30th minute is 0.5, and the corresponding attention performance Y is calculated to be 0.876 through the model.

[0071] S3. The real-time attention level is assessed, categorized into low, medium, and high levels. Y > Y''' indicates high attention, meaning the user is focused, alert, and attentive; Y''' > Y > Y'' indicates medium attention, suggesting attention is being depleted and showing signs of decline; Y < Y'' indicates low attention, indicating poor attention under high temperatures, requiring timely intervention to prevent accidents. In the example, the obtained attention level is 0.876. According to the judgment logic, 1 > 0.876 > 0.6, placing it in the medium attention level range. The result is then sent to the user's terminal.

[0072] S4. The user's attention level is fed back in real time from the user's device and transmitted to the display screen via Bluetooth, including but not limited to mobile phones, computers, and watches. In the example, the attention performance is 0.876, which is in the medium attention level range. The user needs to be observed or given mild intervention to ensure their safety.

[0073] This embodiment can monitor an individual's attention level in real time under high-temperature conditions, ensuring the individual's work efficiency and safety in high-temperature environments.

[0074] Example 2:

[0075] This embodiment provides a system for evaluating human attention levels under high-temperature conditions, including:

[0076] The data acquisition module is configured to acquire ambient temperature data and near-infrared fNIRS data of the left frontal lobe of the human brain.

[0077] The feature extraction module is configured to: divide the ambient temperature range into multiple temperature ranges according to the temperature values ​​from low to high; extract features from the near-infrared fNIRS data in multiple temperature ranges to obtain feature data for each temperature range;

[0078] The calculation module is configured to: determine the temperature range to which the ambient temperature data belongs, and obtain the attention performance value based on the feature data within the corresponding temperature range and the preset attention performance value calculation model within the corresponding temperature range; wherein, the attention performance value calculation model is a polynomial including feature data, exposure time and corresponding coefficients;

[0079] The evaluation module is configured to evaluate based on attention performance scores.

[0080] The working method of the system is the same as that of the present invention and the method for evaluating human attention level under high temperature environment in Embodiment 1, and will not be repeated here.

[0081] Example 3:

[0082] This embodiment provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the human attention level evaluation method under high temperature conditions described in Embodiment 1.

[0083] Example 4:

[0084] This embodiment provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor. When the processor executes the program, it implements the steps of the human attention level evaluation method under high temperature environment described in Embodiment 1.

[0085] Example 5:

[0086] This embodiment provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the steps of the method for evaluating human attention level under high temperature environment as described in Embodiment 1.

[0087] The above description is merely a preferred embodiment of this practice and is not intended to limit the scope of this practice. Various modifications and variations can be made to this practice by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this practice should be included within the protection scope of this practice.

Claims

1. A method for evaluating human attention levels under high-temperature conditions, characterized in that, include: Acquire ambient temperature data and near-infrared fNIRS data of the left frontal lobe of the human brain; The ambient temperature range was divided into multiple temperature ranges according to the order of temperature values ​​from low to high; feature extraction was performed on the near-infrared fNIRS data in multiple temperature ranges to obtain the feature data of each temperature range. The temperature range to which the ambient temperature data belongs is determined. Based on the characteristic data within the corresponding temperature range and the preset attention performance value calculation model within the corresponding temperature range, the attention performance value is obtained. The attention performance value calculation model is a polynomial that includes characteristic data, exposure time, and corresponding coefficients. Evaluation is based on attention performance scores.

2. The method for evaluating human attention levels under high-temperature conditions as described in claim 1, characterized in that, The ambient temperature range is divided into several temperature ranges, including: a temperature greater than or equal to a first preset temperature value and less than a second preset temperature value is considered near-high temperature; a temperature greater than or equal to a second preset temperature value and less than a third preset temperature value is considered high temperature; a temperature greater than or equal to a third preset temperature value and less than a fourth preset temperature value is considered extreme high temperature; the first preset temperature value is less than the second preset temperature value, the second preset temperature value is less than the third preset temperature value, and the third preset temperature value is less than the fourth preset temperature value.

3. The method for evaluating human attention levels under high-temperature conditions as described in claim 2, characterized in that, When performing feature extraction, the extracted features include time-domain indicators and frequency-domain indicators.

4. The method for evaluating human attention levels under high-temperature conditions as described in claim 3, characterized in that, The time-domain metrics include mean, standard deviation, skewness, kurtosis, peak-to-peak value, root mean square value, entropy, and area under curve; the frequency-domain metrics include spectral centroid, spectral standard deviation, spectral skewness, and spectral kurtosis.

5. The method for evaluating human attention levels under high-temperature conditions as described in claim 4, characterized in that, The calculation models for attention performance values ​​in the near-high temperature range, the high temperature range, and the extreme high temperature range are as follows: ； ； ； in, a 1 、b 1 、c 1 、d 1. e 1. a 2 、b 2 、c 2. d 2. , a 3 、b 3 、c 3. d 3 and X represents the coefficient; X represents the feature data; t represents the exposure time. This is a preset unit of time.

6. The method for evaluating human attention levels under high-temperature conditions as described in claim 1, characterized in that, The attention performance value is considered low if it is greater than or equal to the first attention performance value and less than the second attention performance value; the attention performance value is considered medium if it is greater than or equal to the second attention performance value and less than the third attention performance value; and the attention performance value is considered high if it is greater than or equal to the third attention performance value and less than the fourth attention performance value. Wherein, the first attention performance value is less than or equal to the second attention performance value, the second attention performance value is less than or equal to the third attention performance value, and the third attention performance value is less than or equal to the fourth attention performance value.

7. A system for evaluating human attention levels under high-temperature conditions, characterized in that, include: The data acquisition module is configured to acquire ambient temperature data and near-infrared fNIRS data of the left frontal lobe of the human brain. The feature extraction module is configured to: divide the ambient temperature range into multiple temperature ranges according to the temperature values ​​from low to high; extract features from the near-infrared fNIRS data in multiple temperature ranges to obtain feature data for each temperature range; The calculation module is configured to: determine the temperature range to which the ambient temperature data belongs, and obtain the attention performance value based on the feature data within the corresponding temperature range and the preset attention performance value calculation model within the corresponding temperature range; wherein, the attention performance value calculation model is a polynomial including feature data, exposure time and corresponding coefficients; The evaluation module is configured to evaluate based on attention performance scores.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method for evaluating human attention levels under high temperature conditions as described in any one of claims 1-6.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, When the processor executes the program, it implements the steps of the method for evaluating human attention levels under high temperature conditions as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the steps of the method for evaluating human attention levels under high-temperature conditions as described in any one of claims 1-6.

Images