Vehicle charging method, device, electronic device and storage medium

Abstract

Disclosed are a vehicle charging method, device, electronic device and storage medium. Under the premise of complying with the provisions of relevant laws and regulations, not infringing on the privacy of others and not violating public order and good morals, the current charging times of the target vehicle are obtained after obtaining the user's authorization, and the corresponding charging timing determination method is selected according to the charging times to judge the current charging demand of the target vehicle, and after the user enables the relevant prompt function, the target vehicle is prompted to charge when the charging timing is met. In this way, the accuracy and timeliness of the vehicle charging prompt can be improved, the occurrence of users missing charging can be reduced, and the user experience can be improved.

Description

Technical Field

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

[0002] At present, electric vehicles are increasingly widely used, but the battery life of electric vehicles is affected by battery capacity and charging time. Therefore, choosing the right time to remind users to charge plays an important role in improving user experience.

[0003] In current transportation, users usually decide whether to charge based on the remaining power or endurance of the vehicle. This may cause users to miss the charging opportunity or charging station due to lack of awareness, which in turn causes charging anxiety in users. Summary of the invention

[0004] In view of this, an object of embodiments of the present invention is to provide a vehicle charging method, device, electronic device and storage medium.

[0005] In a first aspect, an embodiment of the present invention provides a vehicle charging method, the method comprising:

[0006] Get the current charging times of the target vehicle;

[0007] Determining a charging timing determination method for the target vehicle according to the charging number;

[0008] Determining the current charging demand of the target vehicle according to the charging timing determination method; and

[0009] In response to the charging demand of the target vehicle meeting the charging opportunity, a user is prompted to charge.

[0010] In a second aspect, an embodiment of the present invention provides a vehicle charging device, the device comprising:

[0011] A charging times acquisition unit, used to acquire the current charging times of the target vehicle;

[0012] A determination method acquisition unit, used to determine a charging timing determination method for the target vehicle according to the charging number;

[0013] a charging demand determination unit, configured to determine a current charging demand of a target vehicle according to the charging timing determination method; and

[0014] The charging prompt unit is used to prompt the user to charge in response to the charging demand of the target vehicle meeting the charging opportunity.

[0015] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method described in the first aspect.

[0016] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer program instructions, wherein the computer program instructions implement the method described in the first aspect when executed by a processor.

[0017] The technical solution of the embodiment of the present invention obtains the current charging times of the target vehicle after obtaining the user's authorization, and selects the corresponding charging timing determination method according to the charging times to judge the current charging demand of the target vehicle, and prompts the user to charge when the target vehicle meets the charging timing after the user enables the relevant prompt function. In this way, the accuracy and timeliness of the vehicle charging prompt can be improved, the occurrence of users missing charging can be reduced, and the user experience can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The above and other objects, features and advantages of the present invention will become more apparent through the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:

[0019] Figure 1 is a flow chart of a charging reminder method according to a first embodiment of the present invention;

[0020] Figure 2 is a flow chart of a first determination method according to an embodiment of the present invention;

[0021] Figure 3 is a flow chart of determining the weights of the first prediction value and the second prediction value according to an embodiment of the present invention;

[0022] Figure 4 is a flow chart of a charging reminder method according to a second embodiment of the present invention;

[0023] Figure 5 is a flow chart of obtaining a recommended charging station according to an embodiment of the present invention;

[0024] Figure 6 is a flow chart of determining a recommendation score according to an embodiment of the present invention;

[0025] Figure 7 is a schematic diagram of locations of candidate charging stations according to an embodiment of the present invention;

[0026] Figure 8 is a schematic diagram of a display interface of an embodiment of the present invention;

[0027] Fig. 9is a schematic diagram of a display interface of another embodiment of the present invention;

[0028] Fig.10 is a schematic diagram of a display interface of yet another embodiment of the present invention;

[0029] Fig.11 is a flow chart of a vehicle charging method according to an embodiment of the present invention;

[0030] Fig.12 is a flow chart of a vehicle charging device according to an embodiment of the present invention;

[0031] Fig.13 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The present invention is described below based on embodiments, but the present invention is not limited to these embodiments. In the detailed description of the present invention below, some specific details are described in detail. It is possible for a person skilled in the art to fully understand the present invention without the description of these details. In order to avoid confusing the essence of the present invention, known methods, processes, flows, components and circuits are not described in detail.

[0033] In addition, persons of ordinary skill in the art will appreciate that the drawings provided herein are for illustration purposes and are not necessarily drawn to scale.

[0034] At the same time, it should be understood that in the following description, "circuit" refers to a conductive loop composed of at least one element or subcircuit through electrical connection or electromagnetic connection. When an element or circuit is said to be "connected to" another element or an element / circuit is said to be "connected between" two nodes, it can be directly coupled or connected to another element or there can be an intermediate element, and the connection between the elements can be physical, logical, or a combination thereof. On the contrary, when an element is said to be "directly coupled to" or "directly connected to" another element, it means that there is no intermediate element between the two.

[0035] Unless the context clearly requires otherwise, words such as “include”, “including” and the like in the specification should be interpreted as including rather than being exclusive or exhaustive; that is, as meaning “including but not limited to”.

[0036] In the description of the present invention, it should be understood that the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0037] An electric vehicle is a transport vehicle that uses electric energy as the motive force and is driven by a traction motor. Common electric vehicles include electric cars, electric bicycles, electric tricycles, and the like. Since its impact on the environment is relatively small compared to traditional vehicles, it has been used more and more widely. At the same time, supporting equipment for electric vehicles, such as charging stations, has also been greatly developed. Therefore, reminding users to charge at the right time and accurately pushing charging stations to users are important factors in improving the range of electric vehicles and user experience. Therefore, an embodiment of the present invention provides a vehicle charging method to provide charging reminders and charging station recommendations to users.

[0038] Figure 1 FIG. 1 is a flow chart of a charging reminder method according to a first embodiment of the present invention. Figure 1 In the embodiment shown, the vehicle charging reminder method is used to determine the timing of reminding the user to charge, which can be executed by a control device inside the target vehicle, such as a BMS (BATTERY MANAGEMENT SYSTEM), or by a server connected to the target vehicle. The embodiment of the present invention is described by taking the execution by the target vehicle as an example, and the vehicle reminder method specifically includes the following steps:

[0039] Step S110: Obtain the current charging times of the target vehicle.

[0040] In this embodiment, each time the target vehicle is charged, the charging times are increased by one, and the target vehicle stores the current charging times. When a charging reminder is required, the charging times can be read from the stored data.

[0041] Furthermore, after authorization by the user, historical charging information of the vehicle is mined, which may include at least one of a charging endurance value, a corresponding charging time, and a remaining power. The historical charging endurance value is the distance that the vehicle can travel when charged in the past (assuming that the remaining power of the vehicle is enough to travel 50km when charging, the corresponding historical charging endurance value is 50km), and the charging time may include date, day of the week, time, etc. (for example, 2022.5.13, Friday, 10:00).

[0042] In an optional implementation, the target vehicle may execute a charging reminder according to a predetermined period, wherein the period may be set to a fixed period, such as 30 seconds, 1 minute, 5 minutes, or 10 minutes.

[0043] In another optional implementation, the target vehicle can perform charging reminders based on the remaining power and a predetermined period. For example, the target vehicle obtains the current remaining power in real time, and when the remaining power is less than a predetermined threshold (e.g., 50%), it starts to perform charging reminders according to a predetermined period, wherein the period can be set to a fixed period, such as 30 seconds, 1 minute, 5 minutes, or 10 minutes. Thus, when the remaining power of the battery is sufficient, the charging reminder process is not executed, which reduces the calculation amount of the target vehicle and improves processing efficiency.

[0044] In another optional implementation, the target vehicle can execute a charging reminder based on the remaining power and a predetermined cycle. For example, the target vehicle obtains the current remaining power in real time. When the remaining power is greater than or equal to a predetermined threshold (for example, 50%), the charging reminder is executed according to the predetermined first cycle. When the remaining power is less than the predetermined threshold (for example, 50%), the charging reminder is executed according to the predetermined second cycle. Among them, the first cycle is greater than the second cycle. Thus, when the remaining power of the battery is sufficient, the charging reminder process is executed in a larger cycle, and when the remaining power of the battery is low, the charging reminder process is executed in a smaller cycle. It can avoid missing the charging station, and can also reduce the calculation amount of the target vehicle and improve processing efficiency.

[0045] It should be noted that the embodiments of the present invention acquire, collect, store, use, process, transmit, provide and present data under the premise of complying with the provisions of relevant laws and regulations, not infringing on the privacy of others and not violating public order and good morals.

[0046] Step S120: Compare the current charging times of the target vehicle with a first threshold.

[0047] In this embodiment, when the current charging times of the target vehicle are small, the historical charging data of the target vehicle cannot accurately reflect the charging rules and habits of the user, while when the current charging times of the target vehicle are large, the historical charging data of the target vehicle can more accurately reflect the charging rules and habits of the user. Therefore, by presetting the first threshold, the current charging times of the target vehicle are compared with the first threshold, and different charging timing determination methods are adopted according to the comparison results. Among them, the first threshold can be set to any value according to actual needs, such as 50, 100, 500, etc.

[0048] Further, in response to the current charging times of the target vehicle being less than the first threshold, the process proceeds to step S130.

[0049] In response to the current charging number of the target vehicle being greater than or equal to the first threshold, the process proceeds to step S140.

[0050] It should be understood that the embodiment of the present invention does not limit the range of charging times, and may enter step S130 in response to the current charging times of the target vehicle being less than or equal to the first threshold, or enter step S140 in response to the current charging times of the target vehicle being greater than the first threshold.

[0051] Step S130: The charging timing of the target vehicle is determined in a first determination manner.

[0052] In this embodiment, in response to the current charging times of the target vehicle being less than the first threshold, the charging timing determination mode of the target vehicle is set to the first determination mode, which is a preset initial judgment condition.

[0053] Furthermore, the first determination method is determined based on historical charging information of a vehicle with the same attributes as the target vehicle. The vehicle with the same attributes as the target vehicle may be a vehicle of the same brand as the target vehicle.

[0054] Specifically, historical charging data of vehicles with the same attributes as the target vehicle is obtained, and the historical charging data is statistically analyzed or processed in other ways to obtain a universal charging timing determination method, that is, a first determination method. For example, the first determination method is determined according to a cruising range threshold and / or a time interval threshold, and the cruising range threshold includes a power threshold and / or a mileage threshold. The historical charging data includes time information, remaining mileage information, remaining power information, etc. of a vehicle with the same attributes as the target vehicle when charging.

[0055] For example, the first determination method is that the cruising range information of the target vehicle does not meet the cruising range threshold, wherein the cruising range information includes the current remaining mileage and / or remaining power of the target vehicle. That is, the remaining power of the target vehicle is less than or equal to the power threshold, or the current remaining mileage of the target vehicle is less than or equal to the mileage threshold, or the current remaining power of the target vehicle is less than or equal to the power threshold and the current remaining mileage is less than or equal to the mileage threshold. Among them, the power threshold and the mileage threshold can be obtained based on the historical charging data of vehicles with the same attributes as the target vehicle. Specifically, a certain number of historical charging data of vehicles with the same attributes as the target vehicle are obtained, the remaining power and remaining mileage of each vehicle when charging are obtained, and the power threshold and mileage threshold are determined according to the remaining power and remaining mileage of each vehicle when charging. Among them, the power threshold and the mileage threshold can be obtained by averaging or by other methods, and the embodiment of the present invention does not limit this.

[0056] For another example, the first determination method is that the time interval between the target vehicle and the last charge is greater than or equal to the time interval threshold. The time interval threshold can be obtained based on the historical charging data of vehicles with the same attributes as the target vehicle. Specifically, the historical charging data of a certain number of vehicles with the same attributes as the target vehicle are obtained, and the time interval between two adjacent charges of each vehicle is obtained. The time interval threshold is determined based on the time interval between two adjacent charges of each vehicle, wherein the time interval threshold can be obtained by averaging or by other methods, and the embodiment of the present invention does not limit this.

[0057] For another example, the first determination method may be determined by the battery life information and the charging time interval. Figure 2 The steps shown include:

[0058] Step S131: Obtain a first predicted value corresponding to the battery life information according to the battery life threshold.

[0059] In this embodiment, the method for obtaining the first prediction value can be implemented based on various existing methods, and the embodiment of the present invention does not limit this.

[0060] In some embodiments, when the first prediction value is determined by a power threshold, the first prediction value may be obtained by the following formula:

[0061]

[0062] Among them, Y E Indicates the first predicted value obtained by the power threshold, E r Indicates the power threshold, E t Indicates the current remaining power of the target vehicle.

[0063] In some embodiments, when the first prediction value is determined by a mileage threshold, the first prediction value may be obtained by the following formula:

[0064]

[0065] Among them, Y L represents the first predicted value obtained by the mileage threshold, L r Indicates the mileage threshold, L t Indicates the current remaining mileage of the target vehicle.

[0066] In some embodiments, if the first prediction value is determined based on both the power threshold and the mileage threshold, the above Y E and Y L The first prediction value can be calculated by weighted summation or average value, etc., which is not limited in the present invention.

[0067] Step S132: Obtain a second prediction value corresponding to the time interval according to the time interval threshold.

[0068] In some embodiments, the second prediction value may be obtained by the following formula:

[0069]

[0070] Among them, Y G represents the second predicted value obtained by the time interval threshold, G r represents the time interval threshold, G t Indicates the time interval between the current time and the last charging time of the target vehicle.

[0071] It should be understood that the methods for obtaining the predicted values ​​in the above steps S131 and S132 are only a few examples provided in the embodiments of the present invention. The embodiments of the present invention do not limit the specific methods for obtaining the predicted values, and the predicted values ​​can be obtained based on various existing methods.

[0072] Step S133: weighted sum the first prediction value and the second prediction value to obtain a charging prediction value, where the charging prediction value is used to characterize the probability that the target vehicle needs to be charged.

[0073] In an optional implementation, the weights of the first prediction value and the second prediction value may be preset weights, for example, the weight of the first prediction value is 0.5, the weight of the second prediction value is 0.5, and so on.

[0074] For example, assuming that the weight of the first prediction value is preset to 0.5 and the weight of the second prediction value is preset to 0.5, when the first determination method is determined by the mileage threshold and the time interval threshold, and the obtained mileage threshold is 50km (kilometers), the time interval threshold is 100h (hours). If the current remaining mileage of the target vehicle is 70km and the time interval from the last charge is 120h, then the first prediction value Y obtained by the above method is L is -0.4. The second predicted value Y obtained in the above manner G is 0.2, and the charging prediction value after weighted summation of the first prediction value and the second prediction value is -0.1.

[0075] In another optional implementation, in order to further improve the accuracy of timing prediction, the weight of the first prediction value and the second prediction value can be determined by comparing the endurance information with the endurance threshold. Figure 3 , including the following steps:

[0076] Step S1331, comparing the current cruising range information of the target vehicle with the cruising range threshold.

[0077] In this embodiment, in response to the current cruising range information of the target vehicle being less than or equal to the cruising range threshold, it indicates that the current cruising range of the target vehicle is insufficient. At this time, the weight corresponding to the first prediction value can be set to a larger value, and the weight corresponding to the second prediction value can be set to a smaller value, so as to increase the influence of the first prediction value on the charging prediction value. In response to the current cruising range information of the target vehicle being greater than the cruising range threshold, it indicates that the current cruising range of the target vehicle is sufficient. At this time, the weight corresponding to the first prediction value can be set to a smaller value, and the weight corresponding to the time prediction value can be set to a larger value, so as to increase the influence of the second prediction value on the charging prediction value.

[0078] Step S1332: In response to the current cruising range information of the target vehicle being less than or equal to the cruising range threshold, determining the weight to be a first weight and a second weight, the first weight corresponding to the first predicted value, and the second weight corresponding to the second predicted value.

[0079] In this embodiment, in response to the current cruising range information of the target vehicle being less than or equal to the cruising range threshold, indicating that the current cruising range of the target vehicle is insufficient, at this time, the first weight corresponding to the first prediction value can be set to a larger value, and the second weight corresponding to the second prediction value can be set to a smaller value. For example, the first weight of the first prediction value is 0.7, the second weight of the second prediction value is 0.3, and so on.

[0080] Step S1333: In response to the current cruising range information of the target vehicle being greater than the cruising range threshold, determining the weights to be a third weight and a fourth weight, the third weight corresponding to the first predicted value, and the fourth weight corresponding to the second predicted value.

[0081] In this embodiment, in response to the current cruising range information of the target vehicle being greater than the cruising range threshold, it indicates that the current cruising range of the target vehicle is relatively sufficient. At this time, the third weight corresponding to the first prediction value can be set to a smaller value, and the fourth weight corresponding to the second prediction value can be set to a larger value. For example, the third weight of the first prediction value is 0.3, the fourth weight of the second prediction value is 0.7, and so on.

[0082] Further, the proportion of the first weight in the first weight and the second weight is greater than the proportion of the third weight in the third weight and the fourth weight.

[0083] For example, assuming that the current range information of the target vehicle is less than or equal to the range threshold, the weight of the range prediction value is 0.7, and the weight of the time prediction value is 0.3. When the current range information of the target vehicle is greater than the range threshold, the weight of the range prediction value is 0.3, and the weight of the time prediction value is 0.7. When the first determination method is determined by the mileage threshold and the time interval threshold, and the mileage threshold obtained is 50km (kilometers), the time interval threshold is 100h (hours). If the target vehicle's current remaining mileage is 70km and the time interval from the last charge is 120h, the range prediction value Y obtained by the above method is L is -0.4, and the time prediction value Y obtained by the above method G is 0.2. At this time, the target vehicle's current range information is greater than the range threshold, the weight of the range prediction value is 0.3, the weight of the time prediction value is 0.7, and the charging prediction value after weighted sum of the range prediction value and the time prediction value is 0.02. If the target vehicle's current remaining mileage is 30km and the time interval from the last charge is 80h, the range prediction value Y obtained in the above way is L is 0.4, and the time prediction value Y obtained by the above method G is -0.2. At this time, the current cruising range information of the target vehicle is less than the cruising range threshold. The weight of the cruising range prediction value is 0.7, and the weight of the time prediction value is 0.3. The charging prediction value after weighted summation of the cruising range prediction value and the time prediction value is 0.22.

[0084] Step S140: determining the charging timing determination method at least according to the historical charging data of the target vehicle.

[0085] In this embodiment, in response to the current charging times of the target vehicle being greater than or equal to a first threshold, the charging timing determination method is determined at least according to historical charging data of the target vehicle.

[0086] The historical charging data includes one or more of the charging time, remaining mileage and remaining power of the target vehicle when it is charged. The charging time may include information such as xxxx year xx month xx day, xx hour xx minute, week x, etc. The remaining power may be the actual value of the remaining power or the percentage of the actual value to the total capacity. The remaining mileage may be the actual value of the remaining mileage or the percentage of the actual mileage to the total travel distance when fully charged.

[0087] In an optional implementation, the charging timing determination method is determined at least based on the historical charging data of the target vehicle: a second determination method is obtained by statistically analyzing the historical charging information of the target vehicle, and the second determination method is the charging regularity of the target vehicle. The second determination method is determined based on a cruising range threshold and / or a time interval threshold, and the cruising range threshold includes a power threshold and / or a mileage threshold.

[0088] The cruising range threshold and / or time interval threshold are obtained based on the historical charging data of the target vehicle. The average value of the remaining power during charging in the historical charging data can be used as the power threshold, the average value of the time intervals between two adjacent times in the historical charging data can be used as the time interval threshold, and the remaining mileage during charging in the historical charging data can be used as the mileage threshold.

[0089] Therefore, referring to the first determination method in the above step S130, the second determination method also obtains the endurance threshold and / or the time interval threshold, and then determines the charging timing based on the same method.

[0090] It should be noted that although the first determination method and the second determination method require the use of power thresholds, mileage thresholds, and time interval thresholds, the power thresholds, mileage thresholds, and time interval thresholds in the first determination method are obtained based on historical data of other vehicles with the same attributes as the target vehicle, while the power thresholds, mileage thresholds, and time interval thresholds in the second determination method are obtained based on historical data of the target vehicle itself. Therefore, each user's car usage habits are different, so the power thresholds, mileage thresholds, and time interval thresholds in the first determination method and the second determination method are often different. The power thresholds, mileage thresholds, and time interval thresholds in the second determination method can better represent the habits of the user of the target vehicle.

[0091] In another optional implementation, the charging timing determination method is determined at least based on the historical charging data of the target vehicle: statistical analysis is performed on the historical charging information of the target vehicle to obtain a second determination method, and the charging timing determination method is obtained according to the first determination method and the second determination method. The second determination method is the charging regularity of the target vehicle. Among them, the second determination method is determined according to the endurance threshold and / or the time interval threshold, and the endurance threshold includes a power threshold and / or a mileage threshold. Specifically, the charging prediction value corresponding to the first determination method can be obtained first, and then the charging prediction value corresponding to the second determination method can be obtained, and the charging prediction value corresponding to the first determination method and the second determination method can be weighted summed to obtain the charging prediction value. Among them, the method for obtaining the charging prediction value can refer to the first determination method described above, and the embodiments of the present invention will not be repeated here.

[0092] In another optional implementation, the charging timing determination method is determined at least based on the historical charging data of the target vehicle: a charging timing judgment model is obtained based on the historical charging information of the target vehicle. Specifically, the prediction model is trained with the historical charging information of the target vehicle to obtain the charging timing judgment model, and the charging timing judgment model is used as the second determination method.

[0093] In some embodiments, the charging timing judgment model is a binary classification model. Model training is performed based on abundant historical vehicle charging data. The online data is predicted in real time based on the trained model to draw a conclusion on whether to charge. Specifically, the charging timing judgment model is trained based on the historical charging data of the target vehicle to obtain a pre-trained charging timing judgment model. The current vehicle information obtained is input into the pre-trained charging timing judgment model, and the pre-trained charging timing judgment model outputs whether the target vehicle meets the charging timing.

[0094] Furthermore, the charging timing judgment model can be trained using a logistic regression model.

[0095] Specifically, x is a historical charging sample, and the key features of x include charging time, remaining mileage during charging, remaining power during charging, weather conditions (such as temperature, weather, etc.), etc., where weather conditions can be obtained through the Internet. Set the label y of x to 0 or 1 (0 represents no charging, 1 represents charging), and the probability formula is: p(y=1|x). Based on the known y and x, a set of parameters θ is trained to maximize the probability of the sample appearing. When θ is determined, the current data x of the target vehicle is input, and the output is the probability p.

[0096] Among them, the training formula of the model is:

[0097]

[0098] Among them, x is the input sample, θ is the parameter to be solved, x i is the i-th sample, θ i is the parameter corresponding to the i-th sample.

[0099] Step S150: Determine whether the current charging demand of the target vehicle meets the charging opportunity.

[0100] In this embodiment, the current charging demand of the target vehicle is determined according to the above-mentioned charging timing determination method, that is, whether the vehicle currently needs to be charged is determined according to the charging timing determination method.

[0101] As described above, in response to the target vehicle's current charging times being less than a first threshold, the charging timing determination method for the target vehicle is set to a first determination method, which is determined based on a cruising range threshold and / or a time interval threshold, and the cruising range threshold includes a power threshold and / or a mileage threshold.

[0102] When the first determination method is that the remaining power is less than or equal to the power threshold, it is determined whether the current remaining power of the target vehicle is less than or equal to the power threshold. If it is less than or equal to the power threshold, it is determined that the current charging demand of the target vehicle meets the charging opportunity, that is, the target vehicle needs to be charged and the user needs to be prompted to charge. If it is greater than the power threshold, it is determined that the current charging demand of the target vehicle does not meet the charging opportunity, that is, the target vehicle does not need to be charged at present.

[0103] When the first determination method is that the remaining mileage is less than or equal to the mileage threshold, it is determined whether the current remaining mileage of the target vehicle is less than or equal to the mileage threshold. If it is less than or equal to the mileage threshold, it is determined that the current charging demand of the target vehicle meets the charging opportunity, that is, the target vehicle needs to be charged and the user needs to be prompted to charge. If it is greater than the mileage threshold, it is determined that the current charging demand of the target vehicle does not meet the charging opportunity, that is, the target vehicle does not need to be charged at present.

[0104] When the first determination mode is that the remaining power is less than or equal to the power threshold, and the remaining mileage is less than or equal to the mileage threshold, it is determined whether the current remaining mileage of the target vehicle is less than or equal to the mileage threshold, and whether the remaining power is less than or equal to the power threshold. If the remaining mileage is less than or equal to the mileage threshold and the remaining power is less than or equal to the power threshold, it is determined that the current charging demand of the target vehicle meets the charging opportunity, that is, the target vehicle needs to be charged, and the user needs to be prompted to charge. If the remaining mileage is greater than the mileage threshold, or the remaining power is greater than the power threshold, it is determined that the current charging demand of the target vehicle does not meet the charging opportunity, that is, the target vehicle does not need to be charged at present. Alternatively, the first predicted value corresponding to the remaining power and the first predicted value corresponding to the remaining mileage can be calculated respectively, and the weighted sum is obtained to obtain the charging prediction value, and the charging prediction value is compared to see whether it reaches the charging threshold. If the charging prediction value reaches the charging threshold, it is determined that the current charging demand of the target vehicle meets the charging opportunity, that is, the target vehicle needs to be charged, and the user needs to be prompted to charge. If the charging prediction value does not reach the charging threshold, it is determined that the current charging demand of the target vehicle does not meet the charging opportunity, that is, the target vehicle does not need to be charged at present. The charging threshold value may be set to any value according to actual needs, for example, 0, 0.1, 0.2, etc.

[0105] When the first determination method is that the time interval between the target vehicle and the last charge is greater than or equal to the time interval threshold, it is determined whether the current time interval of the target vehicle is greater than or equal to the time interval threshold. If it is greater than or equal to the time interval threshold, it is determined that the current charging demand of the target vehicle meets the charging opportunity, that is, the target vehicle needs to be charged and the user needs to be prompted to charge. If it is less than the time interval threshold, it is determined that the current charging demand of the target vehicle does not meet the charging opportunity, that is, the target vehicle does not need to be charged at present.

[0106] When the first determination method is determined by the endurance threshold and the time interval threshold, the charging prediction value of the target vehicle is calculated, and the charging prediction value is compared with the charging threshold. If the charging prediction value is greater than or equal to the charging threshold, it is determined that the current charging demand of the target vehicle meets the charging opportunity, that is, the target vehicle needs to be charged and the user needs to be prompted to charge. If it is less than the charging threshold, it is determined that the current charging demand of the target vehicle does not meet the charging opportunity, that is, the target vehicle does not need to be charged at present.

[0107] For example, assuming that the current cruising range information of the target vehicle is less than or equal to the cruising range threshold, the weight of the cruising range prediction value is 0.7, and the weight of the time prediction value is 0.3. When the current cruising range information of the target vehicle is greater than the cruising range threshold, the weight of the cruising range prediction value is 0.3, the weight of the time prediction value is 0.7, and the charging threshold is set to 0.1. When the first determination method is determined by the mileage threshold and the time interval threshold, and the obtained mileage threshold is 50km (kilometers), the time interval threshold is 100h (hours). If the target vehicle's current remaining mileage is 70 km and the time interval from the last charge is 120 hours, the endurance prediction value YL obtained by the above method is -0.4, and the time prediction value YG obtained by the above method is 0.2. At this time, the target vehicle's current endurance information is greater than the endurance threshold, the weight of the endurance prediction value is 0.3, and the weight of the time prediction value is 0.7. The charging prediction value after the weighted sum of the endurance prediction value and the time prediction value is 0.02, which is less than 0.1. It is judged that the current charging demand of the target vehicle does not meet the charging opportunity, that is, the target vehicle does not need to be charged currently. If the target vehicle's current remaining mileage is 30 km and the time interval from the last charge is 80 hours, the endurance prediction value YL obtained by the above method is 0.4, and the time prediction value YG obtained by the above method is -0.2. At this time, the target vehicle's current endurance information is less than the endurance threshold, the weight of the endurance prediction value is 0.7, and the weight of the time prediction value is 0.3. The charging prediction value after weighted summation of the endurance prediction value and the time prediction value is 0.22, which is greater than 0.1. It is judged that the current charging demand of the target vehicle meets the charging opportunity, that is, the target vehicle needs to be charged, and the user needs to be prompted to charge.

[0108] Further, in response to the current charging times of the target vehicle being greater than or equal to a first threshold, the charging timing determination method is determined at least according to historical charging data of the target vehicle.

[0109] In an optional implementation, the second determination method is determined according to a cruising range threshold and / or a time interval threshold, and the cruising range threshold includes a power threshold and / or a mileage threshold. The cruising range threshold and / or the time interval threshold are obtained according to the historical charging data of the target vehicle. The average value of the remaining power during charging in the historical charging data can be counted as the power threshold, the average value of the time intervals between two adjacent times in the historical charging data can be counted as the time interval threshold, and the remaining mileage during charging in the historical charging data can be counted as the mileage threshold.

[0110] Therefore, referring to the above-mentioned first determination method, the charging timing can also be determined through the second determination method.

[0111] In another optional implementation, the charging timing determination method is determined at least based on the historical charging data of the target vehicle: statistical analysis is performed on the historical charging information of the target vehicle to obtain a second determination method, and the charging timing determination method is obtained according to the first determination method and the second determination method. The second determination method is the charging regularity of the target vehicle. Among them, the second determination method is determined according to the endurance threshold and / or the time interval threshold, and the endurance threshold includes a power threshold and / or a mileage threshold. Specifically, the charging prediction value corresponding to the first determination method can be obtained first, and then the charging prediction value corresponding to the second determination method can be obtained, and the charging prediction value corresponding to the first determination method and the second determination method can be weighted summed to obtain the charging prediction value. Among them, the method for obtaining the charging prediction value can refer to the first determination method described above, and the embodiments of the present invention will not be repeated here. For example, assuming that the charging threshold is set to 0.1, the charging prediction value calculated by the first determination method is 0.2, the charging prediction value calculated by the second determination method is 0.04, and the weight corresponding to the first determination method is 0.5, and the weight corresponding to the second determination method is 0.5, then the charging prediction value obtained by the first determination method and the second determination method is 0.2*0.5+0.04*0.5=0.12, which is greater than 0.1, then it is judged that the current charging demand of the target vehicle meets the charging timing, that is, the target vehicle needs to be charged, and the user needs to be prompted to charge.

[0112] In another optional implementation, the charging timing determination method is determined at least based on the historical charging data of the target vehicle: a charging timing judgment model is obtained based on the historical charging information of the target vehicle. Specifically, the prediction model is trained through the historical charging information of the target vehicle to obtain a charging timing judgment model, and the charging timing judgment model is used as the second determination method. Specifically, the target vehicle obtains the current vehicle information, including the current time point, the current remaining power, the current remaining mileage, the current weather conditions (such as temperature, weather, etc.), etc., and the vehicle information is input into the pre-trained charging timing judgment model, and the charging timing judgment model outputs whether to charge. For example, if the charging timing judgment model output is 1, it means that the current charging demand of the target vehicle meets the charging timing, that is, the target vehicle needs to be charged, and the user needs to be prompted to charge. If the charging timing judgment model output is 0, it means that the current charging demand of the target vehicle does not meet the charging timing, that is, the target vehicle does not need to be charged.

[0113] It should be understood that the several methods listed above are only several examples provided in the embodiments of the present invention. The specific implementation method of the embodiments of the present invention is not limited and can be implemented based on various existing methods. For example, the charging timing can also be predicted by combining multiple of the above methods at the same time.

[0114] Further, in response to the charging demand of the target vehicle meeting the charging opportunity, the process proceeds to step S160.

[0115] In response to the charging demand of the target vehicle not meeting the charging opportunity, the process returns to step S110 to wait for the next charging opportunity determination.

[0116] Step S160: Prompt the user to charge.

[0117] Further, in response to the charging demand of the target vehicle meeting the charging opportunity, the user is prompted to charge.

[0118] The embodiment of the present invention obtains the current charging times of the target vehicle after obtaining the user's authorization, in compliance with the provisions of relevant laws and regulations, without infringing on the privacy of others and without violating public order and good morals, and selects the corresponding charging timing determination method according to the charging times to judge the current charging demand of the target vehicle, and prompts the user to charge when the target vehicle meets the charging timing after the user enables the relevant prompt function. In this way, the accuracy and timeliness of the vehicle charging prompt can be improved, the occurrence of users missing charging can be reduced, and the user experience can be improved.

[0119] Figure 4 FIG. 1 is a flow chart of a charging reminder method according to a second embodiment of the present invention. Figure 4In the embodiment shown, the vehicle charging reminder method is used to determine the timing of reminding the user to charge, which can be executed by a control device inside the target vehicle, such as a BMS (BATTERY MANAGEMENT SYSTEM), or by a server connected to the target vehicle. The embodiment of the present invention is described by taking the execution by the target vehicle as an example, and the vehicle reminder method specifically includes the following steps:

[0120] Step S210: Obtain the current charging times of the target vehicle.

[0121] In this embodiment, since the target vehicle is currently charged less frequently, the historical charging data of the target vehicle cannot accurately reflect the user's charging patterns and habits, etc., while when the target vehicle is currently charged more frequently, the historical charging data of the target vehicle can more accurately reflect the user's charging patterns and habits, etc. Therefore, the current charging demand of the target vehicle can be judged by selecting different charging timing determination methods according to the interval in which the target vehicle is currently charged.

[0122] Furthermore, the embodiment of the present invention divides the number of charging times into three intervals by setting a first threshold value N1 and a second threshold value N2, namely a first interval [0, N1), a second interval [N1, N2) and a third interval [N2, +∞). Among them, the first interval [0, N1) means that the number of charging times is less than the first threshold value N1, the second interval [N1, N2) means that the number of charging times is greater than or equal to the first threshold value N1 and less than the second threshold value N2, and the third interval [N2, +∞) means that the number of charging times is greater than or equal to the second threshold value N2.

[0123] It should be understood that the intervals set above are only an example provided by the embodiment of the present invention. The embodiment of the present invention does not limit the boundaries of each interval. For example, the three intervals may also be a first interval [0, N1], a second interval (N1, N2] and a third interval (N2, +∞), wherein the first interval [0, N1] means that the number of charging times is less than or equal to the first threshold N1, the second interval (N1, N2] means that the number of charging times is greater than the first threshold N1 and less than or equal to the second threshold N2, and the third interval (N2, +∞) means that the number of charging times is greater than the second threshold N2.

[0124] Furthermore, the first threshold and the second threshold are positive integers greater than 0, and the first threshold is less than the second threshold. The first threshold and the second threshold can be set to any value, for example, the first threshold is 100, the second threshold is 500, and so on.

[0125] Furthermore, the determination of the interval in which the current number of charging times of the target vehicle is located may be implemented based on various existing methods, and the embodiment of the present invention is implemented through steps S220-S230.

[0126] Step S220: determine whether the number of charging times is less than a first threshold.

[0127] In this embodiment, in response to the number of charging times being less than the first threshold, it indicates that the current number of charging times of the target vehicle is in the first interval, and the process goes to step S240.

[0128] In response to the number of charging times being greater than or equal to the first threshold, it indicates that the current number of charging times of the target vehicle is in the second interval or the third interval, and the process goes to step S230.

[0129] Step S230: determine whether the number of charging times is less than a second threshold.

[0130] In this embodiment, in response to the number of charging times being less than the second threshold, it indicates that the current number of charging times of the target vehicle is in the second interval, and the process goes to step S250.

[0131] In response to the number of charging times being greater than or equal to the second threshold, it indicates that the current number of charging times of the target vehicle is in the third interval, and the process goes to step S260.

[0132] Step S240: The charging timing of the target vehicle is determined in a first determination manner.

[0133] In this embodiment, in response to the number of charging times being less than the first threshold, it indicates that the current number of charging times of the target vehicle is in the first interval, and the charging timing determination method of the target vehicle is determined to be the first determination method. The specific implementation method of the first determination method can refer to the above step S130, and the embodiment of the present invention will not be repeated here.

[0134] Step S250: The charging timing of the target vehicle is determined in the second determination method.

[0135] In this embodiment, in response to the number of charging times being less than the second threshold, it indicates that the current number of charging times of the target vehicle is in the second interval, and the charging timing determination method of the target vehicle is determined to be the second determination method. The specific implementation method of the second determination method can refer to the second determination method in the above step S140, and the embodiment of the present invention will not be repeated here.

[0136] In some embodiments, when the number of charging times is in the second interval, the charging timing determination method for the target vehicle is the first determination method and the second determination method. The specific implementation method can also refer to the above step S140, and the embodiment of the present invention will not be repeated here.

[0137] Step S260: The charging timing of the target vehicle is determined by a charging timing judgment model.

[0138] In this embodiment, in response to the number of charging times being greater than or equal to the second threshold, it indicates that the current number of charging times of the target vehicle is in the third interval, and the charging timing determination method of the target vehicle is determined to be the charging timing judgment model.

[0139] Specifically, the prediction model is trained through the historical charging information of the target vehicle to obtain a charging timing judgment model, and the charging timing judgment model is used as the second determination method. Specifically, the target vehicle obtains the current vehicle information, including the current time point, the current remaining power, the current remaining mileage, the current weather conditions (such as temperature, weather, etc.), etc., and inputs the vehicle information into the pre-trained charging timing judgment model, and the charging timing judgment model outputs whether to charge. For example, if the charging timing judgment model output is 1, it means that the current charging demand of the target vehicle meets the charging timing, that is, the target vehicle needs to be charged, and the user needs to be prompted to charge. If the charging timing judgment model output is 0, it means that the current charging demand of the target vehicle does not meet the charging timing, that is, the target vehicle does not need to be charged.

[0140] It should be understood that the several methods listed above are only several examples provided in the embodiments of the present invention. The specific implementation method of the embodiments of the present invention is not limited and can be implemented based on various existing methods. For example, the charging timing can also be predicted by combining multiple of the above methods at the same time.

[0141] Step S270: Determine whether the current charging demand of the target vehicle meets the charging timing.

[0142] In this embodiment, the current charging demand of the target vehicle is determined according to the above-mentioned charging timing determination method, that is, whether the vehicle currently needs to be charged is determined according to the charging timing determination method. The specific implementation method can refer to the above-mentioned step S150, and the embodiment of the present invention will not be repeated here.

[0143] Further, in response to the charging demand of the target vehicle meeting the charging opportunity, step S280 is entered.

[0144] In response to the charging demand of the target vehicle not meeting the charging opportunity, the process returns to step S210 to wait for the next charging opportunity determination.

[0145] Step S280: Prompt the user to charge.

[0146] Further, in response to the charging demand of the target vehicle meeting the charging opportunity, the user is prompted to charge.

[0147] The embodiment of the present invention determines the current charging demand of the target vehicle by obtaining the current charging times of the target vehicle, selecting the corresponding charging timing determination method according to the charging times, and prompting the user to charge when the target vehicle meets the charging timing. In this way, the accuracy and timeliness of vehicle charging prompts can be improved, the occurrence of users missing charging can be reduced, and the user experience can be improved.

[0148] Among them, prompting the user to charge can be implemented based on various existing methods.

[0149] For example, users are prompted with relevant information such as "charge in time" through voice prompts, interface displays, etc.

[0150] For another example, a recommended charging station matching the target vehicle may be obtained, and the recommended charging station and charging prompt information may be pushed to the user so that the user can select a suitable charging station from the recommended charging stations and charge.

[0151] Specifically, Figure 5 is a flow chart of obtaining a recommended charging station according to an embodiment of the present invention. Figure 5 In the illustrated embodiment, obtaining the recommended charging station includes the following steps:

[0152] Step S310: Acquire real-time data.

[0153] In this embodiment, the real-time data includes vehicle data and charging station data. The vehicle data includes the vehicle location, and the charging station data includes the charging station location and the number of idle charging guns.

[0154] Furthermore, the vehicle data also includes information such as the remaining power and remaining mileage of the target vehicle, and the real-time data also includes information such as road conditions, wherein the road conditions can be obtained through map software and other means.

[0155] Step S320: Determine a candidate charging station according to the vehicle position and the charging station position.

[0156] In this embodiment, charging stations within a predetermined range are acquired as candidate charging stations according to the vehicle position.

[0157] In an optional implementation, the predetermined range can be set according to a predetermined distance, and charging stations within the predetermined distance range are obtained as candidate charging stations, wherein the predetermined distance range can be within a straight-line distance range, that is, within a circle with the position of the target vehicle as the center and the predetermined distance as the radius. Alternatively, the predetermined distance range can also be within a driving distance range, that is, the length of the driving path between the target vehicle and the charging station is less than the predetermined distance.

[0158] In another optional implementation, the predetermined range can be set according to the current remaining mileage of the target vehicle, for example, the remaining mileage is set as the predetermined distance, or the remaining mileage is multiplied by a certain ratio (for example, 80% of the remaining mileage) to set the predetermined distance, or the remaining mileage is subtracted by a certain value (for example, the remaining mileage is subtracted by 3km) to set the predetermined distance. The predetermined distance range is within the driving distance range, that is, the length of the driving path between the target vehicle and the charging station is less than the predetermined distance.

[0159] Step S330: Determine the recommendation score of each candidate charging station.

[0160] In this embodiment, after the recommended charging station is obtained, the recommendation score of each candidate charging station is determined, wherein the recommendation score is used to represent the matching degree between the candidate charging station and the target vehicle.

[0161] Furthermore, when the target vehicle is charged less frequently, the historical data of the target vehicle cannot reflect the user's charging habits, but when the target vehicle is charged more frequently, the historical data of the target vehicle can more accurately reflect the user's charging habits. Therefore, the embodiment of the present invention improves the accuracy of the recommended score by selecting different methods to determine the recommended score according to the number of times the target vehicle is charged.

[0162] Specifically, Figure 6 is a flow chart of determining a recommendation score according to an embodiment of the present invention. Figure 6 In the illustrated embodiment, determining the recommended score for each charging station includes the following steps:

[0163] Step S331, obtaining the current charging times of the target vehicle.

[0164] Step S332: Compare whether the number of charging times is less than or equal to a third threshold.

[0165] In this embodiment, a third threshold is preset, and the charging stage of the target vehicle is determined by comparing the number of charging times with the third threshold, and the charging stage includes a first stage and a second stage. In the first stage, the number of charging times of the target vehicle is small, and in the second stage, the number of charging times of the target vehicle is large.

[0166] Further, in response to the current charging number of the target vehicle being less than or equal to the third threshold, the process proceeds to steps S333-S334.

[0167] In response to the current charging times of the target vehicle being greater than the third threshold, the process proceeds to steps S335-S336.

[0168] Step S333: determine that the charging stage of the target vehicle is the first stage.

[0169] In this embodiment, in response to the current charging times of the target vehicle being less than or equal to a third threshold, it is determined that the charging stage of the target vehicle is the first stage.

[0170] Step S334: determine the recommendation score of each candidate charging station according to the distance between the location of each charging station and the location of the vehicle and the number of idle charging guns.

[0171] In this embodiment, the location information of the target vehicle is obtained, the location information of the charging station and the number of idle charging guns are obtained, and the distance between the location of the target vehicle and the location of the charging station is obtained, and the distance can be a straight-line distance or the length of the driving path. Then, the recommendation score is determined according to the distance between the location of the target vehicle and the location of the charging station and the number of idle charging guns.

[0172] In some embodiments, taking the distance as the length of the driving path as an example, the formula for determining the recommendation score is as follows:

[0173]

[0174] Among them, S i is the recommendation score of the i-th candidate charging station, d i represents the order of the i-th charging station, D i represents the distance between the i-th charging station and the target vehicle, h i is the number of idle charging guns at the i-th charging station, r is the distance ratio, and 1-r is the ratio of idle charging guns, where r is greater than or equal to 0 and less than or equal to 1.

[0175] Among them, for d0, firstly, according to the driving distance from the target vehicle to each candidate charging station, they are arranged in descending order according to the driving distance. The smaller the driving distance, the greater the arrangement order. Thus, the arrangement order of the i-th charging station can be obtained.

[0176] For example, Figure 7The position and path of the target vehicle Car and four candidate charging stations B1, B2, B3 and B4 are shown. Assume that the driving distances between the target vehicle Car and the candidate charging stations B1, B2, B3 and B4 are 5km, 12km, 8km and 3km respectively, D1=5, D2=12, D3=8, D4=3, and the distance ratio r is 0.6. The number of charging guns of the candidate charging stations B1, B2, B3 and B4 are 3, 5, 4 and 1 respectively, that is, h1=3, h2=5, h3=4, h4=1. Sorting by driving distance from large to small, the sequence of candidate charging stations is: (B2, B3, B1, B4), that is, d1=3, d2=1, d3=2, d4=4. Therefore, the recommended scores of candidate charging stations B1, B2, B3 and B4 are:

[0177]

[0178]

[0179]

[0180]

[0181] That is, the recommendation scores of the candidate charging stations B1, B2, B3 and B4 are 1.56, 2.05, 1.75 and 1.2, respectively.

[0182] Step S335: determine that the charging stage of the target vehicle is the second stage.

[0183] In this embodiment, in response to the current charging times of the target vehicle being greater than a third threshold, it is determined that the charging stage of the target vehicle is the second stage.

[0184] Step S336: Determine the recommendation score of each candidate charging station according to the real-time data using a pre-trained recommendation model.

[0185] In this embodiment, in response to the current charging times of the target vehicle being greater than the third threshold, it indicates that the current historical charging data of the target vehicle has accumulated to a certain extent, and therefore, the historical charging data of the target vehicle trains the recommendation model to obtain a pre-trained recommendation model. After the current parameters are input into the pre-trained recommendation model, the pre-trained recommendation model outputs a recommendation score.

[0186] In some embodiments, the recommended model is XGBoost (Extreme Gradient Boosting gradient promotion model). The XGBoost model is to train the next tree on the basis of training a tree to predict the gap between it and the real distribution. By continuously training the tree used to make up for the gap, the simulation of the real distribution is finally achieved with the combination of trees. The objective function of XGboost includes two parts: loss function and regular term. Among them, the loss function represents the degree of model fitting data. Usually, its first-order derivative is used to point out the direction of gradient descent. XGboost also calculates its second-order derivative, further considering the trend of gradient change, fitting faster and more accurate. The regular term is used to control the complexity of the model. The more leaf nodes, the larger the model, not only the operation time is long, but also overfitting after exceeding a certain limit, resulting in a decrease in classification effect. The regular term of XGboost is a penalty mechanism. The more leaf nodes there are, the greater the penalty, thereby limiting the number of leaf nodes.

[0187] First, training samples are generated based on the historical charging data, user behavior data, and historical data of charging stations of the target vehicle, and the initial recommendation model is trained based on the training samples to obtain a pre-trained recommendation model. Among them, the historical charging data is used to characterize features such as whether the vehicle is charged at certain charging stations in the historical time period, the user behavior data includes cross features such as whether the user collects or clicks on certain charging stations, and the historical data of charging stations is data that combines the features of the charging station itself, such as navigation distance, price, number of idle guns, and expected charging waiting time. Among them, a training sample can be generated for each charging, or after screening, a training sample can be generated, for example, samples with a charging time less than a predetermined time (for example, 5 minutes) are deleted to improve the accuracy of the model. Among them, each training sample includes features and labels, wherein the features are obtained based on the above historical charging data, user behavior data, and historical data of charging stations, the labels can be recommendation scores, the recommendation scores can be set manually, and the labels can also be the probability of the charging station being selected. For a certain training sample, the selected charging station is marked as 1, and the other unselected charging stations are marked as 0. For the i-th sample, the feature is recorded as xi and the label is yi. Then the sample data set A is:

[0188] A={(x i ,y i )}

[0189] Wherein, xi is the feature of the i-th training sample, yi is the label of the i-th training sample, i=1, 2,...,n, and n is the number of training samples.

[0190] The recommendation model actually continuously adds trees and continuously splits features to grow a tree. Each time a tree is added, a new function f(x) is actually learned to fit the residual of the previous prediction. When the training is completed and K trees are obtained, to predict the score of a sample, it is actually based on the characteristics of the sample. In each tree, it will fall into a corresponding leaf node, and each leaf node corresponds to a score. Finally, you only need to add up the scores corresponding to each tree to get the predicted value of the sample.

[0191] The model function of the recommendation model can be expressed as K regression tree superpositions. The specific formula is:

[0192]

[0193] in, represents the predicted recommendation score of the i-th training sample, g k represents the base learner, F represents the regression tree model space, and K represents the number of regression trees.

[0194] Furthermore, the objective function is:

[0195]

[0196] in, represents the predicted recommendation score of the i-th training sample, y i represents the label of the i-th training sample, l represents the loss function, and Ω represents the complexity of the model, that is, parameters such as the depth of the tree and the number of leaf nodes.

[0197] in, is a differentiable loss function. is a regularization term, which is related to the structure (number of leaf nodes) and weight of leaf nodes of each tree.

[0198] Furthermore, in order to make the prediction value of the tree group As close as possible to the true value y i , and has the greatest possible generalization ability. XGBoost also needs to accumulate the scores of multiple trees to get the final prediction score (each iteration, based on the existing tree, a tree is added to fit the residual between the prediction result of the previous tree and the true value). The specific formula is as follows:

[0199]

[0200]

[0201]

[0202] …

[0203]

[0204] In the above formula, represents the predicted recommendation score of the i-th sample in the t-th iteration, f t (x i ) represents the residual of the t-th iteration.

[0205] The purpose of training is to obtain f(x) to minimize the objective function. The method of splitting nodes can be achieved by enumerating all different tree structures in a greedy way. Continuously enumerate the structures of different trees, and then use the scoring function to find a tree with the optimal structure, then add it to the model, and repeat this operation. The search process uses a greedy algorithm. Select a feature split, calculate the minimum value of the loss function, and then select another feature split to get another minimum value of the loss function. After enumeration, find the one with the best effect, split the tree, and get the tree structure. That is, using the greedy algorithm, traverse all feature partition points of all features, the difference is that the objective function used is different. The specific method is that the objective function value after the split is greater than the gain of the objective function of a single leaf node. At the same time, in order to limit the growth of the tree from being too deep, a threshold is added. Only when the gain is greater than the threshold will the split be performed. In this way, the split continues to form a tree, and then another tree, and each time the best is taken based on the previous prediction to further split / build the tree. By setting the maximum depth of the tree, when the sample weight sum is less than the set threshold, it will stop growing to prevent overfitting. When the gain brought by the introduced split is less than the set threshold, the split can be ignored, so not every split loss will increase overall. When the tree reaches the maximum depth, stop building the decision tree. Set a hyperparameter to avoid the tree being too deep and leading to learning local samples, thereby overfitting. Stop building the tree when the sample weight is less than the set threshold.

[0206] In this way, a pre-trained recommendation model can be obtained.

[0207] When predicting the recommendation score, the current data of the target vehicle is input into the recommendation model, and the recommendation model outputs the recommendation score of each candidate charging station, wherein the recommendation score may be the probability of each candidate charging station being selected.

[0208] Step S340: Select at least one recommended charging station from the candidate charging stations according to the recommendation score and push it to the user.

[0209] In this embodiment, after the recommendation scores of the candidate charging stations are obtained, at least one recommended charging station is selected from the candidate charging stations according to the recommendation scores, and the recommended charging station is pushed to the user.

[0210] In this embodiment, a higher recommendation score of a candidate charging station indicates a higher matching degree between the candidate charging station and the user. Therefore, a predetermined number of candidate charging stations may be selected as recommended charging stations according to the recommendation scores.

[0211] For example, assuming that the number of recommended charging stations is set to 3, the three charging stations with the largest recommendation scores are selected as the recommended charging stations.

[0212] Furthermore, pushing the recommended charging station to the user is specifically performed by displaying a display interface of the recommended charging station through a display device; wherein the display interface includes one or more of an electronic map, a list of recommended charging stations, location information of recommended charging stations, charging prices, the number of idle charging guns, location information of recommended charging stations in the electronic map, charging success rate and charging time.

[0213] Specifically, the display device may be a vehicle-mounted display screen, or may be a terminal device used by a user, such as a tablet computer, a mobile phone, or other device.

[0214] Furthermore, the charging station data also includes the business characteristics of the charging station; wherein the display interface of the recommended charging station displayed by the display device specifically displays the recommended charging station list after sorting the recommended charging stations according to the business characteristics of the charging station. The business characteristics include marketing activities, etc.

[0215] Specifically, assume the location and path of the target vehicle Car and four candidate charging stations B1, B2, B3 and B4. Assume that the driving distances of the target vehicle Car and the candidate charging stations B1, B2, B3 and B4 are 5km, 12km, 8km and 3km respectively, the number of charging guns of the candidate charging stations B1, B2, B3 and B4 are 3, 5, 4 and 1 respectively, and the recommendation scores of the candidate charging stations B1, B2, B3 and B4 are 1.56, 2.05, 1.75 and 1.2 respectively. If it is preset to obtain 3 recommended charging stations, the three recommended charging stations selected from the largest to the smallest recommendation scores are charging stations B2, B3 and B1.

[0216] In some embodiments, after obtaining each recommended charging station, the recommended charging stations may be sorted according to the business characteristics of each recommended charging station and then displayed as a list of recommended charging stations.

[0217] In some embodiments, the recommendation model can also be trained offline. Specifically, the recommendation model can be retrained after each predetermined number of charges (e.g., 1 time, 5 times, 10 times, etc.), or every predetermined time period (e.g., 1 day, 5 days, 10 days, etc.). Thus, as the user uses the car, the model is trained by continuously updating the training samples to improve the accuracy of the opinion model prediction.

[0218] in, Figure 8 Schematic diagram of a display interface of an embodiment of the present invention. Figure 8 In the illustrated embodiment, the display interface includes one or more of an electronic map, a list of recommended charging stations, location information of recommended charging stations, charging prices, the number of idle charging guns, and location information of recommended charging stations in the electronic map.

[0219] Among them, electronic maps can be Figure 8 The path shown.

[0220] The location information of the recommended charging stations in the electronic map is shown as B1, B2, and B3 in the figure. At the same time, the location of the target vehicle can also be displayed, such as Car in the figure.

[0221] The recommended charging station list is displayed in a floating window above the electronic map.

[0222] In some embodiments, the recommended charging station list may be set to be transparent or semi-transparent to facilitate the user to view the underlying map.

[0223] The location information of the recommended charging stations is displayed in the recommended charging stations list, such as the xx address in the figure.

[0224] The charging price is displayed in the recommended charging station list, such as 1.6 / kWh, 1.8 / kWh, 1.9 / kWh, etc. in the figure, and the unit is 1.6 yuan per kWh.

[0225] The number of idle charging guns is displayed in the recommended charging station list, and the types of charging guns can also be displayed, such as fast charging guns and slow charging guns. Figure 8 In the figure, "Fast, Empty 2 / 7" means there are 7 fast charging guns, two of which are idle, and "Slow, Empty 3 / 6" means there are 6 slow charging guns, three of which are idle.

[0226] In some embodiments, the display interface also includes distance information, such as 12 km, 8 km, and 5 km in the figure.

[0227] In some embodiments, the display interface also includes navigation controls, such as the arrow controls in front of 12 km, 8 km, and 5 km in the figure.

[0228] In some embodiments, the display interface also includes a reservation control, such as the "Quick Reservation" control in the figure. The user can click on the control to make a reservation for the charging gun, so as to avoid the user arriving at the charging station and finding that there are no idle charging guns to use. When the charging gun has been fully reserved, the "Full Reservation" message can be displayed, and the control cannot be triggered.

[0229] In some embodiments, the display interface can also display the charging success rate of the charging station. Fig. 9 As shown, Fig. 9 FIG. 9 is a schematic diagram of a display interface of another embodiment of the present invention. Figure 8 The electronic map, the list of recommended charging stations, the location information of the recommended charging stations, the charging price, the number of idle charging guns, the location information of the recommended charging stations in the electronic map, etc., also includes the charging success rate.

[0230] exist Fig. 9 In the illustrated embodiment, the charging success rate is displayed at the location of the corresponding charging station in the electronic map. For example, the charging success rate of charging station B1 is 80%, the charging success rate of charging station B2 is 100%, and the charging success rate of charging station B3 is 90%.

[0231] In some embodiments, the charging success rate may be obtained by inputting real-time data of the current charging station into a trained success rate prediction model for processing.

[0232] Specifically, based on the success rate prediction model, the historical evaluation of each charging station, the historical idle rate of the charging station at the corresponding time, the charging gun status and other data are processed to obtain the charging success rate of each charging station.

[0233] Among them, the status of the charging gun can be obtained based on the statistical prediction method, which is specifically determined according to the number of successes / failures of each charging station in the past predetermined time period. By monitoring the start and end time of each charging of each charging gun, the usage time t (in hours) of the gun in the nearly predetermined number of days is calculated, and then the usage rate of the charging gun in the predetermined number of days is calculated as: pa = t / (x*24). If the usage rate of the charging gun is significantly different from the usage rate of other charging guns in this station, it is considered that the gun is frequently dropped or damaged. At the same time, even if the charging gun is idle, it will not be included in the counting range of idle charging guns.

[0234] In some embodiments, the display interface can also display the charging time of the charging station. Fig.10 As shown, Fig.10 FIG. 10 is a schematic diagram of a display interface of another embodiment of the present invention. Figure 8 The electronic map, the recommended charging station list, the location information of the recommended charging stations, the charging price, the number of idle charging guns, the location information of the recommended charging stations in the electronic map, etc., also include the charging time. Among them, the charging time is used to characterize the estimated time for the target vehicle to be fully charged.

[0235] exist Fig.10In the illustrated embodiment, the charging success rate is displayed at the location of the corresponding charging station in the electronic map. For example, the charging time of charging station B1 is 25 minutes, the charging time of charging station B2 is 15 minutes, and the charging time of charging station B3 is 20 minutes.

[0236] Specifically, the charging time, that is, the time required for a full charge, can be determined based on the historical charging time of the vehicle. Although each charging station is marked with fast charging and slow charging, users cannot get an approximate charging time based on this. Therefore, based on the analysis of the historical charging time of the charging station (the time from the start to the end of charging), the charging time of the charging station can be mined, and the time of each charging station can be rendered when recommending the charging station. Among them, only the charging station with the shortest time can be marked, or the approximate time required for each charging station can be marked.

[0237] Furthermore, the embodiment of the present invention obtains the charging time efficiency through a time efficiency prediction model. The time efficiency prediction model statistically analyzes the customer arrival time and service time of each charging station based on the queuing model theory, obtains indicators such as waiting time, queue length, and charging device idle rate, and obtains the charging time efficiency based on these indicators.

[0238] For the queuing model, the charging station service system is a random system with the following specific features: the service objects are customers who have lined up to receive charging services, the customer source is unlimited, customers are independent of each other, and the time intervals between customers' arrival are random. The system has multiple charging guns and the charging service time for each customer is independent. Its service follows the first-come-first-served principle. When a customer arrives and there is an idle gun, he will charge and leave after charging. If there is no idle gun, the customer needs to wait in line until there is an idle gun and then charge in a certain order.

[0239] Specifically, the number of vehicles x arriving at the charging station per unit time is random and can be modeled as a Poisson distribution:

[0240]

[0241] Wherein, P(x=k) represents the probability when the number of vehicles arriving at the charging station in a unit time is k, k is greater than 0, and the parameter λ is the average number of occurrences of random events in a unit time.

[0242] For example, the number of vehicles M1 arriving at the charging station for charging in one day (24 hours) can be counted to obtain the parameter λ. The unit time can be hours, minutes, seconds, etc. Taking the unit time as minutes as an example, λ=M1 / (24*60).

[0243] Furthermore, the charging time of each vehicle is equivalent to the interval between two adjacent vehicles leaving the queuing system, which obeys the negative exponential distribution. The specific formula is:

[0244] f T (t) = μ*e -μt

[0245] Among them, μ is the inverse of the average charging time of the vehicle, that is, the number of vehicles that can be charged by each charging gun in a unit time, and f T (t) represents the probability that the vehicle charging time is t, t represents the charging time, and t is greater than 0.

[0246] For example, the time when vehicles leave the charging station in one day (24 hours) can be counted, the interval time between each two adjacent vehicles leaving the charging station can be obtained, and the average value of the interval time can be calculated to obtain the parameter μ.

[0247] Therefore, the parameters λ and μ can be obtained through the above.

[0248] The average service rate of the charging gun in the charging station is determined by the parameters λ and μ, and then the service intensity of the charging station can be obtained. The specific formula is as follows:

[0249]

[0250] Among them, ρ is the service intensity of the charging station, C is the total number of charging guns in the charging station, and the parameters λ and μ are obtained through the above steps.

[0251] Based on the above parameters, the state probability of the charging station can be obtained. When the number of vehicles charging at the charging station is 0, the specific formula is as follows:

[0252]

[0253] Among them, P0 represents the probability when the number of vehicles charging at the charging station is 0, ρ is the service intensity of the charging station, C is the total number of charging guns in the charging station, and the parameters λ and μ are obtained through the above steps.

[0254] When the number of vehicles charging at the charging station is 0, the specific formula is as follows:

[0255]

[0256] Among them, P n represents the probability when the number of vehicles charging at the charging station is n, P0 represents the probability when the number of vehicles charging at the charging station is 0, n is a positive integer greater than 0, ρ is the service intensity of the charging station, C is the total number of charging guns in the charging station, and the parameters λ and μ are obtained through the above steps.

[0257] Therefore, the length of the waiting queue in the charging station can be obtained as:

[0258]

[0259] Among them, L w is the length of the waiting queue in the charging station, P0 represents the probability when the number of vehicles charging at the charging station is 0, n is a positive integer greater than 0, ρ is the service intensity of the charging station, and C is the total number of charging guns in the charging station.

[0260] Therefore, the average waiting time of vehicles at the charging station can be obtained according to the length of the waiting queue in the charging station. The specific formula is as follows:

[0261]

[0262] Where W is the average waiting time of vehicles at the charging station, L w is the waiting queue length in the charging station, and the parameter λ is obtained through the above steps.

[0263] Furthermore, after the average queuing time is obtained, the charging time efficiency is obtained according to the average queuing time and the time from the start of charging to full charging of the vehicle.

[0264] The embodiment of the present invention obtains the current charging times of the target vehicle after obtaining the user's authorization, in compliance with the provisions of relevant laws and regulations, without infringing on the privacy of others and without violating public order and good morals, and selects the corresponding charging timing determination method according to the charging times to judge the current charging demand of the target vehicle, and prompts the user to charge when the target vehicle meets the charging timing after the user enables the relevant prompt function. In this way, the accuracy and timeliness of the vehicle charging prompt can be improved, the occurrence of users missing charging can be reduced, and the user experience can be improved.

[0265] Further, Fig.11 FIG11 is a flow chart of a vehicle charging method according to an embodiment of the present invention. In the embodiment shown in FIG11 , the vehicle charging method includes the following steps:

[0266] Step S410: Obtain the current charging times of the target vehicle.

[0267] Step S420: Determine a charging timing determination method for the target vehicle according to the charging times.

[0268] Step S430: determine the current charging demand of the target vehicle according to the charging timing determination method.

[0269] Step S440: In response to the charging demand of the target vehicle meeting the charging opportunity, prompting the user to charge.

[0270] In some embodiments, the method for determining the charging timing of the target vehicle according to the charging times includes:

[0271] In response to the charging number being less than a first threshold, the charging timing determination method of the target vehicle is a first determination method, the first determination method being a preset initial judgment condition; and

[0272] In response to the number of charging times being greater than or equal to a first threshold, the charging timing determination method is determined at least according to historical charging data of the target vehicle.

[0273] In some embodiments, the first determination method is determined based on a cruising range threshold and / or a time interval threshold, and the cruising range threshold includes a power threshold and / or a mileage threshold.

[0274] In some embodiments, in response to the first determination method being determined according to the endurance threshold and the time interval threshold, the first determination method is specifically:

[0275] Acquire a first prediction value corresponding to the battery life information according to the battery life threshold;

[0276] Acquire a second prediction value corresponding to the time interval according to the time interval threshold; and

[0277] The first prediction value and the second prediction value are weightedly summed to obtain a charging prediction value, where the charging prediction value is used to characterize the probability that the target vehicle needs to be charged.

[0278] In some embodiments, the weighted sum of the first prediction value and the second prediction value to obtain the weight of the charging prediction value is obtained by the following steps:

[0279] Comparing the current cruising range information of the target vehicle with a cruising range threshold;

[0280] In response to the current cruising range information of the target vehicle being less than or equal to the cruising range threshold, determining the weight to be a first weight and a second weight, the first weight corresponding to the first predicted value, and the second weight corresponding to the second predicted value; and

[0281] In response to the current cruising range information of the target vehicle being greater than the cruising range threshold, determining the weight to be a third weight and a fourth weight, the third weight corresponding to the first predicted value, and the fourth weight corresponding to the second predicted value;

[0282] The proportion of the first weight in the first weight and the second weight is greater than the proportion of the third weight in the third weight and the fourth weight.

[0283] In some embodiments, the cruising range threshold and / or time interval threshold is determined based on historical charging information of vehicles with the same attributes as the target vehicle.

[0284] In some embodiments, the method for determining the charging timing at least based on the historical charging data of the target vehicle is specifically:

[0285] In response to the number of charging times being greater than or equal to a first threshold and less than a second threshold, statistically analyzing the historical charging information of the target vehicle to obtain a second determination method, wherein the second determination method is determined according to a cruising range threshold and / or a time interval threshold, wherein the cruising range threshold includes a power threshold and / or a mileage threshold; and

[0286] In response to the number of charging times being greater than or equal to a second threshold, a third determination method is acquired according to historical charging information of the target vehicle, and the third determination method is a charging timing judgment model.

[0287] In some embodiments, the method of determining the charging timing at least based on the historical charging data of the target vehicle includes:

[0288] In response to the number of charging times being greater than or equal to a first threshold and less than a second threshold, statistically analyzing the historical charging information of the target vehicle to obtain a second determination method, and obtaining the charging timing determination method according to the first determination method and the second determination method; and

[0289] In response to the number of charging times being greater than or equal to a second threshold, a third determination method is acquired according to historical charging information of the target vehicle, and the third determination method is a charging timing judgment model.

[0290] In some embodiments, the historical charging data includes one or more of the charging time, remaining mileage, and remaining power of the target vehicle when it is charged.

[0291] In some embodiments, the prompting the user to charge specifically includes:

[0292] Get recommended charging stations; and

[0293] The recommended charging station is pushed to the user.

[0294] In some embodiments, obtaining the recommended charging station specifically includes:

[0295] Acquire real-time data, the real-time data including vehicle data and charging station data, the vehicle data including vehicle location, the charging station data including charging station location and number of idle charging guns;

[0296] determining a candidate charging station according to the vehicle position and the charging station position;

[0297] Determining a recommendation score for each of the candidate charging stations; and

[0298] At least one recommended charging station is selected from the candidate charging stations according to the recommendation score and pushed to the user.

[0299] In some embodiments, determining the recommendation score of each of the candidate charging stations includes:

[0300] Determining a charging stage of the vehicle according to the current charging times of the vehicle, wherein the charging stage includes a first stage and a second stage;

[0301] In response to the vehicle being in the first stage, determining a recommendation score for each candidate charging station according to the distance between each charging station location and the vehicle location and the number of idle charging guns; and

[0302] In response to the vehicle being in the second stage, a recommendation score of each candidate charging station is determined according to the real-time data by using a pre-trained recommendation model.

[0303] In some embodiments, determining the charging stage of the vehicle according to the current charging times of the vehicle includes:

[0304] In response to the current charging number of the target vehicle being less than or equal to a third threshold, determining that the charging stage of the target vehicle is the first stage; and

[0305] In response to the current charging number of the target vehicle being greater than the third threshold, it is determined that the charging stage of the target vehicle is the second stage.

[0306] In some embodiments, the pushing of the recommended charging station to the user specifically includes:

[0307] Displaying a display interface of the recommended charging station through a display device;

[0308] The display interface includes one or more of an electronic map, a list of recommended charging stations, location information of recommended charging stations, charging prices, the number of idle charging guns, location information of recommended charging stations in the electronic map, charging success rate and charging time.

[0309] In some embodiments, the charging station data further includes service characteristics of the charging station;

[0310] The display interface for displaying the recommended charging station through the display device is specifically:

[0311] The recommended charging stations are sorted according to the service characteristics of the charging stations and then the recommended charging station list is displayed.

[0312] The embodiment of the present invention obtains the current charging times of the target vehicle after obtaining the user's authorization, in compliance with the provisions of relevant laws and regulations, without infringing on the privacy of others and without violating public order and good morals, and selects the corresponding charging timing determination method according to the charging times to judge the current charging demand of the target vehicle, and prompts the user to charge when the target vehicle meets the charging timing after the user enables the relevant prompt function. In this way, the accuracy and timeliness of the vehicle charging prompt can be improved, the occurrence of users missing charging can be reduced, and the user experience can be improved.

[0313] Further, Fig.12 It is a flow chart of the vehicle charging device of an embodiment of the present invention. In the embodiment shown in FIG12 , the vehicle charging device includes the following steps: a charging number acquisition unit 121, a determination method acquisition unit 122, a charging demand judgment unit 123, and a charging prompt unit 124. The charging number acquisition unit 121 is used to obtain the current charging number of the target vehicle. The determination method acquisition unit 122 is used to determine the charging timing determination method of the target vehicle according to the charging number. The charging demand judgment unit 123 is used to determine the current charging demand of the target vehicle according to the charging timing determination method. The charging prompt unit 124 is used to prompt the user to charge in response to the charging demand of the target vehicle meeting the charging timing.

[0314] In some embodiments, the determination mode acquisition unit includes:

[0315] A first determining subunit, configured to determine the charging timing of the target vehicle in a first determining manner in response to the charging number being less than a first threshold, wherein the first determining manner is a preset initial judgment condition; and

[0316] The second determination subunit is used to determine the charging timing determination method at least according to the historical charging data of the target vehicle in response to the number of charging times being greater than or equal to the first threshold.

[0317] In some embodiments, the first determination method is determined based on a cruising range threshold and / or a time interval threshold, and the cruising range threshold includes a power threshold and / or a mileage threshold.

[0318] In some embodiments, in response to the first determining method being determined according to the endurance threshold and the time interval threshold, the first determining subunit includes:

[0319] A first prediction value determination module, used to obtain a first prediction value corresponding to the battery life information according to the battery life threshold;

[0320] A second prediction value determination module, configured to obtain a second prediction value corresponding to the time interval according to the time interval threshold; and

[0321] The charging prediction value determination module is used to perform a weighted summation of the first prediction value and the second prediction value to obtain a charging prediction value, wherein the charging prediction value is used to characterize the probability that the target vehicle needs to be charged.

[0322] In some embodiments, the charging prediction value determination module includes:

[0323] A cruising range comparison submodule, used to compare the current cruising range information of the target vehicle with the cruising range threshold;

[0324] A first determining submodule, configured to determine, in response to the current cruising range information of the target vehicle being less than or equal to the cruising range threshold, that the weight is a first weight and a second weight, wherein the first weight corresponds to the first predicted value, and the second weight corresponds to the second predicted value; and

[0325] A second determination submodule, configured to determine, in response to the current cruising range information of the target vehicle being greater than the cruising range threshold, that the weight is a third weight and a fourth weight, wherein the third weight corresponds to the first predicted value, and the fourth weight corresponds to the second predicted value;

[0326] The proportion of the first weight in the first weight and the second weight is greater than the proportion of the third weight in the third weight and the fourth weight.

[0327] In some embodiments, the cruising range threshold and / or time interval threshold is determined based on historical charging information of vehicles with the same attributes as the target vehicle.

[0328] In some embodiments, the second determining subunit includes:

[0329] A first acquisition module, configured to, in response to the number of charging times being greater than or equal to a first threshold and less than a second threshold, perform statistical analysis on the historical charging information of the target vehicle to acquire a second determination method, wherein the second determination method is determined according to a cruising range threshold and / or a time interval threshold, and the cruising range threshold includes a power threshold and / or a mileage threshold; and

[0330] The second acquisition module is used to acquire a third determination method according to the historical charging information of the target vehicle in response to the number of charging times being greater than or equal to the second threshold, wherein the third determination method is a charging timing judgment model.

[0331] In some embodiments, the second determining subunit includes:

[0332] a third acquisition module, configured to, in response to the number of charging times being greater than or equal to the first threshold and less than the second threshold, perform statistical analysis on the historical charging information of the target vehicle to obtain a second determination method, and obtain the charging timing determination method according to the first determination method and the second determination method; and

[0333] The fourth acquisition module is used to acquire a third determination method according to the historical charging information of the target vehicle in response to the number of charging times being greater than or equal to the second threshold, wherein the third determination method is a charging timing judgment model.

[0334] In some embodiments, the historical charging data includes one or more of the charging time, remaining mileage, and remaining power of the target vehicle when it is charged.

[0335] In some embodiments, the charging prompt unit includes:

[0336] A recommended charging station acquisition subunit, used to acquire a recommended charging station; and

[0337] The recommended charging station push subunit is used to push the recommended charging station to the user.

[0338] In some embodiments, the recommended charging station acquisition subunit includes:

[0339] A data acquisition module, used to acquire real-time data, wherein the real-time data includes vehicle data and charging station data, wherein the vehicle data includes vehicle location, and the charging station data includes charging station location and the number of idle charging guns;

[0340] A candidate charging station determination module, configured to determine a candidate charging station according to the vehicle position and the charging station position;

[0341] a recommendation score determination module, configured to determine a recommendation score for each of the candidate charging stations; and

[0342] The recommended charging station selection module is used to select at least one recommended charging station from the candidate charging stations according to the recommendation score and push it to the user.

[0343] In some embodiments, the recommendation score determination module includes:

[0344] A charging stage determination submodule, used to determine the charging stage of the vehicle according to the current charging times of the vehicle, wherein the charging stage includes a first stage and a second stage;

[0345] A first score determination submodule, configured to determine a recommended score for each candidate charging station according to a distance between each charging station and the vehicle and the number of idle charging guns in response to the vehicle being in the first stage; and

[0346] The second score determination submodule is used to determine the recommendation score of each candidate charging station according to the real-time data by using a pre-trained recommendation model in response to the vehicle being in the second stage.

[0347] In some embodiments, the charging stage determination submodule is used to:

[0348] In response to the current charging number of the target vehicle being less than or equal to a third threshold, determining that the charging stage of the target vehicle is the first stage; and

[0349] In response to the current charging number of the target vehicle being greater than the third threshold, it is determined that the charging stage of the target vehicle is the second stage.

[0350] In some embodiments, the recommended charging station push subunit is specifically used for:

[0351] Displaying a display interface of the recommended charging station through a display device;

[0352] The display interface includes one or more of an electronic map, a list of recommended charging stations, location information of recommended charging stations, charging prices, the number of idle charging guns, location information of recommended charging stations in the electronic map, charging success rate and charging time.

[0353] In some embodiments, the charging station data further includes service characteristics of the charging station;

[0354] The display interface for displaying the recommended charging station through the display device is specifically:

[0355] The recommended charging stations are sorted according to the service characteristics of the charging stations and then the recommended charging station list is displayed.

[0356] The embodiment of the present invention obtains the current charging times of the target vehicle after obtaining the user's authorization, in compliance with the provisions of relevant laws and regulations, without infringing on the privacy of others and without violating public order and good morals, and selects the corresponding charging timing determination method according to the charging times to judge the current charging demand of the target vehicle, and prompts the user to charge when the target vehicle meets the charging timing after the user enables the relevant prompt function. In this way, the accuracy and timeliness of the vehicle charging prompt can be improved, the occurrence of users missing charging can be reduced, and the user experience can be improved.

[0357] Fig.13 is a schematic diagram of an electronic device according to an embodiment of the present invention. Fig.13The electronic device shown is a general data processing device, which includes a general computer hardware structure, which includes at least a processor 131 and a memory 132. The processor 131 and the memory 132 are connected via a bus 133. The memory 132 is suitable for storing instructions or programs executable by the processor 131. The processor 131 can be an independent microprocessor or a collection of one or more microprocessors. Thus, the processor 131 executes the instructions stored in the memory 132, thereby executing the method flow of the embodiment of the present invention as described above to realize the processing of data and the control of other devices. The bus 133 connects the above-mentioned multiple components together, and at the same time connects the above-mentioned components to the display controller 134 and the display device and the input / output (I / O) device 135. The input / output (I / O) device 135 can be a mouse, a keyboard, a modem, a network interface, a touch input device, a somatosensory input device, a printer, and other devices known in the art. Typically, the input / output device 135 is connected to the system through an input / output (I / O) controller 136.

[0358] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, devices (equipment) or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0359] The present invention is described with reference to flowcharts of methods, apparatuses (devices) and computer program products according to embodiments of the present application. It should be understood that each process in the flowchart can be implemented by computer program instructions.

[0360] These computer program instructions may be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device that implements the process Figure 1 A function specified in a process or multiple processes.

[0361] These computer program instructions may also be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce the instructions for implementing the process Figure 1 A device that specifies functions in a process or multiple processes.

[0362] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A vehicle charging method, characterized in that: The method comprises: Get the current charging times of the target vehicle; Determining a charging timing determination method for the target vehicle according to the charging number; Determining the current charging demand of the target vehicle according to the charging timing determination method; and In response to the charging demand of the target vehicle meeting the charging opportunity, prompting the user to charge; Wherein, the method for determining the charging timing of the target vehicle according to the charging times includes: In response to the charging number being less than a first threshold, the charging timing determination method of the target vehicle is a first determination method, and the first determination method is a preset initial judgment condition; The first determination method includes: Acquire a first prediction value corresponding to the battery life information according to the battery life threshold; Acquire a second prediction value corresponding to the time interval according to the charging time interval threshold; and The first prediction value and the second prediction value are weightedly summed to obtain a charging prediction value, where the charging prediction value is used to characterize the probability that the target vehicle needs to be charged.

2. The method according to claim 1, characterized in that The method for determining the charging timing of the target vehicle according to the charging times also includes: In response to the number of charging times being greater than or equal to a first threshold, the charging timing determination method is determined at least according to historical charging data of the target vehicle.

3. The method according to claim 2, characterized in that The endurance threshold includes a power threshold and / or a mileage threshold.

4. The method according to claim 1, characterized in that: The weight of the charging prediction value obtained by weighted summing of the first prediction value and the second prediction value is obtained by the following steps: Comparing the current cruising range information of the target vehicle with a cruising range threshold; In response to the current cruising range information of the target vehicle being less than or equal to the cruising range threshold, determining the weight to be a first weight and a second weight, the first weight corresponding to the first predicted value, and the second weight corresponding to the second predicted value; as well as In response to the current cruising range information of the target vehicle being greater than the cruising range threshold, determining the weight to be a third weight and a fourth weight, the third weight corresponding to the first predicted value, and the fourth weight corresponding to the second predicted value; The proportion of the first weight in the first weight and the second weight is greater than the proportion of the third weight in the third weight and the fourth weight.

5. The method according to claim 1, characterized in that The cruising range threshold and / or charging time interval threshold is determined according to historical charging information of vehicles with the same attributes as the target vehicle.

6. The method according to claim 2, characterized in that The method for determining the charging timing at least based on the historical charging data of the target vehicle includes: In response to the number of charging times being greater than or equal to a first threshold and less than a second threshold, statistically analyzing the historical charging information of the target vehicle to obtain a second determination method, wherein the second determination method is determined according to a cruising range threshold and / or a charging time interval threshold, wherein the cruising range threshold includes a power threshold and / or a mileage threshold; and In response to the number of charging times being greater than or equal to a second threshold, a third determination method is acquired according to historical charging information of the target vehicle, and the third determination method is a charging timing judgment model.

7. The method according to claim 2, characterized in that The method for determining the charging timing at least based on the historical charging data of the target vehicle includes: In response to the number of charging times being greater than or equal to a first threshold and less than a second threshold, statistically analyzing the historical charging information of the target vehicle to obtain a second determination method, and obtaining the charging timing determination method according to the first determination method and the second determination method; and In response to the number of charging times being greater than or equal to a second threshold, a third determination method is acquired according to historical charging information of the target vehicle, and the third determination method is a charging timing judgment model.

8. The method according to claim 2, characterized in that: The historical charging data includes one or more of the charging time, remaining mileage and remaining power of the target vehicle when it is charged.

9. The method according to claim 1, characterized in that: The prompting the user to charge includes: Get recommended charging stations; and The recommended charging station is pushed to the user.

10. The method according to claim 9, characterized in that The obtaining of the recommended charging station comprises: Acquire real-time data, the real-time data including vehicle data and charging station data, the vehicle data including vehicle location, the charging station data including charging station location and number of idle charging guns; determining a candidate charging station according to the vehicle position and the charging station position; Determining a recommendation score for each of the candidate charging stations; and At least one recommended charging station is selected from the candidate charging stations according to the recommendation score and pushed to the user.

11. The method according to claim 10, characterized in that Determining the recommendation score of each candidate charging station includes: Determining a charging stage of the vehicle according to the current charging times of the vehicle, wherein the charging stage includes a first stage and a second stage; In response to the vehicle being in the first stage, determining a recommendation score for each candidate charging station according to the distance between each charging station location and the vehicle location and the number of idle charging guns; and In response to the vehicle being in the second stage, a recommendation score of each candidate charging station is determined according to the real-time data by using a pre-trained recommendation model.

12. The method according to claim 11, characterized in that Determining the charging stage of the vehicle according to the current charging times of the vehicle includes: In response to the current charging number of the target vehicle being less than or equal to a third threshold, determining that the charging stage of the target vehicle is the first stage; and In response to the current charging number of the target vehicle being greater than the third threshold, it is determined that the charging stage of the target vehicle is the second stage.

13. The method according to claim 10, characterized in that The step of pushing the recommended charging station to the user specifically includes: Displaying a display interface of the recommended charging station through a display device; The display interface includes one or more of an electronic map, a list of recommended charging stations, location information of recommended charging stations, charging prices, the number of idle charging guns, location information of recommended charging stations in the electronic map, charging success rate and charging time.

14. The method according to claim 13, characterized in that The charging station data also includes service characteristics of the charging station; The display interface for displaying the recommended charging station through the display device is specifically: The recommended charging stations are sorted according to the service characteristics of the charging stations and then the recommended charging station list is displayed.

15. A vehicle charging device, characterized in that: The device comprises: A charging times acquisition unit, used to acquire the current charging times of the target vehicle; A determination method acquisition unit, used to determine a charging timing determination method for the target vehicle according to the charging times; a charging demand determination unit, configured to determine a current charging demand of a target vehicle according to the charging timing determination method; and A charging prompting unit, configured to prompt a user to charge in response to the charging demand of the target vehicle meeting the charging opportunity; Wherein, the method for determining the charging timing of the target vehicle according to the charging times includes: In response to the charging number being less than a first threshold, the charging timing determination method of the target vehicle is a first determination method, and the first determination method is a preset initial judgment condition; The first determination method includes: Acquire a first prediction value corresponding to the battery life information according to the battery life threshold; Acquire a second prediction value corresponding to the time interval according to the charging time interval threshold; and The first prediction value and the second prediction value are weightedly summed to obtain a charging prediction value, where the charging prediction value is used to characterize the probability that the target vehicle needs to be charged.

16. An electronic device comprising a memory and a processor, characterized in that: The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1 to 14.

17. A computer-readable storage medium storing computer program instructions, characterized in that: The computer program instructions, when executed by a processor, implement the method of any one of claims 1-14.

Images