Charging strategy recommendation and charging strategy evaluation model construction method

Abstract

The present invention relates to the technical field of new energy vehicle charging strategy planning, and in particular to a charging strategy recommendation and charging strategy evaluation model construction method. The method of the present invention first obtains multiple state parameters of a target vehicle; then a first charging strategy and the multiple state parameters are input into a charging strategy evaluation model to obtain a first evaluation result; then the second charging strategy is adjusted by repeatedly iterating between obtaining an evaluation result after scrambling by inputting a second charging strategy and the multiple state parameters into the charging strategy evaluation model and adjusting the second charging strategy according to a scrambling deviation and a scrambling amount until the scrambling deviation is less than a scrambling deviation threshold; finally, the second charging strategy is recommended to the target vehicle. The implementation method of the present invention can provide a more optimized charging strategy according to the vehicle state, optimize the user's charging experience, and bring convenience to new energy vehicle owners in choosing a suitable charging strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of new energy vehicle charging strategy planning, and in particular to a charging strategy recommendation and charging strategy evaluation model construction method. Background Art

[0002] The development of new energy vehicles is booming. Among them, pure electric vehicles, extended-range electric vehicles, and hybrid vehicles all use on-board batteries as energy storage power sources, and provide electricity to the motor through the on-board batteries to drive the vehicle. New energy vehicles are energy-saving and environmentally friendly, and their excellent driving experience gives people a good car experience.

[0003] At the same time, new energy vehicles have caused users a lot of trouble in terms of battery life, finding charging piles and finding parking spaces. In related technologies, the charging management platform combines the peak and valley power phases of the power grid to give different charging prices and publicize the current number of remaining charging piles, which makes it convenient for users to find charging piles and reduces energy waste to a certain extent.

[0004] In actual operation, factors such as distance from the charging pile, charging pile operation status, charging waiting time, user charging preferences, length of charging queues, and customer reviews will affect drivers' choice of charging facilities. How to provide a charging strategy recommendation solution to improve the user experience of charging facilities and increase the overall utilization rate of charging facilities has become an urgent problem that technicians in this field need to solve.

[0005] Based on this, it is necessary to develop and design a charging strategy recommendation method. Summary of the invention

[0006] The embodiments of the present invention provide a charging strategy recommendation and a charging strategy evaluation model construction method, which is used to solve the problem of inconvenient charging caused by poor user strategies of new energy vehicles in the prior art.

[0007] In a first aspect, an embodiment of the present invention provides a charging strategy recommendation method, comprising:

[0008] Obtain multiple state parameters of the target vehicle;

[0009] Inputting the first charging strategy and the plurality of state parameters into a charging strategy evaluation model to obtain a first evaluation result;

[0010] The second charging strategy is adjusted by repeatedly iterating between inputting the second charging strategy and the multiple state parameters into the charging strategy evaluation model to obtain an evaluation result after scrambling and adjusting the second charging strategy according to the scrambling deviation and the scrambling amount until the scrambling deviation is less than the scrambling deviation threshold, wherein the second charging strategy is a charging strategy obtained by adding the scrambling amount to the first charging strategy, and the scrambling deviation is a deviation between the evaluation result after scrambling and the evaluation result before scrambling;

[0011] The second charging strategy is recommended to the target vehicle.

[0012] In a possible implementation, the method of repeatedly iterating between inputting the second charging strategy and the multiple state parameters into the charging strategy evaluation model to obtain an evaluation result after scrambling and adjusting the second charging strategy according to the scrambling deviation and the scrambling amount, adjusting the second charging strategy until the scrambling deviation is less than the scrambling deviation threshold, includes:

[0013] Adding the scrambling amount to the first charging strategy to obtain a second charging strategy;

[0014] inputting the second charging strategy and the plurality of state parameters into the charging strategy evaluation model, and obtaining the scrambled evaluation result as the second evaluation result;

[0015] Calculating a difference between the second evaluation result and the first evaluation result as the scrambling deviation;

[0016] If the modulus of the scrambling deviation is greater than the scrambling deviation threshold, the multiple elements of the scrambling amount are adjusted according to the scrambling deviation and the scrambling amount, the second evaluation result is used as the first evaluation result, the scrambling amount is added to the second charging strategy, the second charging strategy with the scrambling amount added is used as the second charging strategy, and the process jumps to the step of inputting the second charging strategy and the multiple state parameters into the charging strategy evaluation model, and taking the obtained scrambled evaluation result as the second evaluation result.

[0017] In a possible implementation manner, the multiple elements of adjusting the scrambling amount according to the scrambling deviation and the scrambling amount include:

[0018] The multiple elements of the scrambling amount are adjusted according to a first formula, the scrambling deviation and the scrambling amount, wherein the first formula is:

[0019]

[0020] Where Distbc (n+1) (dn) is the dnth element of the adjusted scrambling amount, Distbc(n) (dn) is the dnth element of the scrambling amount before adjustment, w dn is the dnth adjustment coefficient, Bias is the scrambling bias;

[0021] Obtain the local optimal limit interval for each element;

[0022] Check whether each element in the scrambled amount is within the corresponding local optimal restriction interval, and take the element within the local optimal restriction interval as the target element;

[0023] The value of the target element is set to the boundary value of the closest local optimal restriction interval.

[0024] In a second aspect, an embodiment of the present invention provides a method for constructing a charging strategy evaluation model, comprising:

[0025] Acquire multiple charging process history records, wherein the charging process history records include a vehicle state parameter set and a charging strategy;

[0026] Clustering multiple vehicle state parameter sets to obtain multiple vehicle state classes;

[0027] Determine a plurality of state charging strategy probabilities according to the plurality of charging strategies and the plurality of vehicle state classes, wherein the state charging strategy probability is a probability of a target charging strategy adopted under a target vehicle state;

[0028] A charging strategy evaluation model is constructed according to the multiple vehicle state parameter sets and the multiple state charging strategy probabilities.

[0029] In a possible implementation, determining multiple state charging strategy probabilities according to the multiple charging strategies and the multiple vehicle state classes includes:

[0030] For each vehicle status class in the plurality of vehicle status classes, performing the following steps:

[0031] Acquire multiple pending charging strategies according to the vehicle state class, wherein the pending charging strategies are charging strategies in the charging process history records where the vehicle state parameter set in the vehicle state class is located;

[0032] Clustering the multiple charging strategies to be processed to obtain multiple charging strategy classes;

[0033] The ratio of the number of charging strategies in each charging strategy class to the number of the plurality of charging strategies to be processed is calculated as the state charging strategy probability.

[0034] In a possible implementation, constructing a charging strategy evaluation model according to the multiple vehicle state parameter sets and the multiple state charging strategy probabilities includes:

[0035] The vehicle state parameter sets are sequentially taken out from the plurality of vehicle state parameter sets, and the following steps are performed after the taking out:

[0036] Input the vehicle state parameter set and the charging strategy in the charging process history record where the vehicle state parameter set is located into the charging strategy description model as independent variables, and use the value of the dependent variable output by the charging strategy description model as the score estimate;

[0037] According to the vehicle state parameter set, a state charging strategy probability verification is obtained, wherein the state charging strategy probability verification is a probability of a target charging strategy of a charging process history record where the vehicle state parameter set is located;

[0038] Calculating the difference between the state charging strategy probability verification and the score estimation as the current estimation difference;

[0039] Calculating the difference between the current estimation difference and the previous estimation difference as the second-order estimation difference, wherein the previous estimation difference is the estimation difference obtained by taking the vehicle state parameter set last time;

[0040] If the absolute value of the second-order estimation difference is greater than the estimation deviation, adjusting the parameters of the charging strategy description model according to the second-order estimation difference, the vehicle state parameter set, and the charging strategy in the charging process history record where the vehicle state parameter set is located;

[0041] Otherwise, the charging strategy description model is used as the charging strategy evaluation model.

[0042] In a possible implementation, the charging strategy description model is:

[0043]

[0044] In the formula, Y is the dependent variable, X is the joint independent variable, and w index is the first parameter of the index, w n is the nth second parameter, x n is the nth sub-variable, c1 is the first bias parameter, c2 is the second bias parameter, index_max is the total index number, and n_max is the total number of sub-variables.

[0045] In a third aspect, an embodiment of the present invention provides a charging strategy recommendation device, which is used to implement the charging strategy recommendation method described in the first aspect or any possible implementation of the first aspect, wherein the charging strategy recommendation device includes:

[0046] A state acquisition module, used to acquire multiple state parameters of the target vehicle;

[0047] An evaluation result acquisition module, used for inputting the first charging strategy and the plurality of state parameters into a charging strategy evaluation model to obtain a first evaluation result;

[0048] a charging strategy optimization module, configured to adjust the second charging strategy by repeatedly iterating between obtaining an evaluation result after scrambling by inputting the second charging strategy and the plurality of state parameters into the charging strategy evaluation model and adjusting the second charging strategy according to a scrambling deviation and a scrambling amount, until the scrambling deviation is less than a scrambling deviation threshold, wherein the second charging strategy is a charging strategy obtained by adding the scrambling amount to the first charging strategy, and the scrambling deviation is a deviation between the evaluation result after scrambling and the evaluation result before scrambling;

[0049] as well as,

[0050] A charging strategy recommendation module is used to recommend the second charging strategy to the target vehicle.

[0051] In a fourth aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it implements the steps of the method described in the first aspect, any possible implementation of the first aspect, the second aspect, or any possible implementation of the second aspect.

[0052] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect, any possible implementation of the first aspect, the second aspect, or any possible implementation of the second aspect are implemented.

[0053] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0054] The embodiment of the present invention discloses a charging strategy recommendation method, which first obtains multiple state parameters of a target vehicle; then inputs a first charging strategy and the multiple state parameters into a charging strategy evaluation model to obtain a first evaluation result; then adjusts the second charging strategy by repeatedly iterating between obtaining an evaluation result after scrambling by inputting the second charging strategy and the multiple state parameters into the charging strategy evaluation model and adjusting the second charging strategy according to a scrambling deviation and a scrambling amount, until the scrambling deviation is less than a scrambling deviation threshold, wherein the second charging strategy is a charging strategy obtained by adding the scrambling amount to the first charging strategy, and the scrambling deviation is a deviation between the evaluation result after scrambling and the evaluation result before scrambling; finally, the second charging strategy is recommended to the target vehicle. The embodiment of the present invention iteratively optimizes the charging strategy by scrambling the charging strategy, obtaining an evaluation result of the charging strategy, and adjusting the scrambling amount according to the evaluation result, so that a more optimized charging strategy can be given according to the vehicle state, thereby optimizing the user's charging experience and bringing convenience to new energy vehicle owners in choosing a suitable charging strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0056] Figure 1 is a flow chart of a charging strategy recommendation method provided in an embodiment of the present invention;

[0057] Figure 2 is a flow chart of a charging strategy evaluation model construction method provided by an embodiment of the present invention;

[0058] Figure 3 is a functional block diagram of a charging strategy recommendation device provided in an embodiment of the present invention;

[0059] Figure 4 It is a functional block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0060] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, and methods are omitted so as not to obscure the description of the present invention with unnecessary details.

[0061] In order to make the purpose, technical solutions and advantages of the present invention more clear, a specific implementation method will be described below in conjunction with the accompanying drawings.

[0062] The following is a detailed description of an embodiment of the present invention. This example is implemented based on the technical solution of the present invention, and provides a detailed implementation method and a specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0063] Figure 1 This is a flowchart of a charging strategy recommendation method provided in the first aspect of an implementation manner of the present invention.

[0064] like Figure 1 As shown, it shows a flowchart of the implementation method of the charging strategy recommendation method provided by the embodiment of the present invention, which is described in detail as follows:

[0065] In step 101, a plurality of state parameters of a target vehicle are obtained.

[0066] In step 102, the first charging strategy and the plurality of state parameters are input into a charging strategy evaluation model to obtain a first evaluation result.

[0067] Exemplarily, the target vehicle refers to the vehicle that has made a recommendation request or has a recommendation request, and the state parameters of the target vehicle usually include one or more of the following: battery capacity, current power, cruising range, current location of the vehicle, and distance from the charging station. Due to the different designs, current states, and preferences of different vehicles, vehicle drivers will adopt different charging strategies. For example, some drivers are accustomed to the strategy of shallow discharge and shallow charge, and find the nearest terminal charging station for charging in time; some are accustomed to deep discharge and deep charge, and tend to find low-peak periods for long-term charging.

[0068] But in general, according to big data, we can count the charging strategies most adopted by new energy vehicle user groups under different vehicle conditions. Based on these big data, we have constructed a charging strategy evaluation model. The charging strategy evaluation model in the implementation mode of the present invention inputs the vehicle's state parameters and charging strategy as independent variables into the model to obtain the evaluation result. The evaluation result represents the probability of being accepted by users under the combination of vehicle status and charging strategy. Regarding the construction of this model, the second aspect of the implementation mode of the present invention is discussed in detail. And the first aspect of the implementation of the present invention is to find a better key strategy charging strategy based on this model. Charging strategies are usually planned from the following aspects: time to arrive at charging, location of charging station, charging time, etc.

[0069] In order to achieve the purpose of finding a better charging strategy, the embodiment of the present invention inputs a randomly generated charging strategy (first charging strategy) into the model, obtains an evaluation result, and optimizes the charging strategy according to the evaluation result. The specific optimization method is discussed and expanded in detail in the following steps.

[0070] In step 103, the second charging strategy is adjusted by repeatedly iterating between inputting the second charging strategy and the multiple state parameters into the charging strategy evaluation model to obtain an evaluation result after scrambling and adjusting the second charging strategy according to the scrambling deviation and the scrambling amount until the scrambling deviation is less than the scrambling deviation threshold, wherein the second charging strategy is a charging strategy obtained by adding the scrambling amount to the first charging strategy, and the scrambling deviation is the deviation between the evaluation result after scrambling and the evaluation result before scrambling.

[0071] In some implementations, step 103 includes:

[0072] Adding the scrambling amount to the first charging strategy to obtain a second charging strategy;

[0073] inputting the second charging strategy and the plurality of state parameters into the charging strategy evaluation model, and obtaining the scrambled evaluation result as the second evaluation result;

[0074] Calculating a difference between the second evaluation result and the first evaluation result as the scrambling deviation;

[0075] If the modulus of the scrambling deviation is greater than the scrambling deviation threshold, the multiple elements of the scrambling amount are adjusted according to the scrambling deviation and the scrambling amount, the second evaluation result is used as the first evaluation result, the scrambling amount is added to the second charging strategy, the second charging strategy with the scrambling amount added is used as the second charging strategy, and the process jumps to the step of inputting the second charging strategy and the multiple state parameters into the charging strategy evaluation model, and taking the obtained scrambled evaluation result as the second evaluation result.

[0076] In some implementations, the multiple elements of adjusting the scrambling amount according to the scrambling deviation and the scrambling amount include:

[0077] The multiple elements of the scrambling amount are adjusted according to a first formula, the scrambling deviation and the scrambling amount, wherein the first formula is:

[0078]

[0079] Where Distbc (n+1) (dn) is the dnth element of the adjusted scrambling amount, Distbc (n)(dn) is the dnth element of the scrambling amount before adjustment, w dn is the dnth adjustment coefficient, Bias is the scrambling bias;

[0080] Obtain the local optimal limit interval for each element;

[0081] Check whether each element in the scrambled amount is within the corresponding local optimal restriction interval, and take the element within the local optimal restriction interval as the target element;

[0082] The value of the target element is set to the boundary value of the closest local optimal restriction interval.

[0083] In step 104 , the second charging strategy is recommended to the target vehicle.

[0084] Exemplarily, in the optimization of charging strategy, the embodiment of the present invention first adds a preset scrambling amount to the first charging strategy, and uses the scrambled first charging strategy as the second charging strategy, and inputs the second charging strategy into the charging strategy evaluation model to obtain the evaluation result again. The difference between the evaluation result obtained this time and the evaluation result obtained last time is the deviation caused by the scrambling amount, which is recorded as the scrambling deviation in the embodiment of the present invention. When the scrambling deviation is greater than the threshold, it means that there is still a large room for optimization. At this time, the scrambling amount is adjusted according to the scrambling deviation, the scrambling amount and the first formula. The first formula is:

[0085]

[0086] Where Distbc (n+1) (dn) is the dnth element of the adjusted scrambling amount, Distbc (n) (dn) is the dnth element of the scrambling amount before adjustment, w dn is the dnth adjustment coefficient, and Bias is the scrambling bias.

[0087] It should be noted that the elements of the scrambling amount are numerical or quantitative values ​​corresponding to several aspects of the above-mentioned charging strategy: for example, the value of the charging time. Since the scrambling amount obtained after adjustment according to the first formula may make the charging strategy enter the local optimum, the implementation mode of the present invention checks each element to avoid entering the local optimum according to the optimal restriction interval. The local optimal restriction interval of the test method of this aspect is, for example, -100 to 100. When one of the elements falls into the element optimal restriction interval, the value of the element that needs to be adjusted is edited to the nearest interval. For example, if the element value is 50, it needs to be adjusted to 100. After the adjustment, the charging strategy is adjusted again according to the adjusted scrambling amount, and the adjusted charging strategy and vehicle status are input into the charging strategy evaluation model to obtain the evaluation result again, and the iteration is repeated until the scrambling deviation threshold is reached.

[0088] When the scrambling deviation is less than the threshold, it means that the optimization is completed and the target vehicle can be recommended.

[0089] The embodiments of the present invention iteratively optimize the charging strategy by scrambling the charging strategy, obtaining the evaluation result of the charging strategy and adjusting the scrambling amount according to the evaluation result. Therefore, a more optimized charging strategy can be given according to the vehicle status, thereby optimizing the user's charging experience and bringing convenience to new energy vehicle owners in choosing a suitable charging strategy.

[0090] Figure 2 A flowchart of a charging strategy evaluation model construction method provided in the first aspect of an implementation manner of the present invention.

[0091] like Figure 2 As shown, it shows a flowchart of the implementation method of the charging strategy recommendation method provided by the embodiment of the present invention, which is described in detail as follows:

[0092] In step 201, a plurality of charging process history records are obtained, wherein the charging process history records include a vehicle state parameter set and a charging strategy.

[0093] In step 202, a plurality of vehicle state parameter sets are clustered to obtain a plurality of vehicle state classes.

[0094] Exemplarily, the charging process history record is a record obtained based on big data, for example, the charging strategies adopted by multiple new energy vehicle owners or drivers in different vehicle states. The embodiment of the present invention is a charging strategy evaluation model constructed based on such big data. In other words, this model is a model for evaluating the probability of a charging strategy being adopted.

[0095] Since the probability of being adopted is related to different states of the vehicle, the vehicle state needs to be quantified. The invention classifies the vehicle state for quantification. Specifically, the vehicle state is clustered according to vehicle state parameters to obtain multiple vehicle states.

[0096] One distance method is to use the Kmeans clustering method. In this case, the vehicle state parameter set in each charging process history record is regarded as a vector. According to the distance between vectors, the vehicle state is clustered into multiple classes, namely vehicle state classes. Each class corresponds to multiple charging strategies. By statistically analyzing the multiple charging strategies in each class, the probability of the charging strategy under the vehicle state condition is obtained.

[0097] In step 203, a plurality of state charging strategy probabilities are determined according to the plurality of charging strategies and the plurality of vehicle state classes, wherein the state charging strategy probability is the probability of a target charging strategy adopted under the target vehicle state.

[0098] In some implementations, step 203 includes:

[0099] For each vehicle status class in the plurality of vehicle status classes, performing the following steps:

[0100] Acquire multiple pending charging strategies according to the vehicle state class, wherein the pending charging strategies are charging strategies in the charging process history records where the vehicle state parameter set in the vehicle state class is located;

[0101] Clustering the multiple charging strategies to be processed to obtain multiple charging strategy classes;

[0102] The ratio of the number of charging strategies in each charging strategy class to the number of the plurality of charging strategies to be processed is calculated as the state charging strategy probability.

[0103] Exemplarily, for the probability determination problem of charging strategies under vehicle status conditions, since charging strategies vary greatly, the statistical probability value is small, which makes the data not typical. Therefore, in an embodiment of the present invention, for each vehicle status class, the charging strategy corresponding to the vehicle status data set in the category is extracted, recorded as the charging strategy to be processed, and these charging strategies to be processed are clustered to obtain charging strategy classes, and then the ratio of the number of charging strategies in each charging strategy class to the charging strategy to be processed is counted, and recorded as the state charging strategy probability.

[0104] In step 204, a charging strategy evaluation model is constructed according to the multiple vehicle state parameter sets and the multiple state charging strategy probabilities.

[0105] In some implementations, constructing a charging strategy evaluation model according to the multiple vehicle state parameter sets and the multiple state charging strategy probabilities includes:

[0106] The vehicle state parameter sets are sequentially taken out from the plurality of vehicle state parameter sets, and the following steps are performed after the taking out:

[0107] Input the vehicle state parameter set and the charging strategy in the charging process history record where the vehicle state parameter set is located into the charging strategy description model as independent variables, and use the value of the dependent variable output by the charging strategy description model as the score estimate;

[0108] According to the vehicle state parameter set, a state charging strategy probability verification is obtained, wherein the state charging strategy probability verification is a probability of a target charging strategy of a charging process history record where the vehicle state parameter set is located;

[0109] Calculating the difference between the state charging strategy probability verification and the score estimation as the current estimation difference;

[0110] Calculating the difference between the current estimation difference and the previous estimation difference as the second-order estimation difference, wherein the previous estimation difference is the estimation difference obtained by taking the vehicle state parameter set last time;

[0111] If the absolute value of the second-order estimation difference is greater than the estimation deviation, adjusting the parameters of the charging strategy description model according to the second-order estimation difference, the vehicle state parameter set, and the charging strategy in the charging process history record where the vehicle state parameter set is located;

[0112] Otherwise, the charging strategy description model is used as the charging strategy evaluation model.

[0113] In some implementations, the charging strategy description model is:

[0114]

[0115] In the formula, Y is the dependent variable, X is the joint independent variable, and w index is the first parameter of the index, w n is the nth second parameter, x n is the nth sub-variable, c1 is the first bias parameter, c2 is the second bias parameter, index_max is the total index number, and n_max is the total number of sub-variables.

[0116] Exemplarily, in an embodiment of the present invention, modeling is performed based on a vehicle state parameter set, a charging strategy, and the probability of the above-mentioned state charging strategy (a vehicle state parameter set and a charging strategy belonging to the same charging process history record).

[0117] The implementation method of the present invention extracts a vehicle state set and a corresponding charging strategy from multiple charging process historical records, and then inputs each extracted vehicle state set and corresponding charging strategy probability into a charging strategy description model to obtain a score estimate. This score estimate is compared with the previously calculated state charging strategy probability (the state charging strategy probability of the vehicle state set and the corresponding charging strategy) to obtain an estimated difference. The difference between this estimated difference and the previous estimated difference is recorded as a second-order estimated difference. The parameters of this model are modified according to this second-order estimated difference until the model converges. In other words, it can correctly express the relationship between the charging strategy adopted in a certain vehicle state in the charging process historical record and the state charging strategy probability. At this time, the charging strategy description model is used as a charging strategy evaluation model. The charging strategy description model of the present invention is:

[0118]

[0119] In the formula, Y is the dependent variable, X is the joint independent variable, and w index is the first parameter of the index, w nis the nth second parameter, x n is the nth sub-variable, c1 is the first bias parameter, c2 is the second bias parameter, index_max is the total index number, and n_max is the total number of sub-variables.

[0120] The charging strategy evaluation model construction method of the present invention extracts the probability of the charging strategy under the target vehicle state based on the charging process history record, and models the model based on the charging process history record and the state charging strategy probability. The model can better express the relationship between the vehicle state, the charging strategy and the probability of the charging strategy being applied. The model has good application objectivity and conforms to the charging strategy of most new energy vehicles. After applying this model, the preferred charging strategy can be found more quickly, which is convenient for the charging management of new energy vehicles and further improves the utilization rate of resources.

[0121] The charging strategy recommendation method of the present invention first obtains multiple state parameters of the target vehicle; then inputs the first charging strategy and the multiple state parameters into the charging strategy evaluation model to obtain a first evaluation result; then adjusts the second charging strategy by repeatedly iterating between obtaining the evaluation result after scrambling by inputting the second charging strategy and the multiple state parameters into the charging strategy evaluation model and adjusting the second charging strategy according to the scrambling deviation and the scrambling amount until the scrambling deviation is less than the scrambling deviation threshold, wherein the second charging strategy is the charging strategy obtained by adding the scrambling amount to the first charging strategy, and the scrambling deviation is the deviation between the evaluation result after scrambling and the evaluation result before scrambling; finally, the second charging strategy is recommended to the target vehicle. The embodiment of the present invention iteratively optimizes the charging strategy by scrambling the charging strategy, obtaining the evaluation result of the charging strategy and adjusting the scrambling amount according to the evaluation result, so that a more optimized charging strategy can be given according to the vehicle state, the user's charging experience is optimized, and it is convenient for new energy vehicle owners to choose a suitable charging strategy.

[0122] It should be understood that the size of the serial numbers of the steps in the above implementation does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the implementation method of the present invention.

[0123] The following is an implementation of the device of the present invention. For details not described in detail, reference may be made to the corresponding method implementation described above.

[0124] Figure 3 is a functional block diagram of a charging strategy recommendation device provided by the third aspect of an embodiment of the present invention, referring to Figure 3The charging strategy recommendation device includes: a state acquisition module 301, an evaluation result acquisition module 302, a charging strategy optimization module 303 and a charging strategy recommendation module 304, wherein:

[0125] A state acquisition module 301 is used to acquire multiple state parameters of the target vehicle;

[0126] An evaluation result acquisition module 302, configured to input the first charging strategy and the plurality of state parameters into a charging strategy evaluation model to obtain a first evaluation result;

[0127] The charging strategy optimization module 303 is used to adjust the second charging strategy by repeatedly iterating between inputting the second charging strategy and the multiple state parameters into the charging strategy evaluation model to obtain an evaluation result after scrambling and adjusting the second charging strategy according to the scrambling deviation and the scrambling amount, until the scrambling deviation is less than the scrambling deviation threshold, wherein the second charging strategy is a charging strategy obtained by adding the scrambling amount to the first charging strategy, and the scrambling deviation is a deviation between the evaluation result after scrambling and the evaluation result before scrambling;

[0128] The charging strategy recommendation module 304 is configured to recommend the second charging strategy to the target vehicle.

[0129] Figure 4 is a functional block diagram of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, the electronic device 4 of this embodiment includes: a processor 400 and a memory 401, wherein the memory 401 stores a computer program 402 that can be run on the processor 400. When the processor 400 executes the computer program 402, the steps in the above-mentioned charging strategy recommendation method and the embodiment are implemented, for example Figure 1 Steps 101 to 104 are shown.

[0130] Exemplarily, the computer program 402 may be divided into one or more modules / units, and the one or more modules / units are stored in the memory 401 and executed by the processor 400 to implement the present invention.

[0131] The electronic device 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 4 may include, but is not limited to, a processor 400 and a memory 401. Those skilled in the art will appreciate that Figure 4 It is only an example of the electronic device 4 and does not constitute a limitation of the electronic device 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 4 may also include input and output devices, network access devices, buses, etc.

[0132] The processor 400 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0133] The memory 401 may be an internal storage unit of the electronic device 4, such as a hard disk or memory of the electronic device 4. The memory 401 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4. Further, the memory 401 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 401 is used to store the computer program 402 and other programs and data required by the electronic device 4. The memory 401 may also be used to temporarily store data that has been output or is to be output.

[0134] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the implementation method can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method implementation method, which will not be repeated here.

[0135] In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0136] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0137] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0138] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0139] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0140] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned implementation method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various methods and device implementation methods. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0141] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A charging strategy recommendation method, characterized in that: include: Obtain multiple state parameters of the target vehicle; Inputting the first charging strategy and the plurality of state parameters into a charging strategy evaluation model to obtain a first evaluation result; The second charging strategy is adjusted by repeatedly iterating between inputting the second charging strategy and the multiple state parameters into the charging strategy evaluation model to obtain an evaluation result after scrambling and adjusting the second charging strategy according to the scrambling deviation and the scrambling amount until the scrambling deviation is less than the scrambling deviation threshold, wherein the second charging strategy is a charging strategy obtained by adding the scrambling amount to the first charging strategy, and the scrambling deviation is a deviation between the evaluation result after scrambling and the evaluation result before scrambling; recommending the second charging strategy to the target vehicle; in, The method of repeatedly iterating between inputting the second charging strategy and the plurality of state parameters into the charging strategy evaluation model to obtain an evaluation result after scrambling and adjusting the second charging strategy according to the scrambling deviation and the scrambling amount, adjusting the second charging strategy until the scrambling deviation is less than the scrambling deviation threshold, comprises: Adding the scrambling amount to the first charging strategy to obtain a second charging strategy; inputting the second charging strategy and the plurality of state parameters into the charging strategy evaluation model, and obtaining the scrambled evaluation result as the second evaluation result; Calculating a difference between the second evaluation result and the first evaluation result as the scrambling deviation; If the modulus of the scrambling deviation is greater than the scrambling deviation threshold, multiple elements of the scrambling amount are adjusted according to the scrambling deviation and the scrambling amount, the second evaluation result is used as the first evaluation result, the scrambling amount is added to the second charging strategy, the second charging strategy with the scrambling amount added is used as the second charging strategy, and the process jumps to the step of inputting the second charging strategy and the multiple state parameters into the charging strategy evaluation model, and using the obtained scrambled evaluation result as the second evaluation result; in, The multiple elements of adjusting the scrambling amount according to the scrambling deviation and the scrambling amount include: The multiple elements of the scrambling amount are adjusted according to a first formula, the scrambling deviation and the scrambling amount, wherein the first formula is: In the formula, is the adjusted scrambling amount elements, is the scrambling amount before adjustment elements, For the The adjustment factor, is the scrambling deviation; Obtain the local optimal limit interval for each element; Check whether each element in the scrambled amount is within the corresponding local optimal restriction interval, and take the element within the local optimal restriction interval as the target element; The value of the target element is set to the boundary value of the closest local optimal restriction interval.

2. A charging strategy evaluation model construction method, characterized in that: A charging strategy evaluation model for constructing the charging strategy recommendation method according to claim 1, wherein the charging strategy evaluation model construction method comprises: Acquire multiple charging process history records, wherein the charging process history records include a vehicle state parameter set and a charging strategy; Clustering multiple vehicle state parameter sets to obtain multiple vehicle state classes; Determine a plurality of state charging strategy probabilities according to the plurality of charging strategies and the plurality of vehicle state classes, wherein the state charging strategy probability is a probability of a target charging strategy adopted under a target vehicle state; A charging strategy evaluation model is constructed according to the multiple vehicle state parameter sets and the multiple state charging strategy probabilities.

3. The method for constructing a charging strategy evaluation model according to claim 2, characterized in that: The determining, according to the plurality of charging strategies and the plurality of vehicle status classes, a plurality of status charging strategy probabilities comprises: For each vehicle status class in the plurality of vehicle status classes, performing the following steps: Acquire multiple pending charging strategies according to the vehicle state class, wherein the pending charging strategies are charging strategies in the charging process history records where the vehicle state parameter set in the vehicle state class is located; Clustering the multiple charging strategies to be processed to obtain multiple charging strategy classes; The ratio of the number of charging strategies in each charging strategy class to the number of the plurality of charging strategies to be processed is calculated as the state charging strategy probability.

4. The method for constructing a charging strategy evaluation model according to any one of claims 2 to 3, characterized in that: The step of constructing a charging strategy evaluation model according to the plurality of vehicle state parameter sets and the plurality of state charging strategy probabilities comprises: The vehicle state parameter sets are sequentially taken out from the plurality of vehicle state parameter sets, and the following steps are performed after the taking out: Input the vehicle state parameter set and the charging strategy in the charging process history record where the vehicle state parameter set is located into the charging strategy description model as independent variables, and use the value of the dependent variable output by the charging strategy description model as the score estimate; According to the vehicle state parameter set, a state charging strategy probability verification is obtained, wherein the state charging strategy probability verification is a probability of a target charging strategy of a charging process history record where the vehicle state parameter set is located; Calculating the difference between the state charging strategy probability verification and the score estimation as the current estimation difference; Calculating the difference between the current estimation difference and the previous estimation difference as the second-order estimation difference, wherein the previous estimation difference is the estimation difference obtained by taking the vehicle state parameter set last time; If the absolute value of the second-order estimation difference is greater than the estimation deviation, adjusting the parameters of the charging strategy description model according to the second-order estimation difference, the vehicle state parameter set, and the charging strategy in the charging process history record where the vehicle state parameter set is located; Otherwise, the charging strategy description model is used as the charging strategy evaluation model.

5. The method for constructing a charging strategy evaluation model according to claim 4, characterized in that: The charging strategy description model is: In the formula, is the dependent variable, is the joint independent variable, For the The first parameter, For the The second parameter, For the The independent variable, is the first bias parameter, is the second bias parameter, is the total number of exponentials, is the total number of sub-independent variables.

6. A charging strategy recommendation device, characterized in that: For implementing the charging strategy recommendation method according to claim 1, the charging strategy recommendation device comprises: A state acquisition module, used to acquire multiple state parameters of the target vehicle; An evaluation result acquisition module, used for inputting the first charging strategy and the plurality of state parameters into a charging strategy evaluation model to obtain a first evaluation result; a charging strategy optimization module, configured to adjust the second charging strategy by repeatedly iterating between obtaining an evaluation result after scrambling by inputting the second charging strategy and the plurality of state parameters into the charging strategy evaluation model and adjusting the second charging strategy according to a scrambling deviation and a scrambling amount, until the scrambling deviation is less than a scrambling deviation threshold, wherein the second charging strategy is a charging strategy obtained by adding the scrambling amount to the first charging strategy, and the scrambling deviation is a deviation between the evaluation result after scrambling and the evaluation result before scrambling; as well as, A charging strategy recommendation module is used to recommend the second charging strategy to the target vehicle.

7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images