Transportation task control method and device of vehicle and vehicle

Abstract

The application discloses a vehicle transportation task control method and device and a vehicle. The method comprises the following steps: acquiring multi-source perception data of the vehicle, including vehicle data and logistics data; when the vehicle is in failure, determining evaluation information including a failure type, a sensitive coefficient of the carried goods and a predicted maintenance duration according to the multi-source perception data; wherein the sensitive coefficient is used to represent the loss degree caused by delayed delivery of the goods; determining a target strategy from a preset transportation maintenance strategy set according to the evaluation information; the transportation maintenance strategy set comprises a plurality of strategies for indicating the operation sequence between vehicle maintenance and goods transportation; and controlling the vehicle to execute a goods transportation task based on the target strategy. Thus, the sensitive coefficient of the goods and the predicted maintenance duration are combined to accurately reflect the loss degree caused by delayed delivery, so as to match the best transportation and maintenance operation sequence, avoid risks such as goods damage or breach of contract caused by blind waiting for maintenance or forced transportation, and improve the reliability of logistics transportation.

Description

Technical Field

[0001] This application relates to the field of vehicle networking technology, and in particular to a method, device and vehicle for controlling vehicle transportation tasks. Background Technology

[0002] In the logistics and transportation sector, mechanical failures of vehicles during cargo transport are a common problem. Traditional troubleshooting methods typically rely on drivers' experience to make judgments, or on dispatch centers making simple decisions based on vehicle fault codes, such as directly arranging tow truck repairs, on-site emergency repairs, or relocation to another vehicle.

[0003] However, these approaches often overlook the inherent characteristics of the goods and the economic value of transportation timeliness. Especially for time-sensitive goods such as cold chain and fresh produce, when non-disruptive malfunctions such as reduced air conditioning capacity occur, forcibly recommending the nearest repair shop may lead to serious cargo damage and breach of contract risks. Furthermore, the assessment of cargo sensitivity is often crude; for example, it fails to distinguish the differences in quality degradation between different varieties within the "fresh produce" category (such as strawberries and apples) after being removed from ideal storage conditions, resulting in insufficient decision-making precision. In addition, due to the significant differences in repair time between different types of malfunctions and repair shops, arbitrarily choosing a repair shop may cause the repair process to affect the timely delivery of goods, thus impacting overall transportation efficiency and economic benefits.

[0004] Therefore, in the event of vehicle malfunction, how to accurately select the order of repair and transportation operations to ensure cargo quality while minimizing economic losses and improving transportation reliability is a problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0005] In view of this, one aspect of this application provides a method for controlling the transportation task of a vehicle, the method comprising: Acquire multi-source perception data of the vehicle; the multi-source perception data includes vehicle data and logistics data; When the vehicle malfunctions, assessment information reflecting the transportation risk of the vehicle is determined based on the multi-source sensing data. The assessment information includes the malfunction type, the sensitivity coefficient of the cargo being transported, and the estimated repair time. The sensitivity coefficient is used to characterize the degree of loss caused by the delayed delivery of the cargo. Based on the assessment information, a target strategy is determined from a preset set of transportation maintenance strategies; the set of transportation maintenance strategies includes multiple strategies for indicating the sequence of operations between vehicle maintenance and cargo transportation. The vehicle is controlled to perform cargo transportation tasks based on the target strategy.

[0006] Optionally, the multi-source perception data further includes interaction information characterizing the driver's intention; determining the sensitivity coefficient includes: Based on the logistics data, determine the multi-dimensional influencing factors of the sensitivity coefficient; the influencing factors include timeliness, cargo vulnerability, economic loss, and contractual constraint. Based on the preset weights of each of the aforementioned influencing factors, the influencing factors are weighted and summed to obtain the initial sensitivity coefficient; Based on the interaction information, a correction factor is determined; and the initial sensitivity coefficient is corrected using the correction factor to obtain the sensitivity coefficient. Specifically, when the interaction information is empty, or when the fault type is an obstructive fault indicating that the vehicle cannot continue to drive, the correction factor is zero; when the interaction information indicates a priority delivery intention, the correction factor is positive; and when the interaction information indicates a priority repair intention, the correction factor is negative.

[0007] Optionally, the logistics data includes the waybill SLA level and the delivery deadline; determining the timeliness urgency includes: Based on the vehicle's departure time, current system time, and estimated travel time from the current location to the unloading location, determine the available time margin for transportation; The total time window for transportation is determined based on the departure time and the receipt deadline. The basic value characterizing the urgency of transportation is determined by the available time margin and the total time window; Based on a preset acceleration factor mapping relationship, the target acceleration factor corresponding to the SLA level of the waybill is determined; the target acceleration factor is used to characterize the user's requirement for timeliness. The time urgency is obtained by correcting the base value using the target acceleration factor.

[0008] Optionally, the logistics data includes product categories; determining the vulnerability of the goods includes: Based on a preset decay period mapping relationship, a target decay value corresponding to the category of goods is determined; the target decay value is the time required for the quality of the goods to decrease to a preset percentage threshold after being removed from ideal storage conditions. The basic vulnerability of the cargo is determined based on the target attenuation value; Determine whether the fault type affects the ideal storage conditions; If so, determine a deviation parameter to characterize the degree of deviation between the actual environment and the ideal environment; based on the deviation parameter, determine a coupling factor to couple the fault with the cargo protection environment; and determine the cargo vulnerability using the coupling factor and the basic vulnerability. If not, the basic vulnerability shall be used as the cargo vulnerability.

[0009] Optionally, the logistics data includes loss impact parameters; the loss impact parameters include the value of the goods, contract penalties, and insurance coverage; determining the degree of economic loss includes: Obtain the historical loss statistics parameters of the vehicle; the historical loss statistics parameters include the historical loss mean and the historical loss standard deviation. Based on the preset maintenance time mapping relationship, determine the standard maintenance time corresponding to the fault type; The probability of cargo damage due to delays is determined by the standard repair time. Based on the probability of cargo damage and the loss impact parameters, the potential economic loss is determined; Based on the historical loss statistics parameters, the potential economic loss is normalized to obtain the economic loss degree.

[0010] Optionally, the logistics data includes contract terms and customer information; determining the contract binding force includes: Obtain the vehicle's historical performance information; Based on the preset constraint mapping relationship, constraint influence factors that characterize the degree of contract constraint are determined; the constraint influence factors include rigidity factors corresponding to the contract terms, level factors corresponding to the customer information, and performance factors corresponding to the historical performance information. Based on preset weighting coefficients, the constraint influence factors are weighted and summed to obtain the contract constraint degree; The rigidity factor is used to characterize the rigidity of the contract terms regarding the timeliness of receipt; the grade factor is used to characterize the importance of the customer; the performance factor is used to characterize the performance level of the vehicle; and the performance factor is maximized when the historical performance information indicates that the vehicle has been delayed within a specified historical period.

[0011] Optionally, the vehicle data includes fault codes; determining the estimated repair time includes: Determine the fault type based on the fault code; Based on the preset fault mapping relationship, determine the basic maintenance time corresponding to the fault type; Determine the repair influencing factors for repair shops within a specified range; the repair influencing factors include technical proficiency factor, queuing waiting factor, and parts waiting factor; Based on the basic repair time and the repair influencing factors, the estimated repair time for each of the repair shops is determined.

[0012] Optionally, the set of transportation and maintenance strategies includes on-site parking, delivery before repair, quick repair before delivery, and repair before delivery; the fault types include blocking faults that indicate the vehicle cannot continue to drive and functional faults that indicate the vehicle can continue to drive. Based on the assessment information, a target strategy is determined from a pre-set set of transportation maintenance strategies, including: When the fault type is the blocking fault, the target strategy is to stop in place; When the fault type is the functional fault, perform the following steps: If the sensitivity coefficient is greater than or equal to the first threshold, the target strategy is to send the product first and then repair it. If the sensitivity coefficient is less than or equal to the second threshold, the target strategy is to repair first and then send; the first threshold is greater than the second threshold. If the sensitivity coefficient is between the first threshold and the second threshold, determine whether the sum of the estimated travel time from the repair shop to the unloading location and the estimated repair time is less than the remaining time between the current system time and the deadline for signing. If it is less than the target value, the target strategy is to send it for quick repair afterward; If it is not less than, the target strategy is to send first and then repair.

[0013] Optionally, the vehicle data includes battery state of charge and battery rated capacity; If the target strategy is "deliver first, repair later", the process further includes the following before controlling the vehicle to perform the cargo transportation task based on the target strategy: The available energy of the vehicle is determined based on the battery state of charge and the battery rated capacity; Determine the energy consumption per unit mileage of the vehicle under the fault condition; Based on the energy consumption per unit mileage under fault conditions, the energy consumption required for the vehicle to travel on each travel segment is determined; the energy consumption includes the first energy consumption for the first travel segment from the current location to the unloading location, and the second energy consumption for the second travel segment from the unloading location to the repair shop; Determine whether the repair shops include energy-accessible shops that meet the energy consumption conditions; the energy consumption conditions are that the sum of the first energy consumption and the second energy consumption is less than the available energy. If included, the target store for carrying out the goods transportation task is determined from the energy-accessible stores; If not, the target strategy is switched to "repair first, then deliver"; and the target store for carrying out the goods transportation task is determined from the repair stores.

[0014] Optionally, determining the vehicle's energy consumption per unit mile under the fault condition includes: Obtain the normal energy consumption per unit mileage of the vehicle under normal conditions; Based on the pre-built energy consumption correction mapping relationship, determine the target energy consumption correction coefficient corresponding to the fault type; The energy consumption per unit mileage in the fault state is determined based on the energy consumption per unit mileage in the normal state and the target energy consumption correction coefficient.

[0015] Optionally, based on the energy consumption per unit mile in the fault state, the energy consumption required for the vehicle to travel on each mileage segment is determined, including: Obtain current weather information and terrain information of the area where the vehicle is located; Based on a preset redundancy mapping relationship, there are weather redundancy coefficients corresponding to the weather information, terrain redundancy coefficients corresponding to the terrain information, and load redundancy coefficients corresponding to each travel segment; the full load redundancy coefficient of the first travel segment is greater than the empty load redundancy coefficient of the second travel segment. Based on a preset energy consumption factor mapping relationship, the auxiliary energy consumption factor corresponding to each travel segment is determined; the auxiliary energy consumption factor is used to characterize the degree of influence of the vehicle auxiliary system's operating status on energy consumption per unit mileage; the first energy consumption factor of the first travel segment is greater than the second energy consumption factor of the second travel segment; The safety redundancy factor for each of the travel segments is determined based on the weather redundancy coefficient, the terrain redundancy coefficient, and the load redundancy coefficient. The energy consumption is determined based on the fault-state energy consumption per unit mileage, the auxiliary energy consumption factor, and the safety redundancy factor.

[0016] Optionally, determining the target store for carrying out the goods transportation task includes: The energy-accessible stores or the repair stores are selected by a specified screening process to obtain candidate stores; the specified screening includes screening based on business status, repair qualifications, and parts availability. Each candidate store was evaluated using multiple dimensions, resulting in a multi-dimensional score. These dimensions included repair capability score, logistics fulfillment score, parts availability score, and repair speed score. Based on a preset scenario factor mapping relationship, the scenario weights corresponding to the target strategy are determined; the scenario weights include maintenance capability weight, fulfillment weight, spare parts weight, and maintenance speed weight. Based on the scenario weights, the multi-dimensional scores are weighted and summed to obtain the comprehensive score for each candidate store. The first specified number of stores in the descending order of the comprehensive scores will be selected as the target stores.

[0017] Optionally, in the scene factor mapping relationship: When the target strategy is "repair first, then send", the maintenance capability weight is the largest among the scenario weights; When the target strategy is to send the product back after quick repair, the repair speed weight is the largest among the scenario weights. When the target strategy is "send first, repair later", the performance weight is the largest among the scenario weights.

[0018] Optionally, the dimension score also includes a distance convenience score, and the corresponding scenario weight also includes a distance weight; when the target strategy is on-site parking, the distance weight is the largest; If the target strategy is "delivery first, repair later", then each candidate store is scored for distance and convenience, including: Determine the deflection angle of each candidate store; the deflection angle is the angle between the vector pointing from the current position to the unloading position with the unloading position as the vertex and the vector pointing from the unloading position to the candidate store; By applying the deflection angle, the total mileage of each travel segment is corrected for detour penalty to obtain the corrected mileage; The distance convenience score is determined based on the corrected mileage.

[0019] Optionally, the repair capability score is determined based on the store's repair performance indicators; the repair performance indicators include first-time repair rate, return rate, and repair time. The logistics fulfillment score is determined based on the delivery performance indicators of goods after store repairs; the delivery performance indicators include on-time receipt rate, average time-delay deviation, and damage correlation rate; wherein, the on-time receipt rate is the percentage of goods that are received on time after store repairs; the average time-delay deviation is the average percentage of overdue waybills; and the damage correlation rate is the percentage of goods damaged due to store repair delays. The accessory guarantee score is determined based on a preset accessory mapping relationship, which is the correspondence between the store's accessory inventory and the score. The repair speed score is determined based on the estimated repair time.

[0020] Optionally, the repair performance indicators and the delivery performance indicators are statistically analyzed in a stratified manner based on preset conditions; the preset conditions include store-wide, fault type cluster, goods type cluster, and receipt area cluster; the stratified statistics include: Obtain historical metrics; these historical metrics include historical maintenance performance metrics and historical delivery performance metrics. The initial indicators are obtained by applying a time decay weight to the historical indicators based on the actual receipt time of the waybill. Based on the preset hierarchical structure, the statistical values ​​of the initial indicators are queried starting from the finest level. During the layer-by-layer query process, if the number of samples at the current level is less than a preset threshold, the query is backtracked to the previous level until the statistical values ​​that meet the preset threshold are obtained. The query conditions in the hierarchical structure are composed of the preset conditions, and the finer the level granularity, the more types of preset conditions constitute the corresponding query conditions. The statistical values ​​are smoothed using Bayesian methods to obtain the target estimate after the historical indicators are corrected.

[0021] Optionally, when the target strategy is quick repair followed by delivery, the method further includes: At preset intervals, obtain feedback from stores regarding the remaining repair time; Determine whether the sum of the current system time, the remaining repair time, and the estimated travel time between the repair shop and the unloading location is greater than the time remaining between the current system time and the delivery deadline. If the value is greater than the specified value, a strategy switching suggestion is generated to switch to the "send first, repair later" strategy, and the strategy switching suggestion is output.

[0022] Optionally, after controlling the vehicle to perform the cargo transportation task based on the target strategy, the method further includes: Collect information on the vehicle's fault repair status, actual receipt time, and actual repair duration; If the target fault with the same fault code recurs within a preset time period, update the first-time repair rate of the corresponding repair shop for the target fault. Compare the actual delivery time with the delivery deadline, and update the on-time delivery rate of the corresponding repair shop; The technical proficiency factor of the corresponding repair shop is updated based on the actual repair time.

[0023] Another aspect of this application provides a vehicle transportation task control device, the device comprising: The perception data acquisition module is used to acquire multi-source perception data of the vehicle; the multi-source perception data includes vehicle data and logistics data. An assessment information acquisition module is used to determine assessment information reflecting the transportation risk of the vehicle based on the multi-source sensing data when the vehicle malfunctions. The assessment information includes the malfunction type, the sensitivity coefficient of the cargo being transported, and the estimated repair time. The sensitivity coefficient is used to characterize the degree of loss caused by the delayed delivery of the cargo. The target strategy determination module is used to determine a target strategy from a preset set of transportation maintenance strategies based on the evaluation information; the set of transportation maintenance strategies includes multiple strategies for indicating the sequence of operations between vehicle maintenance and cargo transportation; The task execution module is used to control the vehicle to perform cargo transportation tasks based on the target strategy.

[0024] Another aspect of this application provides a vehicle including a memory and a processor, wherein the memory stores a computer program executable on the processor, and the processor executes the computer program to implement the steps of a transportation task control method for the vehicle. The transportation task control method, device, and vehicle provided in this application have the following beneficial effects: by integrating onboard data and logistics data, a multi-dimensional quantitative assessment of transportation risks under vehicle malfunction conditions is achieved. Specifically, by combining the cargo sensitivity coefficient with the estimated repair time, the extent of loss caused by delayed delivery is accurately reflected. This allows for the matching of the optimal transportation and repair operation sequence from a preset strategy set based on the assessment information, avoiding risks such as cargo damage and timeliness breaches caused by blindly waiting for repairs or forcibly transporting goods. This minimizes economic losses while ensuring cargo quality and improves the reliability of logistics transportation. Attached Figure Description

[0025] Figure 1 A flowchart illustrating a vehicle transportation task control method provided in an embodiment of this application; Figure 2 A schematic diagram of the structure of a vehicle transportation task control system provided in an embodiment of this application; Figure 3 A schematic diagram illustrating the principle of a target determination strategy provided in an embodiment of this application; Figure 4 A schematic diagram illustrating the principle of determining a target store, provided as an embodiment of this application; Figure 5 A schematic diagram illustrating the principle of a vehicle transportation task control method provided in an embodiment of this application; Figure 6 A schematic diagram of the structure of a vehicle transportation task control device provided in an embodiment of this application; Figure 7 This is a structural schematic diagram of a vehicle provided in an embodiment of this application.

[0026] The reference numerals in the attached diagram are as follows: 60 is the perception data acquisition module, 61 is the evaluation information acquisition module, 62 is the target strategy determination module, 63 is the task execution module, 70 is the memory, 71 is the processor, 72 is the display screen, 73 is the input / output interface, 74 is the communication interface, 75 is the power supply, 76 is the communication bus, 701 is the computer program, 702 is the operating system, and 703 is the data. Detailed Implementation

[0027] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0028] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0029] Figure 1 This is a flowchart illustrating a vehicle transportation task control method provided in an embodiment of this application, as shown below. Figure 1 As shown, the method includes: S10: Acquire multi-source perception data of the vehicle; multi-source perception data includes vehicle data and logistics data; Figure 2 This is a schematic diagram of the structure of a vehicle transportation task control system provided in an embodiment of this application, as shown below. Figure 2 As shown, this system is used to implement the transportation task control method provided in this application. The system includes an edge perception layer, a cloud decision layer, and a service execution layer. It is understood that, in specific embodiments, the cloud decision layer is mainly used to execute the transportation task control method provided in this application, the edge perception layer is mainly used to acquire multi-source perception data, and the service execution layer is mainly used to execute the final output control method.

[0030] During transportation operations, vehicles need to collect and monitor their status and cargo conditions in real time. This allows for timely and accurate implementation of optimal transportation and repair strategies in the event of a vehicle malfunction. Specifically, for example... Figure 2 As shown, in a specific embodiment, the cloud-based decision layer acquires multi-source sensing data collected by the edge sensing layer in real time. This multi-source sensing data may include, but is not limited to, vehicle data and logistics data. Table 1 is a schematic table of multi-source sensing data provided in an embodiment of this application. For ease of understanding, the following explanation will be based on Table 1.

[0031] Table 1 is a schematic diagram of multi-source sensing data. Referring to Table 1, in one optional embodiment, vehicle data can be collected in real time via the vehicle controller area network (CAN bus), and may include, but is not limited to, diagnostic trouble codes (DTC), battery state of charge (SOC), battery rated capacity, and cargo compartment environmental data (such as temperature and humidity).

[0032] Logistics data is obtained through the Transportation Management System (TMS) when a waybill is created. This data may include, but is not limited to, cargo category, Service Level Agreement (SLA), delivery deadline, cargo value, contract terms, and customer information. The waybill SLA level reflects the customer's level of timeliness requirements.

[0033] It should be noted that the vehicles in the embodiments of this application may include, but are not limited to, mini-trucks, light trucks, heavy trucks, and light commercial vehicles (LCVs). Furthermore, the multi-source sensing data in the table above is an illustrative table, and this application does not limit the specific data types collected.

[0034] S11: When a vehicle malfunctions, assessment information reflecting the transportation risk of the vehicle is determined based on multi-source sensing data. The assessment information includes the type of malfunction, the sensitivity coefficient of the cargo being transported, and the estimated repair time. The sensitivity coefficient is used to characterize the degree of loss caused by the delayed delivery of the cargo. When a vehicle detects a fault code via the CAN bus and determines that a malfunction has occurred, such as Figure 2 The multi-source sensing data collected in the above embodiments is first aligned, and then the fault type, the sensitivity coefficient of the cargo, and the estimated maintenance time are determined based on the aligned multi-source sensing data.

[0035] The sensitivity coefficient of the cargo is used to quantify "how much loss this batch of goods will suffer if delivery is delayed," that is, to characterize the degree of loss caused by delayed delivery. The value range is [0,1], and the closer it is to 1, the more priority needs to be given to ensuring delivery, that is, the greater the degree of loss caused.

[0036] In one alternative embodiment, the estimated repair time can be predicted based on factors such as the type of fault and the repair shop's repair capabilities. Multiple assessment pieces of information are then combined to form the input to a risk matrix, which is used to subsequently determine the sequence of transportation and repair operations.

[0037] S12: Based on the assessment information, determine the target strategy from the pre-set set of transportation maintenance strategies; the set of transportation maintenance strategies includes multiple strategies for indicating the sequence of operations between vehicle maintenance and cargo transportation; S13: Control the vehicle to perform cargo transportation tasks based on the target strategy.

[0038] In a specific embodiment, multiple transportation and maintenance strategies are pre-built, which may include, but are not limited to, on-site parking, delivery before repair, and repair before delivery. Based on the fault type and sensitivity coefficient, and combined with the comparison between the estimated repair time and the remaining time, the optimal target strategy can be determined.

[0039] At this point, by integrating vehicle data and logistics data, an assessment system based on a multi-dimensional risk matrix of "people-vehicle-goods" was constructed. This system can dynamically select the optimal transportation and maintenance strategy based on the type of fault, the sensitivity coefficient of the goods, and the estimated maintenance time. It achieves differentiated decision-making such as "forced stop for faults at red lights and priority delivery for urgent goods at yellow lights," which significantly improves the operational efficiency of commercial vehicles and the fulfillment rate of goods.

[0040] For example, such as Figure 2 As shown, when the fault type is an obstructive fault that prevents the vehicle from continuing to drive, the target strategy is to stop the vehicle on the spot and send the target strategy down to the service execution layer to wait for rescue. If the fault type is a functional fault that allows the vehicle to continue driving, a comprehensive judgment is made based on the sensitivity coefficient and the estimated repair time to determine whether to send the vehicle for repair first or repair it first and then send it for repair.

[0041] Once the target strategy is determined, execution instructions are issued to the vehicle and service execution layers to complete the current cargo transportation task. Specifically, if the objective is to stop on-site, roadside assistance is called and driving ceases. If the objective is to deliver first and then repair, a route to the unloading location is planned, and nearby repair shops are recommended. If the objective is to repair first and then deliver, the vehicle proceeds directly to the repair shop.

[0042] In one alternative embodiment, during the execution of the target strategy, the vehicle status and maintenance progress are continuously monitored in real time in order to dynamically switch the target strategy.

[0043] Therefore, the vehicle transportation task control method provided in this application, by integrating onboard data and logistics data, achieves a multi-dimensional quantitative assessment of transportation risks under vehicle malfunction conditions. Specifically, by combining the cargo sensitivity coefficient with the estimated repair time, it accurately reflects the degree of loss caused by delayed delivery. This allows for the matching of the optimal transportation and repair operation sequence from a preset strategy set based on the assessment information, avoiding risks such as cargo damage and timeliness breaches caused by blindly waiting for repairs or forcibly transporting goods. This minimizes economic losses while ensuring cargo quality and improves the reliability of logistics transportation.

[0044] In an optional embodiment, referring to Table 1 above, the multi-source perception data further includes interaction information characterizing the driver's intention; determining the sensitivity coefficient includes: Based on logistics data, we determine the multi-dimensional influencing factors of the sensitivity coefficient; these factors include timeliness, cargo vulnerability, economic loss, and contractual constraint. Based on the pre-set weights of each influencing factor, the influencing factors are weighted and summed to obtain the initial sensitivity coefficient; Based on the interaction information, a correction factor is determined; and the initial sensitivity coefficient is corrected using the correction factor to obtain the sensitivity coefficient. Specifically, when the interaction information is empty, or the fault type is a blocking fault that indicates the vehicle cannot continue to drive, the correction factor is zero; when the interaction information indicates a priority delivery intention, the correction factor is positive; and when the interaction information indicates a priority repair intention, the correction factor is negative.

[0045] In an optional embodiment, multiple influencing factors that affect the degradation of goods quality are introduced when determining the sensitivity coefficient. Table 2 is a schematic table of influencing factors provided by the embodiments of this application. For ease of understanding, the following will be explained in conjunction with Table 2.

[0046] Table 2. Schematic diagram of one type of influence factor Referring to Table 2, in specific embodiments, the multi-dimensional influencing factors may include, but are not limited to, timeliness urgency, cargo vulnerability, economic loss, and contractual binding force. Simultaneously, corresponding weights are pre-set for different influencing factors. As shown in Table 2, cargo vulnerability is the dimension of greatest concern to customers during cargo transportation; therefore, its weight is set to the highest during pre-setting.

[0047] Of course, in an optional embodiment, the weights corresponding to the multi-dimensional impact factors can be dynamically adjusted according to actual business needs and the urgency of each dimension. This application does not limit the setting of the weights. Based on the impact factors and weights in the table above, the initial sensitivity coefficient can be obtained by weighted calculation according to formula (1): (1) Furthermore, considering that drivers can dynamically negotiate delivery times with customers, in one optional embodiment, when a vehicle malfunctions, an interactive interface pops up simultaneously with the vehicle malfunction alarm to collect interactive information representing the driver's intentions. Referring to Table 1, the interactive information can be voice commands input by the driver or commands collected when the touchscreen is triggered; this application does not limit this.

[0048] Furthermore, the initial sensitivity coefficient is corrected according to the driver's intention to obtain the final sensitivity coefficient. Specifically, a correction factor is determined based on the interaction information to correct the initial sensitivity coefficient. Table 3 is a mapping table of interaction information and correction factors provided in the embodiments of this application.

[0049] Table 3 shows the mapping relationship between interactive information and correction factors. In an optional embodiment, when the driver's input interaction information represents a priority delivery intention, such as the interaction information in Table 3 indicating priority delivery or an urgent intention expressed verbally, the corresponding correction factor is... The value is positive. When the interaction information represents a priority for repairing the car, such as the interaction information in Table 3 that prioritizes repairing the car or expresses a relaxed intention through voice, the corresponding correction factor is... It is a negative number.

[0050] Furthermore, when the interactive information is unresponsive (i.e., empty), the correction factor is zero, meaning the initial sensitivity coefficient is not corrected. Alternatively, if the current fault type is a blocking fault indicating that the vehicle cannot continue driving, regardless of the driver's choice, the vehicle is forced to stop on the spot and wait for assistance; in other words, the interactive information does not participate in the correction of the sensitivity coefficient.

[0051] In one alternative embodiment, a correction factor is determined. Subsequently, as an optional embodiment, the initial sensitivity coefficient is corrected according to formula (2) to obtain the final sensitivity coefficient: (2) in, To finally pass the correction factor Corrected sensitivity coefficient, This is the initial sensitivity coefficient.

[0052] Therefore, by introducing a driver intent correction factor, the decision-making logic can incorporate human experience and judgment, avoiding extreme misjudgments caused by relying entirely on algorithms. At the same time, it sets up a safety net for disruptive failures, ensuring absolute safety and improving the overall reliability of freight transportation.

[0053] In one alternative embodiment, the logistics data includes the waybill SLA level and the delivery deadline; determining the time urgency includes: The available time margin for transportation is determined based on the vehicle's departure time, current system time, and estimated travel time from the current location to the unloading location. The total time window for transportation is determined based on the departure time and the deadline for signing for receipt. The basic values ​​characterizing the urgency of transportation are determined by using available time margin and total time window; Based on the preset acceleration factor mapping relationship, the target acceleration factor corresponding to the SLA level of the waybill is determined; the target acceleration factor is used to characterize the user's requirement for timeliness. The timeliness is obtained by correcting the base value using the target acceleration factor.

[0054] It should be noted that the time urgency is used to measure the remaining time in the current system before the acceptance deadline, that is, to characterize the urgency of the goods' acceptance. In an optional embodiment, the time urgency can be determined according to formula (3): (3) Table 4 is a schematic table of relevant parameters for determining the urgency of timeliness provided in the embodiments of this application. The following will refer to Table 4 to explain the above-mentioned determination of urgency of timeliness. Please provide an explanation.

[0055] Table 4 is a schematic table of relevant parameters for determining the urgency of a time-sensitive matter. Referring to Table 4 and Formula (3), in a specific embodiment, based on the vehicle's departure time... Current system time Estimated travel time from current location to unloading location This allows us to determine the available time slack for transportation. Simultaneously, based on the departure time... and the deadline for signing for receipt This allows us to determine the total time window for vehicle transportation.

[0056] Therefore, based on the available time slack and the total time window, a basic value for transportation urgency can be calculated, namely... The basic value representing urgency.

[0057] Furthermore, in an optional embodiment, in order to more accurately determine the urgency of the deadline... The calculation process incorporates differences in users' timeliness needs. Specifically, it incorporates the acceleration factor of the service level described in Table 4, which is used to integrate users' timeliness needs into the timeliness urgency level. In the calculation, different users and different goods application scenarios have different levels of urgency regarding timeliness. For example, for cold chain goods and large general goods, users have higher requirements for the timeliness of cold chain goods. Therefore, in calculating the urgency of timeliness... In order to improve accuracy, it is necessary to comprehensively consider the user's requirements for timeliness.

[0058] In one optional embodiment, a pre-established correspondence between different waybill SLA levels and acceleration factors is obtained, resulting in an acceleration factor mapping relationship. This allows for direct retrieval of the waybill's SLA level during subsequent use, and searching for the corresponding acceleration factor within the acceleration factor mapping relationship. Table 5 is a schematic diagram of an acceleration factor mapping relationship provided by an embodiment of this application. For ease of understanding, the following explanation will be based on Table 5.

[0059] Table 5 is a schematic diagram of an acceleration factor mapping relationship. Referring to Table 5, in one optional embodiment, waybills are pre-classified into multiple levels based on different timeliness requirements, and corresponding typical scenarios are matched. Furthermore, different acceleration factors are also set accordingly. In a specific embodiment, the acquired logistics data may include the waybill SLA level, and the corresponding target acceleration factor can be determined based on Table 5. Further, referring to formula (3), the base value of transportation urgency is corrected using the target waybill SLA level to obtain the final timeliness urgency. .

[0060] As shown in Table 5, different SLA levels for waybills have different timeliness requirements. The higher the timeliness requirement, the larger the acceleration factor, and the more urgency needs to be emphasized. For example, as shown in Table 5, when the waybill SLA level is S, and the typical scenario is an urgent medical shipment, the timeliness requirement is extremely high, necessitating a strong emphasis on urgency. Magnification is performed, and the acceleration factor at this time maximum.

[0061] It should be noted that Table 5 above is an example of an acceleration factor mapping relationship. This application specifies the classification levels and number of waybill SLA levels, and the corresponding acceleration factors. The specific values ​​are not limited and can be set according to actual business needs.

[0062] In addition, it should be noted that when When the time urgency is ≤0 (in the case of immediate order placement), It can be directly set to 1, which is considered an extremely short and urgent case. In specific embodiments, the calculation results are uniformly Clamped to the interval [0, 1]. Clamp refers to a function used to restrict values ​​to a specified range.

[0063] Therefore, by converting service level agreements into acceleration factors, it is possible to differentiate the timeliness needs of different customers, enabling high-timeliness orders to receive higher urgency scores and thus prioritize them in decision-making.

[0064] In one alternative embodiment, the logistics data includes cargo categories; determining cargo vulnerability includes: Based on the preset decay period mapping relationship, the target decay value corresponding to the category of goods is determined; the target decay value is the time required for the quality of goods to decrease to a preset percentage threshold after being removed from ideal storage conditions. Determine the basic vulnerability of the cargo based on the target attenuation value; Determine whether the type of fault affects ideal storage conditions; If so, determine the deviation parameter used to characterize the degree of deviation between the actual environment and the ideal environment; based on the deviation parameter, determine the coupling factor used to couple the fault with the cargo protection environment; and determine the cargo vulnerability through the coupling factor and the basic vulnerability.

[0065] If not, use the basic vulnerability as the cargo vulnerability.

[0066] In a specific embodiment, cargo vulnerability is used to measure the cargo's tolerance to time delays and environmental deviations. In determining cargo vulnerability, the concept of attenuators is introduced to enable detailed modeling of cargo types. Specifically, an attenuator mapping relationship is pre-built, which corresponds to cargo categories and attenuation values. The attenuation value refers to the time required for the quality of the cargo to decrease to a preset percentage threshold after being removed from ideal storage conditions. For example, the time required for the quality of the cargo to drop to 50% of the acceptable standard after being removed from ideal storage conditions. This application does not limit the preset percentage threshold; it can be set according to actual business needs. Specifically, a higher percentage threshold can be set for cargoes with faster quality degradation rates; for example, the percentage threshold for strawberries can be higher than that for apples.

[0067] Table 6 is a schematic table of a decay period mapping relationship provided in the embodiments of this application. For ease of understanding, the following will be explained in conjunction with Table 6.

[0068] Table 6 is a schematic diagram of a decay period mapping relationship. See Table 6 for the attenuation values ​​corresponding to different product categories. Different, attenuation value The shorter the length, the weaker the cargo. Based on the table above, you can quickly look up the attenuation value corresponding to the cargo currently being carried in the vehicle. It should be noted that Table 6 above is an illustrative table. In specific embodiments, the above table (i.e., the decay period mapping relationship) can be updated by deleting, adding, and modifying according to actual business needs.

[0069] Furthermore, in an alternative embodiment, based on a fundamental vulnerability of the cargo that can be determined, see formula (4): (4) in, The reference mapping constant is a constant that can be set according to actual business needs. In an optional embodiment, it can be set to 8. Table 7 is a schematic table of relevant parameters for determining basic vulnerability provided by an embodiment of this application. For ease of understanding, the following explanation will be based on Table 7.

[0070] Table 7 is a schematic table of relevant parameters for determining basic vulnerability. Refer to Table 7 to determine. At that time, determine the attenuation value according to Table 6. Further calculations are performed using formula (4).

[0071] In an alternative embodiment, if the current vehicle malfunction does not affect the ideal storage conditions for the goods, then the goods can be directly... Calculate the initial sensitivity coefficient The fragility of the cargo. Of course, in another alternative embodiment, if the type of failure affects ideal preservation conditions, characterizing the rate of cargo decay will accelerate, then it is necessary to... Building upon this foundation, we further couple failure factors with cargo environmental factors to improve the accuracy of cargo vulnerability calculation.

[0072] Specifically, in one alternative embodiment, the final cargo vulnerability is calculated according to formula (5): (5) in, For the final cargo vulnerability. This is a coupling factor used to couple faults with the cargo protection environment. In a specific embodiment, vulnerability is amplified when the fault type affects the core protection conditions of the cargo (such as air conditioning failure for cold chain cargo). In an optional embodiment, the coupling factor can be calculated according to formula (6). : (6) Table 8 is a schematic table of relevant parameters for determining the coupling factor provided in the embodiments of this application. The meaning of the letters in formula (6) will be explained in conjunction with Table 8.

[0073] Table 8 is a schematic table of relevant parameters for determining the coupling factor. As can be seen from Table 8, A deviation parameter is used to characterize the degree of deviation between the actual environment and the ideal environment. This refers to the environmental deviation threshold for the type of goods. Therefore, in a specific embodiment, sensors installed in the cargo container collect real-time environmental parameters of the goods' storage environment, such as temperature values, and further calculate deviation parameters based on the collected data. .

[0074] In a specific embodiment, different threshold values ​​can be pre-set for different categories of goods. This yields a threshold mapping relationship. Based on this mapping relationship, the critical threshold corresponding to the current product category can then be determined. Therefore, the coupling factor can be calculated according to formula (6). And calculate the final cargo vulnerability according to formula (5). .

[0075] It should be noted that in calculating the coupling factor... At that time, the environmental coupling strength is based on the environmental coupling strength coefficient. To determine this coefficient, a corresponding mapping relationship can be pre-set for different product categories, and the calculation will be performed based on this mapping relationship. Furthermore, a non-linear adjustment index will be introduced during the calculation process. This index can be set according to actual business needs, and this application does not impose any restrictions on it.

[0076] Furthermore, it should be noted that when the vehicle carries multiple types of cargo, the cargo vulnerability is determined according to the above calculation method. At that time, the category with the lowest sensitivity is prioritized. For example, for apples and strawberries, the calculation results for strawberries are prioritized.

[0077] Therefore, by introducing the concept of decay period, we can achieve fine modeling at the product level, and use the fault-environment coupling factor to amplify the impact of faults on vulnerable goods, so that the decision results of the same fault are differentiated for different goods, avoiding misjudgment by "one-size-fits-all" and improving transportation reliability.

[0078] In one optional embodiment, the logistics data includes loss impact parameters; the loss impact parameters include the value of the goods, contract penalties, and insurance coverage; determining the degree of economic loss includes: Obtain historical loss statistics for the vehicle; these historical loss statistics include the historical loss mean and the historical loss standard deviation. Based on the preset maintenance time mapping relationship, determine the standard maintenance time corresponding to the fault type; Determine the probability of cargo damage due to delays by using standard repair time; Based on the probability of cargo damage and the parameters of loss impact, determine the potential economic loss; Based on historical loss statistics, the potential economic loss is normalized to obtain the economic loss degree.

[0079] In a specific embodiment, the economic loss degree is used to characterize the extent of economic loss caused by delayed delivery of goods; the higher the economic loss degree, the greater the extent of economic loss. In an optional embodiment, the economic loss degree can be determined according to formulas (7) to (9): (7) (8) (9) Table 9 is a schematic table of relevant parameters for determining the degree of economic loss provided in the embodiments of this application. The above formulas (7) to (9) and the process of determining the degree of economic loss will be described below in conjunction with Table 9.

[0080] Table 9 is a schematic table of relevant parameters for determining the degree of economic loss. In a specific embodiment, for different vehicle fault types, corresponding standard repair times can be preset, that is, a correspondence between fault types and standard repair times can be constructed to obtain a repair time mapping relationship, wherein the standard repair time is an estimated time within the industry.

[0081] This allows us to establish a repair time mapping relationship, determine the standard repair time corresponding to the current vehicle fault type, and further estimate the expected delay time based on the standard repair time. In order to determine the probability of cargo loss due to delay according to formula (9). .

[0082] Refer to Table 9 and Formula (8) for the probability of cargo damage. Value of goods liquidated damages and insurance coverage amount Potential economic losses can be determined. Furthermore, according to formula (7), the potential economic loss... After normalization, the final economic loss is obtained. .

[0083] Therefore, by normalizing the potential economic losses using historical loss distribution, the degree of economic loss is made comparable across goods of different values. At the same time, by incorporating factors such as cargo damage probability, penalties, and insurance, the economic consequences of delays can be comprehensively quantified, further improving the reliability of vehicle transportation.

[0084] In one alternative embodiment, the logistics data includes contract terms and customer information; determining the degree of contractual binding includes: Obtain the vehicle's historical performance information; Based on the preset constraint mapping relationship, the constraint influence factors that characterize the degree of contract constraint are determined; the constraint influence factors include rigidity factors corresponding to contract terms, level factors corresponding to customer information, and performance factors corresponding to historical performance information. Based on preset weight coefficients, the constraint influence factors are weighted and summed to obtain the contract constraint degree; Among them, the rigidity factor is used to characterize the rigidity of the contract terms on the timeliness of receipt; the grade factor is used to characterize the importance of the customer; the performance factor is used to characterize the performance of the vehicle; when the historical performance information indicates that the vehicle has been delayed within a specified historical period, the performance factor is the largest.

[0085] In a specific embodiment, three dimensions of constraint influence factors—rigidity factor, grade factor, and performance factor—are introduced to calculate the contract constraint degree. In an optional embodiment, the contract constraint degree can be calculated according to formula (10): (10) Table 10 is a schematic table of relevant parameters for determining the degree of contractual constraint provided in the embodiments of this application. The determination of the degree of contractual constraint will be explained below in conjunction with Table 10 and formula (10).

[0086] Table 10 is a schematic table of relevant parameters for determining the degree of contractual binding. Referring to Table 10, in specific embodiments, corresponding weight coefficients are pre-set for different constraint influencing factors. In one optional embodiment, the weight coefficient corresponding to the rigid factor corresponding to the contract terms is the largest. Of course, this application does not limit the weight coefficients for different constraint influencing factors and can set them according to actual business needs.

[0087] Furthermore, it should be noted that the specific values ​​of different influence factors under different constraint influence factors are only an example in Table 10 and can be set according to actual needs. The contract constraint degree can be calculated according to formula (10). .

[0088] It is worth noting that, as shown in Table 10, when vehicle delays occur, a higher performance factor needs to be set to prevent further delays and thus ensure vehicles do not arrive late again. Specifically, the performance factor is maximized when historical performance information indicates vehicle delays within a specified historical timeframe.

[0089] Therefore, incorporating contract rigidity, customer level, and historical performance credit into the constraint quantification, and giving high-value customers and rigid contract constraints greater weight in decision-making, can reduce economic losses.

[0090] In one alternative embodiment, the vehicle data includes fault codes; determining the estimated repair time includes: Determine the fault type based on the fault code; Based on the preset fault mapping relationship, determine the basic maintenance time corresponding to the fault type; Determine the repair influencing factors for repair shops within a specified range; these factors include technical proficiency, waiting time, and parts availability. Based on the basic repair time and repair influencing factors, the estimated repair time for each repair shop is determined.

[0091] In a specific embodiment, a fault mapping relationship is pre-constructed, which is a correspondence between fault types and basic repair times. Based on this correspondence, the basic repair time corresponding to the fault type currently occurring in the vehicle can be determined, so that the estimated repair time of each repair shop can be determined according to the basic repair time. Table 11 is a schematic table of a fault mapping relationship provided by an embodiment of this application, and the following will be explained in conjunction with Table 11.

[0092] Table 11 is a schematic diagram of a fault mapping relationship. Table 11 schematically lists several correspondences. The current fault type of the vehicle can be determined based on the DTC, and the basic repair time can be determined based on this table. This application does not impose specific limitations on the above fault mapping relationship, and the corresponding relationship can be updated by adding, deleting, and modifying according to actual business needs.

[0093] Furthermore, the repair influencing factors of repair shops within a specified range are obtained. This specified range can be a circular area with a specified radius (e.g., 5 kilometers) centered on the vehicle's current location, or it can be a specified administrative region where the vehicle is located, such as the county where the vehicle is located. This application does not specifically limit the specified range. In addition, it should be noted that the repair influencing factors may include, but are not limited to, technical proficiency factors, queuing factors, and parts waiting factors. Table 12 is a schematic table of relevant parameters for determining the estimated repair time of repair shops provided in an embodiment of this application. The following explanation will be based on Table 12.

[0094] Table 12 is a schematic table of relevant parameters for determining the estimated repair time at a repair shop. Referring to Table 12, in one alternative embodiment, the skill proficiency factor... The value ranges from 0.6 to 1.5. A larger value indicates more skilled technicians and faster repair speeds. This application does not limit the range of values. Regarding the queuing factor... The calculation can be performed according to the formula given in Table 12. In a specific embodiment, the number of vehicles currently queuing for repairs at the repair shop is obtained in order to determine the queuing waiting factor. .

[0095] In an alternative embodiment, for the accessory waiting factor Parts mapping relationships can be pre-built, for example, see Table 12. When parts are sufficient, the parts waiting factor can be set. A value of 1 indicates a longer waiting time for parts, and the higher the corresponding parts waiting factor. The larger.

[0096] Based on the above, in an optional embodiment, the estimated repair time for different repair shops can be determined according to formula (11): (11) Therefore, by combining fault type, store technical capabilities, queuing status and parts availability to predict repair time, a basis is provided for the selection of subsequent target strategies, further improving the reliability of vehicle transportation.

[0097] Figure 3 This is a schematic diagram illustrating the principle of a target determination strategy provided in an embodiment of this application. In an optional embodiment, the transportation and maintenance strategy set includes on-site parking, delivery before repair, quick repair before delivery, and repair before delivery; the fault types include blocking faults that indicate the vehicle cannot continue to drive and functional faults that indicate the vehicle can continue to drive. Based on the assessment information, target strategies are determined from a pre-set set of transportation maintenance strategies, including: When the fault type is a blocking fault, the target strategy is to stop in place; When the fault type is a functional fault, perform the following steps: If the sensitivity coefficient is greater than or equal to the first threshold, the target strategy is to send the sample first and then repair it. If the sensitivity coefficient is less than or equal to the second threshold, the target strategy is to repair first and then send; if the first threshold is greater than the second threshold. If the sensitivity coefficient is between the first threshold and the second threshold, determine whether the sum of the estimated travel time from the repair shop to the unloading location and the estimated repair time is less than the remaining time between the current system time and the deadline for signing. If the size is less than the target size, the strategy is to repair quickly and then send it back for repair. If it is not less than, the target strategy is to send the sample first and then repair it.

[0098] In a specific embodiment, such as Figure 3 As shown, after a vehicle malfunctions, multi-source perception data is acquired, and the current fault type is determined based on the DTC in the multi-source perception data. If the current fault type is an interruption fault, it means that the vehicle can no longer continue to drive and can only stop on the spot to wait for rescue, that is, the target strategy is to stop on the spot.

[0099] If the fault type is a functional fault, then a sensitivity coefficient is required. The decision to prioritize vehicle repair or delivery is based on a comprehensive assessment of the estimated repair time. Table 13 is a schematic diagram of sensitivity coefficient level settings provided in an embodiment of this application. For ease of understanding, the following explanation will be based on Table 13.

[0100] Table 13 is a schematic diagram of the sensitivity coefficient level settings. like Figure 3 As shown, in a specific embodiment, the sensitivity coefficient is determined first. The criteria are: whether it is greater than or equal to the first threshold, or less than or equal to the second threshold, or between the second and first thresholds, where the first threshold is greater than the second threshold. For ease of understanding, we will use an example with a first threshold of 0.7 and a second threshold of 0.4.

[0101] See Table 13 and Figure 3 When the sensitivity coefficient When the sensitivity level is ≥0.7, the sensitivity level of the current goods is high (for example, it may be perishable goods such as strawberries), which means that the goods are very likely to suffer high economic losses due to delayed delivery. In other words, the priority of delivery is higher than that of repair. At this time, the target strategy is to deliver first and then repair.

[0102] When the sensitivity coefficient When the sensitivity level is ≤0.4, the sensitivity level of the goods is low (for example, it may be goods that are not easily perishable, such as pumpkins). This means that the economic loss caused by the delay in delivery is relatively low. At this time, it is advisable to repair first and then deliver the goods. That is, the target strategy is to repair first and then deliver.

[0103] When the value is between 0.7 and 0.4, i.e. 0.4 < If the sensitivity is less than 0.7, the sensitivity level of the goods is medium. In this case, the final strategy needs to be determined in conjunction with the estimated repair time. That is to say, at medium sensitivity, one can choose to deliver the goods first or repair them first. At this time, the influencing factor of the estimated repair time can be introduced to comprehensively determine the final target strategy. Table 14 is a schematic table of condition combinations for determining the target strategy provided by the embodiments of this application. For ease of understanding, the following will be explained in conjunction with Table 14.

[0104] Table 14 is a schematic diagram of a combination of conditions for determining a target strategy. See Figure 3 According to Table 14, when 0.4 < When the value is less than 0.7, calculate the estimated repair time for the repair shop. And determine the estimated travel time from the repair shop to the unloading location. Compared with the estimated repair time Is the sum less than the current system time? Deadline for signing The remaining time.

[0105] when At that time, among them, This indicates that even after the vehicle has been repaired, it can still be delivered by the deadline. Previously, goods were delivered on time, so the target strategy was to prioritize quick repair before delivery. It is understandable that in this embodiment, the addition of the quick repair-before-delivery mode is chosen when repair time is short and repairs are completed promptly. This ensures the vehicle is back to normal operation by the time of delivery, guaranteeing vehicle safety while avoiding economic losses due to delayed delivery.

[0106] when This indicates that if repairs are carried out before delivery, the delivery deadline will have passed. If the repair cannot be completed, it will lead to timeouts and potential economic losses. Therefore, the target strategy at this time is to send the item for repair first and then repair it.

[0107] Therefore, based on the sensitivity coefficient stratification, the repair time prediction is further used to achieve a refined differentiation between "fast repair and then delivery" and "delivery first and then repair", so that short-term revision orders can be repaired first and then delivered, avoiding unnecessary detours.

[0108] In one alternative embodiment, the onboard data includes battery state of charge and battery rated capacity; If the target strategy is to deliver first and repair later, before controlling the vehicle to perform the cargo transportation task based on the target strategy, the following steps are also included: The available energy of the vehicle is determined based on the battery state of charge and the battery's rated capacity. Determine the energy consumption per unit mileage of a vehicle under fault conditions; Based on the energy consumption per unit mileage under fault conditions, determine the energy consumption required for the vehicle to travel on each travel segment; the energy consumption includes the first energy consumption of the first travel segment from the current location to the unloading location, and the second energy consumption of the second travel segment from the unloading location to the repair shop; Determine whether the repair shops include energy-accessible shops that meet the energy consumption conditions; the energy consumption conditions are that the sum of the first energy consumption and the second energy consumption is less than the available energy. If included, the target stores for carrying out cargo transportation tasks are identified from the energy-accessible stores; If not, switch the target strategy to "repair first, then deliver"; and identify the target store to perform the goods transportation task from the repair stores.

[0109] Under the target strategy of "deliver first, repair later," the total vehicle mileage includes the first segment from the current location to unloading and the second segment from the unloading location to the repair shop. Due to the long total mileage and the vehicle malfunction, it is necessary to ensure that the vehicle's available energy can complete both segments. Therefore, energy verification of the vehicle is required under this condition. It should be noted that, referring to the description in the above embodiment, the repair shop refers to a shop within a specified range.

[0110] Specifically, based on the vehicle data and The remaining available energy of the vehicle is determined. In one optional embodiment, the available energy is... At the same time, since the vehicle is in a faulty state, it is necessary to determine the energy consumption per unit mileage under fault conditions in order to determine how much energy is required for each of the two travel segments.

[0111] It should be noted that since the vehicle is fully loaded during the first travel segment, and unloaded during the second travel segment, it is now empty. It is understandable that the energy consumption of the vehicle varies greatly under different load conditions. Therefore, when performing energy verification, the energy consumption is divided into two stages for calculation. For details, please refer to formula (12). (12) in, This refers to the energy consumption required for a vehicle to travel on each segment of its journey. As the primary energy consumer, This is the second largest energy consumption.

[0112] like Figure 3 As shown, when there are repair shops... When the energy is available to the store, it indicates that a repair store can support a "deliver first, repair later" strategy; that is, the distance to the repair store and the vehicle's current remaining energy are sufficient to allow the vehicle to deliver the goods first and then repair them. At this point, if... Figure 3 As shown, the strategy of prioritizing delivery and generating a route is maintained, while the target store for final repair is selected from the energy-accessible stores.

[0113] If the repair shop does not meet the requirements When the energy can reach the store, it means that all repair stores are too far away. If delivery is made first and then repairs are done, the vehicle may run out of energy and become unable to drive before reaching the repair store. Therefore, if Figure 3 As shown, the target strategy is then switched from "send first, repair later" to "repair first, send later," and the target store for final repair is selected from all repair stores.

[0114] Therefore, by dividing the triangular path into two segments—fully loaded delivery and empty repair—and calculating energy consumption separately, the accessibility of energy during the entire vehicle's journey can be guaranteed.

[0115] Based on the above embodiments, as an optional embodiment, determining the energy consumption per unit mileage of a vehicle under fault conditions includes: Obtain the normal energy consumption per unit mileage of the vehicle under normal conditions; Based on the pre-built energy consumption correction mapping relationship, determine the target energy consumption correction coefficient corresponding to the fault type; The energy consumption per unit mileage under fault conditions is determined based on the energy consumption per unit mileage under normal conditions and the target energy consumption correction factor.

[0116] In a specific embodiment, the energy consumption per unit mile of the vehicle is closely related to the fault type. Therefore, when determining the energy consumption per unit mile under fault conditions, an energy consumption correction coefficient related to the fault type is introduced. In an optional embodiment, the energy consumption per unit mile under fault conditions can be calculated according to formula (13): (13) Table 15 is a schematic table of relevant parameters for determining the energy consumption per unit mileage in a fault state, provided in an embodiment of this application. The following will be explained in conjunction with Table 15.

[0117] Table 15 is a schematic table of relevant parameters for determining energy consumption per unit mileage in a fault state. As shown in Table 15 and Formula (13), the energy consumption per unit mileage under fault conditions is calculated. At that time, it is necessary to obtain the energy consumption per unit mileage of the vehicle under normal conditions. In a specific embodiment, the energy consumption per unit mileage under normal conditions is... These are vehicle parameters that can be obtained directly.

[0118] Different fault types correspond to different energy consumption correction factors. In one optional embodiment, the correspondence between different fault types and energy consumption correction factors can be pre-set. Table 16 is a schematic table of an energy consumption correction mapping relationship provided by an embodiment of this application.

[0119] Table 16 is a schematic diagram of an energy consumption correction mapping relationship. Refer to Table 16 to set corresponding energy consumption correction factors for different fault types. Energy consumption per unit mileage under fault conditions At that time, the mapping relationship is queried to determine the target energy consumption correction coefficient corresponding to the current vehicle fault type, so as to calculate the energy consumption per unit mileage under fault conditions according to formula (13). .

[0120] Therefore, by mapping fault codes to energy consumption correction coefficients, it is possible to quickly estimate energy consumption per unit mileage under fault conditions without the need for complex vehicle dynamics models, thus providing a fast response and saving computing resources.

[0121] Based on the above embodiments, as an optional embodiment, the energy consumption required for the vehicle to travel on each journey segment is determined according to the energy consumption per unit mileage under fault conditions, including: Obtain current weather information and terrain information of the area where the vehicle is located; Based on the preset redundancy mapping relationship, the weather redundancy coefficient corresponding to weather information, the terrain redundancy coefficient corresponding to terrain information, and the load redundancy coefficient corresponding to each travel segment; the full load redundancy coefficient of the first travel segment is greater than the empty load redundancy coefficient of the second travel segment. Based on the preset energy consumption factor mapping relationship, the auxiliary energy consumption factor corresponding to each travel segment is determined; the auxiliary energy consumption factor is used to characterize the degree of influence of the vehicle auxiliary system operating status on the energy consumption per unit mileage; the first energy consumption factor of the first travel segment is greater than the second energy consumption factor of the second travel segment. The safety redundancy factor for each travel segment is determined based on the weather redundancy coefficient, terrain redundancy coefficient, and load redundancy coefficient. Energy consumption is determined based on the energy consumption per unit mileage under fault conditions, the auxiliary energy consumption factor, and the safety redundancy factor.

[0122] In a specific embodiment, the energy consumption of vehicle driving is closely related to factors such as weather, terrain, load conditions and fault type. Therefore, in order to accurately calculate the energy consumption required for the vehicle to travel in the first and second travel segments, thereby improving the accuracy of subsequent target strategy determination, the influence of the above factors will be comprehensively considered when calculating energy consumption.

[0123] In an alternative embodiment, the first energy consumption is calculated according to formula (14), and the second energy consumption is calculated according to formula (15): (14) (15) Table 17 is a schematic table of relevant parameters for determining energy consumption provided in the embodiments of this application. For ease of understanding, the following explanation will be based on Table 17.

[0124] Table 17 is a schematic table of relevant parameters for determining energy consumption. As shown in Table 17, the first energy consumption during the first stroke segment is... Introducing a safety redundancy factor in the calculation Second energy consumption in the second stroke segment Introducing a safety redundancy factor in the calculation It should be noted that the safety redundancy factor... This is used to incorporate weather, terrain, and load conditions into energy consumption calculations. In addition, the impact of different fault types on energy consumption needs to be considered; therefore, an auxiliary energy consumption factor is introduced when calculating energy consumption for different travel segments.

[0125] As shown in Table 17, in one optional embodiment, auxiliary energy consumption factors corresponding to different travel segments are pre-constructed to obtain an energy consumption factor mapping relationship. Based on this mapping relationship, the auxiliary energy consumption factors for different travel segments can be directly obtained. For example, for the first travel segment where the vehicle is fully loaded and the engine is running at full power when cold, the auxiliary energy consumption factor is... The maximum value can be obtained, for example, it can be set to 1.25. During the second stroke, the vehicle's engine shuts off when cold, at which point the auxiliary energy consumption factor can be used. It can take the value 1.

[0126] Table 18 is a schematic table of a redundancy mapping relationship provided in the embodiments of this application. The load redundancy coefficient will be explained below with reference to Table 18.

[0127] Table 18 is a schematic diagram of a redundant mapping relationship. In an alternative embodiment, the safety redundancy factor can be calculated according to formula (16): (16) in, Safety redundancy factor, including full load redundancy coefficient. and no-load redundancy coefficient .

[0128] As shown in Table 18, in specific embodiments, the weather redundancy coefficients corresponding to different weather conditions are... Unlike other conditions, vehicles consume more energy when the weather is cold, therefore the weather redundancy factor is higher. The maximum value is taken. Similarly, different terrain redundancy coefficients correspond to different terrain types. The difference lies in the terrain redundancy coefficient. When a vehicle is in a mountainous area, there are many uphill sections, resulting in greater energy consumption. maximum.

[0129] For different load capacities, it is understandable that the heavier the vehicle load, the greater the energy consumption. The load redundancy coefficient is determined based on the redundancy mapping relationship shown in Table 18. At that time, the full-load redundancy coefficient of the first travel segment is greater than the no-load redundancy coefficient of the second travel segment.

[0130] Therefore, based on the redundancy mapping relationship shown in Table 18, the weather redundancy coefficient is determined. Terrain redundancy coefficient and load redundancy factor The safety redundancy factor is further determined according to formula (16). .

[0131] Furthermore, see Table 17, and formulas (14) and (15), based on the energy consumption per unit mileage in the fault state. Auxiliary energy consumption factor and redundancy factor Determine the energy consumption for different travel segments (i.e., determine the first energy consumption). Second energy consumption ).

[0132] Therefore, by comprehensively considering multiple factors such as weather, terrain, load, and auxiliary systems, the safety redundancy of energy consumption in each segment is dynamically calculated, making energy verification closer to the actual operating environment, improving the accuracy of energy consumption verification, and thus ensuring the accuracy and reliability of subsequent target strategies.

[0133] Figure 4 This is a schematic diagram illustrating the principle of determining a target store, provided as an embodiment of this application. In one optional embodiment, determining the target store for performing the goods transportation task includes: The system filters energy-accessible stores or repair shops to obtain candidate stores; the filters include business status, repair qualifications, and parts availability. Each candidate store was evaluated across multiple dimensions, resulting in a multi-dimensional score. These dimensions included repair capability, logistics fulfillment, parts availability, and repair speed. Based on the preset scenario factor mapping relationship, the scenario weights corresponding to the target strategy are determined; the scenario weights include maintenance capability weight, fulfillment weight, spare parts weight, and maintenance speed weight. Based on scenario weights, the multi-dimensional scores are weighted and summed to obtain the comprehensive score of each candidate store. The first specified number of stores in the descending order of the comprehensive scores will be selected as the target stores.

[0134] First, it should be noted that, based on the description of the above embodiments, after energy verification, there may be energy-accessible stores or no energy-accessible stores among the repair shops within the specified range. Therefore, when filtering target stores, it may be from energy-accessible stores or from all repair shops. For ease of understanding, the following will combine... Figure 4 Please provide an explanation.

[0135] Figure 4 As shown, all repair shops within a specified range are grouped into a shop set. After the energy verification in the above embodiments, the repair shop This may or may not include energy-accessible stores. Regardless of energy accessibility, vehicle repairs are required, meaning it's necessary to screen for target stores that can be used for repairs.

[0136] Table 19 is a schematic table illustrating a specified filtering method provided in an embodiment of this application. In a specific embodiment, the stores to be filtered are... The screening process is divided into two stages, such as Figure 4 As shown in Table 19, the first stage includes energy verification and designated screening, while the second stage is screening based on comprehensive scoring. The following explanation will be based on Table 19.

[0137] Table 19 is an example of a specified filter. In the above embodiments, based on and available energy First, the repair shops Energy accessibility was verified. If the verification passed, it indicates that there are stores with energy accessibility under the "deliver first, repair later" strategy. In this case, target stores are further filtered from those stores. Of course, if no stores have energy accessibility, then all repair stores need to be considered. Target stores are selected from the middle.

[0138] Whether it's an energy-accessible store or any repair shop All of these require specific screening processes, including screening for business status, repair qualifications, and parts availability. These screenings can be understood as the first stage of rigorous conditional screening. This involves reviewing various repair shops... In, such as Figure 4 As shown, if the specified filter fails, the corresponding stores will be deleted.

[0139] If the specified screening passes, the store will be designated as a candidate store and enter the second stage of comprehensive scoring screening. Table 20 is a schematic table of relevant parameters for determining the comprehensive score provided by an embodiment of this application. Specifically, in an optional embodiment, each candidate store is scored in multiple dimensions to obtain multiple dimension scores, including repair capability score, logistics fulfillment score, parts guarantee score, and repair speed score.

[0140] Table 20 is a schematic table of relevant parameters for determining the comprehensive score. Referring to Table 20, when comprehensively scoring candidate stores, scores are calculated from multiple dimensions, and corresponding weights are assigned to the scores of different dimensions so that a comprehensive score can be obtained by weighted summation. In an optional embodiment, the comprehensive score is calculated according to formula (17): (17) The meanings of the symbols in the formulas are shown in Table 20. It should be noted that the scene weights differ under different strategies; therefore, it is necessary to identify the current scene, i.e., identify the target strategy, based on the strategy representation. Users can define their own strategy identifiers, for example, assigning identifier A to on-site parking and identifier B to drop-off-then-repair. This application does not impose any limitations on the identifier settings.

[0141] Furthermore, the comprehensive score of each candidate store under the target strategy is determined according to formula (17). ,like Figure 4 As shown, the overall score Sort the stores and select the top 3 stores as target stores, for example, recommend the top 3 stores to the client so that the driver can choose the store for final repair.

[0142] Therefore, by screening repair shops through a two-stage funnel (hard filtering + multi-dimensional weighted scoring), logistics fulfillment indicators are incorporated into the evaluation system to achieve a comprehensive balance between repair capabilities and transportation guarantees.

[0143] Based on the above embodiments, as an optional embodiment, in the scene factor mapping relationship: When the target strategy is to repair first and then send, the repair capability has the largest weight in the scenario weighting. When the target strategy is quick repair followed by delivery, the repair speed has the highest weight in the scenario weighting. When the target strategy is to deliver first and then repair, the fulfillment weight is the largest among the scenario weights.

[0144] Table 21 is a schematic table of scene factor mapping relationship provided in the embodiments of this application. In the above embodiments, the comprehensive score is determined. At this time, it is necessary to determine the corresponding scene weight under the current target strategy based on the pre-built scene factor mapping relationship.

[0145] Table 21 is a schematic diagram of a scene factor mapping relationship. Specifically, as shown in Table 21, for the "repair first, then send" strategy, the main goal is to modify the original equipment. Therefore, in this scenario, the repair capability weight in the scenario weighting is... Maximum. In the scenario of repairing and then sending the item back after quick repair, the goal is to repair it as quickly as possible. In this case, the repair speed weight is the most important factor in the scenario's weighting. The maximum weight is given to the delivery-first, repair-later model. However, for the "delivery first, repair later" model, the primary goal is to deliver the goods on time; therefore, the fulfillment weight is the most important factor in the scenario weighting. maximum.

[0146] Based on the above embodiments, as an optional embodiment, the dimensional scoring also includes a distance convenience score, and the corresponding scenario weights also include a distance weight; when the target strategy is on-site parking, the distance weight is the largest; If the target strategy is delivery first, repair later, then score each candidate store based on its proximity to the customer, including: Determine the deflection angle of each candidate store; the deflection angle is the angle between the vector pointing from the current position to the unloading position with the unloading position as the vertex and the vector pointing from the unloading position to the candidate store. By adjusting the deflection angle, the total mileage of each travel segment is corrected by applying a detour penalty to obtain the corrected mileage; Based on the corrected mileage, a distance convenience score is determined.

[0147] In a specific embodiment, to select stores with more defined boundaries, refer to formula (17) when calculating the comprehensive score. At this time, a deflection penalty is introduced to select stores that are more conveniently located. Specifically, the dimensional scoring also includes a distance convenience score. Correspondingly, the scenario weights also include distance weights. See Table 21; under the on-site parking strategy, the objective is distance priority, therefore distance has the highest weight.

[0148] Understandably, when the target strategy is "delivery first, repair later," the vehicle's journey includes both the first and second travel segments, thus necessitating the introduction of a steering angle. Therefore, if... Figure 4 The red lines shown form the screening path. Under the strategy of "send first, repair later", the energy-accessible stores are first screened to obtain candidate stores. The distance of the candidate stores is then corrected. In an optional embodiment, the total mileage of each journey segment is corrected by deflection angle to obtain the corrected mileage. See formula (18). (18) in, The total distance traveled in the first and second segments is, i.e. Table 22 is a schematic table of relevant parameters for determining the correction distance provided in the embodiments of this application. The following description will be based on Table 22.

[0149] Table 22 is a schematic table of relevant parameters for determining the correction distance. Referring to Table 22, in a specific embodiment, the unloading position is taken as the vertex, and the deflection angle of each candidate store is determined based on the angle between the vector pointing from the current position to the unloading position and the vector pointing from the unloading position to the candidate store. Furthermore, the corrected mileage is determined using the above calculation formula (18). .

[0150] Furthermore, in an alternative embodiment, a distance convenience score is calculated according to formula (19). : (19) in, To correct the mileage, The maximum effective distance among the candidate stores.

[0151] Therefore, by introducing a deflection angle penalty, repair shops that are more convenient to the delivery route are prioritized, reducing detour mileage and energy consumption, and improving the overall operational efficiency of the "deliver first, repair later" model.

[0152] Based on the above embodiments, as an optional embodiment, the repair capability score is determined according to the store's repair performance indicators; the repair performance indicators include first-time repair rate, return rate, and repair time. The logistics fulfillment score is determined based on the delivery performance indicators of goods after store repairs. The delivery performance indicators include on-time receipt rate, average time-delay deviation, and damage correlation rate. Among them, the on-time receipt rate is the percentage of goods that are received on time after store repairs; the average time-delay deviation is the average percentage of overdue waybills; and the damage correlation rate is the percentage of goods damaged due to store repair delays. The parts guarantee score is determined based on a preset parts mapping relationship, which is the correspondence between the store's parts inventory and the score. Repair speed rating is determined based on estimated repair time.

[0153] In an alternative embodiment, the maintenance capability score can be determined according to formula (20): (20) Table 23 is a schematic table of maintenance performance indicators provided in the embodiments of this application. The following will be explained in conjunction with Table 23.

[0154] Table 23 is a schematic diagram of a maintenance performance indicator. As shown in Table 23, maintenance capability score The calculation is closely related to the store's one-time repair rate, return rate, and repair time. Among these, the repair time is based on the industry benchmark repair time. and actual repair time Sure.

[0155] Table 24 is a schematic table of delivery performance indicators provided in the embodiments of this application. In another optional embodiment, the logistics performance score can be determined according to formula (21): (twenty one) The meanings of the symbols in formula (21) are shown in Table 24. It should be noted that... It is the final on-time rate of the waybill associated with the repair shop service, so as to establish a causal relationship between the repair behavior and the logistics result.

[0156] Table 24 is a schematic diagram of a delivery performance indicator. Table 25 is a schematic table of a parts mapping relationship provided in an embodiment of this application. In an optional embodiment, the parts inventory quantity of each repair shop is obtained in real time, and the pre-built parts mapping relationship is updated. Referring to Table 25 below, when the Bill of Material (BOM) matches (i.e., the parts required for the current fault exist) and are sufficient, the parts guarantee score is... The highest score is awarded for [the item name]. In addition, when the BOM matches but inventory is insufficient and requires restocking, different parts availability scores are set based on the varying restocking times. The shorter the delivery time, the higher the parts availability rating. The higher the score, the better.

[0157] Table 25 is a schematic diagram of a parts mapping relationship. In the above embodiment, the estimated maintenance time is determined according to formula (11). Based on this, the maintenance speed score is calculated, see formula (22): (twenty two) in, Rate the repair speed. For stores The estimated repair time, The industry benchmark repair time can be determined according to Table 11, i.e., the industry benchmark repair time. Basic maintenance time .

[0158] Therefore, a multi-dimensional quantitative scoring system is constructed, which includes maintenance capabilities, logistics fulfillment, parts supply, and maintenance speed. The logistics fulfillment indicator establishes a causal relationship between maintenance behavior and the final acceptance result, realizing the integration of the Internet of Vehicles and the Logistics Network and improving the reliability of vehicle transportation.

[0159] Figure 5 This is a schematic diagram illustrating the principle of a vehicle transportation task control method provided in this application embodiment. Based on the above embodiment, as an optional embodiment, maintenance performance indicators and delivery performance indicators are statistically analyzed hierarchically based on preset conditions. The preset conditions include overall store conditions, fault type clusters, cargo type clusters, and receipt area clusters. The hierarchical statistics include: Obtain historical metrics; historical metrics include historical maintenance performance metrics and historical delivery performance metrics; Based on the actual receipt time of the waybill, a time decay weight is applied to the historical indicators to obtain the initial indicators; Based on the preset hierarchical structure, the system starts querying the statistical values ​​of the initial indicators from the finest level. During the query process, if the number of samples in the current level is less than the preset threshold, the system will backtrack to the previous level until the statistical values ​​that meet the preset threshold are obtained. The query conditions in the hierarchical structure are composed of preset conditions, and the finer the level granularity, the more types of preset conditions constitute the corresponding query conditions. By performing Bayesian smoothing on the statistical values, we obtain the target estimate after correcting the historical indicators.

[0160] In a specific implementation, to ensure that the evaluation results reflect the store's latest service capabilities, a time decay weighting is used to assign higher weight to recent data, thereby reducing the influence of outdated historical data. Specifically, for example... Figure 5 As shown, after the service ends, historical metrics within a specified historical period are obtained, for example, historical metrics within one month. This application does not limit the specified historical period. Table 26 is a schematic table illustrating a method for determining time decay-related parameters provided in an embodiment of this application, and will be explained below in conjunction with Table 26.

[0161] Table 26 is a schematic table for determining time decay-related parameters. It is understandable that, in specific embodiments, directly averaging the statistical repair performance indicators and delivery performance indicators cannot reflect changes in store capabilities over time (such as store technology improvements or staff turnover). Therefore, in this embodiment, a time decay coefficient is introduced. (Value is 0.0 / day, half-life is 35 days), reducing the impact of historical data on current store service evaluation.

[0162] In an alternative embodiment, the historical indicators are weighted by time decay using formula (23) to obtain the initial indicators: (twenty three) in, For the first The score for each order (1 point for on-time, 0 points for late). For the first The actual time of receipt of the pen service. This is the current system time. Therefore, service records older than the current time have a lower weight in the scoring calculation, thus ensuring that the recent performance of the store is highlighted.

[0163] It is understandable that the maintenance performance indicators and delivery performance indicators in the above embodiments need to be statistically analyzed according to a combination of multiple dimensions. However, the combination space of different signing points, goods, and faults is huge, and directly maintaining independent statistics faces the problem of insufficient samples.

[0164] Therefore, in order to solve the data sparsity problem caused by the huge combination space of different signing points, goods, and faults, such as Figure 5 As shown, clustering and dimensionality reduction are performed on the statistical dimensions, defining four levels of query conditions. Table 27 is a schematic table of a hierarchical structure provided in an embodiment of this application, which will be explained below in conjunction with Table 27.

[0165] Table 27 is a schematic diagram of a hierarchical structure. As shown in Table 27, in one optional embodiment, the hierarchy is divided into four levels. The finer the granularity of the level, the more types of preset conditions there are, and the smaller the corresponding sample size threshold. For example, the first level (Level 1) includes the most condition keys (i.e., preset condition types), while the fourth level is used as the bottom level, with no lower limit on the corresponding sample size.

[0166] In a specific implementation, the system prioritizes querying the statistical values ​​of the initial indicators starting from Level 1. If the sample size is insufficient, the system backtracks level by level. That is, the query starts from the finest level, and if the number of samples at the current level is less than a preset threshold, the system backtracks to the previous level.

[0167] After obtaining the statistical values, further steps, such as... Figure 5 As shown, Bayesian smoothing is used for processing, see formula (24): (twenty four) Table 28 is a schematic table of relevant parameters for a Bayesian smoothing process provided in the embodiments of this application. For the symbols in formula (24), please refer to Table 28.

[0168] Table 28 shows a schematic diagram of relevant parameters for a Bayesian smoothing process. See Figure 5 Once the target statistical values ​​are obtained, they can be used to influence the calculation and ranking of the next store's overall score, and more accurately reflect the latest service capabilities of each store.

[0169] Therefore, by using hierarchical backoff and Bayesian smoothing, the problem of sample sparsity under multidimensional condition combinations is solved, enabling reliable index estimation even in small sample scenarios. At the same time, time decay weighting ensures a greater impact of recent performance.

[0170] In an optional embodiment, when the target strategy is quick repair followed by delivery, the method further includes: At preset intervals, obtain feedback from stores regarding the remaining repair time; Determine whether the sum of the current system time, remaining repair time, and estimated travel time between the repair shop and the unloading location is greater than the time remaining between the current system time and the delivery deadline; If the value is greater than the target value, generate a strategy switching suggestion to switch to "send first, repair later" and output the strategy switching suggestion.

[0171] When a vehicle is performing a quick repair and delivery mission, the remaining repair time is retrieved from the store at preset intervals (e.g., every 15 minutes) to determine whether the vehicle can still deliver the goods on time.

[0172] Specifically, if To generate a strategy switching suggestion to "deliver first, repair later," this suggestion is then output via the vehicle's in-vehicle screen or voice command. The remaining repair time is as reported by the store. This represents the estimated travel time from the store to unloading. In one optional embodiment, if the driver confirms the switch, the system immediately interrupts maintenance, delivers the goods first, and then returns for maintenance. If the driver refuses, the system continues to wait for maintenance to complete.

[0173] Therefore, by dynamically monitoring the remaining time during the maintenance process, and providing early warnings and switching suggestions when it is predicted that delivery cannot be made on time, the system avoids default on goods due to maintenance delays, thereby increasing the robustness and flexibility of decision-making.

[0174] In an optional embodiment, after controlling the vehicle to perform the cargo transportation task based on the target strategy, the method further includes: Collect information on vehicle malfunction and repair status, actual receipt time, and actual repair duration; If the target fault with the same fault code recurs within a preset time period, update the first-time repair rate of the corresponding repair shop for the target fault. Compare the actual delivery time with the delivery deadline, and update the on-time delivery rate of the corresponding repair shops; Update the technical proficiency factor of the corresponding repair shop based on the actual repair time.

[0175] Based on the above embodiments, such as Figure 5 As shown, after the service ends, Collect information on vehicle malfunction and repair status, actual receipt time, and actual repair duration. If the target fault with the same fault code recurs within a preset time period (e.g., 7 days), the first-time repair rate for that target fault at the corresponding repair shop will be updated. (Recurring orders are recorded as 0, and non-recurring orders as 1). Additionally, compare the actual delivery time with the delivery deadline. If the actual receipt time is ≤ This indicates that the vehicle was delivered on time, which can be used to update the on-time acceptance rate of the corresponding repair shop. .

[0176] In another alternative embodiment, based on the actual repair time Compared with industry benchmarks The ratio can be used to update the technical proficiency factor of the corresponding repair shop. Of course, the return rate can be updated after the service is completed. Average timeout deviation Correlation rate with cargo damage These are some of the metrics. All updates are written into a conditional statistics table based on dimensions such as store, fault type, goods type, and delivery area, so that they can be used for subsequent orders.

[0177] This creates a closed loop from decision-making to execution and feedback, enabling stores to continuously iterate and optimize their repair capabilities and logistics fulfillment indicators based on actual operational data. The system has self-learning capabilities, and its decision-making accuracy continues to improve after long-term operation.

[0178] In the above embodiments, the vehicle transportation task control method has been described in detail. This application also provides an embodiment of a vehicle transportation task control device.

[0179] Figure 6 This is a schematic diagram of the structure of a vehicle transportation task control device provided in an embodiment of this application, as shown below. Figure 6 As shown, the device includes: The perception data acquisition module 60 is used to acquire multi-source perception data of the vehicle; the multi-source perception data includes vehicle data and logistics data. The assessment information acquisition module 61 is used to determine assessment information reflecting the transportation risk of the vehicle based on multi-source perception data when the vehicle malfunctions. The assessment information includes the type of malfunction, the sensitivity coefficient of the cargo carried, and the estimated repair time. The sensitivity coefficient is used to characterize the degree of loss caused by the delayed delivery of the cargo. The target strategy determination module 62 is used to determine the target strategy from a preset set of transportation maintenance strategies based on the evaluation information; the set of transportation maintenance strategies includes multiple strategies for indicating the sequence of operations between vehicle maintenance and cargo transportation; Task execution module 63 is used to control the vehicle to perform cargo transportation tasks based on the target strategy.

[0180] Figure 7 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application, such as... Figure 7 As shown, the vehicle includes: a memory 70 for storing computer programs; The processor 71 is used to execute a computer program to implement the steps of the vehicle transportation task control method as described in the above embodiments.

[0181] The processor 71 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 71 may be implemented using at least one of the following hardware forms: Digital Signal Processor (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 71 may also include a main processor and a coprocessor. The main processor, also known as the Central Processing Unit (CPU), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 71 may integrate a Graphics Processing Unit (GPU), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 71 may also include an Artificial Intelligence (AI) processor, which is used to handle computational operations related to machine learning.

[0182] The memory 70 may include one or more computer-readable storage media, which may be non-transitory. The memory 70 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices or flash memory devices. In this embodiment, the memory 70 is used to store at least the following computer program 701, which, after being loaded and executed by the processor 71, is capable of implementing the relevant steps of the vehicle transportation task control method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 70 may also include an operating system 702 and data 703, and the storage method may be temporary storage or permanent storage. The operating system 702 may include Windows, Unix, Linux, etc. The data 703 may include, but is not limited to, relevant data involved in the vehicle transportation task control method.

[0183] In some embodiments, the vehicle may also include a display screen 72, an input / output interface 73, a communication interface 74, a power supply 75, and a communication bus 76.

[0184] Those skilled in the art will understand that Figure 7 The structure shown does not constitute a limitation on the vehicle and may include more or fewer components than illustrated.

[0185] The vehicle provided in this application includes a memory and a processor. When the processor executes the program stored in the memory, it can implement the vehicle transportation task control method described in the above embodiments.

[0186] It should be noted that although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

Claims

1. A method for controlling the transportation tasks of a vehicle, characterized in that, The method includes: Acquire multi-source perception data of the vehicle; the multi-source perception data includes vehicle data and logistics data; When the vehicle malfunctions, assessment information reflecting the transportation risk of the vehicle is determined based on the multi-source sensing data. The assessment information includes the malfunction type, the sensitivity coefficient of the cargo being transported, and the estimated repair time. The sensitivity coefficient is used to characterize the degree of loss caused by the delayed delivery of the cargo. Based on the assessment information, a target strategy is determined from a preset set of transportation maintenance strategies; the set of transportation maintenance strategies includes multiple strategies for indicating the sequence of operations between vehicle maintenance and cargo transportation. The vehicle is controlled to perform cargo transportation tasks based on the target strategy.

2. The vehicle transportation task control method as described in claim 1, characterized in that, The multi-source perception data also includes interaction information characterizing the driver's intention; determining the sensitivity coefficient includes: Based on the logistics data, determine the multi-dimensional influencing factors of the sensitivity coefficient; the influencing factors include timeliness, cargo vulnerability, economic loss, and contractual constraint. Based on the preset weights of each of the aforementioned influencing factors, the influencing factors are weighted and summed to obtain the initial sensitivity coefficient; Based on the interaction information, a correction factor is determined; and the initial sensitivity coefficient is corrected using the correction factor to obtain the sensitivity coefficient. Specifically, when the interaction information is empty, or when the fault type is an obstructive fault indicating that the vehicle cannot continue to drive, the correction factor is zero; when the interaction information indicates a priority delivery intention, the correction factor is positive; and when the interaction information indicates a priority repair intention, the correction factor is negative.

3. The vehicle transportation task control method as described in claim 2, characterized in that, The logistics data includes the waybill SLA level and the delivery deadline; Determining the urgency of the timeframe includes: Based on the vehicle's departure time, current system time, and estimated travel time from the current location to the unloading location, determine the available time margin for transportation; The total time window for transportation is determined based on the departure time and the receipt deadline. The basic value characterizing the urgency of transportation is determined by the available time margin and the total time window; Based on a preset acceleration factor mapping relationship, the target acceleration factor corresponding to the SLA level of the waybill is determined; the target acceleration factor is used to characterize the user's requirement for timeliness. The time urgency is obtained by correcting the base value using the target acceleration factor.

4. The vehicle transportation task control method as described in claim 2, characterized in that, The logistics data includes product categories; determining the vulnerability of the goods includes: Based on a preset decay period mapping relationship, a target decay value corresponding to the category of goods is determined; the target decay value is the time required for the quality of the goods to decrease to a preset percentage threshold after being removed from ideal storage conditions. The basic vulnerability of the cargo is determined based on the target attenuation value; Determine whether the fault type affects the ideal storage conditions; If so, determine a deviation parameter to characterize the degree of deviation between the actual environment and the ideal environment; based on the deviation parameter, determine a coupling factor to couple the fault with the cargo protection environment; and determine the cargo vulnerability using the coupling factor and the basic vulnerability. If not, the basic vulnerability shall be used as the cargo vulnerability.

5. The vehicle transportation task control method as described in claim 2, characterized in that, The logistics data includes loss impact parameters; these parameters include the value of the goods, contract penalties, and insurance coverage. Determining the degree of economic loss includes: Obtain the historical loss statistics parameters of the vehicle; the historical loss statistics parameters include the historical loss mean and the historical loss standard deviation. Based on the preset maintenance time mapping relationship, determine the standard maintenance time corresponding to the fault type; The probability of cargo damage due to delays is determined by the standard repair time. Based on the probability of cargo damage and the loss impact parameters, the potential economic loss is determined; Based on the historical loss statistics parameters, the potential economic loss is normalized to obtain the economic loss degree.

6. The vehicle transportation task control method as described in claim 2, characterized in that, The logistics data includes contract terms and customer information; determining the contract binding force includes: Obtain the vehicle's historical performance information; Based on the preset constraint mapping relationship, constraint influence factors that characterize the degree of contract constraint are determined; the constraint influence factors include rigidity factors corresponding to the contract terms, level factors corresponding to the customer information, and performance factors corresponding to the historical performance information. Based on preset weighting coefficients, the constraint influence factors are weighted and summed to obtain the contract constraint degree; The rigidity factor is used to characterize the rigidity of the contract terms regarding the timeliness of receipt; the grade factor is used to characterize the importance of the customer; the performance factor is used to characterize the performance level of the vehicle; and the performance factor is maximized when the historical performance information indicates that the vehicle has been delayed within a specified historical period.

7. The vehicle transportation task control method as described in claim 1, characterized in that, The vehicle data includes fault codes; determining the estimated repair time includes: Determine the fault type based on the fault code; Based on the preset fault mapping relationship, determine the basic maintenance time corresponding to the fault type; Determine the repair influencing factors for repair shops within a specified range; the repair influencing factors include technical proficiency factor, queuing waiting factor, and parts waiting factor; Based on the basic repair time and the repair influencing factors, the estimated repair time for each of the repair shops is determined.

8. The vehicle transportation task control method as described in claim 1, characterized in that, The set of transportation and maintenance strategies includes on-site parking, delivery before repair, quick repair before delivery, and repair before delivery; the fault types include blocking faults that indicate the vehicle cannot continue to drive and functional faults that indicate the vehicle can continue to drive. Based on the assessment information, a target strategy is determined from a pre-set set of transportation maintenance strategies, including: When the fault type is the blocking fault, the target strategy is to stop in place; When the fault type is the functional fault, perform the following steps: If the sensitivity coefficient is greater than or equal to the first threshold, the target strategy is to send the product first and then repair it. If the sensitivity coefficient is less than or equal to the second threshold, the target strategy is to repair first and then send; the first threshold is greater than the second threshold. If the sensitivity coefficient is between the first threshold and the second threshold, determine whether the sum of the estimated travel time from the repair shop to the unloading location and the estimated repair time is less than the remaining time between the current system time and the signing deadline; If it is less than the target value, the target strategy is to send it for quick repair afterward; If it is not less than, the target strategy is to send first and then repair.

9. The vehicle transportation task control method as described in claim 8, characterized in that, The vehicle data includes battery state of charge and battery rated capacity; If the target strategy is "deliver first, repair later", the process further includes the following before controlling the vehicle to perform the cargo transportation task based on the target strategy: The available energy of the vehicle is determined based on the battery state of charge and the battery rated capacity; Determine the energy consumption per unit mileage of the vehicle under the fault condition; Based on the energy consumption per unit mileage under fault conditions, the energy consumption required for the vehicle to travel on each travel segment is determined; the energy consumption includes the first energy consumption for the first travel segment from the current location to the unloading location, and the second energy consumption for the second travel segment from the unloading location to the repair shop; Determine whether the repair shops include energy-accessible shops that meet the energy consumption conditions; the energy consumption conditions are that the sum of the first energy consumption and the second energy consumption is less than the available energy. If included, the target store for carrying out the goods transportation task is determined from the energy-accessible stores; If not, the target strategy is switched to "repair first, then deliver"; and the target store for carrying out the goods transportation task is determined from the repair stores.

10. The vehicle transportation task control method as described in claim 9, characterized in that, Determining the energy consumption per unit mile of the vehicle under the fault condition includes: Obtain the normal energy consumption per unit mileage of the vehicle under normal conditions; Based on the pre-built energy consumption correction mapping relationship, determine the target energy consumption correction coefficient corresponding to the fault type; The energy consumption per unit mileage in the fault state is determined based on the energy consumption per unit mileage in the normal state and the target energy consumption correction coefficient.

11. The vehicle transportation task control method as described in claim 9, characterized in that, Based on the energy consumption per unit mileage under fault conditions, determine the energy consumption required for the vehicle to travel on each mileage segment, including: Obtain current weather information and terrain information of the area where the vehicle is located; Based on a preset redundancy mapping relationship, there are weather redundancy coefficients corresponding to the weather information, terrain redundancy coefficients corresponding to the terrain information, and load redundancy coefficients corresponding to each travel segment; the full load redundancy coefficient of the first travel segment is greater than the empty load redundancy coefficient of the second travel segment. Based on a preset energy consumption factor mapping relationship, the auxiliary energy consumption factor corresponding to each travel segment is determined; the auxiliary energy consumption factor is used to characterize the degree of influence of the vehicle auxiliary system's operating status on energy consumption per unit mileage; the first energy consumption factor of the first travel segment is greater than the second energy consumption factor of the second travel segment; The safety redundancy factor for each of the travel segments is determined based on the weather redundancy coefficient, the terrain redundancy coefficient, and the load redundancy coefficient. The energy consumption is determined based on the fault-state energy consumption per unit mileage, the auxiliary energy consumption factor, and the safety redundancy factor.

12. The vehicle transportation task control method as described in claim 9, characterized in that, Determining the target store for carrying out the cargo transportation task includes: The energy-accessible stores or the repair stores are selected by a specified screening process to obtain candidate stores; the specified screening includes screening based on business status, repair qualifications, and parts availability. Each candidate store was evaluated using multiple dimensions, resulting in a multi-dimensional score. These dimensions included repair capability score, logistics fulfillment score, parts availability score, and repair speed score. Based on a preset scenario factor mapping relationship, the scenario weights corresponding to the target strategy are determined; the scenario weights include maintenance capability weight, fulfillment weight, spare parts weight, and maintenance speed weight. Based on the scenario weights, the multi-dimensional scores are weighted and summed to obtain the comprehensive score for each candidate store. The first specified number of stores in the descending order of the comprehensive scores will be selected as the target stores.

13. The vehicle transportation task control method as described in claim 12, characterized in that, In the scene factor mapping relationship: When the target strategy is "repair first, then send", the maintenance capability weight is the largest among the scenario weights; When the target strategy is to send the product back after quick repair, the repair speed weight is the largest among the scenario weights. When the target strategy is "send first, repair later", the performance weight is the largest among the scenario weights.

14. The vehicle transportation task control method as described in claim 12, characterized in that, The dimension scoring also includes a distance convenience score, and the corresponding scenario weights also include a distance weight; when the target strategy is on-site parking, the distance weight is the largest. If the target strategy is "delivery first, repair later", then each candidate store is scored for distance and convenience, including: Determine the deflection angle of each candidate store; the deflection angle is the angle between the vector pointing from the current position to the unloading position with the unloading position as the vertex and the vector pointing from the unloading position to the candidate store; By applying the deflection angle, the total mileage of each travel segment is corrected for detour penalty to obtain the corrected mileage; The distance convenience score is determined based on the corrected mileage.

15. The vehicle transportation task control method as described in claim 12, characterized in that, The repair capability score is determined based on the store's repair performance indicators; these indicators include first-time repair rate, return rate, and repair time. The logistics fulfillment score is determined based on the delivery performance indicators of goods after store repairs; the delivery performance indicators include on-time receipt rate, average time-delay deviation, and damage correlation rate; wherein, the on-time receipt rate is the percentage of goods that are received on time after store repairs; the average time-delay deviation is the average percentage of overdue waybills; and the damage correlation rate is the percentage of goods damaged due to store repair delays. The accessory guarantee score is determined based on a preset accessory mapping relationship, which is the correspondence between the store's accessory inventory and the score. The repair speed score is determined based on the estimated repair time.

16. The vehicle transportation task control method as described in claim 15, characterized in that, The maintenance performance indicators and the delivery performance indicators are statistically analyzed in a stratified manner based on preset conditions; The preset conditions include store-wide conditions, fault type clusters, goods type clusters, and delivery area clusters. The hierarchical statistics include: Obtain historical metrics; these historical metrics include historical maintenance performance metrics and historical delivery performance metrics. The initial indicators are obtained by applying a time decay weight to the historical indicators based on the actual receipt time of the waybill. Based on the preset hierarchical structure, the statistical values ​​of the initial indicators are queried starting from the finest level. During the layer-by-layer query process, if the number of samples at the current level is less than a preset threshold, the query is backtracked to the previous level until the statistical values ​​that meet the preset threshold are obtained. The query conditions in the hierarchical structure are composed of the preset conditions, and the finer the level granularity, the more types of preset conditions constitute the corresponding query conditions. The statistical values ​​are smoothed using Bayesian methods to obtain the target estimate after the historical indicators are corrected.

17. The vehicle transportation task control method as described in claim 8, characterized in that, When the target strategy is quick repair followed by delivery, the method further includes: At preset intervals, obtain feedback from stores regarding the remaining repair time; Determine whether the sum of the current system time, the remaining repair time, and the estimated travel time between the repair shop and the unloading location is greater than the time remaining between the current system time and the delivery deadline. If the value is greater than the specified value, a strategy switching suggestion is generated to switch to the "send first, repair later" strategy, and the strategy switching suggestion is output.

18. The vehicle transportation task control method as described in claim 15, characterized in that, After controlling the vehicle to perform the cargo transportation task based on the target strategy, the method further includes: Collect information on the vehicle's fault repair status, actual receipt time, and actual repair duration; If the target fault with the same fault code recurs within a preset time period, update the first-time repair rate of the corresponding repair shop for the target fault. Compare the actual delivery time with the delivery deadline, and update the on-time delivery rate of the corresponding repair shop; The technical proficiency factor of the corresponding repair shop is updated based on the actual repair time.

19. A vehicle transport task control device, characterized in that, The device includes: The perception data acquisition module is used to acquire multi-source perception data of the vehicle; the multi-source perception data includes vehicle data and logistics data. An assessment information acquisition module is used to determine assessment information reflecting the transportation risk of the vehicle based on the multi-source sensing data when the vehicle malfunctions. The assessment information includes the malfunction type, the sensitivity coefficient of the cargo being transported, and the estimated repair time. The sensitivity coefficient is used to characterize the degree of loss caused by the delayed delivery of the cargo. The target strategy determination module is used to determine a target strategy from a preset set of transportation maintenance strategies based on the evaluation information; the set of transportation maintenance strategies includes multiple strategies for indicating the sequence of operations between vehicle maintenance and cargo transportation; The task execution module is used to control the vehicle to perform cargo transportation tasks based on the target strategy.

20. A vehicle comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the vehicle transportation task control method according to any one of claims 1 to 18.

Images