Electric quantity management method and system of intelligent door lock, terminal and storage medium

Abstract

The invention discloses an electric quantity management method and system for an intelligent door lock, a terminal and a storage medium, and the method comprises the steps: obtaining the battery use data of a plurality of different types of intelligent door lock batteries, and carrying out the preprocessing of the battery use data, and obtaining a training data set, performing model training according to the training data set to obtain a battery service time prediction model; acquiring current battery information of the intelligent door lock, inputting the battery information into the battery service time prediction model, and outputting a battery service time prediction result: if the electric quantity value of the battery service time prediction result is lower than the preset electric quantity, switching the working mode of the intelligent door lock, and notifying a user to process. By deeply analyzing the use data of the battery, the residual service life of the battery can be accurately predicted, so that a user can be timely notified to replace the battery or charge the battery, and the working mode of the intelligent door lock can be automatically adjusted according to the attenuation state of the battery, so that the intelligent door lock can still keep normal working performance after the battery is attenuated.

Description

Technical Field

[0001] The present invention relates to the field of power processing technology, and in particular to a power management method, system, terminal and computer-readable storage medium for a smart door lock. Background Art

[0002] With the development of technology, smart door locks have been widely used in homes, offices and other places due to their convenience and safety. Smart door locks are usually powered by batteries, and the battery life and stability directly affect the user experience and reliability of smart door locks. However, the battery will gradually decay during use, resulting in a decrease in the battery life of smart door locks, or even failure to work properly. Therefore, how to effectively predict and manage the battery power and improve the efficiency and reliability of smart door locks is an urgent problem to be solved in the current field of smart door lock technology.

[0003] Existing smart door locks generally monitor and display the remaining battery power through a built-in battery management system; users can replace the battery in time according to the prompts of the battery management system to ensure the normal use of the smart door lock. In addition, some smart door locks use technologies such as wireless charging or solar charging to extend the service life of the battery. However, the existing battery management system can only provide information about the remaining battery power, and users are required to estimate the remaining battery life based on this information. For users who are not familiar with battery characteristics, it may lead to inaccurate estimates, thus affecting the normal use of smart door locks. Secondly, although the existing wireless charging or solar charging technology can extend the service life of the battery, its charging efficiency and stability need to be improved, and it is greatly affected by environmental factors; finally, after the battery decays, the existing smart door locks often cannot automatically adjust their working mode to adapt to the decay state of the battery, which leads to a decrease in the working performance of the smart door lock, or even failure to work normally.

[0004] Therefore, the prior art still needs to be improved and developed. Summary of the invention

[0005] The main purpose of the present invention is to provide a power management method, system, terminal and storage medium for a smart door lock, aiming to solve the problem that the prior art can only provide the remaining power information of the battery, but cannot accurately estimate the remaining battery life, and after the battery decays, it is impossible to automatically adjust the working mode of the smart door lock to adapt to the battery decay state, resulting in a decrease in the working performance of the smart door lock or even failure to work normally.

[0006] To achieve the above object, the present invention provides a power management method for a smart door lock, the power management method for a smart door lock comprising the following steps:

[0007] Obtain battery usage data of multiple different types of smart door lock batteries, pre-process the battery usage data to obtain a training data set, and perform model training based on the training data set to obtain a battery usage time prediction model;

[0008] Obtaining the current battery information of the smart door lock, inputting the battery information into the battery usage time prediction model, and outputting the corresponding battery usage time prediction result;

[0009] If the power value of the battery usage time prediction result is lower than the preset power value, the working mode of the smart door lock is switched and the user is notified to handle it.

[0010] Optionally, the power management method for the smart door lock, wherein the obtaining of battery usage data of multiple different types of smart door lock batteries, preprocessing the battery usage data to obtain a training data set, specifically includes:

[0011] Obtain battery usage data of multiple different types of smart door lock batteries, wherein the battery usage data includes initial power information, battery usage time, battery temperature, and discharge current;

[0012] Performing data cleaning on all the battery usage data to obtain a battery data set, and performing normalization processing on the battery data set to obtain a target battery data set;

[0013] The target battery data set is converted, and the converted target battery usage data set is divided to obtain a training set and a verification set, and a training data set is obtained according to the training set and the verification set.

[0014] Optionally, the power management method for the smart door lock, wherein the data cleaning of all the battery usage data to obtain a battery data set, and the normalization of the battery data set to obtain a target battery data set, specifically includes:

[0015] Performing data integration on all the battery usage data, and performing data removal and value missing processing on the integrated battery usage data to obtain a battery data set, wherein the data integration includes data format conversion, data unit unification and data consistency check;

[0016] A data scaling ratio is set, and data scaling is performed on the battery data set according to the data scaling ratio to obtain a target battery data set.

[0017] Optionally, the power management method for the smart door lock, wherein the data cleaning is performed on all the battery usage data to obtain a battery data set, and the battery data set is normalized to obtain a target battery data set, and then further comprises:

[0018] Performing data verification on the target battery data set to obtain a verification result, wherein the data verification includes data distribution comparison, data integrity check and data consistency check;

[0019] If the verification result is that the data distribution comparison, the data integrity check, and the data consistency check are all verified to pass, then it is determined that the target battery data set passes the verification;

[0020] If the verification result is that any one of the data distribution comparison, the data integrity check and the data consistency check fails, it is determined that the target battery data set fails the verification, and corresponding abnormal data is obtained according to the verification result, and the abnormal data is replaced.

[0021] Optionally, the power management method for the smart door lock, wherein the model training is performed according to the training data set to obtain a battery usage time prediction model, specifically comprising:

[0022] Creating a battery life training model, and inputting a set of battery data samples in the training set into the battery life training model;

[0023] Extracting features from the battery data sample to obtain target battery features, and predicting battery usage time for the battery data according to the target battery features to obtain predicted battery usage time;

[0024] Performing loss calculation on the error between the predicted battery usage time and the corresponding actual battery usage time in the validation set to obtain a target loss value, and modifying the parameters of the battery usage time training model according to the target loss value;

[0025] The next set of battery data samples is input into the battery usage time training model until the training status of the battery usage time training model meets the preset conditions, thereby obtaining a trained battery usage time prediction model.

[0026] Optionally, the power management method for the smart door lock, wherein the error between the predicted battery life and the corresponding actual battery life in the validation set is calculated to obtain a target loss value, and the parameters of the battery life training model are corrected according to the target loss value, specifically comprising:

[0027] Determine a loss function according to the problem type of predicting battery usage time to obtain a target loss function, and calculate the loss of the error between the predicted battery usage time and the corresponding actual battery usage time in the validation set according to the target loss function to obtain a target loss value;

[0028] The gradient information of the target loss function is obtained according to the target loss value, and the parameters of the battery usage time training model are corrected according to the gradient information.

[0029] Optionally, in the power management method of the smart door lock, the battery life prediction result includes the remaining battery life, power value and working mode;

[0030] If the power value of the battery usage time prediction result is lower than the preset power value, the working mode of the smart door lock is switched and the user is notified to process, which specifically includes:

[0031] Compare the power value with a preset power value, and if the power value is less than the preset power value, switch the working mode to a low power consumption mode;

[0032] A low battery reminder is generated according to the battery usage time prediction result, and the low battery reminder is pushed to the user to notify the user to process.

[0033] Optionally, in the power management method of the smart door lock, the power management system of the smart door lock includes:

[0034] A model training module, used to obtain battery usage data of multiple different types of smart door lock batteries, pre-process the battery usage data to obtain a training data set, and perform model training based on the training data set to obtain a battery usage time prediction model;

[0035] A time prediction module, used to obtain the current battery information of the smart door lock, input the battery information into the battery usage time prediction model, and output the corresponding battery usage time prediction result;

[0036] The mode switching module is used to switch the working mode of the smart door lock and notify the user to process if the power value of the battery usage time prediction result is lower than the preset power value.

[0037] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal, wherein the terminal includes: a memory, a processor, and a power management program for a smart door lock stored in the memory and runnable on the processor, and when the power management program for the smart door lock is executed by the processor, the steps of the power management method for the smart door lock as described above are implemented.

[0038] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a power management program for a smart door lock, and when the power management program for a smart door lock is executed by a processor, the steps of the power management method for a smart door lock as described above are implemented.

[0039] In the present invention, battery usage data of multiple different types of smart door lock batteries are obtained, the battery usage data are preprocessed to obtain a training data set, and model training is performed based on the training data set to obtain a battery usage time prediction model; the current battery information of the smart door lock is obtained, the battery information is input into the battery usage time prediction model, and the corresponding battery usage time prediction result is output; if the power value of the battery usage time prediction result is lower than the preset power, the working mode of the smart door lock is switched, and the user is notified to process. The present invention can accurately predict the remaining service life of the battery by performing an in-depth analysis of the battery usage data, so that the user can prepare in advance to avoid the situation where the smart lock cannot work properly due to battery attenuation. It can also automatically adjust the working mode of the smart lock according to the battery attenuation state, so that it can still maintain normal working performance after battery attenuation, thereby improving the use efficiency and reliability of the smart lock and enhancing the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a flow chart of a preferred embodiment of the power management method of the smart door lock of the present invention;

[0041] Figure 2 It is an overall flow chart of a preferred embodiment of the power management method of the smart door lock of the present invention;

[0042] Figure 3 It is a structural diagram of a preferred embodiment of the power management system of the intelligent door lock of the present invention;

[0043] Figure 4 Schematic diagram of the operating environment of a preferred embodiment of the terminal of the present invention. DETAILED DESCRIPTION

[0044] In order to make the purpose, technical solution and advantages of the present invention clearer and more specific, the present invention is further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0045] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0046] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0047] The power management method of the smart door lock described in the preferred embodiment of the present invention is as follows: Figure 1 As shown, the power management method of the smart door lock includes the following steps:

[0048] Step S10: Obtain battery usage data of multiple different types of smart door lock batteries, pre-process the battery usage data to obtain a training data set, and perform model training based on the training data set to obtain a battery usage time prediction model.

[0049] The step S10 comprises:

[0050] Step S11, obtaining battery usage data of multiple different types of smart door lock batteries, wherein the battery usage data includes initial power information, battery usage time, battery temperature and discharge current;

[0051] Step S12, performing data cleaning on all the battery usage data to obtain a battery data set, and performing normalization processing on the battery data set to obtain a target battery data set;

[0052] Step S13, performing data conversion on the target battery data set, performing data division on the converted target battery usage data set to obtain a training set and a verification set, and obtaining a training data set based on the training set and the verification set;

[0053] Step S14, creating a battery life training model, and inputting a group of battery data samples in the training set into the battery life training model;

[0054] Step S15, extracting features from the battery data sample to obtain target battery features, and predicting battery usage time for the battery data according to the target battery features to obtain predicted battery usage time;

[0055] Step S16, performing loss calculation on the error between the predicted battery usage time and the corresponding actual battery usage time in the validation set to obtain a target loss value, and modifying the parameters of the battery usage time training model according to the target loss value;

[0056] Step S17: input the next set of battery data samples into the battery usage time training model until the training status of the battery usage time training model meets the preset conditions, thereby obtaining a trained battery usage time prediction model.

[0057] Specifically, in order to effectively predict and manage the battery power and improve the efficiency and reliability of smart door locks, in an embodiment of the present invention, this is achieved by constructing a battery usage time prediction model. Before training the battery usage time prediction model, a corresponding training data set needs to be prepared. The corresponding process is specifically as follows: first, battery usage data of different types of smart door lock batteries are collected and analyzed, that is, a large amount of battery usage data of smart door lock batteries of different brands and models needs to be collected, wherein the battery usage data includes the initial power information of the battery, the battery usage time, the battery temperature and the discharge current. The battery usage data can be obtained through the battery management system of the smart door lock, and can also be obtained through a special battery testing device. equipment for measurement; secondly, all battery usage data need to be cleaned and preprocessed. The specific data cleaning process is that if the data comes from multiple sources (for example, different smart door lock brands or models), these data need to be integrated into a unified data set, that is, data integration is performed on all the battery usage data, including data format conversion, data unit unification, and data consistency check; then, the integrated battery usage data is preprocessed, specifically, duplicate records in the integrated battery usage data are checked and deleted to ensure that each data is unique; for missing data, fill in according to the specific situation (for example, fill with the mean, median, and mode, or interpolate according to the previous and next data), if the missing value If there are too many records and they have a great impact on the model, consider deleting these records; you can also identify and process data that is obviously illogical or beyond a reasonable range, for example, the battery life cannot be negative, or the discharge current exceeds the maximum value of the battery specification, etc.; normalize the battery data set, that is, set a data scaling ratio, and scale the battery data set according to the data scaling ratio so that it falls into a small specific interval, usually between 0 and 1, so as to obtain the target battery data set. Normalization helps to process data of different dimensions so that they have the same weight in the model; then, perform data conversion on the target battery data set, specifically, create new features or convert existing features according to business needs and data characteristics, for example For example, the rate of change of the battery's discharge current over time can be used as a new feature, or the battery temperature data can be converted into a categorical variable (e.g., low temperature, medium temperature, high temperature). For continuous variables, they can be divided into several intervals (i.e., bins) so that they can be treated as categorical variables in the model, which helps to deal with nonlinear relationships and reduce the complexity of the model. For time series data (e.g., changes in battery usage time over time), smoothing techniques (e.g., moving average, exponential smoothing, etc.) can be used to reduce noise and fluctuations, making the data smoother and easier to analyze. Finally, the converted target battery usage data set is partitioned to obtain a training set and a validation set, and a training data set is obtained based on the training set and the validation set.

[0058] Furthermore, after completing the preprocessing of the target battery data set, it is necessary to verify the target battery data set to ensure that the preprocessing process does not introduce new errors or anomalies, which can be done by comparing the data distribution before and after preprocessing, checking the integrity of the data, and checking the consistency of the data; if the verification result is that the data distribution comparison, the data integrity check, and the data consistency check are all verified and passed, then it is determined that the target battery data set has passed the verification; if the verification result is that any one of the data distribution comparison, the data integrity check, and the data consistency check fails to pass the verification, then it is determined that the target battery data set has failed the verification, and the corresponding abnormal data is obtained according to the verification result, and the abnormal data is replaced until the target battery data set passes the verification.

[0059] After obtaining the training data set, the model can be trained using the training data set to obtain a battery life prediction model. Specifically, a battery life training model is created, and a group of battery data samples in the training set are input into the battery life training model; feature extraction is performed on the battery data samples to obtain target battery features, and battery life prediction is performed on the battery data based on the target battery features to obtain predicted battery life; thereafter, a loss function is used to calculate the error between the predicted battery life output by the model and the actual battery life, and the choice of loss function depends on the type of problem (for example, mean square error loss is commonly used for regression problems). Specifically, a loss function is determined according to the type of problem for predicting battery life to obtain a target loss function, and the predicted battery life is compared with the corresponding battery life in the validation set according to the target loss function. The error between the actual battery usage time is calculated to obtain a target loss value; the gradient information of the target loss function is obtained according to the target loss value, and the parameters of the battery usage time training model are corrected according to the gradient information, so that the battery usage time training model gradually reduces the prediction error during the training process; the next set of battery data samples are input into the battery usage time training model, and the above process is repeated, which will not be repeated here; until the training status of the battery usage time training model meets the preset conditions, the preset conditions include that the target loss value meets the preset requirements or the number of training times reaches the preset number, the preset requirements can be determined according to the accuracy of the battery usage time prediction model, which will not be explained in detail here, the preset number can be the maximum number of training times for the battery usage time training model, for example, 2000 times, etc., and finally a trained battery usage time prediction model is obtained.

[0060] Step S20, obtaining the current battery information of the smart door lock, inputting the battery information into the battery usage time prediction model, and outputting the corresponding battery usage time prediction result.

[0061] Specifically, in an embodiment of the present invention, after obtaining the battery life prediction model, it is necessary to predict the battery life of the current door lock battery of the user's smart door lock. Specifically, obtain the current battery information of the smart door lock, input the battery information into the battery life prediction model, and output the corresponding battery life prediction result, wherein the battery life prediction result includes the remaining battery life, power value and working mode.

[0062] Step S30: If the power value of the battery usage time prediction result is lower than the preset power value, the working mode of the smart door lock is switched and the user is notified to process.

[0063] The step S30 comprises:

[0064] Step S31, comparing the power value with a preset power value, if the power value is less than the preset power value, switching the working mode to a low power consumption mode;

[0065] Step S32: Generate a low-battery reminder according to the battery usage time prediction result, and push the low-battery reminder to the user to notify the user to process.

[0066] Specifically, the power value is compared with a preset power value (for example, 20%). If the power value is less than the preset power value, the working mode is automatically switched to a low power mode to adapt to the attenuation state of the door lock battery. For example, after the door lock battery decays, the smart door lock can automatically reduce power consumption and extend the working time. It can also automatically switch to a backup power supply when the voltage of the door lock battery is lower than a certain threshold to ensure the normal operation of the smart door lock; when the current working mode of the smart door lock is automatically switched to a low power mode, a low power reminder is generated according to the battery usage time prediction result, and the low power reminder is pushed to the user to notify the user to process, and the user can charge the door lock battery or replace the battery.

[0067] Furthermore, the present invention also adopts efficient and stable wireless charging or solar charging technology, such as Qi standard, solar photovoltaic panels, etc., to improve charging efficiency and stability; at the same time, the charging circuit design is optimized to make the charging process more stable, extend the battery life, and use high-efficiency DC-DC converters, high-precision current sampling resistors, stable voltage regulators and other electronic components to reduce the impact of environmental factors, so that the smart door lock can be used more sustainably.

[0068] Furthermore, the overall flow chart of the preferred embodiment of the power management method of the smart door lock in the present invention is as follows: Figure 2 As shown, specifically:

[0069] Step S1, start;

[0070] Step S2, obtaining battery usage data of multiple different types of smart door lock batteries, wherein the battery usage data includes initial power information, battery usage time, battery temperature and discharge current;

[0071] Step S3, performing data cleaning on all the battery usage data to obtain a battery data set;

[0072] Step S4, normalizing the battery data set to obtain a target battery data set; performing data conversion on the target battery data set, dividing the converted target battery usage data set to obtain a training set and a validation set, and obtaining a training data set based on the training set and the validation set;

[0073] Step S5: performing model training according to the training data set to obtain a battery life prediction model;

[0074] Step S6, obtaining the current battery information of the smart door lock, inputting the battery information into the battery usage time prediction model, and outputting the corresponding battery usage time prediction result;

[0075] Step S7, comparing the power value with the preset power value, and determining whether the power value is less than the preset power value, if the power value is greater than or equal to the preset power value, proceeding to step S10, if the power value is less than the preset power value, proceeding to step S8;

[0076] Step S8: If the power value is less than the preset power, the working mode is switched to a low power consumption mode;

[0077] Step S9: generating a low-battery reminder according to the battery usage time prediction result, and pushing the low-battery reminder to the user to notify the user to process;

[0078] Step S10, end.

[0079] Furthermore, if Figure 3 As shown, based on the above-mentioned power management method of the smart door lock, the present invention also provides a power management system of a smart door lock, wherein the power management system of the smart door lock includes:

[0080] The model training module 51 is used to obtain battery usage data of multiple different types of smart door lock batteries, pre-process the battery usage data to obtain a training data set, and perform model training based on the training data set to obtain a battery usage time prediction model;

[0081] The time prediction module 52 is used to obtain the current battery information of the smart door lock, input the battery information into the battery usage time prediction model, and output the corresponding battery usage time prediction result;

[0082] The mode switching module 53 is used to switch the working mode of the smart door lock and notify the user to process if the power value of the battery usage time prediction result is lower than the preset power value.

[0083] Furthermore, if Figure 4 As shown, based on the power management method of the above-mentioned smart door lock, the present invention also provides a terminal accordingly, and the terminal includes a processor 10, a memory 20 and a display 30. Figure 4 Only some components of the terminal are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0084] In some embodiments, the memory 20 may be an internal storage unit of the terminal, such as a hard disk or memory of the terminal. In other embodiments, the memory 20 may also be an external storage device of the terminal, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the terminal. Further, the memory 20 may also include both an internal storage unit of the terminal and an external storage device. The memory 20 is used to store application software and various types of data installed on the terminal, such as the program code of the installation terminal. The memory 20 may also be used to temporarily store data that has been output or is to be output. In one embodiment, the memory 20 stores a power management program 40 of a smart door lock, and the power management program 40 of the smart door lock can be executed by the processor 10, thereby realizing the power management method of the smart door lock in the present application.

[0085] In some embodiments, the processor 10 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run the program code or process data stored in the memory 20, such as executing the power management method of the smart door lock.

[0086] In some embodiments, the display 30 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 30 is used to display information on the terminal and to display a visual user interface. The components of the terminal communicate with each other via a system bus.

[0087] In one embodiment, when the processor 10 executes the power management program 40 of the smart door lock in the memory 20, the following steps are implemented:

[0088] Obtain battery usage data of multiple different types of smart door lock batteries, pre-process the battery usage data to obtain a training data set, and perform model training based on the training data set to obtain a battery usage time prediction model;

[0089] Obtaining the current battery information of the smart door lock, inputting the battery information into the battery usage time prediction model, and outputting the corresponding battery usage time prediction result;

[0090] If the power value of the battery usage time prediction result is lower than the preset power value, the working mode of the smart door lock is switched and the user is notified to handle it.

[0091] The step of obtaining battery usage data of multiple different types of smart door lock batteries and preprocessing the battery usage data to obtain a training data set specifically includes:

[0092] Obtain battery usage data of multiple different types of smart door lock batteries, wherein the battery usage data includes initial power information, battery usage time, battery temperature, and discharge current;

[0093] Performing data cleaning on all the battery usage data to obtain a battery data set, and performing normalization processing on the battery data set to obtain a target battery data set;

[0094] The target battery data set is converted, and the converted target battery usage data set is divided to obtain a training set and a verification set, and a training data set is obtained according to the training set and the verification set.

[0095] The step of performing data cleaning on all the battery usage data to obtain a battery data set, and performing normalization processing on the battery data set to obtain a target battery data set specifically includes:

[0096] Performing data integration on all the battery usage data, and performing data removal and value missing processing on the integrated battery usage data to obtain a battery data set, wherein the data integration includes data format conversion, data unit unification and data consistency check;

[0097] A data scaling ratio is set, and data scaling is performed on the battery data set according to the data scaling ratio to obtain a target battery data set.

[0098] The method further comprises: performing data cleaning on all the battery usage data to obtain a battery data set, and performing normalization processing on the battery data set to obtain a target battery data set, and then further comprising:

[0099] Performing data verification on the target battery data set to obtain a verification result, wherein the data verification includes data distribution comparison, data integrity check and data consistency check;

[0100] If the verification result is that the data distribution comparison, the data integrity check, and the data consistency check are all verified to pass, then it is determined that the target battery data set passes the verification;

[0101] If the verification result is that any one of the data distribution comparison, the data integrity check and the data consistency check fails, it is determined that the target battery data set fails the verification, and corresponding abnormal data is obtained according to the verification result, and the abnormal data is replaced.

[0102] The step of performing model training according to the training data set to obtain a battery life prediction model specifically includes:

[0103] Creating a battery life training model, and inputting a set of battery data samples in the training set into the battery life training model;

[0104] Extracting features from the battery data sample to obtain target battery features, and predicting battery usage time for the battery data according to the target battery features to obtain predicted battery usage time;

[0105] Performing loss calculation on the error between the predicted battery usage time and the corresponding actual battery usage time in the validation set to obtain a target loss value, and modifying the parameters of the battery usage time training model according to the target loss value;

[0106] The next set of battery data samples is input into the battery usage time training model until the training status of the battery usage time training model meets the preset conditions, thereby obtaining a trained battery usage time prediction model.

[0107] The step of performing loss calculation on the error between the predicted battery life and the corresponding actual battery life in the validation set to obtain a target loss value, and correcting the parameters of the battery life training model according to the target loss value, specifically includes:

[0108] Determine a loss function according to the problem type of predicting battery usage time to obtain a target loss function, and calculate the loss of the error between the predicted battery usage time and the corresponding actual battery usage time in the validation set according to the target loss function to obtain a target loss value;

[0109] The gradient information of the target loss function is obtained according to the target loss value, and the parameters of the battery usage time training model are corrected according to the gradient information.

[0110] The battery life prediction result includes the remaining battery life, power value and working mode;

[0111] If the power value of the battery usage time prediction result is lower than the preset power value, the working mode of the smart door lock is switched and the user is notified to process, which specifically includes:

[0112] Compare the power value with a preset power value, and if the power value is less than the preset power value, switch the working mode to a low power consumption mode;

[0113] A low battery reminder is generated according to the battery usage time prediction result, and the low battery reminder is pushed to the user to notify the user to process.

[0114] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a power management program for a smart door lock, and when the power management program for the smart door lock is executed by a processor, the steps of the power management method for the smart door lock as described above are implemented.

[0115] In summary, the present invention provides a power management method, system, terminal and storage medium for a smart door lock, the method comprising: obtaining battery usage data of multiple different types of smart door lock batteries, preprocessing the battery usage data to obtain a training data set, and performing model training based on the training data set to obtain a battery usage time prediction model; obtaining the current battery information of the smart door lock, inputting the battery information into the battery usage time prediction model, and outputting the corresponding battery usage time prediction result; if the power value of the battery usage time prediction result is lower than the preset power, switching the working mode of the smart door lock and notifying the user to process. The present invention can accurately predict the remaining service life of the battery by performing in-depth analysis of the battery usage data, so that the user can prepare in advance to avoid the situation where the smart lock cannot work properly due to battery attenuation. It can also automatically adjust the working mode of the smart lock according to the attenuation state of the battery, so that it can still maintain normal working performance after battery attenuation, thereby improving the use efficiency and reliability of the smart lock and enhancing the user experience.

[0116] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or terminal including the element.

[0117] Of course, those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the program can be stored in a computer-readable storage medium that can be read by a computer, and the program can include the processes of the above-mentioned method embodiments when executed. The computer-readable storage medium can be a memory, a disk, an optical disk, etc.

[0118] It should be understood that the application of the present invention is not limited to the above examples. For ordinary technicians in this field, improvements or changes can be made based on the above description. All these improvements and changes should fall within the scope of protection of the claims attached to the present invention.

Claims

1. A power management method for a smart door lock, characterized in that: The power management method of the smart door lock includes: Obtain battery usage data of multiple different types of smart door lock batteries, pre-process the battery usage data to obtain a training data set, and perform model training based on the training data set to obtain a battery usage time prediction model; Obtaining the current battery information of the smart door lock, inputting the battery information into the battery usage time prediction model, and outputting the corresponding battery usage time prediction result; If the power value of the battery usage time prediction result is lower than the preset power value, the working mode of the smart door lock is switched and the user is notified to handle it.

2. The power management method of the smart door lock according to claim 1, characterized in that: The obtaining of battery usage data of multiple different types of smart door lock batteries and preprocessing of the battery usage data to obtain a training data set specifically includes: Obtain battery usage data of multiple different types of smart door lock batteries, wherein the battery usage data includes initial power information, battery usage time, battery temperature, and discharge current; Performing data cleaning on all the battery usage data to obtain a battery data set, and performing normalization processing on the battery data set to obtain a target battery data set; The target battery data set is converted, and the converted target battery usage data set is divided to obtain a training set and a verification set, and a training data set is obtained according to the training set and the verification set.

3. The power management method of the smart door lock according to claim 2, characterized in that: The data cleaning of all the battery usage data to obtain a battery data set, and the normalization of the battery data set to obtain a target battery data set specifically include: Performing data integration on all the battery usage data, and performing data removal and value missing processing on the integrated battery usage data to obtain a battery data set, wherein the data integration includes data format conversion, data unit unification and data consistency check; A data scaling ratio is set, and data scaling is performed on the battery data set according to the data scaling ratio to obtain a target battery data set.

4. The power management method of the smart door lock according to claim 2, characterized in that: The data cleaning is performed on all the battery usage data to obtain a battery data set, and the battery data set is normalized to obtain a target battery data set, and then the following is further included: Performing data verification on the target battery data set to obtain a verification result, wherein the data verification includes data distribution comparison, data integrity check and data consistency check; If the verification result is that the data distribution comparison, the data integrity check, and the data consistency check are all verified to be passed, it is determined that the target battery data set has passed the verification; If the verification result is that any one of the data distribution comparison, the data integrity check and the data consistency check fails, it is determined that the target battery data set fails the verification, and corresponding abnormal data is obtained according to the verification result, and the abnormal data is replaced.

5. The power management method of the smart door lock according to claim 2, characterized in that: The performing model training according to the training data set to obtain a battery usage time prediction model specifically includes: Creating a battery life training model, and inputting a set of battery data samples in the training set into the battery life training model; Extracting features from the battery data sample to obtain target battery features, and predicting battery usage time for the battery data according to the target battery features to obtain predicted battery usage time; Performing loss calculation on the error between the predicted battery usage time and the corresponding actual battery usage time in the validation set to obtain a target loss value, and modifying the parameters of the battery usage time training model according to the target loss value; The next set of battery data samples is input into the battery usage time training model until the training status of the battery usage time training model meets the preset conditions, thereby obtaining a trained battery usage time prediction model.

6. The power management method of the smart door lock according to claim 5, characterized in that: The calculating the loss of the error between the predicted battery life and the corresponding actual battery life in the validation set to obtain a target loss value, and correcting the parameters of the battery life training model according to the target loss value specifically includes: Determine a loss function according to the problem type of predicting battery usage time to obtain a target loss function, and calculate the loss of the error between the predicted battery usage time and the corresponding actual battery usage time in the validation set according to the target loss function to obtain a target loss value; The gradient information of the target loss function is obtained according to the target loss value, and the parameters of the battery usage time training model are corrected according to the gradient information.

7. The power management method of the smart door lock according to claim 1, characterized in that: The battery life prediction result includes the remaining battery life, power value and working mode; If the power value of the battery usage time prediction result is lower than the preset power value, the working mode of the smart door lock is switched and the user is notified to process, which specifically includes: Compare the power value with a preset power value, and if the power value is less than the preset power value, switch the working mode to a low power consumption mode; A low battery reminder is generated according to the battery usage time prediction result, and the low battery reminder is pushed to the user to notify the user to process.

8. A power management system for a smart door lock, characterized in that: The power management system of the smart door lock includes: A model training module, used to obtain battery usage data of multiple different types of smart door lock batteries, pre-process the battery usage data to obtain a training data set, and perform model training based on the training data set to obtain a battery usage time prediction model; A time prediction module, used to obtain the current battery information of the smart door lock, input the battery information into the battery usage time prediction model, and output the corresponding battery usage time prediction result; The mode switching module is used to switch the working mode of the smart door lock and notify the user to process if the power value of the battery usage time prediction result is lower than the preset power value.

9. A terminal, characterized in that: The terminal includes: a memory, a processor, and a power management program for the smart door lock stored in the memory and executable on the processor. When the power management program for the smart door lock is executed by the processor, the steps of the power management method for the smart door lock as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a power management program for a smart door lock, and when the power management program for a smart door lock is executed by a processor, the steps of the power management method for a smart door lock as described in any one of claims 1-7 are implemented.

Images