Self-adaptive positioning method and device based on user behavior pattern

Abstract

The invention discloses a self-adaptive positioning method and device based on a user behavior mode. The method comprises the following steps: acquiring current time information and real-time state information of wearable equipment; according to the current time information and the real-time state information of the wearable device, performing prediction based on a behavior mode model to obtain a prediction scene; the behavior pattern model is obtained by training through a machine learning model according to historical spatio-temporal data of a user; adaptively selecting a target positioning strategy from a plurality of preset positioning strategies according to the prediction scene; and controlling a positioning system of the wearable device to execute the target positioning strategy. According to the embodiment of the invention, non-inductive smooth switching of the positioning strategy is realized, the power consumption is reduced to the maximum extent while the positioning precision of the key scene is ensured, the endurance of the equipment is prolonged, the user experience and the product stickiness are improved, and the method is particularly suitable for intelligent wearable equipment with relatively high requirements on the endurance and the positioning precision, such as a child intelligent watch.

Description

Technical Field

[0001] This invention relates to the field of wearable device technology, and in particular to an adaptive positioning method and apparatus based on user behavior patterns. Background Technology

[0002] With the widespread adoption of smart wearable devices, location services have become a core function, especially in scenarios such as child safety monitoring and prevention of elderly people getting lost. The timeliness and accuracy of location services directly affect the user experience and safety. Currently, smart wearable devices on the market mainly use single or combined positioning methods such as GPS, LBS (Location Based Services), and Wi-Fi positioning, but they generally suffer from the problem of balancing positioning accuracy and power consumption.

[0003] In existing technologies, GPS positioning modules are typically kept continuously on to ensure positioning accuracy. However, GPS modules consume a lot of power during operation, significantly reducing device battery life and requiring frequent charging, which is inconvenient for users. If the GPS module is turned off to extend battery life, relying solely on LBS or Wi-Fi positioning, while power consumption is reduced, positioning accuracy is poor and cannot meet the precise positioning needs of critical scenarios. Furthermore, some devices support manual switching of positioning modes, but this requires users to manually operate according to the actual scenario, which is cumbersome and has a delayed response, failing to achieve real-time adaptive adjustment. For example, children need precise positioning on their way to school, but parents may forget to switch to high-precision mode; during school hours, high-frequency positioning is not required, but failure to switch to low-power mode in time will result in unnecessary power waste.

[0004] Meanwhile, existing positioning methods lack consideration for users' personalized behavioral patterns. The uniform positioning strategy fails to adapt to the different lifestyles of various users. Different users have different activity ranges, travel times, and activity trajectories, making it difficult for a uniform positioning strategy to achieve the optimal balance between accuracy and power consumption across all user scenarios. For example, some children have fixed routes to and from school, while others have varied activity ranges; using the same positioning frequency and module combination clearly cannot meet the personalized needs of different users.

[0005] Therefore, how to achieve adaptive switching of positioning strategies based on user behavior patterns, while ensuring positioning accuracy in key scenarios and minimizing power consumption and extending device battery life, has become a pressing technical problem to be solved in the field of positioning technology for smart wearable devices. Summary of the Invention

[0006] This invention provides an adaptive positioning method and apparatus based on user behavior patterns, which can solve the technical problems of power consumption and accuracy being mutually exclusive in the positioning function of existing smart wearable devices, the need for manual intervention in mode switching, and the inability to adapt to personalized user behavior. It can realize intelligent prediction and seamless switching of positioning strategies, extend device battery life, and improve positioning accuracy and user experience.

[0007] In a first aspect, embodiments of the present invention provide an adaptive positioning method based on user behavior patterns, comprising:

[0008] Obtain current time information and real-time status information of wearable devices;

[0009] Based on the current time information and the real-time status information of the wearable device, a predicted scenario is obtained based on a behavioral pattern model; the behavioral pattern model is trained on a machine learning model based on the user's historical spatiotemporal data.

[0010] Based on the predicted scenario, an adaptive target positioning strategy is selected from a plurality of preset positioning strategies.

[0011] The positioning system of the wearable device is controlled to execute the target positioning strategy.

[0012] Optionally, the step of training the behavior pattern model using a machine learning model based on the user's historical spatiotemporal data includes:

[0013] Collect users’ historical spatiotemporal data, which includes time information and location information;

[0014] Based on the historical spatiotemporal data, a user behavior pattern model is generated through training a machine learning model.

[0015] Optionally, the step of generating a user behavior pattern model based on the historical spatiotemporal data through training a machine learning model includes:

[0016] Clustering algorithms are used to analyze the location data in the historical spatiotemporal data to automatically identify users' frequent hotspots;

[0017] Build a geofence for each of the aforementioned permanent hotspots and set the fence radius parameter;

[0018] Based on the location and time information in the historical spatiotemporal data, the user's movement trajectory and timestamp information are analyzed to mine the user's time patterns and generate a behavioral pattern model that includes the coordinates of frequently visited hotspots, geofence parameters, and time patterns.

[0019] Optionally, the real-time status information includes coarse LBS location data, motion status data, and real-time data from device sensors;

[0020] The real-time data from the device's sensors includes heart rate sensor data and accelerometer data.

[0021] Optionally, the preset multiple positioning strategies include:

[0022] Deep sleep mode, low power monitoring mode, standard power saving mode, high frequency precision mode, and SOS emergency mode.

[0023] Secondly, embodiments of the present invention provide an adaptive positioning device based on user behavior patterns, comprising:

[0024] The acquisition unit is used to acquire current time information and real-time status information of the wearable device;

[0025] The processing unit is configured to predict a scenario based on a behavior pattern model according to the current time information and the real-time status information of the wearable device; the behavior pattern model is trained by a machine learning model based on the user's historical spatiotemporal data; adaptively select a target positioning strategy from a plurality of preset positioning strategies according to the predicted scenario; and control the positioning system of the wearable device to execute the target positioning strategy.

[0026] Optionally, the processing unit is specifically used for:

[0027] Collect users’ historical spatiotemporal data, which includes time information and location information;

[0028] Based on the historical spatiotemporal data, a user behavior pattern model is generated through training a machine learning model.

[0029] Optionally, the processing unit is specifically used for:

[0030] Clustering algorithms are used to analyze the location data in the historical spatiotemporal data to automatically identify users' frequent hotspots;

[0031] Build a geofence for each of the aforementioned permanent hotspots and set the fence radius parameter;

[0032] Based on the location and time information in the historical spatiotemporal data, the user's movement trajectory and timestamp information are analyzed to mine the user's time patterns and generate a behavioral pattern model that includes the coordinates of frequently visited hotspots, geofence parameters, and time patterns.

[0033] Thirdly, embodiments of the present invention also provide a computing device, comprising:

[0034] Memory, used to store program instructions;

[0035] The processor is used to call the program instructions stored in the memory and execute the above-mentioned adaptive positioning method based on user behavior patterns according to the obtained program.

[0036] Fourthly, embodiments of the present invention also provide a computer-readable non-volatile storage medium, including computer-readable instructions, which, when read and executed by a computer, cause the computer to perform the aforementioned adaptive positioning method based on user behavior patterns.

[0037] The adaptive positioning method based on user behavior patterns provided in this invention includes: acquiring current time information and real-time status information of a wearable device; predicting a scenario based on a behavior pattern model according to the current time information and the real-time status information of the wearable device; the behavior pattern model is trained using a machine learning model based on the user's historical spatiotemporal data; adaptively selecting a target positioning strategy from a set of preset positioning strategies according to the predicted scenario; and controlling the positioning system of the wearable device to execute the target positioning strategy. This invention achieves seamless switching of positioning strategies, maximizing power consumption reduction while ensuring positioning accuracy in critical scenarios, extending device battery life, and improving user experience and product stickiness. It is particularly suitable for smart wearable devices such as children's smartwatches that have high requirements for both battery life and positioning accuracy. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 A schematic diagram of a system architecture provided for an embodiment of the present invention;

[0040] Figure 2 A flowchart illustrating an adaptive positioning method based on user behavior patterns provided in an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram of the structure of an adaptive positioning device based on user behavior patterns, provided in an embodiment of the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0043] First of all, with Figure 1 The structure shown is used as an example to describe the wearable device to which the embodiments of the present invention are applicable. In the embodiments of the present invention, the wearable device 100 may include, but is not limited to, components such as a radio frequency (RF) circuit 110, a memory 120, an input unit 130, a WiFi module 170, a display unit 140, a sensor 150, an audio circuit 160, a processor 180, and a motor 190.

[0044] As those skilled in the art will understand, Figure 1 The structure of the wearable device 100 shown is merely an example and not a limitation. The wearable device 100 may also include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0045] RF circuit 110 can be used for signal reception and transmission during information transmission or calls. Specifically, it receives downlink information from the base station and processes it for the processor 180; additionally, it transmits uplink data from the wearable device 100 to the base station. Typically, RF circuitry includes, but is not limited to, antennas, at least one amplifier, transceiver, coupler, low-noise amplifier (LNA), duplexer, etc. Furthermore, RF circuit 110 can also communicate wirelessly with networks and other devices. The aforementioned wireless communication can use any communication standard or protocol, including but not limited to Global System for Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), email, Short Messaging Service (SMS), etc.

[0046] The memory 120 can be used to store software programs and modules. The processor 180 executes various functional applications and data processing of the wearable device 100 by running the software programs and modules stored in the memory 120. The memory 120 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the wearable device 100 (such as audio data, phone book, etc.). In addition, the memory 120 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0047] The input unit 130 can be used to receive input digital or character information, and to generate key signals related to user settings and function control of the wearable device 100. Specifically, the input unit 130 may include a touch panel 131, a camera device 132, and other input devices 133. The camera device 132 can take pictures of the images to be acquired, and then transmit the images to the processor 180 for processing, and finally present the graphics to the user through the display panel 141. The touch panel 131, also known as a touch screen, can collect touch operations on or near the user (such as operations performed by the user using a finger, stylus, or any suitable object or accessory on or near the touch panel 131), and drive the corresponding connected devices according to a pre-set program. Optionally, the touch panel 131 may include two parts: a touch detection device and a touch controller. The touch detection device detects the user's touch position and the signal generated by the touch operation, transmitting the signal to the touch controller. The touch controller receives touch information from the touch detection device, converts it into touch point coordinates, and sends it to the processor 180. It can also receive and execute commands from the processor 180. Furthermore, the touch panel 131 can be implemented using various types of sensors, including resistive, capacitive, infrared, and surface acoustic wave sensors. In addition to the touch panel 131 and the camera device 132, the input unit 130 may also include other input devices 133. Specifically, these other input devices 132 may include, but are not limited to, one or more of the following: a physical keyboard, function keys (such as volume control buttons, power buttons, etc.), a trackball, and a joystick.

[0048] The display unit 140 can be used to display information input by the user or information provided to the user, as well as various menus of the wearable device 100. The display unit 140 may include a display panel 141, which may optionally be configured using a liquid crystal display (LCD), organic light-emitting diode (OLED), or similar technology. Furthermore, a touch panel 131 may cover the display panel 141. When the touch panel 131 detects a touch operation on or near it, it transmits the information to the processor 180 to determine the type of touch event. Subsequently, the processor 180 provides corresponding visual output on the display panel 141 based on the type of touch event.

[0049] The visual output external display panel 141, which is recognizable by the human eye, can serve as a display device in this embodiment of the invention, used to display text or image information. Although in Figure 1 In this embodiment, the touch panel 131 and the display panel 141 are two separate components to realize the input and output functions of the wearable device 100. However, in some embodiments, the touch panel 131 and the display panel 141 can be integrated to realize the input and output functions of the wearable device 100.

[0050] In addition, the wearable device 100 may also include at least one sensor 150, such as an attitude sensor, a distance sensor, a light sensor, and other sensors.

[0051] Specifically, an attitude sensor can also be called a motion sensor, and one type of motion sensor can be an angular velocity sensor (also known as a gyroscope). When configured in the wearable device 100, it measures the angular velocity of the wearable device 100 when it is in motion, such as when it is tilted or turned. Thus, the gyroscope can accurately analyze and determine the actual actions of the user using the wearable device 100, and then perform corresponding operations on the wearable device 100. Examples include: motion sensing, shaking (using the wearable device 100 to perform certain functions), and inertial navigation based on the motion of an object when there is no GPS signal (such as in a tunnel).

[0052] Sensors can also include optical sensors, which are mainly used to collect information such as the wavelength and intensity of various light rays to adjust the backlight intensity of the display panel 141.

[0053] Furthermore, in this embodiment of the invention, other sensors such as barometers, hygrometers, thermometers, and infrared sensors may also be configured as sensor 150, which will not be described in detail here.

[0054] The light sensor may also include a proximity sensor that can turn off the display panel 141 and / or backlight when the wearable device 100 is moved to the ear.

[0055] Audio circuit 160, speaker 161, and microphone 162 provide an audio interface between the user and wearable device 100. Audio circuit 160 converts received audio data into electrical signals and transmits them to speaker 161, where speaker 161 converts them into sound signals for output. On the other hand, microphone 162 converts collected sound signals into electrical signals, which are received by audio circuit 160, converted into audio data, and then processed by processor 180 before being transmitted via RF circuit 110 to, for example, another wearable device 100, or to memory 120 for further processing.

[0056] WiFi is a short-range wireless transmission technology. Wearable device 100, through WiFi module 170, can help users send and receive emails, browse web pages, and access streaming media, providing users with wireless broadband internet access. Although Figure 1 WiFi module 170 is shown, but it is understood that it is not a necessary component of wearable device 100 and can be omitted as needed without changing the nature of the invention.

[0057] The processor 180 is the control center of the wearable device 100. It connects to various parts of the wearable device 100 via various interfaces and lines. By running or executing software programs and / or modules stored in the memory 120, and by calling data stored in the memory 120, it performs various functions and processes data of the wearable device 100, thereby providing overall monitoring of the wearable device 100. Optionally, the processor 180 may include one or more processing units; preferably, the processor 180 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication.

[0058] It is understandable that the aforementioned modem processor may not be integrated into the processor 180.

[0059] The wearable device 100 may also include at least one motor 190. Since the wearable device 100 is an energy-consuming device, the motor 190 may be a small motor. At the same time, multiple motors may be configured for the wearable device 100 depending on the power that the motor can provide.

[0060] The wearable device 100 also includes a power supply (not shown in the figure) for powering the various components.

[0061] Preferably, the power supply can be logically connected to the processor 180 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. Although not shown, the wearable device 100 may also include a Bluetooth module, etc., which will not be described in detail here.

[0062] It should be noted that the above Figure 1 The structure shown is merely an example, and the embodiments of the present invention are not limited thereto.

[0063] The wearable device in this embodiment of the invention is applicable to various wearable devices such as smartwatches, wristbands, AR / VR devices, and handheld devices.

[0064] Figure 2 An exemplary embodiment of the present invention provides an adaptive positioning process based on user behavior patterns, which can be executed by an adaptive positioning device based on user behavior patterns.

[0065] Step 210: Obtain the current time information and the real-time status information of the wearable device.

[0066] This time information can be a timestamp accurate to the minute, used to record the time nodes of various user activities.

[0067] The real-time status information includes rough LBS location data, motion status data, and real-time data from device sensors; the real-time data from device sensors includes heart rate sensor data and accelerometer data.

[0068] This location data can include GPS trajectory data, LBS cell ID, connected Wi-Fi SSID, and latitude, longitude, and elevation data, comprehensively covering location data sources from different positioning methods.

[0069] GNSS satellite signal information includes the number of visible satellites, satellite signal strength (carrier-to-noise ratio), satellite elevation angle, and azimuth angle. The larger the elevation angle, the higher the satellite signal quality. This data is used to help determine the working efficiency of the positioning module.

[0070] This motion status information is collected by the device's built-in accelerometer to determine whether the user is currently stationary, walking, running, cycling, or riding in a vehicle, providing a basis for motion dimension for scene prediction.

[0071] Data collection employs a combination of local storage and cloud uploading. When the device is in low-power mode, data is uploaded in pre-set batches to further reduce power consumption and avoid wasted power due to frequent communication. All collected data is anonymized to ensure user privacy and security.

[0072] Step 220: Based on the current time information and the real-time status information of the wearable device, predict the scenario based on the behavior pattern model.

[0073] This behavioral pattern model was trained using a machine learning model based on the user's historical spatiotemporal data. Specifically:

[0074] Collect users’ historical spatiotemporal data, which includes time information and location information;

[0075] Based on the historical spatiotemporal data, a user behavior pattern model is generated through training a machine learning model.

[0076] Based on collected historical spatiotemporal data, a machine learning model is trained in the cloud to generate a user behavior pattern model. The specific process is as follows:

[0077] Clustering algorithms are used to analyze location data in the historical spatiotemporal data to automatically identify users' frequent hotspots; geofences are constructed for each frequent hotspot, and fence radius parameters are set; based on location and time information in the historical spatiotemporal data, users' movement trajectories and timestamp information are analyzed to mine users' time patterns and generate a behavioral pattern model that includes frequent hotspot coordinates, geofence parameters, and time patterns.

[0078] Overall, the process can include the following:

[0079] Persistent hotspot identification: Clustering algorithms (such as K-means clustering) are used to analyze historical location data to automatically identify areas where users frequently appear and stay for a long time, i.e., persistent hotspots, such as home, school, nearby shopping malls, hospitals, relatives' residences, etc.

[0080] Geofencing construction: A geofence is constructed for each identified permanent hotspot. A reasonable fence radius parameter is set according to the actual range of the permanent hotspot. When the device location data is within the radius range, it is determined that the user is within the permanent hotspot.

[0081] Behavioral pattern mining: Analyze users' movement trajectory data and timestamp information to uncover users' activity patterns in different time periods. For example, from Monday to Friday, users are on their way to school from 7:30 to 8:00, at school from 8:00 to 17:00, at home from 18:00 to 7:00 the next day, and in the park from 9:00 to 11:00 on weekends.

[0082] Model generation and distribution: Integrate persistent hotspot coordinates, geofence parameters, and time patterns to generate a behavior pattern model. To adapt to the local computing resources of wearable devices, the behavior pattern model is simplified and then distributed to the wearable device for subsequent scene prediction.

[0083] The scene prediction process runs locally on the wearable device to reduce data transmission latency and power consumption. The specific process is as follows:

[0084] Input data acquisition: Real-time acquisition of current time information and real-time device status information, including coarse LBS location data, motion status data collected by the accelerometer, and heart rate data collected by the heart rate sensor.

[0085] Scene prediction calculation: Match the current time information, real-time status information and locally stored behavior pattern model to predict the user's activity scene in the future time period. For example, based on the current time 16:55 and the behavior pattern model, predict that the user will leave school and enter the mobile scene on the way to school in 5 minutes.

[0086] Step 230: Based on the predicted scenario, adaptively select a target positioning strategy from a plurality of preset positioning strategies.

[0087] Based on the predicted scenario output by the scenario prediction process, the target positioning strategy is adaptively selected from multiple preset positioning strategies. Different positioning strategies define different combinations of positioning modules and working parameters.

[0088] Among them, there are several preset positioning strategies, including deep sleep mode, low power monitoring mode, standard power saving mode, high frequency precision mode and SOS emergency mode.

[0089] Specifically, the deep sleep mode maintains only basic communication standby functions, turns off GPS, LBS, Wi-Fi and other positioning modules and unnecessary sensors, and is suitable for scenarios where the user is at home late at night and has fallen asleep. The heart rate sensor helps to determine the user's sleep status.

[0090] Low power monitoring mode: Enables LBS positioning module, sets positioning frequency to once every 30 minutes, disables GPS positioning module and Wi-Fi scanning function, suitable for scenarios where users do not need high-frequency positioning, such as when they are in school or at home.

[0091] Standard power saving mode: Enables LBS positioning module and Wi-Fi scanning function, LBS positioning frequency is once every 5 minutes, Wi-Fi scanning frequency is once every 10 minutes, and GPS positioning module is turned off. Suitable for scenarios where users are lightly active in their usual hotspots.

[0092] High-frequency precision mode: GPS, LBS and Wi-Fi positioning modules are enabled simultaneously. The GPS positioning frequency is set to once every 1-2 minutes. This mode is suitable for scenarios where users are moving, in unknown areas or manually triggering positioning, ensuring positioning accuracy.

[0093] SOS Emergency Mode: All positioning modules (GPS, LBS, Wi-Fi) and sensors operate at full power, reporting positioning data and device status information at the highest frequency, suitable for emergency scenarios where users trigger SOS for help.

[0094] Step 240: Control the positioning system of the wearable device to execute the target positioning strategy.

[0095] The strategy execution process is deployed at the firmware layer of the smart wearable device. It receives the target positioning strategy output by the scene prediction module, controls the positioning system to execute the strategy, and achieves smooth switching of the strategy according to changes in the scene.

[0096] Strategy execution: According to the definition of the target positioning strategy, control the on / off status and working parameters (such as positioning frequency and scanning frequency) of each positioning module to ensure the effective collection and reporting of positioning data;

[0097] Strategy switching: When the scene prediction module predicts an impending scene change, or when real-time status information indicates that the current scene has changed, a strategy switch is triggered. During the switch, the continuity of positioning data is maintained to avoid positioning interruptions or delays, achieving a seamless transition.

[0098] Compared with the prior art, the present invention has the following significant advantages:

[0099] 1. Achieve a dynamic balance between accuracy and power consumption: The positioning strategy is adaptively adjusted based on the user's personalized behavior pattern. In critical scenarios (such as when moving or in unknown areas), a high-frequency precision mode is used to ensure positioning accuracy, while in non-critical scenarios (such as when stationary at home or in school), a low-power mode is used to reduce power consumption, significantly extending the device's battery life. Actual tests show that the device's battery life can be extended by 30%-50% compared to traditional positioning methods.

[0100] 2. Seamless switching of positioning strategies: By predicting scene changes in advance through the scene prediction module, the positioning strategy is adjusted in advance to avoid positioning delays or interruptions caused by passive response. Users do not need to manually intervene, realizing seamless switching of positioning modes and improving the user experience.

[0101] 3. Adapt to personalized behavioral patterns: Train a unique behavioral pattern model based on each user's historical behavioral data. The positioning strategy is highly adapted to the user's daily routine, solving the problem that traditional unified positioning strategies cannot meet the personalized needs of different users.

[0102] 4. Enhance product stickiness: The device automatically achieves optimal positioning management without the need for manual operation by the user, reducing the burden on the user. At the same time, the accurate positioning effect and long battery life increase the user's trust and dependence on the product, enhancing the product's market competitiveness.

[0103] 5. Privacy and security protection: Anonymization is used during data collection, and only necessary location-related data is uploaded to avoid leakage of user privacy information and ensure user data security.

[0104] To make the technical solution of the present invention clearer and more explicit, the present invention will be described in detail below with reference to specific embodiments.

[0105] The adaptive positioning system based on user behavior patterns of this invention is deployed on children's smartwatches and a supporting cloud platform. The system architecture includes a local layer and a cloud layer.

[0106] 1. Local layer (children's smartwatch): Deploys the data acquisition unit, scene prediction module, and strategy execution module of the behavior learning module. The hardware includes a GPS positioning module, LBS positioning module, Wi-Fi module, accelerometer, heart rate sensor, communication module, and processor. The processor is used to run local algorithms and schedule modules.

[0107] 2. Cloud Layer: Deploys the model training unit and model distribution unit of the behavior learning module. It has powerful computing resources to process massive amounts of historical data, train machine learning models, and distribute simplified models to the watch.

[0108] Example 1: Going to school.

[0109] 1. Data collection phase: The children's smartwatch continuously collects the user's (child's) time information, location information, GNSS satellite signal information, and movement status information. For example, it collects data on the user leaving home from 7:00 to 7:30 every Monday to Friday, being in a mobile state from 7:30 to 8:00, and stabilizing in the school area after 8:00. The relevant data is uploaded to the cloud in batches.

[0110] 2. Model training phase: The cloud uses clustering algorithms to identify two frequently visited hotspots, home and school, and builds geofences for them respectively (the radius of the home fence is set to 50 meters and the radius of the school fence is set to 200 meters). It also mines the user's behavioral patterns of "going to school from 7:00 to 8:00 on weekdays and being at school from 8:00 to 17:00", generates a behavioral pattern model, and sends it to the watch.

[0111] 3. Scene Prediction Phase: At 7:00 AM on Monday, the scene prediction module on the watch obtains the current time of 7:00 AM and the real-time motion status (stationary). Combined with the behavior pattern model, it predicts the user's upcoming mobile scene on their way to school.

[0112] 4. Strategy Execution Phase: Before 7:00, the user remains stationary at home, and the watch executes a low-power monitoring mode (LBS locates the user every 30 minutes); at 7:00, the scene prediction module triggers a strategy switch, switching the positioning strategy to standard power-saving mode 2 minutes in advance (7:02) (LBS locates the user every 5 minutes, Wi-Fi scans the user every 10 minutes); at 7:05, the user begins to move, the accelerometer detects the change in motion, and Wi-Fi and LBS detect the change in location, immediately triggering a high-frequency accurate mode (GPS locates the user every 1 minute), continuously reporting accurate trajectories; at 8:00, the user enters the school's geofence and the motion state changes to stationary, the watch confirms after a 5-minute delay (to avoid passing by), and then switches back to low-power monitoring mode.

[0113] Example 2: Nighttime sleep scenario.

[0114] 1. Data collection phase: The watch collects data showing that the user's location is stable at home after 22:00 every day, the heart rate sensor detects a stable heart rate, and the movement status is stationary;

[0115] 2. Model training phase: The behavioral pattern of users sleeping at home from 22:00 to 6:00 the next day is mined in the cloud, updated to the behavioral pattern model and distributed;

[0116] 3. Scene Prediction Phase: At 22:00, the watch obtains the current time, location data within the home's geofence, stable heart rate, and resting state to predict whether the user will enter a sleep scene;

[0117] 4. Strategy execution phase: At 22:05, the watch switches to deep sleep mode, maintaining only basic communication standby and turning off all positioning modules and unnecessary sensors; at 6:30 the next day, based on the behavioral pattern model, it predicts that the user will wake up soon, and switches to low power monitoring mode 10 minutes in advance (6:20) to prepare for the user's activities after waking up.

[0118] Example 3: Weekend Outing Scene

[0119] 1. Data collection phase: On weekends, users go to unfamiliar parks with their parents. The watch collects location data that exceeds the geofence of all regular hotspots, and the movement status is walking.

[0120] 2. Scene Prediction Phase: The scene prediction module on the watch detects that the current location is not within a persistent hotspot, and combined with the user's movement status (walking), predicts that the user is in an unknown area.

[0121] 3. Strategy Execution Phase: The high-frequency precision mode is immediately triggered, with GPS, LBS, and Wi-Fi working simultaneously, and location data is reported every minute; when a user stays still in a certain area of ​​the park for more than 30 minutes, the system switches to the standard power-saving mode; when the user leaves the park, the change in location triggers the high-frequency precision mode until the user returns to their usual hotspot (home), and then switches to the low-power monitoring mode after a 5-minute delay.

[0122] Example 4: SOS emergency scenario.

[0123] When a user encounters an emergency and manually triggers the watch's SOS function, the policy execution module immediately activates the SOS emergency mode. The GPS, LBS, and Wi-Fi positioning modules operate at full power, and the location data reporting frequency increases to once per second. At the same time, the positioning data and emergency help information are sent to the preset contacts through the communication module to ensure user safety.

[0124] Based on the same technological concept Figure 3 An exemplary embodiment of the present invention illustrates the structure of an adaptive positioning device based on user behavior patterns, which can execute an adaptive positioning process based on user behavior patterns.

[0125] like Figure 3 As shown, the device may include:

[0126] The acquisition unit 310 is used to acquire current time information and real-time status information of the wearable device;

[0127] The processing unit 320 is configured to predict a scenario based on a behavior pattern model according to the current time information and the real-time status information of the wearable device; the behavior pattern model is trained by a machine learning model based on the user's historical spatiotemporal data; according to the predicted scenario, adaptively select a target positioning strategy from a plurality of preset positioning strategies; and control the positioning system of the wearable device to execute the target positioning strategy.

[0128] Optionally, the processing unit 320 is specifically used for:

[0129] Collect users’ historical spatiotemporal data, which includes time information and location information;

[0130] Based on the historical spatiotemporal data, a user behavior pattern model is generated through training a machine learning model.

[0131] Optionally, the processing unit 320 is specifically used for:

[0132] Clustering algorithms are used to analyze the location data in the historical spatiotemporal data to automatically identify users' frequent hotspots;

[0133] Build a geofence for each of the aforementioned permanent hotspots and set the fence radius parameter;

[0134] Based on the location and time information in the historical spatiotemporal data, the user's movement trajectory and timestamp information are analyzed to mine the user's time patterns and generate a behavioral pattern model that includes the coordinates of frequently visited hotspots, geofence parameters, and time patterns.

[0135] Optionally, the real-time status information includes coarse LBS location data, motion status data, and real-time data from device sensors;

[0136] The real-time data from the device's sensors includes heart rate sensor data and accelerometer data.

[0137] Optionally, the preset multiple positioning strategies include:

[0138] Deep sleep mode, low power monitoring mode, standard power saving mode, high frequency precision mode, and SOS emergency mode.

[0139] Based on the same technical concept, embodiments of the present invention also provide a computing device, including:

[0140] Memory, used to store program instructions;

[0141] The processor is used to call the program instructions stored in the memory and execute the above-mentioned adaptive positioning method based on user behavior patterns according to the obtained program.

[0142] Based on the same technical concept, embodiments of the present invention also provide a computer-readable non-volatile storage medium, including computer-readable instructions, which, when read and executed by a computer, cause the computer to execute the aforementioned adaptive positioning method based on user behavior patterns.

[0143] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0144] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0145] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0146] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0147] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for adaptive positioning based on user behavior patterns, characterized in that, The method comprises the following steps: acquiring current time information and real-time state information of the wearable device; predicting a predicted scenario based on a behavior pattern model according to the current time information and the real-time state information of the wearable device; the behavior pattern model is obtained by training a machine learning model based on historical spatio-temporal data of a user; adaptively selecting a target positioning strategy from a plurality of preset positioning strategies according to the predicted scenario; controlling a positioning system of the wearable device to execute the target positioning strategy.

2. The method of claim 1, wherein, The behavior pattern model is obtained by training a machine learning model based on historical spatio-temporal data of a user, which comprises the following steps: collecting historical spatio-temporal data of the user, wherein the historical spatio-temporal data comprises time information and location information; training a machine learning model based on the historical spatio-temporal data to generate a behavior pattern model of the user.

3. The method of claim 2, wherein, The behavior pattern model is obtained by training a machine learning model based on the historical spatio-temporal data, which comprises the following steps: analyzing location data in the historical spatio-temporal data by using a clustering algorithm to automatically identify a user's resident hot spot; constructing a geofence for each resident hot spot and setting a fence radius parameter; analyzing a user's moving track and timestamp information based on location information and time information in the historical spatio-temporal data to mine the user's time regularity and generate a behavior pattern model containing coordinates of the resident hot spot, parameters of the geofence and the time regularity.

4. The method of claim 1, wherein, The real-time state information comprises coarse LBS location data, motion state data and real-time data of a device sensor; The real-time data of the device sensor comprises heart rate sensor data and accelerometer data.

5. The method according to any one of claims 1 to 4, characterized in that, The plurality of preset positioning strategies comprise: a deep sleep mode, a low-power consumption monitoring mode, a standard power saving mode, a high-frequency precision mode and an SOS emergency mode.

6. An adaptive positioning device based on user behavior patterns, characterized by, The method comprises the following steps: an acquisition unit is configured to acquire current time information and real-time state information of a wearable device; a processing unit is configured to predict a predicted scenario based on a behavior pattern model according to the current time information and the real-time state information of the wearable device; the behavior pattern model is obtained by training a machine learning model based on historical spatio-temporal data of a user; adaptively select a target positioning strategy from a plurality of preset positioning strategies according to the predicted scenario; and control a positioning system of the wearable device to execute the target positioning strategy.

7. The apparatus of claim 6, wherein, The processing unit is specifically configured to: collect historical spatio-temporal data of a user, wherein the historical spatio-temporal data comprises time information and location information; train a machine learning model based on the historical spatio-temporal data to generate a behavior pattern model of the user.

8. The apparatus of claim 6, wherein, The processing unit is specifically configured to: analyze location data in the historical spatio-temporal data by using a clustering algorithm to automatically identify a user's resident hot spot; construct a geofence for each resident hot spot and set a fence radius parameter; analyze a user's moving track and timestamp information based on location information and time information in the historical spatio-temporal data to mine the user's time regularity and generate a behavior pattern model containing coordinates of the resident hot spot, parameters of the geofence and the time regularity.

9. A computing device, comprising: The method comprises the following steps: a memory is configured to store program instructions; a processor for invoking program instructions stored in the memory to perform the method of any of claims 1 to 5 according to the obtained program execution rights.

10. A computer-readable non-transitory storage medium, characterized in that, computer readable instructions that, when read and executed by a computer, cause the computer to perform the method of any of claims 1 to 5.

Images