Multi-source data fusion positioning method and device, equipment and storage medium

Abstract

The invention relates to the technical field of equipment positioning, in particular to a multi-source data fusion positioning method and device, equipment and a storage medium. The method is applied to wearable target equipment and comprises the steps that multi-source positioning data and inertial measurement data are acquired, the environment category of the equipment is identified based on the multi-source positioning data, weight distribution of positioning sources is dynamically adjusted according to the environment category, and the multi-source positioning data comprises positioning results generated by at least two heterogeneous positioning technologies; respectively calculating each positioning result and executing corresponding position calculation to obtain a plurality of equipment calculation positions; based on the adjusted weight distribution of each positioning source, performing weight fusion on each equipment calculation position to generate an initial fusion position; and performing error correction on the initial fusion position through inertial measurement data, and outputting a final equipment positioning coordinate. According to the method and the device, a multi-source data positioning technology can be coordinated, and the positioning precision requirements of a user in various scenes are met.

Description

Technical Field

[0001] The present application relates to the technical field of device positioning, and in particular to a multi-source data fusion positioning method, apparatus, device and storage medium. Background Art

[0002] The rapid adoption of smart wearable devices has driven the deep integration of positioning technology. Real-time, accurate positioning has become a core user requirement, particularly in scenarios such as child safety monitoring, outdoor sports navigation, and personnel management in specialized industries. Current mainstream positioning technologies rely primarily on a single or limited combination of technologies, such as satellite navigation systems, base station signals, or Wi-Fi hotspots. Their effectiveness is limited by inherent flaws in the underlying technology.

[0003] Existing technical solutions typically use a static positioning mode, relying on satellite signals in open areas and switching to Wi-Fi or base station positioning indoors. However, in environments such as densely populated urban areas, complex indoor structures, and canyons, satellite signals are easily blocked, resulting in positioning failures. Wi-Fi and base station positioning, however, can cause positioning results to drift or even become completely unusable due to uneven infrastructure coverage or fluctuating signal strength. These solutions are unable to adaptively adjust positioning strategies based on real-time environmental changes, resulting in unstable positioning results in complex scenarios.

[0004] It can be seen that the singleness of the signal source and the fragmentation of technology make it difficult to improve positioning accuracy in multiple scenarios, making it difficult to meet users' demand for multi-scenario, high-reliability positioning services. Summary of the Invention

[0005] In order to overcome the shortcomings of the existing technology, the present application provides a multi-source data fusion positioning method, device, equipment and storage medium to coordinate the positioning technology of multi-source data to meet the user's positioning accuracy requirements in various scenarios.

[0006] The technical solution adopted by this application to solve its technical problems is:

[0007] In a first aspect, the present application provides a multi-source data fusion positioning method applied to a wearable target device, the method comprising:

[0008] Acquire multi-source positioning data and inertial measurement data, identify the type of environment in which the device is located based on the multi-source positioning data, and dynamically adjust the weight distribution of each positioning source according to the type of environment, wherein the multi-source positioning data includes positioning results generated by at least two heterogeneous positioning technologies;

[0009] Calculate each positioning result and perform corresponding position calculation to obtain multiple device calculated positions;

[0010] Based on the adjusted weight distribution of each positioning source, weighted fusion is performed on the calculated positions of each device to generate an initial fused position;

[0011] The initial fusion position is error corrected using the inertial measurement data to output final device positioning coordinates.

[0012] Optionally, the step of acquiring multi-source positioning data and inertial measurement data includes:

[0013] screening low-confidence data in the multi-source positioning data by using the confidence index corresponding to each positioning data, and filtering out all the low-confidence data to complete data validity screening;

[0014] Based on the timestamp of the pre-processed positioning data, the inertial measurement data is synchronously calibrated, and the multi-source positioning data that has completed data validity screening and the inertial measurement data that has completed synchronous calibration are integrated and output.

[0015] Optionally, the multi-source positioning data includes satellite positioning data, Wi-Fi positioning data, and base station positioning data, and the step of identifying the type of environment in which the device is located based on the multi-source positioning data includes:

[0016] Identify the current environment of the device as indoor or outdoor based on the historical positioning trajectory and the signal strength of the satellite positioning data;

[0017] assigning an initial weight to each of the positioning data based on the environment category;

[0018] The initial weights are dynamically adjusted according to the real-time data validity detection results to generate the current data weight distribution.

[0019] Optionally, the step of respectively calculating each positioning result and performing corresponding position calculation to obtain the calculated positions of multiple devices includes:

[0020] Determine a first calculated location based on a propagation time difference of satellite positioning data, determine a second calculated location based on fingerprint matching of Wi-Fi positioning data, and determine a third calculated location based on signal strength and location information of positioning data from multiple base stations;

[0021] The first calculated position, the second calculated position, and the third calculated position are integrated and output as a plurality of device calculated positions.

[0022] Optionally, the step of performing weighted fusion on the calculated positions of the devices based on the adjusted weight distribution of the positioning sources to generate an initial fused position includes:

[0023] Based on the dynamically adjusted weight distribution, performing a weighted average calculation on the first calculation position, the second calculation position, and the third calculation position;

[0024] The initial fusion position is generated according to the weighted average calculation result.

[0025] Optionally, the inertial measurement data includes acceleration sensor data and gyroscope data; before the step of performing error correction on the initial fusion position using the inertial measurement data, the method further includes:

[0026] Based on the time series integration operation of the acceleration sensor data, the velocity components of the device in each axis are calculated to determine the resultant velocity vector;

[0027] Obtaining the attitude angle and direction angle of the device based on the angular velocity integration calculation of the gyroscope data;

[0028] The resultant velocity vector, the direction angle, and the attitude angle are integrated into motion state parameters.

[0029] Optionally, the step of performing error correction on the initial fusion position using the inertial measurement data and outputting final device positioning coordinates includes:

[0030] Determining whether the device is in a stationary state based on the motion state parameters; if the device is stationary, outputting the initial fusion position as the final device positioning coordinates;

[0031] If the device is in motion, predict the next moment's position based on the motion state parameters, and compare the predicted position with the initial fusion position;

[0032] In response to the position deviation exceeding a preset threshold, the initial fusion position is dynamically corrected in combination with the acceleration sensor data and the direction angle, and the corrected position is output as the final device positioning coordinate.

[0033] In a second aspect, the present application provides a multi-source data fusion positioning device, comprising:

[0034] a multi-source data acquisition module, configured to acquire multi-source positioning data and inertial measurement data, identify the type of the device's environment based on the multi-source positioning data, and dynamically adjust the weight distribution of each positioning source based on the type of environment, wherein the multi-source positioning data includes positioning results generated by at least two heterogeneous positioning technologies;

[0035] A multi-source data calculation module is used to calculate each positioning result and perform corresponding position calculation to obtain the calculated positions of multiple devices;

[0036] A multi-source data fusion module is used to perform weighted fusion on the calculated positions of each of the devices based on the adjusted weight distribution of each of the positioning sources to generate an initial fused position;

[0037] The device positioning correction module is used to perform error correction on the initial fusion position using the inertial measurement data and output the final device positioning coordinates.

[0038] In a third aspect, the present application provides an electronic device, comprising:

[0039] one or more processors;

[0040] one or more memories;

[0041] and one or more computer programs, wherein the one or more computer programs are stored in the one or more memories, and the one or more computer programs include instructions that, when executed by the one or more processors, cause the electronic device to perform the above method.

[0042] In a fourth aspect, the present application provides a computer-readable storage medium, in which a program or instruction is stored. When the program or instruction is executed, the above method is implemented.

[0043] The beneficial effects of this application are: by integrating multiple heterogeneous positioning technologies and inertial measurement data through wearable target devices, the positioning accuracy and stability in complex environments are significantly improved. Specifically, multi-source positioning data (including satellite navigation, Wi-Fi, base stations and other signal sources) and inertial measurement data are collected simultaneously, and the system adjusts the weight distribution of various positioning technologies according to the adaptability of the current environment to ensure the best positioning effect; then, based on the adjusted weights, multiple positioning results are weightedly fused to generate an initial fused position; finally, the inertial measurement data is used to further correct the error of the initial fused position, thereby outputting the final precise positioning coordinates. This multi-source data fusion positioning method not only overcomes the positioning limitations of a single technology in complex environments, but also realizes dynamic adjustment and precise correction, ensuring high-precision and high-reliability positioning services in a variety of scenarios, significantly improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of a multi-source data fusion positioning device provided in an embodiment of the present application;

[0045] Figure 2 This is a module interaction diagram of the system involved in the multi-source data fusion positioning method provided in an embodiment of the present application;

[0046] Figure 3 This is a virtual structural diagram of the multi-source data fusion positioning device provided by this application;

[0047] Figure 4 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] The present application is further described below with reference to the accompanying drawings and examples.

[0049] The following will clearly and completely describe the concept, specific structure and technical effects of this application in combination with the embodiments and drawings, so as to fully understand the purpose, characteristics and effects of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments of this application, other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application. In addition, all the connection / connection relationships involved in the patent do not refer to the direct connection of components, but refer to the formation of a better connection structure by adding or reducing connection accessories according to the specific implementation situation. The various technical features created in this application can be combined interactively without conflicting with each other.

[0050] Reference Figure 1 , Figure 1 This is a flow chart of a multi-source data fusion positioning device provided by an embodiment of the present application, which shows multiple core steps of the present application. The following are detailed descriptions of each step:

[0051] In step S1, multi-source positioning data and inertial measurement data are obtained, the environment category of the device is identified based on the multi-source positioning data, and the weight distribution of each positioning source is dynamically adjusted according to the environment category, wherein the multi-source positioning data includes positioning results generated by at least two heterogeneous positioning technologies.

[0052] It should be noted that in the embodiments of this application, the multi-source positioning data refers to a set of heterogeneous positioning results generated by different positioning technologies (such as satellite positioning, Wi-Fi positioning, and base station positioning), whose data sources are complementary; the inertial measurement data refers to real-time motion state parameters collected by accelerometers and gyroscopes, including acceleration, angular velocity, and other information. The purpose of this step is to dynamically adapt positioning strategies in different scenarios through the environmental perception capabilities of multi-source data.

[0053] In the embodiment of the present application, the multi-source positioning data includes satellite positioning data, Wi-Fi positioning data and base station positioning data. Figure 2 , Figure 2This is a module interaction diagram involved in the multi-source data fusion positioning method provided in the embodiment of the present application, which shows the module composition and signal interaction in the system involved in the embodiment of the present application, including a GPS module for receiving global positioning system satellite signals to achieve positioning in open outdoor environments; a Beidou module, which uses the Beidou satellite navigation system to enhance positioning capabilities in the country and specific areas; a base station positioning module, which interacts with mobile communication base stations to assist in positioning indoors or in areas with poor satellite signals; a Wi-Fi positioning module, which performs positioning based on surrounding Wi-Fi hotspot information to improve indoor positioning accuracy; an acceleration sensor, which detects the movement status of the wearer of the device and assists in positioning data correction; and a control chip, which serves as the core of the watch, coordinates the work of each module and processes positioning data.

[0054] Specifically, by analyzing satellite signal strength, historical positioning trajectory and current environmental characteristics (such as Wi-Fi hotspot density, base station coverage), the device's environmental category (such as indoor, outdoor or mixed scenarios) is identified, and an initial weight is assigned to each positioning source based on the environmental category. For example, in an open outdoor environment, the weight of satellite positioning data is higher (such as 0.7), while the weight of Wi-Fi positioning is lower (such as 0.1); after entering indoors, the weight of satellite positioning is reduced to 0.1, and the weight of Wi-Fi positioning is increased to 0.6. Among them, satellite signals include but are not limited to Beidou satellite signals and GPS satellite signals.

[0055] More specifically, satellite positioning data is obtained by continuously receiving satellite signals, parsing the satellite signals to obtain data such as longitude, latitude, altitude, timestamp, and PDOP (Position Dilution of Precision), and setting the output frequency at a certain interval, for example, outputting location information once every 1 second.

[0056] More specifically, Wi-Fi positioning data scans surrounding Wi-Fi hotspots to obtain the MAC address (Media Access Control Address), RSSI (Received Signal Strength Indication), channel parameters and other information of the hotspots, and constructs a pre-stored fingerprint database (Wi-Fi fingerprint database). The pre-stored fingerprint database calculates the device location through a fingerprint matching algorithm (such as the K-nearest neighbor algorithm or cosine similarity calculation). Specifically, the real-time collected Wi-Fi fingerprint is compared with the historical fingerprints in the database for similarity to match the optimal location coordinates.

[0057] More specifically, base station positioning data is obtained by communicating with nearby base stations to obtain information such as base station ID, signal strength, base station latitude and longitude, etc.

[0058] More specifically, inertial measurement data is collected through an accelerometer and a gyroscope. The accelerometer collects acceleration data of the device in the X, Y, and Z axis directions at a relatively high frequency (such as 100 Hz), while the gyroscope collects angular velocity data for calculating the movement direction and posture of the device.

[0059] Furthermore, in order to ensure the reliability of multi-source positioning data and avoid excessive offset of the position generated by unreliable positioning data affecting subsequent calculations or fusion, it is necessary to pre-process the data after obtaining each positioning data. Therefore, in the embodiment of the present application, the step of obtaining multi-source positioning data and inertial measurement data includes:

[0060] Low-confidence data in the multi-source positioning data are screened using the confidence index corresponding to each positioning data, and all the low-confidence data are filtered out to complete data validity screening.

[0061] Specifically, each type of positioning data is equipped with an indicator for determining the confidence level of the data. The indicator is then filtered and low-confidence abnormal data is removed based on the threshold corresponding to the indicator. In an embodiment of the present application, a PDOP threshold is preset for satellite positioning data (e.g., a PDOP value of 8). If the PDOP value corresponding to a single satellite positioning data is too high, indicating that its positioning accuracy is poor, the data is removed and no longer used in subsequent processing steps. For Wi-Fi positioning data and base station positioning data, a RSSI threshold is preset for determination. If the RSSI value of each signal strength is lower than the preset RSSI threshold (e.g., the preset RSSI threshold is -100dBm), the signal is considered too weak, the corresponding location information is unreliable, and it is removed.

[0062] Furthermore, based on the timestamp of the pre-processed positioning data, the inertial measurement data is synchronously calibrated, and the multi-source positioning data that has completed data validity screening and the inertial measurement data that has completed synchronous calibration are integrated and output.

[0063] Specifically, in the embodiment of the present application, after completing the validity screening of the multi-source positioning data and inertial measurement data, a timestamp synchronization calibration operation is performed to address the differences in sampling frequencies of different sensors. The synchronization calibration is achieved through a linear interpolation algorithm. Specifically, the high-frequency time series data of the acceleration sensor is resampled based on the timestamp of the positioning data, so that the motion parameters (such as speed and direction angle) in the inertial measurement data are strictly aligned with the time axis of the multi-source positioning data.

[0064] For example, in a specific embodiment, when the satellite positioning module outputs positioning coordinates at a frequency of 1 Hz and the acceleration sensor collects data at a frequency of 100 Hz, the system segments the acceleration data every 0.01 seconds according to the timestamp, and generates an acceleration sequence corresponding to the positioning moment (such as t = 1.0s, 2.0s) through linear interpolation to ensure that the motion state parameters and the positioning coordinates match at the same time node.

[0065] Furthermore, after completing the preprocessing of the multi-source positioning data and synchronizing with the data, it is necessary to identify the type of the environment in which the device is located based on the multi-source positioning data. In an embodiment of the present application, the step of identifying the type of the environment in which the device is located based on the multi-source positioning data includes:

[0066] Identify the current environment of the device as indoor or outdoor based on the historical positioning trajectory and the signal strength of the satellite positioning data;

[0067] assigning an initial weight to each of the positioning data based on the environment category;

[0068] The initial weights are dynamically adjusted according to the real-time data validity detection results to generate the current data weight distribution.

[0069] Specifically, it should be noted that, in the embodiment of the present application, the environmental category identification is achieved based on a joint analysis of the historical positioning trajectory and the signal strength of the satellite positioning data. Among them, the historical positioning trajectory refers to the geographic location sequence data of the device in a continuous time period, which is used to infer the movement trend and permanent area of ​​the device; the signal strength of the satellite positioning data (such as satellite signal-to-noise ratio, number of visible satellites, positioning precision factor PDOP) is used to evaluate the credibility of the current satellite signal. The purpose of this step is to determine whether the device is in an indoor or outdoor environment through multi-dimensional data fusion. For example, when the satellite signal strength is continuously lower than the threshold (such as PDOP>6) and the historical trajectory shows that the device enters the known building coordinate range, it is determined to be an indoor environment.

[0070] It should be noted that, in the embodiment of the present application, the environmental category identification is achieved based on a joint analysis of the historical positioning trajectory and the signal strength of the satellite positioning data. Among them, the historical positioning trajectory refers to the geographic location sequence data of the device in a continuous time period, which is used to infer the movement trend and permanent area of ​​the device; the signal strength of the satellite positioning data (such as satellite signal-to-noise ratio, number of visible satellites, positioning precision factor PDOP) is used to evaluate the credibility of the current satellite signal. The purpose of this step is to determine whether the device is in an indoor or outdoor environment through multi-dimensional data fusion. For example, when the satellite signal strength is continuously lower than the threshold (such as PDOP>6) and the historical trajectory shows that the device enters the known building coordinate range, it is determined to be an indoor environment.

[0071] Furthermore, the dynamic weight adjustment is achieved through real-time data validity detection. Real-time data validity detection includes: satellite signal quantity verification (if the number of visible satellites is <4, it is marked as inefficient data), Wi-Fi hotspot matching analysis (if the fingerprint database matching success rate is <80%, the weight is downgraded), and base station coverage radius verification (if the base station distance is >5 kilometers, it is eliminated). When it is detected that a positioning source data is invalid, the system reallocates the weight according to the preset ratio. For example, if the satellite signal fails due to obstruction, its weight is reduced from 0.7 to 0, the Wi-Fi weight is increased from 0.1 to 0.7, and the base station weight is increased from 0.1 to 0.3 to ensure positioning continuity.

[0072] For example, in one specific embodiment, when a device enters a shopping mall from outdoors, the satellite signal strength (PDOP value) increases from 3 to 9, the number of Wi-Fi hotspots increases from 2 to 8, and the base station signal strength drops from -90dBm to -105dBm. Based on a PDOP value > 6, the system determines that the device has entered an indoor environment and adjusts the satellite weight from 0.7 to 0.1, the Wi-Fi weight from 0.1 to 0.6, and the base station weight from 0.1 to 0.3. Simultaneously, the system detects a 95% success rate in Wi-Fi fingerprint matching and a base station distance of 200 meters. Therefore, the system maintains the dynamic weight distribution and outputs the final positioning coordinates.

[0073] In step S2, each positioning result is calculated and corresponding position calculation is performed to obtain multiple device calculated positions.

[0074] Specifically, in an embodiment of the present application, a first calculated position is determined based on the propagation time difference of satellite positioning data, a second calculated position is determined based on fingerprint matching of Wi-Fi positioning data, and a third calculated position is determined based on signal strength and position information of multiple base station positioning data; the first calculated position, the second calculated position, and the third calculated position are integrated and output as multiple device calculated positions.

[0075] More specifically, it should be noted that in the embodiments of the present application, the position calculation refers to the process of calculating device coordinates using specific algorithms for different positioning data sources. For example, satellite positioning data calculates longitude and latitude using the principle of triangulation, Wi-Fi positioning data calculates location using a fingerprint matching algorithm, and base station positioning data calculates location using trilateration. The purpose of this step is to independently calculate the raw data of each positioning source to generate multiple calculated position candidate sets, providing a basis for subsequent fusion. The calculation processes of each positioning source do not interfere with each other to avoid error transmission caused by coupling between technologies.

[0076] In step S3, based on the adjusted weight distribution of each positioning source, weighted fusion is performed on the calculated positions of each device to generate an initial fused position.

[0077] It should be noted that, in the embodiment of the present application, the weighted fusion refers to the process of mathematically superimposing multiple calculated positions according to weight distribution to generate a comprehensive positioning result. Its purpose is to improve positioning accuracy and reduce the risk of failure of a single technology through the complementarity of multi-source data. For example, in outdoor scenarios, the weight of satellite positioning is dominant, and the fusion result approaches the satellite calculated position; in indoor scenarios, the weights of Wi-Fi and base station positioning are increased, and the fusion result shifts toward the indoor positioning coordinates. In the embodiment of the present application, the weight distribution of each positioning source after adjustment is used to perform weighted fusion on the calculated positions of each device to generate an initial fused position, including:

[0078] Based on the dynamically adjusted weight distribution, performing a weighted average calculation on the first calculation position, the second calculation position, and the third calculation position;

[0079] The initial fusion position is generated according to the weighted average calculation result.

[0080] More specifically, weighted averaging can be performed using either linear or nonlinear weighting. Linear weighting involves directly adding the latitude and longitude coordinates of each calculated location according to their weights, while nonlinear weighting optimizes the fusion result using a Kalman filter or particle filter algorithm. For example, in one specific implementation, the system averages the latitude and longitude coordinates of the satellite-calculated location (weight 0.6), the Wi-Fi-calculated location (weight 0.3), and the base station-calculated location (weight 0.1) to generate the initial fused location. If satellite data fails abnormally, the system automatically increases the Wi-Fi weight to 0.7 and the base station weight to 0.3 to ensure positioning continuity.

[0081] In step S4, the initial fusion position is error corrected using the inertial measurement data, and the final device positioning coordinates are output.

[0082] It should be noted that in the embodiments of this application, error correction refers to using inertial measurement data (acceleration, angular velocity) to construct a motion model, predict the device's motion trajectory, and dynamically correct the positioning result by comparing the deviation between the predicted position and the initial fused position. The purpose is to eliminate the accumulated errors in multi-source fusion and improve positioning stability in dynamic scenarios.

[0083] Specifically, the inertial measurement data needs to be integrated with motion state parameters to facilitate subsequent position prediction. In an embodiment of the present application, the inertial measurement data includes acceleration sensor data and gyroscope data. Before the step of performing error correction on the initial fused position using the inertial measurement data, the method further includes:

[0084] Based on the time series integration operation of the acceleration sensor data, the velocity components of the device in each axis are calculated to determine the resultant velocity vector.

[0085] Specifically, based on the time series integration of the acceleration sensor data, the device's velocity components in the three axes (X / Y / Z) are calculated, and the resultant velocity vector is determined through vector synthesis. For example, in a wearable device, the acceleration sensor collects data at a frequency of 100Hz. An integration algorithm (such as trapezoidal integration or Simpson integration) converts the acceleration into instantaneous velocity components, ultimately generating a resultant velocity vector that includes the magnitude and direction of the velocity.

[0086] Furthermore, the attitude angle and direction angle of the device are obtained according to the angular velocity integration operation of the gyroscope data.

[0087] Specifically, based on the angular velocity data collected by the gyroscope, the device's attitude angle (including pitch and roll angles) and direction angle (yaw angle) are calculated using quaternion or Euler angle integration algorithms. For example, when the device tilts (such as when the user swings their arm), the pitch and roll angles obtained by the gyroscope integration are used to correct the interference of the device's attitude on the positioning signal.

[0088] The resultant velocity vector, the direction angle, and the attitude angle are integrated into motion state parameters.

[0089] Specifically, the resultant velocity vector is combined with the azimuth angle to construct complete motion state parameters. These include velocity magnitude, motion direction (represented by the resultant velocity vector), and the device's actual pointing direction (represented by the azimuth angle), providing multi-dimensional input for subsequent error correction.

[0090] Furthermore, after completing the integration of the motion state parameters, the fused position information is corrected using the motion state parameters. In an embodiment of the present application, the step of performing error correction on the initial fused position using the inertial measurement data and outputting the final device positioning coordinates includes:

[0091] Based on the motion state parameters, it is determined whether the device is in a stationary state; if the device is stationary, the initial fusion position is output as the final device positioning coordinate.

[0092] Specifically, based on the resultant velocity vector and azimuth angle in the motion state parameters, it is determined whether the device is in a stationary state. If the device is stationary (e.g., the modulus of the resultant velocity vector is less than 0.5 m / s and the rate of change of the azimuth angle is less than 1°),

[0093] The system directly outputs the initial fused position as the final positioning coordinate, avoiding additional errors introduced by motion noise. For example, when the user is indoors, the accelerometer detects that the speed is approaching zero, and the system stops the dynamic correction logic and maintains the initial fused position.

[0094] If the device is in motion, predict the next moment's position based on the motion state parameters, and compare the predicted position with the initial fusion position;

[0095] In response to the position deviation exceeding a preset threshold, the initial fusion position is dynamically corrected in combination with the acceleration sensor data and the direction angle, and the corrected position is output as the final device positioning coordinate.

[0096] Specifically, if the device is in motion (such as a combined velocity ≥ 0.5m / s), the system predicts the position at the next moment through the motion state parameters. The prediction is based on a kinematic model. For example, based on the current speed, direction angle and acceleration data, the position coordinates of the future time point are calculated by the uniform acceleration motion formula. The predicted position is compared with the initial fusion position. If the deviation exceeds a preset threshold (such as 5 meters), the dynamic correction mechanism is triggered. The dynamic correction adjusts the initial fusion position in combination with the acceleration sensor data and the direction angle. For example, when the deviation between the predicted position and the initial fusion position reaches a threshold, the system corrects the offset of the fusion position based on the consistency of the acceleration direction and the direction angle (such as the angle between the acceleration direction and the motion direction is less than 10°). The corrected coordinates are finally output as the final device positioning coordinates.

[0097] Reference Figure 3 , Figure 3 : is a virtual structural diagram of a multi-source data fusion positioning device provided by the present application. In a second aspect, the present application provides a multi-source data fusion positioning device, comprising:

[0098] A multi-source data acquisition module 100 is configured to acquire multi-source positioning data and inertial measurement data, identify the type of the device's environment based on the multi-source positioning data, and dynamically adjust the weight distribution of each positioning source based on the type of environment. The multi-source positioning data includes positioning results generated by at least two heterogeneous positioning technologies.

[0099] A multi-source data calculation module 200 is used to calculate each positioning result and perform corresponding position calculation to obtain multiple device calculated positions;

[0100] The multi-source data fusion module 300 is configured to perform weighted fusion on the calculated positions of the devices based on the adjusted weight distribution of the positioning sources to generate an initial fused position;

[0101] The device positioning correction module 400 is used to perform error correction on the initial fusion position using the inertial measurement data and output the final device positioning coordinates.

[0102] The multi-source data fusion positioning device described in the embodiment of the present application can execute the multi-source data fusion positioning method provided in the above embodiment. The multi-source data fusion positioning device has the corresponding functional steps and beneficial effects of the multi-source data fusion positioning method described in the above embodiment. Please refer to the embodiment of the above multi-source data fusion positioning method for details. The embodiment of the present application will not be repeated here.

[0103] The present application also provides an electronic device. Figure 4 , Figure 4 It is a structural diagram of an electronic device provided in an embodiment of the present application, and the electronic device may include a processor and a memory, wherein the processor and the memory may be connected by a bus or otherwise. The processor may be a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components and other chips, or a combination of the above-mentioned various chips. The memory, as a non-transient computer-readable storage medium, may be used to store non-transient software programs, non-transient computer executable programs and modules, such as the program instructions / modules corresponding to the multi-source data fusion positioning method in the embodiment of the present application. The processor executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory, i.e., realizing the multi-source data fusion positioning method in the above-mentioned method embodiment.

[0104] The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. The one or more modules are stored in the memory, and when executed by the processor, the multi-source data fusion positioning method as in the above-mentioned method embodiment is executed. The specific details of the above-mentioned electronic device can be understood by corresponding to the corresponding descriptions and effects in the above-mentioned method embodiment, and will not be repeated here. Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment method can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it may include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be read-only memory (ROM), random access memory (RAM), flash memory (Flash Memory), hard disk drive (HDD) or solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memory.

[0105] In the description provided herein, a large number of specific details are described. However, it is understood that the embodiments of the present application can be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0106] Similarly, it should be understood that in order to streamline the present disclosure and aid understanding of one or more of the various inventive aspects, in the above description of the exemplary embodiments of the present application, various features of the present application are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting an intention that the claimed application requires more features than are expressly recited in each claim. Rather, as reflected in the claims, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Accordingly, the claims that follow the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of the present application.

[0107] It should be noted that the above-mentioned embodiments illustrate rather than limit the invention and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims.

Claims

1. A multi-source data fusion positioning method, characterized in that: Applied to a wearable target device, the method includes: Acquire multi-source positioning data and inertial measurement data, identify the type of environment in which the device is located based on the multi-source positioning data, and dynamically adjust the weight distribution of each positioning source according to the type of environment, wherein the multi-source positioning data includes positioning results generated by at least two heterogeneous positioning technologies; Calculate each positioning result and perform corresponding position calculation to obtain multiple device calculated positions; Based on the adjusted weight distribution of each positioning source, weighted fusion is performed on the calculated positions of each device to generate an initial fused position; The initial fusion position is error corrected using the inertial measurement data to output final device positioning coordinates.

2. The multi-source data fusion positioning method according to claim 1, characterized in that: The step of obtaining multi-source positioning data and inertial measurement data includes: screening low-confidence data in the multi-source positioning data by using the confidence index corresponding to each positioning data, and filtering out all the low-confidence data to complete data validity screening; Based on the timestamp of the pre-processed positioning data, the inertial measurement data is synchronously calibrated, and the multi-source positioning data that has completed data validity screening and the inertial measurement data that has completed synchronous calibration are integrated and output.

3. The multi-source data fusion positioning method according to claim 1, characterized in that: The multi-source positioning data includes satellite positioning data, Wi-Fi positioning data, and base station positioning data. The step of identifying the type of environment in which the device is located based on the multi-source positioning data includes: Identify the current environment of the device as indoor or outdoor based on the historical positioning trajectory and the signal strength of the satellite positioning data; assigning an initial weight to each of the positioning data based on the environment category; The initial weights are dynamically adjusted according to the real-time data validity detection results to generate the current data weight distribution.

4. The multi-source data fusion positioning method according to claim 3, characterized in that: The step of respectively calculating each positioning result and performing corresponding position calculation to obtain the calculated positions of multiple devices includes: Determine a first calculated location based on a propagation time difference of satellite positioning data, determine a second calculated location based on fingerprint matching of Wi-Fi positioning data, and determine a third calculated location based on signal strength and location information of positioning data from multiple base stations; The first calculated position, the second calculated position, and the third calculated position are integrated and output as a plurality of device calculated positions.

5. The multi-source data fusion positioning method according to claim 4, characterized in that: The step of performing weighted fusion on the calculated positions of the devices based on the adjusted weight distribution of the positioning sources to generate an initial fused position includes: Based on the dynamically adjusted weight distribution, performing a weighted average calculation on the first calculation position, the second calculation position, and the third calculation position; The initial fusion position is generated according to the weighted average calculation result.

6. The multi-source data fusion positioning method according to claim 1, characterized in that: The inertial measurement data includes acceleration sensor data and gyroscope data; before the step of performing error correction on the initial fusion position using the inertial measurement data, the method further includes: Based on the time series integration operation of the acceleration sensor data, the velocity components of the device in each axis are calculated to determine the resultant velocity vector; Obtaining the attitude angle and direction angle of the device based on the angular velocity integration calculation of the gyroscope data; The resultant velocity vector, the direction angle, and the attitude angle are integrated into motion state parameters.

7. The multi-source data fusion positioning method according to claim 6, characterized in that: The step of performing error correction on the initial fusion position using the inertial measurement data and outputting the final device positioning coordinates includes: Determining whether the device is in a stationary state based on the motion state parameters; if the device is stationary, outputting the initial fusion position as the final device positioning coordinates; If the device is in motion, predict the next moment's position based on the motion state parameters, and compare the predicted position with the initial fusion position; In response to the position deviation exceeding a preset threshold, the initial fusion position is dynamically corrected in combination with the acceleration sensor data and the direction angle, and the corrected position is output as the final device positioning coordinate.

8. A multi-source data fusion positioning device, characterized in that: include: a multi-source data acquisition module, configured to acquire multi-source positioning data and inertial measurement data, identify the type of the device's environment based on the multi-source positioning data, and dynamically adjust the weight distribution of each positioning source based on the type of environment, wherein the multi-source positioning data includes positioning results generated by at least two heterogeneous positioning technologies; A multi-source data calculation module is used to calculate each positioning result and perform corresponding position calculation to obtain the calculated positions of multiple devices; A multi-source data fusion module is used to perform weighted fusion on the calculated positions of each of the devices based on the adjusted weight distribution of each of the positioning sources to generate an initial fused position; The device positioning correction module is used to perform error correction on the initial fusion position using the inertial measurement data and output the final device positioning coordinates.

9. An electronic device, characterized in that: include: one or more processors; one or more memories; and one or more computer programs, wherein the one or more computer programs are stored in the one or more memories, and the one or more computer programs include instructions that, when executed by the one or more processors, cause the electronic device to perform the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The storage medium stores a program or instruction, and when the program or instruction is executed, the method according to any one of claims 1 to 7 is implemented.

Images