A distraction warning method, system, device and medium based on driver cognitive state monitoring

Abstract

The application discloses a distraction warning method, system, device and medium based on driver cognitive state monitoring, and relates to the technical field of intelligent driving assistance. The method comprises the following steps: acquiring multi-modal data and calculating a cognitive load index; determining a VATS cumulative time based on eye movement tracking data; constructing a cognitive control evaluation model based on the cognitive load index, and determining whether the current driving state is a high cognitive load state by using the cognitive control evaluation model; if the VATS cumulative time is greater than or equal to a set limit value, triggering a first-level warning; wherein the set limit value is dynamically adjusted according to the driver behavior pattern; if the current driving state is a high cognitive load state and the VATS cumulative time is greater than or equal to the set limit value, triggering a second-level warning and suggesting taking over the driving. The application can overcome the problems of insufficient VATS warning effect and inaccurate cognitive state monitoring in the prior art, and improve the driver's cognitive and response efficiency to distraction behavior.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving assistance technology, and in particular to a distraction warning method, system, device and medium based on driver cognitive state monitoring. Background Technology

[0002] Existing driver monitoring systems (DMS) primarily detect distracted behavior by the duration of gaze deviation (such as long distraction (LD)) or the accumulation of brief distractions (such as visual attention time sharing (VATS), but they still have the following problems:

[0003] First, the effectiveness of VATS warnings is insufficient: drivers lack understanding of the VATS triggering mechanism, and general warnings fail to guide behavioral improvement. Second, cognitive state monitoring is inaccurate: traditional DMS relies on single behavioral indicators (such as gaze direction), making it difficult to distinguish cognitive control levels. Finally, the feedback mechanism is rigid: existing systems do not combine dynamic visualization and tiered warnings, failing to adapt to drivers' personalized needs.

[0004] Therefore, there is an urgent need for a new monitoring and early warning method for intelligent driving assistance. Summary of the Invention

[0005] The purpose of this invention is to provide a distraction warning method, system, device and medium based on driver cognitive state monitoring, aiming to solve or improve at least one of the above-mentioned technical problems.

[0006] To achieve the above objectives, the present invention provides the following solution:

[0007] A distraction warning method based on driver cognitive state monitoring includes:

[0008] Acquire multimodal data during driving and calculate the cognitive load index; the multimodal data includes eye-tracking data and MEG neuroimaging data;

[0009] The cumulative VATS time is determined based on the eye-tracking data;

[0010] A cognitive control assessment model is constructed based on the cognitive load index, and the cognitive control assessment model is used to determine whether the current driving state is a high cognitive load state.

[0011] If the accumulated VATS time is greater than or equal to a set limit, a Level 1 warning is triggered; wherein, the set limit is dynamically adjusted according to the driver's behavior pattern;

[0012] If the current driving state is a high cognitive load state, and the accumulated VATS time is greater than or equal to the set limit, a level 2 warning is triggered and a takeover driving suggestion is made.

[0013] Optionally, acquiring multimodal data and calculating the cognitive load index specifically includes:

[0014] Multimodal data was collected using an onboard eye tracker and a MEG-compatible driving simulator;

[0015] The multimodal data is extracted to obtain key parameters, including fixation count, search range, and the theta wave at the frontal midline.

[0016] The cognitive load index is calculated based on the key parameters.

[0017] Optionally, the formula for calculating the cognitive load index is:

[0018] CLI = α × FMT energy + β × Eye movement index normalized value

[0019] The FMT energy is determined by the frontal midline theta wave, where α+β=1 and α≥0.5.

[0020] Optionally, the cognitive control assessment model is expressed as follows: when the eye movement index is less than a set frequency, it is determined that there is an abnormality in the eye movement index; and when the FMT energy is greater than or equal to a set threshold and there is an abnormality in the eye movement index, it is determined that the current driving state is a high cognitive load state; wherein, the FMT energy is determined by the frontal midline theta wave; and the eye movement index includes the number of fixations.

[0021] Optionally, it also includes: statistically analyzing the multimodal data and warning feedback, and using a mental model to analyze the reasons for warning triggering and generate personalized reports.

[0022] The present invention also provides a distraction warning system based on driver cognitive state monitoring, comprising:

[0023] The data acquisition and index calculation unit is used to acquire multimodal data during driving and calculate the cognitive load index; the multimodal data includes eye-tracking data and MEG neuroimaging data;

[0024] VATS cumulative calculation unit, used to determine VATS cumulative time based on the eye-tracking data;

[0025] The state judgment unit is used to construct a cognitive control evaluation model based on the cognitive load index, and use the cognitive control evaluation model to determine whether the current driving state is a high cognitive load state.

[0026] A Level 1 warning triggering unit is used to trigger a Level 1 warning if the accumulated VATS time is greater than or equal to a set limit; wherein the set limit is dynamically adjusted according to the driver's behavior pattern.

[0027] The Level 2 Warning Trigger Unit is used to trigger a Level 2 warning and suggest taking over driving if the current driving state is a high cognitive load state and the accumulated VATS time is greater than or equal to a set limit.

[0028] The present invention also provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to cause the electronic device to perform the distraction warning method based on driver cognitive state monitoring described above.

[0029] The present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the distraction warning method based on driver cognitive state monitoring as described above.

[0030] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0031] This invention discloses a distraction warning method, system, device, and medium based on driver cognitive state monitoring. The method includes acquiring multimodal data and calculating a cognitive load index; determining the cumulative VATS time based on eye-tracking data; constructing a cognitive control assessment model based on the cognitive load index and using the cognitive control assessment model to determine whether the current driving state is a high cognitive load state; triggering a first-level warning if the cumulative VATS time is greater than or equal to a set limit; wherein the set limit is dynamically adjusted according to the driver's behavior pattern; and triggering a second-level warning and suggesting driver takeover if the current driving state is a high cognitive load state and the cumulative VATS time is greater than or equal to the set limit. This invention overcomes the problems of insufficient VATS warning effect and inaccurate cognitive state monitoring in the prior art, improving the driver's cognitive and response efficiency to distraction behaviors. Attached Figure Description

[0032] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is a flowchart illustrating the distraction warning method based on driver cognitive state monitoring according to the present invention.

[0034] Figure 2 This is a schematic diagram of the overall operating logic in this embodiment;

[0035] Figure 3 This is the hierarchical warning triggering logic diagram in this embodiment;

[0036] Figure 4 This is a schematic diagram of the mental model training interface in this embodiment. Detailed Implementation

[0037] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] The purpose of this invention is to provide a distraction warning method, system, device and medium based on driver cognitive state monitoring, aiming to solve or improve at least one of the above-mentioned technical problems.

[0039] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0040] like Figures 1-4 As shown, the present invention provides a distraction warning method based on driver cognitive state monitoring, comprising:

[0041] Acquire multimodal data during driving and calculate the cognitive load index; the multimodal data includes eye-tracking data and MEG neuroimaging data.

[0042] The cumulative VATS time is determined based on the eye-tracking data; a cognitive control assessment model is constructed based on the cognitive load index, and the cognitive control assessment model is used to determine whether the current driving state is a high cognitive load state.

[0043] If the accumulated VATS time is greater than or equal to a set limit, a Level 1 warning is triggered; wherein the set limit is dynamically adjusted according to the driver's behavior pattern; if the current driving state is a high cognitive load state and the accumulated VATS time is greater than or equal to the set limit, a Level 2 warning is triggered and it is recommended to take over driving.

[0044] As one specific implementation method, the specific processing procedure for each of the above steps is as follows.

[0045] For multimodal data fusion:

[0046] It integrates eye-tracking (1000Hz sampling) and MEG neuroimaging data to capture fixation counts, search range, and frontal midline theta wave (FMT) activity in real time.

[0047] Construct a cognitive control assessment model: when FMT energy is greater than or equal to the threshold and eye movement indicators (such as fixation count < 10 times / 4 seconds) are abnormal, it is judged as a state of high cognitive load.

[0048] For dynamic visualization and tiered warnings:

[0049] VATS cumulative progress bar: The dashboard displays the cumulative distraction time within 30 seconds (e.g., "8 / 10 seconds"). When the set limit is reached, a level 1 warning is triggered (icon flashing + voice prompt "Beware of multiple distractions").

[0050] Cognitive state-related warning: If VATS is detected under high cognitive load and the accumulated VATS reaches the set limit, a level 2 warning is triggered (full-screen red prompt + voice "Cognitive overload, it is recommended to slow down").

[0051] For mental model training:

[0052] Interactive simulation training: Driving scenario simulation is embedded in the vehicle's central control screen to guide the driver to identify the difference between LD and VATS, and provide real-time feedback on the reason for the warning trigger (such as "You triggered the warning due to multiple brief distractions").

[0053] Personalized report generation: Generate weekly reports based on historical data (such as "VATS trigger count reduced by 30%), combined with a safe driving points reward mechanism.

[0054] In this embodiment, the mental model is built based on a neural network.

[0055] For adaptive optimization algorithms with set limits:

[0056] Dynamically adjust the VATS threshold based on driver behavior patterns: For drivers who frequently trigger high cognitive warnings, gradually reduce the cumulative VATS threshold (e.g., from 10 seconds to 8 seconds) until distraction behavior improves.

[0057] Integrating MEG data to optimize the eye-tracking-cognition association model: When the correlation between FMT activity and eye-tracking metrics is <0.7, the detection parameters are automatically recalibrated.

[0058] As a specific embodiment, the detailed deployment and application process of the above-described method is provided.

[0059] 1. Hardware Deployment

[0060] The in-vehicle eye tracker (SR Research EyeLink 1000) works in conjunction with a MEG-compatible driving simulator, and data is transmitted to the vehicle's ECU via a CAN bus.

[0061] The central control screen integrates a training module, supporting touch interaction and voice feedback.

[0062] 2. Software Flow

[0063] The data fusion module analyzes eye movement and MEG data in real time and calculates the cognitive load index (CLI = 0.6 × FMT energy + 0.4 × normalized fixation count).

[0064] When CLI ≥ 0.8 and VATS accumulates for ≥ 7 seconds, a Level 2 warning is triggered and a driver takeover is recommended.

[0065] 3. Adaptive Optimization Example

[0066] If the driver triggers the VATS warning three times consecutively when CLI ≥ 0.8, the system will lower the VATS threshold from 10 seconds to 9 seconds and display a message on the central control screen: "Increased distraction risk detected, warning sensitivity has been adjusted."

[0067] Therefore, this technical solution improves the effectiveness of VATS warnings by visualizing VATS and associating warnings with cognitive states. It also improves the accuracy of distraction detection by combining neuroimaging data and further enhances the driver's correct understanding of the VATS mechanism through mental model training.

[0068] In summary, this invention addresses the shortcomings of existing driver monitoring systems (DMS) in providing adequate warnings for driver-to-vehicle (VATS) responses by integrating MEG neuroimaging data with eye-tracking metrics and combining dynamic visualization with a tiered warning mechanism. The system integrates mental model training and adaptive algorithm optimization, significantly improving the driver's cognitive accuracy and response efficiency to distraction behaviors, thereby reducing driving risks caused by cognitive errors.

[0069] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0070] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A distraction warning method based on driver cognitive state monitoring, characterized in that, include: Acquire multimodal data during driving and calculate the cognitive load index; the multimodal data includes eye-tracking data and MEG neuroimaging data; The cumulative time of visual attention time sharing is determined based on the eye-tracking data; A cognitive control assessment model is constructed based on the cognitive load index, and the cognitive control assessment model is used to determine whether the current driving state is a high cognitive load state. If the cumulative time of visual attention sharing is greater than or equal to a set limit, a Level 1 warning is triggered; wherein, the set limit is dynamically adjusted according to the driver's behavior pattern. If the current driving state is a high cognitive load state, and the cumulative time of visual attention time sharing is greater than or equal to the set limit, a level 2 warning is triggered and it is recommended to take over driving; The acquisition of multimodal data and calculation of the cognitive load index specifically includes: Multimodal data was collected using an onboard eye tracker and a MEG-compatible driving simulator; The multimodal data is extracted to obtain key parameters, including fixation count, search range, and the theta wave at the frontal midline. Calculate the cognitive load index based on the key parameters mentioned above; The formula for calculating the cognitive load index is as follows: CLI = α × FMT energy + β × Eye movement index normalized value The FMT energy is determined by the frontal midline theta wave, where α+β=1 and α≥0.

5.

2. The distraction warning method based on driver cognitive state monitoring according to claim 1, characterized in that, The cognitive control assessment model is expressed as follows: when the eye movement index is less than the set frequency, it is determined that there is an abnormality in the eye movement index; and when the FMT energy is greater than or equal to the set threshold and there is an abnormality in the eye movement index, it is determined that the current driving state is a high cognitive load state; wherein, the FMT energy is determined by the frontal midline theta wave; and the eye movement index includes the number of fixations.

3. The distraction warning method based on driver cognitive state monitoring according to claim 1, characterized in that, Also includes: The multimodal data and warning feedback are statistically analyzed, and the causes of warning triggers are analyzed using a mental model to generate personalized reports.

4. A distraction warning system based on driver cognitive state monitoring, using the method as described in any one of claims 1-3, characterized in that, include: The data acquisition and index calculation unit is used to acquire multimodal data during driving and calculate the cognitive load index; the multimodal data includes eye-tracking data and MEG neuroimaging data; A visual attention time-sharing cumulative calculation unit is used to determine the visual attention time-sharing cumulative time based on the eye-tracking data; The state judgment unit is used to construct a cognitive control evaluation model based on the cognitive load index, and use the cognitive control evaluation model to determine whether the current driving state is a high cognitive load state. A Level 1 warning triggering unit is used to trigger a Level 1 warning if the cumulative visual attention time sharing time is greater than or equal to a set limit; wherein the set limit is dynamically adjusted according to the driver's behavior pattern; The Level 2 Warning Trigger Unit is used to trigger a Level 2 warning and suggest taking over driving if the current driving state is a high cognitive load state and the cumulative time of visual attention time sharing is greater than or equal to a set limit.

5. An electronic device, characterized in that, The device includes a memory and a processor, the memory being used to store a computer program, and the processor running the computer program to cause the electronic device to perform the distraction warning method based on driver cognitive state monitoring according to any one of claims 1-3.

6. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by a processor, implements the distraction warning method based on driver cognitive state monitoring as described in any one of claims 1-3.

Images