Low-electric-quantity early warning method and system for card bag anti-lost device

Abstract

The invention provides a low-electric-quantity early warning method and system for a card bag anti-lost device, and belongs to the technical field of lithium ion batteries. According to the method, different scenes are accurately divided based on user behavior change characteristics and environmental condition difference indexes, and residual working duration prediction values under different scene classification results are calculated in combination with working states of the card packet anti-lost device. Meanwhile, first early warning information and second early warning information are generated through double judgment of whether the residual working duration prediction value is lower than a preset residual working duration threshold value of a corresponding scene classification result or not and whether the residual electric quantity is lower than an electric quantity early warning threshold value of the corresponding scene classification result or not; and the early warning information is integrated into the personalized early warning information corresponding to the scene classification result, so that the problems that a single early warning threshold is easy to misjudge and disturb frequently are avoided, personalized early warning contents meeting actual requirements can be provided for users in different use scenes, and the use experience of the users is remarkably improved.

Description

Technical Field

[0001] This disclosure relates to the field of lithium-ion battery technology, specifically to a low battery warning method and system for a wallet anti-loss device. Background Technology

[0002] Currently, in the field of smart devices, battery life management is crucial for user experience and device reliability. Smart devices, such as anti-loss devices, are increasingly widely used in daily life due to their portability and real-time connectivity. However, insufficient battery power can lead to device malfunction, affecting users' ability to track and manage critical items. Existing methods typically alert users through simple battery monitoring or fixed warning thresholds, but these methods struggle to adapt to dynamic factors such as changes in user behavior, environmental conditions, and device aging. This can easily result in inaccurate or overly frequent warnings, reducing user trust. Furthermore, they fail to generate accurate and contextualized battery warnings based on user behavior patterns, further degrading the user experience.

[0003] The information disclosed in the background section is only for enhancing the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0004] In view of this, this disclosure provides a low battery warning method for a wallet anti-loss device, which can improve the accuracy of low battery warning.

[0005] In a first aspect, embodiments of this application provide a low battery warning method for a wallet anti-loss device. The method includes: acquiring user behavior change characteristics and environmental condition difference indicators, wherein the user behavior change characteristics include user action intensity and user usage time, and the environmental condition difference indicators include WiFi signal strength, ambient temperature, and ambient humidity; determining a usage scenario description based on the user behavior change characteristics and the environmental condition difference indicators, wherein the usage scenario description includes indoor stationary state, indoor moving state, outdoor stationary state, and outdoor moving state; determining different scenario classification results based on the usage scenario description and the environmental condition difference indicators; and acquiring the working state of the wallet anti-loss device, wherein the working state includes... The system considers the following parameters: device operating time, device load rate, device nominal voltage, nominal battery capacity, and battery health; based on the operating status, it determines the predicted remaining working time corresponding to the scene classification result; it determines whether the predicted remaining working time is lower than a preset remaining working time threshold corresponding to the scene classification result; if it is determined to be lower than the preset remaining working time threshold, it determines a first warning message; it obtains the remaining battery power of the current wallet anti-loss device; it determines whether the remaining battery power is lower than a battery warning threshold corresponding to the scene classification result; if it is determined to be lower than the battery warning threshold, it determines a second warning message; and based on the first warning message and the second warning message, it determines personalized warning messages corresponding to the scene classification result.

[0006] Secondly, embodiments of this application provide a low battery warning system for a wallet anti-loss device. This system includes: a first acquisition module, a first determination module, a second determination module, a second acquisition module, a third determination module, a judgment module, a fourth determination module, a third acquisition module, a fifth determination module, a sixth determination module, and a seventh determination module. The first acquisition module is used to acquire user behavior change characteristics and environmental condition difference indicators. The user behavior change characteristics include user action intensity and user usage time. The environmental condition difference indicators include WiFi signal strength, ambient temperature, and ambient humidity. The first determination module is used to determine a usage scenario description based on the user behavior change characteristics and the environmental condition difference indicators. The usage scenario description includes indoor stationary state, indoor moving state, outdoor stationary state, and outdoor moving state. The second determination module is used to determine different scenario classification results based on the usage scenario description and the environmental condition difference indicators. The second acquisition module is used to acquire the working status of the wallet anti-loss device. The working status includes device running time, device load rate, device nominal voltage, nominal battery capacity, and battery level. The system comprises the following modules: a health status module; a third determining module, used to determine the predicted remaining working time value corresponding to the scene classification result based on the working status; a judging module, used to judge whether the predicted remaining working time value is lower than the preset remaining working time threshold corresponding to the scene classification result; a fourth determining module, used to determine a first warning message if it is judged to be lower than the preset remaining working time threshold; a third obtaining module, used to obtain the remaining battery power of the current wallet anti-loss device; a fifth determining module, used to judge whether the remaining battery power is lower than the battery warning threshold corresponding to the scene classification result; a sixth determining module, used to determine a second warning message if it is judged to be lower than the battery warning threshold; and a seventh determining module, used to determine personalized warning information corresponding to the scene classification result based on the first warning information and the second warning information.

[0007] This application provides a low battery warning method for a wallet anti-loss device. By determining scene descriptions based on user behavior changes and environmental condition differences, different scenes are accurately classified according to the usage scene descriptions and environmental condition differences to avoid the limitations of single-scene evaluation. Then, combined with the working status of the wallet anti-loss device, the predicted remaining working time under different scene classification results is calculated, fully considering device aging and the actual battery health status, improving the accuracy of battery life prediction. Simultaneously, through dual judgments of "whether the predicted remaining working time is lower than the preset remaining working time threshold of the corresponding scene classification result" and "whether the remaining battery power is lower than the battery warning threshold of the corresponding scene classification result," first and second warning information are generated respectively. These warning information are integrated into personalized warning information corresponding to the scene classification result. This avoids the problems of misjudgment and frequent interruptions caused by single warning thresholds, and provides users with warning content tailored to their actual needs in different usage scenarios. Ultimately, this effectively ensures the reliability of the wallet anti-loss device's anti-loss function in various usage scenarios, reduces the risk of item loss due to low battery failure, significantly improves the user experience, and enhances the practicality and credibility of the wallet anti-loss device's low battery warning information. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments or conventional technologies of this disclosure, the accompanying drawings used in the description of the embodiments or conventional technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a flowchart illustrating a low battery warning method for a wallet anti-loss device provided in an exemplary embodiment of this application.

[0010] Figure 2 This is a flowchart illustrating a low battery warning method for a wallet anti-loss device provided in another exemplary embodiment of this application.

[0011] Figure 3 This is a flowchart illustrating a low battery warning method for a wallet anti-loss device, provided in another exemplary embodiment of this application.

[0012] Figure 4 This is a flowchart illustrating a low battery warning method for a wallet anti-loss device, provided in another exemplary embodiment of this application.

[0013] Figure 5 This is a flowchart illustrating a low battery warning method for a wallet anti-loss device, provided in another exemplary embodiment of this application.

[0014] Figure 6This is a flowchart illustrating a low battery warning method for a wallet anti-loss device, provided in another exemplary embodiment of this application.

[0015] Figure 7 This is a flowchart illustrating a low battery warning method for a wallet anti-loss device, provided in another exemplary embodiment of this application. Detailed Implementation

[0016] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are set forth to give a full understanding of embodiments of this disclosure.

[0017] The terms “a,” “one,” and “the” are used to indicate the existence of one or more elements / components / etc.; the terms “including” and “having” are used to indicate an open-ended inclusion and that other elements / components / etc. may exist in addition to those listed. The terms “first” and “second” are used only as markers and are not a limitation on the number of objects.

[0018] Currently, in the lithium-ion battery field, battery life management is crucial for user experience and device reliability. Smart devices, such as anti-loss devices, are increasingly used in daily life due to their portability and real-time connectivity. However, insufficient battery power can lead to device failure, affecting users' ability to track and manage critical items. Existing methods typically alert users through simple power monitoring or fixed warning thresholds, but these methods struggle to adapt to dynamic factors such as changes in user behavior, environmental conditions, and device aging. This can result in inaccurate or overly frequent warnings, reducing user trust. Furthermore, they fail to generate accurate and contextualized power warnings based on user behavior patterns, further degrading the user experience.

[0019] For example, the power consumption patterns of wallet anti-loss devices differ significantly depending on whether the device is at home, outdoors, or in frequent movement. A single power consumption assessment cannot accurately reflect the rate of power consumption under different usage scenarios. If a user uses the anti-loss device in a low-temperature outdoor environment, the effective battery capacity decreases due to the reduced temperature. However, existing methods may only issue warnings based on a fixed power consumption model, ignoring the combined effects of temperature and usage frequency. This could result in warnings that are either too conservative or too aggressive, causing users to miss alerts at crucial moments or receive frequent irrelevant warnings. Therefore, how to dynamically assess device power consumption and battery health by combining multi-source data, and generate accurate and contextualized power warnings based on user behavior patterns and usage scenarios, has become a key issue in improving the reliability of wallet anti-loss device battery life management.

[0020] This disclosure provides a low battery warning method for a wallet anti-loss device, such as... Figure 1 The low battery warning method shown is for a wallet anti-loss device. This method may include the following steps: Step S110: Obtain user behavior change characteristics and environmental condition difference indicators. User behavior change characteristics include user action intensity and user usage time. Environmental condition difference indicators include WiFi signal strength, ambient temperature and ambient humidity. Step S120: Determine the usage scenario description based on the characteristics of user behavior changes and the indicators of differences in environmental conditions. The usage scenario description includes indoor stationary state, indoor mobile state, outdoor stationary state, and outdoor mobile state. Step S130: Determine different scenario classification results based on the usage scenario description and environmental condition difference indicators; Step S140: Obtain the working status of the wallet anti-loss device, including device running time, device load rate, device nominal voltage, nominal battery capacity, and battery health. Step S150: Determine the predicted remaining working time value of the corresponding scenario classification result based on the working status; Step S160: Determine whether the predicted value of the remaining working time is lower than the preset remaining working time threshold of the corresponding scenario classification result; Step S170: If it is determined that the remaining working time is below the preset threshold, then the first warning information is determined; Step S180: Obtain the remaining battery power of the current card wallet anti-loss device; Step S190: Determine whether the remaining battery power is lower than the battery warning threshold of the corresponding scenario classification result; Step S192: If it is determined that the battery level is below the warning threshold, then a second warning message is determined; Step S194: Determine the personalized warning information for the corresponding scenario classification result based on the first warning information and the second warning information.

[0021] According to the low battery warning method for a wallet anti-loss device provided in this disclosure, the method can obtain user behavior change characteristics and environmental condition difference indicators. User behavior change characteristics include user action intensity and user usage time, while environmental condition difference indicators include WiFi signal strength, ambient temperature, and ambient humidity. Based on these characteristics, the method determines a usage scenario description, including indoor stationary state, indoor mobile state, outdoor stationary state, and outdoor mobile state. It then determines different scenario classification results based on the usage scenario description and environmental condition difference indicators. Finally, it obtains the working status of the wallet anti-loss device, including the working status package. This includes device operating time, device load rate, device nominal voltage, nominal battery capacity, and battery health; determining the predicted remaining working time for the corresponding scenario classification result based on the working status; determining whether the predicted remaining working time is lower than the preset remaining working time threshold for the corresponding scenario classification result; if it is determined to be lower than the preset remaining working time threshold, then determining the first warning information; obtaining the remaining battery power of the current wallet anti-loss device; determining whether the remaining battery power is lower than the battery warning threshold for the corresponding scenario classification result; if it is determined to be lower than the battery warning threshold, then determining the second warning information; and determining the personalized warning information for the corresponding scenario classification result based on the first and second warning information.

[0022] In the above method, scenario descriptions are determined based on user behavior change characteristics and environmental condition difference indicators. Different scenarios are then accurately divided according to the usage scenario descriptions and environmental condition difference indicators to avoid the limitations of single-scenario evaluation. The remaining working time prediction value under different scenario classification results is calculated by combining the working status of the wallet anti-loss device, fully considering device aging and the actual health status of the battery, thus improving the accuracy of battery life prediction. Simultaneously, through dual judgments of "whether the remaining working time prediction value is lower than the preset remaining working time threshold of the corresponding scenario classification result" and "whether the remaining battery power is lower than the battery warning threshold of the corresponding scenario classification result," first and second warning messages are generated respectively. These warning messages are then integrated into personalized warning messages for the corresponding scenario classification results. This avoids the problems of misjudgment and frequent interruptions caused by single warning thresholds, and provides users with warning content tailored to their actual needs in different usage scenarios. Ultimately, this effectively ensures the reliability of the wallet anti-loss device's anti-loss function in various usage scenarios, reduces the risk of item loss due to low battery failure, significantly improves the user experience, and enhances the practicality and credibility of the wallet anti-loss device's low battery warning information.

[0023] The following is a detailed description of each step in the low battery warning method for a wallet anti-loss device provided by this disclosure: In one embodiment of this disclosure, step S110 involves acquiring user behavior change characteristics and environmental condition difference indicators. User behavior change characteristics include user action intensity and user usage time. Environmental condition difference indicators include WiFi signal strength, ambient temperature, and ambient humidity. Specifically, the three-axis acceleration and angular velocity data of the wallet anti-loss device can be collected using the built-in accelerometer (100Hz sampling rate) and gyroscope, and then the user action intensity is calculated using the Euclidean norm. User usage time can include core usage periods and continuous usage duration, which can be extracted from the wallet anti-loss device's connection log (timestamp updated every 5 seconds) to reflect the user's dependence on the wallet anti-loss device during certain periods. WiFi signal strength can be collected by the wallet anti-loss device's WiFi module, reflecting the "enclosedness" of the environment (signal is usually strong indoors and weak outdoors), indirectly assisting in determining the usage scenario type. Ambient temperature can be collected by the device's built-in temperature sensor, affecting the effective capacity of the lithium-ion battery. Ambient humidity can be collected by the wallet anti-loss device's built-in humidity sensor, affecting the device's circuit stability.

[0024] The above method integrates multi-source data such as "user behavior (usage intensity, usage time) + environmental conditions (WiFi signal, temperature, humidity)" to comprehensively capture dynamic factors affecting the power consumption and battery performance of the wallet anti-loss device. This helps to clarify the user's reliance on the anti-loss device and ensures the scenario adaptability and warning accuracy of the entire low battery warning method from the source, solving the core pain point of existing methods that are difficult to adapt to dynamic changes in user behavior and environment.

[0025] In one embodiment of this disclosure, step S120 involves determining a usage scenario description based on user behavior change characteristics and environmental condition difference indicators. The usage scenario description includes indoor stationary state, indoor mobile state, outdoor stationary state, and outdoor mobile state. The step also includes the following steps: Figure 2 As shown, the specific content is as follows: Step S210: Obtain the acceleration and angular velocity data of the card wallet anti-loss device; Step S220: Determine the intensity of the user's action based on the angular velocity data; Step S230: Determine whether the deviation between the user's action intensity and the preset action intensity threshold exceeds the preset deviation threshold; Step S240: If it is determined that the preset deviation threshold is exceeded, then determine whether the WiFi signal strength exceeds the preset signal strength threshold. Step S250: If it is determined that the signal strength exceeds the preset threshold, then it is determined that the user is in an indoor mobile state; Step S260: If it is determined that the preset signal strength threshold is not exceeded, then it is determined that the user is in an outdoor mobile state; Step S270: If it is determined that the preset deviation threshold is not exceeded, then determine whether the WiFi signal strength exceeds the preset signal strength threshold; Step S280: If it is determined that the signal strength exceeds the preset threshold, then it is determined that the user is in a stationary indoor state; Step S290: If it is determined that the preset signal strength threshold is not exceeded, then it is determined that the user is in a stationary outdoor state.

[0026] Specifically, the above steps will be explained in detail using four typical scenarios: "User A working indoors," "User B walking indoors (e.g., retrieving documents from the office)," "User C shopping outdoors," and "User D sitting outdoors (e.g., on a park bench)." For example, the preset action intensity threshold can be set to 10.0 m / s. 2 The preset deviation threshold is set to 0.1 m / s. 2 The default WiFi signal strength threshold is set to -70dBm. Next, the built-in 100Hz sampling rate accelerometer and gyroscope in the wallet anti-loss device can collect real-time motion data of the user while carrying the device, such as acceleration and angular velocity data. The motion intensity is then calculated using the Euclidean norm algorithm. For example, user A's motion intensity is 9.90m / s². 2 User B: The motion intensity is 10.14 m / s 2 User C: Motion intensity is 10.3 m / s 2 User D: Motion intensity is 9.90 m / s 2 User A: Deviation value = |9.90 - 10.0| = 0.10 m / s 2 (≤0.1m / s) 2 (The deviation did not exceed the preset deviation threshold); User B: Deviation value = |10.14 - 10.0| = 0.14 m / s 2 (>0.1m / s) 2 (Exceeding the preset deviation threshold); User C: Deviation value = |10.3 - 10.0| = 0.3 m / s 2 (>0.1m / s) 2 (Exceeding the preset deviation threshold); User D: Deviation value = |9.90 - 10.0| = 0.10 m / s 2 (≤0.1m / s) 2(The signal strength is within the preset deviation threshold). Next, we continue the assessment: User A: WiFi signal strength is -62dBm (> -70dBm, exceeding the preset signal strength threshold), determined to be in an indoor stationary state (indoor office, home environment); User B: WiFi signal strength is -65dBm (> -70dBm, exceeding the preset signal strength threshold), determined to be in an indoor moving state (indoor walking, office environment); User C: WiFi signal strength is -82dBm (< -70dBm, not exceeding the preset signal strength threshold), determined to be in an outdoor moving state (outdoor shopping, park environment); User D: WiFi signal strength is -78dBm (< -70dBm, not exceeding the preset signal strength threshold), determined to be in an outdoor stationary state (outdoor sitting, park environment).

[0027] In the above method, the use of a two-dimensional hierarchical judgment logic of "user action intensity + WiFi signal" is used to achieve accurate classification of the usage scenarios of the wallet anti-loss device. This breaks through the limitation of traditional anti-loss devices that rely on a single data to make a vague judgment of the scenario, forming a clear division of four scenarios. This ensures that the usage scenario description is highly matched with the actual user situation, laying the core foundation for the scenario adaptation and accuracy of the entire low battery warning method.

[0028] In one embodiment of this disclosure, after determining the usage scenario description in step S120, the method further includes the following steps, such as... Figure 3 As shown, the specific content is as follows: Step S310: Establish a logistic regression model, using user behavior change characteristics and environmental condition difference indicators as inputs to the logistic regression model, and the probability values ​​describing different usage scenarios as outputs of the logistic regression model. Step S320: Sort the probability values ​​of different use scenario descriptions, and take the use scenario description corresponding to the maximum value in the sorting results as the current use scenario description.

[0029] Specifically, by sorting the output of the four scenario probabilities from largest to smallest, and taking the scenario corresponding to the highest probability as the final scenario description, the ambiguity of the "threshold comparison" in step S120 can be resolved, such as when the action intensity deviation is close to 0.1 m / s. 2 In such cases, relying solely on thresholds is insufficient for accurate judgment, while probability ranking can quantify the credibility of a scenario. For example, by determining the probabilities of different usage scenario descriptions as follows: indoor stationary state (0.88) > indoor mobile state (0.07) > outdoor stationary state (0.03) > outdoor mobile state (0.02), the probability of indoor stationary state is 0.88, which is the maximum value, thus determining the current usage scenario description as indoor stationary state.

[0030] In one embodiment of this disclosure, step S130, which determines different scenario classification results based on the usage scenario description and environmental condition difference index, further includes the following steps: Figure 4 As shown, the specific content is as follows: Step S410: Standardize the use case descriptions to generate a standard dataset of use case descriptions; Step S420: Standardize the ambient temperature and humidity to generate a standard dataset of environmental condition differences; Step S430: Based on the K-means clustering algorithm, determine the clustering results according to the standard dataset describing the use scenario and the standard dataset showing differences in environmental conditions; Step S440: Calculate the feature importance score in different clustering results based on the random forest algorithm; Step S450: Sort the feature importance scores from the maximum to the minimum, and determine different scene classification results based on the sorting results.

[0031] Specifically, the usage scenario description standard dataset can be generated by encoding the scenario as follows: "Indoor stationary state = 0, indoor mobile state = 1, outdoor stationary state = 2, outdoor mobile state = 3". The scenario standardization value is calculated using the linear normalization formula: Scenario Standardization Value = Encoded Value / 3. The standardized value for user A (indoor stationary state) is 0.00, for user B (indoor mobile state) it is 0.33, for user C (outdoor stationary state) it is 0.67, and for user D (outdoor mobile state) it is 1.00. For ambient temperature and humidity, the temperature normalization range is set to [-10, 35℃] based on the characteristics of lithium-ion batteries. The formula is T' = (T + 10) / 45, where T is the temperature value before normalization and T' is the temperature value after normalization. The humidity normalization range is [30, 80%], and the formula is H' = (H - 30) / 50, where H is the humidity value before normalization and H' is the humidity value after normalization. This generates an environmental condition difference standard dataset. For example, user A (32℃, 75%) is standardized to [0.93, 0.90], user B (20℃, 40%) to [0.53, 0.20], user C (-5℃, 70%) to [0.11, 0.80], and user D (-8℃, 35%) to [0.09, 0.15]. These two types of standard datasets are merged into a sample feature vector (e.g., user A: [0.00, 0.93, 0.90]). Using the K-means clustering algorithm (K=4, 10 iterations), clustering is performed based on "basic scenario power consumption + lithium-ion battery sensitive temperature". User A is assigned to cluster 1 ("low power consumption + high temperature and high humidity"), user B to cluster 2 ("medium power consumption + normal temperature and low humidity"), user C to cluster 3 ("medium power consumption + low temperature and high humidity"), and user D to cluster 4 ("high power consumption + low temperature and low humidity"). Using clustering results as labels and sample feature vectors as input, a random forest model (100 decision trees, maximum depth 10) is trained. Feature importance scores are calculated, with ambient temperature (0.45, affecting lithium-ion battery capacity) > usage scenario coding (0.35, determining basic power consumption) > ambient humidity (0.20, assisting in judging extreme environments). After sorting by scores, the final scenario classification results are determined: User A is in a static state indoors with high temperature and high humidity, User B is in a moving state indoors with normal temperature and low humidity, User C is in a static state outdoors with low temperature and high humidity, and User D is in a moving state outdoors with low temperature and low humidity.

[0032] The above method, through the technical route of "standardization-clustering-feature importance analysis", achieves the refinement and accuracy of the usage scenario classification of the card pack anti-loss device, solves the pain point of the coarse scenario classification in the existing methods, provides accurate scenario basis for generating scenario-based warning content, and ensures the core goal of the entire low battery warning method based on dynamic scenario adaptation from a technical point of view.

[0033] In one embodiment of this disclosure, step S140 involves acquiring the operating status of the wallet anti-loss device. This operating status includes device runtime, device load rate, device nominal voltage, nominal battery capacity, and battery health. Specifically, the wallet anti-loss device can record the initial activation timestamp and the duration of each power-on cycle using a built-in non-volatile log chip, preventing data loss during power outages. For example, user A's wallet anti-loss device was first activated on September 12, 2023, and is currently active on September 12, 2024, averaging 6 hours of daily use, with a cumulative runtime of 2190 hours. The device load rate is the ratio (percentage) of the wallet anti-loss device's current actual power consumption to its rated maximum power consumption, and is closely related to the real-time discharge intensity of the lithium-ion battery. A higher load rate results in a larger lithium-ion battery discharge current and faster battery consumption. The device nominal voltage is the factory standard operating voltage (a fixed value reflecting the battery's electrochemical characteristics and serving as the basis for calculating battery energy) of the lithium-ion battery used in the wallet anti-loss device. For example, the "nominal voltage" of the wallet anti-loss devices for users A, B, C, and D is all 3.7V (a fixed parameter that does not change with usage time). The nominal battery capacity is the factory-marked capacity (unit: mAh, reflecting the total theoretical charge the battery can provide, and is the basis for calculating remaining working time) of the lithium-ion battery used in the wallet anti-loss device. For example, users A and B's wallet anti-loss devices are the same model, using a 200mAh nominal capacity lithium-ion battery, therefore the nominal battery capacity is 200mAh. Battery health is the ratio (percentage) of the actual capacity of the wallet anti-loss device's lithium-ion battery to its nominal capacity, directly reflecting the battery's aging status. The lower the battery health, the less actual usable capacity the lithium-ion battery has, and the shorter the battery life. For example, user A's anti-loss device has a nominal capacity of 200mAh, and cloud historical data shows a current actual capacity of 180mAh: Battery health = (180 / 200) × 100% = 90% (slight aging, lithium-ion battery performance is well preserved).

[0034] In one embodiment of this disclosure, step S150, determining the predicted remaining working time value of the corresponding scene classification result based on the working status, further includes the following steps: Figure 5 As shown, the specific content is as follows: Step S510: Determine the aging factor based on the running time and load rate; Step S520: Determine the temperature influence factor of the corresponding scene classification results based on the ambient temperature; Step S530: Determine the predicted power consumption value of the corresponding scenario classification result based on the aging factor and temperature influence factor; Step S540: Determine the actual battery capacity based on the nominal battery capacity; Step S550: Determine the remaining working time prediction value of the corresponding scenario classification result based on the actual battery capacity and power consumption prediction value.

[0035] Specifically, the formula for calculating the aging factor is: α = 1 + 0.0001 × operating time (hours) + 0.001 × load rate, where α is the aging factor. For example, User A (stationary state indoors at normal temperature): equipment operating time 2190 hours, equipment load rate 30%, then the aging factor α = 1 + 0.0001 × 2190 + 0.001 × 30 = 1 + 0.219 + 0.03 = 1.249. User C (stationary state outdoors at low temperature): operating time 7300 hours (used for 2 years, average 10 hours per day), load rate 40%, the aging factor α = 1 + 0.0001 × 7300 + 0.001 × 40 = 1 + 0.73 + 0.04 = 1.77. User D (low-temperature outdoor mobile state): operating time 1825 hours (1 year of use, average 5 hours per day), load rate 60%, aging factor α = 1 + 0.0001 × 1825 + 0.001 × 60 = 1 + 0.1825 + 0.06 = 1.2425. The temperature influence factor (β) is a parameter that quantifies the impact of ambient temperature on the activity and power consumption of lithium-ion batteries (lithium-ion activity decreases at low temperatures, actual power consumption increases, β ≥ 1; at normal temperature, β ≈ 1). For example, User A (stationary state indoors at normal temperature, 25℃) has β = 1.0; User D (low-temperature outdoor mobile state, outdoor temperature -8℃) has β = 1.3; User C (low-temperature outdoor stationary state, outdoor temperature -5℃) → its β = 1.3. The predicted power consumption value is the actual instantaneous power consumption (unit: mA) of the wallet anti-loss device (including lithium-ion battery) after aging and temperature correction in the current scenario. Its calculation formula is: P1 = P2 × α × β Where P1 is the predicted power consumption value, P2 is the basic power consumption value, α is the aging factor, and β is the temperature influence factor.

[0036] It should be noted that the base power consumption for a stationary state indoors at room temperature is 26, the base power consumption for a mobile state outdoors at low temperatures is 60, and the base power consumption for a stationary state outdoors at low temperatures is 35. Based on the above formulas, for User A (stationary state indoors at room temperature): P1 = 26 × 1.249 × 1.0 ≈ 32.47 mA (approximately 33 mA); for User D (mobile state outdoors at low temperatures): P1 = 60 × 1.2425 × 1.3 ≈ 60 × 1.615 ≈ 96.9 mA (approximately 97 mA); for User C (stationary state outdoors at low temperatures): P1 = 35 × 1.77 × 1.3 ≈ 35 × 2.301 ≈ 80.54 mA (approximately 81 mA).

[0037] The actual battery capacity is the current usable capacity of the lithium-ion battery (unit: mAh), and the capacity decay caused by aging needs to be deducted. It directly determines the upper limit of the battery life. User A: Nominal battery capacity = 200mAh, SOH (State of Health) = 90%, then User A's actual battery capacity = 200 × 90% = 180mAh; User C: Nominal battery capacity = 300mAh, SOH = 75%, then User C's actual battery capacity = 300 × 75% = 225mAh; User D: Nominal battery capacity = 200mAh, SOH = 75%, then User D's actual battery capacity = 200 × 75% = 150mAh.

[0038] The predicted remaining operating time is the time (in hours) that the lithium-ion battery can sustain the device's operation under the current scenario, discharging at its actual power consumption. User A (stationary state indoors): Predicted remaining operating time = 180mAh ÷ 33mA ≈ 5.45 hours, consistent with low power consumption indoors and relatively long battery life; User D (mobile state outdoors in low temperatures): Predicted remaining operating time = 225mAh ÷ 97mA ≈ 2.32 hours, consistent with low temperature and high load, resulting in short battery life and requiring timely warning; User C (stationary state outdoors in low temperatures): Predicted remaining operating time = 150mAh ÷ 81mA ≈ 1.85 hours, consistent with aging and low temperature, further shortening battery life.

[0039] In the above method, by combining running time, load rate, and ambient temperature, the basic power consumption of the scenario is corrected with aging factor and temperature influence factor to ensure that the power consumption prediction value is consistent with the aging state of the wallet anti-loss device and the temperature sensitivity of lithium-ion battery; then, the actual battery capacity is calculated by battery health (SOH) to avoid the problem of "nominal capacity and actual usable capacity being out of sync" caused by lithium-ion battery aging. Finally, the output remaining working time prediction value can accurately match the current scenario and the actual state of the wallet anti-loss device, thereby achieving the invention goal of improving the reliability of smart device battery life management.

[0040] In one embodiment of this disclosure, step S540, determining the actual battery capacity based on the nominal battery capacity, further includes the following steps: Figure 6 As shown, the specific content is as follows: Step S610: Obtain the battery cycle count and battery degradation factor; Step S620: Update battery health based on battery cycle count and battery degradation factor; Step S630: Multiply the updated battery health by the nominal battery capacity, and use the result of the multiplication as the actual battery capacity.

[0041] Specifically, for example, User A (using the wallet anti-loss device for 1 year, commuting, charging once a week): The BMS (Battery Management System) records 52 battery cycle times (1 year × 52 weeks) and a battery degradation factor of 0.05% / cycle; User C (using the wallet anti-loss device for 2 years, charging once a day): The BMS records 730 battery cycle times (2 years × 365 days) and a battery degradation factor of 0.05% / cycle. The formula for updating battery health is: SOH 更新后 =SOH 初始 (Battery cycle count × battery degradation factor). Based on the above formula, User A: SOH 初始 =90%, 52 cycles, SOH 更新后 =90% (52 × 0.05%) = 90% - 2.6% = 87.4%; User C: SOH 初始 =75%, 730 cycles, SOH 更新后 =75% (730 × 0.05%) = 75% 36.5% = 38.5%. The actual battery capacity is the current usable charge of the lithium-ion battery, calculated by multiplying the nominal battery capacity by the updated battery health. This eliminates the bias caused by the initial battery health not considering battery cycle degradation. For example, User A: Nominal battery capacity = 200mAh, updated SOH = 87.4%, then their actual battery capacity = 200 × (87.4 / 100) = 174.8mAh; User C: Nominal battery capacity = 200mAh, SOH... 更新后 =38.5%, then its actual battery capacity = 200 × (38.5 / 100) = 77mAh.

[0042] The above method focuses on the core characteristics of lithium-ion battery cycle degradation to achieve accurate calculation of actual battery capacity. This ensures that the actual battery capacity not only matches the natural aging of the battery but also reflects the additional degradation caused by high-frequency cycling. It provides real and reliable capacity data for calculating the predicted value of remaining working time, avoiding deviations in range prediction caused by misjudgment of actual capacity, and ensuring the accuracy of low battery warning from the data source.

[0043] In one embodiment of this disclosure, in steps S160-S170, it is determined whether the predicted remaining working time is lower than the preset remaining working time threshold of the corresponding scenario classification result; if it is determined to be lower than the preset remaining working time threshold, then a first warning message is determined. Specifically, for example, if user A is in a static indoor environment, the predicted remaining working time of their wallet anti-loss device is calculated to be 5.45 hours, while the preset remaining working time threshold for the corresponding static indoor environment is 6 hours. In this case, it is determined to be the preset remaining working time threshold, and the first warning message can be output as follows: the current device is expected to have 5.45 hours of remaining working time, and the risk level is low.

[0044] In one embodiment of this disclosure, in steps S180-S192, the remaining battery power of the current wallet anti-loss device is obtained; it is determined whether the remaining battery power is lower than the battery warning threshold of the corresponding scenario classification result; if it is determined to be lower than the battery warning threshold, a second warning message is determined. Specifically, for example, user A (stationary state in a normal temperature room, indoor temperature 25℃, Bluetooth low-frequency connection): the BMS detects that its remaining battery power is 9%. The current battery warning threshold corresponding to being stationary in a normal temperature room is 10%. Therefore, it is determined that it is lower than the battery warning threshold, and the second warning message is determined that the current real-time remaining battery power of the device is 9%, which can be charged at a convenient time to avoid power outages during subsequent use.

[0045] The process of determining the power warning threshold for the corresponding scenario classification result includes the following steps: obtaining the weight factor and initial power warning threshold in the corresponding scenario classification result; multiplying the initial power warning threshold by the weight factor of the corresponding scenario classification result, and using the result as the power warning threshold for the corresponding scenario classification result. For example, if user A is stationary in a normal temperature room, the corresponding weight factor is 0.67, and the initial power warning threshold is 15%, then the power warning threshold for user A in a stationary state in a normal temperature room is 15% × 0.67 ≈ 10.05% ≈ 10%. If user B is moving in a normal temperature, low humidity indoor environment, the corresponding weight factor is 0.8, and the initial power warning threshold is 15%, then the power warning threshold for user B in a normal temperature, low humidity indoor environment is 15% × 0.8 = 12%.

[0046] In one embodiment of this disclosure, step 194, determining the personalized warning information for the corresponding scene classification result based on the first warning information and the second warning information, further includes the following steps: Figure 7 As shown, the specific content is as follows: Step S710: Obtain the warning content template that matches the current scene classification result from the preset information database; Step S720: Determine the personalized warning information for the corresponding scenario classification result based on the warning content template, the first warning information, and the second warning information.

[0047] Specifically, when the scenario classification result is "moving outdoors in low temperatures," the corresponding warning content template is:

Low Battery Warning for Wallet Anti-loss Device

Low Battery Warning for Wallet Anti-loss Device

[0048] In the above method, by matching warning content templates and scenarios, and filling in multi-dimensional data, the low battery warning is upgraded from a basic risk warning to a personalized warning. This allows the warning information to not only explain the risk but also provide countermeasures, preventing users from being at a loss after receiving the warning information. The final personalized warning information accurately matches the actual state of the lithium-ion battery and the user scenario, ensuring that the core anti-loss function of the wallet anti-loss device does not fail, and significantly improving the user experience. This achieves the invention goal of improving the reliability of the wallet anti-loss device's battery life management and the user experience.

[0049] This disclosure also provides a low battery warning system for a wallet anti-loss device. The system may include a first acquisition module, a first determination module, a second determination module, a second acquisition module, a third determination module, a judgment module, a fourth determination module, a third acquisition module, a fifth determination module, a sixth determination module, and a seventh determination module. The first acquisition module acquires user behavior change characteristics and environmental condition difference indicators. User behavior change characteristics include user action intensity and user usage time. Environmental condition difference indicators include WiFi signal strength, ambient temperature, and ambient humidity. The first determination module determines a usage scenario description based on the user behavior change characteristics and environmental condition difference indicators. The usage scenario description includes indoor stationary state, indoor moving state, outdoor stationary state, and outdoor moving state. The second determination module determines different scenario classification results based on the usage scenario description and environmental condition difference indicators. The second acquisition module acquires the working status of the wallet anti-loss device, including device running time, device load rate, device nominal voltage, and nominal battery capacity. The system includes: a battery health module; a third determining module for determining the predicted remaining working time based on the working status of the corresponding scenario classification result; a judging module for judging whether the predicted remaining working time is lower than the preset remaining working time threshold of the corresponding scenario classification result; a fourth determining module for determining the first warning information if the predicted remaining working time is lower than the preset remaining working time threshold; a third obtaining module for obtaining the remaining battery power of the current wallet anti-loss device; a fifth determining module for judging whether the remaining battery power is lower than the battery warning threshold of the corresponding scenario classification result; a sixth determining module for determining the second warning information if the remaining battery power is lower than the battery warning threshold; and a seventh determining module for determining the personalized warning information of the corresponding scenario classification result based on the first and second warning information.

[0050] It should be noted that the embodiment of the low battery warning system for a wallet anti-loss device provided in this application can be used to execute the processing flow of the embodiment of the low battery warning method for a wallet anti-loss device in the above embodiment. Its function will not be repeated here, but can be referred to the detailed description of the above method embodiment.

[0051] As described above, the low battery warning system for a wallet anti-loss device provided in this disclosure determines the scene description based on user behavior change characteristics and environmental condition difference indicators, and accurately classifies different scenes according to the usage scene description and environmental condition difference indicators to avoid the limitations of single scene evaluation; then, it calculates the predicted remaining working time under different scene classification results by combining the working status of the wallet anti-loss device, fully considering device aging and the actual health status of the battery, and improving the accuracy of battery life prediction; at the same time, it uses "whether the predicted remaining working time is lower than the preset remaining working time threshold of the corresponding scene classification result" and The system uses a dual judgment of whether the remaining battery level is lower than the battery warning threshold for the corresponding scenario classification result to generate a first warning message and a second warning message respectively. These warning messages are then integrated into a personalized warning message for the corresponding scenario classification result. This avoids the problems of misjudgment and frequent interruptions caused by a single warning threshold, and provides users with warning content that fits their actual needs in different usage scenarios. Ultimately, this effectively ensures the reliability of the wallet anti-loss device's anti-loss function in various usage scenarios, reduces the risk of item loss due to low battery failure, and significantly improves the user experience, enhancing the practicality and credibility of the wallet anti-loss device's low battery warning message.

[0052] This disclosure also provides an electronic device including one or more processors and memory resources, represented by a memory, for storing instructions executable by the processor, such as application programs. The application programs stored in the memory may include one or more modules, each corresponding to a set of instructions. Furthermore, the processor is configured to execute instructions to perform the low battery warning method for the aforementioned wallet anti-loss device.

[0053] The electronic device may also include a power supply component configured to perform power management of the electronic device, a wired or wireless network interface configured to connect the electronic device to a network, and an input / output (I / O) interface. The electronic device can be operated based on operating devices stored in memory, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or similar.

[0054] In one embodiment, a computer device, which may be a server, is also provided. The computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is connected to the system bus via the I / O interfaces. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes non-volatile storage media and internal memory. The non-volatile storage media stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device stores data. The I / O interfaces of the computer device are used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a low-battery warning method for a wallet anti-loss device.

[0055] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a low-battery warning method for a wallet anti-loss device. The display unit of the computer device is used to form a visually visible image and may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0056] This disclosure also provides a non-transitory computer-readable storage medium. When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to execute a low battery warning method for a wallet anti-loss device, including: acquiring user behavior change characteristics and environmental condition difference indicators, wherein the user behavior change characteristics include user action intensity and user usage time, and the environmental condition difference indicators include WiFi signal strength, ambient temperature, ambient humidity, ambient wind speed, and ambient light intensity; determining a usage scenario description based on the user behavior change characteristics and environmental condition difference indicators, wherein the usage scenario description includes indoor stationary state, indoor moving state, outdoor stationary state, and outdoor moving state; and determining the usage scenario description based on the environmental condition difference indicators. The system identifies different scenario classification results; obtains the working status of the wallet anti-loss device, including device running time, device load rate, device nominal voltage, nominal battery capacity, and battery health; determines the predicted remaining working time for the corresponding scenario classification result based on the working status; determines whether the predicted remaining working time is lower than the preset remaining working time threshold for the corresponding scenario classification result; if it is determined to be lower than the preset remaining working time threshold, a first warning message is issued; obtains the remaining battery power of the wallet anti-loss device; determines whether the remaining battery power is lower than the battery warning threshold for the corresponding scenario classification result; if it is determined to be lower than the battery warning threshold, a second warning message is issued; and determines personalized warning messages for the corresponding scenario classification result based on the first and second warning messages.

[0057] This disclosure can take the form of a computer program product implemented on one or more storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing program code. Computer-readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to: phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transfer medium that can be used to store information accessible by a computing device.

[0058] It should be noted that although the steps of the low battery warning method for a wallet anti-loss device in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps, such as omitting certain steps, combining multiple steps into one step, and / or breaking down a step into multiple steps, should all be considered part of this disclosure.

[0059] It should be understood that this disclosure is not limited to the detailed structure and arrangement of the module for the low battery warning system for a wallet anti-loss device as described in this specification. This disclosure can have other embodiments and can be implemented and performed in various ways. The foregoing variations and modifications fall within the scope of this disclosure. It should be understood that this disclosure, as disclosed and defined in this specification, extends to all alternative combinations of two or more individual features mentioned or apparent in the text and / or drawings. All these different combinations constitute multiple alternative aspects of this disclosure. The embodiments described in this specification illustrate the best known mode for implementing this disclosure and will enable those skilled in the art to utilize this disclosure.

Claims

1. A low battery warning method for a wallet anti-loss device, characterized in that, include: The system acquires user behavior change characteristics and environmental condition difference indicators, including user action intensity and user usage time, and environmental condition difference indicators including WiFi signal strength, ambient temperature, and ambient humidity. The usage scenario description is determined based on the user behavior change characteristics and the environmental condition difference index. The usage scenario description includes indoor stationary state, indoor mobile state, outdoor stationary state, and outdoor mobile state. Different scenario classification results are determined based on the usage scenario description and the environmental condition difference index; The working status of the wallet anti-loss device is obtained, including device running time, device load rate, device nominal voltage, nominal battery capacity, and battery health. Based on the working status, determine the predicted value of the remaining working time corresponding to the scene classification result; Determine whether the predicted value of the remaining working time is lower than the preset remaining working time threshold corresponding to the scene classification result; If the remaining working time is determined to be less than the preset threshold, then a first warning message is issued. Get the remaining battery level of the current card wallet anti-loss device; Determine whether the remaining battery power is lower than the battery warning threshold corresponding to the scenario classification result; If the battery level is determined to be below the aforementioned warning threshold, then a second warning message is issued. Personalized warning information corresponding to the scenario classification result is determined based on the first warning information and the second warning information.

2. The low battery warning method for a wallet anti-loss device according to claim 1, characterized in that, The step of determining the usage scenario description based on the user behavior change characteristics and the environmental condition difference indicators includes: Obtain the acceleration and angular velocity data of the card wallet anti-loss device; The intensity of the user's action is determined based on the angular velocity data. Determine whether the deviation between the user's action intensity and a preset action intensity threshold exceeds a preset deviation threshold; If it is determined that the deviation exceeds the preset threshold, then it is determined whether the WiFi signal strength exceeds the preset signal strength threshold. If the signal strength exceeds the preset threshold, it is determined that the user is in an indoor mobile state. If it is determined that the preset signal strength threshold is not exceeded, then it is determined that the user is in an outdoor mobile state; If it is determined that the preset deviation threshold is not exceeded, then it is determined whether the WiFi signal strength exceeds the preset signal strength threshold. If the signal strength exceeds the preset threshold, it is determined that the user is in a stationary indoor state. If the preset signal strength threshold is not exceeded, it is determined that the user is in a stationary outdoor state.

3. The low battery warning method for a wallet anti-loss device according to claim 1, characterized in that, Following the description of the usage scenario, the following is also included: A logistic regression model is established, with the user behavior change characteristics and the environmental condition difference index as the input of the logistic regression model, and the probability values ​​of different usage scenarios as the output of the logistic regression model. The probability values ​​of different use scenario descriptions are sorted, and the use scenario description corresponding to the maximum value in the sorting result is taken as the current use scenario description.

4. The low battery warning method for a wallet anti-loss device according to claim 1, characterized in that, The step of determining different scenario classification results based on the usage scenario description and the environmental condition difference index includes: The usage scenario descriptions are standardized to generate a standard dataset of usage scenario descriptions; The ambient temperature and ambient humidity are standardized to generate a standard dataset of environmental condition differences. Based on the K-means clustering algorithm, the clustering results are determined according to the standard dataset describing the usage scenario and the standard dataset showing the differences in environmental conditions. Based on the random forest algorithm, feature importance scores are calculated for different clustering results; The feature importance scores are sorted from the maximum to the minimum, and different scene classification results are determined based on the sorting results.

5. The low battery warning method for a wallet anti-loss device according to claim 1, characterized in that, The step of determining the predicted remaining working time value corresponding to the scene classification result based on the working status includes: The aging factor is determined based on the running time and the load rate; Determine the temperature influence factor corresponding to the scene classification result based on the ambient temperature; The predicted power consumption value corresponding to the scenario classification result is determined based on the aging factor and the temperature influence factor. Determine the actual battery capacity based on the nominal battery capacity; The remaining working time prediction value corresponding to the scenario classification result is determined based on the actual battery capacity and the power consumption prediction value.

6. The low battery warning method for a wallet anti-loss device according to claim 5, characterized in that, Determining the actual battery capacity based on the nominal battery capacity includes: Obtain the battery cycle count and battery degradation factor; The battery health is updated based on the battery cycle count and the battery degradation factor. The updated battery health is multiplied by the nominal battery capacity, and the result is used as the actual battery capacity.

7. The low battery warning method for a wallet anti-loss device according to claim 1, characterized in that, Determining the power warning threshold corresponding to the scenario classification result includes: Obtain the weight factors and initial battery warning threshold from the corresponding scenario classification results; The initial power warning threshold is multiplied by the weight factor corresponding to the scenario classification result, and the multiplication result is used as the power warning threshold corresponding to the scenario classification result.

8. The low battery warning method for a wallet anti-loss device according to claim 1, characterized in that, The step of determining the personalized warning information corresponding to the scene classification result based on the first warning information and the second warning information includes: Retrieve warning content templates from the preset information database that match the current scene classification results; Personalized warning information corresponding to the scenario classification result is determined based on the warning content template, the first warning information, and the second warning information.

9. A low battery warning system for a wallet anti-loss device, characterized in that, include: The first acquisition module is used to acquire user behavior change characteristics and environmental condition difference indicators. The user behavior change characteristics include user action intensity and user usage time. The environmental condition difference indicators include WiFi signal strength, ambient temperature and ambient humidity. The first determining module is used to determine the usage scenario description based on the user behavior change characteristics and the environmental condition difference index. The usage scenario description includes indoor stationary state, indoor mobile state, outdoor stationary state, and outdoor mobile state. The second determining module is used to determine different scenario classification results based on the usage scenario description and the environmental condition difference index; The second acquisition module is used to acquire the working status of the wallet anti-loss device, which includes device running time, device load rate, device nominal voltage, nominal battery capacity, and battery health. The third determining module is used to determine the predicted value of the remaining working time corresponding to the scene classification result based on the working status; The judgment module is used to determine whether the predicted value of the remaining working time is lower than the preset remaining working time threshold corresponding to the scene classification result; The fourth determining module is used to determine the first warning information if the remaining working time is determined to be less than the preset threshold. The third acquisition module is used to acquire the remaining battery power of the current card wallet anti-loss device; The fifth determining module is used to determine whether the remaining battery power is lower than the battery warning threshold corresponding to the scenario classification result; The sixth determining module is used to determine the second warning information if it is determined that the battery level is below the warning threshold. The seventh determining module is used to determine personalized warning information corresponding to the scenario classification result based on the first warning information and the second warning information.

Images