Charging prediction method, device, apparatus and vehicle

Abstract

This application provides a charging prediction method, apparatus, device, and vehicle. The method includes: acquiring a first historical distance value of the vehicle, a predicted driving distance value for the current trip, and a preset distance threshold; wherein the first historical distance value is used to characterize the driving distance of the vehicle between the departure time of the current trip and the end time of the last charging; if the sum of the first historical distance value and the predicted driving distance value is greater than or equal to the preset distance threshold, a charging reminder message is sent. Through the technical solution of this application, accurate charging reminders can be provided to the user at the vehicle's departure time.

Description

Technical Field

[0001] This application relates to the field of electric vehicle technology, and more specifically, to a charging prediction method, apparatus, device, and vehicle. Background Technology

[0002] With the development of new energy technologies, electric vehicles have become popular among users. Since electric vehicles are powered by electricity, it is usually necessary to predict whether the vehicle needs to be charged during driving, so as to remind users to charge in time and avoid running out of power during driving.

[0003] Currently, the system primarily determines whether charging is needed by comparing the vehicle's current state of charge (SOC) with a preset charge level, and then sends a charging reminder to the user. However, because many factors influence charging prediction, this method cannot provide accurate charging reminders. Summary of the Invention

[0004] This application provides a charging prediction method, apparatus, device, and vehicle, which can improve the accuracy of charging reminders.

[0005] Firstly, a charging prediction method is provided, the method comprising:

[0006] The system acquires the vehicle's first historical distance value, the predicted driving distance for the current trip, and a preset distance threshold. The first historical distance value is used to characterize the vehicle's driving distance between the start time of the current trip and the end time of the last charge.

[0007] If the sum of the first historical distance value and the predicted driving distance value is greater than or equal to the preset distance threshold, a charging reminder message will be sent.

[0008] In the above technical solution, if the sum of the first historical distance value and the predicted driving distance value is greater than or equal to a preset distance threshold, a charging reminder message is sent. The first historical distance value is used to characterize the vehicle's driving distance between the departure time of the current trip and the end time of the last charge. Since the mileage traveled after the last charge and the driving distance of the current trip are considered before the vehicle departs, the factors considered are more comprehensive. Furthermore, the mileage that the vehicle can travel on a full charge is a relatively fixed value. Therefore, charging reminders based on the comparison between the distance traveled after the last charge and the predicted distance of the current trip and the distance threshold are more accurate than charging reminders based on anxiety about battery level.

[0009] In conjunction with the first aspect, in some possible implementations, the method further includes: obtaining a second historical distance value of the vehicle; wherein the second historical distance value is used to characterize the distance traveled by the vehicle between a first time and a second time; the first time is used to characterize the charging start time of the vehicle at a first charging location, the second time is used to characterize the last charging end time before the first time, and the first charging location is a charging location where the charging frequency is lower than a preset frequency and the charging start time is an abnormal time; and the second historical distance value is processed by a quantile algorithm to obtain a preset distance threshold.

[0010] In the above technical solution, the second historical distance value can be processed using a quantile algorithm to obtain a preset distance threshold. Since the second historical distance value is determined based on the start time of charging at the first charging location (e.g., a charging station with low charging frequency and abnormal charging start time) and the end time after the last charging, habitual charging events of users can be avoided. The obtained second historical distance value is closer to the actual distance traveled by the vehicle from a fully charged state to the next charging state, thus making the preset distance value more accurate. In addition, processing the second historical distance value using a quantile algorithm to obtain the preset distance threshold reduces data noise and outliers, making the final preset distance threshold more accurate and reliable. With a more accurate preset distance value, the charging reminder information will also be more accurate.

[0011] Combining the first aspect and the above implementation methods, in some possible implementation methods, the second historical distance value is processed by the quantile algorithm to obtain a preset distance threshold, including: sorting the second historical distance value in ascending order to obtain sorted distance values; selecting the distance value at a preset position from the sorted distance values ​​to obtain the preset distance threshold.

[0012] In combination with the first aspect and the above implementation methods, in some possible implementation methods, the method further includes: obtaining the departure time and departure position of the current trip; and obtaining the predicted travel distance value based on the departure time and departure position.

[0013] In the above technical solution, the predicted driving distance can be obtained based on the departure time and departure location. Even when the vehicle does not know the user's current destination, it can still predict charging and remind the user to charge, thus improving the user experience.

[0014] In combination with the first aspect and the above implementation methods, in some possible implementation methods, obtaining the predicted driving distance value based on the departure time and departure location includes: obtaining historical destinations, which represent the destinations of the vehicle at the departure time and departure location in the historical journey; determining the destination information entropy based on the departure time, departure location, and historical destination; obtaining the predicted destination based on the destination information entropy and a preset destination information entropy range; and obtaining the predicted driving distance value based on the distance between the predicted destination and the departure location.

[0015] In the above technical solution, destination information entropy is determined based on departure time, departure location, and historical destinations. Historical destinations represent the vehicle's destinations at different departure times and locations throughout its historical journey. The volatility of each destination corresponding to the vehicle at that departure time and location can be obtained from historical journey data. Therefore, when determining the predicted destination based on a preset destination information entropy range, a destination with lower volatility (e.g., lower destination information entropy) can be selected, thereby improving the accuracy of the predicted destination. A more accurate predicted destination leads to a more accurate predicted distance for the current journey. Furthermore, compared to predicting based on probability values, using information entropy to determine the current journey's destination has a higher probability of being the predicted destination, resulting in a more accurate predicted destination and thus a more accurate predicted travel distance.

[0016] In combination with the first aspect and the above implementation methods, in some possible implementation methods, obtaining the predicted driving distance value based on the departure time and departure location includes: obtaining historical distance values, which are used to represent the driving distance values ​​of the vehicle at the departure time and departure location in the historical journey; determining the distance information entropy based on the departure time, departure location and historical distance values; and obtaining the predicted driving distance value based on the distance information entropy and a preset distance information entropy range.

[0017] In the above technical solution, distance information entropy is determined based on departure time, departure location, and historical distance values. Historical distance values ​​represent the distance traveled by the vehicle at the departure time and departure location in the historical journey. The volatility of each distance value corresponding to the vehicle at the departure time and departure location can be obtained from the historical journey data. Therefore, when determining the predicted driving distance value based on the preset distance information entropy range, a value with lower volatility (e.g., a smaller distance information entropy) can be selected to improve the accuracy of the predicted distance value. In addition, since multiple destinations can correspond to one distance value, using distance information entropy is more accurate than obtaining the predicted driving distance value based on destination information entropy.

[0018] In conjunction with the first aspect and the above implementation methods, in some possible implementation methods, before sending a charging reminder message if the sum of the first historical distance value and the predicted driving distance value is greater than or equal to a preset distance threshold, the method further includes: obtaining the historical charging location, the historical destination, and the historical charging end time; if the distance between the predicted destination and the historical charging location is less than or equal to the first distance threshold, not sending a charging reminder message; or, if the distance between the predicted destination and the historical destination is less than or equal to a second distance threshold, not sending a charging reminder message; or, if the time difference between the departure time and the historical charging end time is less than or equal to a first time threshold, not sending a charging reminder message.

[0019] In the above technical solution, if the distance between the predicted destination and the historical charging location is less than or equal to a first distance threshold, no charging reminder information is sent. Since users can charge their devices themselves when the predicted destination is close to the historical charging location (e.g., a frequently used charging location), not sending a charging reminder information can reduce the push of invalid charging information. Similarly, if the distance between the predicted destination and the historical destination is less than or equal to a second distance threshold, no charging reminder information is sent. Since the distance between the predicted destination of the current trip and the historical destination (e.g., a frequently used destination) is very close, it can be ensured that users can charge their devices in time at the historical destination when their batteries are low on power. Not sending a charging reminder information can reduce the push of invalid charging reminder information. If the time difference between the departure time and the historical charging end time is less than or equal to a first time threshold, no charging reminder information is sent. If the departure time and the historical charging end time are less than or equal to the first time threshold, it means that the user has just finished charging, and there is no need to remind the user to charge their devices. This can also avoid the push of invalid charging information.

[0020] Secondly, a charging prediction device is provided, the device comprising:

[0021] The first acquisition module is used to acquire the vehicle's first historical distance value, the predicted driving distance value of the current trip, and a preset distance threshold; wherein, the first historical distance value is used to represent the vehicle's driving distance between the departure time of the current trip and the end time of the last charge.

[0022] The sending module is used to send a charging reminder message if the sum of the first historical distance value and the predicted driving distance value is greater than or equal to a preset distance threshold.

[0023] In conjunction with the second aspect, in some possible implementations, the device further includes: a second acquisition module, configured to acquire a second historical distance value of the vehicle; wherein the second historical distance value is used to characterize the distance traveled by the vehicle between a first time and a second time; the first time is used to characterize the charging start time of the vehicle at a first charging location, the second time is used to characterize the last charging end time before the first time, and the first charging location is a charging location where the charging frequency is lower than a preset frequency and the charging start time is an abnormal time; and a first processing module, configured to process the second historical distance value using a quantile algorithm to obtain a preset distance threshold.

[0024] In combination with the second aspect and the above implementation methods, in some possible implementation methods, the first processing module is specifically used to sort the second historical distance values ​​in ascending order to obtain sorted distance values; and select the distance value of a preset position from the sorted distance values ​​to obtain a preset distance threshold.

[0025] In combination with the second aspect and the above implementation methods, in some possible implementation methods, the device further includes: a third acquisition module, used to acquire the departure time and departure position of the current trip; and a second processing module, used to obtain the predicted travel distance value based on the departure time and departure position.

[0026] Combining the second aspect and the above implementation methods, in some possible implementation methods, the second processing module is specifically used to obtain historical distance values, which represent the distance traveled by the vehicle at the departure time and departure position in the historical journey; determine the distance information entropy based on the departure time, departure position and historical distance values; and obtain the predicted travel distance value based on the distance information entropy and a preset distance information entropy range.

[0027] In conjunction with the second aspect and the above implementation methods, in some possible implementation methods, the second processing module is further used to obtain historical destinations, which represent the destinations of the vehicle at the departure time and departure position in the historical journey; determine the destination information entropy based on the departure time, departure position and historical destination; obtain the predicted destination based on the destination information entropy and the preset destination information entropy range; and obtain the predicted driving distance value based on the distance between the predicted destination and the departure position.

[0028] In conjunction with the second aspect and the above implementation methods, in some possible implementation methods, the device further includes: a fourth acquisition module, used to acquire historical charging location, historical destination, and historical charging end time; a first transmission control module, used to not send charging prompt information if the predicted distance between the destination and the historical charging location is less than or equal to a first distance threshold; or, if the predicted distance between the destination and the historical destination is less than or equal to a second distance threshold; or, if the time difference between the departure time and the historical charging end time is less than or equal to a first time threshold, not send charging prompt information.

[0029] Thirdly, a charging prediction device is provided, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, causing the device to perform the methods of the first aspect or any possible implementation thereof.

[0030] Fourthly, a vehicle is provided, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, causing the vehicle to perform the methods described in the first aspect or any possible implementation thereof.

[0031] Fifthly, a computer program product is provided, comprising: computer program code, which, when run on a computer, causes the computer to perform the methods described in the first aspect or any possible implementation thereof.

[0032] In a sixth aspect, a computer-readable storage medium is provided that stores computer program code, which, when executed on a computer, causes the computer to perform the methods described in the first aspect or any possible implementation thereof. Attached Figure Description

[0033] Figure 1 This is a schematic diagram illustrating a scenario of cloud server and vehicle interaction provided in an embodiment of this application;

[0034] Figure 2 This is a schematic flowchart of a charging prediction method provided in an embodiment of this application;

[0035] Figure 3 This is a schematic diagram of a travel scenario provided in an embodiment of this application;

[0036] Figure 4 This is a schematic diagram of another travel scenario provided in an embodiment of this application;

[0037] Figure 5This is a schematic diagram of another charging prediction process provided in an embodiment of this application;

[0038] Figure 6 This is a schematic diagram of the structure of a charging prediction device provided in an embodiment of this application;

[0039] Figure 7 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application. Detailed Implementation

[0040] The technical solutions in this application will be clearly and thoroughly described below with reference to the accompanying drawings. In the description of the embodiments of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. "And / or" in the text is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the description of the embodiments of this application, "multiple" refers to two or more than two.

[0041] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature.

[0042] Figure 1 This is a schematic diagram illustrating a scenario of cloud server and vehicle interaction provided in an embodiment of this application.

[0043] For example, such as Figure 1 As shown in Figure (a), vehicle 110 and cloud server 120 are connected and can exchange information.

[0044] For example, vehicle 110 can upload historical trip data and historical charging data to cloud server 120. After receiving the historical trip data and historical charging data, cloud server 120 can perform operations such as... Figure 1The processing shown in Figure (b) is as follows: 1. Calculate the anxiety level, that is, determine the user's anxiety level based on the user's historical charging data; for example, if the user often charges when the battery level is 30%, then 30% is determined as the anxiety level; 2. Calculate the optimal battery performance level, for example, if it is determined based on historical trip data and historical charging data that charging when the battery level is 30% is the best for battery performance, then 30% is determined as the optimal battery performance level. The calculated anxiety level or optimal battery performance level is stored or sent to vehicle 110 for storage. Then, the battery level of vehicle 110 is compared with the anxiety level or optimal battery performance level. When the battery level is about to reach the anxiety level or optimal battery performance level, a charging command is sent to vehicle 110. After receiving the charging command, vehicle 110 displays a charging prompt on the vehicle's infotainment screen.

[0045] Another possible approach is for vehicle 110 to calculate the anxiety level or the optimal battery level based on historical trip data and charging data stored in the database, and store the calculation results in vehicle 110. When the battery level is about to reach the anxiety level or the optimal battery level, a charging reminder message is displayed on the vehicle's infotainment screen.

[0046] Since many factors affect battery capacity, such as temperature and air conditioning, the anxiety charge level and the optimal battery capacity level will differ. Therefore, relying solely on the anxiety charge level or the optimal battery capacity level for charging prediction has low accuracy.

[0047] Based on the above-mentioned technical problems, this application proposes a charging prediction method, device, equipment, and vehicle, which can predict the charging distance before the vehicle travels based on the distance traveled since the last charging and the distance to be traveled in the current trip. If the sum of the distance traveled since the last charging and the distance to be traveled in the current trip is greater than or equal to a preset distance threshold, a charging reminder message is sent, which can improve the accuracy of the charging reminder message and thus make accurate charging reminders.

[0048] Below, in conjunction with Figure 2 The charging prediction method provided in this application is described in detail.

[0049] Figure 2 This is a schematic flowchart illustrating a charging prediction method provided in an embodiment of this application. It should be understood that this method can be applied to, for example... Figure 1 In the scenario shown in Figure (a), the method can be used... Figure 1 The execution can be performed on cloud server 120 as shown in Figure (a), or it can also be... Figure 1The method is executed in vehicle 110 as shown in Figure (b). The following embodiments of this application illustrate the charging prediction method provided by this application by taking the execution of this method in vehicle 110 as an example.

[0050] For example, such as Figure 2 As shown, the method 200 includes:

[0051] S210, obtain the vehicle's first historical distance value, the predicted driving distance value of the current trip, and the preset distance threshold.

[0052] The first historical distance value is used to characterize the distance the vehicle has traveled between the start time of the current trip and the end time of the last charge.

[0053] The predicted distance for the current trip is the total distance from the starting point to the destination; the preset distance value can be a fixed distance value, such as 200KM.

[0054] Below, in conjunction with Figure 3 The first historical distance value and the predicted driving distance value for the current trip are explained.

[0055] Figure 3 This is a schematic diagram of a travel scenario provided in an embodiment of this application.

[0056] For example, such as Figure 3 As shown, the vehicle started at 8:00 AM on August 4, 2013, in preparation for departure. The last time it was charged was at charging station A, from 10:00 AM to 6:00 PM on August 3, 2013. After charging, it did not go anywhere else and went directly home (i.e., departure point B). The distance traveled by the vehicle from the end time of charging at charging station A at 6:00 PM on August 3 to the departure time of the current trip at 8:00 AM on August 4 is the first historical distance value, D1. If the destination of the current trip is destination C, then the predicted travel distance value is D2.

[0057] Optionally, if the user used navigation software before the start of the current trip, the predicted driving distance for the current trip can be obtained from the navigation information in the navigation software.

[0058] Optionally, if the user has not used navigation software before the start of the current trip, the predicted driving distance can be obtained through prediction.

[0059] In some embodiments, the process of predicting the predicted travel distance value may be as follows: obtaining the departure time and departure position of the current trip; and obtaining the predicted travel distance value based on the departure time and departure position.

[0060] It should be understood that most of the trips taken by commonly used family commuter cars are repetitive. Therefore, if the user does not turn on the trip navigation, the distance traveled for the current trip can be predicted based on the departure time and location of the current trip.

[0061] In the above technical solution, the predicted driving distance is obtained based on the departure time and departure location. By predicting the driving distance of the current trip based on the departure time and departure location, charging reminders can be provided even when the vehicle does not know the user's current destination, thus improving the user experience.

[0062] This application provides the following two methods for predicting the predicted travel distance based on the departure time and departure location:

[0063] One possible implementation involves obtaining historical destinations; determining the destination information entropy based on the departure time, departure location, and historical destinations; obtaining the predicted destination based on the destination information entropy and a preset range of destination information entropy; and obtaining the predicted driving distance value based on the distance between the predicted destination and the departure location.

[0064] Among them, historical destinations are used to represent the destinations of a vehicle at the departure time and departure location in the historical trip. For example, if the departure time of the current trip is 8:00 and the departure location is location 1, then all destinations of the vehicle at the departure time of 8:00 and departure location 1 in the historical trip will be retrieved.

[0065] Furthermore, the destination information entropy is determined based on the departure time, departure location, and all obtained destinations.

[0066] Destination information entropy is used to characterize the volatility of a vehicle's destination at a given departure time and location. It should be understood that the higher the destination information entropy, the greater the volatility of a vehicle's destination at that departure time and location, and in other words, the lower the certainty of a vehicle's destination at that departure time and location.

[0067] The process of determining the destination information entropy may include the following steps:

[0068] Step 1: Calculate the probability value of each destination corresponding to the departure time and departure location.

[0069] For example, in the historical itinerary, there are 100 trips with this departure time and departure position. Among them, the destination of 70 trips is position 1; the destination of 20 trips is position 2; and the destination of 10 trips is position 3. Then the probability of position 1 is 70%; the probability of position 2 is 20%; and the probability of position 3 is 10%.

[0070] Step 2: Calculate the destination information entropy based on the probability value of the destination and the information entropy formula.

[0071] Specifically, by substituting the probability values ​​of each destination obtained above into the information entropy formula, we can obtain the information entropy of each destination.

[0072] The information entropy formula is as follows: H(X)=-∑p(x)log2p(x), where H(x) represents the information entropy of the random variable X, and p(x) represents the probability of X taking a certain value.

[0073] Furthermore, after obtaining at least one destination information entropy, the destination corresponding to the information entropy that satisfies the preset destination information entropy range among the at least one destination information entropy is determined as the predicted destination, and then the distance between the predicted destination and the starting position of the current trip is determined as the predicted driving distance.

[0074] The preset destination information entropy range is a pre-defined information entropy range that can be set by those skilled in the art according to the actual situation, for example, 0.3 to 0.4.

[0075] Optionally, the destination information entropy can be calculated in real time by the vehicle or the cloud based on the departure time and departure location of the current trip; or it can be calculated in advance and stored on the vehicle or in the cloud.

[0076] Optionally, since the greater the destination information entropy, the less certain it is that the vehicle is at that departure time and departure location, a smaller destination information entropy range can be set to improve the accuracy of destination prediction, thereby improving the accuracy of predicted driving distance.

[0077] Table 1

[0078] Departure time Starting position destination Destination information entropy 7：30 Home company 0.2 7：30 Home supermarket 0.35 8：00 Home company 0.5 8：00 Home Gym 0.7 12：00 company charging station 0.8 12：00 company Gas station 0.75 ... ... ... ...

[0079] For example, Table 1 shows an example of the destination and its information entropy corresponding to the departure time and departure location. Table 1 lists different destinations and their information entropies corresponding to the same departure time and departure location. For example, the information entropy of a company destination departing from home at 7:30 is 0.2; the information entropy of a supermarket destination departing from home at 7:30 is 0.35; the information entropy of a company destination departing from home at 8:00 is 0.5; the information entropy of a gym destination departing from home at 8:00 is 0.7; the information entropy of a charging station destination departing from the company at 12:00 is 0.8; and the information entropy of a gas station destination departing from the company at 12:00 is 0.75.

[0080] For example, taking a departure time of 7:30, a departure location of home, and a preset destination information entropy range of 0.3 to 0.4 as an example, from Table 1 above, we find the destination information entropy that is 0.35, has a departure time of 7:30, a departure location of home, and a destination information entropy that meets the range of 0.3 to 0.4. The destination information entropy corresponding to this is the supermarket, so the supermarket is used as the predicted destination.

[0081] Furthermore, the distance between home and supermarket is used as the predicted driving distance.

[0082] In the above technical solution, destination information entropy is determined based on departure time, departure location, and historical destinations. Historical destinations represent the vehicle's destinations at different departure times and locations throughout its historical journey. The volatility of each destination corresponding to the vehicle at that departure time and location can be obtained from historical journey data. Therefore, when determining the predicted destination based on a preset destination information entropy range, a destination with lower volatility (e.g., lower destination information entropy) can be selected, thereby improving the accuracy of the predicted destination. A more accurate predicted destination leads to a more accurate predicted distance for the current journey. Furthermore, compared to predicting based on probability values, using information entropy to determine the current journey's destination has a higher probability of being the predicted destination, resulting in a more accurate predicted destination and thus a more accurate predicted travel distance.

[0083] Below, we introduce another possible implementation method for predicting the predicted driving distance based on the departure time and departure location. This method involves obtaining historical distance values; determining the distance information entropy based on the departure time, departure location, and historical distance values; and obtaining the predicted driving distance based on the distance information entropy and a preset distance information entropy range.

[0084] The historical distance value represents the distance traveled by a vehicle at a given departure time and location during a historical trip. For example, if the current trip departs at 8:00 and the departure location is location 1, then all distance values ​​for that vehicle's historical trips departing at 8:00 and departing at location 1 will be retrieved.

[0085] Furthermore, the distance information entropy is determined based on the departure time, departure location, and all obtained distance values.

[0086] Among them, distance information entropy is used to characterize the volatility of the distance between the vehicle and the departure location at that departure time and location. It should be understood that the larger the distance information entropy, the greater the volatility of the distance between the vehicle and the departure location at that departure time and location, that is, the smaller the certainty of the distance between the vehicle and the departure location at that departure time and location.

[0087] The process of determining distance information entropy may include the following steps:

[0088] Step 1: Calculate the probability value of each distance value corresponding to the departure time and departure position.

[0089] For example, in the historical itinerary, there are 100 trips at this departure time and departure location. Among them, 70 trips have a distance of 100KM; 20 trips have a distance of 50KM; and 10 trips have a distance of 20KM. Then, the probability of a distance of 100KM is 70%; the probability of a distance of 50KM is 20%; and the probability of a distance of 20KM is 10%.

[0090] Step 2: Calculate the distance information entropy based on the probability values ​​of each distance and the information entropy formula.

[0091] Specifically, by substituting the probability values ​​of each distance obtained above into the information entropy formula, we can obtain the information entropy of multiple destinations.

[0092] The information entropy formula is as follows: H(X)=-∑p(x)log2p(x), where H(x) represents the information entropy of the random variable X, and p(x) represents the probability of X taking a certain value.

[0093] Furthermore, after obtaining multiple distance information entropies, the distance corresponding to the information entropy that satisfies the preset distance information entropy range among the multiple distance information entropies is determined as the predicted driving distance value.

[0094] The preset distance information entropy range is a pre-defined range of information entropy, which can be set by those skilled in the art according to actual conditions, for example, 0.2 to 0.3. It should be understood that the preset distance information entropy range can be the same as the preset destination information entropy range, and this application embodiment does not limit this.

[0095] Optionally, since the greater the distance information entropy, the less certain the distance is at the departure time and departure location, a smaller range of distance information entropy can be set to improve the accuracy of the predicted driving distance value.

[0096] Table 2

[0097] Departure time Starting position driving distance Distance information entropy 7：30 Home 20KM 0.2 7：30 Home 25KM 0.5 8：00 Home 50KM 0.7 8：00 Home 100KM 0.8 12：00 company 5KM 0.65 12：00 company 10KM 0.75 ... ... ... ...

[0098] For example, Table 2 shows an example of the driving distance and its information entropy corresponding to the departure time and departure location. Table 2 lists different driving distances and their information entropies corresponding to the same departure time and departure location; for example, the information entropy is 0.2 for a driving distance of 20KM from home at 7:30; 0.5 for a driving distance of 25KM from home at 7:30; 0.7 for a driving distance of 50KM from home at 8:00; 0.8 for a driving distance of 100KM from home at 8:00; 0.65 for a driving distance of 5KM from the company at 12:00; and 0.75 for a driving distance of 10KM from the company at 12:00.

[0099] For example, taking a departure time of 7:30, a departure location of home, and a preset distance information entropy range of 0.2 to 0.3 as an example, from Table 2 above, we find the distance information entropy that is 0.2, has a departure time of 7:30, a departure location of home, and a distance information entropy that meets the range of 0.2 to 0.3. The distance information entropy corresponding to this distance information entropy is 20KM. Therefore, 20KM is used as the predicted driving distance.

[0100] In the above technical solution, distance information entropy is determined based on departure time, departure location, and historical distance values. Historical distance values ​​represent the distance traveled by the vehicle at the departure time and departure location in the historical journey. The volatility of each distance value corresponding to the vehicle at the departure time and departure location can be obtained from the historical journey data. Therefore, when determining the predicted driving distance value based on the preset distance information entropy range, a value with lower volatility (e.g., a smaller distance information entropy) can be selected to improve the accuracy of the predicted distance value. In addition, since multiple destinations can correspond to one distance value, using distance information entropy is more accurate than obtaining the predicted driving distance value based on destination information entropy.

[0101] Optionally, the preset distance value in S210 can be an anxiety mileage value. The anxiety mileage value can be understood as follows: if a user drives 300KM on a full charge and then feels that the battery may be low and actively goes to recharge, then 300KM is an anxiety mileage value for that user.

[0102] This application provides a method to quantify a user's anxiety mileage value. Specifically, the process of calculating the anxiety mileage value can be as follows: obtaining the second historical distance value of the vehicle; processing the second historical distance value through a quantile algorithm to obtain a preset distance threshold.

[0103] The second historical distance value is used to characterize the distance the vehicle traveled between the first and second time points.

[0104] The first moment is used to characterize the start time of charging of the vehicle at the first charging position; the second moment is used to characterize the end time of the previous charging before the first moment.

[0105] The first charging position is a charging position where the charging frequency is lower than the preset frequency (i.e., an infrequently used charging position) and the charging start time is an abnormal time (an infrequently used charging start time).

[0106] Optionally, the first charging location can be determined based on the charging frequency, for example, if the charging frequency is lower than a preset frequency (5 times); or the first charging location can be determined based on the charging location, for example, if the charging location is relatively remote, the first charging location can be determined.

[0107] Below, in conjunction with Figure 4 The second historical distance value is explained.

[0108] Figure 4 This is a schematic diagram of another travel scenario provided in the embodiments of this application.

[0109] For example, such as Figure 4 As shown, the vehicle was fully charged at a frequently used charging station A between 9:00 and 18:00 on August 4, 2013. After passing through a supermarket, a park, and a scenic area, it was charged at a less frequently visited charging station B between 12:00 and 20:00 on August 6, 2013.

[0110] The first time point is the starting time of charging at charging station B at 12:00, and the second time point is the ending time of charging at charging station A at 18:00. The distance traveled by the vehicle between the two times point (that is, the distance traveled from charging station A to supermarket, park, scenic spot and charging station B) is the second historical distance value.

[0111] Furthermore, at least one second historical distance value is processed using a quantile algorithm. This process can be as follows: sort the second historical distance values ​​in ascending order to obtain sorted distance values; select the distance value at a preset position from the sorted distance values ​​to obtain a preset distance threshold.

[0112] The preset position can be 50%, 75%, etc., and no specific limitation is made here.

[0113] For example, there are 10 second historical distance values ​​obtained, such as 300KM, 350KM, 400KM, 255KM, 230KM, 350KM, 420KM, 480KM, 500KM, and 240KM. These 10 second historical distance values ​​are sorted in ascending order, and the sorted result is: 230KM < 240KM < 255KM < 300KM < 350KM = 350KM < 400KM < 420KM < 480KM < 500KM. The distance value at a preset position is selected from the sorted result and determined as the second historical distance value. For example, when the preset position is 50%, the distance value of 350KM, which is ranked 5th, is determined as the preset distance value.

[0114] In the above technical solution, the second historical distance value can be processed using a quantile algorithm to obtain a preset distance threshold. Since the second historical distance value is determined based on the start time of charging at the first charging location (e.g., a charging station with low charging frequency and abnormal charging start time) and the end time after the last charging, habitual charging events of users can be avoided. The obtained second historical distance value is closer to the actual distance traveled by the vehicle from a fully charged state to the next charging state, thus making the preset distance value more accurate. In addition, processing the second historical distance value using a quantile algorithm to obtain the preset distance threshold reduces data noise and outliers, making the final preset distance threshold more accurate and reliable. With a more accurate preset distance value, the charging reminder information will also be more accurate.

[0115] S220: If the sum of the first historical distance value and the predicted driving distance value is greater than or equal to a preset distance threshold, a charging reminder message is sent.

[0116] For example, after obtaining the first historical distance value, the predicted driving distance value, and the preset distance value through the above example embodiment, the sum of the distances of the first historical distance value and the predicted driving distance value is compared with a preset distance threshold. If the sum of the distances is greater than or equal to the preset distance threshold, a charging reminder message is sent, such as... Figure 1 As shown in Figure (a).

[0117] In the above technical solution, if the sum of the first historical distance value and the predicted driving distance value is greater than or equal to a preset distance threshold, a charging reminder message is sent. The first historical distance value is used to represent the vehicle's driving distance between the departure time of the current trip and the end time of the last charging. Since the mileage traveled after the last charging and the driving distance of the current trip are considered before the vehicle departs, the factors considered are more comprehensive. Furthermore, the mileage that the vehicle can travel on a full charge is a relatively fixed value. Therefore, charging reminders based on the comparison between the distance traveled after the last charging and the predicted distance of the current trip and the distance threshold are more accurate and reasonable than charging reminders based on anxiety about battery level.

[0118] In some embodiments, to avoid sending invalid charging reminder messages, the method may further include: obtaining historical charging locations, historical destinations, and historical charging end times before sending the charging reminder messages; not sending charging reminder messages if the predicted distance between the destination and the historical charging location is less than or equal to a first distance threshold; or, not sending charging reminder messages if the predicted distance between the destination and the historical destination is less than or equal to a second distance threshold; or, not sending charging reminder messages if the time difference between the departure time and the historical charging end time is less than or equal to a first time threshold.

[0119] Among them, the historical charging location is the frequently used charging location, the historical destination is the frequently used destination, and the historical charging end time is the frequently used charging end time.

[0120] Optionally, frequently used charging locations, frequently used destinations, and frequently used charging end times can be marked in historical trip data and historical charging data, and the corresponding frequently used charging locations, frequently used destinations, and frequently used charging end times can be obtained based on the markings.

[0121] The first distance threshold and the second distance threshold can be set according to the actual situation, such as 5KM. The first distance threshold and the second distance threshold can be the same threshold or different thresholds. This application embodiment does not limit this.

[0122] Similarly, the first time threshold can also be set according to the actual situation, such as 3 hours.

[0123] In the above technical solution, if the distance between the predicted destination and the historical charging location is less than or equal to a first distance threshold, no charging reminder information is sent. Since users can charge their devices themselves when the predicted destination is close to the historical charging location (e.g., a frequently used charging location), not sending a charging reminder information can reduce the push of invalid charging information. Similarly, if the distance between the predicted destination and the historical destination is less than or equal to a second distance threshold, no charging reminder information is sent. Since the predicted destination of the current trip is very close to the historical destination (e.g., a frequently used destination), it can be ensured that users can charge their devices in time at the historical destination when their batteries are low, and not sending a charging reminder information can reduce the push of invalid charging reminder information. If the time difference between the departure time and the historical charging end time is less than or equal to a first time threshold, no charging reminder information is sent. If the departure time and the historical charging end time are less than or equal to the first time threshold, it means that the user has just finished charging, and there is no need to remind the user to charge their devices, which can also avoid the push of invalid information.

[0124] In some embodiments, to improve the accuracy of charging reminder information, the preset distance threshold and the first historical distance value can be updated every preset time interval. For example, new trip data and charging data can be obtained and processed every week to obtain the latest preset distance threshold and the first historical distance value in the manner described in the above embodiments.

[0125] In the above technical solution, the first historical distance value and the preset distance threshold required for charging prediction are updated based on historical data of the most recent historical period. This can be adapted to the charging habits of car owners in different seasons, making the charging prediction results more in line with the user's psychological expectations.

[0126] In some embodiments, after the vehicle sends a charging reminder message, it can detect the user's selection operation in response to the charging reminder message. If the user chooses to charge, it can navigate to a charging station near the current location. If the user chooses not to charge, the pop-up window on the display screen will close, and the pop-up reminder can continue after a preset time.

[0127] Optionally, the system can navigate the user to the nearest charging station based on the vehicle's current location and a navigation map.

[0128] In the above technical solution, navigating to the nearest charging station when the user selects to charge allows the user to charge in a timely manner, improving the user experience.

[0129] Based on the technical solutions provided in the above embodiments of this application, the following is in conjunction with... Figure 5 The specific implementation method will be described accordingly.

[0130] Figure 5 This is a schematic diagram of another charging prediction process provided in an embodiment of this application.

[0131] For example, such as Figure 5 As shown in Figure S510, historical trip data and historical charging data are merged, and the merged data is processed.

[0132] Specifically, the vehicle or cloud server obtains long-term (e.g., 6 months) historical driving data, merges the trip data and charging data in the historical driving data, and processes the merged data as follows: 1. Preprocessing, which may include data cleaning, removal of outliers, etc.; 2. Marking common starting points, common destinations, common charging end times, and common charging locations.

[0133] Table 3

[0134]

[0135] For example, Table 3 is an example of the merged historical itinerary data; Table 3 lists the starting point, ending point, charging location, charging start time, and charging end time for 7 historical itinerary events; for example, itinerary 1 starts at home, ends at the company, charges at home, starts at 20:00, and ends at 6:00 the next day; itinerary 2 starts at home, ends at the company, charges at the company, starts at 9:00, and ends at 16:00; itinerary 3 starts at home, ends at scenic spot 1, charges at home, starts at 21:00, and ends at the next day. Two days, 6:00 AM; Itinerary 4: Starting point is supermarket, destination is company, charging location is company, charging start time is 10:00 AM, charging end time is 4:00 PM; Itinerary 5: Starting point is home, destination is province A, charging location is charging station 1, charging start time is 9:00 PM, charging end time is 5:00 AM; Itinerary 6: Starting point is home, destination is suburbs, charging location is charging station 2, charging start time is 10:00 PM, charging end time is 6:00 AM on the second day; Itinerary 7: Starting point is company, destination is scenic area 2, charging location is charging station 3, charging start time is 6:00 PM, charging end time is 10:00 PM.

[0136] It should be understood that the data in Table 3 is only an example, and a trip event may also include data such as travel time, travel distance, and charging time.

[0137] Optionally, taking the trip data listed in Table 3 as an example, the starting point with a frequency greater than or equal to the first preset frequency (e.g., 5 times), the destination with a frequency greater than or equal to the second preset frequency (e.g., 5 times), the charging location with a frequency greater than or equal to the third preset frequency (e.g., 5 times), and the charging end time with a frequency greater than or equal to the fourth preset frequency (e.g., 8 times) can be marked.

[0138] S520 calculates the destination information entropy and distance information entropy corresponding to the departure location and departure time.

[0139] Among them, destination information entropy is used to characterize the volatility of the vehicle's destination at the departure time and departure location; distance information entropy is used to characterize the volatility of the vehicle's distance at the departure time and departure location.

[0140] It should be understood that the destination or distance corresponding to the same departure location and departure time in historical travel data may be different. Therefore, by calculating the destination information entropy and distance information entropy corresponding to the departure location and departure time, the destination or distance of the current trip can be effectively predicted.

[0141] Specifically, the probability values ​​of each destination or distance corresponding to the same departure location and departure time in historical travel data are calculated, and each probability value is substituted into the information entropy formula to calculate the information entropy of each destination or distance corresponding to the departure location and departure time.

[0142] The information entropy formula is as follows: H(X)=-∑p(x)log2p(x), where H(x) represents the information entropy of the random variable X, and p(x) represents the probability of X taking a certain value.

[0143] The calculation process of destination information entropy and distance information entropy will be explained below with reference to Tables 4 and 5.

[0144] Table 4

[0145] Departure time Starting position destination 7:30 Home company 7:30 Home company 7:30 Home company 7:30 Home supermarket 7:30 Home garden 17:00 Home Gym 17:00 Home Gym 17:00 Home School 17:00 Home School 17:00 Home School ... ... ...

[0146] For example, Table 4 lists the destinations corresponding to the same departure time and departure location. For instance, if the departure time is 7:30 and the departure location is home, the destinations are: company 3 times, supermarket 1 time, and park 1 time; if the departure time is 17:00 and the departure location is home, the destinations are: gym 2 times and school 3 times.

[0147] Referring to Table 4, the probability of a destination being the company when departing at 7:30 AM from home is 3 / 5; the probability of the destination being the supermarket is 1 / 5; and the probability of the destination being the park is 1 / 5. Substituting these probability values ​​into the information entropy formula, we get the information entropy for the company as 0.44; for the supermarket as 0.46; and for the park as 0.46. Similarly, we can obtain the destination information entropy for each destination when departing at 3:00 PM from home.

[0148] Table 5

[0149] Departure time Starting position driving distance 7:30 Home 20KM 7:30 Home 20KM 7:30 Home 20KM 7:30 Home 5KM 7:30 Home 10KM 17:00 Home 15KM 17:00 Home 15KM 17:00 Home 30KM 17:00 Home 30KM 17:00 Home 30KM ... ... ...

[0150] For example, Table 5 lists the driving distances corresponding to the same departure time and departure location. For instance, if the departure time is 7:30 and the departure location is home, the driving distance is 20KM for 3 times, 5KM for 1 time, and 10KM for 1 time; if the departure time is 17:00 and the departure location is home, the driving distance is 15KM for 2 times and 30KM for 3 times.

[0151] Referring to Table 5, the probability of a travel distance of 15 km for a departure time of 17:00 and a departure location of home is 2 / 5; the probability of 30 km is 3 / 5. Substituting these probability values ​​into the information entropy formula, the distance information entropy for a travel distance of 15 km is 0.53; and the distance information entropy for a travel distance of 30 km is 0.44. Similarly, the distance information entropies for a departure time of 7:30 and a departure location of home can be obtained.

[0152] S530, calculate anxiety mileage.

[0153] It should be understood that anxiety mileage is used to determine whether the distance a vehicle has traveled since its last full charge meets the distance required for recharging. The calculated anxiety mileage value can be used as a preset distance value.

[0154] The method for calculating anxiety mileage has been described in detail in step 210, and will not be repeated here.

[0155] Optionally, the calculation process of S510 to S530 described above can be an offline calculation process.

[0156] S540, predicts the current travel distance.

[0157] One possible approach is to first predict the destination of the current trip and then use the distance between the destination and the starting point as the current travel distance.

[0158] Taking the destination information entropy obtained in Table 4 as an example, if the departure time of the current trip is 7:30 and the departure location is home, multiple destination information entropies can be obtained: company information entropy: 0.44; supermarket information entropy: 0.46; park information entropy: 0.46. The destination corresponding to the information entropy within the preset destination information entropy range from these multiple destination information entropies is selected as the predicted destination. For example, when the preset destination information entropy range is 0.4 to 0.45, the corresponding destination is the company.

[0159] Furthermore, the distance between the company and home is calculated as the driving distance for the current trip.

[0160] Another possible approach is to directly predict the distance of the current journey.

[0161] Taking the destination entropy information obtained in Table 5 as an example, if the departure time of the current trip is 17:00 and the departure location is home, multiple distance entropy information can be obtained: the distance entropy information for 15KM is 0.53; the distance entropy information for 30KM is 0.44. The distance corresponding to the entropy information within a preset range from these multiple distance entropy information is selected as the driving distance of the current trip. For example, when the preset destination entropy information range is 0.4 to 0.45, the corresponding distance is 30KM.

[0162] Furthermore, 30KM will be used as the current travel distance.

[0163] S550: Determine if charging is required; if yes, proceed to S560; otherwise, proceed to S590.

[0164] For example, the sum of the predicted current trip distance and the distance traveled since the last charge is compared with the anxiety mileage, and if it is greater than or equal to the anxiety mileage, then S560 is executed.

[0165] Optionally, the calculation process of S540 and S550 can be a real-time calculation process, that is, real-time charging prediction is performed at the beginning of each trip.

[0166] S560, Do you want to provide a charging reminder? If yes, proceed to S570; otherwise, proceed to S590.

[0167] To avoid sending invalid charging notifications, you can skip sending charging notifications in the following situations:

[0168] Case 1: The distance between the predicted destination and the frequently used destination is less than or equal to a first distance threshold (e.g., 10KM); it should be understood that the frequently used destination is a destination with charging facilities.

[0169] Scenario 2: The predicted distance between the destination and the frequently used charging location is less than or equal to the second distance threshold (e.g., 10KM);

[0170] Case 3: The time difference between the departure time and the usual charging end time is less than or equal to the first time threshold (e.g., 2 hours).

[0171] If none of the above three conditions are met, then execute S570.

[0172] S570 sends a charging reminder message.

[0173] Optionally, charging reminders can be displayed on the vehicle's infotainment screen via a pop-up window; or users can be reminded to charge via voice commands.

[0174] S580, update anxiety mileage.

[0175] Optionally, data such as anxiety mileage, destination information entropy, and distance information entropy can be updated and calculated periodically (e.g., once a month) to ensure the real-time performance and accuracy of charging prediction.

[0176] Optionally, the updating process of data such as anxiety mileage, destination information entropy, and distance information entropy can be an offline calculation process, and the updated data can be stored in the cloud or on the vehicle to ensure that charging prediction can be made based on the latest data during real-time charging prediction.

[0177] S590, End.

[0178] Figure 6 This is a schematic diagram of the structure of a charging prediction device provided in an embodiment of this application.

[0179] For example, such as Figure 6 As shown, the device 600 includes:

[0180] The first acquisition module 610 is used to acquire the vehicle's first historical distance value, the predicted driving distance value of the current trip, and a preset distance threshold; wherein, the first historical distance value is used to characterize the vehicle's driving distance between the departure time of the current trip and the end time of the last charging.

[0181] The sending module 620 is used to send a charging reminder message if the sum of the first historical distance value and the predicted driving distance value is greater than or equal to a preset distance threshold.

[0182] Optionally, the device further includes: a second acquisition module, configured to acquire a second historical distance value of the vehicle; wherein the second historical distance value is used to characterize the distance traveled by the vehicle between a first time and a second time; the first time is used to characterize the charging start time of the vehicle at a first charging location, the second time is used to characterize the last charging end time before the first time, and the first charging location is a charging location where the charging frequency is lower than a preset frequency and the charging start time is an abnormal time; and a first processing module, configured to process the second historical distance value using a quantile algorithm to obtain a preset distance threshold.

[0183] In some embodiments, the first processing module is specifically used to sort the second historical distance values ​​in ascending order to obtain sorted distance values; and to select the distance value of a preset position from the sorted distance values ​​to obtain a preset distance threshold.

[0184] Optionally, the device further includes: a third acquisition module for acquiring the departure time and departure position of the current trip; and a second processing module for obtaining the predicted travel distance value based on the departure time and departure position.

[0185] In some embodiments, the second processing module is specifically used to obtain historical distance values, which represent the distance traveled by the vehicle at the departure time and departure location in the historical journey; determine the distance information entropy based on the departure time, departure location and historical distance values; and obtain the predicted travel distance value based on the distance information entropy and a preset distance information entropy range.

[0186] In some embodiments, the second processing module is further configured to obtain historical destinations, which represent the destinations of the vehicle at the departure time and departure location in the historical journey; determine the destination information entropy based on the departure time, departure location and historical destination; obtain the predicted destination based on the destination information entropy and a preset destination information entropy range; and obtain the predicted driving distance value based on the distance between the predicted destination and the departure location.

[0187] Optionally, the device further includes: a fourth acquisition module, used to acquire historical charging location, historical destination, and historical charging end time; and a first transmission control module, used to not send charging prompt information if the predicted distance between the destination and the historical charging location is less than or equal to a first distance threshold; or, if the predicted distance between the destination and the historical destination is less than or equal to a second distance threshold; or, if the time difference between the departure time and the historical charging end time is less than or equal to a first time threshold, not send charging prompt information.

[0188] Figure 7 This is a schematic diagram of the structure of a vehicle provided in an embodiment of this application.

[0189] For example, such as Figure 7 As shown, the vehicle 700 includes a memory 710 and a processor 720, wherein the memory 710 stores executable program code 711, and the processor 720 is used to call and execute the executable program code 711 to perform a charging prediction method.

[0190] This embodiment can divide the vehicle into functional modules according to the above method example. For example, each function can be assigned to a separate module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware. It should be noted that the module division in this embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0191] When each functional module is divided according to its corresponding function, the vehicle may include: a first acquisition module, a sending module, etc. It should be noted that all relevant content of each step involved in the above method embodiments can be referenced from the functional descriptions of the corresponding functional modules, and will not be repeated here.

[0192] The vehicle provided in this embodiment is used to execute the above-described charging prediction method, and thus can achieve the same effect as the above-described implementation method.

[0193] When using integrated units, the vehicle may include a processing module and a storage module. The processing module is used to control and manage the vehicle's actions. The storage module supports the vehicle in executing program code and data.

[0194] The processing module may be a processor or a controller, which can implement or execute various exemplary logic blocks, modules, and circuits as disclosed in this application. The processor may also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (DSP) and microprocessors, etc., and the storage module may be a memory.

[0195] This embodiment also provides a charging prediction device, including a memory and a processor. The memory is used to store executable program code, and the processor is used to call and run the executable program code from the memory, causing the executable program code to perform a charging prediction method.

[0196] This embodiment also provides a computer-readable storage medium storing computer program code. When the computer program code is run on a computer, the computer executes the above-described related method steps to implement a charging prediction method in the above embodiment.

[0197] This embodiment also provides a computer program product that, when run on a computer, causes the computer to perform the aforementioned related steps to implement a charging prediction method as described in the above embodiment.

[0198] In addition, the vehicle provided in the embodiments of this application may specifically be a chip, component or module. The vehicle may include a connected processor and a memory. The memory is used to store instructions. When the vehicle is running, the processor may call and execute the instructions to make the chip execute a charging prediction method in the above embodiments.

[0199] In this embodiment, the vehicle, equipment, computer-readable storage medium, computer program product, or chip are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects of the corresponding methods provided above, and will not be repeated here.

[0200] Through the above description of the embodiments, those skilled in the art will understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0201] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0202] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A charge prediction method characterized by, The method includes: Obtain the vehicle's first historical distance value and the predicted driving distance value for the current trip; wherein, the first historical distance value is used to characterize the vehicle's driving distance between the departure time of the current trip and the end time of the last charging; Obtain the second historical distance value of the vehicle; wherein the second historical distance value is used to characterize the driving distance of the vehicle between the first time and the second time; the first time is used to characterize the charging start time of the vehicle at the first charging position, the second time is used to characterize the last charging end time before the first time, the first charging position is a charging position where the charging frequency is lower than a preset frequency and the charging start time is an abnormal time, and the abnormal time is used to characterize the charging start time that is not frequently used. The second historical distance value is processed using a quantile algorithm to obtain a preset distance threshold; If the sum of the first historical distance value and the predicted driving distance value is greater than or equal to the preset distance threshold, a charging reminder message is sent.

2. The method of claim 1, wherein, The step of processing the second historical distance value using a quantile algorithm to obtain a preset distance threshold includes: Sort the second historical distance values ​​in ascending order to obtain the sorted distance values; The distance value of a preset position is selected from the sorted distance values ​​to obtain the preset distance threshold.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Obtain the departure time and departure location of the current trip; The predicted driving distance is obtained based on the departure time and departure location.

4. The method of claim 3, wherein, The step of obtaining the predicted driving distance value based on the departure time and the departure location includes: Obtain historical distance values, which represent the distance traveled by the vehicle at the departure time and departure location during the historical journey; The distance information entropy is determined based on the departure time, the departure location, and the historical distance value. The predicted driving distance value is obtained based on the distance information entropy and the preset distance information entropy range.

5. The method of claim 3, wherein, The step of obtaining the predicted driving distance value based on the departure time and the departure location includes: Obtain historical destinations, which are used to represent the destinations of the vehicle at the departure time and departure location in the historical journey; Determine the destination information entropy based on the departure time, departure location, and historical destination; The predicted destination is obtained based on the destination information entropy and the preset destination information entropy range; The predicted driving distance value is obtained based on the distance between the predicted destination and the starting position.

6. The method according to claim 5, characterized in that, Before sending a charging reminder message if the sum of the first historical distance value and the predicted driving distance value is greater than or equal to the preset distance threshold, the method further includes: Get historical charging locations, historical destinations, and historical charging end times; If the distance between the predicted destination and the historical charging location is less than or equal to a first distance threshold, the charging prompt message is not sent; or, If the distance between the predicted destination and the historical destination is less than or equal to a second distance threshold, the charging reminder message will not be sent; or, If the time difference between the start time and the historical charging end time is less than or equal to the first time threshold, the charging prompt information will not be sent.

7. A charging prediction device, characterized in that, The device includes: The first acquisition module is used to acquire the vehicle's first historical distance value and the predicted driving distance value of the current trip; wherein, the first historical distance value is used to characterize the driving distance of the vehicle between the departure time of the current trip and the end time of the last charging. The second acquisition module is used to acquire the second historical distance value of the vehicle; wherein, the second historical distance value is used to represent the driving distance of the vehicle between the first time and the second time; the first time is used to represent the charging start time of the vehicle at the first charging position, the second time is used to represent the last charging end time before the first time, the first charging position is a charging position where the charging frequency is lower than a preset frequency and the charging start time is an abnormal time, and the abnormal time is used to represent the charging start time of infrequent use. The first processing module is used to process the second historical distance value using a quantile algorithm to obtain a preset distance threshold; the sending module is used to send a charging reminder message if the sum of the first historical distance value and the predicted driving distance value is greater than or equal to the preset distance threshold.

8. A charging prediction device, characterized in that, The device includes: Memory, used to store executable program code; A processor for calling and running the executable program code from the memory, causing the device to perform the method as described in any one of claims 1 to 6.

9. A vehicle, characterized in that, The vehicles include: Memory, used to store executable program code; A processor for calling and running the executable program code from the memory, causing the vehicle to perform the method as described in any one of claims 1 to 6.

Images