Method, system, medium and device for predicting remaining usage time of battery swap mileage

Abstract

The present invention discloses a method, system, medium and device for predicting the remaining usage time of battery swap mileage. The prediction method includes: obtaining the user's historical battery swap data; extracting multiple groups of battery swap variables, the historical battery swap mileage balance and the historical usage time corresponding to each group of battery swap variables from the historical battery swap data; calculating the historical average daily battery swap mileage based on the historical battery swap data; using the historical average daily battery swap mileage, multiple groups of battery swap variables, the historical battery swap mileage balance and the historical usage time as training data to train a prediction model; obtaining the user's current battery swap variables and the current battery swap mileage balance; inputting the current battery swap variables and the current battery swap mileage balance into the prediction model to obtain the remaining usage time of the current battery swap mileage balance. The technical solution of the present invention improves the accuracy and timeliness of the prediction and enhances the user experience.

Description

[0001] This invention is a divisional application of the invention patent with application date of December 3, 2019, application number 201911217463.2, and name “Method, system, medium and equipment for predicting the remaining usage time of battery swap mileage”. Technical Field

[0002] The present invention relates to the field of battery replacement technology, and in particular to a method, system, medium and equipment for predicting the remaining usage time of a battery replacement mileage. Background Art

[0003] Electric vehicles are an increasingly popular form of energy-saving and environmentally friendly transportation, boasting low carbon dioxide emissions, low maintenance costs, and a positive user experience. When using an electric vehicle, users are most concerned about how long the battery can last after a battery swap, as they assess whether the vehicle will become inoperable during long-distance travel due to depletion of the remaining battery mileage.

[0004] In the prior art, after a battery swap, the remaining mileage is usually estimated, and then the mileage that the car can still travel is displayed to the user, who then makes his or her own judgment on how long the electric vehicle's current mileage balance can continue to be used. However, after learning the battery swap mileage, the user has no idea where to start. They have no idea how long the electric vehicle's current mileage balance can continue to be used, and can only make vague judgments based on historical driving conditions. Moreover, since multiple variables such as the user's driving habits, weather conditions, and temperature will have varying degrees of impact on the remaining usage time of the battery swap mileage, the user's subjective judgment of the usable time based on the mileage after the battery swap is not only inaccurate but also very inefficient, seriously affecting the user experience. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the defect in the prior art that the remaining mileage after battery replacement cannot be directly and accurately displayed to the user for how long the remaining mileage can be used, and to provide a method, system, medium and equipment for predicting the remaining usage time of the battery replacement mileage.

[0006] The present invention solves the above technical problems through the following technical solutions:

[0007] A method for predicting the remaining usage time of a battery swap mileage, the method comprising:

[0008] Obtain the user's historical battery replacement data;

[0009] Extracting multiple groups of battery swap variables, historical battery swap mileage balances and historical usage time corresponding to each group of battery swap variables from the historical battery swap data;

[0010] Calculate the historical daily average battery swap mileage based on the historical battery swap data;

[0011] The prediction model is trained using the historical average daily battery swap mileage, multiple groups of battery swap variables, the historical battery swap mileage balance, and the historical usage time as training data;

[0012] Obtain the user's current battery swap variable and current battery swap mileage balance;

[0013] The current battery exchange variable and the current battery exchange mileage balance are input into the prediction model to obtain the remaining usage time of the current battery exchange mileage balance.

[0014] Preferably, the historical battery replacement data is data of a preset historical period;

[0015] The step of calculating the historical average daily battery swap mileage based on the historical battery swap data includes:

[0016] Determine whether the difference between the total number of natural days in the preset historical period and the total number of battery replacement consumption days in the preset historical period exceeds a preset threshold;

[0017] If so, the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of battery swap consumption days;

[0018] If not, the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of natural days, or the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of battery swap consumption days.

[0019] Preferably, different battery swapping variables have different weight coefficients;

[0020] The step of inputting the current battery swap variable and the current battery swap mileage balance into the prediction model to obtain the remaining usage time of the current battery swap mileage balance includes:

[0021] Inputting the current battery swap variable and the current battery swap mileage balance into the prediction model;

[0022] Matching and determining the weight coefficient corresponding to the current battery swap variable;

[0023] The weight coefficient, the current battery swap mileage balance and the historical average daily battery swap mileage are used to predict the remaining usage time of the current battery swap mileage balance.

[0024] Preferably, the formula for predicting the remaining usage time of the current battery swap mileage using the weight coefficient, the current battery swap mileage, and the historical average daily battery swap mileage is:

[0025] Y=X1*X2*X3*……*Xn*(W / W0);

[0026] Among them, Y is the remaining usage time, Xn is the weight coefficient, n is a positive integer, W is the current battery replacement mileage balance, and W0 is the historical average daily battery replacement mileage.

[0027] Preferably, after the step of inputting the current battery swap variable and the current battery swap mileage balance into the prediction model to obtain the remaining usage time of the current battery swap mileage balance, the step further includes:

[0028] Generate a battery replacement suggestion based on the remaining usage time;

[0029] The remaining usage time and / or the battery replacement suggestion are sent to a predetermined user terminal.

[0030] A system for predicting the remaining usage time of a battery swap mileage, the prediction system comprising:

[0031] Historical battery swap data acquisition module, used to obtain the user's historical battery swap data;

[0032] A data extraction module is used to extract multiple groups of battery swap variables, the historical battery swap mileage balance and historical usage time corresponding to each group of battery swap variables from the historical battery swap data;

[0033] A calculation module, configured to calculate the historical average daily battery swap mileage based on the historical battery swap data;

[0034] A training module, configured to train a prediction model using the historical average daily battery swap mileage, multiple sets of battery swap variables, the historical battery swap mileage balance, and the historical usage time as training data;

[0035] The current battery swap data acquisition module is used to obtain the user's current battery swap variables and the current battery swap mileage balance;

[0036] The prediction module is used to input the current battery exchange variable and the current battery exchange mileage balance into the prediction model to obtain the remaining usage time of the current battery exchange mileage balance.

[0037] Preferably, the historical battery replacement data is data of a preset historical period;

[0038] The calculation module includes a judgment submodule, which is used to judge whether the total number of natural days in the preset historical period and the total number of battery replacement consumption days in the preset historical period differ by more than a preset threshold;

[0039] If so, the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of battery swap consumption days;

[0040] If not, the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of natural days, or the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of battery swap consumption days.

[0041] Preferably, different battery swapping variables have different weight coefficients;

[0042] The prediction module is also used to input the current battery exchange variable and the current battery exchange mileage balance into the prediction model; match and determine the weight coefficient corresponding to the current battery exchange variable; and use the weight coefficient, the current battery exchange mileage balance and the historical average daily battery exchange mileage to predict the remaining usage time of the current battery exchange mileage balance.

[0043] Preferably, the formula used by the prediction module to predict the remaining usage time of the current battery swap mileage is:

[0044] Y=X1*X2*X3*……*Xn*(W / W0);

[0045] Among them, Y is the remaining usage time, Xn is the weight coefficient, n is a positive integer, W is the current battery replacement mileage balance, and W0 is the historical average daily battery replacement mileage.

[0046] Preferably, the prediction system further includes a battery replacement suggestion generating module and a sending module;

[0047] The battery replacement suggestion generating module is used to generate a battery replacement suggestion according to the remaining usage time;

[0048] The sending module is used to send the remaining usage time and / or the battery replacement suggestion to a predetermined user terminal.

[0049] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the aforementioned method for predicting the remaining usage time of the battery replacement mileage are implemented.

[0050] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the aforementioned method for predicting the remaining usage time of the battery replacement mileage.

[0051] The positive progressive effect of the present invention is that the method, system, medium and equipment for predicting the remaining usage time of the battery swap mileage provided by the present invention take into account the influence of various influencing factors on the battery usage process when predicting the remaining usage time of the battery swap mileage, and use the trained prediction model to fit the data, intuitively display the remaining usage time of the battery swap mileage to the user, improve the accuracy and timeliness of the prediction, and improve the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a flowchart of the method for predicting the remaining usage time of the battery replacement mileage in Example 1 of the present invention.

[0053] Figure 2 This is a structural block diagram of the system for predicting the remaining usage time of battery replacement mileage in Example 2 of the present invention.

[0054] Figure 3 It is a structural diagram of an electronic device for predicting the remaining usage time of battery replacement mileage in Example 3 of the present invention. DETAILED DESCRIPTION

[0055] The present invention is further described below by way of examples, but the present invention is not limited to the scope of the examples.

[0056] Example 1

[0057] This embodiment provides a method for predicting the remaining usage time of battery replacement mileage, such as Figure 1 As shown, the prediction method may include the following steps:

[0058] Step S10: Obtain the user's historical battery replacement data;

[0059] The historical battery replacement data here can be the battery replacement data of a preset historical period, for example, data within 1 month from the current time or data within 3 months from the current time, etc.

[0060] Step S11: extracting multiple groups of battery swap variables, the historical battery swap mileage balance and historical usage time corresponding to each group of battery swap variables from the historical battery swap data;

[0061] In this embodiment, battery replacement variables may include battery health, user portrait, whether it is a holiday, temperature and humidity inside or outside the battery pack, etc.

[0062] Specifically, the user portrait may include the user's use of car air conditioning in different seasons, the user's throttle control habits during driving, etc.

[0063] Step S12: Calculate the historical average daily battery swap mileage based on historical battery swap data;

[0064] In this embodiment, the historical battery replacement data is data from a preset historical period;

[0065] Step S12 can be specifically implemented in the following manner: determine whether the total number of natural days in the preset historical period and the total number of battery swap consumption days in the preset historical period differ by more than a preset threshold; if so, the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of battery swap consumption days; if not, the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of natural days, or the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of battery swap consumption days.

[0066] For example, in scenario 1, if the preset historical period is 90 days and the preset threshold is 10 days, then in this scenario, the natural days are 90 days. If the user has performed battery replacement operations on 85 of the 90 days, that is, the difference between the total number of natural days and the total number of battery replacement consumption days is only 5 days, which does not exceed the preset threshold of 10 days, then the historical average daily battery replacement mileage can be obtained by dividing the total battery replacement mileage of the battery replacement within 85 days by the total number of natural days (90 days), or by dividing the total battery replacement mileage of the battery replacement within 85 days by the total number of battery replacement consumption days (85 days).

[0067] In scenario 2, if the preset historical period is 90 days and the preset threshold is 10 days, then in this scenario, there are 90 natural days. If the user performs battery replacement operations on 50 of these days, that is, the difference between the total number of natural days and the total number of battery replacement consumption days is 40 days, which exceeds the preset threshold of 10 days, then the historical average daily battery replacement mileage can be calculated by dividing the total battery replacement mileage of battery replacements within 50 days by the total number of battery replacement consumption days (50 days).

[0068] Step S13: Using the historical average daily battery swap mileage, multiple sets of battery swap variables, historical battery swap mileage balance, and historical usage time as training data, a prediction model is trained;

[0069] The prediction model may be a trained linear regression model.

[0070] Step S14: Obtain the user's current battery swap variable and current battery swap mileage balance;

[0071] Step S15: Input the current battery swap variable and the current battery swap mileage balance into the prediction model to obtain the remaining usage time of the current battery swap mileage balance.

[0072] In this embodiment, different weight coefficients can be set for different battery swapping variables;

[0073] Based on this, after inputting the current battery swap variable and the current battery swap mileage balance into the prediction model, the weight coefficient corresponding to the current battery swap variable can be matched and determined. Next, the weight coefficient, the current battery swap mileage balance and the historical average daily battery swap mileage can be used to predict the remaining usage time of the current battery swap mileage balance.

[0074] Specifically, the formula for predicting the remaining usage time of the current battery swap mileage using the weight coefficient, the current battery swap mileage, and the historical average daily battery swap mileage can be:

[0075] Y=X1*X2*X3*……*Xn*(W / W0);

[0076] Among them, Y is the remaining usage time, Xn is the weight coefficient, n is a positive integer, W is the current battery swap mileage balance, and W0 is the historical average daily battery swap mileage.

[0077] Furthermore, after obtaining historical battery swap data, it can also be preprocessed to improve the accuracy of subsequent calculations. Preprocessing includes but is not limited to data cleaning, data integration, data transformation, and data reduction.

[0078] Specifically, data cleaning refers to "cleaning" data by filling in missing values, smoothing noisy data, identifying or removing outliers (such as peaks or troughs in data), and resolving inconsistencies. Data cleaning can standardize data formats, remove abnormal data, correct erroneous data, and eliminate duplicate data.

[0079] Data integration refers to combining data from multiple data sources and storing them in a unified manner, thereby simplifying data storage space.

[0080] Data transformation refers to converting data into a form suitable for data calculation through smooth aggregation, data generalization or normalization, thereby improving the speed of subsequent data calculations.

[0081] Data reduction refers to reducing a large amount of data into a data set, which not only maintains the integrity of the original data but also improves the orderliness of data storage.

[0082] In this embodiment, the historical battery replacement data may include training set data and test set data;

[0083] Preferably, when training the model, multiple groups of battery swapping variables in the training set data and the historical battery swapping mileage balance corresponding to each group of battery swapping variables can be used as input, and the model can be trained with the historical usage time as output to obtain a prediction model; next, the prediction model can also be tested using the test set data, and it can be determined whether the test results meet the preset conditions. If so, it indicates that the prediction model is relatively accurate and can be used for subsequent prediction operations. If not, the weight coefficient is adjusted, and the model is retrained using the training set data until the prediction results meet the requirements.

[0084] Furthermore, after predicting the remaining usage time of the current battery swap mileage balance, the prediction method in this embodiment further includes the following steps:

[0085] Step S16: Generate a battery replacement suggestion based on the remaining usage time;

[0086] Step S17: Send the remaining usage time and / or battery replacement suggestion to the predetermined user terminal.

[0087] Specifically, the user terminal may be any type of PC or mobile terminal (eg, mobile phone, iPad), etc., and the embodiment of the present invention does not impose any limitation on this.

[0088] The method, system, medium and device for predicting the remaining usage time of the battery swap mileage provided by the present invention take into account the influence of various influencing factors on the battery usage process when predicting the remaining usage time of the battery swap mileage, and use the trained prediction model to fit the data to intuitively display the remaining usage time of the battery swap mileage to the user, thereby improving the accuracy and timeliness of the prediction and improving the user experience.

[0089] Example 2

[0090] This embodiment provides a system for predicting the remaining usage time of battery replacement mileage. Figure 2 As shown, the prediction system 1 may include:

[0091] A historical battery swap data acquisition module 10 is used to acquire the user's historical battery swap data;

[0092] The historical battery replacement data here can be the battery replacement data of a preset historical period, for example, data within 1 month from the current time or data within 3 months from the current time, etc.

[0093] The data extraction module 11 is used to extract multiple groups of battery swap variables, the historical battery swap mileage balance and historical usage time corresponding to each group of battery swap variables from the historical battery swap data;

[0094] In this embodiment, battery replacement variables may include battery health, user portrait, whether it is a holiday, temperature and humidity inside or outside the battery pack, etc.

[0095] Specifically, the user portrait may include the user's use of car air conditioning in different seasons, the user's throttle control habits during driving, etc.

[0096] Calculation module 12, used to calculate the historical average daily battery swap mileage based on historical battery swap data;

[0097] In this embodiment, the historical battery replacement data is data from a preset historical period;

[0098] The calculation module 12 is also used to determine whether the total number of natural days in the preset historical period and the total number of battery swap consumption days in the preset historical period differ by more than a preset threshold; if so, the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of battery swap consumption days; if not, the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of natural days, or the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of battery swap consumption days.

[0099] For example, in scenario 1, if the preset historical period is 90 days and the preset threshold is 10 days, then in this scenario, the natural days are 90 days. If the user has performed battery replacement operations on 85 of the 90 days, that is, the difference between the total number of natural days and the total number of battery replacement consumption days is only 5 days, which does not exceed the preset threshold of 10 days, then the historical average daily battery replacement mileage can be obtained by dividing the total battery replacement mileage of the battery replacement within 85 days by the total number of natural days (90 days), or by dividing the total battery replacement mileage of the battery replacement within 85 days by the total number of battery replacement consumption days (85 days).

[0100] In scenario 2, if the preset historical period is 90 days and the preset threshold is 4 days, then in this scenario, there are 90 natural days. If the user performs battery replacement operations on 85 of these days, that is, the difference between the total number of natural days and the total number of battery replacement consumption days is 5 days, which exceeds the preset threshold of 4 days, then the historical average daily battery replacement mileage can be calculated as the total battery replacement mileage within 85 days / the total number of battery replacement consumption days (85 days).

[0101] The prediction system 1 also includes a training module 13, which is used to train a prediction model using historical average daily battery replacement mileage, multiple sets of battery replacement variables, historical battery replacement mileage balance and historical usage time as training data; wherein the prediction model can be a trained linear regression model.

[0102] The current battery swap data acquisition module 14 is used to obtain the user's current battery swap variables and the current battery swap mileage balance;

[0103] The prediction module 15 is used to input the current battery swap variable and the current battery swap mileage balance into the prediction model to obtain the remaining usage time of the current battery swap mileage balance.

[0104] In this embodiment, different battery swapping variables may have different weight coefficients.

[0105] The prediction module 15 is also used to input the current battery swap variable and the current battery swap mileage balance into the prediction model; match and determine the weight coefficient corresponding to the current battery swap variable; and use the weight coefficient, the current battery swap mileage balance and the historical average daily battery swap mileage to predict the remaining usage time of the current battery swap mileage balance.

[0106] Specifically, the prediction module predicts the remaining usage time of the current battery swap mileage using the following formula:

[0107] Y=X1*X2*X3*……*Xn*(W / W0);

[0108] Among them, Y is the remaining usage time, Xn is the weight coefficient, n is a positive integer, W is the current battery swap mileage balance, and W0 is the historical average daily battery swap mileage.

[0109] Furthermore, the prediction system 1 may also include a preprocessing module 16, which can preprocess the historical battery swapping data to improve the accuracy of subsequent calculations. Preprocessing includes but is not limited to data cleaning, data integration, data transformation, and data reduction.

[0110] Specifically, data cleaning refers to "cleaning" data by filling in missing values, smoothing noisy data, identifying or removing outliers (such as peaks or troughs in data), and resolving inconsistencies. Data cleaning can standardize data formats, remove abnormal data, correct erroneous data, and eliminate duplicate data.

[0111] Data integration refers to combining data from multiple data sources and storing them in a unified manner, thereby simplifying data storage space.

[0112] Data transformation refers to converting data into a form suitable for data calculation through smooth aggregation, data generalization or normalization, thereby improving the speed of subsequent data calculations.

[0113] Data reduction refers to reducing a large amount of data into a data set, which not only maintains the integrity of the original data but also improves the orderliness of data storage.

[0114] In this embodiment, the historical battery replacement data may include training set data and test set data; the prediction system may also include a test module 17.

[0115] When the training module 13 trains the model, it can use multiple groups of battery swap variables in the training set data and the historical battery swap mileage balance corresponding to each group of battery swap variables as input, and use the historical usage time as output to train the model to obtain a prediction model; next, the testing module 17 can use the test set data to test the prediction model, and determine whether the test results meet the preset conditions. If so, it indicates that the prediction model is relatively accurate and can be used for subsequent prediction operations. If not, the weight coefficient is adjusted and the training module 13 is called. The training module 13 re-uses the training set data to train the model based on the adjusted weight coefficient until the prediction result meets the requirements.

[0116] Furthermore, the prediction system 1 may further include a battery replacement suggestion generating module 18 and a sending module 19;

[0117] The battery replacement suggestion generation module 18 is used to generate a battery replacement suggestion based on the remaining usage time; the sending module 19 is used to send the remaining usage time and / or the battery replacement suggestion to the predetermined user terminal.

[0118] Specifically, the user terminal may be any type of PC or mobile terminal (eg, mobile phone, iPad), etc., and the embodiment of the present invention does not impose any limitation on this.

[0119] The prediction system for the remaining usage time of the battery swap mileage provided by the present invention takes into account the influence of various influencing factors on the battery usage process when predicting the remaining usage time of the battery swap mileage, and uses the trained prediction model to fit the data to intuitively display the remaining usage time of the battery swap mileage to the user, thereby improving the accuracy and timeliness of the prediction and improving the user experience.

[0120] Example 3

[0121] The present invention also provides an electronic device, such as Figure 3 As shown, the electronic device may include a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for predicting the remaining usage time of the battery replacement mileage in the aforementioned embodiment 1 are implemented.

[0122] It is understandable that Figure 3 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0123] like Figure 3 As shown, electronic device 2 may be implemented as a general-purpose computing device, such as a server device. Components of electronic device 2 may include, but are not limited to, at least one processor 3, at least one memory 4, and a bus 5 connecting various system components (including memory 4 and processor 3).

[0124] The bus 5 may include a data bus, an address bus, and a control bus.

[0125] The memory 4 may include a volatile memory, such as a random access memory (RAM) 41 and / or a cache memory 42 , and may further include a read-only memory (ROM) 43 .

[0126] The memory 4 may also include a program tool 45 (or utility) having a set (at least one) of program modules 44, such program modules 44 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0127] The processor 3 executes various functional applications and data processing by running the computer program stored in the memory 4, such as the steps of the method for predicting the remaining usage time of the battery replacement mileage in Example 1 of the present invention.

[0128] The electronic device 2 can also communicate with one or more external devices 6 (e.g., a keyboard, a pointing device, etc.). Such communication can be performed via an input / output (I / O) interface 7. Furthermore, the model generating electronic device 2 can also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network) via a network adapter 8.

[0129] like Figure 3 As shown, the network adapter 8 can communicate with other modules of the model-generated electronic device 2 via the bus 5. Those skilled in the art will appreciate that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with the model-generated electronic device 2, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (RAID) systems, tape drives, and data backup storage systems.

[0130] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to embodiments of the present invention, the features and functions of two or more units / modules described above may be embodied in a single unit / module. Conversely, the features and functions of a single unit / module described above may be further divided and embodied by multiple units / modules.

[0131] Example 4

[0132] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the method for predicting the remaining usage time of the battery replacement mileage in Example 1 are implemented.

[0133] Among them, more specific forms of computer-readable storage media may include but are not limited to: portable disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0134] In a possible embodiment, the present invention can also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of the method for predicting the remaining usage time of the battery replacement mileage in Example 1.

[0135] The program code for executing the present invention may be written in any combination of one or more programming languages, and may be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on the remote device.

[0136] Although specific embodiments of the present invention have been described above, those skilled in the art will appreciate that these are merely illustrative and that the scope of the present invention is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present invention, and such changes and modifications are intended to fall within the scope of the present invention.

Claims

1. A method for predicting the remaining usage time of battery replacement mileage, characterized in that: The prediction method comprises: Obtain users' historical battery replacement data as training data and train a prediction model; Obtain the user's current battery swap variable and current battery swap mileage balance; wherein different battery swap variables have different weight coefficients; Matching and determining the weight coefficient corresponding to the current battery swap variable; Predicting the remaining usage time of the current battery swap mileage balance through the prediction model based on the weight coefficient and the current battery swap mileage balance; The step of obtaining the user's historical battery replacement data as training data and training a prediction model includes: Calculate the historical daily average battery swap mileage based on the historical battery swap data; The step of predicting the remaining usage time of the current battery swap mileage balance through the prediction model based on the weight coefficient and the current battery swap mileage balance includes: The weight coefficient, the current battery swap mileage balance and the historical average daily battery swap mileage are used to predict the remaining usage time of the current battery swap mileage balance.

2. The method for predicting the remaining usage time of battery replacement mileage according to claim 1, characterized in that: The step of obtaining the user's historical battery replacement data as training data and training the prediction model further includes: Extracting multiple groups of battery swap variables, historical battery swap mileage balances and historical usage time corresponding to each group of battery swap variables from the historical battery swap data; The prediction model is trained using the historical average daily battery swap mileage, multiple groups of battery swap variables, the historical battery swap mileage balance and the historical usage time as training data.

3. The method for predicting the remaining usage time of battery replacement mileage according to claim 1, characterized in that: The historical battery replacement data is data from a preset historical period; The step of calculating the historical average daily battery swap mileage based on the historical battery swap data includes: Determine whether the difference between the total number of natural days in the preset historical period and the total number of battery replacement consumption days in the preset historical period exceeds a preset threshold; If so, the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of battery swap consumption days; If not, the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of natural days, or the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of battery swap consumption days.

4. The method for predicting the remaining usage time of battery replacement mileage according to claim 1, characterized in that: The formula for predicting the remaining usage time of the current battery swap mileage using the weight coefficient, the current battery swap mileage, and the historical average daily battery swap mileage is: Y=X1*X2*X3*……*Xn*(W / W0); Among them, Y is the remaining usage time, Xn is the weight coefficient of the nth battery replacement variable, n is a positive integer, W is the current battery replacement mileage balance, and W0 is the historical average daily battery replacement mileage.

5. The method for predicting the remaining usage time of battery replacement mileage according to any one of claims 1 to 4, characterized in that: After the step of predicting the remaining usage time of the current battery exchange mileage balance through the prediction model based on the weight coefficient and the current battery exchange mileage balance, the step further includes: Generate a battery replacement suggestion based on the remaining usage time; The remaining usage time and / or the battery replacement suggestion are sent to a predetermined user terminal.

6. A system for predicting the remaining usage time of battery replacement mileage, characterized in that: The prediction system includes: The training module is used to obtain the user's historical battery replacement data as training data and train the prediction model; The current battery swap data acquisition module is used to obtain the user's current battery swap variable and the current battery swap mileage balance; different battery swap variables have different weight coefficients; A prediction module is used to match and determine the weight coefficient corresponding to the current battery swap variable; based on the weight coefficient and the current battery swap mileage balance, the remaining usage time of the current battery swap mileage balance is predicted by the prediction model; The training module includes: A calculation module, configured to calculate the historical average daily battery swap mileage based on the historical battery swap data; The prediction module is also used to use the weight coefficient, the current battery exchange mileage balance and the historical average daily battery exchange mileage to predict the remaining usage time of the current battery exchange mileage balance.

7. The system for predicting the remaining usage time of battery replacement mileage according to claim 6, characterized in that: The training module also includes: A data extraction module is used to extract multiple groups of battery swap variables, the historical battery swap mileage balance and historical usage time corresponding to each group of battery swap variables from the historical battery swap data; A training module is used to train a prediction model using the historical average daily battery swap mileage, multiple groups of battery swap variables, the historical battery swap mileage balance and the historical usage time as training data.

8. The system for predicting the remaining usage time of battery replacement mileage according to claim 7, characterized in that: The historical battery replacement data is data from a preset historical period; The calculation module includes a judgment submodule, which is used to judge whether the total number of natural days in the preset historical period and the total number of battery replacement consumption days in the preset historical period differ by more than a preset threshold; If so, the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of battery swap consumption days; If not, the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of natural days, or the historical average daily battery swap mileage = the total battery swap mileage of the preset historical period / the total number of battery swap consumption days.

9. The system for predicting the remaining usage time of battery replacement mileage according to claim 6, characterized in that: The formula used by the prediction module to predict the remaining usage time of the current battery swap mileage is: Y=X1*X2*X3*……*Xn*(W / W0); Among them, Y is the remaining usage time, Xn is the weight coefficient of the nth battery replacement variable, n is a positive integer, W is the current battery replacement mileage balance, and W0 is the historical average daily battery replacement mileage.

10. The system for predicting the remaining usage time of battery swap mileage according to any one of claims 6 to 9, characterized in that: The prediction system also includes a battery replacement suggestion generation module and a sending module; The battery replacement suggestion generating module is used to generate a battery replacement suggestion according to the remaining usage time; The sending module is used to send the remaining usage time and / or the battery replacement suggestion to a predetermined user terminal.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for predicting the remaining usage time of the battery replacement mileage described in any one of claims 1-5 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for predicting the remaining usage time of the battery replacement mileage described in any one of claims 1-5 are implemented.

Images