Charging method, device and electronic equipment

Abstract

The application discloses a charging method and device and electronic equipment, and belongs to the technical field of artificial intelligence. The method comprises the following steps: acquiring first target information, wherein the first target information comprises first information for representing a first charging scene and second information for representing a charging habit of a first user; determining a first charging speed corresponding to the first charging scene based on the first information and the second information, and determining a second charging speed based on the second information; determining a target charging speed based on the first charging speed and the second charging speed; and charging based on the target charging speed.

Description

Technical Field

[0001] This application belongs to the field of artificial intelligence technology, specifically relating to a charging method, device, and electronic device. Background Technology

[0002] As people use electronic devices more and more frequently, users' demands for the battery life of these devices are also increasing.

[0003] To improve the charging speed of electronic devices, fast charging technology has gradually become widespread. However, with the increase in charging speed and power of electronic devices, the heat generated by the battery during charging has also become more and more serious. How to balance the charging speed of electronic devices and the control of battery heat has become a major challenge. Summary of the Invention

[0004] The purpose of this application is to provide a charging method, apparatus, and electronic device that can balance the charging speed and battery heat control issues of the electronic device.

[0005] In a first aspect, embodiments of this application provide a charging method, the method comprising:

[0006] Obtain first target information, which includes: first information for characterizing a first charging scenario and second information for characterizing the charging habits of a first user;

[0007] Based on the first information and the second information, a first charging speed corresponding to the first charging scenario is determined, and a second charging speed is determined based on the second information;

[0008] Based on the first charging speed and the second charging speed, determine the target charging speed;

[0009] Charge according to the target charging speed.

[0010] Secondly, embodiments of this application provide a charging device, which includes:

[0011] The first acquisition module is used to acquire first target information, the first target information including: first information for characterizing the first charging scenario and second information for characterizing the charging habits of the first user;

[0012] The first determining module is used to determine the first charging speed corresponding to the first charging scenario based on the first information and the second information;

[0013] The second determining module is used to determine the second charging speed based on the second information;

[0014] The third determining module is used to determine the target charging speed based on the first charging speed and the second charging speed;

[0015] A charging module is used to charge the device based on the target charging speed.

[0016] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the charging method as described in the first aspect.

[0017] Fourthly, embodiments of this application provide a readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the charging method as described in the first aspect.

[0018] Fifthly, embodiments of this application provide a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being used to run programs or instructions to implement the steps of the charging method as described in the first aspect.

[0019] In this embodiment, by acquiring first target information, which includes first information characterizing a first charging scenario and second information characterizing a first user's charging habits; determining a first charging speed corresponding to the first charging scenario based on the first and second information, and determining a second charging speed based on the second information; determining a target charging speed based on the first and second charging speeds; and charging based on the target charging speed. In this way, by combining relevant information of the first charging scenario and relevant information of the user, a suitable charging speed can be provided to the user in the first charging scenario, thereby balancing the charging speed of the electronic device and battery heat control, providing fast charging to the user while taking into account battery heat dissipation. Attached Figure Description

[0020] Figure 1 This is a flowchart of the charging method provided in the embodiments of this application;

[0021] Figure 2 This is a structural diagram of the charging device provided in the embodiments of this application;

[0022] Figure 3 This is a structural diagram of the electronic device provided in the embodiments of this application;

[0023] Figure 4 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of this application. Detailed Implementation

[0024] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0025] The terms "first," "second," etc., used in the specification and claims of this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such use of data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more. Furthermore, in the specification and claims, "and / or" indicates at least one of the connected objects, and the character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0026] The charging method provided in this application will be described in detail below with reference to the accompanying drawings, through specific embodiments and application scenarios.

[0027] Figure 1 This is a flowchart of the charging method provided in the embodiments of this application, such as... Figure 1 As shown, it includes the following steps:

[0028] Step 101: Obtain first target information, which includes: first information for characterizing the first charging scenario and second information for characterizing the charging habits of the first user.

[0029] In this step, the first charging scenario can refer to the charging environment of the electronic device, which may include, but is not limited to, charging time, charging location, and the remaining battery power of the electronic device while it is charging.

[0030] The charging time can be the specific time the user charges the electronic device, such as 8:00 AM, or an approximate charging time, such as 7:00 AM to 9:00 AM; no specific limitation is made here. The charging location can be a Global Positioning System (GPS) location, which is a discrete latitude and longitude coordinate, or a location with specific meaning, such as an office or home; no specific limitation is made here.

[0031] The first user can be any user, or a user associated with an electronic device, such as a user of the electronic device. Charging habits may include, but are not limited to, the first user's average daily charging frequency (e.g., 5 times per day), average battery charge per charge (e.g., 50% charge per charge), and the percentage of the battery that the user charged to a certain threshold (e.g., 100%) in the first charging scenario based on historical data. For example, if a user charges 100 times at the current time and location in historical data, and 90 of those charges reach a certain threshold (e.g., 100%), then the percentage of the user charging to that threshold in the first charging scenario based on historical data is 90%.

[0032] In addition, the first target information may also include the first user's identity information, such as gender, age, and occupation.

[0033] Upon receiving a charging signal, the system can acquire the first target information. This acquisition can be achieved through methods including, but not limited to, the following:

[0034] Upon receiving a charging signal, monitor the remaining battery power of the electronic device and retrieve other applications of the electronic device, such as time display applications and location display applications, to obtain first information to characterize the first charging scenario.

[0035] Obtain the identity information of a first user pre-stored in the electronic device, and / or, second information pre-stored in the electronic device to characterize the charging habits of the first user;

[0036] Obtain the charging data of the first user within a historical time period to statistically obtain second information to characterize the charging habits of the second user.

[0037] Step 102: Based on the first information and the second information, determine the first charging speed corresponding to the first charging scenario.

[0038] In this step, the first charging speed can indicate the first user's level of anxiety about the battery level. The first charging speed can be characterized by a level (such as high, medium and low) or by the charging current. No specific limitation is made here.

[0039] In one optional implementation, the first charging speed corresponding to the first charging scenario can be directly determined based on the first information and the second information using a preset algorithm.

[0040] In another alternative implementation, the first charging speed can be determined as follows:

[0041] Based on the first information and the second information, the power demand level corresponding to the first charging scenario is determined, and the power demand level is used to characterize the correspondence between battery power demand and charging speed.

[0042] The first charging speed is determined based on the stated power demand.

[0043] The level of battery demand can be represented by a rating system, such as Level 1 anxiety, which indicates the user's level of anxiety about battery power needs. Battery demand can also be represented as a percentage, such as 100%, which indicates a high user demand for battery power and a faster charging speed. The following explanation will use a rating system to illustrate battery demand in detail.

[0044] In one alternative implementation, a higher level value representing the degree of power demand indicates a greater battery power demand, signifying greater anxiety about the battery's remaining charge and a faster charging speed is required. Conversely, a lower level value represents a lower battery power demand, indicating less anxiety about the battery's remaining charge and a slower charging speed is possible.

[0045] For example, the rating scale representing the level of power demand can include three levels: high, medium, and low, corresponding to high, medium, and low levels of user anxiety about battery life, respectively. Correspondingly, charging speeds also correspond to high, medium, and low levels.

[0046] In another alternative implementation, a smaller level value representing the degree of power demand indicates a greater battery power demand, signifying that the first user is more anxious about the battery's battery level and requires a faster charging speed. Conversely, a larger level value representing the degree of power demand indicates a lower battery power demand, signifying that the first user is less anxious about the battery's battery level and requires a slower charging speed.

[0047] In one optional implementation, the power demand level corresponding to the first charging scenario can be determined based on the first information and the second information, through a first preset relationship. For example, when the first charging scenario represents charging at home and the user's charging habit is charging once a day on average, the level value representing the power demand level can be low, indicating that the user is not anxious about the battery level and the battery demand is small. Conversely, when the first charging scenario represents charging in the office and the user's charging frequency is relatively high, the level value representing the power demand level can be high, indicating that the user is more anxious about the battery level and the battery demand is large.

[0048] In another alternative implementation, the first information and the second information can be quantified. For example, the time period from 7 to 9 o'clock can be quantified as a value 1, and the location can be quantified as a value 1, a value 2, or other values. Among them, the value 1 can represent the place where the user goes most often, and the value 2 can represent the place where the user goes second most often.

[0049] The quantified first and second information are input into a first model for probability prediction to obtain the first probability that a first user will charge the battery to a first preset threshold in the first charging scenario. Based on the first probability, the level of battery demand is determined. For example, a higher first probability indicates that the user is more likely to charge the battery to the first preset threshold in the first charging scenario, indicating a lower demand for battery power and less anxiety about battery life; correspondingly, a slower charging speed is required. Conversely, a lower first probability indicates that the user is more likely not to charge the battery to the first preset threshold in the first charging scenario, indicating a greater need for battery power and more anxiety about battery life; correspondingly, a faster charging speed is required.

[0050] Accordingly, charging speed levels can be determined based on the level of power demand, thus obtaining the first charging speed. For example, if the level representing the level of power demand is high, medium, and low, the corresponding charging speed levels are high, medium, and low, respectively, denoted by V. battery This indicates that the charging current can also be determined based on the level of power demand to obtain the first charging speed.

[0051] Step 103: Determine the second charging speed based on the second information.

[0052] In this step, the second charging speed can indicate the first user's level of anxiety about battery overheating. The second charging speed can be characterized by levels (such as high, medium, and low) or by charging current, without specific limitations here.

[0053] In one optional implementation, the second charging speed can be directly determined based on the second target information using a preset algorithm. The second target information may include second information and may also include the identity information of the first user, such as gender, age, and occupation.

[0054] In another alternative implementation, the second charging speed can be determined as follows:

[0055] Based on the second target information, the degree of heat limitation is determined. The degree of heat limitation is used to characterize the correspondence between battery heat limitation and charging speed. The second target information includes the second information.

[0056] The second charging speed is determined based on the degree of heat limitation.

[0057] Among them, the degree of heat limitation can be used to characterize the correspondence between battery heat limitation and charging speed. The degree of heat limitation can be characterized by levels, such as the second anxiety level, which can characterize the user's anxiety about battery heat. The degree of heat limitation can also be characterized by percentages, such as 100%, which indicates that the user has a high degree of concern about battery heat limitation and the charging speed is slower. The following explanation of the degree of heat limitation will use the level representation as an example.

[0058] In one alternative implementation, a higher level value characterizing the degree of heat limitation indicates greater user anxiety about battery heat generation and higher sensitivity to battery heat. Consequently, a greater degree of battery heat limitation is required, meaning battery heat needs to be limited as much as possible, resulting in a slower charging speed. Conversely, a lower level value characterizing the degree of heat limitation indicates less user anxiety about battery heat generation and lower sensitivity to battery heat. Consequently, a smaller degree of battery heat limitation is required, allowing for a faster charging speed.

[0059] For example, the level of heat limitation can be categorized into three levels: high, medium, and low, corresponding to users' levels of anxiety about battery overheating. Similarly, charging speed can be categorized into three levels: low, medium, and high.

[0060] The degree of fever restriction can be determined based on the second information, or it can be determined based on the second information and the identity information of the first user. No specific limitation is made here.

[0061] Correspondingly, a charging speed level can be determined based on the degree of heat limitation, thus obtaining a second charging speed. For example, when the level characterizing the degree of heat limitation is high, medium, and low, the corresponding charging speed levels are low, medium, and high, respectively, denoted by V. heating Alternatively, the charging current can be determined based on the degree of heat limitation to obtain the second charging speed.

[0062] Step 104: Determine the target charging speed based on the first charging speed and the second charging speed.

[0063] In one optional implementation, the first charging speed and the second charging speed can be weighted to obtain the target charging speed. For example, the first charging speed represents a charging current of 1 ampere per hour (A / h), and the second charging speed represents a charging current of 2 A / h. The target charging speed is obtained by weighting these two values.

[0064] In another alternative implementation, the target charging speed is determined by the levels of the first and second charging speeds. Specifically, the target charging speed can be queried from a preset rule table based on the first and second charging speeds.

[0065] The preset rule tables are shown in Table 1 and Table 2 below. Table 1 and Table 2 correspond to the determination of the target charging speed under different strategies. Table 1 prioritizes ensuring a good user experience regarding battery heat generation when determining the target charging speed, aiming to prevent the battery from overheating. Table 2 prioritizes ensuring a good user experience regarding charging speed, giving priority to maximizing charging speed.

[0066] In Tables 1 and 2, the first column represents the battery anxiety corresponding to the first charging speed, and the first row represents the heat anxiety corresponding to the second charging speed.

[0067] Table 1. Preset Rules Table (One of the Preset Rules)

[0068]

[0069] Table 2. Preset Rules Table 2

[0070]

[0071] As can be seen from Tables 1 and 2 above, when the charging speed level corresponding to the power demand (i.e., the first charging speed level) and the charging speed level corresponding to the heat limitation (i.e., the second charging speed level) are consistent, that charging speed level is determined as the target charging speed. For example, if both the charging speed level corresponding to the power demand and the charging speed level corresponding to the heat limitation are high, then the electronic device will be charged using high-speed charging.

[0072] When the charging speed level corresponding to the power demand level and the charging speed level corresponding to the heat limitation level are inconsistent, a target charging speed is determined based on these two charging speed levels according to a certain strategy. For example, if the charging speed level corresponding to the power demand level is high and the charging speed level corresponding to the heat limitation level is low, if the battery heat limitation is given priority, a target charging speed and a low charging speed can be determined, that is, the electronic device is charged in a low-speed charging mode.

[0073] In this way, users' anxiety about battery level and battery heat can be balanced, providing users with a suitable charging speed, and minimizing battery heat generation while ensuring the user's charging speed experience.

[0074] Step 105: Charge based on the target charging speed.

[0075] In this step, the charging current corresponding to the target charging speed can be used to charge the electronic device. In the specific implementation process, high-speed, medium-speed, and low-speed charging can be achieved by adjusting the charging current. The higher the charging speed, the higher the charging current, and correspondingly, the lower the charging speed, the lower the charging current.

[0076] It's important to note that during a single charge, the charging conditions of an electronic device may change over time, and consequently, the target charging speed may also change. Therefore, the charging speed can be continuously adjusted during a single charge by regulating the charging current, i.e., variable-speed charging of the electronic device. A single charge can refer to the period from receiving the charging signal to its loss. This eliminates the need for additional hardware for battery cooling, saving costs while ensuring a smooth charging experience for the user.

[0077] In this embodiment, by acquiring first target information, which includes first information characterizing a first charging scenario and second information characterizing a first user's charging habits; based on the first and second information, determining a first charging speed corresponding to the first charging scenario, and based on the second information, determining a second charging speed; based on the first and second charging speeds, determining a target charging speed; and charging based on the target charging speed. Thus, by combining relevant information about the first charging scenario and relevant information about the user, a suitable charging speed can be provided to the user in the first charging scenario, thereby balancing the charging speed of the electronic device and battery heat control, providing fast charging to the user while taking into account battery heat dissipation.

[0078] Optionally, the first information includes at least one of charging time, charging location, and remaining battery power;

[0079] And / or, the second information includes at least one of the following: the average number of historical charging times of the first user within a preset time period, the average amount of battery charge per historical charging by the first user, and a target ratio. The target ratio is the ratio of the first number of historical charging times to the second number of historical charging times. The first number of historical charging times is the number of times the battery capacity was charged to a first preset threshold during historical charging in the first charging scenario. The second number of historical charging times is the total number of historical charging times performed in the first charging scenario.

[0080] The first preset threshold can be set according to the actual situation, such as 99%, 100%, etc.

[0081] Optionally, step 102 specifically includes:

[0082] The first information and the second information are input into the first model to perform probability prediction, and the first probability that the first user will charge the battery to a first preset threshold in the first charging scenario is obtained.

[0083] Based on the first probability and the pre-acquired first level classification threshold, the power demand level corresponding to the first charging scenario is determined, and the power demand level is used to characterize the correspondence between battery power demand and charging speed.

[0084] The first charging speed is determined based on the stated power demand.

[0085] The first model is trained based on the first training sample data, which includes first sample information for characterizing the second charging scenario, second sample information for characterizing the charging habits of the second user, and charging results. The charging results are used to characterize whether the second user has charged the battery to the first preset threshold in the second charging scenario.

[0086] In this embodiment, by combining the first information and the second information, including time, location, current battery power remaining, and the first user's charging habits, the first model predicts whether the user's current charge will reach a first preset threshold, such as being fully charged, in order to quantify the user's anxiety level regarding battery power.

[0087] For example, if the first model predicts that the user can fully charge the battery this time, it means that the user is not in a hurry to charge the battery in the first charging scenario, that is, the user is not anxious about the battery level. Conversely, if the model predicts that the user can fully charge the battery this time, it means that the user is anxious about the battery level.

[0088] In one optional implementation, the input to the first model can be a feature representation of the first information and the second information, such as time x1, location x2, remaining battery power of the electronic device x3, average number of daily charging times x4, average charging power per charge x5, and the percentage of the battery that was charged to a first preset threshold in the current time and location in historical data x6. The output can be a first probability that the first user will charge the battery to the first preset threshold in the first charging scenario.

[0089] The first model can be a machine learning model or a deep learning model. The following explanation uses a machine learning model as an example. In an optional implementation, the first model can be a logistic regression model, and its structure can be represented by the following equation (1).

[0090]

[0091] In equation (1) above, p is the probability that the user will charge the battery to the first preset threshold in the first charging scenario, and w1, w2, ..., w6 and b are the network parameters of the first model.

[0092] Before using the first model, it needs to be pre-trained. The purpose of this training is to fix the network parameters of the first model so that it can accurately predict the probability that any user, such as the first user, will charge the battery to a first preset threshold in a charging scenario.

[0093] The first model can be trained based on the first training sample data, which includes first sample information for characterizing the second charging scenario, second sample information for characterizing the charging habits of the second user, and charging results. The charging results are used to characterize whether the second user has charged the battery to the first preset threshold in the second charging scenario.

[0094] The first training sample data may include at least one first sample information, at least one second sample information, and the charging result under the corresponding charging scenario. This charging result has two possibilities: a value of 1 indicates that the second user charged the battery to the first preset threshold in the second charging scenario, and a value of 0 indicates that the second user did not charge the battery to the first preset threshold in the second charging scenario. The second charging scenario may be the same as or different from the first charging scenario; no specific limitation is made here.

[0095] The first training sample data may include training sample data from at least one second user. This second user may or may not include the first user; no specific limitation is made here. If the first training sample data does not include the first user's training sample data, the first model can be trained using training sample data from other users. If the first training sample data includes the first user's training sample data, the first user's training sample data can be combined with the training sample data from other users to train the first model, thus fixing the network parameters of the first model. Accordingly, based on the first user's first target information, the network parameters of the first model can be used to predict the first user's anxiety level regarding battery power.

[0096] Quantization can be performed before the information is input into the first model. For example, the feature of time x1 needs to be discretized and divided into different time periods. The specific processing rules are shown in Table 3 below.

[0097] Table 3. Quantification of Time

[0098]

[0099]

[0100] Since the user's location is scattered latitude and longitude, the features of location x2 also need to be quantified and processed into location information with specific meaning. For example, the user's most frequently visited location can be represented by the value 1; the user's second most frequently visited location can be represented by the value 2, and so on. In an optional implementation, an unsupervised learning algorithm such as k-means can be used to cluster the user's location data, resulting in m clusters, where each cluster represents one of the user's most frequently visited locations. Then, the features of location x2 can be processed into numerical features and input into the first model. For example, if x2 is located in the 3rd cluster, then the value of x2 input into the first model would be 3.

[0101] The remaining battery power of the electronic device x3, the average number of charging times per day x4, the average charging amount per charge x5, and the percentage of the battery that was charged to the first preset threshold at the current time position in historical data x6 are all numerical features that do not require further quantification and can be directly input into the first model.

[0102] Correspondingly, numerical features can be input into the first model for probability prediction to obtain the probability p that the user will charge the battery to the first preset threshold in the charging scenario. The loss function is constructed during the training phase and is expressed by the following formula (2).

[0103] L=-[ylogp1+(1-y)log(1-p1)] (2)

[0104] In equation (2) above, L is the network loss value of the first model, and y is the charging result in the first training sample data.

[0105] Gradient descent can be used to update the network parameters of the first model by minimizing the loss function. The network parameters of the first model can be continuously updated in a loop until L is less than a certain threshold and convergence is achieved. At this time, the first model can be trained and the optimal w1, w2, ..., w6 and b can be obtained.

[0106] After training, the first model can learn the correlation between x4, x5, x6 and charging to a first preset threshold. A higher x4 and a lower x5 indicate that the user is more likely to start charging when there is still a lot of battery left, thus having a greater demand for battery power and higher battery anxiety. A higher x6 indicates a higher probability that the current charge will reach the first preset threshold, indicating a lower demand for battery power and less user anxiety about battery power.

[0107] Then, the first model trained above can be used to input the corresponding numerical features and predict the probability that any user will charge the battery to a first preset threshold in a charging scenario.

[0108] For example, for the first user, the first information is: time 9:30, location: company (clustering shows that the company is the second most frequently visited place by the first user), and the current battery remaining power is 30%. The second information is: average number of charging times per day is 5, average power per charge is 50%, and the proportion of times the battery was charged to the first preset threshold at the current time and location in the past is 80%. After quantifying the time and location, the numerical features input into the first model are [2,2,0.3,5,0.5,0.8]. The first model calculates the first probability based on these data.

[0109] In one optional implementation, for each user charge, the level of power demand can be categorized into three levels—low, medium, and high—based on the probability predicted by the first model. The first probability is compared with a pre-acquired first level classification threshold to determine the level of power demand. For example, if the first level classification threshold is 0.1 and 0.8, a probability value less than or equal to 0.1 is determined to be high; a probability value greater than 0.1 and less than 0.8 is determined to be medium; and a probability value greater than or equal to 0.8 is determined to be low.

[0110] The threshold for classifying the first level can be set or determined based on the distribution of the second probability obtained from the first training sample data; no specific limitation is made here.

[0111] Accordingly, charging speed levels can be determined based on the level of power demand, thus obtaining the first charging speed. For example, if the level representing the level of power demand is high, medium, and low, the corresponding charging speed levels are high, medium, and low, respectively, denoted by V. battery This indicates that the charging current can also be determined based on the level of power demand to obtain the first charging speed.

[0112] In this embodiment, by inputting the first information and the second information into a first model for probability prediction, a first probability is obtained that the first user will charge the battery to a first preset threshold in the first charging scenario. Based on the first probability and a pre-acquired first level classification threshold, the power demand level corresponding to the first charging scenario is determined, and based on the power demand level, a first charging speed is determined. Thus, the user's anxiety level about battery power can be quantified through the model, thereby determining the first charging speed.

[0113] Optionally, before determining the power demand level corresponding to the first charging scenario based on the first probability and a pre-acquired first level classification threshold, the method further includes:

[0114] Once the first model training is complete, based on the first model, obtain the second probability that the second user will charge the battery to the first preset threshold in the second charging scenario;

[0115] The first target probability value is determined as the first level division threshold, and the first target probability value is the probability value that makes the distribution of the second probability satisfy the first preset distribution.

[0116] In this embodiment, the first level classification threshold can be determined based on the distribution of the second probability obtained from the first training sample data.

[0117] Specifically, once the first model training is complete, the second probability corresponding to each second charging scenario can be obtained, and the first target probability value whose distribution of the second probability satisfies the first preset distribution is determined as the first level classification threshold.

[0118] In one optional implementation, the probability values ​​of the second probability distribution at the 25th and 75th percentiles can be determined as the first level classification thresholds, namely p1 (e.g., probability value 0.1) and p2 (e.g., probability value 0.8), where p1 is less than p2. That is, the 25% of users below p1 have high battery anxiety, the 25%-75% of users between p1 and p2 have medium battery anxiety, and the 25% of users above p2 have low battery anxiety. This further improves the accuracy of determining battery demand levels.

[0119] Optionally, step 103 specifically includes:

[0120] The second target information is input into the second model for probability prediction to obtain the third probability that the first user will complain about battery overheating. The second target information includes the second information.

[0121] Based on the third probability and the pre-acquired second-level classification threshold, the degree of heat limitation is determined, which is used to characterize the correspondence between battery heat limitation and charging speed;

[0122] The second charging speed is determined based on the degree of heat limitation.

[0123] The second model is trained based on the second training sample data, which includes third sample information and complaint information used to characterize the charging habits of the third user. The complaint information is used to characterize whether there is a complaint record from the third user regarding battery overheating.

[0124] In this embodiment, the second target information may include second information and may also include the identity information of the first user. The following description takes the example of the second target information including both the second information and the identity information of the first user.

[0125] A second model can be used to predict the probability of users complaining about battery overheating, thus quantifying users' anxiety about battery overheating. For example, if the second model predicts a high probability that a user will complain about battery overheating, it indicates that the user is anxious about battery overheating; otherwise, it indicates no anxiety.

[0126] In one optional implementation, the input to the second model can be the feature representation of the second information and identity information, such as gender x1, age x2, occupation x3, average number of daily charging times x4, average charging amount per charge x5, and the percentage of the battery charged to a first preset threshold at the current time position in historical data x6. The output can be the third probability that the first user complains about battery overheating.

[0127] The second model can be a machine learning model or a deep learning model. The following explanation uses a machine learning model as an example. In an optional implementation, the second model can be a logistic regression model. Its model structure can be the same as the structure of the first model (i.e., the structure of the second model can also be represented by the above formula (1)) or different. No specific limitation is made here.

[0128] Before the information is input into the second model, it can be quantified. For example, the value 1 can be used to represent male gender and the value 0 to represent female gender. As for occupation, a preset quantification table can be used to quantify occupation. For example, the occupation of Didi driver can be represented by the value 4.

[0129] The training method of the second model can be the same as that of the first model. The difference is that when calculating the network loss value, the label of the first model (i.e., y in the above formula (2)) is the charging result, while the label of the second model is the complaint information. Here, y=1 indicates that the third user has complained about the battery overheating, and y=0 indicates that the third user has not complained about the battery overheating.

[0130] The second training sample data may include training sample data from at least one third user. This third user may or may not include the first user; no specific limitation is made here. If the second training sample data does not include the first user's training sample data, the second model can be trained using training sample data from other users. If the second training sample data includes the first user's training sample data, the first user's training sample data can be combined with the training sample data from other users to train the second model, thus fixing the network parameters of the second model. Accordingly, based on the first user's second target information, the network parameters of the second model can be used to predict the first user's anxiety level regarding battery overheating.

[0131] Then, the second model trained above can be used to predict the probability of any user complaining about battery overheating by inputting the corresponding numerical features.

[0132] For example, for the first user, the identity information is: male, age 25, occupation: Didi driver. The second information is: average number of charging times per day: 5 times, average charge per charge: 50%, and the proportion of times the user has charged to the first preset threshold at the current time and location in the past is 80%. After quantifying the gender and occupation, the numerical features input into the second model are [1, 25, 4, 5, 0.5, 0.8]. The second model calculates the third probability based on these data.

[0133] In one optional implementation, for each user charge, the level of heat limitation can be divided into three levels—low, medium, and high—based on the probability predicted by the second model. The third probability is compared with a pre-acquired second-level threshold to determine the degree of heat limitation. For example, if the level thresholds are 0.1 and 0.8, a probability value less than or equal to 0.1 indicates a low level, a probability value greater than 0.1 and less than 0.8 indicates a medium level, and a probability value greater than or equal to 0.8 indicates a high level.

[0134] The threshold for the second level division can be obtained by setting it, or it can be determined based on the distribution of the fourth probability obtained from the second training sample data. No specific limitation is made here.

[0135] Correspondingly, a charging speed level can be determined based on the degree of heat limitation, thus obtaining a second charging speed. For example, when the level characterizing the degree of heat limitation is high, medium, and low, the corresponding charging speed levels are low, medium, and high, respectively, denoted by V. heating Alternatively, the charging current can be determined based on the degree of heat limitation to obtain the second charging speed.

[0136] In this embodiment, by inputting the second target information into the second model for probability prediction, a third probability is obtained that the first user will complain about battery overheating. Based on the third probability and a pre-acquired second-level classification threshold, the degree of overheating restriction is determined, and based on the degree of overheating restriction, a second charging speed is determined. Thus, the model can quantify the user's anxiety about battery overheating, thereby determining the second charging speed.

[0137] Optionally, before determining the degree of heat restriction based on the third probability and a pre-acquired second-level classification threshold, the method further includes:

[0138] Once the second model has been trained, based on the second model, a fourth probability is obtained that the third user will complain about battery overheating.

[0139] The second target probability value is determined as the second level classification threshold, and the second target probability value is the probability value that makes the distribution of the fourth probability satisfy the second preset distribution.

[0140] In this embodiment, once the second model training is complete, a fourth probability of multiple third users complaining about battery overheating can be obtained. The second target probability value, whose distribution satisfies the second preset distribution, is determined as the second level classification threshold.

[0141] In one alternative implementation, the probability values ​​of the fourth probability distribution at the 25th and 75th percentiles can be determined as the second-level classification thresholds, p3 and p4, respectively, where p3 is less than p4. That is, the 25% of users below p3 have low anxiety about battery overheating, the 25%-75% of users between p3 and p4 have moderate anxiety about battery overheating, and the 25% of users above p4 have high anxiety about battery overheating. This further improves the accuracy of determining the degree of overheating limitation.

[0142] Optionally, step S104 specifically includes:

[0143] When the charging strategy is the first strategy, the charging speed that is smaller of the first charging speed and the second charging speed is determined as the target charging speed;

[0144] When the charging strategy is the second strategy, the charging speed with the larger value between the first charging speed and the second charging speed is determined as the target charging speed;

[0145] The first strategy indicates that the battery temperature should be less than or equal to a second preset threshold during charging, while the second strategy indicates that the charging speed should be prioritized during charging.

[0146] In this embodiment, the target charging speed can be determined by combining the first charging speed and the second charging speed according to a certain strategy.

[0147] When the charging strategy is set to the first priority, it indicates that electronic devices tend to prioritize maintaining battery heat dissipation during charging, in V... battery and V heating In case of inconsistency, prioritize the charging speed that ensures the battery does not overheat as the target charging speed.

[0148] The specific formula is: V charging =min(V battery V heating ), where V chargingTarget charging speed. For example, when a user's anxiety about battery level is moderate, a medium-speed charging method is typically used. However, if the user's anxiety about battery overheating is high, a low-speed charging method is chosen based on both factors. Based on this strategy, low, medium, and high charging speeds can be provided to users by combining their anxiety about battery level and overheating.

[0149] When the charging strategy is the second strategy, it indicates that electronic devices are more inclined to prioritize the user experience of fast charging, in V battery and V heating In case of inconsistency, prioritize ensuring charging speed.

[0150] The specific formula is: V charging =max(V battery V heating For example, when a user's anxiety about battery heat is moderate, a medium-speed charging method is typically used. However, if the user's anxiety about battery level is high, a high-speed charging method is chosen based on a comprehensive consideration. Based on this strategy, low, medium, and high charging speeds can be provided to users by combining their anxiety about battery level and battery heat.

[0151] In this way, users' anxiety about battery level and battery heat can be balanced, providing users with a suitable charging speed.

[0152] It should be noted that the charging method provided in this application embodiment can be executed by a charging device or a control module within the charging device for executing the charging method. This application embodiment uses the charging device executing the charging method as an example to illustrate the charging device provided in this application embodiment.

[0153] See Figure 2 , Figure 2 This is a structural diagram of the charging device provided in the embodiments of this application, as shown below. Figure 2 As shown, the charging device 200 includes:

[0154] The first acquisition module 201 is used to acquire first target information, the first target information including: first information for characterizing the first charging scenario and second information for characterizing the charging habits of the first user;

[0155] The first determining module 202 is used to determine the first charging speed corresponding to the first charging scenario based on the first information and the second information;

[0156] The second determining module 203 is used to determine the second charging speed based on the second information;

[0157] The third determining module 204 is used to determine the target charging speed based on the first charging speed and the second charging speed;

[0158] The charging module 205 is used to charge based on the target charging speed.

[0159] Optionally, the first information includes at least one of charging time, charging location, and remaining battery power;

[0160] And / or, the second information includes at least one of the following: the average number of historical charging times of the first user within a preset time period, the average amount of battery charge per historical charging by the first user, and a target ratio. The target ratio is the ratio of the first number of historical charging times to the second number of historical charging times. The first number of historical charging times is the number of times the battery capacity was charged to a first preset threshold during historical charging in the first charging scenario. The second number of historical charging times is the total number of historical charging times performed in the first charging scenario.

[0161] Optionally, the first determining module 202 is specifically used for:

[0162] The first information and the second information are input into the first model to perform probability prediction, and the first probability that the first user will charge the battery to a first preset threshold in the first charging scenario is obtained.

[0163] Based on the first probability and the pre-acquired first level classification threshold, the power demand level corresponding to the first charging scenario is determined, and the power demand level is used to characterize the correspondence between battery power demand and charging speed.

[0164] The first charging speed is determined based on the power demand level;

[0165] The first model is trained based on the first training sample data, which includes first sample information for characterizing the second charging scenario, second sample information for characterizing the charging habits of the second user, and charging results. The charging results are used to characterize whether the second user has charged the battery to the first preset threshold in the second charging scenario.

[0166] Optionally, the device further includes:

[0167] The second acquisition module is used to acquire, based on the first model, the second probability that the second user will charge the battery to the first preset threshold in the second charging scenario, after the first model training is completed.

[0168] The fourth determining module is used to determine the first target probability value as the first level division threshold, wherein the first target probability value is the probability value that makes the distribution of the second probability satisfy the first preset distribution.

[0169] Optionally, the second determining module 203 is specifically used for:

[0170] The second target information is input into the second model for probability prediction to obtain the third probability that the first user will complain about battery overheating. The second target information includes the second information.

[0171] Based on the third probability and the pre-acquired second-level classification threshold, the degree of heat limitation is determined, which is used to characterize the correspondence between battery heat limitation and charging speed;

[0172] The second charging speed is determined based on the degree of heat limitation.

[0173] The second model is trained based on the second training sample data, which includes third sample information and complaint information used to characterize the charging habits of the third user. The complaint information is used to characterize whether there is a complaint record from the third user regarding battery overheating.

[0174] Optionally, the third determining module 204 is specifically used for:

[0175] When the charging strategy is the first strategy, the smaller of the first charging speed and the second charging speed is determined as the target charging speed, where the first charging speed is determined based on the power demand and the second charging speed is determined based on the heat limitation.

[0176] When the charging strategy is the second strategy, the charging speed with the larger value between the first charging speed and the second charging speed is determined as the target charging speed;

[0177] The first strategy indicates that the battery temperature should be less than or equal to a second preset threshold during charging, while the second strategy indicates that the charging speed should be prioritized during charging.

[0178] In this embodiment, by acquiring first target information, which includes first information characterizing a first charging scenario and second information characterizing a first user's charging habits; based on the first and second information, determining a first charging speed corresponding to the first charging scenario, and based on the second information, determining a second charging speed; based on the first and second charging speeds, determining a target charging speed; and charging based on the target charging speed. Thus, by combining relevant information about the first charging scenario and relevant information about the user, a suitable charging speed can be provided to the user in the first charging scenario, thereby balancing the charging speed of the electronic device and battery heat control, providing fast charging to the user while taking into account battery heat dissipation.

[0179] The charging device in this application embodiment can be a device, or a component, integrated circuit, or chip in an electronic device. The device can be a mobile electronic device or a non-mobile electronic device. For example, mobile electronic devices can be mobile phones, tablets, laptops, PDAs, in-vehicle electronic devices, wearable devices, ultra-mobile personal computers (UMPCs), netbooks, or personal digital assistants (PDAs), etc., while non-mobile electronic devices can be servers, network-attached storage (NAS), personal computers (PCs), televisions (TVs), ATMs, or self-service machines, etc. This application embodiment does not impose specific limitations.

[0180] The charging device in this application embodiment can be a device with an operating system. This operating system can be Android, iOS, or other possible operating systems; this application embodiment does not specifically limit the specific operating system used.

[0181] The charging device provided in this application embodiment can achieve... Figure 1 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0182] Optionally, such as Figure 3 As shown, this application embodiment also provides an electronic device 300, including a processor 301, a memory 302, and a program or instructions stored in the memory 302 and executable on the processor 301. When the program or instructions are executed by the processor 301, they implement the various processes of the above-described charging method embodiment and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0183] It should be noted that the electronic devices in the embodiments of this application include the mobile electronic devices and non-mobile electronic devices described above.

[0184] Figure 4 A schematic diagram of the hardware structure of an electronic device to implement an embodiment of this application.

[0185] The electronic device 400 includes, but is not limited to, components such as: radio frequency unit 401, network module 402, audio output unit 403, input unit 404, sensor 405, display unit 406, user input unit 407, interface unit 408, memory 409, and processor 410.

[0186] Those skilled in the art will understand that the electronic device 400 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 410 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 4 The electronic device structure shown does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0187] Processor 410, used for:

[0188] Obtain first target information, which includes: first information for characterizing a first charging scenario and second information for characterizing the charging habits of a first user;

[0189] Based on the first information and the second information, a first charging speed corresponding to the first charging scenario is determined, and a second charging speed is determined based on the second information;

[0190] Based on the first charging speed and the second charging speed, determine the target charging speed;

[0191] Charge according to the target charging speed.

[0192] In this embodiment, by acquiring first target information, which includes first information characterizing a first charging scenario and second information characterizing a first user's charging habits; based on the first and second information, determining a first charging speed corresponding to the first charging scenario, and based on the second information, determining a second charging speed; based on the first and second charging speeds, determining a target charging speed; and charging based on the target charging speed. Thus, by combining relevant information about the first charging scenario and relevant information about the user, a suitable charging speed can be provided to the user in the first charging scenario, thereby balancing the charging speed of the electronic device and battery heat control, providing fast charging to the user while taking into account battery heat dissipation.

[0193] Optionally, the first information includes at least one of charging time, charging location, and remaining battery power;

[0194] And / or, the second information includes at least one of the following: the average number of historical charging times of the first user within a preset time period, the average amount of battery charge per historical charging by the first user, and a target ratio. The target ratio is the ratio of the first number of historical charging times to the second number of historical charging times. The first number of historical charging times is the number of times the battery capacity was charged to a first preset threshold during historical charging in the first charging scenario. The second number of historical charging times is the total number of historical charging times performed in the first charging scenario.

[0195] Optionally, the processor 410 is also used for:

[0196] The first information and the second information are input into the first model to perform probability prediction, and the first probability that the first user will charge the battery to a first preset threshold in the first charging scenario is obtained.

[0197] Based on the first probability and the pre-acquired first level classification threshold, the power demand level corresponding to the first charging scenario is determined, and the power demand level is used to characterize the correspondence between battery power demand and charging speed.

[0198] The first charging speed is determined based on the power demand level;

[0199] The first model is trained based on the first training sample data, which includes first sample information for characterizing the second charging scenario, second sample information for characterizing the charging habits of the second user, and charging results. The charging results are used to characterize whether the second user has charged the battery to the first preset threshold in the second charging scenario.

[0200] Optionally, the processor 410 is also used for:

[0201] Once the first model training is complete, based on the first model, obtain the second probability that the second user will charge the battery to the first preset threshold in the second charging scenario;

[0202] The first target probability value is determined as the first level division threshold, and the first target probability value is the probability value that makes the distribution of the second probability satisfy the first preset distribution.

[0203] Optionally, the processor 410 is also used for:

[0204] The second target information is input into the second model for probability prediction to obtain the third probability that the first user will complain about battery overheating. The second target information includes the second information.

[0205] Based on the third probability and the pre-acquired second-level classification threshold, the degree of heat limitation is determined, which is used to characterize the correspondence between battery heat limitation and charging speed;

[0206] The second charging speed is determined based on the degree of heat limitation.

[0207] The second model is trained based on the second training sample data, which includes third sample information and complaint information used to characterize the charging habits of the third user. The complaint information is used to characterize whether there is a complaint record from the third user regarding battery overheating.

[0208] Optionally, the processor 410 is also used for:

[0209] Once the second model has been trained, based on the second model, a fourth probability is obtained that the third user will complain about battery overheating.

[0210] The second target probability value is determined as the second level classification threshold, and the second target probability value is the probability value that makes the distribution of the fourth probability satisfy the second preset distribution.

[0211] Optionally, the processor 410 is also used for:

[0212] When the charging strategy is the first strategy, the smaller of the first charging speed and the second charging speed is determined as the target charging speed, where the first charging speed is determined based on the power demand and the second charging speed is determined based on the heat limitation.

[0213] When the charging strategy is the second strategy, the charging speed with the larger value between the first charging speed and the second charging speed is determined as the target charging speed;

[0214] The first strategy indicates that the battery temperature should be less than or equal to a second preset threshold during charging, while the second strategy indicates that the charging speed should be prioritized during charging.

[0215] It should be understood that, in this embodiment, the input unit 404 may include a graphics processing unit (GPU) 4041 and a microphone 4042. The GPU 4041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 406 may include a display panel 4061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 407 includes a touch panel 4071 and other input devices 4072. The touch panel 4071 is also called a touch screen. The touch panel 4071 may include a touch detection device and a touch controller. Other input devices 4072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, joysticks, etc., which will not be described in detail here. The memory 409 can be used to store software programs and various data, including but not limited to applications and operating systems. The processor 410 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understandable that the aforementioned modem processor may not be integrated into the processor 410.

[0216] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described charging method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0217] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0218] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface is coupled to the processor. The processor is used to run programs or instructions to implement the various processes of the above charging method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0219] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0220] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0221] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a computer software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause an electronic device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0222] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A charging method, characterized in that, The method includes: Obtain first target information, which includes: first information for characterizing a first charging scenario and second information for characterizing the charging habits of a first user; Based on the first information and the second information, a first charging speed corresponding to the first charging scenario is determined, and a second charging speed is determined based on the second information; the first charging speed indicates the first user's anxiety level regarding battery power, and the second charging speed indicates the first user's anxiety level regarding battery overheating; When the charging strategy is the first strategy, the charging speed with the smaller value between the first charging speed and the second charging speed is determined as the target charging speed; when the charging strategy is the second strategy, the charging speed with the larger value between the first charging speed and the second charging speed is determined as the target charging speed; wherein, the first strategy indicates that the battery temperature should be less than or equal to a second preset threshold during charging, and the second strategy indicates that the charging speed should be guaranteed first during charging. Charge according to the target charging speed.

2. The method according to claim 1, characterized in that, The first information includes at least one of the following: charging time, charging location, and remaining battery power; And / or, the second information includes at least one of the following: the average number of historical charging times of the first user within a preset time period, the average amount of battery charge per historical charging by the first user, and a target ratio. The target ratio is the ratio of the first number of historical charging times to the second number of historical charging times. The first number of historical charging times is the number of times the battery capacity was charged to a first preset threshold during historical charging in the first charging scenario. The second number of historical charging times is the total number of historical charging times performed in the first charging scenario.

3. The method according to claim 1, characterized in that, Determining the first charging speed corresponding to the first charging scenario based on the first information and the second information includes: The first information and the second information are input into the first model to perform probability prediction, and the first probability that the first user will charge the battery to a first preset threshold in the first charging scenario is obtained. Based on the first probability and the pre-acquired first level classification threshold, the power demand level corresponding to the first charging scenario is determined, and the power demand level is used to characterize the correspondence between battery power demand and charging speed. The first charging speed is determined based on the stated power demand. The first model is trained based on the first training sample data, which includes first sample information for characterizing the second charging scenario, second sample information for characterizing the charging habits of the second user, and charging results. The charging results are used to characterize whether the second user has charged the battery to the first preset threshold in the second charging scenario.

4. The method according to claim 3, characterized in that, Before determining the power demand level corresponding to the first charging scenario based on the first probability and a pre-acquired first level classification threshold, the method further includes: Once the first model training is complete, based on the first model, obtain the second probability that the second user will charge the battery to the first preset threshold in the second charging scenario; The first target probability value is determined as the first level division threshold, and the first target probability value is the probability value that makes the distribution of the second probability satisfy the first preset distribution.

5. The method according to claim 1, characterized in that, Determining the second charging speed based on the second information includes: The second target information is input into the second model for probability prediction to obtain the third probability that the first user will complain about battery overheating. The second target information includes the second information. Based on the third probability and the pre-acquired second-level classification threshold, the degree of heat limitation is determined, which is used to characterize the correspondence between battery heat limitation and charging speed; The second charging speed is determined based on the degree of heat limitation. The second model is trained based on the second training sample data, which includes third sample information and complaint information used to characterize the charging habits of the third user. The complaint information is used to characterize whether there is a complaint record from the third user regarding battery overheating.

6. A charging device, characterized in that, The device includes: The first acquisition module is used to acquire first target information, the first target information including: first information for characterizing the first charging scenario and second information for characterizing the charging habits of the first user; The first determining module is used to determine a first charging speed corresponding to the first charging scenario based on the first information and the second information; the first charging speed indicates the first user's anxiety level about battery power. The second determining module is used to determine a second charging speed based on the second information; the second charging speed indicates the first user's level of anxiety about battery overheating; The third determining module is used to determine the target charging speed based on the first charging speed and the second charging speed; A charging module is used to charge based on the target charging speed; The third determining module is specifically used for: When the charging strategy is the first strategy, the smaller of the first charging speed and the second charging speed is determined as the target charging speed. When the charging strategy is the second strategy, the charging speed with the larger value between the first charging speed and the second charging speed is determined as the target charging speed; The first strategy indicates that the battery temperature should be less than or equal to a second preset threshold during charging, while the second strategy indicates that the charging speed should be prioritized during charging.

7. The apparatus according to claim 6, characterized in that, The first information includes at least one of the following: charging time, charging location, and remaining battery power; And / or, the second information includes at least one of the following: the average number of historical charging times of the first user within a preset time period, the average amount of battery charge per historical charging by the first user, and a target ratio. The target ratio is the ratio of the first number of historical charging times to the second number of historical charging times. The first number of historical charging times is the number of times the battery capacity was charged to a first preset threshold during historical charging in the first charging scenario. The second number of historical charging times is the total number of historical charging times performed in the first charging scenario.

8. The apparatus according to claim 6, characterized in that, The first determining module is specifically used for: The first information and the second information are input into the first model to perform probability prediction, and the first probability that the first user will charge the battery to a first preset threshold in the first charging scenario is obtained. Based on the first probability and the pre-acquired first level classification threshold, the power demand level corresponding to the first charging scenario is determined, and the power demand level is used to characterize the correspondence between battery power demand and charging speed. The first charging speed is determined based on the power demand level; The first model is trained based on the first training sample data, which includes first sample information for characterizing the second charging scenario, second sample information for characterizing the charging habits of the second user, and charging results. The charging results are used to characterize whether the second user has charged the battery to the first preset threshold in the second charging scenario.

9. The apparatus according to claim 6, characterized in that, The second determining module is specifically used for: The second target information is input into the second model for probability prediction to obtain the third probability that the first user will complain about battery overheating. The second target information includes the second information. Based on the third probability and the pre-acquired second-level classification threshold, the degree of heat limitation is determined, which is used to characterize the correspondence between battery heat limitation and charging speed; The second charging speed is determined based on the degree of heat limitation. The second model is trained based on the second training sample data, which includes third sample information and complaint information used to characterize the charging habits of the third user. The complaint information is used to characterize whether there is a complaint record from the third user regarding battery overheating.

10. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the charging method as described in any one of claims 1-5.

Images