Fatigue driving warning method and related device

Abstract

The application discloses a fatigue driving early warning method and related equipment, and relates to the technical field of intelligent driving. The method comprises the following steps: acquiring driving time sequence information in a first preset time period, wherein the first preset time period is a preset time period before the current time; performing time sequence prediction based on the driving time sequence information to obtain at least one fatigue driving information in a second preset time period, wherein the second preset time period is a preset time period after the current time, the fatigue driving information comprises a fatigue score and a score time point corresponding to the fatigue score; determining a fatigue driving early warning level based on the fatigue score and the score time point and performing early warning. The application can effectively improve the safety of road driving.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and more specifically, to a fatigue driving warning method and related equipment. Background Technology

[0002] Fatigue driving is a major cause of traffic accidents. According to statistics from recent years, the number of road traffic accidents directly caused by fatigue driving each year is enormous, resulting in numerous casualties and property damage. Accidents involving commercial vehicles, in particular, often result in severe injuries and significant losses.

[0003] While fatigue driving warning methods in related technologies can monitor driver fatigue to some extent and issue warnings when signs of fatigue are detected, they still have limitations in providing timely early warnings. This is mainly because many methods rely on intervention only after the driver has already exhibited obvious fatigue behavior or changes in physiological indicators, failing to adequately capture and predict early signs of fatigue, thus potentially missing the optimal intervention window. In other words, these technologies suffer from poor road safety. Summary of the Invention

[0004] The summary section of this application introduces a series of simplified concepts, which will be further explained in detail in the detailed description section. The summary section of this application is not intended to limit the key features and essential technical features of the claimed technical solution, nor is it intended to determine the scope of protection of the claimed technical solution.

[0005] The fatigue driving warning method and related device provided in this application can effectively improve road driving safety.

[0006] In a first aspect, this application provides a fatigue driving warning method, the method comprising: acquiring driving time sequence information within a first preset time period, wherein the first preset time period is a preset time period prior to the current moment; performing time sequence prediction based on the driving time sequence information to obtain at least one fatigue driving information within a second preset time period, wherein the second preset time period is a preset time period after the current moment, the fatigue driving information including a fatigue score and a scoring time point corresponding to the fatigue score; and determining a fatigue driving warning level and issuing a warning based on the fatigue score and the scoring time point.

[0007] In one feasible implementation, the driving time-series information includes time-series features, as well as physiological state sequence features and in-vehicle environment sequence features corresponding to the time-series features; the step of performing time-series prediction based on the driving time-series information to obtain at least one fatigue driving information within a second preset time period includes: concatenating the time-series features, the physiological state sequence features, and the in-vehicle environment sequence features to obtain fused time-series features; inputting the fused time-series features into a fatigue time-series prediction model to obtain a prediction output vector; and extracting and processing the prediction output vector based on the second preset time period to obtain the fatigue driving information.

[0008] In one feasible implementation, determining the fatigue driving warning level and issuing a warning based on the fatigue score and the scoring time point includes: calculating a comprehensive time-period score corresponding to the fatigue driving information based on the fatigue score and the scoring time point, wherein the comprehensive time-period score is positively correlated with the fatigue score and negatively correlated with the time elapsed between the scoring time point and the current time; and determining the fatigue driving warning level and issuing a warning based on the comprehensive time-period score.

[0009] In one feasible implementation, calculating the comprehensive score for the time period corresponding to the fatigue driving information based on the fatigue score and the scoring time point includes: substituting the fatigue score and the scoring time point into a comprehensive scoring formula to calculate the comprehensive score for the time period, wherein the comprehensive scoring formula is: In the formula, Y is the comprehensive score for the time period, y i For the i-th fatigue score within the second preset time period, t i t0 is the i-th scoring time point within the second preset time period, t0 is the current time point, and n is the total number of fatigue driving information within the second preset time period.

[0010] In one feasible implementation, determining the fatigue driving warning level and issuing a warning based on the comprehensive score for the time period includes: correcting the comprehensive score for the time period based on historical driving duration data and current driving duration data to obtain a corrected score for the time period; and determining the fatigue driving warning level and issuing a warning based on the corrected score for the time period.

[0011] In one feasible implementation, determining the fatigue driving warning level and issuing a warning based on the comprehensive score of the time period includes: when the comprehensive score of the time period is greater than or equal to a first scoring threshold and less than a second scoring threshold, adjusting the in-vehicle environment through an in-vehicle environment adjustment device to reduce the comprehensive score of the time period calculated at the next time point; when the comprehensive score of the time period is greater than or equal to the second scoring threshold, determining the fatigue driving warning level and issuing a warning based on the comprehensive score of the time period.

[0012] In one feasible implementation, the fatigue driving warning level includes a mild fatigue level, a moderate fatigue level, and a severe fatigue level. The step of determining the fatigue driving warning level and issuing a warning based on the comprehensive score of the time period when it is greater than or equal to the second scoring threshold includes: when the comprehensive score of the time period is greater than or equal to the second scoring threshold, and the fatigue driving warning level is determined to be mild fatigue based on the comprehensive score of the time period, displaying a warning reminder message on the vehicle's display screen; when the comprehensive score of the time period is greater than or equal to the second scoring threshold, and the fatigue driving warning level is determined to be moderate fatigue based on the comprehensive score of the time period, broadcasting a warning reminder message through the vehicle's loudspeaker; and when the comprehensive score of the time period is greater than or equal to the second scoring threshold, and the fatigue driving warning level is determined to be severe fatigue based on the comprehensive score of the time period, planning the vehicle's route destination as a nearby parking lot through the vehicle's navigation device.

[0013] Secondly, this application also provides a fatigue driving warning device, comprising: an acquisition unit for acquiring driving time sequence information within a first preset time period, wherein the first preset time period is a time period before the current time; a prediction unit for performing time sequence prediction based on the driving time sequence information to obtain at least one fatigue driving information within a second preset time period, wherein the second preset time period is a time period after the current time, and the fatigue driving information includes a fatigue score and a score time point corresponding to the fatigue score; and a warning unit for determining a fatigue driving warning level and issuing a warning based on the fatigue score and the score time point.

[0014] Thirdly, this application also provides an electronic device, including: a memory and a processor, wherein the processor is configured to implement the fatigue driving warning method described in the first aspect when executing a computer program stored in the memory.

[0015] Fourthly, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the fatigue driving warning method described in the first aspect.

[0016] Fifthly, this application also provides a computer program product, including a computer program or computer-executable instructions, which, when executed by a processor, implement the fatigue driving warning method provided in the embodiments of this application.

[0017] In summary, this application acquires and analyzes driving time sequence information within a certain period prior to the current moment (a first preset period) to predict fatigue driving conditions in the future (a second preset period). This forward-looking predictive capability allows the system to issue warnings before the driver actually enters a fatigue state, thereby effectively preventing traffic accidents caused by fatigue driving. It significantly improves drivers' driving safety awareness and prompts them to take timely measures to alleviate fatigue when they feel it, thus effectively enhancing road safety. In conclusion, the fatigue driving warning method provided by this application can effectively improve road safety. Attached Figure Description

[0018] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit this specification. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0019] Figure 1 A flowchart illustrating a fatigue driving warning method provided in an embodiment of this application;

[0020] Figure 2 This is a schematic diagram of the composition structure of a fatigue driving warning device provided in an embodiment of this application;

[0021] Figure 3 This is a schematic diagram of the composition structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0022] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and not to describe a particular order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms “is” and “has,” and any variations thereof, used in this application are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] In this application, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented, wholly or partially, using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of a larger module or unit that includes the functionality of that module or unit.

[0024] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. In the following description, "some embodiments" are referred to, which describes a subset of all possible embodiments. However, it is understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0025] See Figure 1 , Figure 1 This is a flowchart illustrating a fatigue driving warning method provided in an embodiment of this application. The method may specifically include the following steps 101 to 103:

[0026] Step 101: Obtain driving time sequence information within a first preset time period, wherein the first preset time period is a preset time period prior to the current moment;

[0027] Specifically, the first preset time period is a designated, fixed-length time frame used to collect data from the driver's driving activities. It represents a time window looking back from the current moment to the past, used to analyze the driver's driving patterns. First, the specific length of the first preset time period can be determined according to preset rules or user settings, such as the most recent one hour, two hours, or a longer period, or a period with driving records within the most recent month, six months, or longer. Subsequently, relevant data is collected in real time or periodically from vehicle sensors, driver monitoring devices (such as cameras and physiological monitoring devices), and in-vehicle environmental sensors. Finally, the collected data is organized into a driving time-series information format, including but not limited to vehicle driving status (speed, acceleration, steering, etc.), driver physiological status (heart rate, blink rate, facial expression, etc.), and in-vehicle environmental status (temperature, humidity, noise level, etc.).

[0028] For example, assuming the first preset time period is set to the most recent hour, data can be collected and processed from the following aspects: For vehicle driving status, information such as vehicle speed, acceleration, and braking / accelerator operation frequency can be obtained through the vehicle's CAN bus interface. This data can reflect the driver's driving behavior and the vehicle's dynamic state; For driver's physiological state, the driver's blinking frequency, facial expression, head posture, etc. can be monitored using in-vehicle cameras combined with facial recognition technology and biometric algorithms to assess their fatigue level. Wearable devices (such as smartwatches) can also be used to monitor the driver's heart rate, blood oxygen saturation, and other physiological indicators; For the in-vehicle environment, real-time data on the in-vehicle environment can be obtained through in-vehicle temperature sensors, humidity sensors, and noise monitoring equipment. This data helps to understand the impact of the in-vehicle environment on the driver's fatigue state.

[0029] By implementing step 101, historical data on driver behavior patterns, physiological states, and environmental conditions can be obtained, providing necessary data support for subsequent steps. This ensures that the prediction model has a sufficiently rich source of information, thereby improving the accuracy and reliability of the prediction.

[0030] Step 102: Perform time-series prediction based on driving time-series information to obtain at least one fatigue driving information within a second preset time period, wherein the second preset time period is a preset time period after the current time, and the fatigue driving information includes a fatigue score and a score time point corresponding to the fatigue score.

[0031] Specifically, the second preset time period refers to a future time window after the current moment, used to predict driver fatigue. Similar to the first preset time period, the second preset time period is also pre-set, and its length depends on various factors, including prediction needs, driving environment, and driver habits. The second preset time period is set to provide sufficient time for early warning before signs of driver fatigue appear. Fatigue driving information refers to a series of data related to driver fatigue state obtained through time-series prediction, used to assess the degree of fatigue that may occur or worsen within the second preset time period. Fatigue driving information includes a quantitative assessment result of the driver's fatigue level (fatigue score) and the specific time point corresponding to the fatigue score (score time point). In the specific implementation of step 102, firstly, the collected driving time-series information can be preprocessed, including but not limited to data cleaning, outlier removal, and feature extraction, to ensure the quality and relevance of the input data; then, a suitable time-series prediction model is selected or trained. These models can be based on statistics (such as the ARIMA model), machine learning (such as random forests and support vector machines), or deep learning (such as LSTM, GRU, and other recurrent neural networks); then, historical driving time-series information is used as training data to train the selected model, enabling it to learn the complex relationship between driving behavior and fatigue state; finally, the latest driving time-series information is input into the trained model to perform time-series prediction, obtaining fatigue driving information within the second preset time period, including fatigue scores and corresponding score time points.

[0032] By implementing step 102 and analyzing historical driving data, it is possible to predict future fatigue levels before the driver exhibits obvious fatigue symptoms, thereby issuing early warnings and improving the timeliness of the warnings.

[0033] Step 103: Based on the fatigue score and the score time point, determine the fatigue driving warning level and issue a warning;

[0034] Specifically, the fatigue driving warning level refers to classifying the predicted fatigue score into different levels according to certain standards, with each level representing a different severity of driver fatigue. In the specific implementation of step 102, firstly, fatigue driving warnings can be divided into different levels, such as low fatigue, moderate fatigue, and high fatigue, based on the range of the fatigue score and preset thresholds. Each level corresponds to a different level of risk and the preventative measures required. Next, the scoring time points are analyzed, especially those approaching or exceeding the warning threshold, to determine the urgency and importance of the warning. Then, based on the warning level and scoring time points, specific warning strategies are formulated. These strategies may include audible alarms, visual cues (such as warning lights or information displays on the dashboard), seat vibration, automatic adjustment of the in-vehicle environment (such as lowering the temperature or playing refreshing music), and possible vehicle control interventions (such as speed limits or automatic takeover). Finally, based on the formulated warning strategies, a warning is issued to the driver at an appropriate time, and additional safety measures may be taken to protect the safety of the driver and the vehicle.

[0035] By implementing step 103, the warning level is determined based on the fatigue score and time point, enabling the warning system to take corresponding measures according to different fatigue levels, avoiding a "one-size-fits-all" warning approach. Through timely and effective warnings, the risk of traffic accidents caused by fatigued driving is reduced, and the overall safety of road traffic is improved.

[0036] In summary, this application embodiment acquires and analyzes driving time sequence information within a certain time period (first preset time period) before the current moment, and then predicts fatigue driving conditions in the future period (second preset time period). This forward-looking predictive capability enables the system to issue a warning before the driver actually enters a fatigue state, thereby effectively preventing traffic accidents caused by fatigue driving. It can significantly improve the driver's driving safety awareness and prompt the driver to take timely measures to alleviate fatigue when feeling fatigued, thus effectively improving road driving safety. In conclusion, the fatigue driving warning method provided by this application embodiment can effectively improve road driving safety.

[0037] In some embodiments, the aforementioned driving time-series information may include time-series features, as well as physiological state sequence features and in-vehicle environment sequence features corresponding to the time-series features; step 102 may include: concatenating the time-series features, physiological state sequence features and in-vehicle environment sequence features to obtain fused time-series features; inputting the fused time-series features into a fatigue time-series prediction model to obtain a prediction output vector; and extracting and processing the prediction output vector based on a second preset time period to obtain fatigue driving information.

[0038] Specifically, time-series features are a series of data points arranged chronologically during the driving process. Physiological state series features refer to a series of data points related to the driver's physiological state, changing over time and reflecting the driver's health and fatigue level; these features may include heart rate changes (reflecting the driver's level of tension or fatigue), eye state (such as blinking frequency and eye-closing time), and breathing patterns (breathing frequency and depth). In-vehicle environment series features refer to a series of data points showing changes in the in-vehicle environment over time, potentially affecting the driver's comfort and fatigue level; these features may include in-vehicle temperature (temperature changes may affect driver comfort and alertness), lighting conditions (brightness and color of in-vehicle lighting may affect the driver's mood and visual fatigue), and noise levels (intensity and type of in-vehicle noise may affect the driver's attention and fatigue level). In the specific implementation process, firstly, the collected time-series features, physiological state sequence features, and in-vehicle environment sequence features are processed by feature concatenation, integrating information from different dimensions into a unified feature space so that the subsequent model can comprehensively consider the impact of various factors on the driver's fatigue state. Subsequently, the concatenated fused time-series features are used as input and passed to the pre-trained fatigue time-series prediction model. This model is built based on deep learning or other machine learning algorithms and can learn and understand the complex relationship between input features and fatigue driving state, thereby outputting the corresponding prediction results. Finally, according to the second preset time period (usually a specific time period, such as the next 10 minutes, 30 minutes, 1 hour, etc.), fatigue driving information related to this time period is extracted from the prediction output vector, which may include fatigue level, warning signals, etc., to remind the driver or vehicle system to take appropriate safety measures in real time.

[0039] By implementing the above embodiments, combining time series features, physiological state series features, and in-vehicle environment series features, and obtaining fused time series features through feature splicing, the accuracy and comprehensiveness of fatigue prediction are improved. This comprehensive application of multi-source data can more comprehensively capture changes in the driver's fatigue state and provide richer input information for the prediction model.

[0040] In some embodiments, step 103 may include: calculating a comprehensive time-period score corresponding to the fatigue driving information based on the fatigue score and the scoring time point, wherein the comprehensive time-period score is positively correlated with the fatigue score and negatively correlated with the time elapsed between the scoring time point and the current time; and determining the fatigue driving warning level and issuing a warning based on the comprehensive time-period score.

[0041] Specifically, firstly, based on the obtained fatigue score and the corresponding time point (i.e., the scoring time point), the system executes a comprehensive scoring algorithm. This algorithm aims to calculate the comprehensive time-period score corresponding to the currently considered fatigue driving information. In this process, the comprehensive time-period score is positively correlated with the fatigue score, that is, the higher the fatigue score, the higher the comprehensive time-period score. At the same time, the comprehensive time-period score is also negatively correlated with the time distance between the scoring time point and the current time, that is, the closer the scoring time point is to the current time, the greater its influence weight, and vice versa. Next, based on the calculated comprehensive time-period score, it is compared with a preset warning level threshold to determine the current fatigue driving warning level. Warning levels are usually divided into multiple levels, such as low, medium, high, or emergency, each level corresponding to different warning measures and response strategies. Once the warning level is determined, the system will trigger the corresponding warning mechanism, such as reminding the driver of the risk of fatigue driving through sound, light, vibration, or display screen information, and may simultaneously activate other safety measures, such as automatic deceleration, maintaining a safe distance, or preparing to take over vehicle control.

[0042] By implementing the above embodiments, a comprehensive time-based scoring system is introduced, taking into account both the fatigue score and the distance between the scoring time points. This makes the early warning more reasonable and timely, and more accurately reflects the changing trend of the driver's fatigue level over a future period, providing a scientific basis for determining the early warning level.

[0043] In some embodiments, calculating a comprehensive time-period score corresponding to fatigue driving information based on the fatigue score and the scoring time point may include: substituting the fatigue score and the scoring time point into a comprehensive scoring formula to calculate the comprehensive time-period score, wherein the comprehensive scoring formula is:

[0044]

[0045] In the formula, Y represents the comprehensive score for the time period, y i For the i-th fatigue score within the second preset time period, t i t0 is the i-th scoring time point within the second preset time period, t0 is the current time point, and n is the total number of fatigue driving information within the second preset time period.

[0046] Specifically, first, the ratio of the maximum fatigue score to the time factor is calculated. The maximum value among the ratios of all fatigue scores within the second preset time period to the square root of the difference between their respective score times and the current time is taken. This ratio considers both the severity of the fatigue score and its proximity to the current time; the more severe the score and the closer the time, the larger the ratio. Next, the average fatigue score is calculated, which is the average of all fatigue scores within the second preset time period, reflecting the driver's average fatigue level throughout the entire period. Finally, the results of these two parts are multiplied to obtain the comprehensive time period score. This comprehensive time period score considers both the severity of fatigue and the time factor, enabling the warning system to more accurately determine when and how to issue a warning. The square root and the reciprocal of the time difference in the formula ensure that more recent prediction times have a greater impact on the comprehensive score, thus making the warning more timely and effective.

[0047] Through the implementation of the above embodiments, a specific comprehensive scoring formula is proposed. This formula takes into account both the absolute value of the fatigue score and the distance between the scoring time point and the current time. The comprehensive score for the time period can be accurately calculated using this formula, ensuring the fairness and accuracy of the scoring.

[0048] In some embodiments, the aforementioned determination of the fatigue driving warning level and issuance of a warning based on a comprehensive time-period score may include: correcting the comprehensive time-period score based on historical driving duration data and current driving duration data to obtain a corrected time-period score; and determining the fatigue driving warning level and issuing a warning based on the corrected time-period score.

[0049] Specifically, historical driving time data and current driving time data can be considered to optimize the initially calculated comprehensive score for each time period, in order to eliminate or reduce the influence of certain factors, such as individual differences in drivers, driving habits, or fatigue patterns under specific driving conditions. In practice, this involves analyzing the driver's historical driving behavior to understand their fatigue tendencies and driving habits; considering the current driving time to determine if the driver has already been driving for an extended period, which may increase the risk of fatigue; and adjusting the original comprehensive score for each time period based on this data to better reflect the driver's actual fatigue state.

[0050] For example, suppose driver A has more than 10 long-distance driving records in the past month and does not have enough rest time between two drives. Based on this historical data, driver A is considered to be prone to fatigue. During the current driving process, if the system detects that driver A has been driving continuously for 3 hours, then even if the initial comprehensive score for the time period is low, the score will be adjusted upward based on the historical data.

[0051] By implementing the above embodiments, historical driving time data and current driving time data are introduced to correct the comprehensive score for the time period, making the warning more consistent with the actual situation of the driver. This personalized correction can more accurately reflect the driver's fatigue state and improve the pertinence and effectiveness of the warning.

[0052] In some embodiments, the aforementioned determination of the fatigue driving warning level and issuance of a warning based on the comprehensive score of the time period may further include: when the comprehensive score of the time period is greater than or equal to a first scoring threshold and less than a second scoring threshold, adjusting the in-vehicle environment through an in-vehicle environment adjustment device to reduce the comprehensive score of the time period calculated at the next time point; when the comprehensive score of the time period is greater than or equal to the second scoring threshold, determining the fatigue driving warning level and issuing a warning based on the comprehensive score of the time period.

[0053] Specifically, the first scoring threshold is a pre-set score used to determine whether the driver's fatigue level warrants intervention. When the calculated overall score for the time period is greater than or equal to this threshold, it indicates that the driver's fatigue level has reached a concern level but not yet warrants an immediate warning. The first scoring threshold can be set based on the driver's safety margin and the system's intervention timing. The second scoring threshold is another pre-set score, higher than the first, used to determine whether the driver's fatigue level is severe enough to warrant a warning. When the overall score for the time period is greater than or equal to the second scoring threshold, it indicates that the driver's fatigue level is very severe. This score can be used to determine the fatigue driving warning level and take corresponding warning measures. The second scoring threshold can be set based on the necessity and urgency of the warning. In the specific implementation process, firstly, the overall score for the time period can be compared with two preset scoring thresholds (the first scoring threshold and the second scoring threshold). If the overall score for the time period is greater than or equal to the first scoring threshold but less than the second scoring threshold, it indicates that the driver may be in a state of mild or moderate fatigue, but has not yet reached the level of emergency warning. At this time, the in-vehicle environment can be fine-tuned by controlling the in-vehicle environment adjustment devices (such as air conditioning, audio, seat heating or ventilation, etc.) to create a more comfortable driving environment that helps alleviate fatigue, thereby hoping to reduce the overall score for the time period calculated at the next time point. However, if the overall score for the time period is greater than or equal to the second scoring threshold, it indicates that the driver is already in a state of high fatigue and there is a significant driving safety risk. In this case, the fatigue driving warning level can be determined immediately based on the current overall score for the time period according to the preset algorithm or rules, and the corresponding warning mechanism can be triggered. These warning mechanisms may include, but are not limited to, audible alarms, visual cues, vibration feedback, sending emergency rest suggestions to the driver, or automatically taking over vehicle control, to ensure that the driver can be aware of the risk of fatigue driving in a timely manner and take appropriate safety measures.

[0054] By implementing the above embodiments, different intelligent intervention measures can be taken according to different ranges of comprehensive scores over different time periods, which can provide effective help and support to drivers at different stages. This graded intervention strategy can effectively prevent drivers from becoming overly fatigued, while also reducing unnecessary alarms that may cause interference to drivers.

[0055] In some embodiments, the aforementioned fatigue driving warning levels include mild fatigue, moderate fatigue, and severe fatigue. When the comprehensive score for a given time period is greater than or equal to a second scoring threshold, determining the fatigue driving warning level and issuing a warning based on the comprehensive score for that time period includes: when the comprehensive score for a given time period is greater than or equal to the second scoring threshold, and the fatigue driving warning level is determined to be mild fatigue based on the comprehensive score for that time period, displaying a warning reminder message on the vehicle's display screen; when the comprehensive score for a given time period is greater than or equal to the second scoring threshold, and the fatigue driving warning level is determined to be moderate fatigue based on the comprehensive score for that time period, broadcasting a warning reminder message through the vehicle's loudspeaker; when the comprehensive score for a given time period is greater than or equal to the second scoring threshold, and the fatigue driving warning level is determined to be severe fatigue based on the comprehensive score for that time period, planning the vehicle's route destination as a nearby parking lot through the vehicle's navigation device.

[0056] Specifically, firstly, the system compares the overall score over a given time period with a preset scoring threshold. In particular, when the score is greater than or equal to a second scoring threshold, the system can further determine the fatigue driving warning level. These warning levels include, but are not limited to, mild fatigue, moderate fatigue, and severe fatigue. Subsequently, corresponding warning measures can be implemented based on the determined warning level. Specifically, if the overall score over a given time period is greater than or equal to the second scoring threshold, and the warning level determined by the score is mild fatigue, the system will display a warning reminder on the in-vehicle display screen, appearing in the form of text, icons, or animation. This aims to gently remind the driver of fatigue and suggest appropriate rest measures. If the warning level is moderate fatigue, the system will broadcast a warning reminder through the in-vehicle loudspeaker. This audible warning is more direct and harder to ignore, helping to quickly attract the driver's attention and emphasizing the severity of the current fatigue driving risk. When the warning level reaches severe fatigue, more aggressive measures can be taken to ensure driving safety. The system may automatically plan a route through the in-vehicle navigation device, changing the vehicle's destination to a nearby parking lot, aiming to immediately relieve the driver from driving and guide them to a safe area for sufficient rest.

[0057] Through the implementation of the above embodiments, different levels of warning measures are taken for different levels of fatigue driving warnings; from mild warning reminders to moderate broadcast warnings and severe planned parking routes, this multi-level warning mechanism can ensure that drivers can receive timely and effective reminders and assistance in different fatigue states, thereby further improving driving safety.

[0058] Furthermore, as an implementation of the aforementioned method embodiments, this application also provides a fatigue driving warning device for implementing the aforementioned method embodiments. This device embodiment corresponds to the aforementioned method embodiments. For ease of reading, this fatigue driving warning device embodiment will not repeat the details of the aforementioned method embodiments one by one, but it should be understood that the device in this application embodiment can correspondingly implement all the contents of the aforementioned method embodiments. For example... Figure 2 As shown, the fatigue driving warning device 20 includes: an acquisition unit 201, a prediction unit 202, and a warning unit 203. The acquisition unit 201 is used to acquire driving time sequence information within a first preset time period, wherein the first preset time period is the time period before the current time. The prediction unit 202 is used to perform time sequence prediction based on the driving time sequence information to obtain at least one fatigue driving information within a second preset time period, wherein the second preset time period is the time period after the current time. The fatigue driving information includes a fatigue score and a score time point corresponding to the fatigue score. The warning unit 203 is used to determine the fatigue driving warning level and issue a warning based on the fatigue score and the score time point.

[0059] In some embodiments, the driving time-series information includes time-series features, as well as physiological state sequence features and in-vehicle environment sequence features corresponding to the time-series features; the prediction unit 202 is further configured to perform feature concatenation on the time-series features, physiological state sequence features and in-vehicle environment sequence features to obtain fused time-series features; input the fused time-series features into the fatigue time-series prediction model to obtain a prediction output vector; and extract and process the prediction output vector based on a second preset time period to obtain fatigue driving information.

[0060] In some embodiments, the warning unit 203 is further configured to calculate a comprehensive time-period score corresponding to the fatigue driving information based on the fatigue score and the scoring time point, wherein the comprehensive time-period score is positively correlated with the fatigue score and negatively correlated with the time distance between the scoring time point and the current time; and to determine the fatigue driving warning level and issue a warning based on the comprehensive time-period score.

[0061] In some embodiments, the early warning unit 203 is further configured to substitute the fatigue score and the score time point into the comprehensive scoring formula to calculate the comprehensive score for the time period, wherein the comprehensive scoring formula is: In the formula, Y represents the comprehensive score for the time period, y iFor the i-th fatigue score within the second preset time period, t i t0 is the i-th scoring time point within the second preset time period, t0 is the current time point, and n is the total number of fatigue driving information within the second preset time period.

[0062] In some embodiments, the warning unit 203 is further configured to correct the comprehensive score of the time period based on historical driving time data and current driving time data to obtain a time period correction score; and to determine the fatigue driving warning level and issue a warning based on the time period correction score.

[0063] In some embodiments, the warning unit 203 is further configured to adjust the in-vehicle environment through an in-vehicle environment adjustment device when the comprehensive score of the time period is greater than or equal to the first score threshold and less than the second score threshold, so as to reduce the comprehensive score of the time period calculated at the next time point; when the comprehensive score of the time period is greater than or equal to the second score threshold, determine the fatigue driving warning level based on the comprehensive score of the time period and issue a warning.

[0064] In some embodiments, the fatigue driving warning levels include a slight fatigue level, a moderate fatigue level, and a severe fatigue level. The warning unit 203 is further configured to display a warning reminder message on the vehicle display screen when the comprehensive score for the time period is greater than or equal to a second scoring threshold and the fatigue driving warning level is determined to be a slight fatigue level based on the comprehensive score for the time period; to broadcast a warning reminder message through the vehicle loudspeaker when the comprehensive score for the time period is greater than or equal to the second scoring threshold and the fatigue driving warning level is determined to be a moderate fatigue level based on the comprehensive score for the time period; and to plan the vehicle's route destination as a nearby parking lot through the vehicle navigation device when the comprehensive score for the time period is greater than or equal to the second scoring threshold and the fatigue driving warning level is determined to be a severe fatigue level based on the comprehensive score for the time period.

[0065] This application also provides a computer-readable storage medium storing computer-executable instructions or computer programs, which, when executed by a processor, will cause the processor to perform any step of the fatigue driving warning method provided in this application.

[0066] In some embodiments, the computer-readable storage medium may be a memory such as RAM, read-only memory (ROM), flash memory, magnetic surface memory, optical disc, or compact disc read-only memory (CD-ROM); or it may be a variety of devices including one or any combination of the above-mentioned memories.

[0067] In some embodiments, computer-executable instructions may take the form of programs, software, software modules, scripts, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as stand-alone programs or as modules, components, subroutines, or other units suitable for use in a computing environment.

[0068] In some embodiments, computer-executable instructions may, but do not necessarily, correspond to files in a file system, and may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a HyperText Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple co-located files (e.g., files that store one or more modules, subroutines, or code sections).

[0069] In some embodiments, computer-executable instructions may be deployed to execute on an electronic device, or on multiple electronic devices located at one location, or on multiple electronic devices distributed across multiple locations and interconnected via a communication network.

[0070] like Figure 3 As shown, this application also provides an electronic device 30, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor. When the processor 320 executes the computer program 311, it implements any step of the above-mentioned fatigue driving warning method.

[0071] This application also provides a computer program product comprising a computer program or computer-executable instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer program or computer-executable instructions from the computer-readable storage medium and executes the computer program or computer-executable instructions, causing the electronic device to perform any step of the fatigue driving warning method described above.

[0072] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A fatigue driving warning method, characterized in that, include: Obtain driving time sequence information within a first preset time period, wherein the first preset time period is a preset time period prior to the current moment; Based on the driving time sequence information, time sequence prediction is performed to obtain at least one fatigue driving information within a second preset time period, wherein the second preset time period is a preset time period after the current moment, and the fatigue driving information includes a fatigue score and a score time point corresponding to the fatigue score. Substituting the fatigue score and the scoring time point into the comprehensive scoring formula, a comprehensive time-segment score is calculated. The comprehensive time-segment score is positively correlated with the fatigue score and negatively correlated with the time elapsed between the scoring time point and the current time. The comprehensive scoring formula is as follows: In the formula, The overall score for the aforementioned time period is as follows: For the second preset time period The fatigue score mentioned above This refers to the i-th scoring time point within the second preset time period. The current time point, This represents the total number of fatigue driving information entries within the second preset time period. Based on the comprehensive score for the aforementioned time period, a fatigue driving warning level is determined and a warning is issued.

2. The fatigue driving warning method according to claim 1, characterized in that, The driving time sequence information includes time sequence features, as well as physiological state sequence features and in-vehicle environment sequence features corresponding to the time sequence features; The step of performing time-series prediction based on the driving time-series information to obtain at least one fatigue driving information within a second preset time period includes: The time series features, the physiological state sequence features, and the in-vehicle environment sequence features are concatenated to obtain fused time series features; The fused temporal features are input into the fatigue temporal prediction model to obtain the prediction output vector; The fatigue driving information is obtained by extracting and processing the predicted output vector based on the second preset time period.

3. The fatigue driving warning method according to claim 1, characterized in that, The process of determining the fatigue driving warning level and issuing a warning based on the comprehensive score over the time period includes: Based on historical driving time data and current driving time data, the comprehensive score for the time period is corrected to obtain the time period corrected score; Based on the time period correction score, the fatigue driving warning level is determined and a warning is issued.

4. The fatigue driving warning method according to claim 1, characterized in that, The process of determining the fatigue driving warning level and issuing a warning based on the comprehensive score over the time period includes: When the comprehensive score for the time period is greater than or equal to the first score threshold and less than the second score threshold, the in-vehicle environment is adjusted by the in-vehicle environment adjustment device so that the comprehensive score for the time period calculated at the next time point is reduced. When the comprehensive score for the time period is greater than or equal to the second score threshold, the fatigue driving warning level is determined and a warning is issued based on the comprehensive score for the time period.

5. The fatigue driving warning method according to claim 4, characterized in that, The fatigue driving warning levels include mild fatigue level, moderate fatigue level, and severe fatigue level; When the comprehensive score for the time period is greater than or equal to the second score threshold, the fatigue driving warning level is determined and a warning is issued based on the comprehensive score for the time period, including: When the comprehensive score for the time period is greater than or equal to the second score threshold, and the fatigue driving warning level is determined to be a slight fatigue level based on the comprehensive score for the time period, a warning reminder message is displayed on the vehicle display screen. When the comprehensive score for the time period is greater than or equal to the second score threshold, and the fatigue driving warning level is determined to be moderate fatigue level based on the comprehensive score for the time period, a warning reminder message is broadcast through the vehicle loudspeaker. When the comprehensive score for the time period is greater than or equal to the second score threshold, and the fatigue driving warning level is determined to be severe fatigue level based on the comprehensive score for the time period, the vehicle route destination is planned to be a nearby parking lot through the in-vehicle navigation device.

6. A fatigue driving warning device, characterized in that, include: The acquisition unit is used to acquire driving time sequence information within a first preset time period, wherein the first preset time period is the time period before the current moment; The prediction unit is used to perform time-series prediction based on the driving time-series information to obtain at least one fatigue driving information within a second preset time period, wherein the second preset time period is a time period after the current moment, and the fatigue driving information includes a fatigue score and a score time point corresponding to the fatigue score. The early warning unit is used to substitute the fatigue score and the scoring time point into a comprehensive scoring formula to calculate a comprehensive score for a time period. The comprehensive score for the time period is positively correlated with the fatigue score and negatively correlated with the time elapsed between the scoring time point and the current time. The comprehensive scoring formula is as follows: In the formula, The overall score for the aforementioned time period is as follows: For the second preset time period The fatigue score mentioned above This refers to the i-th scoring time point within the second preset time period. The current time point, The number of all fatigue driving information within the second preset time period; based on the comprehensive score of the time period, determine the fatigue driving warning level and issue a warning.

7. An electronic device, comprising: The memory and processor are characterized in that the processor, when executing a computer program stored in the memory, implements the steps of the fatigue driving warning method as described in any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the fatigue driving warning method as described in any one of claims 1-5.

Images