Intelligent automobile power-assisted rescue system

Abstract

The invention discloses an intelligent automobile power-assisted rescue system, which belongs to the technical field of automobile rescue and comprises a rescue data integration module, a rescue vehicle matching strategy optimization module, a rescue global path planning module and an automobile power-assisted rescue module. The method specifically comprises the steps that hard constraint conditions are set for preliminary screening, soft constraints are set from the three dimensions of areas, resources and capacity for secondary screening, the comprehensive adaptation degree of each rescue vehicle is obtained, and the rescue vehicles are selected to form a candidate rescue vehicle set; basic driving time, a basic risk coefficient and basic energy consumption are calculated respectively, correction is carried out by introducing a multi-factor correction coefficient, time cost, safety cost and energy cost are obtained, a comprehensive evaluation function is constructed to carry out path optimization, and a rescue global navigation path is planned for each candidate rescue vehicle. And the optimal rescue vehicle is selected according to the comprehensive evaluation score, so that the precision and the resource utilization efficiency of automobile assistance rescue are improved.

Description

Technical Field

[0001] This invention belongs to the field of automotive rescue technology, specifically referring to an intelligent automotive assistance rescue system. Background Technology

[0002] Automotive assisted rescue systems utilize IoT, big data analytics, and AI technologies to achieve efficient and intelligent matching and dispatching of rescue needs and resources. However, existing systems suffer from several drawbacks: a large number of rescue vehicles, a lack of hierarchical filtering logic for matching resource characteristics with rescue needs, and the tendency for single-dimensional matching to lead to ineffective resource dispatch and the failure to prioritize high-quality rescue resources, resulting in low rescue efficiency and unreasonable resource allocation. Furthermore, existing systems often fail to consider multiple objectives in route planning, and their road cost assessments do not incorporate actual driving factors, leading to inaccurate evaluations. The overall performance of candidate rescue vehicles is also difficult to comprehensively assess, resulting in the inability to accurately select the optimal rescue vehicle and hindering efficient, safe, and low-cost rescue operations. Summary of the Invention

[0003] To address the aforementioned issues and overcome the shortcomings of existing technologies, this invention provides an intelligent vehicle-assisted rescue system. Addressing the problems of existing systems, such as a large number of rescue vehicles, a lack of hierarchical filtering logic for matching resource characteristics with rescue needs, and the tendency for single-dimensional matching to lead to ineffective resource scheduling and the failure to prioritize high-quality rescue resources, resulting in low rescue efficiency and unreasonable resource allocation, this solution sets hard constraints for initial screening to quickly eliminate vehicles that do not meet the basic rescue requirements. A second screening is then conducted using soft constraints across three dimensions: region, resources, and capabilities, refining the matching criteria from the core rescue dimension. Finally, by integrating regional response adaptability, resource redundancy adaptability, and capability precision adaptability, a comprehensive adaptability score for each rescue vehicle is obtained. This allows for the selection of a candidate rescue vehicle set, achieving a comprehensive quantitative evaluation of the overall rescue capabilities of each vehicle and improving the accuracy of vehicle-assisted rescue dispatch and resource utilization efficiency. To address the problems in existing vehicle-assisted rescue systems, such as route planning failing to consider multiple objectives, road cost assessment lacking integration with actual driving factors leading to inaccurate evaluations, and difficulty in comprehensively assessing the overall performance of candidate rescue vehicles, which in turn hinders the accurate selection of the optimal rescue vehicle and the achievement of efficient, safe, and low-cost rescue, this solution calculates the basic travel time, basic risk coefficient, and basic energy consumption separately. By introducing multi-factor correction coefficients, it obtains time cost, safety cost, and energy cost, accurately quantifying the actual travel cost of the rescue route. A comprehensive evaluation function is constructed for route optimization, planning a global navigation route for each candidate rescue vehicle, achieving multi-objective collaborative optimization of the rescue route. The optimal rescue vehicle is selected based on the comprehensive evaluation score, enabling a comprehensive quantitative comparison of the route performance of candidate vehicles, accurately selecting the optimal rescue vehicle, ensuring efficient, safe, and low-cost rescue missions, and improving the success rate of vehicle-assisted rescue.

[0004] The present invention provides an intelligent vehicle assistance rescue system, comprising a rescue data integration module, a rescue vehicle matching strategy optimization module, a rescue global path planning module, and a vehicle assistance rescue module;

[0005] The rescue data integration module collects and preprocesses vehicle-assisted rescue data.

[0006] The rescue vehicle matching strategy optimization module sets hard constraints for initial screening, and sets soft constraints for secondary screening from three dimensions: region, resources, and capabilities. It integrates regional response adaptability, resource redundancy adaptability, and capability precision adaptability to obtain the comprehensive adaptability of each rescue vehicle, and selects rescue vehicles to form a candidate rescue vehicle set.

[0007] The global rescue route planning module calculates the basic travel time, basic risk coefficient, and basic energy consumption respectively. By introducing a multi-factor correction coefficient, it obtains the time cost, safety cost, and energy cost. A comprehensive evaluation function is constructed to optimize the route and plan a global rescue navigation route for each candidate rescue vehicle. The optimal rescue vehicle is selected based on the comprehensive evaluation score.

[0008] The vehicle assistance rescue module sends the global navigation path for rescue to the vehicle terminal, and the optimal rescue vehicle travels to the geographical coordinates of the distressed location according to the planned path to carry out vehicle assistance rescue.

[0009] Furthermore, the rescue data integration module collects and preprocesses vehicle-assisted rescue data;

[0010] The vehicle assistance data includes customer request data and rescue vehicle status data;

[0011] The customer assistance data includes assistance ID, geographical coordinates of the assistance request, type of assistance event, and customer vehicle characteristics;

[0012] The rescue vehicle status data includes rescue vehicle ID, rescue vehicle type, rescue capability, rescue resource status, rescue status, rescue vehicle geographical coordinates, energy consumption per unit mileage, maximum vehicle response distance, and service area.

[0013] The preprocessing includes data cleaning, data normalization, and data encoding.

[0014] Furthermore, the rescue vehicle matching strategy optimization module includes a hard constraint initial screening unit, a soft constraint screening unit, and a multi-dimensional fit comprehensive ranking unit; specifically, it includes the following:

[0015] The initial screening unit with hard constraints sets hard constraints on rescue vehicle status, rescue vehicle service area, rescue event type-rescue vehicle type matching, customer vehicle characteristics-rescue vehicle capability matching, and rescue resource status. Based on these hard constraints, all rescue vehicles are initially screened, and only those that simultaneously meet all hard constraints are retained to form a preliminary matching vehicle set. If the preliminary matching vehicle set is empty, the hard constraints are relaxed step by step for re-screening.

[0016] Soft constraint filtering unit; sets soft constraints for regional response adaptability, resource redundancy adaptability, and capability precision adaptability. Based on these soft constraints, it performs a secondary filtering on rescue vehicles in the initial matching vehicle set, retaining only those that simultaneously meet all soft constraints to form a secondary matching vehicle set. If the secondary matching vehicle set is empty, all soft constraint threshold restrictions are temporarily removed, and the initial matching vehicle set is directly used as the secondary matching vehicle set. This includes the following:

[0017] Soft constraint on regional response adaptability; Based on the geographical coordinates of the request for assistance and the geographical coordinates of the rescue vehicles, calculate the regional response adaptability of each rescue vehicle, and filter out rescue vehicles with regional response adaptability ≥ response threshold;

[0018] Resource redundancy fit is subject to soft constraints; the resource redundancy fit of each rescue vehicle is calculated, and rescue vehicles with resource redundancy fit ≥ redundancy threshold are selected.

[0019] Soft constraints on capability accuracy; construct a capability requirement set based on the type of emergency call and the characteristics of the customer's vehicle, construct a vehicle capability description set based on the type of rescue vehicle and the rescue capability, match the capability requirement set with the vehicle capability description set, calculate the capability accuracy of each rescue vehicle, and select rescue vehicles with capability accuracy ≥ accuracy threshold.

[0020] The multi-dimensional adaptability comprehensive ranking unit integrates regional response adaptability, resource redundancy adaptability, and capability precision adaptability to calculate the comprehensive adaptability of each rescue vehicle in the secondary matching vehicle set. The vehicles are then sorted from high to low according to their comprehensive adaptability, and the top N rescue vehicles are selected to form a candidate rescue vehicle set.

[0021] Furthermore, the global rescue route planning module includes a road data integration unit, a time cost setting unit, a safety cost setting unit, an energy cost setting unit, a global rescue navigation route generation unit, and an optimal rescue vehicle selection unit; specifically, it includes the following:

[0022] Road data integration unit: For the set of candidate rescue vehicles, collect road data from the current location to the geographic coordinates of the request for assistance for each candidate rescue vehicle and perform preprocessing. The road data includes static road network data, dynamic road condition data and environmental impact data.

[0023] Time cost setting unit: Based on static road network data, calculate the basic travel time of each road segment, and then introduce congestion correction coefficient, road surface condition correction coefficient and road construction control correction coefficient to correct the basic travel time and obtain the time cost of the road segment.

[0024] Safety cost setting unit: Based on the road grade of static road network data and the historical accident rate of dynamic road condition data, calculate the basic risk coefficient of each road segment, and then introduce the weather correction coefficient and the rescue vehicle type correction coefficient to correct the basic risk coefficient and obtain the safety cost of the road segment.

[0025] Energy cost setting unit: Based on the energy consumption per unit mileage in the rescue vehicle status data, calculate the basic energy consumption of each road segment, and then introduce the congestion energy consumption correction coefficient and the road surface condition energy consumption correction coefficient to correct the basic energy consumption and obtain the energy cost of the road segment.

[0026] A global navigation path generation unit for rescue vehicles; based on the A-Star heuristic search algorithm, it plans a global navigation path from the current location to the geographical coordinates of the request for assistance for each candidate rescue vehicle in the candidate vehicle set. It comprehensively considers time cost, safety cost, and energy cost, and constructs a comprehensive evaluation function for path optimization; including the following:

[0027] Initialization; use the geographical coordinates of the candidate rescue vehicle as the starting point of the path and the geographical coordinates of the request for help as the ending point of the path, and initialize the open list and the closed list, and add the starting point to the open list;

[0028] Construct a comprehensive evaluation function; for the current node, the comprehensive evaluation function consists of the actual comprehensive cost and the estimated comprehensive cost;

[0029] Iteratively expand nodes; select the node with the smallest comprehensive evaluation function value from the open list for expansion, update the actual cost and estimated cost of all its adjacent nodes, and move the current node to the closed list; repeat this process until the endpoint is added to the open list;

[0030] Path generation; backtracking from the endpoint to the starting point, generating a complete global navigation path for rescue from the location of candidate rescue vehicles to the geographic coordinates of the distress call;

[0031] The optimal rescue vehicle selection unit normalizes the time cost, safety cost, and energy cost of the global navigation path for each candidate rescue vehicle. The three normalized costs are weighted and fused to obtain the comprehensive evaluation score of the corresponding global navigation path. The candidate rescue vehicles are sorted from low to high according to the comprehensive evaluation score, and the vehicle with the lowest comprehensive evaluation score is selected as the optimal rescue vehicle. If multiple vehicles have the same lowest comprehensive evaluation score, the normalized time cost is further compared, and the vehicle with the smallest normalized time cost is selected as the optimal rescue vehicle.

[0032] Furthermore, the vehicle assistance rescue module sends the global navigation path corresponding to the optimal rescue vehicle to the vehicle's onboard terminal and simultaneously pushes the rescue vehicle information to the customer requesting assistance. The optimal rescue vehicle then proceeds to the geographical coordinates of the requesting assistance according to the planned path to carry out vehicle assistance rescue.

[0033] The beneficial effects achieved by adopting the above solution are as follows:

[0034] (1) In response to the problems of existing car-assisted rescue systems, such as a large number of rescue vehicles, a lack of hierarchical screening logic for matching resource characteristics with rescue needs, and the tendency for single-dimensional matching to lead to ineffective resource scheduling and failure to prioritize the matching of high-quality rescue resources, resulting in low rescue efficiency and unreasonable resource allocation, this solution sets hard constraints for initial screening to quickly eliminate vehicles that do not meet the basic requirements for rescue, reduce the amount of computation for ineffective matching, and improve the efficiency of basic rescue matching. Soft constraints are set for secondary screening from three dimensions: region, resources, and capabilities. The matching criteria are refined from the core rescue dimension to select high-quality rescue vehicles that meet the needs of rescue, thereby improving the accuracy of matching. By integrating regional response adaptability, resource redundancy adaptability, and capability precision adaptability, the comprehensive adaptability of each rescue vehicle is obtained. Rescue vehicles are selected to form a candidate rescue vehicle set, realizing a comprehensive quantitative evaluation of the comprehensive rescue capabilities of rescue vehicles and improving the accuracy of car-assisted rescue scheduling and the efficiency of resource utilization.

[0035] (2) To address the problems in existing car-assisted rescue systems, such as path planning not taking into account multiple objectives, road segment cost assessment not being combined with actual driving factors leading to distorted assessments, and difficulty in comprehensively evaluating the overall performance of candidate rescue vehicles, which in turn makes it impossible to accurately select the optimal rescue vehicle and achieve efficient, safe, and low-cost rescue, this solution calculates the basic driving time, basic risk coefficient, and basic energy consumption separately. By introducing multi-factor correction coefficients, time cost, safety cost, and energy cost are obtained, accurately quantifying the actual driving cost of the rescue road segment, improving the accuracy of cost assessment, and providing a realistic quantitative basis for path planning. A comprehensive evaluation function is constructed for path optimization, planning a global navigation path for each candidate rescue vehicle, realizing multi-objective collaborative optimization of the rescue path, avoiding high-risk road segments, and ensuring rescue endurance. The optimal rescue vehicle is selected based on the comprehensive evaluation score, realizing a comprehensive quantitative comparison of the road performance of candidate vehicles, accurately selecting the optimal rescue vehicle, ensuring that the rescue mission is carried out efficiently, safely, and with low cost, and improving the success rate of car-assisted rescue. Attached Figure Description

[0036] Figure 1 A schematic diagram of an intelligent vehicle assistance and rescue system provided by the present invention;

[0037] Figure 2 A schematic diagram of the module for optimizing the matching strategy for rescue vehicles;

[0038] Figure 3 This is a schematic diagram of the global path planning module for rescue operations.

[0039] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. Detailed Implementation

[0040] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0041] In the description of this invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0042] Example 1, see Figure 1 The present invention provides an intelligent vehicle assistance rescue system, including a rescue data integration module, a rescue vehicle matching strategy optimization module, a rescue global path planning module, and a vehicle assistance rescue module;

[0043] The rescue data integration module collects and preprocesses vehicle-assisted rescue data.

[0044] The rescue vehicle matching strategy optimization module sets hard constraints for initial screening, and sets soft constraints for secondary screening from three dimensions: region, resources, and capabilities. It integrates regional response adaptability, resource redundancy adaptability, and capability precision adaptability to obtain the comprehensive adaptability of each rescue vehicle, and selects rescue vehicles to form a candidate rescue vehicle set.

[0045] The global rescue route planning module calculates the basic travel time, basic risk coefficient, and basic energy consumption respectively. By introducing a multi-factor correction coefficient, it obtains the time cost, safety cost, and energy cost. A comprehensive evaluation function is constructed to optimize the route and plan a global rescue navigation route for each candidate rescue vehicle. The optimal rescue vehicle is selected based on the comprehensive evaluation score.

[0046] The vehicle assistance rescue module sends the global navigation path for rescue to the vehicle terminal, and the optimal rescue vehicle travels to the geographical coordinates of the distressed location according to the planned path to carry out vehicle assistance rescue.

[0047] Example 2, see Figure 1 This embodiment is based on the above embodiment. In the rescue data integration module, the vehicle assistance rescue data is collected and preprocessed.

[0048] The vehicle assistance data includes customer request data and rescue vehicle status data;

[0049] The customer assistance data includes assistance ID, geographical coordinates of the assistance request, type of assistance event, and customer vehicle characteristics;

[0050] The types of distress calls include power failure, tire failure, traffic accident, dead battery, fuel exhaustion, and vehicle being trapped.

[0051] The customer's vehicle characteristics include power type, vehicle brand and model, vehicle weight, and tire specifications;

[0052] The rescue vehicle status data includes rescue vehicle ID, rescue vehicle type, rescue capability, rescue resource status, rescue status, rescue vehicle geographical coordinates, energy consumption per unit mileage, maximum vehicle response distance, and service area.

[0053] The types of rescue vehicles include charging vehicles, fuel delivery vehicles, flatbed trailers, service vehicles, and comprehensive rescue vehicles;

[0054] The rescue capabilities include the maximum output power of the charging vehicle, the maximum fuel capacity of the fuel delivery vehicle, the maximum load capacity of the flatbed trailer, the service type of the service vehicle, and the comprehensive capabilities of the integrated rescue vehicle.

[0055] The status of rescue resources includes the current available power of the charging vehicle, the current available fuel liters of the fuel delivery vehicle, the current tonnage capacity of the flatbed trailer, the inventory of key spare parts of the service vehicle, and the current resource status of each sub-capacity of the comprehensive rescue vehicle.

[0056] The rescue status includes idle, dispatched to, rescue in progress, rescue completed and returning, and off-duty. When the rescue status is rescue completed and returning, the estimated return time is collected.

[0057] The preprocessing includes data cleaning, data normalization, and data encoding;

[0058] The data cleaning process involves identifying and processing invalid data, filling missing values ​​with the mean, and detecting and processing outliers using the 3σ principle.

[0059] The data normalization is to use the max-min scaling method to unify numerical data to the range [0, 1].

[0060] The data encoding uses One-Hot encoding to convert categorical data into numerical data.

[0061] Example 3, see Figure 1 and Figure 2 This embodiment, based on the above embodiment, includes a hard constraint initial screening unit, a soft constraint screening unit, and a multi-dimensional fit comprehensive ranking unit in the rescue vehicle matching strategy optimization module; specifically, it includes the following:

[0062] Initial screening unit with hard constraints: In car-assisted rescue, there are many rescue vehicles, and some may not meet the basic needs of a rescue request due to issues such as status, capability, or service area. Direct matching would lead to rescue failure. Hard constraints are set for rescue vehicle status, service area, rescue event type-rescue vehicle type matching, customer vehicle characteristics-rescue vehicle capability matching, and rescue resource status. Based on these hard constraints, all rescue vehicles are initially screened, retaining only those that simultaneously meet all hard constraints to form a preliminary matching vehicle set. If the preliminary matching vehicle set is empty, the hard constraints are gradually relaxed in sequence. Re-screening; first, relax the hard constraints on the status of rescue vehicles, screening for rescue vehicles that are idle or have completed a rescue and are returning with an estimated return time of ≤15 minutes; if the initial matching vehicle set is still empty, relax the hard constraints on the service area of ​​the rescue vehicles, screening for rescue vehicles whose service area can cover the geographical coordinates of the customer's request for help or whose service area boundary is less than 5 kilometers away from the geographical coordinates of the request for help; if the initial matching vehicle set is still empty, send an alarm message to the staff and initiate manual coordination; ensure that the rescue vehicles initially matched all have the basic ability to handle the current request for help, avoid ineffective resource allocation, and improve the basic matching efficiency of vehicle-assisted rescue; including the following:

[0063] Hard constraint on the status of rescue vehicles; the rescue status must be idle.

[0064] Hard constraints on the service area of ​​rescue vehicles; the service area of ​​rescue vehicles must cover the geographical coordinates of the customer requesting assistance.

[0065] The rescue event type and rescue vehicle type must match the hard constraint; the list of rescue vehicle types must contain the types required to handle the current rescue event.

[0066] Customer vehicle characteristics - hard constraint for matching rescue vehicle capabilities; the capability parameters of the rescue vehicle must meet the basic requirements corresponding to the customer vehicle characteristics.

[0067] Hard constraints on the status of rescue resources; the minimum amount of resources required for this rescue is estimated based on the type of rescue event and the characteristics of the customer's vehicle, and the current available resources of the rescue vehicle must not be less than the minimum amount of resources;

[0068] The soft constraint screening unit: While all vehicles in the initial matched vehicle set meet basic rescue needs, they differ in response efficiency, resource utilization, and capability matching accuracy. Directly entering the sorting process would prevent high-quality rescue resources from being prioritized. Soft constraints are set for regional response adaptability, resource redundancy adaptability, and capability accuracy adaptability. Based on these soft constraints, the rescue vehicles in the initial matched vehicle set are further screened, retaining only those that simultaneously meet all soft constraints to form a secondary matched vehicle set. If the secondary matched vehicle set is empty, all soft constraint thresholds are temporarily removed, and the initial matched vehicle set is directly used as the secondary matched vehicle set. This refines the adaptability of rescue vehicles from three dimensions: region, resources, and capability, selecting high-quality rescue resources that better meet the needs of the rescue request, laying the foundation for subsequent accurate sorting and optimizing the resource allocation efficiency of vehicle-assisted rescue. This includes the following:

[0069] A soft constraint is applied to regional response adaptability; based on the geographical coordinates of the request for assistance and the geographical coordinates of the rescue vehicles, the regional response adaptability of each rescue vehicle is calculated, and vehicles with regional response adaptability ≥ response threshold XY are selected. th The rescue vehicles; the formula used is as follows:

[0070] ;

[0071] In the formula, v i This is the i-th rescue vehicle, where i is the index of the rescue vehicle. It is v i Regional response adaptation, It is the geographical coordinates of the request for help and v i The distance between the geographical coordinates of the rescue vehicles It is v i The maximum response distance of the vehicle, It is the distance attenuation coefficient. , , It is a smoothing term. ;

[0072] Resource redundancy fit soft constraint; calculate the resource redundancy fit of each rescue vehicle, and filter vehicles with resource redundancy fit ≥ redundancy threshold RY. th The rescue vehicles; the formula used is as follows:

[0073] ;

[0074] In the formula, and They are v i Resource redundancy adaptability and resource ratio, , It is v i The current available resources, Rrep This is the estimated minimum resource requirement for this rescue operation. Where m is the ideal interval half-width, and m is the deviation penalty coefficient. , , ;

[0075] A soft constraint on capability precision fit is applied. A capability requirement set is constructed based on the type of emergency call and the characteristics of the customer's vehicle. A vehicle capability description set is constructed based on the type of rescue vehicle and its rescue capabilities. The capability requirement set and the vehicle capability description set are matched, and the capability precision fit of each rescue vehicle is calculated. Vehicles with a capability precision fit ≥ a precision threshold (JY) are selected. th The rescue vehicles; the formula used is as follows:

[0076] ;

[0077] In the formula, It is v i Ability precision adaptation, A rep It is a set of capability requirements. It is v i A set of vehicle capability descriptions , and They are Sets and Size of the set;

[0078] A multi-dimensional adaptability comprehensive ranking unit is used. Vehicles in the secondary matching vehicle set have varying strengths and weaknesses in single-dimensional adaptability, and single-dimensional evaluation cannot comprehensively measure the overall rescue capability of vehicles, making it difficult to determine the optimal candidate vehicle. This unit integrates regional response adaptability, resource redundancy adaptability, and capability precision adaptability to calculate the comprehensive adaptability of each rescue vehicle in the secondary matching vehicle set. The vehicles are then ranked from highest to lowest comprehensive adaptability, and the top N rescue vehicles are selected to form a candidate rescue vehicle set. This comprehensive ranking achieves a comprehensive evaluation of multi-dimensional capabilities, ensuring that the selected candidate vehicles represent the resources with the best overall capabilities, laying the foundation for subsequent route planning and optimal vehicle selection. The formula used is as follows:

[0079] ;

[0080] In the formula, It is v i The overall adaptability is calculated using α, β, and γ as weights for regional response adaptability, resource redundancy adaptability, and capability precision adaptability, respectively. , , , , .

[0081] By performing the above operations, this solution addresses the problems in existing car-assisted rescue systems, such as a large number of rescue vehicles, a lack of hierarchical screening logic for matching resource characteristics with rescue needs, and the tendency for single-dimensional matching to lead to ineffective resource scheduling and the failure to prioritize high-quality rescue resources, resulting in low rescue efficiency and unreasonable resource allocation. This solution uses hard constraints for initial screening to quickly eliminate vehicles that do not meet the basic rescue needs, reducing the computational load of ineffective matching and improving the efficiency of basic rescue matching. A second screening is performed using soft constraints across three dimensions: region, resources, and capabilities. This refines the matching criteria from the core rescue dimensions, selecting high-quality rescue vehicles that fit the rescue needs and improving matching accuracy. Finally, by integrating regional response adaptability, resource redundancy adaptability, and capability precision adaptability, a comprehensive adaptability score for each rescue vehicle is obtained. Rescue vehicles are then selected to form a candidate rescue vehicle set, enabling a comprehensive quantitative evaluation of the overall rescue capabilities of rescue vehicles and improving the accuracy of car-assisted rescue dispatch and resource utilization efficiency.

[0082] Example 4, see Figure 1 and Figure 3 This embodiment, based on the above embodiment, includes a road data integration unit, a time cost setting unit, a safety cost setting unit, an energy cost setting unit, a rescue global navigation route generation unit, and an optimal rescue vehicle selection unit in the global rescue route planning module; specifically, it includes the following:

[0083] Road data integration unit: For the set of candidate rescue vehicles, collect road data from the current location to the geographic coordinates of the request for assistance for each candidate rescue vehicle and perform preprocessing. The road data includes static road network data, dynamic road condition data and environmental impact data.

[0084] The static road network data includes road topology, road class, road segment length, historical accident rate, and road speed limit. Road class includes expressways, national highways, urban roads, and rural roads.

[0085] The dynamic traffic data includes road congestion index and road construction control information, which includes no construction control, single lane closure, and multi-lane closure.

[0086] The environmental impact data includes weather type and road surface condition. Weather type includes sunny, rainy, snowy, and foggy weather, and road surface condition includes dry road surface, wet road surface, and icy road surface.

[0087] Time Cost Setting Unit: The core requirement for vehicle-assisted rescue is timeliness. Simply calculating travel time based on road speed limits doesn't consider actual factors like congestion, road surface conditions, and construction, making it impossible to accurately assess the actual travel time of a road segment. Based on static road network data, the basic travel time for each road segment is calculated. Then, congestion correction coefficients, road surface condition correction coefficients, and road construction control correction coefficients are introduced to adjust the basic travel time, yielding the time cost of the road segment. Differentiated congestion correction coefficients are set according to road grade, and road surface and construction correction coefficients are set according to actual road conditions. This accurately adapts to the time differences in different road types and driving environments in vehicle-assisted rescue, improving the accuracy of time cost assessment. The formula used is as follows:

[0088] ;

[0089] ;

[0090] In the formula, L k and These are the base travel time, length, and speed limit for the k-th road segment, where k is the road segment index. , , and G k These are the time cost, congestion index, road surface condition correction factor, and road construction control correction factor for the k-th road segment. Dry road surface, wet road surface and icy road surface corresponding to The values ​​are 1.0, 1.2, and 1.8 respectively; G corresponds to no construction control, single-lane closure, and multi-lane closure. k The values ​​are 1.0, 1.5, and 2.0, respectively; λ is the congestion correction coefficient, with λ values ​​of 1.5, 1.2, 2.0, and 1.8 for highways, national roads, urban roads, and rural roads, respectively.

[0091] Safety Cost Setting Unit: In car-assisted rescue, the driving safety of rescue vehicles is paramount. A single road grade or accident rate cannot comprehensively assess the driving risk of a road segment, failing to consider the risk differences caused by weather and vehicle type, easily leading to safety hazards in the planned route. Based on road grade data from static road network data and historical accident rates from dynamic road condition data, the basic risk coefficient for each road segment is calculated. Then, weather correction coefficients and rescue vehicle type correction coefficients are introduced to adjust the basic risk coefficient, yielding the safety cost of the road segment. Differentiated risk weights are set according to road grade, and scientific influence coefficients are set according to weather type, taking into account the risk characteristics of rescue vehicle types, adapting to the safety priority principle of car-assisted rescue, and avoiding high-risk road segments. The formulas used are as follows:

[0092] ;

[0093] ;

[0094] In the formula, , and These are the basic risk coefficient, road grade risk weight, and historical accident rate for the k-th road segment; and the corresponding risk coefficients for expressways, national highways, urban roads, and rural roads. The values ​​were 0.2, 0.3, 0.5, and 0.8, respectively. , and These are the safety cost, weather correction factor, and rescue vehicle type correction factor for the k-th road segment. Sunny days, rainy days, snowy days, and foggy days correspond to The values ​​are 0.1, 0.3, 0.7, and 0.7 respectively;

[0095] Energy Cost Setting Unit: In car-assisted rescue operations, the energy consumption of rescue vehicles directly affects their rescue range. Simply calculating the basic energy consumption per unit mileage doesn't consider actual factors like congestion and road conditions, making it impossible to accurately assess the actual energy consumption of a road segment and easily leading to insufficient energy for the vehicle en route. Based on the energy consumption per unit mileage in the rescue vehicle's status data, the basic energy consumption for each road segment is calculated. Then, congestion energy consumption correction coefficients and road condition energy consumption correction coefficients are introduced to correct the basic energy consumption, yielding the energy cost for each road segment. Combining the energy consumption characteristics of the rescue vehicle and actual driving influencing factors, the actual energy cost for each road segment is quantitatively calculated, reflecting the true energy consumption of the rescue vehicle traversing that road segment. The formula used is as follows:

[0096] ;

[0097] ;

[0098] In the formula, U is the basic energy consumption of the kth road segment. cons It is the energy consumption per unit mile of the rescue vehicle. , and These are the energy cost, congestion energy consumption correction factor, and road surface condition energy consumption correction factor for the k-th road segment, respectively. Dry road surface, wet road surface and icy road surface corresponding to The values ​​are 1.0, 1.1, and 1.3 respectively;

[0099] A global navigation path generation unit for rescue is included. Route planning for vehicle-assisted rescue needs to simultaneously consider three core requirements: time, safety, and energy. A single cost indicator cannot achieve multi-objective path optimization and may lead to unintended consequences in the planned path. Based on the A-Star heuristic search algorithm, a global navigation path from the current location to the geographical coordinates of the request for assistance is planned for each candidate rescue vehicle in the candidate vehicle set. A comprehensive evaluation function is constructed to optimize the path, taking into account time, safety, and energy costs. This unit considers the multi-objective requirements of vehicle-assisted rescue, with actual costs reflecting the real-time consumption of the traveled sections. Estimated costs improve the algorithm's optimization efficiency and adapt to the real-time and multi-objective requirements of rescue route planning. The unit includes the following:

[0100] Initialization; use the geographical coordinates of the candidate rescue vehicle as the starting point of the path and the geographical coordinates of the request for help as the ending point of the path, and initialize the open list and the closed list, and add the starting point to the open list;

[0101] Construct a comprehensive evaluation function; for the current node, the comprehensive evaluation function consists of the actual comprehensive cost and the estimated comprehensive cost; the formula used is as follows:

[0102] ;

[0103] ;

[0104] ;

[0105] In the formula, , and These are the comprehensive evaluation function value, actual comprehensive cost value, and estimated comprehensive cost value of node n, respectively, ω T ω B and ω H These are the time cost weight, the security cost weight, and the energy cost weight. , It is the path from the starting point to node n. , and These are the estimated time cost, estimated security cost, and estimated energy cost from node n to the destination, respectively. , It is the distance from node n to the destination, v avg It is the average driving speed. , It is the average safety cost, L unit It is per unit mileage. , and These are the average congestion energy consumption correction factor and the average road surface energy consumption correction factor, respectively.

[0106] Iteratively expand nodes; select the node with the smallest comprehensive evaluation function value from the open list for expansion, update the actual cost and estimated cost of all its adjacent nodes, and move the current node to the closed list; repeat this process until the endpoint is added to the open list;

[0107] Path generation; backtracking from the endpoint to the starting point, generating a complete global navigation path for rescue from the location of candidate rescue vehicles to the geographic coordinates of the distress call;

[0108] The optimal rescue vehicle selection unit addresses the significant differences in path cost dimensions among candidate rescue vehicles, each with its own advantages and disadvantages. A single cost index cannot comprehensively evaluate the overall path performance of a vehicle, making it difficult to determine the optimal rescue vehicle. The unit normalizes the time cost, safety cost, and energy cost of the corresponding global navigation path for each candidate rescue vehicle. A weighted fusion of these three normalized costs yields a comprehensive evaluation score for the corresponding global navigation path. Candidate rescue vehicles are ranked from lowest to highest comprehensive evaluation score, and the vehicle with the lowest score is selected as the optimal rescue vehicle. If multiple vehicles have the same lowest comprehensive evaluation score, the normalized time cost is further compared, and the vehicle with the lowest normalized time cost is selected as the optimal rescue vehicle. The weighted fusion takes into account the multi-objective needs of vehicle-assisted rescue, prioritizing time cost comparison when scores are tied, aligning with the core requirement of timeliness in rescue operations, and ensuring that the selected optimal vehicle can complete the rescue efficiently, safely, and with low energy consumption using the optimal path. The formula used is as follows:

[0109] ;

[0110] In the formula, v j It is the j-th candidate rescue vehicle, where j is the index of the candidate rescue vehicle. , and They are v j The maximum-min normalized values ​​of the time cost, safety cost, and energy cost of the global navigation path for rescue.

[0111] By performing the above operations, this solution addresses the problems in existing car-assisted rescue systems, such as route planning failing to consider multiple objectives, road segment cost assessment not incorporating actual driving factors leading to distorted evaluations, and difficulty in comprehensively evaluating the overall performance of candidate rescue vehicles. These issues result in the inability to accurately select the optimal rescue vehicle and achieve efficient, safe, and low-cost rescue. This solution calculates the basic driving time, basic risk coefficient, and basic energy consumption separately. By introducing multi-factor correction coefficients, it obtains time cost, safety cost, and energy cost, accurately quantifying the actual driving cost of rescue road segments, improving the accuracy of cost assessment, and providing a realistic quantitative basis for route planning. A comprehensive evaluation function is constructed for route optimization, planning a global navigation route for each candidate rescue vehicle. This achieves multi-objective collaborative optimization of rescue routes, avoiding high-risk road segments and ensuring rescue endurance. The optimal rescue vehicle is selected based on the comprehensive evaluation score, enabling a comprehensive quantitative comparison of candidate vehicle road performance, accurately selecting the optimal rescue vehicle, ensuring efficient, safe, and low-cost rescue missions, and improving the success rate of car-assisted rescue.

[0112] Example 5, see Figure 1 This embodiment is based on the above embodiment. In the car assistance rescue module, the global navigation route corresponding to the optimal rescue vehicle is sent to the vehicle's on-board terminal, and the rescue vehicle information is pushed to the customer requesting assistance at the same time. The optimal rescue vehicle goes to the geographical coordinates of the requesting assistance according to the planned route to carry out car assistance rescue. During the rescue, the system monitors the vehicle's location and status in real time. If the traffic conditions change, the route can be replanned. After the rescue task is completed, the rescue personnel confirm the completion through the terminal, the system automatically updates the status of the rescue vehicle, and archives and saves the car assistance rescue data.

[0113] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0114] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention.

[0115] The present invention and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present invention; the actual structure is not limited thereto. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the invention, such designs should fall within the protection scope of the present invention.

Claims

1. An intelligent vehicle assistance and rescue system, characterized in that: It includes a rescue data integration module, a rescue vehicle matching strategy optimization module, a global rescue route planning module, and a vehicle-assisted rescue module; The rescue data integration module collects and preprocesses vehicle-assisted rescue data. The rescue vehicle matching strategy optimization module sets hard constraints for initial screening, and sets soft constraints for secondary screening from three dimensions: region, resources, and capabilities. It integrates regional response adaptability, resource redundancy adaptability, and capability precision adaptability to obtain the comprehensive adaptability of each rescue vehicle, and selects rescue vehicles to form a candidate rescue vehicle set. The global rescue route planning module calculates the basic travel time, basic risk coefficient, and basic energy consumption respectively. By introducing a multi-factor correction coefficient, it obtains the time cost, safety cost, and energy cost. A comprehensive evaluation function is constructed to optimize the route and plan a global rescue navigation route for each candidate rescue vehicle. The optimal rescue vehicle is selected based on the comprehensive evaluation score. The vehicle assistance rescue module sends the global navigation path for rescue to the vehicle terminal, and the optimal rescue vehicle travels to the geographical coordinates of the distressed location according to the planned path to carry out vehicle assistance rescue.

2. The intelligent vehicle assistance and rescue system according to claim 1, characterized in that: The global rescue route planning module includes a road data integration unit, a time cost setting unit, a safety cost setting unit, an energy cost setting unit, a global rescue navigation route generation unit, and an optimal rescue vehicle selection unit; specifically, it includes the following: Road data integration unit: For the set of candidate rescue vehicles, collect road data from the current location to the geographic coordinates of the request for assistance for each candidate rescue vehicle and perform preprocessing. The road data includes static road network data, dynamic road condition data and environmental impact data. Time cost setting unit: Based on static road network data, calculate the basic travel time of each road segment, and then introduce congestion correction coefficient, road surface condition correction coefficient and road construction control correction coefficient to correct the basic travel time and obtain the time cost of the road segment. Safety cost setting unit: Based on the road grade of static road network data and the historical accident rate of dynamic road condition data, calculate the basic risk coefficient of each road segment, and then introduce the weather correction coefficient and the rescue vehicle type correction coefficient to correct the basic risk coefficient and obtain the safety cost of the road segment. Energy cost setting unit: Based on the energy consumption per unit mileage in the rescue vehicle status data, calculate the basic energy consumption of each road segment, and then introduce the congestion energy consumption correction coefficient and the road surface condition energy consumption correction coefficient to correct the basic energy consumption and obtain the energy cost of the road segment. Rescue global navigation path generation unit; Optimal rescue vehicle selection unit.

3. The intelligent vehicle assistance and rescue system according to claim 2, characterized in that: The global navigation path generation unit for rescue is based on the A-Star heuristic search algorithm. It plans a global navigation path from the current location to the geographical coordinates of the request for assistance for each candidate rescue vehicle in the candidate vehicle set. It comprehensively considers time cost, safety cost, and energy cost, and constructs a comprehensive evaluation function for path optimization. Specifically... Includes the following: Initialization; use the geographical coordinates of the candidate rescue vehicle as the starting point of the path and the geographical coordinates of the request for help as the ending point of the path, and initialize the open list and the closed list, and add the starting point to the open list; Construct a comprehensive evaluation function; for the current node, the comprehensive evaluation function consists of the actual comprehensive cost and the estimated comprehensive cost; Iteratively expand nodes; select the node with the smallest comprehensive evaluation function value from the open list for expansion, update the actual cost and estimated cost of all its adjacent nodes, and move the current node to the closed list; Repeat this process until the endpoint is added to the open list; Path generation: Tracing back from the endpoint to the starting point, a complete global navigation path for rescue is generated, from the location of candidate rescue vehicles to the geographic coordinates of the request for assistance.

4. The intelligent vehicle assistance and rescue system according to claim 2, characterized in that: The optimal rescue vehicle selection unit normalizes the time cost, safety cost, and energy cost of the global navigation path corresponding to each candidate rescue vehicle. It then weights and fuses the three normalized costs to obtain a comprehensive evaluation score for the corresponding global navigation path. The candidate rescue vehicles are sorted from low to high according to their comprehensive evaluation scores, and the vehicle with the lowest comprehensive evaluation score is selected as the optimal rescue vehicle. If multiple vehicles have the same lowest comprehensive evaluation score, the normalized time cost is further compared, and the vehicle with the lowest normalized time cost is selected as the optimal rescue vehicle.

5. The intelligent vehicle assistance and rescue system according to claim 1, characterized in that: The rescue vehicle matching strategy optimization module includes a hard constraint initial screening unit, a soft constraint screening unit, and a multi-dimensional fit comprehensive ranking unit; specifically, it includes the following: The initial screening unit for hard constraints sets hard constraints on rescue vehicle status, service area, rescue event type-rescue vehicle type matching, customer vehicle characteristics-rescue vehicle capability matching, and rescue resource status. Based on these hard constraints, all rescue vehicles are initially screened, and only those that simultaneously meet all hard constraints are retained, forming a preliminary set of matched vehicles. If the initial set of matched vehicles is empty, the hard constraints will be relaxed step by step in sequence for re-screening; Soft constraint screening unit; Set soft constraints for regional response adaptability, resource redundancy adaptability, and capability precision adaptability. Based on the soft constraints, perform a secondary screening on the rescue vehicles in the initial matching vehicle set, retaining only the rescue vehicles that simultaneously meet all the soft constraints to form a secondary matching vehicle set. If the secondary matching vehicle set is empty, temporarily cancel all soft constraint threshold restrictions and directly use the initial matching vehicle set as the secondary matching vehicle set. Multidimensional fit comprehensive ranking unit.

6. The intelligent vehicle assistance and rescue system according to claim 5, characterized in that: The soft constraint screening unit specifically includes the following: Soft constraint on regional response adaptability; Based on the geographical coordinates of the request for assistance and the geographical coordinates of the rescue vehicles, calculate the regional response adaptability of each rescue vehicle, and filter out rescue vehicles with regional response adaptability ≥ response threshold; Soft constraints on resource redundancy adaptability; Calculate the resource redundancy fit of each rescue vehicle and filter out rescue vehicles with a resource redundancy fit ≥ the redundancy threshold; Soft constraint on capability accuracy: Construct a capability requirement set based on the type of emergency and the characteristics of the customer's vehicle, and construct a vehicle capability description set based on the type of rescue vehicle and the rescue capability. Match the capability requirement set with the vehicle capability description set, calculate the capability accuracy of each rescue vehicle, and select rescue vehicles with a capability accuracy of ≥ accuracy threshold.

7. The intelligent vehicle assistance and rescue system according to claim 5, characterized in that: The multi-dimensional adaptability comprehensive ranking unit integrates regional response adaptability, resource redundancy adaptability, and capability precision adaptability to calculate the comprehensive adaptability of each rescue vehicle in the secondary matching vehicle set. The top N rescue vehicles are selected from high to low according to their comprehensive adaptability to form a candidate rescue vehicle set.

8. The intelligent vehicle assistance and rescue system according to claim 1, characterized in that: The rescue data integration module collects and preprocesses vehicle-assisted rescue data. The vehicle assistance data includes customer request data and rescue vehicle status data; The customer assistance data includes assistance ID, geographical coordinates of the assistance request, type of assistance event, and customer vehicle characteristics; The rescue vehicle status data includes rescue vehicle ID, rescue vehicle type, rescue capability, rescue resource status, rescue status, rescue vehicle geographical coordinates, energy consumption per unit mileage, maximum vehicle response distance, and service area. The preprocessing includes data cleaning, data normalization, and data encoding.

9. The intelligent vehicle assistance and rescue system according to claim 1, characterized in that: The vehicle assistance rescue module sends the global navigation route corresponding to the optimal rescue vehicle to the vehicle's onboard terminal and simultaneously pushes the rescue vehicle information to the customer requesting assistance. The optimal rescue vehicle then proceeds to the geographical coordinates of the requesting assistance according to the planned route to provide vehicle assistance rescue.

Images