Vehicle driving hazard warning method, device and equipment

Abstract

The present application relates to the field of vehicle driving safety, and is used to solve the problem that existing technologies are difficult to meet the needs of efficient and accurate safety warnings in scenarios such as logistics and freight. Specifically disclosed is a vehicle driving hazard warning method, device and equipment, the method comprising: obtaining real-time data of multiple vehicles; obtaining the corresponding monitoring frequency of each vehicle based on the driving speed, geographic location coordinates and current time information corresponding to each vehicle; obtaining the corresponding monitoring data of each vehicle according to the monitoring frequency, and obtaining the corresponding hazard warning level of the vehicle; if the corresponding vehicle is determined to be a risk vehicle according to the hazard warning level, generating hazard broadcast information according to the corresponding monitoring data, hazard warning level, dangerous road section data and real-time traffic event data of the risk vehicle, and controlling the risk vehicle to play the hazard broadcast information. The present invention provides an efficient and intelligent safety driving solution for specific scenarios such as logistics and freight.

Description

Technical Field

[0001] The present application relates to the field of vehicle driving safety, and in particular to a vehicle driving hazard warning method, device and equipment. Background Art

[0002] With the rapid development of industries such as logistics and dedicated freight, the need for safe driving of vehicles in complex road conditions is becoming increasingly urgent. Traditional vehicle driving hazard warning systems typically use fixed-frequency monitoring and a unified warning strategy, which has the following technical drawbacks:

[0003] Low monitoring efficiency: Failure to accurately screen vehicle business types (such as "pickup and dispatch" and "mainline"), resulting in redundant invalid data and increased system processing load;

[0004] Single early warning strategy: Adjusting monitoring frequency based on only a single dimension makes it difficult to balance monitoring accuracy and resource consumption;

[0005] The warning trigger mechanism is crude: no monitoring judgment suppression rules are set, which can easily lead to frequent false alarms or invalid warnings, distracting the driver's attention.

[0006] Therefore, there is an urgent need for a method to solve the problem that existing technologies are difficult to meet the needs of efficient and accurate safety warnings in scenarios such as logistics and freight. Summary of the Invention

[0007] The present application provides a vehicle driving hazard warning method, device and equipment, which are used to solve the problem that existing technologies are difficult to meet the needs of efficient and accurate safety warnings in scenarios such as logistics and freight.

[0008] In a first aspect, the present application provides a vehicle driving hazard warning method, the method comprising:

[0009] Acquire real-time data of multiple vehicles, including vehicle speed, geographic location coordinates, current time information, as well as dangerous road section data and real-time traffic event data acquired from external data sources;

[0010] Obtaining a monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates, and current time information corresponding to each vehicle, including: determining a speed level corresponding to the vehicle based on the driving speed, determining an area danger level corresponding to the vehicle based on the geographic location coordinates, and determining a current time period corresponding to the vehicle based on the current time information; and determining a monitoring frequency corresponding to the vehicle based on the speed level, area danger level, and current time period;

[0011] Acquire monitoring data corresponding to each of the vehicles according to the monitoring frequency, and acquire a danger warning level corresponding to the vehicle according to the monitoring data, dangerous road section data, and real-time traffic event data;

[0012] If the corresponding vehicle is determined to be a risky vehicle according to the danger warning level, danger broadcast information is generated according to the monitoring data, danger warning level, dangerous road section data and real-time traffic event data corresponding to the risky vehicle, and the risky vehicle is controlled to play the danger broadcast information.

[0013] In some embodiments, the real-time data also includes the business type of the vehicle. Before obtaining the monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates and current time information corresponding to each vehicle, the method also includes: determining whether the business type of the vehicle is a target business type; obtaining the monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates and current time information of the vehicle corresponding to the target business type; wherein the target business type includes any one of dispatch, dispatch trunk, trunk line and dedicated line.

[0014] In some embodiments, the speed level includes high-speed driving, low-speed driving, and parking and shutting down the vehicle; the regional danger level includes high-risk area, medium-risk area, and low-risk area; the current time period includes nighttime, morning and evening rush hour, and regular daytime period; determining the monitoring frequency corresponding to the vehicle based on the speed level, regional danger level, and current time period includes: generating a first monitoring frequency based on the speed level; wherein the first monitoring frequency corresponding to high-speed driving is higher than the first monitoring frequency corresponding to low-speed driving; and the first monitoring frequency corresponding to parking and shutting down the vehicle is lower than the first monitoring frequency corresponding to low-speed driving; generating a second monitoring frequency based on the regional danger level; wherein the second monitoring frequency corresponding to the high-risk area is higher than the second monitoring frequency corresponding to the medium-risk area, and the second monitoring frequency corresponding to the medium-risk area is higher than the second monitoring frequency corresponding to the low-risk area; generating a third monitoring frequency based on the current time period; wherein the third monitoring frequency corresponding to nighttime is higher than the third monitoring frequency corresponding to the morning and evening rush hour; and the third monitoring frequency corresponding to the morning and evening rush hour is higher than the third monitoring frequency corresponding to the regular daytime period; and determining the monitoring frequency corresponding to the vehicle based on the first monitoring frequency, the second monitoring frequency, and the third monitoring frequency.

[0015] In some embodiments, the method further includes: obtaining a preset basic frequency; determining a speed weight according to the speed level, determining a regional gain according to the regional danger level, and determining a time period coefficient according to the current time period; wherein the speed weights corresponding to high-speed driving, low-speed driving, and parking and engine shutdown are 1.2, 1, and 0.5, respectively; the regional gains corresponding to the high-risk area, medium-risk area, and low-risk area are 1.5, 1.2, and 1, respectively; the time period coefficients corresponding to the nighttime, morning and evening peak hours, and daytime regular periods are 1.1, 1.1, and 1, respectively; and calculating the monitoring frequency based on the basic frequency, speed weight, regional gain, and time period coefficient.

[0016] In some embodiments, obtaining the danger warning level corresponding to the vehicle based on the monitoring data, dangerous road section data and real-time traffic event data includes: matching the geographic location coordinates with the dangerous area coordinates corresponding to the dangerous road section data to determine whether the vehicle enters or approaches the dangerous area; combining the real-time traffic event data to calculate the relative distance and estimated arrival time between the vehicle and the event area; the real-time traffic event data includes traffic accident information, road construction information and road closure information; based on the relative distance, estimated arrival time and the risk level corresponding to the dangerous area, generating the danger warning level corresponding to the vehicle.

[0017] In some embodiments, if the corresponding vehicle is determined to be a risky vehicle based on the danger warning level, danger broadcast information is generated based on the monitoring data, danger warning level, dangerous road section data and real-time traffic event data corresponding to the risky vehicle, including: matching a preset standardized warning voice library according to the danger warning level to generate corresponding broadcast content; determining the broadcast time of the broadcast content in combination with the warning period in the dangerous road section data and the impact range of the real-time traffic event data; the standardized warning voice library includes preset reminder statements for multiple danger types; and generating the danger broadcast information based on the broadcast content and the broadcast time.

[0018] Exemplarily, controlling the risk vehicle to play the danger broadcast information includes: controlling the voice playback module of the risk vehicle to play the broadcast content according to preset broadcast rules and the broadcast time; the broadcast rules include entry broadcast and along-the-way broadcast.

[0019] In some embodiments, before controlling the risk vehicle to play the danger broadcast information, it also includes: within a preset unit time range, when the distance between the real-time geographic location coordinates of the vehicle and the previous real-time geographic location coordinates is less than 100 meters, and the vehicle has completed the playback of the danger broadcast information once within a preset time period, stop playing the danger warning.

[0020] In a second aspect, the present application provides a vehicle driving hazard warning device, applied to a computer device, the device comprising:

[0021] A data acquisition unit is used to acquire real-time data of multiple vehicles, wherein the real-time data includes the vehicle's driving speed, geographic location coordinates, current time information, as well as dangerous road section data and real-time traffic event data acquired from an external data source;

[0022] a frequency determination unit, configured to obtain a monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates, and current time information corresponding to each vehicle, including: determining a speed level corresponding to the vehicle based on the driving speed, determining an area danger level corresponding to the vehicle based on the geographic location coordinates, and determining a current time period corresponding to the vehicle based on the current time information; and determining the monitoring frequency corresponding to the vehicle based on the speed level, area danger level, and current time period;

[0023] a level generating unit, configured to obtain monitoring data corresponding to each of the vehicles according to the monitoring frequency, and obtain a danger warning level corresponding to the vehicle according to the monitoring data, dangerous road section data, and real-time traffic event data;

[0024] The danger broadcast unit is used to generate danger broadcast information based on the monitoring data, danger warning level, dangerous road section data and real-time traffic event data corresponding to the risk vehicle if the corresponding vehicle is determined to be a risk vehicle according to the danger warning level, and control the risk vehicle to play the danger broadcast information.

[0025] In a third aspect, the present application provides a computer device, the computer device comprising a memory and a processor;

[0026] The memory is used to store computer programs;

[0027] The processor is used to execute the computer program and implement any one of the vehicle driving hazard warning methods provided in the embodiments of the present application when executing the computer program.

[0028] The present application discloses a vehicle driving hazard warning method, device and equipment. The provided method collects real-time vehicle data (including business type, vehicle speed, location, time) and external data sources (dangerous road sections, real-time traffic events); based on vehicle speed level (high speed / low speed / parking), regional hazard level (high / medium / low risk), and time period characteristics (night / peak / regular), multi-dimensional collaborative monitoring frequency is determined to optimize resource allocation; combining monitoring data, dangerous road sections and real-time traffic events, through location matching, distance calculation and multi-source data fusion, a hazard warning level is generated; based on the warning level, the broadcast content and timing are generated, accurate warning is achieved through voice broadcast, and monitoring suppression rules (such as a 100-meter driving distance threshold and a 5-minute warning interval) are set to avoid redundant judgments.

[0029] By screening target business types, we focus on the core scenarios of logistics and freight, reduce invalid data processing, and improve system operation efficiency; based on the three-dimensional frequency reduction strategy of vehicle speed, area, and time period, we realize intelligent adaptation of monitoring frequency (such as high-frequency monitoring in high-risk areas and low-frequency monitoring in parking status), reducing resource consumption while ensuring safety; through the dual suppression rules of driving distance threshold (100 meters) and time interval (5 minutes), we avoid repeated warnings in a short period of time, improve the effectiveness of warning information and driver acceptance; combine dangerous road section data with real-time traffic events to realize dynamic assessment and accurate broadcast of vehicle risks (support custom configuration of entry broadcast and along-the-way broadcast), significantly improving the pertinence and real-time nature of driving safety warnings.

[0030] Through the collaborative innovation of business type filtering, multi-dimensional monitoring strategies and intelligent early warning mechanisms, this invention effectively solves the problems of traditional early warning systems such as "extensive monitoring, waste of resources, and inaccurate early warnings", and provides efficient and intelligent safe driving solutions for specific scenarios such as logistics and freight. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0032] Figure 1 This is a schematic flow chart of the steps of a vehicle driving hazard warning method provided by an embodiment of the present application;

[0033] Figure 2 This is a schematic block diagram of a vehicle driving hazard warning device provided in an embodiment of the present application;

[0034] Figure 3 This is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0036] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0037] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0038] It will also be understood that the term "and / or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0039] The following describes some embodiments of the present application in detail with reference to the accompanying drawings. In the absence of conflict, the following embodiments and features therein may be combined with each other.

[0040] With the rapid development of industries such as logistics and dedicated freight, the need for safe driving of vehicles in complex road conditions is becoming increasingly urgent. Traditional vehicle driving hazard warning systems typically use fixed-frequency monitoring and a unified warning strategy, which has the following technical drawbacks:

[0041] Low monitoring efficiency: Failure to accurately screen vehicle business types (such as "pickup and dispatch" and "mainline"), resulting in redundant invalid data and increased system processing load;

[0042] Single early warning strategy: Adjusting monitoring frequency based on only a single dimension makes it difficult to balance monitoring accuracy and resource consumption;

[0043] The warning trigger mechanism is crude: no monitoring judgment suppression rules are set, which can easily lead to frequent false alarms or invalid warnings, distracting the driver's attention.

[0044] Therefore, there is an urgent need for a method to solve the problem that existing technologies are difficult to meet the needs of efficient and accurate safety warnings in scenarios such as logistics and freight.

[0045] See also Figure 1 , Figure 1 This is a schematic flow chart of a vehicle driving hazard warning method provided by an embodiment of the present application. The method is applied to a computer device that interacts with the vehicle-mounted systems corresponding to multiple vehicles to provide a safety warning for each vehicle.

[0046] like Figure 1 As shown, the specific steps of the vehicle driving hazard warning method include: step S101 to step S104.

[0047] S101. Acquire real-time data of multiple vehicles, where the real-time data includes the vehicle's driving speed, geographic location coordinates, current time information, and dangerous road section data and real-time traffic event data acquired from an external data source.

[0048] Specifically, through the interaction between computer equipment and the vehicle system, vehicle operating status data and external risk environment data are collected in real time to build an early warning data foundation.

[0049] The data range includes: vehicle-owned data: driving speed (m / s or km / h), geographic location coordinates (latitude and longitude), current time information (accurate to the minute), business type (dispatch, trunk dispatch, trunk line, dedicated line); external data sources include: dangerous road section data (including dangerous area / road section geo-fences, risk levels, hazard types such as accident-prone areas / construction sections), real-time traffic event data (location, impact range, and duration of traffic accidents, road closures, temporary controls, etc.).

[0050] The system can read vehicle CAN bus data in real time through onboard terminals (such as OBD devices and GPS modules) to obtain speed and location information. It can also obtain the current time through the vehicle's built-in clock or network-synchronized time. It can also obtain the business type through business type tags preset in the vehicle operations management system (such as transport order attributes). It also uses APIs to pull real-time data on dangerous road sections and traffic incidents from traffic management platforms, map service platforms, or third-party data platforms, supporting data parsing in JSON / XML formats.

[0051] The integration of vehicle status, business attributes and external risk data provides a comprehensive data foundation for subsequent business filtering and risk assessment, avoiding the one-sidedness of a single data source; through a dynamic data interface, data updates can be achieved in seconds / minutes, ensuring that warning information is synchronized with actual road conditions, meeting the high real-time requirements of logistics and transportation.

[0052] S102. Based on the driving speed, geographic location coordinates, and current time information corresponding to each vehicle, obtaining a monitoring frequency corresponding to each vehicle, including: determining a speed level corresponding to the vehicle according to the driving speed, determining an area danger level corresponding to the vehicle according to the geographic location coordinates, and determining a current time period corresponding to the vehicle according to the current time information; and determining a monitoring frequency corresponding to the vehicle according to the speed level, area danger level, and current time period.

[0053] Specifically, based on the vehicle's real-time status (speed), the environment it is in (regional risk), and time characteristics (time period), a three-dimensional linkage monitoring frequency adjustment strategy is constructed to achieve intelligent allocation of monitoring resources.

[0054] Dimensional classification includes: Speed ​​Level: High Speed ​​(>80 km / h), Low Speed ​​(10-80 km / h), and Engine-Off (Speed ​​= 0 and Engine Off); Regional Danger Level: Based on geofence matching in dangerous road section data, it is divided into high-risk areas (such as accident-prone curves), medium-risk areas (around construction sites), and low-risk areas (generally safe sections); Current Time Period: Nighttime (22:00-6:00 the next day), Morning and Evening Peak Hours (7:00-9:00, 17:00-19:00), and Regular Daytime (rest of the day). Frequency adjustment rules include: reducing monitoring frequency in high-risk areas, at night, and during high-speed driving (to reduce invalid data); increasing monitoring frequency in low-risk areas, during regular hours, and during low-speed driving (to achieve precise monitoring).

[0055] Dimension matching algorithms may include: speed level: automatically determined by comparing the real-time speed value with a preset threshold; regional danger level: using a geo-fence spatial matching algorithm (such as buffer analysis) to determine whether the vehicle coordinates fall into the high / medium / low-risk area of ​​a dangerous road section; time period: automatically matching the current time information with a preset time interval (such as through a cron expression).

[0056] By establishing a three-dimensional weight matrix, for example: monitoring frequency when driving at high speed = basic frequency × 0.8, when driving at low speed = basic frequency × 1.2, when parking and shutting down = basic frequency × 0.5; frequency in high-risk areas = current speed level frequency × 1.5, medium-risk areas = × 1.2, low-risk areas = × 1.0; frequency at night / peak hours = regional speed frequency × 1.1, regular hours = × 1.0.

[0057] Dynamically adjust the monitoring density for different scenarios, such as high-frequency monitoring in high-risk areas (to avoid missed reports) and low-frequency monitoring in parking states (to save computing power), to solve the problems of "waste of resources" or "insufficient monitoring" in traditional fixed-frequency monitoring; combined with the actual operating characteristics of logistics vehicles (such as trunk transportation on mostly high-speed sections and pick-up and delivery services on mostly low-speed urban sections), to achieve refined customization of monitoring strategies and improve system operation efficiency.

[0058] S103 , acquiring monitoring data corresponding to each vehicle according to the monitoring frequency, and acquiring a danger warning level corresponding to the vehicle according to the monitoring data, dangerous road section data, and real-time traffic event data.

[0059] Specifically, the real-time status data of the vehicle is obtained based on the monitoring frequency, and combined with the dangerous road section and traffic event data, the current danger warning level of the vehicle (high / medium / low risk) is generated through position matching, distance calculation, and risk weighting algorithm.

[0060] By comparing the vehicle's real-time coordinates with the geographic fences of dangerous sections, it is determined whether the vehicle has entered or is approaching a dangerous area (for example, within 500 meters of the fence boundary is marked as "close"); the straight-line distance between the vehicle and the area where the real-time traffic incident occurred and the estimated arrival time (based on real-time speed and path planning) are calculated; combined with the preset risk level of the dangerous section (such as a weight of 0.8 for high-risk sections and 0.5 for medium-risk sections), the degree of impact of the incident (such as a weight of 1.0 for road closures and 0.6 for accident congestion), and the distance / time threshold (such as <200 meters and an estimated arrival time of <5 minutes trigger a high-risk warning), the final level is output through a weighted summation algorithm.

[0061] Geographic information processing can store geographic fences of dangerous road sections in spatial databases (such as PostGIS) and quickly determine the spatial relationship between vehicle coordinates and dangerous areas through spatial query statements (such as ST_DWithin); path planning algorithms can obtain real-time road conditions by calling map APIs, calculate the shortest path and estimated arrival time from the vehicle to the traffic incident area, and dynamically update it based on real-time speed; risk weight parameters can be calibrated through historical accident data. For example, if statistics show that the probability of an accident within 200 meters of a high-risk road section increases by 30%, the corresponding distance threshold weight will be increased by 0.3.

[0062] Avoid the one-sidedness of traditional single data (such as relying solely on GPS location) and reduce the false alarm rate through cross-validation of multi-source data (location + event + speed); respond to changes in traffic events in real time (such as temporary road closures caused by sudden accidents), ensure that the warning level is updated in real time with road conditions, and improve the timeliness and reliability of warnings.

[0063] S104. If the corresponding vehicle is determined to be a risky vehicle according to the danger warning level, generate danger broadcast information according to the monitoring data, danger warning level, dangerous road section data and real-time traffic event data corresponding to the risky vehicle, and control the risky vehicle to play the danger broadcast information.

[0064] Specifically, when a vehicle is judged to be a "risk vehicle" (danger warning level ≥ medium risk), customized voice broadcast information is generated based on the risk level, business scenario and preset rules, and redundant warnings are avoided through suppression strategies.

[0065] The announcement content is generated by matching a standardized voice library (such as "There is a high-accident section 500 meters ahead, please slow down"), and supports customized configuration (for example, logistics companies can add branded announcements); it distinguishes between "entry announcements" (triggered once when entering a dangerous area) and "along the way announcements" (repeated every 2 kilometers in the dangerous area), and combines the vehicle's driving distance (for example, if the driving distance is less than 100 meters per unit time, the monitoring will be ignored) and time interval (if an announcement has been made within 5 minutes, it will be suppressed) to avoid frequent reminders; the voice module is called through the vehicle system API, supporting TTS text-to-speech or playing pre-recorded audio files.

[0066] Distance suppression involves recording the last monitored coordinates. If the current coordinates are less than 100 meters away from the last one (calculated using the latitude and longitude distance formula), the warning is skipped. Time suppression maintains vehicle-level reporting timestamps. If the interval between the current and last reporting timestamps is less than 5 minutes, the warning process is terminated. Reporting rule configuration includes a management backend interface that allows logistics companies to customize reporting content for different risk levels, trigger distances (e.g., reporting 1 kilometer in advance in high-risk areas), and reporting frequency (e.g., reporting every 3 minutes along the route).

[0067] Through the dual suppression rules of distance and time, repeated warnings in a short period of time (such as frequent triggering on congested roads) are avoided, which reduces information overload for drivers and improves the acceptance of warnings; it supports diversified reporting methods such as "entering" and "along the way", and combines the driving characteristics of logistics vehicles (such as trunk line transportation requiring long-distance continuous reminders) to achieve accurate delivery of warning information and effectively reduce the risk of accidents.

[0068] In some embodiments, the real-time data also includes the business type of the vehicle. Before obtaining the monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates and current time information corresponding to each vehicle, the method also includes: determining whether the business type of the vehicle is a target business type; obtaining the monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates and current time information of the vehicle corresponding to the target business type; wherein the target business type includes any one of dispatch, dispatch trunk, trunk line and dedicated line.

[0069] Business type data acquisition involves the logistics management system assigning business type tags to vehicles during registration or task assignment. Tags include "fetch and dispatch" (last-mile delivery), "fetch and dispatch trunk" (combined trunk and branch transport), "trunk" (long-distance trunk transport), and "dedicated" (fixed-route transport). This tag information is synchronized to the early warning system via the vehicle terminal or the cloud. During real-time data collection, the business type field is extracted from the vehicle's real-time data. For example, the JSON data format sent by the vehicle terminal contains a business_type field with a preset enumeration value (fetch and dispatch / fetch and dispatch trunk / trunk / dedicated).

[0070] The system presets a target business type set {"delivery", "delivery trunk", "trunk line", "dedicated line"}. When real-time data for a vehicle is obtained, the system first verifies whether its business_type belongs to this set. If it belongs to the target type (such as a trunk line vehicle), the vehicle data is retained and subsequently used in the monitoring frequency calculation process. If it does not belong to the target type (such as a private car or non-logistics vehicle), it is directly filtered out and no further calculation is performed.

[0071] Focusing on core logistics and freight scenarios, the system eliminates invalid data from non-target business-type vehicles (such as private vehicles), reducing the number of vehicles the system must process (for example, hundreds of private vehicles may coexist around a logistics park, but only dozens of target vehicles are processed after filtering). This reduces server computing load and improves system response speed. Given the high-frequency travel, fixed routes, and higher safety risks of logistics vehicles (such as trunk line vehicles that often travel on highways and dispatch vehicles that often traverse complex urban areas), the system implements refined monitoring only for vehicles in target business types, avoiding the resource waste associated with the "one-size-fits-all" monitoring approach of traditional systems and making the monitoring strategy more tailored to the actual needs of the logistics industry.

[0072] In some embodiments, the speed level includes high-speed driving, low-speed driving, and parking and shutting down the vehicle; the regional danger level includes high-risk area, medium-risk area, and low-risk area; the current time period includes nighttime, morning and evening rush hour, and regular daytime period; determining the monitoring frequency corresponding to the vehicle based on the speed level, regional danger level, and current time period includes: generating a first monitoring frequency based on the speed level; wherein the first monitoring frequency corresponding to high-speed driving is higher than the first monitoring frequency corresponding to low-speed driving; and the first monitoring frequency corresponding to parking and shutting down the vehicle is lower than the first monitoring frequency corresponding to low-speed driving; generating a second monitoring frequency based on the regional danger level; wherein the second monitoring frequency corresponding to the high-risk area is higher than the second monitoring frequency corresponding to the medium-risk area, and the second monitoring frequency corresponding to the medium-risk area is higher than the second monitoring frequency corresponding to the low-risk area; generating a third monitoring frequency based on the current time period; wherein the third monitoring frequency corresponding to nighttime is higher than the third monitoring frequency corresponding to the morning and evening rush hour; and the third monitoring frequency corresponding to the morning and evening rush hour is higher than the third monitoring frequency corresponding to the regular daytime period; and determining the monitoring frequency corresponding to the vehicle based on the first monitoring frequency, the second monitoring frequency, and the third monitoring frequency.

[0073] The speed levels can be divided into: high-speed driving: speed > 80km / h (a common high-speed scenario for trunk transportation); low-speed driving: 10km / h ≤ speed ≤ 80km / h (urban driving scenario for dispatch vehicles); parking and shutdown: speed = 0 and the vehicle power status is "off" (the engine status is obtained through the OBD interface).

[0074] The regional danger level classification may include: high-risk areas: geographical fences marked as "accident-prone areas" and "sharp bends and steep slopes" in the dangerous road section data (such as a radius of 500 meters); medium-risk areas: geographical fences of construction sections and temporary traffic control areas (such as a radius of 1 kilometer); low-risk areas: regular road sections that are not marked with any dangerous attributes.

[0075] The current time period divisions may include: night: 22:00-6:00 the next day (a period when drivers are prone to fatigue); morning and evening peak hours: 7:00-9:00, 17:00-19:00 (periods with high congestion); regular daytime hours: 6:00-7:00, 9:00-17:00, 19:00-22:00 (non-congested, well-lit periods).

[0076] The first monitoring frequency (speed dimension) includes: high-speed driving: basic frequency × 1.2 (high-speed scenarios require high-frequency monitoring to avoid sudden risks); low-speed driving: basic frequency × 1.0 (routine monitoring); parking and shutdown: basic frequency × 0.5 (the risk is lower when the vehicle is stationary, and reducing the frequency saves power).

[0077] The second monitoring frequency (regional dimension) includes: high-risk area: current speed dimension frequency × 1.5 (highest risk, further increase monitoring density); medium-risk area: current speed dimension frequency × 1.2 (medium risk, moderately increase frequency); low-risk area: current speed dimension frequency × 1.0 (regular frequency).

[0078] The third monitoring frequency (time period dimension) includes: nighttime: regional speed frequency × 1.1 (poor visibility, increase vigilance); morning and evening rush hours: regional speed frequency × 1.1 (congestion and easy rear-end collisions, increase monitoring); regular daytime hours: regional speed frequency × 1.0 (normal monitoring).

[0079] The final monitoring frequency is calculated by weighted multiplication of the three dimensions, for example: monitoring frequency = first frequency × second frequency × third frequency (in actual implementation, the weights of each dimension can be adjusted through the configuration interface to support customized strategies for logistics companies).

[0080] Breaking the limitations of traditional single-dimensional frequency adjustment (e.g., speed alone), this approach achieves scenario-based dynamic adaptation through a three-dimensional linkage of "speed + region + time of day." For example, a trunk vehicle traveling on a high-risk mountain road at night (highway, high-risk, nighttime) can increase its monitoring frequency by 2.5 times compared to a regular road section, ensuring real-time detection of risks. Meanwhile, a parked vehicle in a park (parked, low-risk, daytime) can reduce its monitoring frequency to 0.5 times, saving the vehicle system's power consumption and data transmission costs by 40%. By balancing monitoring accuracy and resource consumption through a quantitative model, this approach avoids issues like "high-frequency monitoring leading to network congestion" or "low-frequency monitoring leading to missed risks," making it particularly suitable for large-scale deployments of logistics fleets.

[0081] In some embodiments, the method further includes: obtaining a preset basic frequency; determining a speed weight according to the speed level, determining a regional gain according to the regional danger level, and determining a time period coefficient according to the current time period; wherein the speed weights corresponding to high-speed driving, low-speed driving, and parking and engine shutdown are 1.2, 1, and 0.5, respectively; the regional gains corresponding to the high-risk area, medium-risk area, and low-risk area are 1.5, 1.2, and 1, respectively; the time period coefficients corresponding to the nighttime, morning and evening peak hours, and daytime regular periods are 1.1, 1.1, and 1, respectively; and calculating the monitoring frequency based on the basic frequency, speed weight, regional gain, and time period coefficient.

[0082] For example, speed classification: Real-time vehicle speed analysis using onboard OBD data categorizes vehicles into high speed (>80 km / h), low speed (10-80 km / h), and parked (0 km / h with the engine off). This classification is accompanied by a base frequency weight (speed weight: high speed × 1.2, low speed × 1.0, parked × 0.5). Regional hazard classification: Using GIS geo-fencing technology, roads are categorized as high-risk (accident-prone areas / sharp bends and steep slopes, fenced with a 500-meter radius), medium-risk (construction sections / temporarily restricted areas, fenced with a 1-kilometer radius), and low-risk (conventional roads). Frequency gain coefficients are assigned accordingly (regional gain: high-risk × 1.5, medium-risk × 1.2, low-risk × 1.0). Current time period: UTC time is parsed to divide the time into nighttime (22:00-6:00, time period coefficient is ×1.1), morning and evening peak hours (7:00-9:00 / 17:00-19:00, time period coefficient is ×1.1), and regular daytime hours (time period coefficient is ×1.0), reflecting driver fatigue and road condition complexity.

[0083] Dynamic frequency calculation formula: Monitoring frequency = base frequency (5 times / minute) × speed weight × regional gain × time period coefficient. For example, for a trunk vehicle traveling at high speed in a high-risk area at night, the final frequency = 5 × 1.2 × 1.5 × 1.1 = 9.9 times / minute, nearly double the normal frequency (5 times / minute).

[0084] Dynamically adjusting monitoring density based on real-time risks avoids blind spots in high-risk highway scenarios (such as missed reports of unexpected risks with traditional fixed-frequency monitoring) and reduces ineffective data transmission from stationary vehicles (e.g., a 50% reduction in frequency when parked). This reduces vehicle-to-vehicle data costs by over 30% and extends vehicle terminal battery life by 20%. Through multi-dimensional coupling, high-risk scenarios (such as nighttime highway driving in mountainous areas) are accurately identified, positively correlating monitoring frequency with accident probability. In actual measurements, the delay in risk data collection in such scenarios has been reduced from 15 seconds with traditional solutions to 6 seconds, giving drivers more time to react to emergencies.

[0085] In some embodiments, obtaining the danger warning level corresponding to the vehicle based on the monitoring data, dangerous road section data and real-time traffic event data includes: matching the geographic location coordinates with the dangerous area coordinates corresponding to the dangerous road section data to determine whether the vehicle enters or approaches the dangerous area; combining the real-time traffic event data to calculate the relative distance and estimated arrival time between the vehicle and the event area; the real-time traffic event data includes traffic accident information, road construction information and road closure information; based on the relative distance, estimated arrival time and the risk level corresponding to the dangerous area, generating the danger warning level corresponding to the vehicle.

[0086] By adopting geofence spatial query technology (such as PostGIS's ST_Within function), the vehicle's real-time geographic location coordinates (latitude and longitude) are matched with the polygonal / circular geofences in the dangerous road section data: if the coordinates fall completely within the high-risk area fence, it is marked as "entering the dangerous area"; if the coordinates are ≤500 meters away from the fence boundary, it is marked as "approaching the dangerous area."

[0087] By analyzing the event location (latitude and longitude), impact range (such as a road closure length of 2 kilometers), and event type (traffic accident / construction / road closure) from real-time traffic event data, the straight-line distance between the vehicle and the event area (Haversine formula) and the estimated time of arrival (ETA) are calculated: Straight-line distance: If the distance is ≤1 kilometer, the distance threshold judgment is triggered; ETA calculation: Based on the real-time vehicle speed and the shortest path planned by navigation (calling the map API to obtain real-time traffic conditions), if the ETA is ≤10 minutes, it is marked as "about to arrive at the event area."

[0088] We further establish a weighted scoring table, as shown below:

[0089] index high-risk areas Medium-risk areas Low-risk areas Distance ≤ 500 meters Distance 500-1000 meters ETA ≤ 5 minutes 5 minutes < ETA ≤ 10 minutes Rating (0-10 points) 8 5 3 7 4 10 6

[0090] The danger warning level classification can include: high risk: total score ≥ 8 points (immediate warning trigger); medium risk: 5 points ≤ total score < 8 points (early warning); low risk: total score < 5 points (only recorded but not broadcast).

[0091] Compared to traditional warnings that rely solely on GPS location (e.g., alerting only upon entering a dangerous road section), the system now incorporates new "approaching a dangerous area" and "real-time traffic event impact" criteria. For example, if a road closure occurs 2 kilometers ahead of a vehicle, and the system calculates the ETA (Expected Time to Achieve) and determines it will arrive in 10 minutes, the system, taking into account the high impact of the road closure, triggers a medium-risk warning in advance, increasing the lead time from the traditional 500 meters to 2 kilometers, allowing for more response time. Cross-validation of multi-source data (e.g., if a vehicle enters a high-risk area but no real-time events occur, the score is 6, triggering only a medium-risk warning; if there is an accident ahead, the score increases to 9, triggering a high-risk warning) avoids misjudgments caused by a single piece of data (e.g., mistakenly marking a normal road section as a dangerous area).

[0092] In some embodiments, if the corresponding vehicle is determined to be a risky vehicle based on the danger warning level, danger broadcast information is generated based on the monitoring data, danger warning level, dangerous road section data and real-time traffic event data corresponding to the risky vehicle, including: matching a preset standardized warning voice library according to the danger warning level to generate corresponding broadcast content; determining the broadcast time of the broadcast content in combination with the warning period in the dangerous road section data and the impact range of the real-time traffic event data; the standardized warning voice library includes preset reminder statements for multiple danger types; and generating the danger broadcast information based on the broadcast content and the broadcast time.

[0093] The construction of a standardized warning voice library includes: the voice library is stored in layers according to hazard type and risk level. Examples are as follows: High-risk warning: accident-prone areas: "There is a high-accident section 500 meters ahead, please slow down and keep a safe distance!"; road construction: "There is road construction 300 meters ahead, please avoid construction vehicles!"; medium-risk warning: congested sections: "Congestion is 1 kilometer ahead, it is recommended to plan a detour in advance!"; temporary control: "The road is temporarily controlled 2 kilometers ahead, please pay attention to traffic signs!"

[0094] The voice library supports custom extensions, and logistics companies can upload localized announcements through the management backend (such as "XX Logistics reminds you: The road ahead is entering a mountainous section, please drive carefully").

[0095] This system combines the warning period from dangerous road section data (e.g., a bridge section triggers a warning only during heavy rain) with the impact range of real-time traffic events (e.g., a road closure affecting vehicles within 3 kilometers ahead): If a vehicle enters a high-risk area and the current time falls within that area's "nighttime key warning period" (22:00-6:00), a warning is triggered 1 kilometer in advance. If the real-time traffic event is a "road closure," and the vehicle is 500 meters from the closure's starting point with an estimated arrival time of 3 minutes, the warning is triggered immediately. This system generates structured data containing "warning content" and "trigger timestamps." A standardized voice library ensures uniform warning content to avoid ambiguity (e.g., a "construction section" clearly indicates "yield to construction vehicles" rather than vague reminders). Testing has shown that drivers respond 1.2 seconds faster to standardized warnings than to unstructured voice, shortening braking distances by 3-5 meters in emergencies.

[0096] The timing of the broadcast is dynamically adjusted based on the warning period and the scope of influence. For example, if a trunk vehicle passes through a medium-risk area during regular daytime hours, the system will judge that the risk is low and shorten the advance broadcast distance from 1 kilometer at night to 500 meters. This not only ensures the reminder effect, but also avoids excessive interference when visibility is good during the day, thereby improving the driver's trust and cooperation in the warning.

[0097] Exemplarily, controlling the risk vehicle to play the danger broadcast information includes: controlling the voice playback module of the risk vehicle to play the broadcast content according to preset broadcast rules and the broadcast time; the broadcast rules include entry broadcast and along-the-way broadcast.

[0098] The entry announcement includes triggering a voice announcement when the vehicle first enters the fence boundary of a dangerous area (such as a high-risk area with a radius of 500 meters). It is suitable for "one-time risk scenarios" (such as one-way road sections and temporary construction sites).

[0099] Along-the-way broadcasts include repeated broadcasts every 2 kilometers or 3 minutes when the vehicle continues to travel in a dangerous area (such as entering a high-risk mountain road section up to 10 kilometers long), to ensure that the driver remains vigilant and avoids the risk of negligence due to long-term driving.

[0100] A broadcast command is sent to the vehicle's onboard system via the vehicle's Ethernet or CAN bus. The command includes the broadcast content, volume, and priority (high-risk warnings take precedence over entertainment system audio). Upon receiving the command, the vehicle's onboard system pauses the currently playing music or call (for high-risk warnings), invokes the TTS module or pre-recorded audio file for the broadcast, and resumes normal functionality after the broadcast is complete.

[0101] Differentiated warning strategies are provided for different risk scenarios. For example, when urban dispatch vehicles pass through short construction sections, an "entry announcement" (only a single reminder) is triggered to avoid frequent interruptions. Meanwhile, when trunk-line vehicles enter long, high-risk mountainous sections, "route announcements" provide repeated warnings every two kilometers. This addresses the extreme issue of traditional systems with either no or repeated warnings, aligning warning frequency with the duration of the risk. Priority control ensures that high-risk warnings "strongly interrupt" non-safety-related functions (such as music playback), while medium and low-risk warnings only provide "weak notifications" (without interrupting current calls). This balances safety and user experience. Field tests with logistics fleets have shown that driver acceptance of warnings has increased from 65% to 89%.

[0102] In some embodiments, before controlling the risk vehicle to play the danger broadcast information, it also includes: within a preset unit time range, when the distance between the real-time geographic location coordinates of the vehicle and the previous real-time geographic location coordinates is less than 100 meters, and the vehicle has completed the playback of the danger broadcast information once within a preset time period, stop playing the danger warning.

[0103] The system records the last moment's geographic coordinates of each vehicle (storage accuracy is 6 decimal places for longitude and latitude, approximately 1 meter accuracy), and calculates the distance between the current coordinates and the previous coordinates within a unit of time (e.g., 1 minute). If the distance is less than 100 meters (calculated using the Haversine formula, corresponding to short-distance movement within urban blocks or congested slow-moving scenarios), it is judged as "invalid movement" and the current danger warning judgment is skipped.

[0104] Maintain the most recent broadcast timestamp for each vehicle. When a new warning is triggered, calculate the interval between the current time and the timestamp: if the interval is less than 5 minutes (configurable) and the current warning level is medium or below (high-risk warnings are not suppressed), stop playing the warning information.

[0105] In congested areas (vehicles moving less than 100 meters per minute) or during temporary stops, the system automatically suppresses repeated monitoring. For example, when a dispatch vehicle is waiting at a red light in an urban area, even if it is in a medium-risk area, it will not trigger frequent warnings due to minor changes in position, reducing invalid alerts by over 70% and preventing drivers from overlooking important alerts due to repeated alerts. By controlling the time interval (for example, only allowing one medium-risk alert within 5 minutes), the system ensures that each alert is a new risk that truly requires attention, rather than repeated reminders. For example, when a vehicle passes through a long construction section, the system will use the "along-the-way alert" rule to trigger alerts every three minutes, rather than every second. This allows drivers to focus on key information and reduces the risk of decision-making errors caused by information overload.

[0106] In some embodiments, during vehicle driving, to improve driving safety and assist decision-making, the system of this application utilizes a risk identification algorithm based on multi-dimensional data fusion. This algorithm collects and analyzes the following key information in real time: current driving direction (provided by a gyroscope or inertial navigation system); current driving speed (obtained by a vehicle speed sensor); and geographic two-dimensional coordinate information (obtained by a GPS module, including longitude and latitude). Combining this information, the algorithm constructs a dynamic perception zone centered on the vehicle, covering a certain range (e.g., N kilometers) in front and around it, and identifies and assesses potential risk events in the traffic environment within this zone.

[0107] The core processing flow of the algorithm is as follows:

[0108] 1. Area Modeling: Based on the current location and driving direction, a sector-shaped or rectangular field of view (e.g., 3 km ahead, 500 meters to the left and right) is defined to define the risk area of ​​concern. Road features and potential hazards within this area are annotated using map databases (such as high-precision maps, historical accident sites, and construction sites).

[0109] 2. Access real-time data from external systems such as V2X communication (vehicle-to-infrastructure collaboration), radar, cameras, and AIS (Internet of Vehicles platform). Combined with known risk areas, all targets are mapped into a unified coordinate system to establish a complete model of the surrounding environment.

[0110] 3. Risk event identification: Calculate the likelihood of a vehicle's driving behavior, including predicting its future trajectory (using methods such as Kalman filtering and LSTM neural networks); and calculating the relative distance and estimated time of arrival (TTC) between the vehicle and the vehicle.

[0111] 4. Priority Assessment and Warning Decision-Making: A comprehensive assessment is conducted based on the risk level (e.g., low, medium, high, emergency) and the driver's status (e.g., attention monitoring, steering operation). If the risk value exceeds the set threshold, the corresponding warning mechanism is triggered. Auditory Alert: The voice broadcast device emits a prompt tone.

[0112] At the same time, we have established a comprehensive early warning database that automatically activates warning mechanisms when vehicles approach these pre-defined danger zones, providing drivers with advance warnings and effectively reducing the incidence of accidents. Leveraging advanced GPS positioning technology and cloud computing platforms, our system enables real-time vehicle location tracking and road condition updates. This means drivers can instantly access the latest traffic conditions, including important information such as traffic congestion, accident scenes, and weather changes, enabling them to make more informed route and driving decisions. Data on all potentially dangerous road sections a vehicle passes through is recorded, and precise early warning rules are developed based on this data. If a vehicle is detected approaching any known danger zone, the system immediately initiates a warning program, using visual or audible signals to remind the driver to remain vigilant and ensure driving safety.

[0113] This system obtains real-time data on various traffic events, such as road construction and traffic accidents, published by external navigation platforms. After processing, this data is synchronized to the internal map platform, providing drivers with more accurate and timely warning services, ensuring they are always in optimal driving conditions. To ensure the professionalism and consistency of warning information, common warning types, warning levels, and voice broadcast content are standardized (warning types are divided into high-risk, medium-risk, and low-risk warnings).

[0114] By choosing to broadcast upon approach / broadcast along the way. This not only improves the user experience, but also enhances the effectiveness of information communication. By extracting key data such as the location of electronic eyes, traffic facility information and real-time traffic events from the navigation platform. Data processing: Data fusion: In view of the possible overlap of routes between different tasks, advanced data fusion technology is used to eliminate redundant information and ensure the accuracy and completeness of the information. Data timeliness: Establish an efficient update mechanism to ensure that highly timely information such as traffic events is always kept up to date. Data application: Ultimately, the processed warning information will be applied to the actual driving process through voice broadcasts and other forms, providing drivers with real-time safety tips to help them complete their tasks smoothly. At the same time, if there is a problem with the current area broadcast, it can be modified / deleted by feedback to the superior, thereby ensuring the accuracy of the warning data.

[0115] See also Figure 2 , Figure 2 The embodiment of the present application further provides a schematic block diagram of a vehicle driving hazard warning device, wherein the vehicle driving hazard warning device 200 is used to execute the aforementioned vehicle driving hazard warning method. The vehicle driving hazard warning device can be configured in a server or a terminal.

[0116] The server can be a standalone server or a server cluster, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms. The terminal can be an electronic device such as a mobile phone, tablet computer, laptop computer, desktop computer, user digital assistant, and wearable device.

[0117] like Figure 2 As shown, the vehicle driving hazard warning device 200 includes:

[0118] The data acquisition unit 201 is used to acquire real-time data of multiple vehicles, including the vehicle's driving speed, geographic location coordinates, current time information, as well as dangerous road section data and real-time traffic event data acquired from external data sources;

[0119] The frequency determination unit 202 is configured to obtain a monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates, and current time information corresponding to each vehicle, including: determining a speed level corresponding to the vehicle based on the driving speed, determining an area danger level corresponding to the vehicle based on the geographic location coordinates, and determining a current time period corresponding to the vehicle based on the current time information; and determining a monitoring frequency corresponding to the vehicle based on the speed level, area danger level, and current time period;

[0120] A level generating unit 203 is configured to obtain monitoring data corresponding to each vehicle according to the monitoring frequency, and obtain a danger warning level corresponding to the vehicle according to the monitoring data, dangerous road section data, and real-time traffic event data;

[0121] The danger broadcast unit 204 is used to generate danger broadcast information based on the monitoring data, danger warning level, dangerous road section data and real-time traffic event data corresponding to the risk vehicle if the corresponding vehicle is determined to be a risk vehicle according to the danger warning level, and control the risk vehicle to play the danger broadcast information.

[0122] In some embodiments, the real-time data also includes the business type of the vehicle. Before obtaining the monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates and current time information corresponding to each vehicle, the method also includes: determining whether the business type of the vehicle is a target business type; obtaining the monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates and current time information of the vehicle corresponding to the target business type; wherein the target business type includes any one of dispatch, dispatch trunk, trunk line and dedicated line.

[0123] In some embodiments, the speed level includes high-speed driving, low-speed driving, and parking and shutting down the vehicle; the regional danger level includes high-risk area, medium-risk area, and low-risk area; the current time period includes nighttime, morning and evening rush hour, and regular daytime period; determining the monitoring frequency corresponding to the vehicle based on the speed level, regional danger level, and current time period includes: generating a first monitoring frequency based on the speed level; wherein the first monitoring frequency corresponding to high-speed driving is higher than the first monitoring frequency corresponding to low-speed driving; and the first monitoring frequency corresponding to parking and shutting down the vehicle is lower than the first monitoring frequency corresponding to low-speed driving; generating a second monitoring frequency based on the regional danger level; wherein the second monitoring frequency corresponding to the high-risk area is higher than the second monitoring frequency corresponding to the medium-risk area, and the second monitoring frequency corresponding to the medium-risk area is higher than the second monitoring frequency corresponding to the low-risk area; generating a third monitoring frequency based on the current time period; wherein the third monitoring frequency corresponding to nighttime is higher than the third monitoring frequency corresponding to the morning and evening rush hour; and the third monitoring frequency corresponding to the morning and evening rush hour is higher than the third monitoring frequency corresponding to the regular daytime period; and determining the monitoring frequency corresponding to the vehicle based on the first monitoring frequency, the second monitoring frequency, and the third monitoring frequency.

[0124] In some embodiments, the method further includes: obtaining a preset basic frequency; determining a speed weight according to the speed level, determining a regional gain according to the regional danger level, and determining a time period coefficient according to the current time period; wherein the speed weights corresponding to high-speed driving, low-speed driving, and parking and engine shutdown are 1.2, 1, and 0.5, respectively; the regional gains corresponding to the high-risk area, medium-risk area, and low-risk area are 1.5, 1.2, and 1, respectively; the time period coefficients corresponding to the nighttime, morning and evening peak hours, and daytime regular periods are 1.1, 1.1, and 1, respectively; and calculating the monitoring frequency based on the basic frequency, speed weight, regional gain, and time period coefficient.

[0125] In some embodiments, obtaining the danger warning level corresponding to the vehicle based on the monitoring data, dangerous road section data and real-time traffic event data includes: matching the geographic location coordinates with the dangerous area coordinates corresponding to the dangerous road section data to determine whether the vehicle enters or approaches the dangerous area; combining the real-time traffic event data to calculate the relative distance and estimated arrival time between the vehicle and the event area; the real-time traffic event data includes traffic accident information, road construction information and road closure information; based on the relative distance, estimated arrival time and the risk level corresponding to the dangerous area, generating the danger warning level corresponding to the vehicle.

[0126] In some embodiments, if the corresponding vehicle is determined to be a risky vehicle based on the danger warning level, danger broadcast information is generated based on the monitoring data, danger warning level, dangerous road section data and real-time traffic event data corresponding to the risky vehicle, including: matching a preset standardized warning voice library according to the danger warning level to generate corresponding broadcast content; determining the broadcast time of the broadcast content in combination with the warning period in the dangerous road section data and the impact range of the real-time traffic event data; the standardized warning voice library includes preset reminder statements for multiple danger types; and generating the danger broadcast information based on the broadcast content and the broadcast time.

[0127] Exemplarily, controlling the risk vehicle to play the danger broadcast information includes: controlling the voice playback module of the risk vehicle to play the broadcast content according to preset broadcast rules and the broadcast time; the broadcast rules include entry broadcast and along-the-way broadcast.

[0128] In some embodiments, before controlling the risk vehicle to play the danger broadcast information, it also includes: within a preset unit time range, when the distance between the real-time geographic location coordinates of the vehicle and the previous real-time geographic location coordinates is less than 100 meters, and the vehicle has completed the playback of the danger broadcast information once within a preset time period, stop playing the danger warning.

[0129] It should be noted that, those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the model training device and each module described above can refer to the corresponding processes in the aforementioned vehicle driving hazard warning method embodiment, and will not be repeated here.

[0130] The above-mentioned vehicle driving hazard warning device can be implemented in the form of a computer program. The computer program can be used in Figure 3 Runs on the computer device shown.

[0131] See also Figure 3 , Figure 3 This is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device may be a server or a terminal.

[0132] See Figure 3 The computer device includes a processor, a memory and a network interface connected through a system bus, wherein the memory may include a storage medium and an internal memory.

[0133] The storage medium may store an operating system and a computer program. The computer program includes program instructions, which, when executed, may cause the processor to execute any one of the vehicle driving hazard warning methods provided in the embodiments of the present application.

[0134] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0135] The internal memory provides an environment for the execution of a computer program stored in a storage medium. When executed by a processor, the computer program enables the processor to execute any of the vehicle driving hazard warning methods. The storage medium can be either non-volatile or volatile.

[0136] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0137] It should be understood that the processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0138] Exemplarily, in one embodiment, the processor is configured to execute a computer program stored in the memory to implement the following steps:

[0139] Acquire real-time data of multiple vehicles, including vehicle speed, geographic location coordinates, current time information, as well as dangerous road section data and real-time traffic event data acquired from external data sources;

[0140] Obtaining a monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates, and current time information corresponding to each vehicle, including: determining a speed level corresponding to the vehicle based on the driving speed, determining an area danger level corresponding to the vehicle based on the geographic location coordinates, and determining a current time period corresponding to the vehicle based on the current time information; and determining a monitoring frequency corresponding to the vehicle based on the speed level, area danger level, and current time period;

[0141] Acquire monitoring data corresponding to each of the vehicles according to the monitoring frequency, and acquire a danger warning level corresponding to the vehicle according to the monitoring data, dangerous road section data, and real-time traffic event data;

[0142] If the corresponding vehicle is determined to be a risky vehicle according to the danger warning level, danger broadcast information is generated according to the monitoring data, danger warning level, dangerous road section data and real-time traffic event data corresponding to the risky vehicle, and the risky vehicle is controlled to play the danger broadcast information.

[0143] In some embodiments, the real-time data also includes the business type of the vehicle. Before obtaining the monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates and current time information corresponding to each vehicle, the method also includes: determining whether the business type of the vehicle is a target business type; obtaining the monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates and current time information of the vehicle corresponding to the target business type; wherein the target business type includes any one of dispatch, dispatch trunk, trunk line and dedicated line.

[0144] In some embodiments, the speed level includes high-speed driving, low-speed driving, and parking and shutting down the vehicle; the regional danger level includes high-risk area, medium-risk area, and low-risk area; the current time period includes nighttime, morning and evening rush hour, and regular daytime period; determining the monitoring frequency corresponding to the vehicle based on the speed level, regional danger level, and current time period includes: generating a first monitoring frequency based on the speed level; wherein the first monitoring frequency corresponding to high-speed driving is higher than the first monitoring frequency corresponding to low-speed driving; and the first monitoring frequency corresponding to parking and shutting down the vehicle is lower than the first monitoring frequency corresponding to low-speed driving; generating a second monitoring frequency based on the regional danger level; wherein the second monitoring frequency corresponding to the high-risk area is higher than the second monitoring frequency corresponding to the medium-risk area, and the second monitoring frequency corresponding to the medium-risk area is higher than the second monitoring frequency corresponding to the low-risk area; generating a third monitoring frequency based on the current time period; wherein the third monitoring frequency corresponding to nighttime is higher than the third monitoring frequency corresponding to the morning and evening rush hour; and the third monitoring frequency corresponding to the morning and evening rush hour is higher than the third monitoring frequency corresponding to the regular daytime period; and determining the monitoring frequency corresponding to the vehicle based on the first monitoring frequency, the second monitoring frequency, and the third monitoring frequency.

[0145] In some embodiments, the method further includes: obtaining a preset basic frequency; determining a speed weight according to the speed level, determining a regional gain according to the regional danger level, and determining a time period coefficient according to the current time period; wherein the speed weights corresponding to high-speed driving, low-speed driving, and parking and engine shutdown are 1.2, 1, and 0.5, respectively; the regional gains corresponding to the high-risk area, medium-risk area, and low-risk area are 1.5, 1.2, and 1, respectively; the time period coefficients corresponding to the nighttime, morning and evening peak hours, and daytime regular periods are 1.1, 1.1, and 1, respectively; and calculating the monitoring frequency based on the basic frequency, speed weight, regional gain, and time period coefficient.

[0146] In some embodiments, obtaining the danger warning level corresponding to the vehicle based on the monitoring data, dangerous road section data and real-time traffic event data includes: matching the geographic location coordinates with the dangerous area coordinates corresponding to the dangerous road section data to determine whether the vehicle enters or approaches the dangerous area; combining the real-time traffic event data to calculate the relative distance and estimated arrival time between the vehicle and the event area; the real-time traffic event data includes traffic accident information, road construction information and road closure information; based on the relative distance, estimated arrival time and the risk level corresponding to the dangerous area, generating the danger warning level corresponding to the vehicle.

[0147] In some embodiments, if the corresponding vehicle is determined to be a risky vehicle based on the danger warning level, danger broadcast information is generated based on the monitoring data, danger warning level, dangerous road section data and real-time traffic event data corresponding to the risky vehicle, including: matching a preset standardized warning voice library according to the danger warning level to generate corresponding broadcast content; determining the broadcast time of the broadcast content in combination with the warning period in the dangerous road section data and the impact range of the real-time traffic event data; the standardized warning voice library includes preset reminder statements for multiple danger types; and generating the danger broadcast information based on the broadcast content and the broadcast time.

[0148] Exemplarily, controlling the risk vehicle to play the danger broadcast information includes: controlling the voice playback module of the risk vehicle to play the broadcast content according to preset broadcast rules and the broadcast time; the broadcast rules include entry broadcast and along-the-way broadcast.

[0149] In some embodiments, before controlling the risk vehicle to play the danger broadcast information, it also includes: within a preset unit time range, when the distance between the real-time geographic location coordinates of the vehicle and the previous real-time geographic location coordinates is less than 100 meters, and the vehicle has completed the playback of the danger broadcast information once within a preset time period, stop playing the danger warning.

[0150] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped on the computer device.

[0151] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A vehicle driving hazard warning method, characterized in that: include: Acquire real-time data of multiple vehicles, including vehicle speed, geographic location coordinates, current time information, as well as dangerous road section data and real-time traffic event data acquired from external data sources; Obtaining a monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates, and current time information corresponding to each vehicle, including: determining a speed level corresponding to the vehicle based on the driving speed, determining an area danger level corresponding to the vehicle based on the geographic location coordinates, and determining a current time period corresponding to the vehicle based on the current time information; and determining a monitoring frequency corresponding to the vehicle based on the speed level, area danger level, and current time period; Acquire monitoring data corresponding to each of the vehicles according to the monitoring frequency, and acquire a danger warning level corresponding to the vehicle according to the monitoring data, dangerous road section data, and real-time traffic event data; If the corresponding vehicle is determined to be a risky vehicle according to the danger warning level, danger broadcast information is generated according to the monitoring data, danger warning level, dangerous road section data and real-time traffic event data corresponding to the risky vehicle, and the risky vehicle is controlled to play the danger broadcast information; the real-time data also includes the business type of the vehicle. Before obtaining the corresponding monitoring frequency of each vehicle based on the driving speed, geographic location coordinates and current time information corresponding to each vehicle, the method also includes: determining whether the business type of the vehicle is a target business type; obtaining the corresponding monitoring frequency of each vehicle based on the driving speed, geographic location coordinates and current time information of the vehicle corresponding to the target business type; wherein, the target business type includes any one of dispatch, trunk dispatch, trunk line and dedicated line.

2. The method according to claim 1, characterized in that The speed level includes high speed driving, low speed driving and parking; the area danger level includes high risk area, medium risk area and low risk area; the current time period includes night time, morning and evening rush hour and normal daytime period; The determining of the monitoring frequency corresponding to the vehicle according to the speed level, the regional danger level, and the current time period includes: Generate a first monitoring frequency according to the speed level; wherein the first monitoring frequency corresponding to high-speed driving is higher than the first monitoring frequency corresponding to low-speed driving; and the first monitoring frequency corresponding to parking and shutting off the engine is lower than the first monitoring frequency corresponding to low-speed driving; Generating a second monitoring frequency according to the danger level of the area; wherein the second monitoring frequency corresponding to the high-risk area is higher than the second monitoring frequency corresponding to the medium-risk area, and the second monitoring frequency corresponding to the medium-risk area is higher than the second monitoring frequency corresponding to the low-risk area; Generate a third monitoring frequency according to the current time period; wherein the third monitoring frequency corresponding to nighttime is higher than the third monitoring frequency corresponding to the morning and evening peaks; and the third monitoring frequency corresponding to the morning and evening peaks is higher than the third monitoring frequency corresponding to the regular daytime period; A monitoring frequency corresponding to the vehicle is determined according to the first monitoring frequency, the second monitoring frequency, and the third monitoring frequency.

3. The method according to claim 2, characterized in that The method further comprises: Get the preset basic frequency; The speed weight is determined according to the speed level, the regional gain is determined according to the regional danger level, and the time period coefficient is determined according to the current time period; wherein, the speed weights corresponding to high-speed driving, low-speed driving, and parking and shutting down are 1.2, 1, and 0.5, respectively; the regional gains corresponding to high-risk areas, medium-risk areas, and low-risk areas are 1.5, 1.2, and 1, respectively; and the time period coefficients corresponding to nighttime, morning and evening peak hours, and regular daytime hours are 1.1, 1.1, and 1, respectively; The monitoring frequency is calculated according to the basic frequency, speed weight, area gain and time period coefficient.

4. The method according to claim 1, wherein The obtaining of the danger warning level corresponding to the vehicle according to the monitoring data, the dangerous road section data and the real-time traffic event data includes: Matching the geographic location coordinates with the dangerous area coordinates corresponding to the dangerous road section data to determine whether the vehicle has entered or is approaching the dangerous area; Calculate the relative distance between the vehicle and the area where the incident occurred and the estimated arrival time based on the real-time traffic event data, which includes traffic accident information, road construction information, and road closure information; A danger warning level corresponding to the vehicle is generated based on the relative distance, the estimated arrival time, and the risk level corresponding to the danger zone.

5. The method according to claim 1, wherein If the corresponding vehicle is determined to be a risk vehicle according to the danger warning level, generating danger broadcast information according to the monitoring data corresponding to the risk vehicle, the danger warning level, the dangerous road section data and the real-time traffic event data, including: According to the danger warning level, a preset standardized warning voice library is matched to generate corresponding broadcast content; The broadcasting time of the broadcast content is determined by combining the warning period in the dangerous road section data and the impact range of the real-time traffic event data; the standardized warning voice library includes preset reminder sentences for multiple types of dangers; The danger broadcast information is generated according to the broadcast content and the broadcast time.

6. The method according to claim 5, characterized in that The controlling the risk vehicle to play the danger broadcast information includes: According to the preset broadcasting rules and the broadcasting time, control the voice playback module of the risk vehicle to play the broadcasting content; The broadcasting rules include entry broadcasting and en route broadcasting.

7. The method according to claim 1, characterized in that Before controlling the risk vehicle to play the danger broadcast information, the method further includes: Within a preset unit time range, when the distance between the real-time geographic location coordinates of the vehicle and the previous real-time geographic location coordinates is less than 100 meters, and the vehicle has completed the playback of the danger broadcast information once within the preset time period, the playback of the danger warning is stopped.

8. A vehicle driving hazard warning device, characterized in that: The device comprises: A data acquisition unit is used to acquire real-time data of multiple vehicles, wherein the real-time data includes the vehicle's driving speed, geographic location coordinates, current time information, as well as dangerous road section data and real-time traffic event data acquired from an external data source; a frequency determination unit, configured to obtain a monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates, and current time information corresponding to each vehicle, including: determining a speed level corresponding to the vehicle based on the driving speed, determining an area danger level corresponding to the vehicle based on the geographic location coordinates, and determining a current time period corresponding to the vehicle based on the current time information; and determining the monitoring frequency corresponding to the vehicle based on the speed level, area danger level, and current time period; a level generating unit, configured to obtain monitoring data corresponding to each of the vehicles according to the monitoring frequency, and obtain a danger warning level corresponding to the vehicle according to the monitoring data, dangerous road section data, and real-time traffic event data; The danger broadcast unit is used to generate danger broadcast information according to the monitoring data, danger warning level, dangerous road section data and real-time traffic event data corresponding to the risk vehicle, if the corresponding vehicle is determined to be a risk vehicle according to the danger warning level, and control the risk vehicle to play the danger broadcast information; the real-time data also includes the business type of the vehicle, and before obtaining the monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates and current time information corresponding to each vehicle, it also includes: determining whether the business type of the vehicle is the target business type; obtaining the monitoring frequency corresponding to each vehicle based on the driving speed, geographic location coordinates and current time information of the vehicle corresponding to the target business type; wherein the target business type includes any one of dispatch, trunk dispatch, trunk line and dedicated line.

9. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is configured to execute the computer program and implement the method according to any one of claims 1 to 7 when executing the computer program.

Images