Method, device, medium, equipment and product for predicting battery life of rental vehicles

Abstract

The present invention is applied to the field of data processing technology and provides a method, apparatus, medium, device, and product for predicting the battery life of a rental vehicle. The method comprises: pre-constructing a prediction model for predicting battery parameters; performing multiple rounds of prediction processing on the battery parameters of a target battery according to the prediction model until the predicted battery parameters of the target battery meet the prediction stopping conditions; and determining the predicted life of the target battery based on the total number of charge and discharge cycles determined by the multiple rounds of battery parameter prediction processing. The technical solution provided by the embodiment of the present invention simulates the variable charge and discharge mode of the target battery through multiple rounds of prediction processing, setting corresponding charge and discharge characteristics for each round, and being able to predict the battery life based on multiple charge and discharge characteristics. This method is suitable for situations where multiple charge and discharge characteristics exist in car rental scenarios.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, medium, equipment and product for predicting the battery life of a rental vehicle. Background Art

[0002] With the development of new energy vehicles, the demand for rental vehicles is increasing year by year. Due to the high frequency of use of rental vehicles, monitoring the vehicle status is particularly important, especially monitoring the health of the power battery of new energy vehicles. This not only makes it easier for renters to choose the right vehicle, but also allows merchants to set prices based on battery status.

[0003] Unlike the usage of traditional household new energy vehicles, the power batteries of rental new energy vehicles are easily affected by the driver's driving habits and charging methods, which causes the battery capacity to decay and change, making it difficult to predict the health status of the power battery. Summary of the Invention

[0004] To solve the above problems, the embodiments of the present invention aim to provide a method, apparatus, medium, device and product for predicting the battery life of a rental vehicle.

[0005] In a first aspect, an embodiment of the present invention provides a method for predicting the battery life of a rental vehicle, comprising:

[0006] Pre-built prediction models for predicting battery parameters;

[0007] Performing multiple rounds of prediction processing on the battery parameters of the target battery according to the prediction model until the predicted battery parameters of the target battery meet the prediction stop condition;

[0008] Determining the predicted life of the target battery based on the total number of charge and discharge cycles determined by multiple rounds of battery parameter prediction processing;

[0009] The current round of prediction processing includes:

[0010] Determining current charge and discharge characteristics of the target battery in a current round;

[0011] Determine the current number of charge and discharge cycles corresponding to the current wheel, and add the current number of charge and discharge cycles to the total number of charge and discharge cycles;

[0012] The battery parameters predicted by the previous round of prediction processing are used as the initial battery parameters of the current round of prediction processing. The prediction model is used to predict the battery parameters of the target battery according to the current charge and discharge characteristics and the current number of charge and discharge cycles, and the battery parameters of the target battery after charging and discharging the current number of charge and discharge cycles are determined.

[0013] In some optional embodiments, the current charge and discharge characteristics are determined based on the following method:

[0014] Determine, according to the target characteristic transfer matrix of the target battery, the charge and discharge characteristics transferred from the previous charge and discharge characteristics of the previous round, and use the transferred charge and discharge characteristics as the current charge and discharge characteristics in the current round;

[0015] The target feature transfer matrix is ​​used to represent the probability of the target battery transferring from one charge and discharge feature to another charge and discharge feature.

[0016] In some optional embodiments, determining the charge and discharge characteristics transferred from the previous charge and discharge characteristics of the previous round according to the target characteristic transfer matrix of the target battery includes:

[0017] Collect statistics on the transfer of charge and discharge characteristics of the reference battery during the rental process to generate the initial feature transfer matrix Q;

[0018] The target characteristic transfer matrix P of the target battery is determined according to the initial characteristic transfer matrix Q, and:

[0019] ;

[0020] in, represents the probability that the target battery is in the i-th charge and discharge characteristic, represents the probability that the target battery is in the jth charge and discharge characteristic, i≠j; represents the probability of transferring from the i-th charge and discharge feature to the j-th charge and discharge feature in the initial feature transfer matrix Q, represents the probability of transferring from the jth charge-discharge feature to the ith charge-discharge feature in the initial feature transfer matrix Q, represents the probability of transferring from the i-th charge and discharge feature to the j-th charge and discharge feature in the target feature transfer matrix P;

[0021] According to the target feature transfer matrix P, determine the last charge and discharge feature from the previous round The probability distribution of various charge and discharge characteristics transferred to, and the current charge and discharge characteristics of the current round are selected according to the probability distribution ; T represents the round of the prediction process.

[0022] In some optional embodiments, the current charge and discharge characteristics of the current round are selected according to the probability distribution. ,include:

[0023] According to the probability values ​​corresponding to various charge and discharge characteristics in the probability distribution, the value space from 0 to 1 is divided into multiple value ranges, and the size of each value range matches the probability value corresponding to the corresponding charge and discharge characteristic;

[0024] Randomly generate a random number between 0 and 1, and use the charge and discharge characteristics corresponding to the value range in which the random number falls as the current charge and discharge characteristics of the current round .

[0025] In some optional implementations, determining the current number of charge and discharge cycles corresponding to the current wheel includes:

[0026] After determining the current charge and discharge feature, repeatedly performing the feature transfer operation until determining the next charge and discharge feature for the next round of prediction processing;

[0027] The feature transfer operation includes:

[0028] Determining, according to the target feature transfer matrix, a pending charge and discharge feature to be transferred from the current charge and discharge feature;

[0029] If the pending charge and discharge characteristic is the same as the current charge and discharge characteristic, the current charge and discharge cycle number is incremented by one, and then the characteristic transfer operation is continued; the initial value of the current charge and discharge cycle number is 1;

[0030] If the pending charge and discharge feature is different from the current charge and discharge feature, the pending charge and discharge feature is used as the next charge and discharge feature in the next round of prediction processing.

[0031] In some optional embodiments, the prediction model includes prediction sub-models corresponding to various charge and discharge characteristics; the prediction sub-models are used to predict changes in battery parameters of the target battery with the number of charge and discharge cycles when the target battery is charged and discharged according to the corresponding charge and discharge characteristics;

[0032] The method of using the prediction model to predict the battery parameters of the target battery according to the current charge and discharge characteristics and the current number of charge and discharge cycles, and determining the battery parameters of the target battery after charging and discharging the current number of charge and discharge cycles, includes:

[0033] Determining a target prediction sub-model corresponding to the current charge and discharge characteristics;

[0034] The initial battery parameters of the current round of prediction processing and the current number of charge and discharge cycles are input into the target prediction sub-model, and the battery parameters of the target battery after charging and discharging the current number of charge and discharge cycles are determined according to the prediction results of the target prediction sub-model.

[0035] In a second aspect, an embodiment of the present invention further provides a device for predicting the battery life of a rental vehicle, comprising:

[0036] A model building module for pre-building a prediction model for predicting battery parameters;

[0037] A prediction module, configured to perform multiple rounds of prediction processing on the battery parameters of the target battery according to the prediction model until the predicted battery parameters of the target battery meet a stop prediction condition;

[0038] a lifespan determination module, configured to determine a predicted lifespan of the target battery based on a total number of charge and discharge cycles determined by multiple rounds of battery parameter prediction processing;

[0039] The prediction module performs the current round of prediction processing, including:

[0040] Determining current charge and discharge characteristics of the target battery in a current round;

[0041] Determine the current number of charge and discharge cycles corresponding to the current wheel, and add the current number of charge and discharge cycles to the total number of charge and discharge cycles;

[0042] The battery parameters predicted by the previous round of prediction processing are used as the initial battery parameters of the current round of prediction processing. The prediction model is used to predict the battery parameters of the target battery according to the current charge and discharge characteristics and the current number of charge and discharge cycles, and the battery parameters of the target battery after charging and discharging the current number of charge and discharge cycles are determined.

[0043] In a third aspect, an embodiment of the present invention further provides a computer storage medium storing computer executable instructions, wherein the computer executable instructions are used in any one of the above methods for predicting the battery life of a rental vehicle.

[0044] In a fourth aspect, an embodiment of the present invention further provides an electronic device, including:

[0045] at least one processor; and,

[0046] a memory communicatively connected to the at least one processor; wherein,

[0047] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform any of the above-mentioned methods for predicting the battery life of a rental vehicle.

[0048] In a fifth aspect, the present invention provides a computer program product comprising computer instructions for causing a computer to execute any one of the above methods for predicting the battery life of a rental vehicle.

[0049] The solution provided in the first aspect of the embodiment of the present invention uses multiple rounds of prediction processing, and the charge and discharge characteristics of the target battery are set in each round of prediction processing. By setting corresponding charge and discharge characteristics for each round, the simulation of the variable charge and discharge mode of the target battery is realized, and the battery life can be predicted based on multiple charge and discharge characteristics. It is suitable for situations where there are multiple charge and discharge characteristics in car rental scenarios. When the rental vehicle battery is used based on various driving habits and charging methods, the service life of the rental vehicle battery can also be predicted relatively accurately, which can provide a reference basis for the pricing of rental vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 A flowchart showing a method for predicting the battery life of a rental vehicle provided by an embodiment of the present invention is shown;

[0052] Figure 2 A flowchart showing another method for predicting the battery life of a rental vehicle provided by an embodiment of the present invention;

[0053] Figure 3 A schematic diagram showing a feature transfer provided by an embodiment of the present invention is shown;

[0054] Figure 4 A schematic diagram showing the structure of a device for predicting the battery life of a rental vehicle provided by an embodiment of the present invention is shown;

[0055] Figure 5 A schematic structural diagram of an electronic device for executing a method for predicting the battery life of a rental vehicle provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0056] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature specified as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.

[0057] In the rental car scenario, the power batteries of new energy vehicles are easily affected by the driver's driving habits and charging methods. Specifically, the driving habits of individual tenants are uncontrollable. For example, because the vehicles they rent are not their own, some tenants may adopt a driving style of rapid acceleration and braking, which can easily lead to frequent high-current discharge and recharge of the battery, increasing the battery's internal resistance and causing battery aging.

[0058] Moreover, unlike slow charging in home scenarios, most tenants in car rental scenarios often use fast charging to charge their vehicles in order to quickly replenish energy. However, fast charging will accelerate the polarization reaction of the battery, and long-term use will lead to faster capacity decay. In addition, some tenants may also frequently perform deep discharge, that is, exhaust the battery power to an extremely low level (such as less than 10%) and then recharge it, or frequently fully charge and discharge (such as fully charge to 100% and then discharge to nearly 0). This will also aggravate the battery's chemical side reactions, accelerate capacity decay, and lead to a reduction in battery cycle life.

[0059] A typical power battery has a cycle life of up to 1,500 cycles, meaning it can be charged and discharged 1,500 times. However, poor driving habits and charging methods can easily affect battery life, resulting in the actual cycle life of rental vehicle batteries often being only around 1,200 cycles, or even lower.

[0060] Currently, there are solutions for predicting battery cycle life, such as predicting battery degradation based on the battery's electrochemical model (for example, a pseudo-two-dimensional model), or predicting based on deep neural network models such as LSTM (long short-term memory network). However, these prediction solutions are mainly suitable for scenarios where charging changes are not significant, such as household vehicles.

[0061] An embodiment of the present invention provides a method for predicting the battery life of a rental vehicle. Through multiple rounds of prediction processing, and setting the battery's charge and discharge characteristics in each round of prediction processing, the battery life is predicted based on multiple charge and discharge characteristics. The method is suitable for situations where multiple charge and discharge characteristics exist in car rental scenarios.

[0062] The present invention provides a method for predicting the battery life of a rental vehicle, see Figure 1 As shown, including:

[0063] Step 101: Pre-build a prediction model for predicting battery parameters.

[0064] In this embodiment, to predict the battery lifespan, battery parameters related to battery lifespan are predicted. For example, these battery parameters may include battery capacity and battery internal resistance. Battery capacity prediction technology is relatively mature, so battery capacity is preferred as the battery parameter to be predicted.

[0065] A corresponding prediction model is pre-built to predict the battery parameters. For example, the prediction model can be built based on LSTM to predict changes in battery parameters. The battery parameters are related to the battery's charge and discharge characteristics, so the prediction model needs to be able to predict battery parameters under different charge and discharge characteristics. This will be explained later.

[0066] Step 102: performing multiple rounds of prediction processing on the battery parameters of the target battery according to the prediction model until the predicted battery parameters of the target battery meet the prediction stop condition.

[0067] In this embodiment, the rental vehicle battery for which lifespan prediction is required is referred to as a target battery. Multiple rounds of prediction processing are performed on the target battery based on the prediction model, and each round of prediction processing is used to update the battery parameters of the target battery. After the multiple prediction processes, the predicted battery parameters gradually approach the parameters corresponding to the end of life of the target battery. At this time, it can be determined that the predicted battery parameters meet the stop prediction condition. In other words, the stop prediction condition is that the predicted battery parameters of the target battery indicate the end of life (EOL) of the target battery.

[0068] For example, if the battery parameter is battery capacity, a capacity attenuation threshold may be set, such as 80%. If the battery capacity of the target battery is lower than 80% after multiple rounds of prediction processing, it may be determined that the prediction stop condition is met.

[0069] Taking the current round of prediction processing as an example, the current round of prediction processing includes steps 1021 to 1023.

[0070] Step 1021: Determine the current charge and discharge characteristics of the target battery in the current round.

[0071] In this embodiment, the target battery of the rental vehicle may have multiple charge and discharge characteristics, which may be determined based on the driving habits (discharge mode) and charging mode corresponding to the target battery. Different driving habits and charging modes correspond to different charge and discharge characteristics.

[0072] For example, two driving habits can be determined based on whether the driver accelerates and brakes suddenly; two charging methods can be determined based on whether fast charging is used. Based on the two driving habits and two charging methods, four charging and discharging characteristics can be determined. It is understood that driving habits and charging methods can be further subdivided to identify more charging and discharging characteristics. This embodiment does not limit the specific number of charging and discharging characteristics.

[0073] For each round of prediction processing, a unique charge and discharge feature needs to be determined; for the convenience of description, the charge and discharge feature corresponding to the current round of prediction processing is referred to as the current charge and discharge feature.

[0074] Step 1022: Determine the current charge and discharge cycle number corresponding to the current round, and add the current charge and discharge cycle number to the total charge and discharge cycle number.

[0075] In this embodiment, the total number of charge and discharge cycles represents the charge and discharge status of the target battery. During each round of prediction processing, the target battery is charged and discharged for a certain number of cycles. For the current round of prediction processing, the number of charge and discharge cycles of the target battery is called the current number of charge and discharge cycles. The total number of charge and discharge cycles is updated by adding the current number of charge and discharge cycles to the total number of charge and discharge cycles.

[0076] It can be understood that when predicting the target battery, the target battery has an initial total number of charge and discharge cycles, on which the number of charge and discharge cycles corresponding to each round of prediction processing is sequentially increased to achieve an update of the total number of charge and discharge cycles.

[0077] The number of charge and discharge cycles in each round (e.g., the current number of charge and discharge cycles) can be a fixed value not less than 1, for example, 1, meaning that only one charge and discharge process is performed on the target battery in each round of prediction processing. Alternatively, the number of charge and discharge cycles in each round can be determined based on other methods.

[0078] Step 1023: Use the battery parameters predicted by the previous round of prediction processing as the initial battery parameters for the current round of prediction processing, and use the prediction model to predict the battery parameters of the target battery according to the current charge and discharge characteristics and the current number of charge and discharge cycles to determine the battery parameters of the target battery after the current number of charge and discharge cycles.

[0079] In this embodiment, each round of prediction processing updates the battery parameters (e.g., battery capacity, internal resistance, etc.) of the target battery. When the current round of prediction processing is performed, the battery parameters predicted by the previous round of prediction processing are used as the initial battery parameters for the current round of prediction processing, i.e., the initial battery parameters. It should be understood that the initial battery parameters corresponding to the first round of prediction processing are the actual battery parameters of the target battery.

[0080] After determining the current charge and discharge characteristics and the current number of charge and discharge cycles, the battery parameters of the target battery can be predicted based on the prediction model. The prediction obtains the change in the battery parameters of the target battery after the current number of charge and discharge cycles, that is, the target battery will change from the initial battery parameters to what extent, thereby determining the battery parameters of the target battery after the current number of charge and discharge cycles. Moreover, if the stopping prediction condition is not met at this time, the battery parameters will also be used as the initial battery parameters for the next round of prediction processing, and the prediction processing will continue.

[0081] For example, if the battery parameter is battery capacity, and the initial battery capacity (i.e., initial battery parameter) in the current round of prediction processing is 90%, if the target battery's battery capacity decreases by 0.5% after the current number of charge-discharge cycles, then the target battery's battery capacity after the current number of charge-discharge cycles can be determined to be 89.5%. In the next round of prediction processing, predictions are continued based on the initial condition of a battery capacity of 89.5%.

[0082] Step 103: Determine the predicted life of the target battery according to the total number of charge and discharge cycles determined by multiple rounds of battery parameter prediction processing.

[0083] In this embodiment, when the battery parameters of the target battery meet the conditions for stopping prediction, the prediction processing is stopped, that is, the total number of charge and discharge cycles of the target battery is no longer increased. The total number of charge and discharge cycles at this time is the maximum number of charge and discharge cycles that can be charged and discharged when the target battery reaches the end of its life. Therefore, based on the total number of charge and discharge cycles at this time, the predicted life of the target battery can be determined. The predicted life is specifically the number of cycles of the target battery, that is, the total number of charge and discharge cycles of the target battery.

[0084] For example, the current actual number of charge and discharge cycles of the target battery is 300 times, that is, the initial value of the total number of charge and discharge cycles is 300; if the number of charge and discharge cycles is set to 1 in each round of prediction processing, if the prediction stop condition is reached after 1000 rounds of prediction processing, the total number of charge and discharge times of the target battery is 1300 times, that is, the predicted cycle life (i.e., predicted life) of the target battery is 1300 times, or in other words, the target battery can continue to be charged and discharged for approximately 1000 times.

[0085] The method for predicting the battery life of a rental vehicle provided in an embodiment of the present invention performs multiple rounds of prediction processing, and sets the charge and discharge characteristics of the target battery in each round of prediction processing. By setting corresponding charge and discharge characteristics for each round, the simulation of the variable charge and discharge mode of the target battery is realized. The method can predict the battery life based on multiple charge and discharge characteristics, and is suitable for situations where multiple charge and discharge characteristics exist in rental vehicle scenarios. When the rental vehicle battery is used based on various driving habits and charging methods, the method can also relatively accurately predict the service life of the rental vehicle battery, which can provide a reference basis for the pricing of rental vehicles.

[0086] The present invention also provides another method for predicting the battery life of a rental vehicle, see Figure 2 As shown, this includes:

[0087] Step 201: Pre-build a prediction model for predicting battery parameters.

[0088] For details, please refer to the relevant description of step 101 above, which will not be repeated here.

[0089] Step 202: Determine the charge and discharge characteristics that have been transferred from the previous charge and discharge characteristics in the previous round based on the target characteristic transfer matrix of the target battery, and use the transferred charge and discharge characteristics as the current charge and discharge characteristics in the current round. The target characteristic transfer matrix represents the probability of the target battery transferring from one charge and discharge characteristic to another.

[0090] In this embodiment, during step 1021, "Determining the Current Charge and Discharge Characteristics of the Target Battery in the Current Wheel," a corresponding charge and discharge characteristic may be randomly selected as the current charge and discharge characteristic based on the probability distribution of various charge and discharge characteristics. However, the current charge and discharge characteristic may be continuous; for example, when a driver rents a vehicle for a long period of time, the charge and discharge characteristics (driving habits, charging method) may not change over time. Traditional methods of randomly selecting charge and discharge characteristics cannot reflect this continuity.

[0091] Based on this, a matrix is ​​constructed to represent the transfer probability between various charge and discharge characteristics of the target battery, namely the target feature transfer matrix, which is subsequently represented by P. In this embodiment, the target feature transfer matrix P is used to represent the transfer probability between various charge and discharge characteristics; if there are n types of charge and discharge characteristics, the target feature transfer matrix P is an n×n matrix, where the element p in the i-th row and j-th column is ij represents the probability of transitioning from the i-th charge-discharge characteristic to the j-th charge-discharge characteristic. When i=j, the charge-discharge characteristic does not change.

[0092] If the charge and discharge feature of the previous round is charge and discharge feature A, the probability of transferring from the charge and discharge feature A to each charge and discharge feature can be determined based on the target feature transfer matrix P, and then the charge and discharge feature to be used next time, that is, the current charge and discharge feature, can be determined based on each probability.

[0093] Taking the three charge and discharge characteristics as an example, the transfer of the three charge and discharge characteristics can be seen in Figure 3 As shown, in this embodiment, Indicates that the element p ij , Figure 3 The corresponding target feature transfer matrix P can be expressed as:

[0094] .

[0095] Taking the first row of the target feature transfer matrix P as an example, the three elements respectively represent the probability of transferring from the first charge and discharge feature to various charge and discharge features.

[0096] If the previous charge-discharge feature is the first charge-discharge feature, the probability of transferring to various charge-discharge features can be determined based on the three elements in the first row of the target feature transfer matrix P, that is, 、 、 , based on these three probabilities, determine which type of charging and discharging characteristics the current charging and discharging characteristics are.

[0097] In some optional embodiments, the above step 202 of "determining the charge and discharge characteristics transferred from the previous charge and discharge characteristics of the previous round according to the target characteristic transfer matrix of the target battery" may include steps A1 to A3.

[0098] Step A1: Collect statistics on the transfer of charge and discharge characteristics of the reference battery during the rental process to generate an initial feature transfer matrix Q.

[0099] Step A2: Determine the target characteristic transfer matrix P of the target battery according to the initial characteristic transfer matrix Q, and:

[0100] ;

[0101] in, Indicates the probability that the target battery is in the i-th charge and discharge characteristics, Indicates the probability that the target battery is in the jth charge and discharge characteristics, i≠j; represents the probability of transferring from the i-th charge and discharge feature to the j-th charge and discharge feature in the initial feature transfer matrix Q, represents the probability of transferring from the jth charge and discharge feature to the ith charge and discharge feature in the initial feature transfer matrix Q, It represents the probability of transferring from the i-th charge and discharge feature to the j-th charge and discharge feature in the target feature transfer matrix P.

[0102] Step A3: According to the target feature transfer matrix P, determine the last charge and discharge feature from the previous round The probability distribution of various charge and discharge characteristics transferred to, and the current charge and discharge characteristics of the current round are selected according to the probability distribution ; T represents the round of prediction processing.

[0103] In this embodiment, based on the target feature transfer matrix P, the charge and discharge features in each round of prediction processing can be determined in sequence to form a Markov chain corresponding to the charge and discharge features.

[0104] In each round of prediction processing, the corresponding charge and discharge characteristics need to conform to the required probability distribution S. The probability distribution S can be specifically based on statistics of various charge and discharge characteristics throughout the life cycle of the reference battery to determine the proportion of various charge and discharge characteristics, thereby determining the corresponding probability distribution S.

[0105] Furthermore, the charge and discharge characteristics of the next round of prediction processing determined based on the target feature transfer matrix P must also conform to the probability distribution S to ensure the stability of the Markov chain, that is, to meet the following requirements: ; The probability distribution S is a 1×n matrix (i.e., a row vector).

[0106] .

[0107] In the above formula, represents the probability that the target battery is in the i-th charge and discharge characteristic, It represents the probability of transferring from the i-th charge and discharge feature to the j-th charge and discharge feature in the target feature transfer matrix P.

[0108] And, from the above formula, we can get: For example, when j=1, the first element of the probability distribution S is .

[0109] Since each element in the j-th row of the target feature transfer matrix P represents the probability of transferring from the j-th charge and discharge feature to another charge and discharge feature, the sum of these probabilities should be 1, that is, , add it to , we can get:

[0110] .

[0111] Suppose for any i, , then the above equation can be guaranteed to hold, that is, In other words, as long as , it can be guaranteed , the former is a sufficient condition for the latter.

[0112] In order to accurately determine the target feature transfer matrix P, in this embodiment, the transfer of charge and discharge characteristics of the reference battery during the rental process is obtained and these transfer conditions are statistically analyzed to preliminarily determine the corresponding feature transfer matrix. If the feature transfer matrix is ​​directly used as the target feature transfer matrix P at this time, it does not necessarily meet the requirements. Therefore, the feature matrix is ​​called the initial feature transfer matrix Q. It can be understood that the initial feature transfer matrix Q is also an n×n matrix.

[0113] The reference battery may be a battery of the same model as the target battery; or the reference battery may be the target battery, that is, statistics are collected on the transfer of charge and discharge characteristics of the target battery during the rental process.

[0114] Furthermore, the transfer situation specifically includes the number of transfers of the reference battery from one charge and discharge characteristic to another charge and discharge characteristic, and the proportion of the total number of transfers of the charge and discharge characteristic. For example, if n=3 (i.e., there are three charge and discharge characteristics), by counting the transfer situations of the charge and discharge characteristics, it can be determined that the number of transfers from the first charge and discharge characteristic to the second charge and discharge characteristic and the third charge and discharge characteristic are 400 and 500 times, respectively, while the number of transfers for the first charge and discharge characteristic remains unchanged is 100 times. Then, the total number of transfers for the first charge and discharge characteristic is 1000 times, and the transfer probabilities to the first charge and discharge characteristic, the second charge and discharge characteristic, and the third charge and discharge characteristic are 0.1, 0.4, and 0.5, respectively. That is, the three elements of the first row of the initial feature transfer matrix Q are 0.1, 0.4, and 0.5, respectively.

[0115] Although it is difficult to directly determine the accurate target feature transfer matrix P based on the probability distribution S, as shown above, if ,but . Each element in the initial feature transfer matrix Q Represents the corresponding element in the target feature transfer matrix P , which can be expressed as: , is the undetermined coefficient.

[0116] at this time, .

[0117] like ,but , that is, the former is also a sufficient condition for the latter.

[0118] in, represents the probability that the target battery currently has the jth charge and discharge characteristic, and It represents the probability that the target battery transfers from the jth charge and discharge characteristics to the ith charge and discharge characteristics, that is, is a probability of 0~1; similarly, It is also a probability of 0~1.

[0119] therefore, , its physical meaning is: although Not necessarily , but there is a certain probability yes In other words, when sampling based on the initial feature transfer matrix Q, if the probability To decide whether to retain the sampled samples, the transfer of the retained samples can eventually be made to conform to the target feature transfer matrix P.

[0120] But due to the probability If it is too small, most of the samples will be discarded, that is, only a small number of samples will be retained (for example, , will result in 90% of the samples being discarded and only 10% of the samples being retained), which is inefficient.

[0121] for and The smaller of

[0122] .

[0123] like , accordingly, ,at this time .

[0124] Therefore, in this embodiment, the probability , which satisfies ,Right now:

[0125] .

[0126] Moreover, the probability at this time Greater than , thus enabling sampling with higher probability.

[0127] It should be noted that when i≠j, If i=j, then based on the fact that the sum of the probabilities corresponding to the same charge and discharge characteristics is 1, we can calculate:

[0128] .

[0129] In determining the elements of the target feature transfer matrix P After that, the charge and discharge characteristics of the previous round can be determined. The probability distribution of various charge and discharge characteristics transferred to the target corresponds to the elements of the corresponding row in the target feature transfer matrix P. Then, the current charge and discharge characteristics of the current round are selected based on the probability distribution. .

[0130] Optionally, the above step A3 "selects the current charge and discharge characteristics of the current round according to the probability distribution ”, including steps A31 to A32.

[0131] Step A31 : dividing the value space from 0 to 1 into multiple value ranges according to the probability values ​​corresponding to various charge and discharge characteristics in the probability distribution, wherein the size of each value range matches the probability value corresponding to the corresponding charge and discharge characteristic.

[0132] Step A32: randomly generate a random number between 0 and 1, and use the charge and discharge characteristics corresponding to the value range in which the random number falls as the current charge and discharge characteristics of the current round. .

[0133] For example, if there are three charge and discharge characteristics, For the first type of charge and discharge characteristics, the corresponding probability distribution can be determined according to the first row elements of the target feature transfer matrix P; assuming that the probability distribution is (0.5, 0.3, 0.2), the corresponding value ranges can be set for the three probability values: (0, 0.5], (0.5, 0.8], and (0.8, 1).

[0134] A random number r is randomly generated between 0 and 1. Based on the size of the random number r, it can be determined which value range it falls into, and then the corresponding charge and discharge characteristics can be determined. For example, if the random number r = 0.68, it falls into the value range (0.5, 0.8] with a probability of 0.3 (the probability corresponding to the second charge and discharge characteristics), so the second charge and discharge characteristics can be used as the current charge and discharge characteristics. .

[0135] In this embodiment, as shown in the above step 1022, it is necessary to determine the current number of charge and discharge cycles corresponding to the current round, wherein determining the current number of charge and discharge cycles corresponding to the current round includes: after determining the current charge and discharge characteristics, repeatedly performing the feature transfer operation until the next charge and discharge characteristics of the next round of prediction processing are determined.

[0136] The above-mentioned feature transfer operation includes: determining the pending charge and discharge feature to be transferred from the current charge and discharge feature according to the target feature transfer matrix; if the pending charge and discharge feature is the same as the current charge and discharge feature, then adding one to the current charge and discharge cycle number, and then continuing to perform the feature transfer operation; the initial value of the current charge and discharge cycle number is 1; if the pending charge and discharge feature is different from the current charge and discharge feature, then using the pending charge and discharge feature as the next charge and discharge feature for the next round of prediction processing.

[0137] Specifically, if Figure 2 As shown, the process of determining the current number of charge and discharge cycles specifically includes steps 203 to 207.

[0138] Step 203: The current charge-discharge cycle number of the target battery is set to 1. That is, the initial value of the current charge-discharge cycle number is 1.

[0139] Step 204: Determine the pending charge and discharge feature to be transferred from the current charge and discharge feature based on the target feature transfer matrix. This process can also be based on the method of steps A31 to A32 to determine the pending charge and discharge feature, which will not be described in detail here.

[0140] Step 205: Check whether the pending charge-discharge characteristics are the same as the current charge-discharge characteristics. If they are the same, proceed to step 206; otherwise, proceed to step 207.

[0141] Step 206: The current charge and discharge cycle number of the target battery is incremented by 1. Then, step 204 is executed again, i.e., the above-mentioned feature transfer operation is repeated.

[0142] Step 207: Using the pending charge and discharge feature as the next charge and discharge feature for the next round of prediction processing.

[0143] In this embodiment, when determining the current number of charge and discharge cycles, a transition judgment is continued based on the target feature transfer matrix P to determine whether there are multiple instances of the same charge and discharge characteristics. If so, these instances of the same charge and discharge characteristics are treated as a single prediction process, thereby reducing the number of prediction processes and improving processing efficiency.

[0144] For example, after determining the current charge and discharge characteristics, if the determined pending charge and discharge characteristics are the same as the current charge and discharge characteristics, the current number of charge and discharge cycles is increased by 1, that is, the current number of charge and discharge cycles becomes 2; if step 204 is then executed to again determine the pending charge and discharge characteristics that are the same as the current charge and discharge characteristics, the current number of charge and discharge cycles becomes 3, and so on.

[0145] If the determined pending charge and discharge characteristics are different from the current charge and discharge characteristics, the current charge and discharge cycle number will no longer be increased by one. At this time, the determined pending charge and discharge characteristics can be used as the charge and discharge characteristics corresponding to the next round of prediction processing, that is, the next charge and discharge characteristics.

[0146] It should be noted that during the first round of prediction processing, when determining the current charge and discharge characteristics based on step 202, calculation processing is required, for example, determining the current charge and discharge characteristics based on the random number r. In subsequent rounds of prediction processing, since the next charge and discharge characteristics have been determined in the previous round of prediction processing, no additional calculation is required when executing step 202, and the charge and discharge characteristics determined in the previous round can be directly used.

[0147] Step 208: Add the current number of charge and discharge cycles to the total number of charge and discharge cycles.

[0148] Step 209: Use the battery parameters predicted by the previous round of prediction processing as the initial battery parameters for the current round of prediction processing, and use the prediction model to predict the battery parameters of the target battery based on the current charge and discharge characteristics and the current number of charge and discharge cycles to determine the battery parameters of the target battery after the current number of charge and discharge cycles.

[0149] In some optional embodiments, the prediction model includes prediction sub-models corresponding to various charge and discharge characteristics; the prediction sub-models are used to predict changes in battery parameters of the target battery with the number of charge and discharge cycles when the target battery is charged and discharged according to the corresponding charge and discharge characteristics.

[0150] The above step 209 "using the prediction model to predict the battery parameters of the target battery according to the current charge and discharge characteristics and the current charge and discharge cycles, and determining the battery parameters of the target battery after the current charge and discharge cycles" may include steps B1 to B2.

[0151] Step B1: Determine the target prediction sub-model corresponding to the current charge and discharge characteristics.

[0152] Step B2: Input the initial battery parameters of the current round of prediction processing and the current number of charge and discharge cycles into the target prediction sub-model, and determine the battery parameters of the target battery after the current number of charge and discharge cycles based on the prediction results of the target prediction sub-model.

[0153] In this embodiment, a model for predicting battery parameter changes, i.e., a prediction sub-model, is set for each charge-discharge characteristic. For example, if four charge-discharge characteristics are involved, four prediction sub-models are required. These prediction sub-models can predict how the battery parameters of the target battery change with the number of charge-discharge cycles under certain charge-discharge characteristics.

[0154] Specifically, for the current charge and discharge characteristics of the current cycle, a corresponding prediction sub-model, namely a target prediction sub-model, can be determined. The target prediction sub-model can predict changes in the battery parameters of the target battery, such as the decay rate of the battery capacity of the target battery, when the target battery is charged and discharged with the current charge and discharge characteristics.

[0155] The initial battery parameters of the current round of prediction processing and the current number of charge and discharge cycles are input into the target prediction sub-model. The initial battery parameters are used as the initial values ​​of charge and discharge, and the current number of charge and discharge cycles is used as the number of cycles corresponding to charge and discharge. It can be determined that after the target battery is charged and discharged for the current number of charge and discharge cycles according to the current charge and discharge characteristics, the battery parameters of the target battery will change from the initial battery parameters, thereby determining the battery parameters of the target battery after the current number of charge and discharge cycles.

[0156] In each round of prediction processing, the appropriate target prediction sub-model is selected according to the method of step B1 to step B2, which can realize the prediction of battery parameters under different charge and discharge characteristics, and finally obtain the final total charge and discharge cycles of the target battery.

[0157] Step 210: Check whether the battery parameters meet the stop prediction condition. If yes, proceed to step 211; otherwise, re-execute step 202, i.e., perform the next round of prediction processing.

[0158] Step 211: Determine the predicted life of the target battery based on the total number of charge and discharge cycles determined by multiple rounds of battery parameter prediction processing.

[0159] The battery life prediction method for rental vehicles provided in an embodiment of the present invention can predict battery parameters after a certain number of charge and discharge cycles. Even if the battery's charge and discharge method (e.g., whether fast charging or not) changes later, the vehicle life prediction can continue based on the changed charge and discharge behavior. After multiple predictions, the final number of charge and discharge cycles that the battery can sustain can be predicted, thus achieving battery life prediction. The feature transfer matrix can capture the continuously changing characteristics of charge and discharge characteristics, enabling long-term rental scenarios. Based on the initial feature transfer matrix and probability distribution, the target feature transfer matrix can be accurately determined, ensuring the stability of the probability distribution of charge and discharge characteristics.

[0160] The above details the process of the method for predicting the battery life of a rental vehicle. This method can also be implemented by a corresponding device. The structure and function of the device are described in detail below.

[0161] Based on the same inventive concept, the present invention also provides a device for predicting the battery life of a rental vehicle. Figure 4 As shown, the device includes:

[0162] A model building module 401 is used to pre-build a prediction model for predicting battery parameters;

[0163] A prediction module 402 is configured to perform multiple rounds of prediction processing on the battery parameters of the target battery according to the prediction model until the predicted battery parameters of the target battery meet a stop prediction condition;

[0164] A lifespan determination module 403 is configured to determine a predicted lifespan of the target battery based on a total number of charge and discharge cycles determined by multiple rounds of battery parameter prediction processing;

[0165] The prediction module 402 performs the current round of prediction processing, including:

[0166] Determining current charge and discharge characteristics of the target battery in a current round;

[0167] Determine the current number of charge and discharge cycles corresponding to the current wheel, and add the current number of charge and discharge cycles to the total number of charge and discharge cycles;

[0168] The battery parameters predicted by the previous round of prediction processing are used as the initial battery parameters of the current round of prediction processing. The prediction model is used to predict the battery parameters of the target battery according to the current charge and discharge characteristics and the current number of charge and discharge cycles, and the battery parameters of the target battery after charging and discharging the current number of charge and discharge cycles are determined.

[0169] In some optional embodiments, the current charge and discharge characteristics are determined based on the following method:

[0170] Determine, according to the target characteristic transfer matrix of the target battery, the charge and discharge characteristics transferred from the previous charge and discharge characteristics of the previous round, and use the transferred charge and discharge characteristics as the current charge and discharge characteristics in the current round;

[0171] The target feature transfer matrix is ​​used to represent the probability of the target battery transferring from one charge and discharge feature to another charge and discharge feature.

[0172] In some optional embodiments, determining the charge and discharge characteristics transferred from the previous charge and discharge characteristics of the previous round according to the target characteristic transfer matrix of the target battery includes:

[0173] Collect statistics on the transfer of charge and discharge characteristics of the reference battery during the rental process to generate the initial feature transfer matrix Q;

[0174] The target characteristic transfer matrix P of the target battery is determined according to the initial characteristic transfer matrix Q, and:

[0175] ;

[0176] in, represents the probability that the target battery is in the i-th charge and discharge characteristic, represents the probability that the target battery is in the jth charge and discharge characteristic, i≠j; represents the probability of transferring from the i-th charge and discharge feature to the j-th charge and discharge feature in the initial feature transfer matrix Q, represents the probability of transferring from the jth charge-discharge feature to the ith charge-discharge feature in the initial feature transfer matrix Q, represents the probability of transferring from the i-th charge and discharge feature to the j-th charge and discharge feature in the target feature transfer matrix P;

[0177] According to the target feature transfer matrix P, determine the last charge and discharge feature from the previous round The probability distribution of various charge and discharge characteristics transferred to, and the current charge and discharge characteristics of the current round are selected according to the probability distribution ; T represents the round of the prediction process.

[0178] In some optional embodiments, the current charge and discharge characteristics of the current round are selected according to the probability distribution. ,include:

[0179] According to the probability values ​​corresponding to various charge and discharge characteristics in the probability distribution, the value space from 0 to 1 is divided into multiple value ranges, and the size of each value range matches the probability value corresponding to the corresponding charge and discharge characteristic;

[0180] Randomly generate a random number between 0 and 1, and use the charge and discharge characteristics corresponding to the value range in which the random number falls as the current charge and discharge characteristics of the current round .

[0181] In some optional implementations, determining the current number of charge and discharge cycles corresponding to the current wheel includes:

[0182] After determining the current charge and discharge feature, repeatedly performing the feature transfer operation until determining the next charge and discharge feature for the next round of prediction processing;

[0183] The feature transfer operation includes:

[0184] Determining, according to the target feature transfer matrix, a pending charge and discharge feature to be transferred from the current charge and discharge feature;

[0185] If the pending charge and discharge characteristic is the same as the current charge and discharge characteristic, the current charge and discharge cycle number is incremented by one, and then the characteristic transfer operation is continued; the initial value of the current charge and discharge cycle number is 1;

[0186] If the pending charge and discharge feature is different from the current charge and discharge feature, the pending charge and discharge feature is used as the next charge and discharge feature in the next round of prediction processing.

[0187] In some optional embodiments, the prediction model includes prediction sub-models corresponding to various charge and discharge characteristics; the prediction sub-models are used to predict changes in battery parameters of the target battery with the number of charge and discharge cycles when the target battery is charged and discharged according to the corresponding charge and discharge characteristics;

[0188] The method of using the prediction model to predict the battery parameters of the target battery according to the current charge and discharge characteristics and the current number of charge and discharge cycles, and determining the battery parameters of the target battery after charging and discharging the current number of charge and discharge cycles, includes:

[0189] Determining a target prediction sub-model corresponding to the current charge and discharge characteristics;

[0190] The initial battery parameters of the current round of prediction processing and the current number of charge and discharge cycles are input into the target prediction sub-model, and the battery parameters of the target battery after charging and discharging the current number of charge and discharge cycles are determined according to the prediction results of the target prediction sub-model.

[0191] An embodiment of the present invention further provides a computer storage medium storing computer executable instructions, which includes a program for executing the above-mentioned method for predicting the battery life of a rental vehicle. The computer executable instructions can execute the method in any of the above-mentioned method embodiments.

[0192] Among them, the computer storage medium can be any available medium or data storage device that can be accessed by the computer, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO)), optical storage (such as CDs, DVDs, BDs, HVDs, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drives (SSDs)), etc.

[0193] A portion of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the form in which the computer program instruction exists in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc. Accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium that can be accessed by the computer.

[0194] Figure 5 The block diagram of the structure of an electronic device according to another embodiment of the present invention is shown. The electronic device 1100 may be a host server with computing capabilities, a personal computer (PC), or a portable computer or terminal. The specific embodiments of the present invention do not limit the specific implementation of the electronic device.

[0195] The electronic device 1100 includes at least one processor 1110 , a communication interface 1120 , a memory array 1130 , and a bus 1140 . The processor 1110 , the communication interface 1120 , and the memory array 1130 communicate with each other via the bus 1140 .

[0196] The communication interface 1120 is used to communicate with network elements, where the network elements include, for example, a virtual machine management center, shared storage, etc.

[0197] The processor 1110 is used to execute programs. The processor 1110 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention.

[0198] Memory 1130 is used for executable instructions. Memory 1130 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage. Memory 1130 may also be a memory array. Memory 1130 may also be divided into blocks, and the blocks may be combined into virtual volumes according to certain rules. The instructions stored in memory 1130 can be executed by processor 1110, so that processor 1110 can execute the method for predicting the battery life of a rental vehicle in any of the above-mentioned method embodiments.

[0199] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for predicting the battery life of a rental vehicle, characterized in that: include: Pre-built prediction models for predicting battery parameters; Performing multiple rounds of prediction processing on the battery parameters of the target battery according to the prediction model until the predicted battery parameters of the target battery meet the prediction stop condition; Determining the predicted life of the target battery based on the total number of charge and discharge cycles determined by multiple rounds of battery parameter prediction processing; The current round of prediction processing includes: Determining current charge and discharge characteristics of the target battery in a current round; Determine the current number of charge and discharge cycles corresponding to the current wheel, and add the current number of charge and discharge cycles to the total number of charge and discharge cycles; The battery parameters predicted by the previous round of prediction processing are used as the initial battery parameters of the current round of prediction processing. The prediction model is used to predict the battery parameters of the target battery according to the current charge and discharge characteristics and the current number of charge and discharge cycles, and the battery parameters of the target battery after charging and discharging the current number of charge and discharge cycles are determined.

2. The method according to claim 1, characterized in that The current charge and discharge characteristics are determined based on the following method: Determine, according to the target characteristic transfer matrix of the target battery, the charge and discharge characteristics transferred from the previous charge and discharge characteristics of the previous round, and use the transferred charge and discharge characteristics as the current charge and discharge characteristics in the current round; The target feature transfer matrix is ​​used to represent the probability of the target battery transferring from one charge and discharge feature to another charge and discharge feature.

3. The method according to claim 2, characterized in that The determining, based on the target characteristic transfer matrix of the target battery, the charge and discharge characteristic transferred from the previous charge and discharge characteristic of the previous round includes: Collect statistics on the transfer of charge and discharge characteristics of the reference battery during the rental process to generate the initial feature transfer matrix Q; The target characteristic transfer matrix P of the target battery is determined according to the initial characteristic transfer matrix Q, and: ； in, represents the probability that the target battery is in the i-th charge and discharge characteristic, represents the probability that the target battery is in the jth charge and discharge characteristic, i≠j; represents the probability of transferring from the i-th charge and discharge feature to the j-th charge and discharge feature in the initial feature transfer matrix Q, represents the probability of transferring from the jth charge-discharge feature to the ith charge-discharge feature in the initial feature transfer matrix Q, represents the probability of transferring from the i-th charge and discharge feature to the j-th charge and discharge feature in the target feature transfer matrix P; According to the target feature transfer matrix P, determine the last charge and discharge feature from the previous round The probability distribution of various charge and discharge characteristics transferred to, and the current charge and discharge characteristics of the current round are selected according to the probability distribution ; T represents the round of the prediction process.

4. The method according to claim 3, characterized in that The current charge and discharge characteristics of the current round are selected according to the probability distribution ,include: According to the probability values ​​corresponding to various charge and discharge characteristics in the probability distribution, the value space from 0 to 1 is divided into multiple value ranges, and the size of each value range matches the probability value corresponding to the corresponding charge and discharge characteristic; Randomly generate a random number between 0 and 1, and use the charge and discharge characteristics corresponding to the value range in which the random number falls as the current charge and discharge characteristics of the current round .

5. The method according to claim 2, characterized in that Determining the current number of charge and discharge cycles corresponding to the current wheel includes: After determining the current charge and discharge feature, repeatedly performing the feature transfer operation until determining the next charge and discharge feature for the next round of prediction processing; The feature transfer operation includes: Determining, according to the target feature transfer matrix, a pending charge and discharge feature to be transferred from the current charge and discharge feature; If the pending charge and discharge characteristic is the same as the current charge and discharge characteristic, the current charge and discharge cycle number is incremented by one, and then the characteristic transfer operation is continued; the initial value of the current charge and discharge cycle number is 1; If the pending charge and discharge feature is different from the current charge and discharge feature, the pending charge and discharge feature is used as the next charge and discharge feature in the next round of prediction processing.

6. The method according to any one of claims 1 to 5, characterized in that The prediction model includes prediction sub-models corresponding to various charge and discharge characteristics; the prediction sub-models are used to predict changes in the battery parameters of the target battery with the number of charge and discharge cycles when the target battery is charged and discharged according to the corresponding charge and discharge characteristics; The method of using the prediction model to predict the battery parameters of the target battery according to the current charge and discharge characteristics and the current number of charge and discharge cycles, and determining the battery parameters of the target battery after charging and discharging the current number of charge and discharge cycles, includes: Determining a target prediction sub-model corresponding to the current charge and discharge characteristics; The initial battery parameters of the current round of prediction processing and the current number of charge and discharge cycles are input into the target prediction sub-model, and the battery parameters of the target battery after charging and discharging the current number of charge and discharge cycles are determined according to the prediction results of the target prediction sub-model.

7. A device for predicting the battery life of a rental vehicle, characterized in that: include: A model building module for pre-building a prediction model for predicting battery parameters; A prediction module, configured to perform multiple rounds of prediction processing on the battery parameters of the target battery according to the prediction model until the predicted battery parameters of the target battery meet a stop prediction condition; a lifespan determination module, configured to determine a predicted lifespan of the target battery based on a total number of charge and discharge cycles determined by multiple rounds of battery parameter prediction processing; The prediction module performs the current round of prediction processing, including: Determining current charge and discharge characteristics of the target battery in a current round; Determine the current number of charge and discharge cycles corresponding to the current wheel, and add the current number of charge and discharge cycles to the total number of charge and discharge cycles; The battery parameters predicted by the previous round of prediction processing are used as the initial battery parameters of the current round of prediction processing. The prediction model is used to predict the battery parameters of the target battery according to the current charge and discharge characteristics and the current number of charge and discharge cycles, and the battery parameters of the target battery after charging and discharging the current number of charge and discharge cycles are determined.

8. A computer storage medium, characterized in that The computer storage medium stores computer-executable instructions, and the computer-executable instructions are used to execute the method for predicting the battery life of a rental vehicle according to any one of claims 1 to 6.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method for predicting the battery life of a rental vehicle as described in any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the method for predicting the battery life of a rental vehicle according to any one of claims 1 to 6.

Images