Method and device for determining home position of user and wearable intelligent equipment

Abstract

The invention relates to the technical field of wearable intelligent equipment, and further relates to a method and device for determining the home position of a user and wearable intelligent equipment. The method comprises the following steps: when the wearable intelligent equipment is in an indoor environment, acquiring wireless signal data and multi-source sensing data; determining wireless signal feature data according to the wireless signal data, and determining a standing proportion, a charging behavior similarity and a position aggregation degree according to the multi-source sensing data; performing weighted summation on the wireless signal feature data, the standing proportion, the position aggregation degree and the charging behavior similarity; and when the weighted summation result is not less than the total threshold, determining that the target coordinate is the user home position. According to the method, the wireless signal data and the multi-source sensing data are effectively fused, the problem that a single judgment condition is prone to interference or misjudgment is avoided, the accuracy and reliability of user home position recognition are remarkably improved, a solid foundation is provided for subsequent intelligent services based on home scenes, and therefore the user experience is optimized.

Description

Technical Field

[0001] This application relates to the field of wearable smart device technology, and further to a method and apparatus for determining a user's home location, and a wearable smart device. Background Technology

[0002] With the increasing popularity of wearable smart devices, users' demand for intelligent and personalized services is growing. Among these, accurately identifying the user's home location is a key prerequisite for realizing various smart services.

[0003] In existing technologies, some devices roughly infer home location by obtaining the user's location and combining it with the duration of stay. However, such methods are difficult to accurately identify home location due to the reliance on a single criterion.

[0004] Therefore, there is an urgent need for a method to determine the location of a user's home, thereby improving the accuracy of identifying the user's home location. Summary of the Invention

[0005] To address the aforementioned technical issues, this application provides a method and apparatus for determining a user's home location, as well as a wearable smart device, which improves the accuracy and reliability of user home location identification, provides a solid foundation for subsequent smart services based on home scenarios, and thus optimizes the user experience.

[0006] In a first aspect, this application provides a method for determining a user's home location, applied to a wearable smart device, comprising: acquiring wireless signal data and multi-source sensing data when the wearable smart device is in an indoor environment; determining wireless signal feature data based on the wireless signal data, and determining a static ratio, charging behavior similarity, and location aggregation degree based on the multi-source sensing data; performing a weighted summation of the wireless signal feature data, static ratio, location aggregation degree, and charging behavior similarity; and determining the target coordinates as the user's home location when the weighted summation result is not less than a total threshold; the target coordinates are the coordinates of the wearable smart device just before entering the indoor environment.

[0007] The above method for determining a user's home location involves comprehensively acquiring wireless signal data and multi-source sensing data when the wearable smart device is indoors. Based on the wireless signal data, wireless signal characteristic data is determined. Simultaneously, the multi-source sensing data is used to calculate the stationary ratio, charging behavior similarity, and location aggregation degree. Then, a weighted sum is applied to the wireless signal characteristic data, stationary ratio, location aggregation degree, and charging behavior similarity. When the weighted sum is not less than a total threshold, the coordinates of the device just before entering the room (i.e., the target coordinates) are determined as the user's home location. This method effectively integrates wireless signal data and multi-source sensing data, avoiding the problem of single-condition judgment being easily interfered with or misjudged. It significantly improves the accuracy and reliability of user home location identification, providing a solid foundation for subsequent smart services based on home scenarios, thereby optimizing the user experience.

[0008] In one implementation, the multi-source sensing data includes acceleration data, positioning data, and charging feature data. Based on the multi-source sensing data, the stationary ratio, charging behavior similarity, and location aggregation degree are determined. Specifically, this includes: determining the stationary ratio based on the acceleration data; determining the location aggregation degree based on the positioning data and target coordinates; and determining the charging behavior similarity based on the charging feature data and a preset charging behavior pattern.

[0009] In one implementation, the static ratio is determined based on acceleration data, specifically including: determining the static duration of the wearable smart device in a static state based on acceleration data; and determining the static ratio based on the static duration and the data collection cycle.

[0010] In one implementation, the location aggregation degree is determined based on the positioning data and target coordinates, specifically including: determining the aggregation area based on the target coordinates and aggregation radius; and determining the location aggregation degree based on the positioning data and aggregation area.

[0011] One implementation also includes: adjusting the aggregation radius based on the source of the location data; and adjusting the total threshold based on historical data and machine learning models.

[0012] In one implementation, the wireless signal feature data includes at least one of wireless signal repetition rate, wireless signal nighttime activity, and wireless signal similarity. Determining the wireless signal feature data based on the wireless signal data specifically includes: statistically analyzing the frequency of occurrence of each wireless signal address in the wireless signal data within the acquisition period; determining the wireless signal repetition rate based on the frequency of occurrence of each wireless signal address within the acquisition period; and / or, identifying wireless signal addresses that are identical in the wireless signal data and the preset signal database based on the wireless signal data and the preset signal database; determining the wireless signal similarity based on the identical wireless signal addresses and all wireless signal addresses in the preset signal database; and / or, using the number of times a wearable smart device scans the wireless signal at night in the wireless signal data as the wireless signal nighttime activity.

[0013] The above method for determining a user's home location acquires parameters such as the proportion of idle time, charging behavior similarity, location aggregation degree, wireless signal repetition rate, wireless signal nighttime activity, and wireless signal similarity. These parameters are then weighted and summed, or weighted and summed after threshold assignment. The target coordinates are determined to be the user's home location when the weighted sum is not less than a total threshold. This method fully utilizes acceleration data, positioning data, charging characteristic data, and Wi-Fi / Bluetooth wireless signal data continuously collected by wearable smart devices in indoor environments to construct a highly reliable home location identification model from multiple dimensions. Compared to traditional schemes relying on a single judgment condition, this application significantly improves the accuracy and robustness of home location identification, effectively enhancing the user experience.

[0014] In one implementation, a weighted summation is performed on the wireless signal feature data, the idle ratio, the location aggregation degree, and the charging behavior similarity. Specifically, this includes: assigning a first value to any parameter in the target sample set when it is less than its corresponding threshold, and assigning a second value to any parameter in the target sample set when it is not less than its corresponding threshold; performing a weighted summation based on the weight of each parameter in the target sample set and its corresponding first or second value; the target sample set includes wireless signal feature data, the idle ratio, the location aggregation degree, and the charging behavior similarity.

[0015] The above method for determining a user's home location introduces a threshold judgment and binarization assignment mechanism into a target sample set composed of wireless signal feature data, idle ratio, location aggregation degree, and charging behavior similarity. Specifically, when any parameter is less than its corresponding threshold, it is assigned a first value; when it is not less than the threshold, it is assigned a second value. A weighted sum is then performed based on the preset weights of each parameter, effectively simplifying the weighted fusion calculation process. While ensuring recognition accuracy, this method significantly improves the operating efficiency of this application on resource-constrained wearable smart devices, further enhancing the reliability and practicality of home location identification.

[0016] In one implementation, the method further includes: when any parameter in the target sample set is the wireless signal repetition rate, and the frequency of occurrence of any wireless signal address in the wireless signal repetition rate during the acquisition period is less than the threshold corresponding to the wireless signal repetition rate, the wireless signal repetition rate is assigned a first value; when any parameter in the target sample set is the wireless signal repetition rate, and the frequency of occurrence of any wireless signal address in the wireless signal repetition rate during the acquisition period is not less than the threshold corresponding to the wireless signal repetition rate, the wireless signal repetition rate is assigned a second value.

[0017] Secondly, this application also provides an apparatus for determining a user's home location, comprising: a receiving module configured to acquire wireless signal data and multi-source sensing data when the wearable smart device is in an indoor environment; a processing module configured to: determine wireless signal feature data based on the wireless signal data, and determine a static ratio, charging behavior similarity, and location aggregation degree based on the multi-source sensing data; and perform a weighted summation of the wireless signal feature data, static ratio, location aggregation degree, and charging behavior similarity; and a home location determination module configured to determine the target coordinates as the user's home location when the weighted summation result is not less than a total threshold; the target coordinates are the coordinates of the wearable smart device just before entering the indoor environment.

[0018] Thirdly, this application provides a wearable smart device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method for determining the user's home location as implemented above.

[0019] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for determining a user's home location as described above.

[0020] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method for determining a user's home location as described above.

[0021] Compared with the prior art, the present invention has at least one of the following beneficial effects:

[0022] 1. This method integrates wireless signal data and multi-source sensing data when a wearable smart device is in an indoor environment. Wireless signal feature data is determined based on the wireless signal data, while the multi-source sensing data is used to calculate the stationary ratio, charging behavior similarity, and location aggregation degree. A weighted sum is then applied to these factors. When the weighted sum is not less than a total threshold, the coordinates of the device just moments before entering the room (i.e., the target coordinates) are determined as the user's home location. This method effectively integrates wireless signal data and multi-source sensing data, avoiding the problem of interference or misjudgment caused by a single judgment condition. It significantly improves the accuracy and reliability of user home location identification, providing a solid foundation for subsequent smart services based on home scenarios, thereby optimizing the user experience.

[0023] 2. Parameters such as the static ratio, charging behavior similarity, location aggregation degree, wireless signal repetition rate, wireless signal nighttime activity, and wireless signal similarity are obtained. These parameters are then weighted and summed, or weighted and summed after threshold assignment. The target coordinates are determined to be the user's home location when the weighted summation result is not less than the total threshold. This method fully utilizes acceleration data, positioning data, charging characteristic data, and WIFI / Bluetooth wireless signal data continuously collected by wearable smart devices in indoor environments to construct a highly reliable home location identification model from multiple dimensions. Compared to traditional solutions relying on a single judgment condition, this application significantly improves the accuracy and robustness of home location identification, effectively enhancing the user experience.

[0024] 3. By introducing a threshold judgment and binarization assignment mechanism into the target sample set composed of wireless signal feature data, static ratio, location aggregation degree, and charging behavior similarity, this method assigns a first value when any parameter is less than its corresponding threshold, and a second value when it is not less than the threshold. This is combined with preset weights for each parameter to perform a weighted summation, effectively simplifying the weighted fusion calculation process. While ensuring recognition accuracy, this significantly improves the operating efficiency of this application on resource-constrained wearable smart devices, further enhancing the reliability and practicality of home location identification. Attached Figure Description

[0025] The preferred embodiments will now be described in a clear and easy-to-understand manner, in conjunction with the accompanying drawings, to further explain the above-mentioned characteristics, technical features, advantages, and implementation methods of the present invention.

[0026] Figure 1 A flowchart illustrating a method for determining a user's home location according to an embodiment of this application is shown;

[0027] Figure 2 This document illustrates a flowchart illustrating how to determine the static ratio, charging behavior similarity, and location aggregation degree according to an embodiment of this application.

[0028] Figure 3 This document illustrates a flowchart of a method for determining wireless signal characteristic data according to an embodiment of this application.

[0029] Figure 4 This document illustrates a flowchart of a weighted summation method provided in an embodiment of this application.

[0030] Figure 5 This illustration shows a structural block diagram of a device for determining a user's home location according to an embodiment of this application;

[0031] Figure 6 A structural block diagram of a wearable smart device provided in an embodiment of this application is shown. Detailed Implementation

[0032] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the specific implementation methods of the present invention will be described below with reference to the accompanying drawings. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings and other implementation methods can be obtained based on these drawings without any creative effort.

[0033] To keep the drawings concise, each figure only schematically shows the parts relevant to the invention, and these do not represent the actual structure of the product. Furthermore, to facilitate understanding, in some figures, only one of components with the same structure or function is schematically depicted, or only one is labeled. In this document, "one" not only means "only one," but can also mean "more than one."

[0034] It should also be further understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0035] In this document, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0036] Furthermore, in the description of this application, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0037] It should be noted that the above embodiments can be freely combined as needed. The above are merely preferred embodiments of the present invention. It should be pointed out that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

[0038] With the widespread adoption of wearable smart devices, users' demand for intelligent and personalized services is growing. Accurately identifying a user's home location is a crucial prerequisite for implementing various scenario-based intelligent services (such as automatic switching to "home mode" and personalized notification management). Current technologies sometimes obtain a user's location and roughly infer their home location based on dwell time or access frequency. However, such methods struggle to accurately identify the home location.

[0039] In some implementations of this application, wireless signal (such as Wi-Fi or Bluetooth) fingerprints can be introduced for location determination. However, this often relies on only single-dimensional data, resulting in low recognition accuracy and susceptibility to interference from temporary stops (such as offices or frequently visited shops). Furthermore, after identifying the home location, there is a lack of an effective linkage mechanism with upper-layer application services, failing to fully leverage the potential of home location recognition results in enhancing the human-computer interaction experience.

[0040] Therefore, there is an urgent need for a method to determine the location of a user's home, which can effectively improve the accuracy of identifying the user's home location and fully leverage the potential of home location identification results in enhancing the human-computer interaction experience.

[0041] The following explanation is based on the accompanying diagram:

[0042] Reference Appendix Figure 1 The diagram illustrates a flowchart of a method for determining a user's home location provided in an embodiment of this application. Figure 1 As shown, this method is applied to wearable smart devices and includes:

[0043] The S100 acquires wireless signal data and multi-source sensing data when wearable smart devices are in an indoor environment.

[0044] S110 determines wireless signal characteristic data based on wireless signal data, and determines the idle ratio, charging behavior similarity, and location aggregation degree based on multi-source sensing data.

[0045] S120 performs a weighted summation of wireless signal characteristic data, stationary ratio, location aggregation degree, and charging behavior similarity.

[0046] S130, when the weighted summation result is not less than the total threshold, the target coordinates are determined as the user's home location. The target coordinates are the coordinates of the wearable smart device just before it enters the room.

[0047] Wearable smart devices may include, but are not limited to, smartwatches, smart bracelets, and smart glasses. Wearable smart devices may or may not have the function of collecting wireless signal data and multi-source sensing data. This application does not limit this. Multi-source sensing data may include, but is not limited to, acceleration data, positioning data, and charging characteristic data. When a wearable smart device has the function of collecting wireless signal data and multi-source sensing data, the wearable smart device may include an accelerometer, an inertial sensor, a device or module with wireless signal acquisition capabilities (e.g., a WIFI module or device, a Bluetooth module or device, a radio frequency transceiver module or device, etc.), a satellite positioning module or GNSS (Global Navigation Satellite System Receiver) receiver, a power detection module, or a power management module, etc.

[0048] Wearable smart devices can determine whether they have entered an indoor environment by monitoring changes in satellite positioning signals. For example, if the satellite signal strength suddenly weakens or disappears completely from a stable state, it can be determined that the wearable smart device is indoors. Alternatively, users can manually operate the wearable smart device to inform it that it is currently indoors.

[0049] When the wearable smart device is in an indoor environment, its coordinates are recorded just before it entered the room (or the last valid satellite positioning coordinates before entering the room). After confirming that the wearable smart device is indoors, it can acquire wireless signal data and multi-source sensing data. This wireless signal data and multi-source sensing data can be obtained periodically by the wearable smart device, or periodically collected and transmitted to the wearable smart device by other devices. Wireless signal data can include Bluetooth signal data and / or Wi-Fi signal data. Bluetooth signal data can include the Bluetooth signal address (or Bluetooth device MAC address), Bluetooth signal strength, Bluetooth device name, and Bluetooth device type. Wi-Fi signal data can include the Wi-Fi signal address (or Wi-Fi signal MAC address), Wi-Fi signal strength, SSID name, and timestamp.

[0050] Wearable smart devices can determine wireless signal characteristic data based on wireless signal data. This wireless signal characteristic data can include at least one of the following: wireless signal repetition rate, wireless signal nighttime activity, and wireless signal similarity. Wireless signal repetition rate refers to the frequency of occurrence of each wireless signal address within the data collection period. Wireless signal nighttime activity refers to the number of times the wearable smart device scans for wireless signals at night (defined as 22:00-08:00, adjustable according to user habits). Wireless signal similarity refers to the proportion of wireless signal addresses in the wireless signal data that are identical to those in a preset signal database, occupying a portion of all wireless signal addresses in the preset database.

[0051] Wearable smart devices can determine inactivity ratio, charging behavior similarity, and location aggregation degree based on multi-source sensing data. Inactivity ratio refers to the proportion of the data collection period during which the wearable smart device is inactive. Charging behavior similarity refers to the similarity between charging characteristic data and preset charging behavior patterns (which are typical charging patterns in a home environment). Location aggregation degree refers to the degree of aggregation of the wearable smart device's location data.

[0052] Wearable smart devices can directly perform a weighted sum based on wireless signal characteristic data, idle ratio, location aggregation degree, and charging behavior similarity, along with the weights corresponding to these parameters. Alternatively, thresholds can be set for each of the wireless signal characteristic data, idle ratio, location aggregation degree, and charging behavior similarity. Then, when these parameters are less than or equal to their respective thresholds, values ​​are assigned to them. The wearable smart device can then perform a weighted sum based on the weights and assigned values ​​of these parameters. Each parameter in the wireless signal characteristic data also has its own weight, threshold, and assigned value. Finally, when the weighted sum is not less than the total threshold (the total threshold setting varies depending on the weighted summing method, and can be set according to the actual situation), the target coordinates are determined as the user's home location.

[0053] This application embodiment acquires wireless signal data and multi-source sensing data comprehensively when the wearable smart device is in an indoor environment. Based on the wireless signal data, it determines wireless signal feature data. Simultaneously, it uses the multi-source sensing data to calculate the stationary ratio, charging behavior similarity, and location aggregation degree. Then, it performs a weighted sum of the wireless signal feature data, stationary ratio, location aggregation degree, and charging behavior similarity. When the weighted sum is not less than a total threshold, the coordinates of the device just before entering the room (i.e., the target coordinates) are determined as the user's home location. This method effectively integrates wireless signal data and multi-source sensing data, avoiding the problem of single-condition judgment being easily interfered with or misjudged. It significantly improves the accuracy and reliability of user home location identification, providing a solid foundation for subsequent smart services based on home scenarios, thereby optimizing the user experience.

[0054] Reference Appendix Figure 2 It illustrates a flowchart of a method for determining the static ratio, charging behavior similarity, and location aggregation degree according to an embodiment of this application, such as... Figure 2 As shown, it includes:

[0055] S200, based on acceleration data, determines the static ratio.

[0056] S210, determine the degree of location aggregation based on the positioning data and target coordinates.

[0057] S220 determines the similarity of charging behavior based on charging characteristic data and preset charging behavior patterns.

[0058] The static ratio refers to the proportion of the data acquisition cycle during which a wearable smart device remains stationary. Therefore, by periodically analyzing acceleration data, the static duration of the wearable smart device can be determined, and then the static ratio can be determined based on the static duration and the data acquisition cycle of the acceleration data.

[0059] Charging behavior similarity refers to the similarity between charging characteristic data and preset charging behavior patterns (which are typical charging patterns in a home environment). Therefore, wearable smart devices can periodically record charging characteristic data (such as, but not limited to, charging start time, charging end time, charging duration, and whether charging is done at a fixed location). The charging characteristic data is then compared with the preset charging behavior patterns to determine the charging behavior similarity.

[0060] Location aggregation degree refers to the degree of clustering of location data from wearable smart devices. After entering an indoor environment, wearable smart devices can periodically acquire location data. Then, based on the target coordinates and a preset aggregation radius, an aggregation area is determined. The location aggregation degree is determined by the proportion of location data falling within this aggregation area.

[0061] For a similar process, please refer to the appendix. Figure 3 This illustrates a flowchart of a method for determining wireless signal characteristic data according to an embodiment of this application. Figure 3 As shown, it includes:

[0062] S300: Calculate the frequency of occurrence of each wireless signal address in the wireless signal data within the acquisition period; determine the wireless signal repetition rate based on the frequency of occurrence of each wireless signal address within the acquisition period.

[0063] S310, and / or, based on the wireless signal data and the preset signal database, determine the wireless signal addresses that are the same in the wireless signal data and the preset signal database; and based on the same wireless signal addresses and all wireless signal addresses in the preset signal database, determine the wireless signal similarity.

[0064] S320, and / or, uses the number of times a wearable smart device scans the wireless signal at night as the wireless signal nighttime activity level.

[0065] Wireless signal data can include Wi-Fi signal data and / or Bluetooth signal data. Therefore, the wireless signal repetition rate can be the Wi-Fi and / or Bluetooth signal repetition rate, the wireless signal similarity can be the Wi-Fi and / or Bluetooth signal similarity, and the wireless signal nighttime activity can be the Wi-Fi and / or Bluetooth signal nighttime activity. After obtaining the same wireless signal addresses in the wireless signal data and the preset signal database, the proportion of the same wireless signal addresses to all wireless signal addresses in the preset signal database can be calculated, and this proportion can be used as the wireless signal similarity.

[0066] Through the aforementioned appendix Figure 2 and 3 After obtaining parameters such as idle ratio, charging behavior similarity, location aggregation, wireless signal repetition rate, wireless signal nighttime activity, and wireless signal similarity, these parameters can be directly weighted and summed. Alternatively, corresponding thresholds can be set for each parameter, and values ​​can be assigned to these parameters when they are less than or equal to their respective thresholds. Wearable smart devices can then perform weighted summation based on the weights and assigned values ​​of these parameters. Finally, when the weighted summation result is not less than the total threshold, the target coordinates are determined as the user's home location.

[0067] This application acquires parameters such as the static ratio, charging behavior similarity, location aggregation degree, wireless signal repetition rate, wireless signal nighttime activity, and wireless signal similarity. Based on these parameters, a weighted summation is performed, or a weighted summation combined with a threshold assignment is performed. Finally, the target coordinates are determined to be the user's home location when the weighted summation result is not less than a total threshold. This method fully utilizes acceleration data, positioning data, charging characteristic data, and WIFI / Bluetooth wireless signal data continuously collected by wearable smart devices in indoor environments to construct a highly reliable home location identification model from multiple dimensions. Compared to traditional schemes that rely on a single judgment condition, this application significantly improves the accuracy and robustness of home location identification, effectively enhancing the user experience.

[0068] Reference Appendix Figure 4 This illustrates a flowchart of a weighted summation method provided in an embodiment of this application. For example... Figure 4 As shown, it includes:

[0069] S400: When any parameter in the target sample set is less than its corresponding threshold, the parameter is assigned a first value; when any parameter in the target sample set is not less than its corresponding threshold, the parameter is assigned a second value.

[0070] S410, perform a weighted summation based on the weight of each parameter in the target sample set and its corresponding first or second value. The target sample set includes wireless signal feature data, stationary ratio, location aggregation degree, and charging behavior similarity.

[0071] Wireless signal feature data may include at least one of wireless signal repetition rate, wireless signal nighttime activity, and wireless signal similarity. The following example illustrates the case where wireless signal feature data includes wireless signal repetition rate, wireless signal nighttime activity, and wireless signal similarity.

[0072] Users can pre-set corresponding thresholds for idle ratio, charging behavior similarity, location aggregation, wireless signal repetition rate, wireless signal nighttime activity, and wireless signal similarity. When a parameter is less than its corresponding threshold, the parameter is assigned the first value; when it is not less than its corresponding threshold, the parameter is assigned the second value.

[0073] Wearable smart devices process wireless signal data and multi-source sensing data to obtain parameters such as idle ratio, charging behavior similarity, location aggregation degree, wireless signal repetition rate, wireless signal nighttime activity, and wireless signal similarity. These parameters are then compared to their corresponding thresholds to determine their assigned values. The wearable smart device performs a weighted sum based on the assigned values ​​and weights of each parameter. Finally, the weighted sum is compared to a total threshold. If the weighted sum is not less than the total threshold, the target coordinates are determined to be the user's home location.

[0074] In one consideration of wireless signal repetition rate, the wireless signal repetition rate is actually the frequency of occurrence of each wireless signal address within the acquisition period. Therefore, the aforementioned wireless signal repetition rate being less than or not less than the corresponding threshold can mean that the frequency of occurrence of each wireless signal address within the acquisition period is less than or not less than the corresponding threshold, or it can mean that the average frequency of occurrence of each wireless signal address within the acquisition period is less than or not less than the corresponding threshold, etc.

[0075] This application's embodiments introduce a threshold judgment and binarization assignment mechanism into the target sample set composed of wireless signal feature data, static ratio, location aggregation degree, and charging behavior similarity. Specifically, when any parameter is less than its corresponding threshold, it is assigned a first value; when it is not less than the threshold, it is assigned a second value. A weighted sum is then performed based on the preset weights of each parameter, effectively simplifying the weighted fusion calculation process. While ensuring recognition accuracy, this significantly improves the operating efficiency of this application on resource-constrained wearable smart devices, further enhancing the reliability and practicality of home location identification.

[0076] In another consideration involving wireless signal repetition rate, the aforementioned wireless signal repetition rate being less than or not less than the corresponding threshold can refer to the existence of any wireless signal address having an occurrence frequency less than or not less than the corresponding threshold within the acquisition period.

[0077] For example, in one embodiment of this application, the method further includes: when any parameter in the target sample set is the wireless signal repetition rate, and the frequency of occurrence of any wireless signal address in the wireless signal repetition rate during the acquisition period is less than the threshold corresponding to the wireless signal repetition rate, assigning the wireless signal repetition rate a first value; when any parameter in the target sample set is the wireless signal repetition rate, and the frequency of occurrence of any wireless signal address in the wireless signal repetition rate during the acquisition period is not less than the threshold corresponding to the wireless signal repetition rate, assigning the wireless signal repetition rate a second value. This embodiment of the application improves the sensitivity of the wireless signal repetition rate as a criterion for determining home location by determining the threshold based on the frequency of occurrence of a single wireless signal address.

[0078] In one embodiment of this application, the method further includes: adjusting the aggregation radius based on the source of the location data; and adjusting the total threshold based on historical data and a machine learning model.

[0079] Wearable smart devices can use massive amounts of historical user data (including the raw data for the aforementioned judgment conditions) and the user's home location settings (which can be set via a mobile app) to perform machine learning or statistical analysis using machine learning models to derive a total threshold. Wearable smart devices can also adjust the aggregation radius based on the source of the location data. For example, if the location data source is satellite positioning, the aggregation radius can be adjusted to a first aggregation radius; if the location data source is network positioning (e.g., the combined effect of Wi-Fi and base stations), the aggregation radius can be adjusted to a second aggregation radius. The first aggregation radius is smaller than the second aggregation radius.

[0080] When wireless signal repetition rate includes both Wi-Fi and Bluetooth signal repetition rate, separate thresholds need to be set for each to ensure environmental stability. The weights of the parameters in the aforementioned embodiments can be adjusted according to their importance or user needs; this application does not limit this adjustment.

[0081] Reference Appendix Figure 5 This illustrates a structural block diagram of a device for determining a user's home location according to an embodiment of this application. Figure 5 As shown, the device 500 includes: a receiving module 510 configured to acquire wireless signal data and multi-source sensing data when the wearable smart device is in an indoor environment; a processing module 520 configured to: determine wireless signal feature data based on the wireless signal data, and determine the static ratio, charging behavior similarity, and location aggregation degree based on the multi-source sensing data; and perform a weighted summation of the wireless signal feature data, static ratio, location aggregation degree, and charging behavior similarity; and a home location determination module 530 configured to determine the target coordinates as the user's home location when the weighted summation result is not less than a total threshold; the target coordinates are the coordinates of the wearable smart device just before entering the indoor environment.

[0082] This application embodiment acquires wireless signal data and multi-source sensing data comprehensively when the wearable smart device is in an indoor environment. Based on the wireless signal data, it determines wireless signal feature data. Simultaneously, it uses the multi-source sensing data to calculate the stationary ratio, charging behavior similarity, and location aggregation degree. Then, it performs a weighted sum of the wireless signal feature data, stationary ratio, location aggregation degree, and charging behavior similarity. When the weighted sum is not less than a total threshold, the coordinates of the device just before entering the room (i.e., the target coordinates) are determined as the user's home location. This method effectively integrates wireless signal data and multi-source sensing data, avoiding the problem of single-condition judgment being easily interfered with or misjudged. It significantly improves the accuracy and reliability of user home location identification, providing a solid foundation for subsequent smart services based on home scenarios, thereby optimizing the user experience.

[0083] Reference Appendix Figure 6 This application also provides a wearable smart device 600, which includes a memory 610, a processor 620, and a computer program stored on the memory 610. The processor 620 executes the computer program to implement the steps of the method for determining the user's home location in any of the above embodiments.

[0084] The memory 610 may be non-volatile memory (NVM), such as, but not limited to, semiconductor non-volatile memory, disk storage, or optical storage. Semiconductor non-volatile memory includes, but is not limited to, read-only memory (ROM) or flash memory, such as mask ROM, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), NAND flash memory, or NOR flash memory.

[0085] The memory 610 can also be volatile memory, such as random access memory (RAM). RAM includes, for example, static random-access memory (SRAM) or dynamic random-access memory (DRAM). DRAM includes, for example, synchronous dynamic RAM (SDRAM) or double data rate SDRAM (DDR). With the development of technology, DDR includes, but is not limited to, DDR1, DDR2, DDR3, ..., DDR5, and may also include future DDR6.

[0086] Processor 620 is a circuit with signal processing capabilities. In one example, the processor can be a circuit with instruction read and execute capabilities; such as a central processing unit (CPU), microcontroller unit (MCU), microprocessor unit (MPU), graphics processing unit (GPU), or digital signal processor (DSP). In another example, the processor can realize its processing capabilities through the logical relationships of hardware circuits, which can be fixed or reconfigurable; for example, the processor can be a dedicated processor, such as a processor implemented with an application-specific integrated circuit (ASIC), which realizes its processing capabilities through the design of the logical relationships between components within the circuit; or a processor implemented with a programmable logic device (PLD), which realizes its processing capabilities by configuring the logical relationships between logic devices through a configuration file; for example, a processor implemented with a field-programmable gate array (FPGA). In another example, the processor can be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), tensor processing unit (TPU), deep learning processing unit (DPU), etc. This application is not limited to the type of processor.

[0087] The wearable smart device used in this application embodiment is basically similar to the method embodiment, so the description is relatively simple. For relevant details, please refer to the description of the method embodiment.

[0088] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for determining a user's home location as described in any of the above embodiments.

[0089] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the method for determining a user's home location as described in any of the above embodiments.

[0090] It should be noted that the above embodiments can be freely combined as needed. The above are merely preferred embodiments of the present invention. It should be pointed out that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining a user's home location, applied to a wearable smart device, characterized in that, include: When the wearable smart device is in an indoor environment, it acquires wireless signal data and multi-source sensing data; Based on the wireless signal data, wireless signal feature data is determined, and based on the multi-source sensing data, the static ratio, charging behavior similarity, and location aggregation degree are determined. The wireless signal feature data, the static ratio, the location aggregation degree, and the charging behavior similarity are weighted and summed. When the weighted summation result is not less than the total threshold, the target coordinates are determined as the user's home location; The target coordinates are the coordinates of the wearable smart device just before it enters the room.

2. The method for determining a user's home location according to claim 1, characterized in that, The multi-source sensing data includes acceleration data, positioning data, and charging characteristic data; The step of determining the idle ratio, charging behavior similarity, and location aggregation degree based on the multi-source sensing data specifically includes: Determine the static ratio based on the acceleration data; Based on the positioning data and target coordinates, determine the degree of location aggregation; The similarity of charging behavior is determined based on the charging feature data and the preset charging behavior pattern.

3. The method for determining a user's home location according to claim 2, characterized in that, Determining the static ratio based on the acceleration data specifically includes: Based on the acceleration data, determine the duration of time the wearable smart device remains in a static state; The settling ratio is determined based on the settling time and the collection cycle.

4. The method for determining a user's home location according to claim 2, characterized in that, The step of determining the location aggregation degree based on the positioning data and target coordinates specifically includes: The aggregation region is determined based on the target coordinates and aggregation radius; The location aggregation degree is determined based on the location data and the aggregation area.

5. The method for determining a user's home location according to claim 4, characterized in that, Also includes: Adjust the aggregation radius according to the source of the location data; The total threshold is adjusted based on historical data and machine learning models.

6. The method for determining a user's home location according to claim 1, characterized in that, The wireless signal feature data includes at least one of wireless signal repetition rate, wireless signal nighttime activity, and wireless signal similarity; the step of determining the wireless signal feature data based on the wireless signal data specifically includes: The frequency of occurrence of each wireless signal address in the wireless signal data during the acquisition period is statistically analyzed. The repetition rate of the wireless signal is determined based on the frequency of occurrence of each wireless signal address within the acquisition period; And / or, Based on the wireless signal data and the preset signal database, determine the wireless signal address that is the same as the wireless signal data and the preset signal database; The similarity of wireless signals is determined based on the same wireless signal address and all wireless signal addresses in the preset signal database; And / or, The number of times the wearable smart device scans the wireless signal at night is taken as the nighttime activity level of the wireless signal.

7. The method for determining a user's home location according to any one of claims 1-6, characterized in that, The weighted summation of the wireless signal feature data, the static ratio, the location aggregation degree, and the charging behavior similarity specifically includes: When any parameter in the target sample set is less than its corresponding threshold, the parameter is assigned the first value; when any parameter in the target sample set is not less than its corresponding threshold, the parameter is assigned the second value. A weighted sum is performed based on the weight of each parameter in the target sample set and its corresponding first or second value. The target sample set includes the wireless signal feature data, the static ratio, the location aggregation degree, and the charging behavior similarity.

8. The method for determining a user's home location according to claim 7, characterized in that, Also includes: When any parameter in the target sample set is the wireless signal repetition rate, and the frequency of any wireless signal address in the wireless signal repetition rate during the acquisition period is less than the threshold corresponding to the wireless signal repetition rate, the wireless signal repetition rate is assigned a first value. When any parameter in the target sample set is the wireless signal repetition rate, and the frequency of occurrence of any wireless signal address in the wireless signal repetition rate within the acquisition period is not less than the threshold corresponding to the wireless signal repetition rate, the wireless signal repetition rate is assigned a second value.

9. A device for determining a user's home location, applied to a wearable smart device, characterized in that, include: The receiving module is configured to acquire wireless signal data and multi-source sensing data when the wearable smart device is in an indoor environment; The processing module is configured to: determine wireless signal feature data based on the wireless signal data, and determine the idle ratio, charging behavior similarity, and location aggregation degree based on the multi-source sensing data; and perform a weighted summation of the wireless signal feature data, the idle ratio, the location aggregation degree, and the charging behavior similarity. The home location determination module is configured to determine the target coordinates as the user's home location when the weighted summation result is not less than the total threshold. The target coordinates are the coordinates of the wearable smart device just before it enters the room.

10. A wearable smart device, comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method for determining a user's home location as described in any one of claims 1-7.

Images