Charging station recommendation method, device, equipment and readable storage medium

Abstract

The present invention provides a charging station recommendation method, device, equipment and readable storage medium. The method includes: calculating the remaining mileage of a vehicle; when the remaining mileage of the vehicle is less than a mileage threshold, obtaining the historical charging order corresponding to the vehicle; and recommending a charging station based on the remaining mileage of the vehicle and the historical charging order. Through the present invention, since the charging station recommendation is based on the historical charging order, and the historical charging order represents the user's habits, the charging station finally recommended to the user is more in line with the user's habits, that is, the charging station recommendation is more in line with the user's expectations.

Description

Technical Field

[0001] The present invention relates to the field of new energy vehicle technology, and in particular to a charging station recommendation method, device, equipment and readable storage medium. Background Art

[0002] As the country's requirements for energy conservation and emission reduction are becoming increasingly stringent, various types of new energy power models have appeared on the market, and series plug-in hybrid vehicles are one of them. Compared with pure electric vehicles, series plug-in hybrid vehicles have no risk of charging anxiety. As long as there is a gas station, they can keep running. Therefore, in areas where there are no charging stations or fewer charging stations, this type of vehicle is also more practical; compared with gasoline-electric hybrid vehicles, when charging conditions are good in urban areas, they do not need to refuel and can meet pure electric drive requirements, which can save vehicle costs. At the same time, pure electric drive can also provide a better driving experience.

[0003] In the prior art, the charging station recommendation scheme for new energy vehicles is generally based on some information of the charging station itself, such as the number of available charging piles, charging unit price, etc. This method easily leads to the recommended charging station not meeting the user's expectations. Summary of the invention

[0004] The main purpose of the present invention is to provide a charging station recommendation method, device, equipment and readable storage medium, aiming to solve the technical problem in the prior art that charging station recommendations do not meet user expectations.

[0005] In a first aspect, the present invention provides a charging station recommendation method, the charging station recommendation method comprising:

[0006] Calculate the remaining mileage of the vehicle;

[0007] When the remaining mileage of the vehicle is less than the mileage threshold, obtain the historical charging order corresponding to the vehicle;

[0008] A charging station recommendation is made based on the remaining mileage of the vehicle and historical charging orders.

[0009] Optionally, the step of calculating the remaining mileage of the vehicle includes:

[0010] Based on the historical average fuel consumption, the fuel consumption per kilometer is obtained;

[0011] Obtaining the remaining fuel mileage according to the remaining fuel amount and the fuel consumption per kilometer;

[0012] Based on the historical average power consumption, the power consumption per kilometer is obtained;

[0013] Obtaining a remaining electric driving mileage according to the remaining power and the power consumption per kilometer;

[0014] The remaining fuel mileage and the remaining electric mileage are accumulated to obtain the remaining mileage of the vehicle.

[0015] Optionally, the step of obtaining the fuel consumption per kilometer according to the historical average fuel consumption includes:

[0016] When the cumulative mileage of the vehicle is greater than or equal to the first preset mileage value, weighted calculation is performed on the historical average fuel consumption corresponding to multiple preset mileages in the fuel mode to obtain the fuel consumption per kilometer;

[0017] When the vehicle's cumulative mileage is greater than or equal to the second preset mileage value and less than the first preset mileage value, the historical average fuel consumption corresponding to the most recent second preset mileage value in the fuel mode is used as the fuel consumption per kilometer;

[0018] When the vehicle's cumulative mileage is less than the second preset mileage value, if the vehicle is currently in fuel mode, the current instantaneous fuel consumption is used as the fuel consumption per kilometer; if the engine is not in fuel mode, the first default value is used as the fuel consumption per kilometer.

[0019] Optionally, the step of obtaining the power consumption per kilometer based on the historical average power consumption includes:

[0020] When the cumulative mileage of the vehicle is greater than or equal to the third preset mileage value, weighted calculation is performed on the historical average power consumption corresponding to multiple preset mileages in the pure electric mode to obtain the power consumption per kilometer;

[0021] When the vehicle's cumulative mileage is greater than or equal to the second preset mileage value and less than the third preset mileage value, the historical average power consumption corresponding to the most recent second preset mileage value in pure electric mode is used as the power consumption per kilometer;

[0022] When the vehicle's cumulative mileage is less than the second preset mileage value, if the current vehicle is in pure electric mode, the current instantaneous power consumption is used as the power consumption per kilometer; if the current vehicle is not in pure electric mode, the second default value is used as the power consumption per kilometer.

[0023] Optionally, the step of recommending a charging station according to the remaining mileage of the vehicle and the historical charging orders includes:

[0024] When the number of charging orders included in the historical charging orders is greater than or equal to a preset value, data cleaning is performed on the order data corresponding to the historical charging orders;

[0025] Normalizing the cleaned order data to obtain first order data;

[0026] Perform correlation analysis on each pair of fields in the first order data to obtain correlation coefficients between each pair of fields;

[0027] For two target fields whose correlation coefficients are greater than a preset coefficient, a new field value is obtained according to the two target fields and the correlation coefficients corresponding to the two target fields, and the numerical values ​​corresponding to the two target fields in the first order data are replaced by the new field value to obtain second order data;

[0028] Performing cluster analysis based on the second order data to obtain several categories;

[0029] Selecting a target category containing the largest number of order data from the several categories;

[0030] A charging station recommendation is performed based on the vehicle location, the location of the charging station corresponding to the charging order in the target category, and the remaining mileage of the vehicle.

[0031] Optionally, the step of recommending a charging station according to the remaining mileage of the vehicle and the historical charging orders includes:

[0032] When the number of charging orders included in the historical charging orders is less than a preset value, the charging station to be recommended is determined according to the remaining mileage of the vehicle, the vehicle location, and the locations of the charging stations corresponding to the charging orders included in the historical charging orders;

[0033] Perform data cleaning and normalization on the target order data corresponding to the target historical charging orders corresponding to the charging station to be recommended, and obtain new target order data corresponding to each charging station to be recommended;

[0034] Based on the new target order data corresponding to each charging station to be recommended, a score of each charging station to be recommended is obtained;

[0035] The charging station recommendation is made based on the score of each charging station to be recommended.

[0036] Optionally, the data cleaning rules are:

[0037] For numeric data, if the value is an integer, the null value is filled with the mode of the corresponding field; if the value is a decimal, the null value is filled with the average of the corresponding field.

[0038] In a second aspect, the present invention further provides a charging station recommendation device, the charging station recommendation device comprising:

[0039] A calculation module, used to calculate the remaining mileage of the vehicle;

[0040] An acquisition module is used to acquire the historical charging order corresponding to the vehicle when the remaining mileage of the vehicle is less than the mileage threshold;

[0041] The recommendation module is used to recommend charging stations based on the remaining mileage of the vehicle and historical charging orders.

[0042] In a third aspect, the present invention further provides a charging station recommendation device, comprising a processor, a memory, and a charging station recommendation program stored in the memory and executable by the processor, wherein when the charging station recommendation program is executed by the processor, the steps of the charging station recommendation method as described above are implemented.

[0043] In a fourth aspect, the present invention further provides a readable storage medium having a charging station recommendation program stored thereon, wherein when the charging station recommendation program is executed by a processor, the steps of the charging station recommendation method as described above are implemented.

[0044] In the present invention, the remaining mileage of the vehicle is calculated; when the remaining mileage of the vehicle is less than the mileage threshold, the historical charging orders corresponding to the vehicle are obtained; and charging stations are recommended based on the remaining mileage of the vehicle and the historical charging orders. Through the present invention, since the charging station recommendation is based on the historical charging orders, and the historical charging orders represent the user's habits, the charging station finally recommended to the user is more in line with the user's habits, that is, the charging station recommendation is more in line with the user's expectations. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A schematic diagram of the hardware structure of a charging station recommended by the embodiment of the present invention;

[0046] Figure 2 A schematic diagram of a flow chart of an embodiment of a charging station recommendation method of the present invention;

[0047] Figure 3 Schematic diagram of functional modules of an embodiment of a charging station recommendation device of the present invention.

[0048] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0049] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0050] In a first aspect, an embodiment of the present invention provides a charging station recommendation device, which may be a device having a data processing function, such as a personal computer (PC), a notebook computer, or a server.

[0051] Reference Figure 1 , Figure 1This is a schematic diagram of the hardware structure of the charging station recommendation device involved in the embodiment of the present invention. In the embodiment of the present invention, the charging station recommendation device may include a processor 1001 (e.g., a central processing unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components; the user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface, a wireless interface (such as wireless fidelity WIreless-FIdelity, WI-FI interface); the memory 1005 may be a high-speed random access memory (random access memory, RAM), or a stable memory (non-volatile memory), such as a disk storage, and the memory 1005 may optionally be a storage device independent of the aforementioned processor 1001. Those skilled in the art will understand that Figure 1 The hardware structure shown in the figure does not constitute a limitation of the present invention, and may include more or less components than those shown in the figure, or combine certain components, or arrange the components differently.

[0052] Continue to refer to Figure 1 , Figure 1 The memory 1005 as a computer storage medium may include an operating system, a network communication module, a user interface module, and a charging station recommendation program. The processor 1001 may call the charging station recommendation program stored in the memory 1005 and execute the charging station recommendation method provided in the embodiment of the present invention.

[0053] In a second aspect, an embodiment of the present invention provides a charging station recommendation method.

[0054] In one embodiment, referring to Figure 2 , Figure 2 This is a flow chart of an embodiment of a charging station recommendation method of the present invention. Figure 2 As shown, the recommended charging station methods include:

[0055] Step S10, calculating the remaining mileage of the vehicle;

[0056] In this embodiment, the vehicle targeted is a series plug-in hybrid electric vehicle, which can be driven by fuel and electricity. Therefore, it is necessary to calculate the vehicle's remaining fuel mileage and remaining electric mileage, and then accumulate the remaining fuel mileage and the remaining electric mileage to obtain the vehicle's remaining mileage.

[0057] Furthermore, in one embodiment, step S10 includes:

[0058] Step S101, obtaining the fuel consumption per kilometer based on the historical average fuel consumption;

[0059] In this embodiment, the historical average fuel consumption of the vehicle within a certain mileage in the fuel mode can be directly used as the fuel consumption per kilometer.

[0060] Furthermore, in one embodiment, step S101 includes:

[0061] Step S1011, when the cumulative mileage of the vehicle is greater than or equal to the first preset mileage value, weighted calculation is performed on the historical average fuel consumption corresponding to multiple preset mileages in the fuel mode to obtain the fuel consumption per kilometer;

[0062] In this embodiment, the first preset mileage value takes 1000km as an example. If the vehicle's cumulative mileage is ≥1000km, the fuel consumption per kilometer = the average fuel consumption of the past 1000km in fuel mode × weight 11 + the average fuel consumption of the past 500km in fuel mode × weight 12 + the average fuel consumption of the past 200km in fuel mode × weight 13 + the average fuel consumption of the past 100km in fuel mode × weight 14, where the values ​​of weights 11 to 14 are set according to actual needs.

[0063] It should be noted that this is only a schematic illustration of multiple preset mileages and does not constitute a limitation to this embodiment.

[0064] Step S1012, when the vehicle's cumulative mileage is greater than or equal to the second preset mileage value and less than the first preset mileage value, the historical average fuel consumption corresponding to the most recent second preset mileage value in the fuel mode is used as the fuel consumption per kilometer;

[0065] In this embodiment, the second preset mileage value takes 50 km as an example. If 50 km ≤ the vehicle's cumulative mileage < 1000 km, the fuel consumption per kilometer = the average fuel consumption of the past 50 km in the fuel mode.

[0066] It should be noted that if there is no average fuel consumption statistic value in the past 50 km fuel mode, the fuel consumption per kilometer is set to the first default value, such as 0.05 L / km.

[0067] Step S1013, when the vehicle's cumulative mileage is less than the second preset mileage value, if the current vehicle is in fuel mode, the current instantaneous fuel consumption is used as the fuel consumption per kilometer; if the engine is not in fuel mode, the first default value is used as the fuel consumption per kilometer.

[0068] In this embodiment, if the vehicle's cumulative mileage is less than 50km, if the vehicle is currently in fuel mode, the current instantaneous fuel consumption is used as the fuel consumption per kilometer; if the engine is not in fuel mode, the first default value is used as the fuel consumption per kilometer.

[0069] In this embodiment, historical data is reasonably used to make the calculated fuel consumption per kilometer more accurate.

[0070] Step S102, obtaining the remaining fuel mileage according to the remaining fuel amount and the fuel consumption per kilometer;

[0071] In this embodiment, the remaining fuel mileage can be calculated based on the remaining fuel amount and the fuel consumption per kilometer calculated in the above steps.

[0072] It is easy to understand that the above method of calculating the fuel consumption per kilometer ensures the accuracy of the calculated fuel consumption per kilometer, thereby ensuring the accuracy of the remaining fuel mileage obtained here.

[0073] Step S103, obtaining the power consumption per kilometer based on the historical average power consumption;

[0074] In this embodiment, the historical average power consumption of the vehicle within a certain mileage in pure electric mode can be directly used as the power consumption per kilometer.

[0075] Furthermore, in one embodiment, step S103 includes:

[0076] Step S1031, when the cumulative mileage of the vehicle is greater than or equal to the third preset mileage value, weighted calculation is performed on the historical average power consumption corresponding to multiple preset mileages in the pure electric mode to obtain the power consumption per kilometer;

[0077] In this embodiment, the third preset mileage value takes 2000km as an example. When the vehicle's cumulative mileage is ≥2000km, the power consumption per kilometer = the average power consumption in the past 2000km in pure electric mode * weight 21 + the average power consumption in the past 1000km in pure electric mode * weight 22 + the average power consumption in the past 750km in pure electric mode * weight 23 + the average power consumption in the past 500km in pure electric mode * weight 24 + the average power consumption in the past 200km in pure electric mode * weight 25, among which weights 21 to 25 are set according to actual needs.

[0078] It should be noted that this is only a schematic illustration of multiple preset mileages and does not constitute a limitation to this embodiment.

[0079] Step S1032, when the vehicle's cumulative mileage is greater than or equal to the second preset mileage value and less than the third preset mileage value, the historical average power consumption corresponding to the most recent second preset mileage value in pure electric mode is used as the power consumption per kilometer;

[0080] In this embodiment, if 50km≤the vehicle's cumulative mileage<2000km, the power consumption per kilometer=the average power consumption over the past 50km in pure electric mode.

[0081] It should be noted that if there is no statistical value of the average power consumption in the pure electric mode over the past 50 km, the power consumption per kilometer is set to a second default value, such as 0.2%.

[0082] Step S1033, when the vehicle's cumulative mileage is less than the second preset mileage value, if the current vehicle is in pure electric mode, the current instantaneous power consumption is used as the power consumption per kilometer; if the current vehicle is not in pure electric mode, the second default value is used as the power consumption per kilometer.

[0083] In this embodiment, if the vehicle's cumulative mileage is less than 50km, if the vehicle is currently in pure electric mode, the current instantaneous power consumption is used as the power consumption per kilometer; if the vehicle is currently not in pure electric mode, the second default value is used as the power consumption per kilometer.

[0084] In this embodiment, historical data is reasonably used to make the calculated power consumption per kilometer more accurate.

[0085] Step S104, obtaining the remaining electric driving mileage according to the remaining power and the power consumption per kilometer;

[0086] In this embodiment, the remaining electric driving mileage can be obtained by conversion based on the remaining power and the power consumption per kilometer calculated in the above steps.

[0087] It is easy to understand that the above method of calculating the power consumption per kilometer ensures the accuracy of the calculated power consumption per kilometer, thereby ensuring the accuracy of the remaining electric driving range obtained here.

[0088] Step S105, accumulating the remaining fuel mileage and the remaining electric mileage to obtain the remaining mileage of the vehicle.

[0089] In this embodiment, the remaining fuel mileage and the remaining electric mileage calculated above are accumulated to obtain the remaining mileage of the vehicle.

[0090] Step S20, when the remaining mileage of the vehicle is less than the mileage threshold, obtaining the historical charging order corresponding to the vehicle;

[0091] In this embodiment, the mileage threshold is set according to actual needs. When the remaining mileage of the vehicle is less than the mileage threshold, it means that the vehicle needs to be charged, and the historical charging order corresponding to the vehicle is obtained. Among them, each historical charging order of the vehicle can be associated with the unique identification code of the vehicle (such as VIN code) and saved in the cloud server. Taking vehicle 1 as an example, when the remaining mileage of vehicle 1 is less than the mileage threshold, the historical charging order corresponding to the VIN code of vehicle 1 is obtained from the cloud server.

[0092] Step S30: recommending a charging station based on the remaining mileage of the vehicle and historical charging orders.

[0093] In this embodiment, it is assumed that the historical charging orders include charging orders 1 to 10, and each charging order includes detailed charging data, such as the location of the charging station, the status of the equipment in the charging station, the charging unit price, the charging time, etc. Among them, the charging stations that can be recommended to the user can be preliminarily determined in combination with the location of the charging station, the current location of the vehicle, and the remaining mileage of the vehicle, and then the charging station that is more suitable for the current vehicle is selected according to the charging data recorded in the charging order corresponding to the preliminarily determined charging station, so as to recommend the charging station.

[0094] Furthermore, in one embodiment, step S30 includes:

[0095] Step S3011, when the number of charging orders included in the historical charging orders is greater than or equal to a preset value, data cleaning is performed on the order data corresponding to the historical charging orders;

[0096] In this embodiment, the preset value is set according to the actual situation, for example, it is set to 1000, that is, when the number of charging orders included in the historical charging orders is greater than or equal to 1000, the order data corresponding to the historical charging orders are cleaned.

[0097] For ease of description, the following takes the data cleaning of order data corresponding to 10 historical charging orders as an example. The order data corresponding to the 10 historical charging orders are shown in Table 1:

[0098]

[0099] Table 1

[0100] As shown in Table 1, the fields included in the order data are: charging station rating, electricity price, service fee price, available number of slow charging stations, available number of fast charging stations, number of fast charging stations, number of slow charging stations, charging service fee for this order, charging electricity fee for this order, total charging fee for this order, and parking fee. It should be noted that this is only a schematic description of the order data, and the order data may also include other fields related to charging, such as the start time of charging, the end time of charging, and the location of the charging station.

[0101] Data cleaning rules:

[0102] For numeric data (such as charging station ratings, electricity prices, service fee prices, the number of slow-charging charging stations available, the number of fast-charging charging stations available, the number of fast-charging charging stations, the number of slow-charging charging stations, the charging service fee for the order, the charging electricity fee for the order, the total charging fee for the order, parking fees, the latitude and longitude of the charging station, etc.), if the value is an integer, the null value is filled with the mode of the corresponding field; if the value is a decimal, the null value is filled with the average of the corresponding field.

[0103] For time type data, if it is a null value, fill it with the time of the previous order data.

[0104] Step S3012, normalizing the cleaned order data to obtain first order data;

[0105] In this embodiment, the order data after data cleaning is normalized, that is, for numerical data, min-max normalization is used, so that the values ​​are concentrated in the interval [0, 1]. For example, taking the charging station score in Table 1 as an example, the minimum value min of this field is 3 and the maximum value is 4.5. Then the charging station score of the first order data in Table 1 is normalized as follows:

[0106] (3-3) / (4.5-3), the value after normalization is 0. Similarly, the order data after data cleaning is normalized to obtain the first order data.

[0107] Step S3013, performing correlation analysis on each pair of fields in the first order data to obtain correlation coefficients between each pair of fields;

[0108] In this embodiment, the two fields take the charging station score and electricity price as an example, x i Score the charging station in the i-th order data, y i is the electricity price in the i-th order data, x' is the average charging station score in n order data, y' is the average electricity price in n order data, and n is the number of charging orders included in the historical charging order. The calculation formula of the correlation coefficient r is:

[0109]

[0110] By analogy, the correlation coefficient between any two fields in the first order data can be obtained.

[0111] Step S3014: for two target fields whose correlation coefficients are greater than a preset coefficient, obtain new field values ​​according to the two target fields and the correlation coefficients corresponding to the two target fields, and replace the values ​​corresponding to the two target fields in the first order data with the new field values ​​to obtain second order data;

[0112] In this embodiment, the correlation coefficients of any two fields in the first order data are obtained according to step S3013, and it is possible to determine which pairs of fields have correlation coefficients greater than a preset coefficient, wherein the preset coefficient is set according to actual conditions and is not limited here.

[0113] For example, the preset coefficient is set to 0.5, which is only for illustrative purposes.

[0114] If the correlation coefficient between the charging station score and the electricity price is 0.58, the charging station score and the electricity price are the target fields. Then, a new field value is obtained according to the two target fields and the correlation coefficients corresponding to the two target fields, and the new field value is used to replace the values ​​corresponding to the two target fields in the first order data. Taking the first order data in the first order data as an example, assuming that the charging station score of the first order data in the first order data is a and the electricity price is b, then c=a+0.58*b is calculated, and c is the new field value, and the new field value replaces a and b in the first order data.

[0115] And so on, the second order data can be obtained.

[0116] Step S3015, performing cluster analysis based on the second order data to obtain several categories;

[0117] In this embodiment, clustering algorithms (kmeans, dbscan, neural network algorithm, graph clustering algorithm, etc.) are used to perform clustering analysis on the second order data to obtain several categories, that is, the multiple order data included in the second order data are divided into several categories.

[0118] Step S3016, selecting a target category containing the largest number of order data items from the plurality of categories;

[0119] In this embodiment, it is assumed that there are three categories, among which Category 1 contains the largest number of order data, and Category 1 is taken as the target category.

[0120] Step S3017, recommending a charging station based on the vehicle location, the location of the charging station corresponding to the charging order in the target category, and the remaining mileage of the vehicle.

[0121] In this embodiment, assuming that the charging stations corresponding to the order data included in the target category include charging stations 1 to 100, the distance between the vehicle and charging stations 1 to 100 is determined based on the vehicle position and the positions of charging stations 1 to 100, and then a charging station whose distance is less than the remaining mileage of the vehicle is selected, and then a recommendation is made based on the selected charging stations, for example, the N closest to the vehicle are recommended from the selected charging stations. N is set according to actual needs.

[0122] Furthermore, in one embodiment, step S30 includes:

[0123] Step S3021, when the number of charging orders included in the historical charging order is less than a preset value, determining a charging station to be recommended according to the remaining mileage of the vehicle, the vehicle location, and the locations of the charging stations corresponding to the charging orders included in the historical charging order;

[0124] In this embodiment, when the number of charging orders included in the historical charging order is less than the preset value, if the charging stations corresponding to the charging orders included in the historical charging order include charging station 1 to charging station 100, the distance between the vehicle and charging station 1 to charging station 100 is determined according to the vehicle position and the position of charging station 1 to charging station 100, and then the charging station whose distance is less than the remaining mileage of the vehicle is selected as the charging station to be recommended. For example, the charging station to be recommended is charging station 1 to charging station 50.

[0125] Step S3022, performing data cleaning and normalization processing on the target order data corresponding to the target historical charging orders corresponding to the charging station to be recommended, to obtain new target order data corresponding to each charging station to be recommended;

[0126] In this embodiment, data cleaning and normalization processing can refer to the above-mentioned embodiments of steps S3011 to S3022, which will not be described in detail here.

[0127] Step S3023, obtaining a score of each charging station to be recommended based on the new target order data corresponding to each charging station to be recommended;

[0128] In this embodiment, it is assumed that the new target order data includes the number of idle fast-charging guns at the charging station after data cleaning and normalization, the number of idle slow-charging guns at the charging station after data cleaning and normalization, the distance of the vehicle from the charging station after data cleaning and normalization, and the ambient temperature of the charging station after data cleaning and normalization. Then the score of the charging station to be recommended = α1*the number of idle fast-charging guns at the charging station after data cleaning and normalization+α2*the number of idle slow-charging guns at the charging station after data cleaning and normalization+α3*the distance of the vehicle from the charging station after data cleaning and normalization+α4*the ambient temperature of the charging station after data cleaning and normalization. Among them, α1~α4 are weights, which are set according to actual conditions.

[0129] At this point, the score of each charging station to be recommended can be obtained.

[0130] Step S3024: recommend a charging station based on the score of each charging station to be recommended.

[0131] In this embodiment, the top N charging stations with the highest scores may be recommended, where N is set according to actual needs.

[0132] In this embodiment, the remaining mileage of the vehicle is calculated; when the remaining mileage of the vehicle is less than the mileage threshold, the historical charging orders corresponding to the vehicle are obtained; and charging stations are recommended based on the remaining mileage of the vehicle and the historical charging orders. In this embodiment, since the charging station recommendation is based on the historical charging orders, and the historical charging orders represent the user's habits, the charging station finally recommended to the user is in line with the user's habits, which makes the charging station recommendation more in line with the user's expectations.

[0133] In a third aspect, an embodiment of the present invention further provides a charging station recommendation device.

[0134] In one embodiment, referring to Figure 3 , Figure 3 This is a functional module diagram of an embodiment of a charging station recommendation device of the present invention. Figure 3 As shown, the recommended equipment for charging stations includes:

[0135] A calculation module 10 is used to calculate the remaining mileage of the vehicle;

[0136] An acquisition module 20 is used to acquire a historical charging order corresponding to the vehicle when the remaining mileage of the vehicle is less than a mileage threshold;

[0137] The recommendation module 30 is used to recommend a charging station according to the remaining mileage of the vehicle and the historical charging orders.

[0138] Furthermore, in one embodiment, the calculation module 10 is used to:

[0139] Based on the historical average fuel consumption, the fuel consumption per kilometer is obtained;

[0140] Obtaining the remaining fuel mileage according to the remaining fuel amount and the fuel consumption per kilometer;

[0141] Based on the historical average power consumption, the power consumption per kilometer is obtained;

[0142] Obtaining a remaining electric driving mileage according to the remaining power and the power consumption per kilometer;

[0143] The remaining fuel mileage and the remaining electric mileage are accumulated to obtain the remaining mileage of the vehicle.

[0144] Furthermore, in one embodiment, the calculation module 10 is used to:

[0145] When the cumulative mileage of the vehicle is greater than or equal to the first preset mileage value, weighted calculation is performed on the historical average fuel consumption corresponding to multiple preset mileages in the fuel mode to obtain the fuel consumption per kilometer;

[0146] When the vehicle's cumulative mileage is greater than or equal to the second preset mileage value and less than the first preset mileage value, the historical average fuel consumption corresponding to the most recent second preset mileage value in the fuel mode is used as the fuel consumption per kilometer;

[0147] When the vehicle's cumulative mileage is less than the second preset mileage value, if the vehicle is currently in fuel mode, the current instantaneous fuel consumption is used as the fuel consumption per kilometer; if the engine is not in fuel mode, the first default value is used as the fuel consumption per kilometer.

[0148] Furthermore, in one embodiment, the calculation module 10 is used to:

[0149] When the cumulative mileage of the vehicle is greater than or equal to the third preset mileage value, weighted calculation is performed on the historical average power consumption corresponding to multiple preset mileages in the pure electric mode to obtain the power consumption per kilometer;

[0150] When the vehicle's cumulative mileage is greater than or equal to the second preset mileage value and less than the third preset mileage value, the historical average power consumption corresponding to the most recent second preset mileage value in pure electric mode is used as the power consumption per kilometer;

[0151] When the vehicle's cumulative mileage is less than the second preset mileage value, if the current vehicle is in pure electric mode, the current instantaneous power consumption is used as the power consumption per kilometer; if the current vehicle is not in pure electric mode, the second default value is used as the power consumption per kilometer.

[0152] Furthermore, in one embodiment, the recommendation module 30 is used to:

[0153] When the number of charging orders included in the historical charging orders is greater than or equal to a preset value, data cleaning is performed on the order data corresponding to the historical charging orders;

[0154] Normalizing the cleaned order data to obtain first order data;

[0155] Perform correlation analysis on each pair of fields in the first order data to obtain correlation coefficients between each pair of fields;

[0156] For two target fields whose correlation coefficients are greater than a preset coefficient, a new field value is obtained according to the two target fields and the correlation coefficients corresponding to the two target fields, and the numerical values ​​corresponding to the two target fields in the first order data are replaced by the new field value to obtain second order data;

[0157] Performing cluster analysis based on the second order data to obtain several categories;

[0158] Selecting a target category containing the largest number of order data from the several categories;

[0159] A charging station recommendation is performed based on the vehicle location, the location of the charging station corresponding to the charging order in the target category, and the remaining mileage of the vehicle.

[0160] Furthermore, in one embodiment, the recommendation module 30 is used to:

[0161] When the number of charging orders included in the historical charging orders is less than a preset value, the charging station to be recommended is determined according to the remaining mileage of the vehicle, the vehicle location, and the locations of the charging stations corresponding to the charging orders included in the historical charging orders;

[0162] Perform data cleaning and normalization on the target order data corresponding to the target historical charging orders corresponding to the charging station to be recommended, and obtain new target order data corresponding to each charging station to be recommended;

[0163] Based on the new target order data corresponding to each charging station to be recommended, a score of each charging station to be recommended is obtained;

[0164] The charging station recommendation is made based on the score of each charging station to be recommended.

[0165] Furthermore, in one embodiment, the data cleaning rules are:

[0166] For numeric data, if the value is an integer, the null value is filled with the mode of the corresponding field; if the value is a decimal, the null value is filled with the average of the corresponding field.

[0167] Among them, the functional implementation of each module in the above-mentioned charging station recommendation device corresponds to each step in the above-mentioned charging station recommendation method embodiment, and its functions and implementation processes are no longer repeated here.

[0168] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium.

[0169] The readable storage medium of the present invention stores a charging station recommendation program, wherein when the charging station recommendation program is executed by a processor, the steps of the charging station recommendation method described above are implemented.

[0170] The method implemented when the charging station recommendation program is executed may refer to the various embodiments of the charging station recommendation method of the present invention, and will not be described in detail here.

[0171] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0172] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0173] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for a terminal device to execute the methods described in each embodiment of the present invention.

[0174] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A charging station recommendation method, characterized in that: The charging station recommendation method comprises: Calculate the remaining mileage of the vehicle; When the remaining mileage of the vehicle is less than the mileage threshold, obtain the historical charging order corresponding to the vehicle; Recommending charging stations based on the remaining mileage of the vehicle and historical charging orders; The step of recommending a charging station according to the remaining mileage of the vehicle and the historical charging orders includes: When the number of charging orders included in the historical charging orders is greater than or equal to a preset value, data cleaning is performed on the order data corresponding to the historical charging orders; Normalizing the cleaned order data to obtain first order data; Perform correlation analysis on each pair of fields in the first order data to obtain correlation coefficients between each pair of fields; For two target fields whose correlation coefficients are greater than a preset coefficient, a new field value is obtained according to the two target fields and the correlation coefficients corresponding to the two target fields, and the numerical values ​​corresponding to the two target fields in the first order data are replaced by the new field value to obtain second order data; Performing cluster analysis based on the second order data to obtain several categories; Selecting a target category containing the largest number of order data from the several categories; A charging station recommendation is performed based on the vehicle location, the location of the charging station corresponding to the charging order in the target category, and the remaining mileage of the vehicle.

2. The charging station recommendation method according to claim 1, characterized in that: The step of calculating the remaining mileage of the vehicle comprises: Based on the historical average fuel consumption, the fuel consumption per kilometer is obtained; Obtaining the remaining fuel mileage according to the remaining fuel amount and the fuel consumption per kilometer; Based on the historical average power consumption, the power consumption per kilometer is obtained; Obtaining a remaining electric driving mileage according to the remaining power and the power consumption per kilometer; The remaining fuel mileage and the remaining electric mileage are accumulated to obtain the remaining mileage of the vehicle.

3. The charging station recommendation method according to claim 2, characterized in that: The step of obtaining the fuel consumption per kilometer according to the historical average fuel consumption comprises: When the cumulative mileage of the vehicle is greater than or equal to the first preset mileage value, weighted calculation is performed on the historical average fuel consumption corresponding to multiple preset mileages in the fuel mode to obtain the fuel consumption per kilometer; When the vehicle's cumulative mileage is greater than or equal to the second preset mileage value and less than the first preset mileage value, the historical average fuel consumption corresponding to the most recent second preset mileage value in the fuel mode is used as the fuel consumption per kilometer; When the vehicle's cumulative mileage is less than the second preset mileage value, if the vehicle is currently in fuel mode, the current instantaneous fuel consumption is used as the fuel consumption per kilometer; if the engine is not in fuel mode, the first default value is used as the fuel consumption per kilometer.

4. The charging station recommendation method according to claim 2, characterized in that: The step of obtaining the power consumption per kilometer according to the historical average power consumption comprises: When the cumulative mileage of the vehicle is greater than or equal to the third preset mileage value, weighted calculation is performed on the historical average power consumption corresponding to multiple preset mileages in the pure electric mode to obtain the power consumption per kilometer; When the vehicle's cumulative mileage is greater than or equal to the second preset mileage value and less than the third preset mileage value, the historical average power consumption corresponding to the most recent second preset mileage value in pure electric mode is used as the power consumption per kilometer; When the vehicle's cumulative mileage is less than the second preset mileage value, if the current vehicle is in pure electric mode, the current instantaneous power consumption is used as the power consumption per kilometer; if the current vehicle is not in pure electric mode, the second default value is used as the power consumption per kilometer.

5. The charging station recommendation method according to claim 1, characterized in that: The step of recommending a charging station according to the remaining mileage of the vehicle and the historical charging orders includes: When the number of charging orders included in the historical charging orders is less than a preset value, the charging station to be recommended is determined according to the remaining mileage of the vehicle, the vehicle location, and the locations of the charging stations corresponding to the charging orders included in the historical charging orders; Perform data cleaning and normalization on the target order data corresponding to the target historical charging orders corresponding to the charging station to be recommended, and obtain new target order data corresponding to each charging station to be recommended; Based on the new target order data corresponding to each charging station to be recommended, a score of each charging station to be recommended is obtained; The charging station recommendation is made based on the score of each charging station to be recommended.

6. The charging station recommendation method according to claim 1 or 5, characterized in that: The data cleaning rules are: For numeric data, if the value is an integer, the null value is filled with the mode of the corresponding field; if the value is a decimal, the null value is filled with the average of the corresponding field.

7. A charging station recommendation device, characterized in that: The charging station recommendation device comprises: A calculation module, used to calculate the remaining mileage of the vehicle; An acquisition module is used to acquire the historical charging order corresponding to the vehicle when the remaining mileage of the vehicle is less than the mileage threshold; A recommendation module is used to clean the order data corresponding to the historical charging orders when the number of charging orders contained in the historical charging orders is greater than or equal to a preset value; normalize the order data after data cleaning to obtain first order data; perform correlation analysis on the fields in the first order data to obtain correlation coefficients between the fields; for two target fields whose correlation coefficients are greater than the preset coefficient, obtain new field values ​​according to the two target fields and the correlation coefficients corresponding to the two target fields, and replace the numerical values ​​corresponding to the two target fields in the first order data with the new field values ​​to obtain second order data; perform cluster analysis based on the second order data to obtain several categories; select the target category containing the largest number of order data from the several categories; and recommend charging stations according to the vehicle location, the location of the charging station corresponding to the charging order in the target category, and the remaining mileage of the vehicle.

8. A charging station recommendation device, characterized in that: The charging station recommendation device includes a processor, a memory, and a charging station recommendation program stored in the memory and executable by the processor, wherein when the charging station recommendation program is executed by the processor, the steps of the charging station recommendation method according to any one of claims 1 to 6 are implemented.

9. A readable storage medium, characterized in that: The readable storage medium stores a charging station recommendation program, wherein when the charging station recommendation program is executed by a processor, the steps of the charging station recommendation method according to any one of claims 1 to 6 are implemented.

Images