Driving data processing method and system for intelligent connected automobile

Abstract

The invention relates to the technical field of data processing, in particular to a driving data processing method and system for an intelligent networked automobile, and the method comprises the steps: obtaining the driving data of a target vehicle in each sub-period in the latest detection period; calculating a smoothness index based on the driving data of each sub-cycle, and determining a recommended driving mode corresponding to the smoothness index based on a preset mode corresponding table; a speed limit interval of a road section where the target vehicle is located and a driving data interval corresponding to the recommended driving mode are obtained, a recommended driving action sequence is determined based on the speed limit interval, the driving data interval and driving data of the target vehicle in the current sub-period, and the recommended driving action sequence comprises multiple recommended driving actions and corresponding action time; pushing the recommended driving mode and the recommended driving action sequence to the target vehicle; according to the invention, accurate matching of personalized driving experience can be realized, and the driving safety and comfort are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a method and system for processing driving data of an intelligent connected vehicle. Background Art

[0002] In related technologies, the driving mode of a vehicle is usually judged and adjusted manually. However, during driving, the complex and changeable road conditions and driving environment make the manual judgment have a large error, and it is difficult to achieve the optimal driving efficiency and safety guarantee.

[0003] An Intelligent Connected Vehicle (ICV) is the product of the deep integration of the vehicle networking and intelligent driving technologies, and realizes the intelligent interaction between vehicle and vehicle, vehicle and person, vehicle and road, vehicle and cloud platform through technologies such as in-vehicle sensors, communication networks, and big data.

[0004] With the development of intelligent connected vehicles, it is possible to collect driving data in real time through intelligent connected vehicles. However, how to process the collected driving data to achieve the precise matching of personalized driving experiences and improve driving safety and comfort has become a technical problem to be solved urgently. Summary of the Invention

[0005] To solve the above problems, the present invention provides a method and system for processing driving data of an intelligent connected vehicle, aiming to achieve the precise matching of personalized driving experiences and improve driving safety and comfort.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] On the one hand, an embodiment of the present invention provides a method for processing driving data of an intelligent connected vehicle, and the method includes the following steps:

[0008] S100, obtaining the driving data of each sub-cycle of the target vehicle in the most recent detection cycle;

[0009] S200, calculating a smoothness index based on the driving data of each sub-cycle, and determining a recommended driving mode corresponding to the smoothness index based on a preset mode correspondence table;

[0010] S300, obtaining the speed limit interval of the road section where the target vehicle is located and the driving data interval corresponding to the recommended driving mode, and determining a recommended driving action sequence based on the speed limit interval, the driving data interval, and the driving data of the target vehicle in the current sub-cycle, where the recommended driving action sequence includes a plurality of recommended driving actions and corresponding action times;

[0011] S400, pushing the recommended driving mode and the recommended driving action sequence to the target vehicle.

[0012] Optionally, the ride smoothness index calculated based on the driving data of each sub-cycle includes:

[0013] S210, collect the driving data of the target vehicle in each sub-cycle, where the driving data includes the average speed, average following distance, and maximum acceleration of the target vehicle relative to the longitudinal vehicle;

[0014] S220, calculate the standard deviation of speed based on the average speed of each sub-cycle, and perform normalization processing on the standard deviation of speed, the reciprocal of the average following distance, and the maximum acceleration respectively to obtain multiple corresponding normalized data;

[0015] S230, process the multiple normalized data by the weighted average method to obtain the ride smoothness index.

[0016] Optionally, the recommended driving mode corresponding to the ride smoothness index determined based on the preset mode correspondence table includes:

[0017] Obtain the mode correspondence table, which contains multiple driving modes, and each driving mode has a corresponding ride smoothness index interval and driving data interval;

[0018] Determine the ride smoothness index interval corresponding to the ride smoothness index, and use the driving mode corresponding to the ride smoothness index interval as the recommended driving mode.

[0019] Optionally, in S300, the recommended driving action sequence determined based on the speed limit interval, driving data interval, and driving data of the target vehicle in the current sub-cycle includes:

[0020] S310, use a sliding window to process the average energy consumption of the target vehicle in the last M sub-cycles to obtain the characteristic energy consumption of each sub-cycle;

[0021] S320, sort the M sub-cycles in descending order according to the characteristic energy consumption, divide the M sub-cycles into a high energy consumption group and a low energy consumption group, and select one sub-cycle from the high energy consumption group and the low energy consumption group in order to form N sub-cycle pairs;

[0022] S330, determine the difference in characteristic energy consumption between each sub-cycle pair, and fit the sub-cycle pair with the difference in characteristic energy consumption exceeding the difference threshold and the difference in average speed between the two sub-cycles in the sub-cycle pair to obtain a fitting curve of speed difference and energy consumption influence degree;

[0023] S340, establish a joint model based on the speed limit interval and driving data interval, and use the particle swarm algorithm to solve the joint model to obtain the target average speed and target acceleration; the joint model is an objective function for solving the maximization of the ride smoothness index on the premise of satisfying the speed limit interval and driving data interval;

[0024] S350. Determine the speed difference based on the target average speed and the average speed of the current sub - cycle, and determine the adjustment speed with the minimum energy consumption impact within the range not exceeding the speed difference based on the fitting curve;

[0025] S360. Determine whether the difference between the speed difference and the adjustment speed is less than the speed deviation threshold. If so, execute S370; if not, determine the adjustment duration based on the target acceleration and the adjustment speed, determine the corresponding sub - cycle based on the adjustment duration, and execute S350 after reaching the corresponding sub - cycle;

[0026] S370. Determine the recommended driving actions corresponding to the target acceleration of each sub - cycle, and form a recommended driving action sequence by arranging the recommended driving actions and the corresponding sub - cycles in sequence.

[0027] Optionally, the expression of the joint model is;

[0028] S = Max(α * D(v)+β * F(1 / d)+γ * A(a));

[0029] Where S represents the smoothness index, v represents the target average speed, d represents the average following distance, the average following distance d is greater than or equal to the preset minimum following distance, a represents the acceleration, the acceleration a is less than or equal to the maximum acceleration in the driving data interval, α, β, and γ are all weight coefficients between 0 and 1, and α + β + γ = 1; Max() represents the maximization function; D(v) represents the speed difference between the current average speed of the target vehicle and the target average speed, F(1 / d) represents the reciprocal of the average following distance when the target vehicle reaches the target average speed, and A(a) represents the acceleration of the target vehicle from the current average speed to the target average speed.

[0030] Optionally, in S400, the step of pushing the recommended driving mode and the recommended driving action sequence to the target vehicle includes:

[0031] Taking the current sub - cycle as the center of the sliding window and m sub - cycles as the radius of the sliding window; using the sliding window to traverse the average energy consumption of multiple sub - cycles in segments, and taking the sum of the average energy consumption of each sub - cycle within the sliding window as the characteristic energy consumption corresponding to the current sub - cycle; where m is less than or equal to M / 2.

[0032] Optionally, in S400, the step of pushing the recommended driving mode and the recommended driving action sequence to the target vehicle includes:

[0033] Push the recommended driving mode to the interactive terminal of the target vehicle;

[0034] Push the corresponding recommended driving action to the interactive terminal of the target vehicle in sequence for each sub - cycle.

[0035] On the other hand, an embodiment of the present invention provides a driving data processing system for an intelligent connected vehicle, including:

[0036] At least one processor;

[0037] At least one memory for storing at least one program;

[0038] When the at least one program is executed by the at least one processor, the at least one processor implements the above-mentioned method.

[0039] The beneficial effects of the present invention are as follows: The present invention discloses a driving data processing method and system for an intelligent connected vehicle. The present invention obtains a smoothness index from the driving data, and then determines the driving mode corresponding to the smoothness index to ensure the matching of vehicle performance and driving habits. By real-time monitoring of the speed limit section where the target vehicle is located, based on the speed limit section, the driving data section, and the driving data of the target vehicle in the current sub-cycle, a recommended driving action sequence is determined, which can meet the requirements of the speed limit section, adapt to the driving data section corresponding to the recommended driving mode, and combine the driving data of the target vehicle in the current sub-cycle to dynamically adjust the driving action to ensure the vehicle runs smoothly within the speed limit range, realizing the precise matching of personalized driving experience and enhancing driving safety and comfort. The present invention processes the driving data in real time, accurately generates a recommended driving mode and a recommended driving action sequence, significantly improves driving efficiency and safety, effectively makes up for the deficiencies of manual judgment, realizes the precise matching of personalized driving experience, and enhances driving safety and comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings without creative efforts based on these drawings.

[0041] Figure 1 It is a flowchart of a driving data processing method for an intelligent connected vehicle according to an embodiment of the present invention;

[0042] Figure 2 It is a structural diagram of a driving data processing system for an intelligent connected vehicle according to an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The following will clearly and completely describe the concept, specific structure, and technical effects generated by the present invention in combination with embodiments and drawings to fully understand the purpose, solution, and effects of the present invention. It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other.

[0044] Referring Figure 1 , as Figure 1 shown in the following is a method for processing driving data of an intelligent connected vehicle provided by an embodiment of the present invention. The method includes the following steps:

[0045] S100, obtaining the driving data of each sub-cycle of the target vehicle in the most recent detection cycle;

[0046] Specifically, the driving data includes the average speed, average following distance, and maximum acceleration of the target vehicle relative to the longitudinal vehicle; the maximum acceleration includes the maximum braking acceleration and the maximum driving acceleration.

[0047] S200, calculating a smoothness index based on the driving data of each sub-cycle, and determining the recommended driving mode corresponding to the smoothness index based on a preset mode correspondence table;

[0048] Specifically, the mode correspondence table contains multiple driving modes, and each driving mode has a corresponding smoothness index interval and driving data interval; exemplarily, the driving modes include an economy mode, a comfort mode, and a sport mode. By setting the performance parameters of the target vehicle, different driving modes have corresponding smoothness index intervals and driving data intervals to adapt to different driving styles. The smoothness index characterizes the degree of change of the characteristic data; the larger the smoothness index, the more intense the driving style and the higher the required performance parameters; when the smoothness index is low, the economy mode is recommended to focus on energy conservation; when the smoothness index is medium, the comfort mode is selected to balance energy conservation and power; when the smoothness index is high, the sport mode is switched to provide a stronger power response to ensure that the driving experience matches the style. By adapting the corresponding driving mode, personalized driving needs are thus met.

[0049] S300, obtaining the speed limit interval of the road where the target vehicle is located and the driving data interval corresponding to the recommended driving mode, and determining a recommended driving action sequence based on the speed limit interval, the driving data interval, and the driving data of the target vehicle in the current sub-cycle. The recommended driving action sequence includes multiple recommended driving actions and corresponding action times;

[0050] Specifically, the speed limit interval refers to the speed limit range set on a specific road, which usually varies according to the road type and traffic conditions.

[0051] S400, pushing the recommended driving mode and the recommended driving action sequence to the target vehicle.

[0052] Specifically, the recommended driving action sequence is pushed to the user through the interaction terminal of the target vehicle to assist the user in adjusting the target vehicle to the smoothness index range corresponding to the driving mode. The pushing method can adopt video broadcasting, marking and broadcasting corresponding voices on the road section where the target vehicle is traveling. For example, in the next sub-cycle of the current sub-cycle, the voice of "step on the brake gently" is broadcast, and a brake icon is marked on the road section traveled in the next sub-cycle, so as to prompt the user to perform the corresponding driving action. After the user completes the execution of the recommended driving action sequence, it is expected that the target vehicle can be adjusted to the smoothness index range corresponding to the driving mode. If there is a deviation during the actual execution process and the smoothness index range cannot be reached, steps S100 to S400 will be executed in a loop, thereby gradually improving the smoothness index.

[0053] In the embodiments provided by the present invention, the smoothness index is obtained through driving data, and then the driving mode corresponding to the smoothness index is determined to ensure the matching of vehicle performance and driving habits. By real-time monitoring the speed limit range of the road section where the target vehicle is located, based on the speed limit range, the driving data range, and the driving data of the target vehicle in the current sub-cycle, the recommended driving action sequence is determined, which can meet the requirements of the speed limit range, adapt to the driving data range corresponding to the recommended driving mode, and combine the driving data of the target vehicle in the current sub-cycle to dynamically adjust the driving action, ensuring the vehicle runs smoothly within the speed limit range, achieving the precise matching of the personalized driving experience, and improving driving safety and comfort.

[0054] In some embodiments, in S200, the calculation of the smoothness index based on the driving data of each sub-cycle includes:

[0055] S210, collecting the driving data of the target vehicle in each sub-cycle, where the driving data includes the average speed, average following distance, and maximum acceleration of the target vehicle relative to the longitudinal vehicle;

[0056] S220, calculating the speed standard deviation based on the average speed of each sub-cycle, and respectively performing normalization processing on the speed standard deviation, the reciprocal of the average following distance, and the maximum acceleration to obtain multiple corresponding normalized data;

[0057] S230, processing the multiple normalized data by the weighted average method to obtain the smoothness index.

[0058] It should be noted that the usage frequency and intensity of the accelerator pedal and the brake pedal can reflect the intensity of driving. The speed preference of the driver can be quantified through the average speed and the speed standard deviation; the operation limit of the driver can be quantified through the average following distance; frequent hard acceleration and hard braking usually reflect the aggressiveness of the driver, and the aggressiveness of driving can be quantified through the maximum acceleration.

[0059] Driving style is reflected by the standard deviation of speed, radical operations (including the number of hard brakes and rapid accelerations), and the average following distance. The greater the standard deviation of speed and the more radical operations, the more inclined the driver is to a radical driving style.

[0060] Specifically, a cautious driver has small speed fluctuations, few hard brakes and rapid accelerations, or a relatively large average following distance, tending to a steady and safe driving style, which matches the economic mode.

[0061] A balanced driver shows moderate speed changes, occasional hard brakes and rapid accelerations, and a moderate average following distance, usually achieving a balance between safety and efficiency, which matches the comfort mode.

[0062] A radical driver has large speed fluctuations, frequently hard brakes, rapid accelerations and a small average following distance, with a radical driving style, and may pursue the limit of operations in specific situations, which matches the sport mode.

[0063] In some embodiments, determining the recommended driving mode corresponding to the smoothness index based on the preset mode correspondence table includes:

[0064] Obtain the mode correspondence table, which contains multiple driving modes, and each driving mode has a corresponding smoothness index range and driving data range;

[0065] Determine the smoothness index range corresponding to this smoothness index, and use the driving mode corresponding to this smoothness index range as the recommended driving mode.

[0066] It should be noted that by real-time monitoring the smoothness index and determining the corresponding recommended driving mode, it can adaptively match the current driving habit and further improve the driving experience.

[0067] In some embodiments, in S300, determining the recommended driving action sequence based on the speed limit range, driving data range, and the driving data of the target vehicle in the current sub-cycle includes:

[0068] S310, use a sliding window to process the average energy consumption of the target vehicle in the most recent M sub-cycles to obtain the characteristic energy consumption of each sub-cycle;

[0069] S320, sort the M sub-cycles in descending order according to the characteristic energy consumption, divide the M sub-cycles into a high energy consumption group and a low energy consumption group, and select one sub-cycle from the high energy consumption group and the low energy consumption group in sequence to form N sub-cycle pairs;

[0070] S330, determine the difference in characteristic energy consumption of each sub-cycle pair, and fit the sub-cycle pair whose difference in characteristic energy consumption exceeds the difference threshold and the difference in average speed of the two sub-cycles in this sub-cycle pair to obtain a fitting curve of speed difference and energy consumption influence degree;

[0071] It can be understood that N ≤ M / 2 or (M - 1) / 2; by calculating the difference in the characteristic energy consumption of the two sub-periods in each sub-period pair respectively, the characteristic energy consumption differences of N sub-period pairs are obtained, and the sub-period pairs with the characteristic energy consumption differences exceeding the change threshold are selected; the average speeds of the two sub-periods in the sub-period pair are subtracted to obtain the corresponding relationship between multiple characteristic energy consumption differences and average speed differences, and the influence degree of the average speed on the characteristic energy consumption is fitted as the energy consumption influence degree of the average speed; it can reflect the influence degree of the user's personalized driving habit on the energy consumption, which is convenient for obtaining the recommended driving action sequence adapted to the user's driving habit subsequently.

[0072] S340, establish a joint model based on the speed limit interval and the driving data interval, and use the particle swarm optimization algorithm to solve the joint model to obtain the target average speed and the target acceleration; the joint model is an objective function for solving the maximization of the smoothness index on the premise of satisfying the speed limit interval and the driving data interval.

[0073] In this step, by optimizing the objective function, it is ensured that the optimal smoothness index is achieved under the constraints of speed limit and driving data, which is convenient for generating the recommended driving action sequence subsequently and improving the driving efficiency and comfort.

[0074] S350, determine the speed difference based on the target average speed and the average speed of the current sub-period, and determine the adjustment speed with the minimum energy consumption influence degree within the range not exceeding the speed difference based on the fitting curve.

[0075] Specifically, after subtracting the average speed of the current sub-period from the target average speed, the speed difference is obtained. By finding the range not exceeding the speed difference in the fitting curve, the adjustment speed with the minimum energy consumption influence degree within this range is found as the expected average speed to be reached by the next driving action, and gradually approaching the final target average speed.

[0076] S360, determine whether the difference between the speed difference and the adjustment speed is less than the speed deviation threshold. If so, execute S370; if not, determine the adjustment duration based on the target acceleration and the adjustment speed, determine the corresponding sub-period based on the adjustment duration, and execute S350 after reaching the corresponding sub-period.

[0077] Specifically, a certain deviation between the speed difference and the adjustment speed is allowed, and the speed deviation threshold can be set according to the actual situation. For example, it is set to be less than 5 kilometers per hour. If the difference between the speed difference and the adjustment speed is less than the speed deviation threshold, it means that the speed adjustment is completed; if it is greater than or equal to the speed deviation threshold, the adjustment duration is determined based on the target acceleration and the adjustment speed, the adjustment duration is divided by the duration of the sub-period, and the ceiling integer is taken as the number of sub-periods to obtain the target acceleration of the subsequent sub-period.

[0078] In this step, the adjustment speed is precisely controlled by fitting a curve to ensure that each adjustment is within the optimal energy consumption range, gradually optimizing the driving mode, achieving the best balance between energy consumption and smoothness, and enhancing the overall driving experience. Through continuous adjustment, real-time feedback and fine-tuning of the driving strategy can be achieved to ensure that each operation is on the optimal energy consumption path, ultimately realizing an efficient and smooth driving process, significantly reducing energy consumption, and improving driving comfort.

[0079] S370. Determine the recommended driving actions corresponding to the target acceleration of each sub-cycle, and form a recommended driving action sequence by arranging the recommended driving actions and the corresponding sub-cycles in sequence.

[0080] In this embodiment, through a refined adjustment strategy, it is possible to effectively reduce energy consumption while maintaining driving smoothness, achieving a double improvement in driving efficiency and comfort, meeting the personalized needs of users, and optimizing the overall driving experience.

[0081] In some embodiments, the expression of the joint model is:

[0082] S = Max(α * D(v) + β * F(1 / d) + γ * A(a));

[0083] Wherein, S represents the smoothness index, v represents the target average speed, d represents the average following distance, the average following distance d is greater than or equal to a preset minimum following distance, a represents the acceleration, the acceleration a is less than or equal to the maximum acceleration of the driving data interval, α, β, and γ are all weight coefficients between 0 and 1, and α + β + γ = 1; Max() represents the maximization function; D(v) represents the speed difference between the current average speed and the target average speed of the target vehicle, F(1 / d) represents the reciprocal of the average following distance when the target vehicle reaches the target average speed, and A(a) represents the acceleration of the target vehicle from the current average speed to the target average speed.

[0084] It should be noted that the value range of the acceleration a is limited by the maximum acceleration of the driving data interval. Considering the constraint of the average following distance d, safe driving is ensured. The setting of the target average speed v needs to balance energy consumption and safety. By dynamically adjusting the weight coefficients α, β, and γ, the joint model can more flexibly respond to different driving scenarios and optimize the balance between energy consumption and efficiency.

[0085] In some embodiments, the method of using a sliding window to process the average energy consumption of the target vehicle in the most recent M sub-cycles to obtain the characteristic energy consumption of each sub-cycle includes:

[0086] Use the current sub - cycle as the center of the sliding window and m sub - cycles as the radius of the sliding window; segment and traverse the average energy consumption of multiple sub - cycles using the sliding window, and take the sum of the average energy consumption of each sub - cycle within the sliding window as the characteristic energy consumption corresponding to the current sub - cycle; where m is less than or equal to M / 2.

[0087] It should be noted that obtaining the characteristic energy consumption corresponding to the sub - cycle through the sliding window can more accurately reflect the energy consumption changes of the vehicle at different times. Through the processing of the sliding window, the abnormality of single - sub - cycle data is avoided, and the obtained characteristic energy consumption is more comprehensive and effective.

[0088] In some embodiments, in S400, the step of pushing the recommended driving mode and the recommended driving action sequence to the target vehicle includes:

[0089] Push the recommended driving mode to the interactive terminal of the target vehicle;

[0090] Push the corresponding recommended driving actions to the interactive terminal of the target vehicle in sequence for each sub - cycle.

[0091] It should be noted that after obtaining the recommended driving mode and the recommended driving action sequence, pushing the recommended driving mode to the interactive terminal of the target vehicle can prompt the user to switch the driving mode, ensure that the driving behavior is consistent with the recommended actions, and improve driving safety and economy. At the same time, the sequentially - pushed driving action guidance helps the driver gradually optimize the operation and achieve the best balance between energy consumption and efficiency.

[0092] Reference Figure 2 , the embodiment of the present invention also provides a driving data processing system for an intelligent connected vehicle, including:

[0093] At least one processor;

[0094] At least one memory for storing at least one program;

[0095] When the at least one program is executed by the at least one processor, the at least one processor implements the above - mentioned method.

[0096] The content in the above - mentioned method embodiments is applicable to this embodiment. The functions specifically implemented in this embodiment are the same as those in the above - mentioned method embodiments, and the beneficial effects achieved are also the same as those in the above - mentioned method embodiments, and will not be elaborated here.

[0097] Although the description of the present disclosure has been rather detailed and has particularly described several of the described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but rather should be regarded as effectively covering the intended scope of the present disclosure by reference to the appended claims, considering the prior art to provide a broad interpretation of these claims. In addition, the present disclosure has been described above in terms of embodiments foreseeable by the inventors for the purpose of providing a useful description, and those non-substantive modifications to the present disclosure that are not currently foreseeable may still represent equivalent modifications of the present disclosure.

Claims

1. A method for processing driving data of an intelligent networked vehicle, characterized in that: The method comprises the following steps: S100, obtaining the driving data of the target vehicle in each sub-cycle in the most recent detection cycle; S200, calculating a ride comfort index based on the driving data of each sub-cycle, and determining a recommended driving mode corresponding to the ride comfort index based on a preset mode correspondence table; S300, obtaining a speed limit interval of a road section where the target vehicle is located and a driving data interval corresponding to a recommended driving mode, and determining a recommended driving action sequence based on the speed limit interval, the driving data interval, and the driving data of the target vehicle in a current sub-period, wherein the recommended driving action sequence includes a plurality of recommended driving actions and corresponding action times; S400: Push the recommended driving mode and the recommended driving action sequence to the target vehicle.

2. The method for processing driving data of an intelligent networked vehicle according to claim 1, characterized in that: The smoothness index is calculated based on the driving data of each sub-cycle, including: S210, collecting driving data of the target vehicle in each sub-period, wherein the driving data includes an average speed, an average following distance, and a maximum acceleration of the target vehicle relative to the longitudinal vehicle; S220, calculating a speed standard deviation based on the average speed of each sub-period, and normalizing the speed standard deviation, the inverse of the average following distance, and the maximum acceleration to obtain a plurality of corresponding normalized data; S230, processing the plurality of normalized data by a weighted average method to obtain a ride comfort index.

3. The method for processing driving data of an intelligent networked vehicle according to claim 2, characterized in that: The determining the recommended driving mode corresponding to the ride comfort index based on a preset mode correspondence table includes: Acquire a mode correspondence table, wherein the mode correspondence table includes a plurality of driving modes, each driving mode having a corresponding smoothness index interval and a driving data interval; A ride index interval corresponding to the ride index is determined, and a driving mode corresponding to the ride index interval is used as a recommended driving mode.

4. The method for processing driving data of an intelligent networked vehicle according to claim 1, characterized in that: In S300, determining the recommended driving action sequence based on the speed limit interval, the driving data interval and the driving data of the target vehicle in the current sub-period includes: S310, using a sliding window to process the average energy consumption of the target vehicle in the most recent M sub-cycles to obtain characteristic energy consumption of each sub-cycle; S320, arranging the M sub-periods in descending order according to the characteristic energy consumption from large to small, dividing the M sub-periods into a high energy consumption group and a low energy consumption group, and selecting one sub-period from the high energy consumption group and one sub-period from the low energy consumption group in order to form N sub-period pairs; S330, determining the characteristic energy consumption difference of each sub-period pair, fitting the sub-period pair whose characteristic energy consumption difference exceeds the difference threshold and the average speed difference of the two sub-periods in the sub-period pair, and obtaining a fitting curve of the speed difference and the energy consumption influence degree; S340, establishing a joint model based on the speed limit interval and the driving data interval, and solving the joint model using a particle swarm algorithm to obtain a target average speed and a target acceleration; the joint model is a target function for solving a maximum smoothness index under the premise of satisfying the speed limit interval and the driving data interval; S350, determining a speed difference based on the target average speed and the average speed of the current sub-period, and determining an adjustment speed with the least energy consumption impact within a range not exceeding the speed difference based on the fitting curve; S360, determining whether the speed difference and the difference between the adjusted speed are less than the speed deviation threshold, if so, executing S370; if not, determining the adjustment duration based on the target acceleration and the adjusted speed, determining the corresponding sub-period based on the adjustment duration, and executing S350 after reaching the corresponding sub-period; S370, determining the recommended driving action corresponding to the target acceleration of each sub-cycle, and sequentially forming a recommended driving action sequence with each recommended driving action and the corresponding sub-cycle.

5. The method for processing driving data of an intelligent networked vehicle according to claim 4, characterized in that: The expression of the joint model is: S=Max(α*D(v)+β*F(1 / d)+γ*A(a)); Among them, S represents the smoothness index, v represents the target average speed, d represents the average following distance, the average following distance d is greater than or equal to the preset minimum following distance, a represents the acceleration, the acceleration a is less than or equal to the maximum acceleration of the driving data interval, α, β, γ are all weight coefficients between 0 and 1, and α+β+γ=1; Max() represents the maximization function; D(v) represents the speed difference between the current average speed of the target vehicle and the target average speed, F(1 / d) represents the inverse of the average following distance of the target vehicle when it reaches the target average speed, and A(a) represents the acceleration of the target vehicle when it reaches the target average speed from the current average speed.

6. The method for processing driving data of an intelligent networked vehicle according to claim 4, characterized in that: The sliding window is used to process the average energy consumption of the target vehicle in the latest M sub-cycles to obtain the characteristic energy consumption of each sub-cycle, including: The current sub-period is taken as the center of the sliding window, and m sub-periods are taken as the radius of the sliding window. The average energy consumption of multiple sub-periods is segmented and traversed using the sliding window, and the sum of the average energy consumption of each sub-period in the sliding window is taken as the characteristic energy consumption corresponding to the current sub-period. Among them, m is less than or equal to M / 2.

7. The method for processing driving data of an intelligent networked vehicle according to claim 1, characterized in that: In S400, the recommended driving mode and the recommended driving action sequence are pushed to the target vehicle, including: Push the recommended driving mode to the interactive terminal of the target vehicle; The corresponding recommended driving actions are pushed to the interactive terminal of the target vehicle in sequence in each sub-cycle.

8. A driving data processing system for an intelligent networked vehicle, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method according to any one of claims 1 to 7.

Images