Multi-power module intelligent management method and related device

Abstract

The application provides a multi-power module intelligent management method and related device, the method comprises the following steps: obtaining original working data of m power modules in a historical period, and spatiotemporal expansion data of a target user; constructing a power consumption demand feature set according to the original working data and the spatiotemporal expansion data; performing clustering analysis on n characteristic vectors and n time period labels to obtain k reference clustering centers; obtaining target scene demand and real-time trigger data of the target user in a current period; determining a target clustering center corresponding to the target scene demand in the k reference clustering centers; screening the m power modules based on the target clustering center to obtain a target power module; and controlling the target power module to perform a prompt operation according to the real-time trigger data to prompt the target user to carry the target power module. The multi-source data is fused to cluster and match the scene, the power module is accurately prompted, and the scene adaptability of the multi-power module is improved.

Description

Technical Field

[0001] This application relates to the field of power module management technology, and in particular to a method and related apparatus for intelligent management of multiple power modules. Background Technology

[0002] Currently, the management of multiple power modules relies heavily on filtering based on a single power or capacity dimension, without combining user behavior during different time periods and spatiotemporal scene characteristics for demand modeling. This results in low adaptability of recommended power modules to actual power usage scenarios, failing to meet the differentiated power needs of different scenarios such as commuting and outdoor activities.

[0003] Meanwhile, the existing power module reminder mechanism usually relies solely on user-initiated queries and lacks multi-condition verification, making it prone to false or missed triggers. This makes it difficult to provide accurate reminders at critical points when users need to carry the power supply, thus affecting the user experience.

[0004] Therefore, improving the scenario adaptability of multi-power module management is an urgent issue to be addressed. Summary of the Invention

[0005] This application provides a method and related device for intelligent management of multiple power modules. By integrating historical working data and spatiotemporal extended data to construct a demand feature vector, and combining cluster analysis to achieve scenario-based demand matching, a multi-condition triggering mechanism is used to provide precise prompts to the target power module, thereby improving the scenario adaptability of multi-power module management.

[0006] In a first aspect, embodiments of this application provide a method for intelligent management of multiple power supply modules, the method comprising: Obtain the raw operating data of m power modules within a historical time period, as well as the spatiotemporal extended data of the target user; m is an integer greater than 1. A power demand feature set is constructed based on the original working data and the spatiotemporal extended data; the power demand feature set includes n feature vectors and n time period labels; each feature vector corresponds to a time period label; n is an integer greater than 1; Cluster analysis is performed on the n feature vectors and the n time period labels to obtain k reference cluster centers; each reference cluster center includes at least one time period label; k is a positive integer less than or equal to n; Obtain the target scenario requirements and real-time trigger data of the target user within the current time period; Determine the target cluster center corresponding to the target scenario requirement among the k reference cluster centers; Based on the target cluster center, the m power modules are screened to obtain the target power modules; Based on the real-time trigger data, the target power module is controlled to perform a prompting operation to prompt the target user to carry the target power module.

[0007] Secondly, embodiments of this application provide a multi-power module intelligent management device, the device comprising a first acquisition module, a construction module, a clustering module, a second acquisition module, a determination module, a filtering module, and a control module, wherein: The first acquisition module is used to acquire the original working data corresponding to m power modules within a historical time period, as well as the spatiotemporal extended data corresponding to the target user; m is an integer greater than 1. The construction module is used to construct an electricity demand feature set based on the original working data and the spatiotemporal extended data; the electricity demand feature set includes n feature vectors and n time period labels; each feature vector corresponds to a time period label; n is an integer greater than 1; The clustering module is used to perform clustering analysis on the n feature vectors and the n time period labels to obtain k reference cluster centers; each reference cluster center includes at least one time period label; k is a positive integer less than or equal to n; The second acquisition module is used to acquire the target user's target scenario needs and real-time trigger data within the current time period; The determining module is used to determine the target cluster center corresponding to the target scenario requirement among the k reference cluster centers; The filtering module is used to filter the m power modules based on the target cluster center to obtain the target power modules; The control module is used to control the target power module to perform a prompting operation based on the real-time triggering data, so as to prompt the target user to carry the target power module.

[0008] Thirdly, embodiments of this application provide an electronic device, including a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for performing steps in any method of the first aspect of this application.

[0009] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in any method of the first aspect of this application.

[0010] Fifthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in any method of the first aspect of this application. The computer program product may be a software installation package.

[0011] By implementing the embodiments of this application, a demand feature vector can be constructed by integrating historical working data and spatiotemporal extended data, and scenario-based demand matching can be achieved by combining cluster analysis. Then, precise prompts can be given to the target power module through a multi-condition triggering mechanism, thereby improving the scenario adaptability of multi-power module management. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a system architecture diagram of a mobile power bank intelligent management system provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of a power module provided in an embodiment of this application; Figure 3 This is an application scenario diagram of a mobile power bank intelligent management system provided in an embodiment of this application; Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application; Figure 5 This is a flowchart illustrating an intelligent management method for multiple power supply modules provided in an embodiment of this application; Figure 6 This is a schematic diagram of a process for determining target cluster centers provided in an embodiment of this application; Figure 7 This is a flowchart illustrating an example of performing a prompting operation provided in an embodiment of this application; Figure 8 This is a functional module block diagram of a multi-power module intelligent management device provided in an embodiment of this application. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0015] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0016] It should be understood that the term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this document indicates that the preceding and following related objects are in an "or" relationship. In the embodiments of this application, "multiple" refers to two or more.

[0017] In the embodiments of this application, "at least one item" or its similar expression refers to any combination of these items, including any combination of a single item or a plurality of items. "One or more" means one or more, while "multiple" means two or more. For example, "at least one item" of a, b, or c can represent the following seven cases: a, b, c; a and b; a and c; b and c; a, b, and c. Each of a, b, and c can be an element or a set containing one or more elements.

[0018] In this application, the term "connection" refers to various connection methods, such as direct connection or indirect connection, to achieve communication between devices. This application does not impose any limitations on this.

[0019] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0020] Currently, the management of multiple power modules relies heavily on filtering based on a single power or capacity dimension, without combining user behavior during different time periods and spatiotemporal scene characteristics for demand modeling. This results in low adaptability of recommended power modules to actual power usage scenarios, failing to meet the differentiated power needs of different scenarios such as commuting and outdoor activities.

[0021] Meanwhile, the existing power module reminder mechanism usually relies solely on user-initiated queries and lacks multi-condition verification, making it prone to false or missed triggers. This makes it difficult to provide accurate reminders at critical points when users need to carry the power supply, thus affecting the user experience.

[0022] Therefore, improving the scenario adaptability of multi-power module management is an urgent issue to be addressed.

[0023] To address the aforementioned issues, this application provides an intelligent management method and related apparatus for multiple power modules. The method involves acquiring raw operating data for m power modules within a historical time period, and spatiotemporal extended data for a target user; where m is an integer greater than 1. A power demand feature set is constructed based on the raw operating data and the spatiotemporal extended data. This feature set includes n feature vectors and n time period labels; each feature vector corresponds to a time period label; n is an integer greater than 1. Cluster analysis is performed on the n feature vectors and n time period labels to obtain k reference cluster centers; each reference cluster center includes at least one time period label; k is a positive integer less than or equal to n. The method also involves acquiring the target scenario requirements and real-time trigger data for the target user within the current time period; determining the target cluster center corresponding to the target scenario requirements among the k reference cluster centers; filtering the m power modules based on the target cluster center to obtain the target power module; and controlling the target power module to perform a prompting operation based on the real-time trigger data to prompt the target user to carry the target power module.

[0024] It is evident that by integrating historical working data with spatiotemporal extended data to construct a demand feature vector, combining cluster analysis to achieve scenario-based demand matching, and then using a multi-condition triggering mechanism to provide precise prompts to the target power module, the scenario adaptability of multi-power module management is improved.

[0025] For easier understanding, please refer to Figure 1 , Figure 1 This is a system architecture diagram of a mobile power bank intelligent management system provided in an embodiment of this application. The mobile power bank intelligent management system includes a user terminal layer, a communication layer, and a cloud service layer.

[0026] The user terminal layer serves as the user interaction entry point, specifically including user terminals such as smartphones and tablets. The user terminal has a built-in management APP with data collection, scene input, and visualization display functions. It can collect the spatiotemporal extended data (location, time, scene tags) of the target user, receive the target scene requirements actively input by the target user, and display the hardware parameters, matching degree, and prompt information of the power module. It also supports the target user to configure personalized prompt requirements (vibration / sound mode, intensity).

[0027] The communication layer serves as a data transmission bridge, employing a dual-mode architecture of Bluetooth Low Energy (BLE) communication and mobile network communication. BLE communication is used for short-range data interaction between the user terminal and the power module, enabling the issuance of reminder commands and the uploading of hardware parameters and status data of the power module. Mobile network communication is used for remote data interaction between the user terminal and the cloud service layer, enabling the synchronization and updating of historical power consumption data.

[0028] The cloud service layer can deploy a data storage module, a clustering analysis module, and a scenario matching module. The data storage module is used to store historical electricity consumption data, user spatiotemporal expansion data, and personalized configuration information. The clustering analysis module uses the k-means algorithm to cluster the electricity demand feature set and generate cluster centers. The scenario matching module matches the corresponding target cluster center according to the current target scenario requirements in order to complete the selection of the best power supply module.

[0029] It is evident that by constructing a three-layer collaborative architecture consisting of a user terminal layer, a communication layer, and a cloud service layer, scenario-based intelligent matching and accurate prompts for multiple power modules are achieved, effectively improving the scenario adaptability and user convenience of modular mobile power management.

[0030] For easier understanding, please refer to Figure 2 , Figure 2 This is a schematic diagram of a power module provided in an embodiment of this application. The power module is an independently operating mobile power supply, including a hardware circuit unit and a function execution unit. The hardware circuit unit is responsible for the power supply and data transmission of the power module, including a battery cell, a power management circuit, a self-test MCU module, and a Bluetooth communication module. It can realize real-time detection of core parameters such as battery power, health, and temperature, as well as bidirectional data interaction with user terminals and cloud service layers. The function execution unit is responsible for responding to prompts and includes a sensor component, a vibration component, and a sound component. It can output vibration prompts or sound prompts of different intensities according to the instructions of the self-test MCU module, and at the same time collect the picking state of the module through an accelerometer to provide data support for trigger condition verification.

[0031] For easier understanding, please refer to Figure 3 , Figure 3This is an application scenario diagram of a mobile power intelligent management system provided in an embodiment of this application. It includes m power modules that provide raw operating data to the system, including parameters such as rated capacity, remaining power, battery health, charging / discharging status, and operating temperature, providing basic hardware data for subsequent module selection. User terminals provide spatiotemporal extended data to the system, including historical usage periods, usage locations, scene tags, and device types, used to construct user power consumption behavior characteristics. Target users directly input target scenario requirements and real-time trigger data into the system, such as manually selected travel scenarios (commuting / outdoors), clicked recommendation buttons, and Bluetooth connection status, used to trigger scenario matching and prompting processes. The mobile power intelligent management system receives raw operating data, spatiotemporal extended data, target scenario requirements, and real-time trigger data, and then executes core algorithm steps such as power demand feature set construction, cluster analysis, target scenario matching, and power module selection to ultimately determine the target power module suitable for the current scenario. Target power module: The optimal compatible module selected by the system based on user scenario requirements and module hardware parameters. It will then receive prompts from the system and perform vibration / sound prompts to guide the target user to carry it.

[0032] The following is combined with Figure 4 The electronic devices in the embodiments of this application will be described. Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 4 As shown, the electronic device includes one or more processors, a memory, a communication interface, and one or more programs. The processor is connected to the memory and the communication interface via an internal communication bus.

[0033] The processor can be used for: Obtain the raw operating data of m power modules within a historical time period, as well as the spatiotemporal extended data of the target user; m is an integer greater than 1. A power demand feature set is constructed based on the original working data and the spatiotemporal extended data; the power demand feature set includes n feature vectors and n time period labels; each feature vector corresponds to a time period label; n is an integer greater than 1; Cluster analysis is performed on the n feature vectors and the n time period labels to obtain k reference cluster centers; each reference cluster center includes at least one time period label; k is a positive integer less than or equal to n; Obtain the target scenario requirements and real-time trigger data of the target user within the current time period; Determine the target cluster center corresponding to the target scenario requirement among the k reference cluster centers; Based on the target cluster center, the m power modules are screened to obtain the target power modules; Based on the real-time trigger data, the target power module is controlled to perform a prompting operation to prompt the target user to carry the target power module.

[0034] The one or more programs are stored in the aforementioned memory and configured to be executed by the aforementioned processor, and the one or more programs include instructions for performing any step in the above method embodiments.

[0035] The processor can be a central processing unit (CPU), a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, cells, and circuits described in conjunction with the disclosure of this application. The processor can also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc. The communication unit can be a communication interface, transceiver, transceiver circuit, etc., and the storage unit can be a memory.

[0036] The memory can be volatile or non-volatile, or a combination of both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0037] It is understood that the electronic device may include more or fewer structural elements than those shown in the block diagram above, such as a power module, physical buttons, a Wi-Fi module, a speaker, a Bluetooth module, sensors, a display module, etc., without limitation. It is understood that the electronic device may incorporate elements such as... Figure 1 The system architecture described above.

[0038] After understanding the software and hardware architecture of this application, the following will be combined with... Figure 5 This application describes an intelligent management method for multiple power supply modules. Figure 5 This is a flowchart illustrating a multi-power module intelligent management method provided in an embodiment of this application, specifically including the following steps: Step S501: Obtain the original working data corresponding to m power modules within the historical time period, as well as the spatiotemporal extended data corresponding to the target user.

[0039] Where m is an integer greater than 1, each of the m power modules has a built-in self-test MCU module and sensor components. Through the self-test MCU module and sensor components built into each power module, raw operating data of the m power modules over a historical period is collected. This raw operating data includes, but is not limited to: the rated capacity, real-time remaining power, number of charge / discharge cycles, charge / discharge power, duration of a single charge / discharge cycle, battery health, operating temperature, and abnormal status records (such as over-temperature alarms and short-circuit warnings) of each power module. The data is collected in real time during operation by the power modules and periodically uploaded to user terminals (such as mobile phones) or cloud servers for storage via Bluetooth communication.

[0040] Then, by using the user terminal's location module, time module, and application logs, spatiotemporal extended data corresponding to the target user is collected. This spatiotemporal extended data includes, but is not limited to: the user's historical time interval for using the power module (e.g., weekdays 7:00-9:00, weekends 14:00-18:00), the type of location used (e.g., commuting, outdoor camping, office), the usage scenario tag (e.g., short trips, long trips, emergency backup), and the type of electrical device used during the same time period (e.g., mobile phone, tablet, laptop). During the collection process, the location data is anonymized, retaining only the location type feature to avoid leakage of user privacy.

[0041] Finally, the collected raw working data and spatiotemporal extended data are cleaned to remove invalid data (such as abnormal values ​​caused by sensor failures and blank records of lost positioning signals), and aligned according to timestamps to ensure that the power supply working data and user spatiotemporal data in the same time interval correspond one-to-one, providing a high-quality data foundation for the subsequent construction of power demand feature sets.

[0042] Step S502: Construct an electricity demand feature set based on the original working data and the spatiotemporal extended data.

[0043] The electricity demand feature set includes n feature vectors and n time period labels; each feature vector corresponds to a time period label; n is an integer greater than 1.

[0044] The specific steps of constructing the electricity demand feature set based on the original working data and the spatiotemporal extended data include: A1. Normalize the original working data and the spatiotemporal extended data respectively to obtain the first feature data and the second feature data; A2. Integrate the first feature data and the second feature data to obtain the third feature data; A3. Divide the historical time period into n time period windows according to a preset duration; A4. Based on the n time period windows, the third feature data is divided to obtain n fourth feature data; A5. Construct the n feature vectors based on the n fourth feature data; A6. Generate the n time period labels based on the n time period windows.

[0045] In a specific embodiment, firstly, for numerical parameters in the original working data (such as rated capacity, charge / discharge power, operating temperature, and battery health), a preset min-max normalization algorithm is used to map them to the [0, 1] interval to eliminate the influence of different units on feature weights. The normalization formula is as follows: .

[0046] in, The parameter represents the normalization parameter; Represents the original value of the parameter; This indicates the minimum value of the parameter in historical data; This indicates the maximum value of the parameter in historical data.

[0047] For categorical parameters (such as abnormal status records) in the original working data, one-hot encoding is used to convert them into binary vectors; for categorical parameters such as time interval, location type, and scene label in the spatiotemporal extended data, one-hot encoding is also used; for numerical parameters (such as usage duration), min-max normalization is used. The processed data are denoted as the first feature data and the second feature data, respectively.

[0048] Then, following the timestamp alignment principle, the first feature data (power module operating characteristics) and the second feature data (user spatiotemporal characteristics) within the same time interval are concatenated dimensionally to form a high-dimensional feature matrix that integrates the power supply operating status and user usage scenarios, denoted as the third feature data. During the concatenation process, invalid data with mismatched timestamps are removed to ensure that each piece of third feature data contains complete information on the correlation between power supply operation and user scenarios.

[0049] Next, a preset duration is set according to the time pattern of user electricity consumption behavior. The preset duration can be configured as 1 hour, 2 hours, or 1 natural time period (such as morning peak 7:00-9:00, evening peak 18:00-20:00). According to the preset duration, the continuous historical time period is divided into n non-overlapping time period windows. Each time period window corresponds to an independent time interval label. For example, the daily 7:00-9:00 of the past 7 days can be divided into 7 time period windows, or divided into 7 time period windows according to natural days. No specific limitation is made here.

[0050] Then, extract the feature subsets of the timestamps in the third feature data that belong to each time period window. Each time period window corresponds to a feature subset, and these n feature subsets are recorded as n fourth feature data. If there is no corresponding feature data in a certain time period window, the average of the historical data of the same period in that time period window is used to fill it, or it is marked as "no data" for subsequent processing.

[0051] Next, dimensionality reduction is performed on each fourth feature data point, and the resulting feature matrix is ​​converted into a one-dimensional vector. Each fourth feature data point corresponds to a one-dimensional feature vector, ultimately yielding n feature vectors that correspond one-to-one with the n time-period windows. These feature vectors are shown below: .

[0052] in, Indicates the first 1 eigenvector; Indicates the first Power usage rate for each time window; Indicates the first Average charge / discharge power over a time window; Indicates the first Travel displacement within a time window; Indicates the first The frequency of module usage within each time window; Indicates the first The average temperature of the module in each time window.

[0053] Finally, n time period labels are generated according to the time attributes and scene attributes of n time period windows. The label format is "time interval-scene type", such as "weekday 7:00-9:00-commuting" and "weekend 14:00-18:00-outdoor camping". If a certain time period window does not have a clear scene attribute, scene clustering and labeling are performed based on the characteristics such as the type of electrical equipment and charging and discharging power in that time period window to ensure that each time period label can represent the user's electricity consumption scene in the corresponding time period.

[0054] It is evident that by normalizing and integrating the raw working data of the power module and the spatiotemporal extended data of the target user, dividing the data into time periods, and constructing feature vectors, the standardized, structured, and scenario-based representation of multi-source heterogeneous data has been achieved, providing a unified and high-quality feature foundation for subsequent cluster analysis and scenario matching.

[0055] Step S503: Perform cluster analysis on the n feature vectors and the n time period labels to obtain k reference cluster centers.

[0056] Each reference cluster center includes at least one time period label; k is a positive integer less than or equal to n.

[0057] The specific steps for performing cluster analysis on the n feature vectors and the n time period labels to obtain k reference cluster centers include: B1. Randomly select k feature vectors from the n feature vectors as the first cluster centers to obtain k first cluster centers; B2. Perform an iterative update step on the k first cluster centers until the position change of each cluster center is less than the preset change threshold, then terminate the iteration and obtain the k reference cluster centers. The iterative update steps are as follows: B21. Calculate the Euclidean distance between each of the n feature vectors and the k first cluster centers, and assign it to the cluster corresponding to the nearest first cluster center to obtain k first clusters; B22. Assign each of the n time period labels to the cluster corresponding to its associated feature vector; B23. According to the preset cluster center calculation formula, calculate for each of the k first clusters to obtain k second cluster centers.

[0058] In a specific embodiment, firstly, k feature vectors are randomly selected from n feature vectors as the first cluster centers, resulting in k first cluster centers. The value of k can be determined based on the elbow method, that is, by calculating the sum of squared clustering errors (SSE) corresponding to different k values, the k value at which the SSE curve shows a clear inflection point is selected as the number of clusters to ensure the optimal clustering effect, and k is a positive integer less than or equal to n.

[0059] Then, perform iterative update steps on the k first cluster centers until the position change of each cluster center is less than the preset change threshold (the preset change threshold can be configured to 0.001~0.01 to control the clustering convergence accuracy), then terminate the iteration and obtain k reference cluster centers.

[0060] The iterative update steps are as follows: First, calculate the Euclidean distance between each of the n feature vectors and the k first cluster centers. Then, based on the calculated Euclidean distance, assign each feature vector to the cluster corresponding to the nearest first cluster center, resulting in k first clusters, each containing several feature vectors.

[0061] Then, each of the n time period labels is assigned to the cluster corresponding to its associated feature vector. Since each time period label corresponds one-to-one with a feature vector, the cluster to which the feature vector belongs is directly taken as the cluster to which its associated time period label belongs, so that each first cluster contains both the feature vector and the corresponding time period label, realizing the intra-cluster association between the feature vector and the time period label.

[0062] Finally, based on the preset cluster center calculation formula, the k second cluster centers are calculated for each of the k first clusters. The cluster center calculation formula is as follows: .

[0063] in, Represents the kth second cluster center among the k second cluster centers. A second cluster center; Indicates the k first clusters of the first cluster. The number of feature vectors within the first cluster; For the first cluster, the first 1 eigenvector.

[0064] It should be noted that after the cluster centers are calculated, the k second cluster centers are used as new cluster centers, and the process returns to step B21 to continue iterative updates until the convergence condition is met.

[0065] As can be seen, by iteratively updating the cluster centers, the feature vectors of electricity demand are clustered in a scenario-based manner, generating stable reference cluster centers, which provides reliable data support for the rapid matching of target scenario requirements and the selection of power modules.

[0066] Step S504: Obtain the target scenario requirements and real-time trigger data of the target user within the current time period.

[0067] Specifically, the acquisition of target scenario requirements includes active input and passive identification. Active input involves the target user manually selecting their planned travel scenario via their terminal, such as "commuting," "camping," or "business trip," and this manually selected scenario is directly identified as the target scenario requirement. Passive identification involves scene matching using real-time location information, time information, and historical behavior data from the user's terminal. Specifically, it extracts the time attributes of the current time period (e.g., weekday 7:00-9:00) and the user's current location type (e.g., subway station, highway service area), compares them with time period labels representing electricity demand characteristics, and identifies the scenario corresponding to the time period label with the highest matching degree as the target scenario requirement. It should be noted that if the scenario actively input by the target user differs from the passively identified scenario, the scenario actively input by the target user will be used as the final target scenario requirement.

[0068] Then, the system acquires the target user's actions on the user terminal, such as clicking the "Power Recommendation" button or checking the power module status, and generates a click recommendation identifier. The power module's self-test MCU module collects the module's physical status, such as whether it has been picked up or is idle, and generates a module pick-up identifier. The power module's built-in Bluetooth module collects the connection status between the user terminal and the power module, such as whether Bluetooth pairing has been established and whether the connection duration has exceeded a preset threshold, and generates a Bluetooth connection identifier. The click recommendation identifier, module pick-up identifier, and Bluetooth connection identifier are integrated to obtain real-time trigger data. Each trigger identifier has a value of either 1 or 0; a value of 1 indicates that the corresponding trigger condition is met, and a value of 0 indicates that the corresponding trigger condition is not met.

[0069] Step S505: Determine the target cluster center corresponding to the target scenario requirement among the k reference cluster centers.

[0070] For easier understanding, please refer to Figure 6 , Figure 6 This is a flowchart illustrating a process for determining a target cluster center according to an embodiment of this application. The specific steps for determining the target cluster center corresponding to the target scenario requirement among the k reference cluster centers include: C1. Analyze at least one time period label corresponding to each of the k reference cluster centers to obtain k reference scenario requirements; C2. Obtain the reference scenario requirement that matches the target scenario requirement among the k reference scenario requirements, and use its corresponding reference cluster center as the target cluster center.

[0071] In a specific embodiment, firstly, the scene attribute features (such as "commuting", "outdoor camping", "business trip" etc.) of all time period labels within each reference cluster center are extracted, and the frequency of each scene attribute in the time period labels within the cluster is counted; the scene attribute with the highest frequency is determined as the reference scene requirement corresponding to the reference cluster center; if there are multiple scene attributes with the same frequency and the highest value, the cosine similarity between the feature vector of the reference cluster center and the typical feature vector of each scene attribute is calculated, and the scene attribute with the highest similarity is selected as the reference scene requirement.

[0072] Then, a preset keyword matching algorithm can be used to calculate the matching degree between the target scenario requirement and the k reference scenario requirements, and obtain the reference scenario requirement with the highest matching degree with the target scenario requirement, and determine its corresponding reference cluster center as the target cluster center.

[0073] As can be seen, by associating cluster centers with time period labels and mapping them to reference scenario requirements, a rapid match between target scenario requirements and historical clustering features is achieved, ensuring the scenario adaptability and accuracy of subsequent power module selection.

[0074] Step S506: Based on the target cluster center, the m power modules are screened to obtain the target power modules.

[0075] The specific steps for filtering the m power modules based on the target cluster center to obtain the target power module include: D1. Obtain the set of m hardware parameters corresponding to the m power modules; D2. Construct m parameter vectors based on the m hardware parameter sets; D3. Calculate the cosine similarity between the target cluster center and each of the m parameter vectors to obtain the m cosine similarities; D4. Select the power supply module corresponding to the largest cosine similarity among the m cosine similarities as the target power supply module.

[0076] In a specific embodiment, firstly, the hardware parameter information is read by the self-test MCU module built into each power module, and a hardware parameter set is generated based on this information. The hardware parameter set includes, but is not limited to, the rated capacity, weight, and charging power of the power module; specific limitations are not specified here. Then, the numerical parameters in the hardware parameter set of each power module are normalized using a min-max method to eliminate dimensional differences between parameters. The normalized parameters are then concatenated in a fixed-dimensional order to construct a parameter vector corresponding to each power module. ,in, Indicates the first The normalized value of the rated capacity of each power module; Indicates the first The normalized value of the module weight of each power module; Indicates the first The normalized value of the module charging power of each power module.

[0077] Next, according to the preset cosine similarity calculation formula, the cosine similarity between the target cluster center and each of the m parameter vectors is calculated, resulting in m cosine similarities. The cosine similarity calculation formula is as follows: .

[0078] in, Indicates the first The cosine similarity is calculated, with a value ranging from [0, 1]. The larger the value, the higher the compatibility between the power module and the target scenario requirements. Indicate the target cluster center; Indicates the modulus of the target cluster center; Indicates the first The magnitude of a parameter vector.

[0079] Then, the power module with the highest cosine similarity among the m cosine similarities is selected as the target power module. If multiple power modules have the same cosine similarity and all are the maximum value, the historical usage frequency of these power modules is further compared, and the power module with the highest usage frequency in the same scenario is selected as the final target power module.

[0080] As can be seen, by constructing the hardware parameter vector of the power module and matching it with the cosine similarity of the target cluster center, the optimal power module selection based on scenario requirements is achieved, which effectively improves the scenario adaptability of the module recommendation and the user experience.

[0081] Step S507: Based on the real-time trigger data, control the target power module to perform a prompting operation to prompt the target user to carry the target power module.

[0082] The real-time trigger data includes a click recommendation indicator, a module pick-up indicator, and a Bluetooth connection indicator. The specific steps for controlling the target power module to perform a prompt operation based on the real-time trigger data include: E1. Obtain the target time period label corresponding to the target cluster center among the n time period labels; E2. If at least one of the click recommendation icon, the module pick-up icon, and the Bluetooth connection icon is 1, and the current time period matches the time interval corresponding to the target time period tag, the prompt operation is executed.

[0083] In a specific embodiment, firstly, all time period labels associated with the cluster of the target cluster center are extracted. Based on the attribute characteristics of the target scenario requirements (such as time interval and scenario type), the time period label with the highest matching degree with the target scenario requirements is selected as the target time period label. The target time period label contains clear time interval information (such as "weekday 7:00-9:00") and scenario attribute information (such as "commuting"), which is used to verify whether the current time period meets the scenario triggering conditions.

[0084] Then, a logical decision is made based on the real-time trigger data, and the logical decision formula is as follows: .

[0085] in, This indicates the logical judgment result (1 indicates that the scene trigger condition is met, and 0 indicates that it is not met). This indicates that the recommendation icon has been clicked (1 indicates that the target user clicked the recommendation button on the user's terminal, and 0 indicates that it was not clicked). The module pick-up indicator (1 indicates that the power module has been picked up, 0 indicates that it has not been detected); This indicates a Bluetooth connection identifier (1 indicates that the power module and the user terminal have successfully paired via Bluetooth, and 0 indicates that they have not paired). This indicates that the current time period belongs to the time interval corresponding to the target time period label, meaning that the current time period matches the time interval corresponding to the target time period label. Indicates the current time period; This indicates the time interval corresponding to the target time period label.

[0086] Specifically, if at least one of the recommended icon, module pick-up icon, and Bluetooth connection icon is 1, and the current time period matches the time interval corresponding to the target time period tag (i.e., the logical judgment result is 1), then the prompt operation is executed; if the logical judgment result is 0, then no operation is executed, thereby avoiding accidental triggering outside the target time period and ensuring the accuracy of the prompt operation.

[0087] It is evident that by combining user interaction, module status, communication connection, and time period matching into a multi-condition triggering mechanism, precise triggering of prompts is achieved, effectively avoiding false prompts in non-target scenarios and improving user convenience and experience.

[0088] For easier understanding, please refer to Figure 7 , Figure 7 This is a flowchart illustrating an example of performing a prompt operation according to an embodiment of this application. The specific steps for performing the prompt operation include: F1. Obtain the target user's target prompting requirements; the target prompting requirements include at least one of the following: vibration prompting requirements, sound prompting requirements; F2. Control the target power module to perform the prompt operation according to the target prompt requirements.

[0089] In a specific embodiment, firstly, the target user's target prompting requirements are obtained. These target prompting requirements include at least one of the following: vibration prompting requirements and sound prompting requirements. The methods for obtaining these target prompting requirements are divided into proactive configuration and scene default. Proactive configuration: The target user pre-sets their preferred prompting method and intensity through their user terminal, for example, selecting "low-intensity vibration prompt only," "medium-intensity sound prompt only," or "high-intensity combination of vibration and sound prompt." Scene default: If the target user does not proactively configure, a default prompting method is automatically matched according to the target scene requirements. For example, in a "commuting scenario," the default is low-intensity vibration prompt (to avoid noise interference in public places), and in an "outdoor camping scenario," the default is high-volume sound prompt (for easy identification in noisy environments). No specific limitations are made here.

[0090] It should be noted that the system can prioritize reading the prompts actively configured by the target user, and if no active configuration is made, it can use the default prompts for the scenario. Then, it generates corresponding prompt instructions according to the target prompt requirements and sends them to the self-test MCU module of the target power module to control the target power module to perform the corresponding prompt operations.

[0091] It is evident that by supporting user-configured or scene-default vibration / sound prompts, the system achieves personalized and scenario-based adaptation of prompt methods, satisfying the usage preferences of different users while improving the scenario adaptability and user perception of prompt operations.

[0092] The above primarily describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the electronic device includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0093] This application embodiment can divide the electronic device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0094] When dividing each function into modules according to its corresponding function. Figure 8 This is a functional block diagram of a multi-power module intelligent management device 800 provided in an embodiment of this application. The multi-power module intelligent management device 800 includes a first acquisition module 810, a construction module 820, a clustering module 830, a second acquisition module 840, a determination module 850, a filtering module 860, and a control module 870, wherein: The first acquisition module 810 is used to acquire the original working data corresponding to m power modules within a historical time period, as well as the spatiotemporal extended data corresponding to the target user; m is an integer greater than 1. The construction module 820 is used to construct an electricity demand feature set based on the original working data and the spatiotemporal extended data; the electricity demand feature set includes n feature vectors and n time period labels; each feature vector corresponds to a time period label; n is an integer greater than 1; The clustering module 830 is used to perform clustering analysis on the n feature vectors and the n time period labels to obtain k reference cluster centers; each reference cluster center includes at least one time period label; k is a positive integer less than or equal to n; The second acquisition module 840 is used to acquire the target user's target scenario needs and real-time trigger data within the current time period; The determining module 850 is used to determine the target cluster center corresponding to the target scenario requirement among the k reference cluster centers; The filtering module 860 is used to filter the m power modules based on the target cluster center to obtain the target power modules; The control module 870 is used to control the target power module to perform a prompting operation based on the real-time triggering data, so as to prompt the target user to carry the target power module.

[0095] Optionally, in constructing the electricity demand feature set based on the original working data and the spatiotemporal extended data, the construction module 820 is specifically used for: The original working data and the spatiotemporal extended data are normalized respectively to obtain the first feature data and the second feature data. The first feature data and the second feature data are integrated to obtain the third feature data; The historical time period is divided into n time period windows according to a preset duration; Based on the n time period windows, the third feature data is divided to obtain n fourth feature data; Construct the n feature vectors based on the n fourth feature data; The n time period labels are generated based on the n time period windows.

[0096] Optionally, in the process of performing cluster analysis on the n feature vectors and the n time period labels to obtain k reference cluster centers, the clustering module 830 is specifically used for: From the n feature vectors, k feature vectors are randomly selected as the first cluster centers to obtain k first cluster centers; An iterative update step is performed on the k first cluster centers until the position change of each cluster center is less than a preset change threshold, then the iteration is terminated, and the k reference cluster centers are obtained. The iterative update steps are as follows: Calculate the Euclidean distance between each of the n feature vectors and the k first cluster centers, and assign it to the cluster corresponding to the nearest first cluster center to obtain k first clusters; Each of the n time period labels is assigned to the cluster corresponding to its associated feature vector; According to the preset cluster center calculation formula, the k first clusters are calculated for each of the k first clusters to obtain k second cluster centers.

[0097] Optionally, in determining the target cluster center corresponding to the target scenario requirement among the k reference cluster centers, the determining module 850 is specifically used for: Analyze at least one time period label corresponding to each of the k reference cluster centers to obtain k reference scenario requirements; Obtain the reference scenario requirement that matches the target scenario requirement among the k reference scenario requirements, and use its corresponding reference cluster center as the target cluster center.

[0098] Optionally, in the step of filtering the m power modules based on the target cluster center to obtain the target power module, the filtering module 860 is specifically used for: Obtain the set of m hardware parameters corresponding to the m power modules; Construct m parameter vectors based on the m hardware parameter sets; Calculate the cosine similarity between the target cluster center and each of the m parameter vectors to obtain m cosine similarities; The power module corresponding to the largest cosine similarity among the m cosine similarities is selected as the target power module.

[0099] Optionally, the real-time trigger data includes a click recommendation indicator, a module pick-up indicator, and a Bluetooth connection indicator. In controlling the target power module to perform the prompt operation based on the real-time trigger data, the control module 870 is specifically used for: Obtain the target time period label corresponding to the target cluster center from among n time period labels; If at least one of the click recommendation icon, the module pick-up icon, and the Bluetooth connection icon is 1, and the current time period matches the time interval corresponding to the target time period tag, the prompt operation is executed.

[0100] Optionally, in performing the prompting operation, the control module 870 is further specifically configured to: Obtain the target user's target prompting requirements; the target prompting requirements include at least one of the following: vibration prompting requirements and sound prompting requirements; The target power module is controlled to perform the prompt operation according to the target prompt requirement.

[0101] It is evident that by integrating historical working data with spatiotemporal extended data to construct a demand feature vector, combining cluster analysis to achieve scenario-based demand matching, and then using a multi-condition triggering mechanism to provide precise prompts to the target power module, the scenario adaptability of multi-power module management is improved.

[0102] It should be noted that the specific implementation of each operation can be described in the corresponding description of the method embodiments shown above. The multi-power module intelligent management device 800 can be used to execute the above method embodiments of this application, and will not be described again here.

[0103] This application also provides a computer-readable storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the methods described in the above method embodiments, wherein the computer includes an electronic device.

[0104] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments. The computer program product may be a software installation package, and the computer may include an electronic device.

[0105] It should be noted that, for the sake of simplicity, the above embodiments are all described as a series of actions. Those skilled in the art should understand that this application is not limited to the described order of actions, as some steps in the embodiments of this application can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions, steps, modules, or units involved are not necessarily essential to the embodiments of this application.

[0106] In the above embodiments, the descriptions of each embodiment in this application have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0107] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

[0108] The steps of the methods or algorithms described in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in RAM, flash memory, ROM, EPROM, electrically erasable programmable read-only memory (EEPROM), registers, hard disk, portable hard disk, read-only optical disk (CD-ROM), or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Furthermore, the ASIC can reside in a terminal device or management device. Alternatively, the processor and storage medium can exist as discrete components in the terminal device or management device.

[0109] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in the embodiments of this application can be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0110] The modules / units included in the various devices and products described in the above embodiments can be software modules / units, hardware modules / units, or a combination of both. For example, for devices and products applied to or integrated into a chip, all modules / units can be implemented using hardware methods such as circuits, or at least some modules / units can be implemented using software programs that run on a processor integrated within the chip, while the remaining (if any) modules / units can be implemented using hardware methods such as circuits. For devices and products applied to or integrated into a chip module, all modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components of the chip module, or at least some modules / units can be implemented using hardware methods such as circuits. The implementation is achieved through a software program that runs on the processor integrated within the chip module. The remaining modules / units (if any) can be implemented using hardware methods such as circuits. For various devices and products applied to or integrated into terminal equipment, each of their modules / units can be implemented using hardware methods such as circuits. Different modules / units can be located in the same component (e.g., chip, circuit module, etc.) or different components within the terminal equipment. Alternatively, at least some modules / units can be implemented through a software program that runs on the processor integrated within the terminal equipment, while the remaining modules / units (if any) can be implemented using hardware methods such as circuits.

[0111] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the embodiments of this application. It should be understood that the above descriptions are merely specific embodiments of the embodiments of this application and are not intended to limit the protection scope of the embodiments of this application. Any modifications, equivalent substitutions, improvements, etc., made on the basis of the technical solutions of the embodiments of this application should be included within the protection scope of the embodiments of this application.

Claims

1. A method for intelligent management of multiple power supply modules, characterized in that, The method includes: Obtain the raw operating data of m power modules within a historical time period, as well as the spatiotemporal extended data of the target user; m is an integer greater than 1. A power demand feature set is constructed based on the original working data and the spatiotemporal extended data; the power demand feature set includes n feature vectors and n time period labels; each feature vector corresponds to a time period label; n is an integer greater than 1; Cluster analysis is performed on the n feature vectors and the n time period labels to obtain k reference cluster centers; each reference cluster center includes at least one time period label; k is a positive integer less than or equal to n; Obtain the target scenario requirements and real-time trigger data of the target user within the current time period; Determine the target cluster center corresponding to the target scenario requirement among the k reference cluster centers; Based on the target cluster center, the m power modules are screened to obtain the target power modules; Based on the real-time trigger data, the target power module is controlled to perform a prompting operation to prompt the target user to carry the target power module.

2. The method as described in claim 1, characterized in that, The step of constructing a power demand feature set based on the original working data and the spatiotemporal extended data includes: The original working data and the spatiotemporal extended data are normalized respectively to obtain the first feature data and the second feature data. The first feature data and the second feature data are integrated to obtain the third feature data; The historical time period is divided into n time period windows according to a preset duration; Based on the n time period windows, the third feature data is divided to obtain n fourth feature data; Construct the n feature vectors based on the n fourth feature data; The n time period labels are generated based on the n time period windows.

3. The method as described in claim 1, characterized in that, The clustering analysis of the n feature vectors and the n time period labels yields k reference cluster centers, including: From the n feature vectors, k feature vectors are randomly selected as the first cluster centers to obtain k first cluster centers; An iterative update step is performed on the k first cluster centers until the position change of each cluster center is less than a preset change threshold, then the iteration is terminated, and the k reference cluster centers are obtained. The iterative update steps are as follows: Calculate the Euclidean distance between each of the n feature vectors and the k first cluster centers, and assign it to the cluster corresponding to the nearest first cluster center to obtain k first clusters; Each of the n time period labels is assigned to the cluster corresponding to its associated feature vector; According to the preset cluster center calculation formula, the k first clusters are calculated for each of the k first clusters to obtain k second cluster centers.

4. The method as described in claim 2, characterized in that, Determining the target cluster center corresponding to the target scenario requirement among the k reference cluster centers includes: Analyze at least one time period label corresponding to each of the k reference cluster centers to obtain k reference scenario requirements; Obtain the reference scenario requirement that matches the target scenario requirement among the k reference scenario requirements, and use its corresponding reference cluster center as the target cluster center.

5. The method as described in claim 2, characterized in that, The step of filtering the m power modules based on the target cluster center to obtain the target power module includes: Obtain the set of m hardware parameters corresponding to the m power modules; Construct m parameter vectors based on the m hardware parameter sets; Calculate the cosine similarity between the target cluster center and each of the m parameter vectors to obtain m cosine similarities; The power module corresponding to the largest cosine similarity among the m cosine similarities is selected as the target power module.

6. The method according to any one of claims 1-5, characterized in that, The real-time trigger data includes a click recommendation indicator, a module pick-up indicator, and a Bluetooth connection indicator. Controlling the target power module to perform a prompt operation based on the real-time trigger data includes: Obtain the target time period label corresponding to the target cluster center from among n time period labels; If at least one of the click recommendation icon, the module pick-up icon, and the Bluetooth connection icon is 1, and the current time period matches the time interval corresponding to the target time period tag, the prompt operation is executed.

7. The method as described in claim 6, characterized in that, The execution of the prompt operation includes: Obtain the target user's target prompting requirements; the target prompting requirements include at least one of the following: vibration prompting requirements and sound prompting requirements; The target power module is controlled to perform the prompt operation according to the target prompt requirement.

8. A multi-power module intelligent management device, characterized in that, The device includes a first acquisition module, a construction module, a clustering module, a second acquisition module, a determination module, a filtering module, and a control module, wherein: The first acquisition module is used to acquire the original working data corresponding to m power modules within a historical time period, as well as the spatiotemporal extended data corresponding to the target user; m is an integer greater than 1. The construction module is used to construct an electricity demand feature set based on the original working data and the spatiotemporal extended data; the electricity demand feature set includes n feature vectors and n time period labels; each feature vector corresponds to a time period label; n is an integer greater than 1; The clustering module is used to perform clustering analysis on the n feature vectors and the n time period labels to obtain k reference cluster centers; each reference cluster center includes at least one time period label; k is a positive integer less than or equal to n; The second acquisition module is used to acquire the target user's target scenario needs and real-time trigger data within the current time period; The determining module is used to determine the target cluster center corresponding to the target scenario requirement among the k reference cluster centers; The filtering module is used to filter the m power modules based on the target cluster center to obtain the target power modules; The control module is used to control the target power module to perform a prompting operation based on the real-time triggering data, so as to prompt the target user to carry the target power module.

9. An electronic device, characterized in that, include: Processor, memory, communication interface, and one or more programs; The one or more programs are stored in the memory and configured to be executed by the processor, the programs including instructions for performing the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1-7.

Images