A distraction warning system

Abstract

The application belongs to the technical field of vehicle safety, and discloses a distraction driving early warning system, which comprises a data acquisition unit for acquiring the line-of-sight data of a driver, a distraction behavior detection unit for identifying long distraction (LD) and visual attention time sharing (VATS) based on the line-of-sight data in real time, a hierarchical warning unit for triggering a warning according to the cumulative duration of VATS, a feedback explanation unit for providing a warning reason, a model training unit for providing an interactive tutorial and generating a personalized report, and a system optimization unit for feedback optimization of the system according to the historical behavior of the driver. The application optimizes the detection and warning mechanism of visual attention time sharing, improves the cognitive and response efficiency of the driver to the distraction behavior, and thus reduces distraction driving.

Description

Technical Field

[0001] This invention belongs to the field of vehicle safety technology, and in particular relates to a distracted driving warning system. Background Technology

[0002] Existing driver monitoring systems (DMS) trigger warnings by detecting prolonged distraction (LD, such as a 3-second sustained line of sight deviance) and visual attention time sharing (VATS, such as a cumulative 10-second brief line of sight deviance within 30 seconds). However, research shows that drivers generally lack a proper understanding of the triggering mechanisms of VATS, resulting in VATS warnings being significantly less effective than LD warnings. This problem stems from the fact that traditional DMSs only provide general warnings without clearly distinguishing the reasons for the warning triggers, preventing drivers from forming a complete mental model. Furthermore, existing systems lack dynamic feedback mechanisms designed for VATS, making it difficult to guide drivers in understanding the cumulative effect of multiple brief distractions.

[0003] Existing technologies, such as the DMS algorithm in the Euro NCAP (European New Car Assessment Program), can detect VATS (Vehicle Distraction Skills), but they do not address the cognitive deficiencies of users. Patent application CN113123456A proposes improving warning effectiveness through multimodal warnings (visual + auditory), but it does not address mental model optimization; patent application US20220167890A1 uses machine learning to adjust warning thresholds, but it does not propose solutions to the cognitive problems related to VATS. Therefore, there is an urgent need for a distraction warning system that can enhance drivers' understanding of VATS. Summary of the Invention

[0004] The purpose of this invention is to provide a distracted driving warning system to solve the problems existing in the prior art.

[0005] To achieve the above objectives, the present invention provides a distracted driving warning system, comprising:

[0006] The data acquisition unit is used to collect the driver's line-of-sight data;

[0007] The distraction behavior detection unit is used to identify long distraction LD and visual attention time sharing VATS in real time based on the gaze data.

[0008] A tiered warning unit is used to trigger warnings based on the cumulative duration of VATS;

[0009] The feedback explanation unit is used to provide the reason for the warning;

[0010] The model training unit is used to provide interactive tutorials and generate personalized reports;

[0011] The system optimization unit is used to optimize the system based on feedback from the driver's historical behavior.

[0012] Optionally, the data acquisition unit specifically includes:

[0013] The gaze data acquisition module is used to collect the driver's gaze data in real time through the vehicle-mounted camera and eye tracker;

[0014] The data transmission module is used to transmit gaze data to the distraction detection unit via the CAN bus.

[0015] Optionally, the distraction behavior detection unit specifically includes:

[0016] The real-time detection module is used to analyze line-of-sight data in real time using Euro NCAP standard algorithms and to determine line-of-sight (LD) and line-of-sight (VATS).

[0017] The cumulative progress visualization module is used to display the current cumulative VATS duration.

[0018] Optionally, the hierarchical warning unit specifically includes:

[0019] The Level 1 warning module is used to trigger a gentle alert when the cumulative VATS time reaches 70% of a preset threshold, reminding the driver to reduce brief distractions;

[0020] The Level 2 warning module is used to trigger a multimodal warning when the cumulative duration of VATS reaches a preset threshold.

[0021] Optionally, the feedback interpretation unit specifically includes:

[0022] The voice explanation module is used to explain the reason for the warning through voice.

[0023] The text explanation module is used to explain the reason for the warning in words.

[0024] Optionally, the model training unit specifically includes:

[0025] The simulation training module is used to guide drivers through an interactive tutorial to learn the differences between LD and VATS and the warning rules during the initial stage of vehicle startup.

[0026] The report generation module is used to generate personalized reports based on the driver's historical behavior data.

[0027] Optionally, the system optimization unit specifically includes:

[0028] The behavior pattern analysis module is used to analyze the driver's behavior patterns based on machine learning algorithms and historical behavior.

[0029] The threshold adjustment module is used to dynamically adjust the preset threshold of VATS based on the driver's behavior patterns.

[0030] The technical effects of this invention are as follows:

[0031] This invention addresses the shortcomings of existing Driver Management Systems (DMS) in providing adequate VATS warnings through a mechanism that visualizes VATS cumulative progress, provides tiered warnings, and offers feedback explanations. By combining mental model training with adaptive algorithm optimization, the system significantly improves drivers' awareness and response efficiency to distracting behaviors, ultimately reducing the risk of distracted driving. 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] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0034] Figure 1 This is a system architecture diagram in an embodiment of the present invention;

[0035] Figure 2 This is a schematic diagram of the VATS cumulative progress visualization interface in an embodiment of the present invention;

[0036] Figure 3 This is a schematic diagram of graded warnings in an embodiment of the present invention;

[0037] Figure 4 This is a schematic diagram of the mental model training interface in an embodiment of the present invention. Detailed Implementation

[0038] Various exemplary embodiments of the present invention will now be described in detail. This detailed description should not be considered as a limitation of the present invention, but rather as a more detailed description of certain aspects, features, and embodiments of the present invention.

[0039] It should be understood that the terminology used in this invention is merely for describing particular embodiments and is not intended to limit the invention. Furthermore, with respect to numerical ranges in this invention, it should be understood that each intermediate value between the upper and lower limits of the range is also specifically disclosed. Every smaller range between any stated value or intermediate value within a stated range, and any other stated value or intermediate value within said range, is also included in this invention. The upper and lower limits of these smaller ranges may be independently included or excluded from the range.

[0040] Various modifications and variations can be made to the specific embodiments described in this specification without departing from the scope or spirit of the invention, as will be apparent to those skilled in the art. Other embodiments derived from this specification will also be obvious to those skilled in the art. This application specification and embodiments are merely exemplary.

[0041] The terms “include,” “including,” “have,” “contain,” etc., used in this article are all open-ended terms, meaning that they include but are not limited to.

[0042] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0043] like Figure 1 - Figure 4 As shown, this embodiment provides a distracted driving warning system, including:

[0044] The data acquisition unit is used to collect the driver's line-of-sight data;

[0045] The distraction behavior detection unit is used to identify long distraction LD and visual attention time sharing VATS in real time based on the gaze data.

[0046] A tiered warning unit is used to trigger warnings based on the cumulative duration of VATS;

[0047] The feedback explanation unit is used to provide the reason for the warning;

[0048] The model training unit is used to provide interactive tutorials and generate personalized reports;

[0049] The system optimization unit is used to optimize the system based on feedback from the driver's historical behavior.

[0050] To address the issue of insufficient effectiveness of existing DMS (Distracted Driving Management Systems) in providing VATS (Visual Attention Time Sharing) warnings, this embodiment offers a distracted driving warning system based on driver mental model optimization. By optimizing the detection and warning mechanism of Visual Attention Time Sharing (VATS) and through a dynamic feedback mechanism and cognitive guidance module, this embodiment helps drivers establish a correct mental model, significantly improving the effectiveness of VATS warnings and enhancing drivers' cognitive and response efficiency to distracted behaviors, thereby reducing distracted driving.

[0051] The system provided in this embodiment specifically includes:

[0052] Distraction Behavior Detection Unit: Integrates Euro NCAP standard algorithms to detect LD (deviant gaze for 3 seconds) and VATS (vacancies for 10 seconds within 30 seconds) in real time. It also adds a VATS accumulation progress visualization function, dynamically displaying the current VATS accumulation time (such as a progress bar or percentage) on the in-vehicle display screen to alert the driver when approaching the warning threshold. Figure 1 This is a system architecture diagram of this embodiment, illustrating the interaction flow of the distraction detection, graded warning, mental model training, and adaptive optimization units. Figure 2 This is a diagram of the VATS cumulative progress visualization interface, which includes a progress bar and real-time prompts.

[0053] Hierarchical warning and feedback unit:

[0054] Level 1 Warning (VATS Pre-Warning): When VATS accumulates to 70% of the threshold, a mild alert (such as a flashing dashboard icon) is triggered to remind the driver to reduce brief distractions.

[0055] Level 2 Warning (Formal Warning): When the VATS threshold is reached, a multimodal warning (visual + voice) is triggered, and the message "Multiple brief gaze deviations have been detected. Please focus on driving" is clearly announced.

[0056] Feedback and explanation function: After a warning, the driver can explain the reason for the warning via voice or text (such as "You have not been looking at the road for 8 seconds in the past 30 seconds") to enhance the driver's understanding of the VATS mechanism. Figure 3 This is a diagram illustrating tiered warnings. Level 1 warnings are indicated by a flashing icon, while Level 2 warnings are indicated by a full-screen notification and a voice announcement.

[0057] Mental Model Training Unit:

[0058] Simulation training mode: During the initial vehicle startup, the driver is guided through an interactive tutorial to learn the differences between LD and VATS and the warning rules.

[0059] Real-time learning feedback: Based on drivers' historical behavior data, generate personalized reports (such as "VATS triggers decreased by 20% this week") to motivate them to continuously improve.

[0060] Figure 4 The image shows the mental model training interface, used to display interactive tutorials and personalized report examples.

[0061] Adaptive Algorithm Optimization Unit: Based on machine learning analysis of driver behavior patterns, dynamically adjusts the VATS threshold. For example, for drivers who frequently trigger VATS, the cumulative threshold is gradually reduced (e.g., from 10 seconds to 8 seconds) until the distracted behavior improves.

[0062] This embodiment significantly improves drivers' understanding of distraction mechanisms and helps them form a correct mental model through visualization of VATS cumulative progress and tiered warnings. Simultaneously, through feedback explanation and personalized training, this embodiment enhances the effectiveness of VATS warnings to a level comparable to LD (expected to reduce the effect by more than 40%). Furthermore, the adaptive algorithm optimization in this embodiment can provide customized warning strategies for different driving habits, reducing the false alarm rate.

[0063] Specific implementation examples of this embodiment include:

[0064] Hardware deployment: The driver's gaze data is collected in real time through an in-vehicle camera and eye tracker, and transmitted to the in-vehicle ECU via CAN bus.

[0065] The dashboard integrates a progress display area, and the central control screen supports an interactive training module.

[0066] Software Flow: The distraction behavior detection unit continuously analyzes gaze data to determine the LD / VATS status. When VATS accumulates to 70% of the threshold, a Level 1 warning is triggered; when it reaches 100%, a Level 2 warning is triggered and an explanation is broadcast. A monthly driver behavior report is generated and pushed to the central control screen, combined with a reward mechanism (such as safe driving points) to incentivize users.

[0067] Adaptive optimization example: If a driver triggers VATS more than 5 times in a week, the system will automatically reduce the cumulative threshold from 10 seconds to 9 seconds and inform the driver of the reason for the adjustment.

[0068] The above description is merely a preferred embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A distraction warning system, comprising: The system comprises: a data acquisition unit for acquiring the driver's line of sight data; a distraction behavior detection unit for real-time identification of long distraction LD and visual attention time sharing VATS based on the line of sight data; a hierarchical warning unit for triggering a warning according to the cumulative duration of visual attention time sharing VATS; a feedback interpretation unit for providing the warning reason; a model training unit for providing interactive tutorials and generating personalized reports; a system optimization unit for feedback optimization of the system according to the driver's historical behavior; The data acquisition unit specifically comprises: a line of sight data acquisition module for real-time acquisition of the driver's line of sight data through a vehicle-mounted camera and an eye tracker; a data transmission module for transmitting the line of sight data to the distraction behavior detection unit through a CAN bus; The distraction behavior detection unit specifically comprises: a real-time detection module for real-time analysis of the line of sight data through Euro NCAP standard algorithm, and judging the real-time identification of long distraction LD and visual attention time sharing VATS; a cumulative progress visualization module for displaying the cumulative duration of visual attention time sharing VATS; The hierarchical warning unit specifically comprises: a first-level warning module for triggering a gentle prompt when the cumulative duration of visual attention time sharing VATS reaches 70% of the preset threshold, reminding the driver to reduce short distraction; a second-level warning module for triggering a multi-modal warning when the cumulative duration of visual attention time sharing VATS reaches the preset threshold; The model training unit specifically comprises: a simulation training module for guiding the driver to learn the difference between long distraction LD and visual attention time sharing VATS and the warning rules through interactive tutorials at the initial stage of vehicle start; a report generation module for generating a personalized report according to the driver's historical behavior data; The system optimization unit specifically comprises: a behavior pattern analysis module for analyzing the driver's behavior pattern according to machine learning algorithm and historical behavior; a threshold adjustment module for dynamically adjusting the preset threshold of visual attention time sharing VATS according to the driver's behavior pattern.

2. The system of claim 1, wherein, The feedback interpretation unit specifically comprises: a voice interpretation module for explaining the triggering reason of the warning through voice; a text interpretation module for explaining the triggering reason of the warning through text.

Images