WO2023216933A1 - 室内定位方法、装置、电子设备及介质 - Google Patents

室内定位方法、装置、电子设备及介质 Download PDF

Info

Publication number
WO2023216933A1
WO2023216933A1 PCT/CN2023/091676 CN2023091676W WO2023216933A1 WO 2023216933 A1 WO2023216933 A1 WO 2023216933A1 CN 2023091676 W CN2023091676 W CN 2023091676W WO 2023216933 A1 WO2023216933 A1 WO 2023216933A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
positioning
geomagnetic
electronic device
fingerprint
Prior art date
Application number
PCT/CN2023/091676
Other languages
English (en)
French (fr)
Inventor
洪伟评
张德竟
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2023216933A1 publication Critical patent/WO2023216933A1/zh

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G01S5/0252—Radio frequency fingerprinting
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/005—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 with correlation of navigation data from several sources, e.g. map or contour matching
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/04—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by terrestrial means
    • G01C21/08—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by terrestrial means involving use of the magnetic field of the earth
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/01—Determining conditions which influence positioning, e.g. radio environment, state of motion or energy consumption
    • G01S5/012—Identifying whether indoors or outdoors
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
    • G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
    • G01S5/0257—Hybrid positioning
    • G01S5/0258—Hybrid positioning by combining or switching between measurements derived from different systems
    • G01S5/02585—Hybrid positioning by combining or switching between measurements derived from different systems at least one of the measurements being a non-radio measurement
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information

Definitions

  • This application relates to the field of indoor positioning, and in particular to an indoor positioning method, device, electronic equipment and medium.
  • indoor positioning technology has become a research hotspot in the field of Location-based Services (LBS).
  • LBS Location-based Services
  • wireless fidelity Wireless Fidelity, Wi-Fi
  • base station-based methods radio frequency identification (Radio Frequency Identification, RFID)-based methods
  • Bluetooth Bluetooth-based methods.
  • Methods, etc., positioning methods based on wireless fidelity have gradually become the mainstream method of indoor positioning technology.
  • Existing indoor positioning methods based on wireless fidelity include an offline Wi-Fi fingerprint collection stage and an online positioning stage.
  • Wi-Fi fingerprints at different locations in the indoor environment are collected, and the Wi-Fi fingerprints are collected.
  • a set of data composed of the Wi-Fi fingerprint and the corresponding location is the location fingerprint, and multiple location fingerprints constitute the Wi-Fi fingerprint positioning database.
  • the user submits the currently collected Wi-Fi fingerprint to the positioning server, and by matching it with the location fingerprint in the Wi-Fi fingerprint location database, the location corresponding to the location fingerprint with the greatest similarity is used as the user's current location.
  • Wi-Fi fingerprint positioning database Because the positioning accuracy of indoor positioning methods based on wireless fidelity is greatly affected by the quality of the location fingerprint of the Wi-Fi fingerprint positioning database, and the Wi-Fi fingerprint in the location fingerprint has poor timeliness, such as changes in the indoor pattern, Wi-Fi -Indoor environment changes such as changes in the location of Fi hotspots will cause changes in Wi-Fi fingerprints, resulting in a decrease in positioning accuracy. Therefore, the location fingerprints in the Wi-Fi fingerprint positioning database need to be updated periodically. Manual updates are costly and The efficiency is low, and crowdsourcing collection methods are currently used to update the Wi-Fi fingerprint positioning database.
  • Crowdsourcing is a method of collecting location fingerprints. Multiple users collect real-time location fingerprints through electronic devices and submit them to the Wi-Fi fingerprint positioning database for update. Existing crowdsourcing collection usually uses the received satellite status or the user's walking state in indoor scenes as the triggering condition for crowdsourcing collection on electronic devices, and determines the triggering crowdsourced data through pedestrian dead reckoning technology (Pedestrian Dead Reckoning, PDR). The location when the packet was collected. Due to the limitations of the existing triggering conditions for crowdsourcing collection, it is difficult to effectively trigger the collection of crowdsourcing data in some areas of the indoor environment, such as entrances and exits of underground garages, elevators, escalators, etc., resulting in less crowdsourcing data corresponding to these areas.
  • PDR pedestrian dead reckoning technology
  • Figures 1 and 2 show the distribution of crowdsourced data collected in underground garages by existing crowdsourcing collection methods.
  • the collection of crowdsourcing data in the figure is concentrated in the middle area.
  • very little crowdsourced data is generated in areas where entrances and exits of underground garages such as elevators, escalators, and stairs are located, indicating that existing crowdsourcing collection solutions are difficult to trigger the collection of crowdsourced data in these entrances and exits.
  • Too little crowdsourced data collected in indoor areas will make it difficult to update the location fingerprints of corresponding areas in the Wi-Fi fingerprint positioning database in a timely manner, which will reduce the positioning accuracy of these areas.
  • pedestrian dead reckoning technology will cause The cumulative error is getting larger and larger, resulting in the accuracy of the location data in the crowdsourced data getting worse and worse, which will also reduce the positioning accuracy.
  • Embodiments of the present application provide an indoor positioning method, device, electronic equipment, and media to solve the problems of uneven distribution of crowdsourcing data and inaccurate location data in the prior art.
  • embodiments of the present application provide an indoor positioning method for a first electronic device.
  • the method includes:
  • the second electronic device determines the first Wi-Fi fingerprint positioning database according to the received first Wi-Fi fingerprint data.
  • Fi locates the position, determines the geomagnetic positioning position according to the geomagnetic data within the matching range of the geomagnetic positioning determined by the first Wi-Fi positioning position in the geomagnetic positioning database, and updates the Wi-Fi fingerprint positioning database.
  • the position of crowdsourced data in indoor positioning technology is data calculated through PDR technology.
  • the position calculated by PDR technology will accumulate errors over time, eventually leading to a decrease in positioning accuracy.
  • the location of crowdsourced data can be determined through geomagnetic positioning, avoiding the use of PDR technology for inference, improving the location accuracy of crowdsourced data, and thus improving positioning accuracy.
  • Wi-Fi fingerprint positioning technology and geomagnetic positioning technology are combined.
  • a rough positioning position is obtained through fast Wi-Fi fingerprint positioning, and then the corresponding geomagnetic positioning matching range is determined based on the rough positioning position.
  • the geomagnetic data It only needs to be matched within the determined geomagnetic positioning matching range, which can reduce the amount of geomagnetic data for matching, thereby improving the efficiency of geomagnetic positioning.
  • the current scene can be recognized without adding additional scene recognition equipment, which simplifies the device environment for scene recognition.
  • the sensor data of the sensor is obtained, and it is determined based on the sensor data that the current scene meets the conditions for triggering crowdsourcing data collection, including:
  • the sensor data is input into a preset scene recognition model, and based on the recognition results of the scene recognition model, it is determined that the current scene meets the conditions for triggering crowdsourcing data collection, including:
  • the sensor data is integrated into cross-floor status data, and the cross-floor status data is used as the input data of the scene recognition model, which can improve the accuracy of cross-floor scene recognition for driving.
  • the cross-floor status data includes: slope, angular velocity, linear velocity, height and driving trajectory.
  • the senor includes at least one of the following: an acceleration sensor, a gyroscope sensor, Air pressure sensor, gravity sensor, geomagnetic sensor.
  • the sensor data also includes signal data
  • the signal data includes data received by the first electronic device through the wireless communication module.
  • the first Wi-Fi fingerprint data at least includes the identification and received signal strength of the wireless fidelity access point.
  • the current scene is at least one of the following: indoor and outdoor scenes, driving and walking switching scenes, walking switching scenes, and driving and cross-floor scenes.
  • the method further includes:
  • the method further includes:
  • Crowdsourcing data is generated according to the received geomagnetic positioning position and the first Wi-Fi fingerprint data and sent to the second electronic device, so that the second electronic device updates the Wi-Fi fingerprint positioning database according to the received crowdsourcing data.
  • the geomagnetic positioning position also includes a geomagnetic positioning error.
  • the geomagnetic positioning error is greater than a preset error threshold, the generation of crowdsourcing data is stopped.
  • crowdsourcing data with inaccurate locations can be filtered, and crowdsourcing data with inaccurate locations can be avoided from being used to update the Wi-Fi fingerprint positioning database.
  • the method further includes:
  • crowdsourcing data collection is stopped.
  • the crowdsourcing data collection is controlled, the same electronic device is prevented from collecting too much crowdsourcing data, and the power consumption of the electronic device is reduced.
  • Embodiments of this application provide an indoor positioning method. This method determines that the current scene meets the conditions for triggering crowdsourcing data collection, and obtains the first Wi-Fi fingerprint data from multiple wireless fidelity access points and the first Wi-Fi fingerprint data collected by geomagnetic sensors. Geomagnetic data, sending the first Wi-Fi fingerprint data and the geomagnetic data collected by the geomagnetic sensor to the backend server. The backend server determines the first Wi-Fi positioning position in the Wi-Fi fingerprint positioning database based on the received first Wi-Fi fingerprint data.
  • the geomagnetic positioning position based on the geomagnetic data within the matching range of the geomagnetic positioning determined by the first Wi-Fi positioning position in the geomagnetic positioning database, and update the Wi-Fi fingerprint positioning database, so that the collected crowdsourcing data can be
  • the distribution in indoor areas is more uniform, and the location estimation of crowdsourced data is more accurate, which can improve the positioning accuracy during online positioning.
  • embodiments of the present application provide an indoor positioning method for a system including a first electronic device and a second electronic device.
  • the method includes:
  • the first electronic device determines that the current scene meets the conditions for triggering crowdsourcing data collection
  • the first electronic device acquires the first Wi-Fi fingerprint data from multiple wireless fidelity access points and the geomagnetic data collected by the geomagnetic sensor and sends them to the second electronic device;
  • the second electronic device determines the first Wi-Fi positioning position based on the received first Wi-Fi fingerprint data, determines the geomagnetic positioning position based on the geomagnetic data and the first Wi-Fi positioning position, and updates the Wi-Fi fingerprint positioning database. .
  • the second electronic device determines the first Wi-Fi positioning position according to the received first Wi-Fi fingerprint data, and determines the geomagnetic field according to the geomagnetic data and the first Wi-Fi positioning position.
  • Target location including:
  • the second electronic device determines the first Wi-Fi positioning position in the Wi-Fi fingerprint positioning database according to the received first Wi-Fi fingerprint data, and determines the first Wi-Fi positioning position in the geomagnetic positioning database according to the geomagnetic data. Determine the geomagnetic positioning position within the matching range of geomagnetic positioning.
  • the second electronic device updates the Wi-Fi fingerprint positioning database, including:
  • the second electronic device sends the geomagnetic positioning position to the first electronic device
  • the first electronic device generates crowdsourcing data based on the received geomagnetic positioning position and the first Wi-Fi fingerprint data and sends it to the second electronic device;
  • the second electronic device updates the Wi-Fi fingerprint positioning database according to the received crowdsourcing data.
  • an indoor positioning device which includes:
  • the determination module is used to determine that the current scene meets the conditions for triggering crowdsourcing data collection
  • An acquisition module used to acquire the first Wi-Fi fingerprint data from multiple wireless fidelity access points and the geomagnetic data collected by the geomagnetic sensor;
  • a sending module configured to send the first Wi-Fi fingerprint data and the geomagnetic data collected by the geomagnetic sensor to the second electronic device, so that the second electronic device can locate the first Wi-Fi fingerprint data in the Wi-Fi fingerprint positioning database according to the received first Wi-Fi fingerprint data.
  • Determine the first Wi-Fi positioning position determine the geomagnetic positioning position according to the geomagnetic data within the matching range of the geomagnetic positioning determined by the first Wi-Fi positioning position in the geomagnetic positioning database, and update the Wi-Fi fingerprint positioning database.
  • inventions of the present application provide an indoor positioning system.
  • the system includes a first electronic device and a second electronic device.
  • the first electronic device is used to determine that the current scene meets the conditions for triggering crowdsourcing data collection, and Obtain the first Wi-Fi fingerprint data from multiple wireless fidelity access points and the geomagnetic data collected by the geomagnetic sensor and send them to the second electronic device;
  • a second electronic device configured to determine the first Wi-Fi positioning position based on the received first Wi-Fi fingerprint data, determine the geomagnetic positioning position based on the geomagnetic data and the first Wi-Fi positioning position, and position the Wi-Fi fingerprint
  • the database is updated.
  • embodiments of the present application provide an electronic device, which includes:
  • a memory for storing instructions for execution by one or more processors of the electronic device, and a processor, being one of the processors of the electronic device, for performing the above-described first aspect and various possible implementations of the first aspect. Any indoor positioning method.
  • embodiments of the present application provide a readable storage medium. Instructions are stored on the readable storage medium. When the instructions are executed on an electronic device, the electronic device causes the electronic device to perform the above-mentioned first aspect and various possibilities of the first aspect. Any indoor positioning method in the implementation or any indoor positioning method in the above second aspect and various possible implementations of the second aspect.
  • embodiments of the present application provide a computer program product, including a computer program/instruction, which is characterized in that, when executed by a processor, the computer program/instruction implements the above-mentioned first aspect and various possible implementations of the first aspect. Any indoor positioning method in the above second aspect and any indoor positioning method in various possible implementations of the second aspect.
  • Figure 1 shows a schematic diagram of the distribution of crowdsourced data collected in an underground garage according to some embodiments of the present application.
  • Figure 2 shows a schematic diagram of the distribution of crowdsourced data collected in another underground garage according to some embodiments of the present application.
  • Figure 3 shows a schematic scene diagram of an indoor positioning method according to some embodiments of the present application.
  • Figure 4 shows a schematic diagram of geomagnetic positioning position and geomagnetic positioning error according to some embodiments of the present application.
  • Figure 5 shows a hardware structure diagram of an electronic device used for an indoor positioning method according to some embodiments of the present application.
  • Figure 6 shows a schematic flowchart of an indoor positioning method according to some embodiments of the present application.
  • Figure 7 shows a schematic diagram of a vehicle's cross-floor process in a cross-floor scenario according to some embodiments of the present application.
  • Figure 8 shows a schematic diagram of a vehicle's driving trajectory on different ramp types according to some embodiments of the present application.
  • Figure 9 shows a schematic structural diagram of an indoor positioning device according to some embodiments of the present application.
  • Figure 10 shows a hardware structure diagram of another electronic device used for an indoor positioning method according to some embodiments of the present application.
  • Illustrative embodiments of the present application include, but are not limited to, indoor positioning methods, devices, electronic devices, and media.
  • the processor may be a microprocessor, a digital signal processor, a microcontroller, etc., and/or any combination thereof.
  • the processor may be a single-core processor, a multi-core processor, etc., and/or any combination thereof.
  • the indoor positioning method of this application is suitable for scenarios where users use electronic devices to perform positioning in an indoor environment.
  • the trigger condition for crowdsourcing data collection is based on the satellite status received by the mobile phone or the user's walking status in the indoor environment.
  • the resulting position error leads to the problem of low positioning accuracy.
  • embodiments of the present application provide an indoor positioning method with higher positioning accuracy. Specifically, it is determined based on the sensor data from various sensors built into the electronic device that the current scene meets the conditions for triggering crowdsourcing data collection, and the obtained Wi-Fi fingerprint data and geomagnetic sensor collection from multiple Wi-Fi access points are The geomagnetic data is provided to the backend server for corresponding geomagnetic positioning to obtain the geomagnetic positioning position, and the Wi-Fi fingerprint positioning database is updated based on the Wi-Fi fingerprint data and geomagnetic positioning position, which can make the collected crowdsourcing data distributed in the indoor area. It is more uniform and can also collect crowdsourced data in some special areas. The location estimation of crowdsourced data is also more accurate, which can improve the positioning accuracy during online positioning.
  • FIG 3 is a schematic diagram of a scenario in which an electronic device performs crowdsourcing data collection and online positioning in the indoor positioning method according to the embodiment of the present application.
  • the scene includes an electronic device 100, a Wi-Fi positioning server 200, a geomagnetic positioning server 300, and Wi-Fi access points (Access Point, AP) 301, 302, 303, and 304.
  • Wi-Fi access points Access Point, AP
  • Wi-Fi access points 301, 302, 303, and 304 are used to send Wi-Fi signals to the outside, and the intensity of the sent Wi-Fi signals decreases as the transmission distance increases.
  • the Media Access Control (MAC) address of Wi-Fi access point 301 is MAC1
  • the MAC address of Wi-Fi access point 302 is MAC2
  • the MAC address of Wi-Fi access point 303 is MAC3
  • the MAC address of Wi-Fi access point 301 is MAC3.
  • the MAC address of Fi access point 304 is MAC4.
  • the four Wi-Fi access points in Figure 3 are only an example and do not constitute a limit on the number of Wi-Fi access points in the online positioning scenario.
  • the Wi-Fi access points in the embodiments of the present application The entry point can be any number of Wi-Fi access points that the electronic device 100 can scan.
  • the electronic device 100 receives the Wi-Fi signal sent by the Wi-Fi access point and determines the corresponding received signal strength (RSS), where the received signal from the Wi-Fi access point 301 The strength is RSS1, the received signal strength from Wi-Fi access point 302 is RSS2, the received signal strength from Wi-Fi access point 303 is RSS3, and the received signal strength from Wi-Fi access point 304 is RSS4.
  • the electronic device 100 sends the binary data composed of MAC1 and RSS1, MAC2 and RSS2, MAC3 and RSS3, MAC4 and RSS4 as Wi-Fi positioning data to the Wi-Fi positioning server 200.
  • the positioning server 200 locates the current location of the electronic device 100 according to the Wi-Fi positioning data.
  • the Wi-Fi positioning server 200 is configured to receive Wi-Fi positioning data sent by the electronic device 100, match the Wi-Fi positioning data in a pre-established Wi-Fi fingerprint positioning database, and determine whether the Wi-Fi positioning data in the database matches the Wi-Fi positioning data.
  • the Wi-Fi fingerprint with the highest similarity is used to determine the current location of the electronic device 100 based on the Wi-Fi fingerprint. For example, the location corresponding to the Wi-Fi fingerprint with the highest similarity can be used as the current location, or the location corresponding to the Wi-Fi fingerprint with the highest similarity can be used. Correlation calculations are performed on the locations corresponding to multiple Wi-Fi fingerprints near the Wi-Fi fingerprint, and the calculation results are used as the current location of the electronic device 100 and so on.
  • the Wi-Fi fingerprint positioning database is established in the offline Wi-Fi fingerprint collection phase. For example, the user can select the locations of multiple reference points in the indoor area, and simultaneously collect multiple references from different Wi-Fi access points at each reference point. The received signal strength value of the Wi-Fi access point received by multiple reference points is then used as a location fingerprint. Stored in the Wi-Fi fingerprint positioning database.
  • the electronic device 100 can use various built-in sensors such as acceleration sensor 180E, gyroscope sensor 180B, air pressure sensor 180C, gravity sensor, etc. and/or signal fingerprint data such as geomagnetic data and Wi-Fi signal data. , cellular signal (Global System for Mobile Communications, GSM) data, etc. to identify whether the current scene is a scene that triggers crowdsourcing data collection. By identifying the current scene, it can be determined whether the user is currently indoors and in an environment that can provide crowdsourcing data. If For scenarios that trigger crowdsourcing data collection, crowdsourcing data is collected and submitted to the Wi-Fi positioning server 200. If it is not a scenario that triggers crowdsourcing data collection, there is no need to collect crowdsourcing data.
  • GSM Global System for Mobile Communications
  • the crowdsourced data collected by the electronic device 100 may include the MAC address of the Wi-Fi access point, the received signal strength, and the current location of the electronic device 100 .
  • the electronic device 100 sends the MAC address and received signal strength of the Wi-Fi access point as Wi-Fi fingerprints to the Wi-Fi positioning server 200, and the Wi-Fi positioning server 200 determines the corresponding Wi-Fi location based on the Wi-Fi fingerprints. Fi locates the position and returns it to the electronic device 100 .
  • the electronic device 100 acquires geomagnetic data through the built-in geomagnetic sensor 180D, and sends the geomagnetic data and Wi-Fi positioning position to the geomagnetic positioning server 300 .
  • the geomagnetic positioning server 300 performs positioning based on the geomagnetic data and the Wi-Fi positioning position to obtain a more precise position and returns it to the electronic device 100.
  • the electronic device 100 uses the received more precise position as the current position of the electronic device 100.
  • the geomagnetic positioning server 300 is used to receive the geomagnetic data and Wi-Fi positioning position sent by the electronic device 100, and perform matching according to the geomagnetic data in the geomagnetic positioning database collected and established in advance manually. During the matching, all data in the geomagnetic positioning database will not be processed. Instead, the matching is performed within the matching range of the geomagnetic positioning determined by the Wi-Fi positioning position.
  • the matching results include the geomagnetic positioning position closest to the geomagnetic data in the database and the corresponding geomagnetic positioning error (uncertainty).
  • the geomagnetic positioning position can be represented by latitude and longitude data.
  • the geomagnetic positioning error is used to describe the maximum error value of the geomagnetic positioning position.
  • the error value The larger the value, the less accurate the geomagnetic positioning position.
  • the true position of the electronic device 100 can be any point within the black circle in the figure.
  • Y in the figure represents the uncertainty of geomagnetic positioning, that is, the geomagnetic positioning error.
  • the larger the radius Y the wider the range of the black circle.
  • the larger the circle the worse the accuracy of geomagnetic positioning.
  • the smaller the range of the black circle the higher the accuracy of geomagnetic positioning.
  • the geomagnetic positioning server 300 finally returns the closest geomagnetic positioning position and the corresponding geomagnetic positioning error to the electronic device 100 , and the electronic device 100 uses the received geomagnetic positioning position as the current position of the electronic device 100 .
  • the electronic device 100 sends the collected crowdsourcing data to the Wi-Fi positioning server 200.
  • the crowdsourcing data sent may include the MAC address MAC1 and RSS1 of the Wi-Fi access point 301, and the MAC of the Wi-Fi access point 302. addresses MAC2, RSS2, MAC addresses MAC3, RSS3 of the Wi-Fi access point 303, MAC addresses MAC4, RSS4 of the Wi-Fi access point 304, the current location of the electronic device 100, and the like.
  • the Wi-Fi positioning server 200 is configured to receive crowdsourcing data sent by the electronic device 100, generate a crowdsourcing database based on the crowdsourcing data, and update the corresponding location fingerprint in the Wi-Fi fingerprint positioning database based on the crowdsourcing data. Specifically, the Wi-Fi fingerprint of the corresponding location in the Wi-Fi fingerprint positioning database can be updated according to the current location of the electronic device 100 in the crowdsourcing data.
  • Wi-Fi positioning server 200 and the geomagnetic positioning server 300 can be the same server or different services. server, the embodiment of this application does not specifically limit this.
  • the electronic devices in the embodiments of the present application may include but are not limited to mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR)/virtual reality (VR) devices, notebook computers, Ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (personal digital assistants, PDAs), etc.
  • AR augmented reality
  • VR virtual reality
  • UMPCs Ultra-mobile personal computers
  • PDAs personal digital assistants
  • the sensor module 180 may include a pressure sensor 180A, a gyro sensor 180B, an air pressure sensor 180C, a geomagnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, and ambient light. Sensor 180L, bone conduction sensor 180M, etc.
  • the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 100 .
  • the electronic device 100 may include more or fewer components than shown in the figures, or some components may be combined, some components may be separated, or some components may be arranged differently.
  • the components illustrated may be implemented in hardware, software, or a combination of software and hardware.
  • the processor 110 may include one or more processing units, where different processing units may be independent devices or integrated in one or more processors.
  • the controller may be the nerve center and command center of the electronic device 100 .
  • the controller can generate operation control signals based on the instruction operation code and timing signals to complete the control of fetching and executing instructions.
  • the processor 110 may also be provided with a memory for storing instructions and data.
  • the memory in processor 110 is cache memory. This memory may hold instructions or data that have been recently used or recycled by processor 110 . If the processor 110 needs to use the instructions or data again, it can be called directly from the memory. Repeated access is avoided and the waiting time of the processor 110 is reduced, thus improving the efficiency of the system.
  • processor 110 may include one or more interfaces.
  • Interfaces may include integrated circuit (inter-integrated circuit, I2C) interface, integrated circuit built-in audio (inter-integrated circuit sound, I2S) interface, pulse code modulation (pulse code modulation, PCM) interface, universal asynchronous receiver and transmitter (universal asynchronous receiver/transmitter (UART) interface, mobile industry processor interface (MIPI), general-purpose input/output (GPIO) interface, subscriber identity module (SIM) interface, and /or universal serial bus (USB) interface, etc.
  • I2C integrated circuit
  • I2S integrated circuit built-in audio
  • PCM pulse code modulation
  • UART universal asynchronous receiver and transmitter
  • MIPI mobile industry processor interface
  • GPIO general-purpose input/output
  • SIM subscriber identity module
  • USB universal serial bus
  • the charging management module 140 is used to receive charging input from the charger.
  • the power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110.
  • the wireless communication function of the electronic device 100 can be implemented through the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor and the baseband processor.
  • the mobile communication module 150 can provide solutions for wireless communication including 2G/3G/4G/5G applied on the electronic device 100 .
  • the wireless communication module 160 can provide applications on the electronic device 100 including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) network), Bluetooth (Bluetooth, BT), and global navigation satellites.
  • WLAN wireless local area networks
  • WiFi wireless fidelity
  • Bluetooth Bluetooth
  • BT Bluetooth
  • global navigation satellites global navigation satellites
  • GNSS global navigation satellite system
  • frequency modulation frequency modulation, FM
  • NFC near field communication technology
  • infrared technology infrared, IR
  • the electronic device 100 implements display functions through a GPU, a display screen 194, an application processor, and the like.
  • the GPU is an image processing microprocessor and is connected to the display screen 194 and the application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering.
  • Processor 110 may Includes one or more GPUs that execute program instructions to generate or change display information.
  • the display screen 194 is used to display images, videos, etc.
  • Display 194 includes a display panel.
  • the electronic device 100 may include 1 or N display screens 194, where N is a positive integer greater than 1.
  • the electronic device 100 can implement the shooting function through an ISP, a camera 193, a video codec, a GPU, a display screen 194, an application processor, and the like.
  • the ISP is used to process the data fed back by the camera 193.
  • the ISP may be provided in the camera 193.
  • Camera 193 is used to capture still images or video. The object passes through the lens to produce an optical image that is projected onto the photosensitive element.
  • the photosensitive element may be.
  • the electronic device 100 may include 1 or N cameras 193, where N is a positive integer greater than 1.
  • Digital signal processors are used to process digital signals. In addition to digital image signals, they can also process other digital signals. For example, when the electronic device 100 selects a frequency point, the digital signal processor is used to perform Fourier transform on the frequency point energy.
  • Video codecs are used to compress or decompress digital video.
  • Electronic device 100 may support one or more video codecs.
  • the external memory interface 120 can be used to connect an external memory card.
  • the external memory card communicates with the processor 110 through the external memory interface 120 to implement the data storage function. Such as saving music, videos, etc. files in external memory card.
  • Internal memory 121 may be used to store computer executable program code, which includes instructions.
  • the processor 110 executes instructions stored in the internal memory 121 to execute various functional applications and data processing of the electronic device 100 .
  • the internal memory 121 may include a high-speed random access memory, and may also include a non-volatile memory.
  • the electronic device 100 can implement audio functions through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the headphone interface 170D, and the application processor. Such as music playback, recording, etc.
  • the audio module 170 is used to convert digital audio information into analog audio signal output, and is also used to convert analog audio input into digital audio signals. Audio module 170 may also be used to encode and decode audio signals.
  • Speaker 170A also called “speaker” is used to convert audio electrical signals into sound signals.
  • Receiver 170B also called “earpiece”, is used to convert audio electrical signals into sound signals.
  • Microphone 170C also called “microphone” or “microphone”, is used to convert sound signals into electrical signals.
  • the headphone interface 170D is used to connect wired headphones.
  • the pressure sensor 180A is used to sense pressure signals and can convert the pressure signals into electrical signals.
  • the gyro sensor 180B may be used to determine the motion posture of the electronic device 100 .
  • Air pressure sensor 180C is used to measure air pressure. In some embodiments, the electronic device 100 calculates the altitude through the air pressure value measured by the air pressure sensor 180C to assist positioning and navigation.
  • Geomagnetic sensor 180D includes a Hall sensor.
  • the acceleration sensor 180E can detect the acceleration of the electronic device 100 in various directions (generally three axes). When the electronic device 100 is stationary, the magnitude and direction of gravity can be detected. It can also be used to identify the posture of electronic devices and be used in horizontal and vertical screen switching, pedometer and other applications.
  • Distance sensor 180F for measuring distance. Electronic device 100 can measure distance via infrared or laser.
  • Proximity light sensor 180G may include, for example, a light emitting diode (LED) and a light detector, such as a photodiode.
  • the light emitting diode may be an infrared light emitting diode.
  • the ambient light sensor 180L is used to sense ambient light brightness.
  • the electronic device 100 can adaptively adjust the brightness of the display screen 194 according to the perceived ambient light brightness.
  • Fingerprint sensor 180H is used to collect fingerprints.
  • the electronic device 100 can use the collected fingerprint characteristics to achieve fingerprint unlocking, access to application locks, fingerprint photography, fingerprint answering of incoming calls, etc.
  • Temperature sensor 180J is used to detect temperature. In some embodiments, the electronic device 100 utilizes the temperature detected by the temperature sensor 180J to execute the temperature processing strategy.
  • Touch sensor 180K also called “touch panel”.
  • the touch sensor 180K can be disposed on the display screen 194.
  • the touch sensor 180K and the display screen 194 form a touch screen, which is also called a "touch screen”.
  • Bone conduction sensor 180M can acquire vibration signals.
  • the buttons 190 include a power button, a volume button, etc.
  • Key 190 may be a mechanical key. It can also be a touch button.
  • the electronic device 100 may receive key inputs and generate key signal inputs related to user settings and function control of the electronic device 100 .
  • the motor 191 can generate vibration prompts.
  • the motor 191 can be used for vibration prompts for incoming calls and can also be used for touch vibration feedback.
  • Indicator 192 may be an indicator light, It can be used to indicate charging status, power changes, messages, missed calls, notifications, etc.
  • the SIM card interface 195 is used to connect a SIM card.
  • the above describes the possible hardware structure of the electronic device 100. It can be understood that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the electronic device 100. In other embodiments of the present application, the electronic device 100 may include more or fewer components than shown in the figures, or some components may be combined, some components may be separated, or some components may be arranged differently. The components illustrated may be implemented in hardware, software, or a combination of software and hardware.
  • the execution subject of the indoor positioning method may be the processor of the electronic device 100, and may include the following steps:
  • Step S601 Obtain sensor data and/or signal data.
  • the scenarios that trigger crowdsourcing data collection may include but are not limited to: indoor and outdoor scenarios, driving and walking switching scenarios, walking switching scenarios, driving and cross-floor scenarios, etc.
  • indoor and outdoor scenes include scenes in which users drive or walk from an outdoor environment to an indoor environment; driving and walking switching scenarios include scenes in which users switch from driving to walking in an indoor environment; and walking switching scenarios include scenarios in which users switch from driving to walking.
  • the walking state on the same floor is switched to the elevator or escalator state, or the stair walking state; the driving cross-floor scene includes the scene where the user crosses floors by driving.
  • the electronic device 100 it is usually necessary to determine the current scene of the electronic device 100. For example, when determining whether it is in an indoor or outdoor scene, the moving speed and height of the electronic device 100 need to be known. , ambient light intensity, GSM signal reception intensity, etc. To obtain these states, it is necessary to use the acceleration sensor 180E, the gyroscope sensor 180B, the air pressure sensor 180C, the ambient light sensor and other sensors built in the electronic device 100 or the GSM wireless module, Wi-Fi wireless Modules, etc. collect data; when determining whether it is in a driving or walking switching scene or a walking switching scene, it is necessary to know the moving speed, moving direction, angular velocity, etc.
  • Gyroscope sensor 180B is used to collect data; when determining whether it is in a driving across floors scene, it is necessary to know the moving speed, moving direction, angular velocity, height, etc. of the electronic device 100. To obtain these states, the acceleration sensor 180E built into the electronic device 100 is required. , gyro sensor 180B, air pressure sensor 180C to collect data, etc.
  • the user's electronic device 100 can collect data from the built-in sensor 180 in real time.
  • the sensors may include but are not limited to: acceleration sensor 180E, gyroscope sensor 180B, air pressure sensor 180C, gravity sensor, etc., and then collect data based on the collected data.
  • the sensor data determines the scene in which the electronic device 100 is currently located through a pre-established scene recognition model.
  • the acceleration sensor 180E is a sensor used to measure acceleration. It usually consists of a mass block, a damper, an elastic element, a sensitive element and an adjustment circuit. During the acceleration process, the acceleration sensor 180E measures the inertial force exerted on the mass block. , use the law of inertia to obtain the acceleration value.
  • common acceleration sensors include capacitive, inductive, strain gauge, piezoresistive, piezoelectric, etc.
  • the gyro sensor 180B used in the electronic device 100 is a sensor for measuring angular velocity.
  • the working principle is to use the Coriolis force in physics to generate small capacitance changes internally, and then calculate the angular velocity based on the measured capacitance data.
  • the air pressure sensor 180C is a sensor used to measure atmospheric pressure.
  • the sensing element of some air pressure sensors is a pressure-sensitive film.
  • the film is connected to a flexible resistor. Changes in air pressure cause the deformation of the film to change the resistance of the flexible resistor. According to the measured resistance
  • the value determines the corresponding air pressure value;
  • the sensing element of some air pressure sensors is a variable capacitance silicon diaphragm box. Changes in air pressure will cause the deformation of the silicon diaphragm box, which in turn will cause changes in the capacitance capacity of the parallel plate of the silicon diaphragm box.
  • the air pressure is determined based on the capacitance value. value.
  • Gravity sensors are used to measure acceleration caused by gravity. They work based on the principle of the piezoelectric effect, that is, by changing the force caused by acceleration. The voltage generated when the medium deforms is measured to determine the corresponding acceleration value.
  • the sensor data obtained by the electronic device 100 may be data from one type of sensor or data from multiple types of sensors, and the embodiments of the present application do not specifically limit this.
  • the electronic device 100 can collect signal data received through the wireless communication module in real time.
  • the signal data may include but is not limited to Wi-Fi signal data, cellular signal data, etc., and then use the pre-established scenarios based on the signal data.
  • the recognition model determines the scene in which the electronic device 100 is currently located.
  • Step S602 Determine whether the current scene is a scene that triggers crowdsourcing data collection based on sensor data and/or signal data. If so, execute step S603 to collect crowdsourcing data. Otherwise, go to step S601 for execution.
  • the current scene of the electronic device 100 refers to the scene mode in which the electronic device 100 is currently located. Since the electronic device 100 is usually carried by the user or placed near the user, the current scene of the electronic device 100 can substantially reflect the scene mode in which the user is. Environmental scenes and user activity state scenes, these user-related scenes can be used to trigger the electronic device 100 to perform corresponding processing.
  • sensor data and/or signal data can be input into a pre-established scene recognition model to obtain model output results, and based on the model output results, it can be determined whether it belongs to a scene that triggers crowdsourcing data collection.
  • the scene recognition model may be a model using a machine learning algorithm.
  • the model uses sensor data and/or signal data as training data to train the machine learning algorithm. After the training is completed, a model that can be used for scene recognition is obtained. .
  • the scene recognition model may be one or more.
  • the scene recognition model may be a model that recognizes multiple scenes, or it may be multiple sub-models that recognize corresponding individual scenes.
  • the embodiments of the present application do not specifically limit this. This will be described in detail below.
  • Step S603 Collect crowdsourcing data.
  • the electronic device 100 After determining that the current scene is a scene that triggers crowdsourcing data collection, the electronic device 100 performs geomagnetic data acquisition and Wi-Fi scanning to collect crowdsourcing data.
  • the electronic device 100 acquires the geomagnetic data of the current location through the built-in geomagnetic sensor 180D, and sends the acquired geomagnetic data to the geomagnetic positioning server 300.
  • the geomagnetic positioning server 300 will use the received geomagnetic data in a pre-established Match in the geomagnetic positioning database, determine the geomagnetic positioning position corresponding to the geomagnetic data and the corresponding geomagnetic positioning error and return it to the electronic device 100 .
  • the electronic device 100 sends the Wi-Fi fingerprint obtained after performing Wi-Fi scanning to the Wi-Fi positioning server 200, and the Wi-Fi positioning server 200 adds the Wi-Fi fingerprint to the Wi-Fi fingerprint. Match in the positioning database, determine the Wi-Fi positioning position and the corresponding Wi-Fi positioning error and return it to the electronic device 100; the electronic device 100 sends the Wi-Fi positioning position and the geomagnetic data of the current position obtained through the geomagnetic sensor 180D to the geomagnetic Positioning server 300.
  • the geomagnetic positioning server 300 matches the received geomagnetic data within the matching range of the geomagnetic positioning determined by the Wi-Fi positioning position in the pre-established geomagnetic positioning database, and determines the geomagnetic positioning position corresponding to the geomagnetic data and the corresponding geomagnetic positioning. error.
  • Wi-Fi positioning to reduce the matching range of geomagnetic data in the geomagnetic positioning database, the matching speed of geomagnetic positioning can be accelerated, the accuracy of the geomagnetic positioning position can be improved, and the geomagnetic positioning error can be reduced.
  • the geomagnetic positioning server 300 sends the determined geomagnetic positioning position and the corresponding geomagnetic positioning error to the Wi-Fi positioning server 200, and the Wi-Fi positioning server 200 determines the geomagnetic positioning position according to the received Wi-Fi fingerprint and geomagnetic positioning error. Update the Wi-Fi fingerprint positioning database.
  • the geomagnetic positioning server 300 sends the determined geomagnetic positioning position and the corresponding geomagnetic positioning error to the electronic device 100, and the electronic device 100 generates the corresponding public information based on the Wi-Fi fingerprint and the received geomagnetic positioning position. Packet data.
  • the electronic device 100 when the geomagnetic positioning error received by the electronic device 100 exceeds a preset error threshold, the electronic device 100 does not generate corresponding Wi-Fi crowdsourcing data.
  • the geomagnetic positioning error exceeds the preset error threshold, indicating that the accuracy of geomagnetic positioning is poor.
  • the geomagnetic positioning position corresponding to the crowdsourcing data is inaccurate and cannot be used as valid crowdsourcing data.
  • crowdsourced data may include, but is not limited to, geomagnetic positioning locations, Wi-Fi fingerprint data, etc.
  • the Wi-Fi fingerprint data includes the identification of the Wi-Fi access point that the electronic device 100 can currently receive, such as the MAC address and the corresponding received signal strength.
  • determining the location of crowdsourced data based on geomagnetic positioning can improve the location accuracy of crowdsourced data, thereby improving the accuracy of positioning during online positioning.
  • the crowdsourcing data may include information about the current scene, such as the identification of the current scene, etc. By adding scene information to the crowdsourcing data, the crowdsourcing data can be classified according to the generated scene.
  • the collection of crowdsourcing data is stopped when the preset crowdsourcing collection stop conditions are met.
  • crowdsourcing collection stop conditions can be defined based on crowdsourcing collection requirements, such as “stop crowdsourcing collection when the number of crowdsourcing collection triggers exceeds the preset threshold in each scenario that triggers crowdsourcing data collection”; “electronic equipment If the crowdsourcing collection time on the day exceeds the preset time threshold, the crowdsourcing collection will be stopped”; “The storage space occupied by the crowdsourcing data collected on the electronic device on the day exceeds the preset storage threshold", etc.
  • Step S604 Submit the crowdsourcing data to the Wi-Fi positioning server 200 for data update.
  • the electronic device 100 sends the generated crowdsourcing data to the Wi-Fi positioning server 200.
  • the Wi-Fi positioning server 200 checks whether a Wi-Fi crowdsourcing database exists, and if not, generates a Wi-Fi crowdsourcing database. Fi crowdsourcing database and write the received crowdsourcing data, if it exists, directly write the received crowdsourcing data into the Wi-Fi crowdsourcing database.
  • the crowdsourcing data includes relevant information of the scene, and the crowdsourcing data can be stored in the Wi-Fi crowdsourcing database of the corresponding scene.
  • the crowdsourcing data generated in the driving and walking switching scene is stored in the corresponding driving database.
  • the Wi-Fi crowdsourcing database of the walking switching scene the crowdsourcing data generated in the walking switching scene is stored in the corresponding Wi-Fi crowdsourcing database of the walking switching scene.
  • the crowdsourcing data in the Wi-Fi crowdsourcing database can be used to update the Wi-Fi fingerprint positioning database.
  • the data in the Wi-Fi fingerprint positioning database is detected based on crowdsourcing data to identify whether there are changes in the Wi-Fi fingerprint. For example, the addition, reduction, aging, and moving location of Wi-Fi access points will cause Wi-Fi -Fi fingerprint changes. If a change in the Wi-Fi access point is detected and the data update conditions are met, the Wi-Fi fingerprint positioning database is updated using the crowdsourced data in the Wi-Fi crowdsourced database.
  • Data update conditions can be set in advance, for example, the data update cycle exceeds the preset update cycle threshold, or the number of Wi-Fi access points that the Wi-Fi fingerprint positioning database can match is less than the preset access point threshold.
  • the electronic device 100 first receives the Wi-Fi fingerprint of the Wi-Fi access point, such as the MAC address, received signal strength, etc.
  • the electronic device 100 only uses the Wi-Fi fingerprint positioning database for positioning.
  • the electronic device 100 sends the Wi-Fi fingerprint to the Wi-Fi positioning server 200, and the Wi-Fi positioning server 200 performs positioning according to the Wi-Fi fingerprint positioning database.
  • the Fi fingerprint is matched in the Wi-Fi fingerprint positioning database and the matched Wi-Fi positioning position is returned to the electronic device 100.
  • the electronic device 100 directly uses the received Wi-Fi positioning position as the current position of the electronic device.
  • the electronic device 100 uses the Wi-Fi fingerprint positioning database to assist in geomagnetic positioning. Specifically, the electronic device 100 sends the Wi-Fi fingerprint to the Wi-Fi positioning server 200, and the Wi-Fi positioning server 200 performs geomagnetic positioning based on The Wi-Fi fingerprint is matched in the Wi-Fi fingerprint positioning database and the matched Wi-Fi positioning position is returned to the electronic device 100 . The electronic device 100 then sends the Wi-Fi positioning position and the geomagnetic data collected through the built-in geomagnetic sensor 180D to the geomagnetic positioning server 300. The geomagnetic positioning server 300 determines the geomagnetic positioning based on the Wi-Fi positioning position in the geomagnetic positioning database based on the geomagnetic data. match within the matching range, and return the matched more accurate geomagnetic positioning position to the electronic device 100 , and the electronic device 100 uses the received geomagnetic positioning position as the current position of the electronic device.
  • the scene may be determined according to the sensor data and/or signal data of the electronic device 100. specific In other words, sensor data and/or signal data are input into a pre-established scene recognition model to perform scene recognition.
  • the training data of the scene recognition model is pre-collected sensor data.
  • the sensor data can have corresponding scene identifiers.
  • the machine learning algorithm outputs the corresponding predicted scene based on the input sensor data, and compares the output predicted scene with the actual scene.
  • the scenes are compared, and the parameters of the machine learning algorithm are continuously and iteratively optimized based on the loss function value of the comparison results, and the machine learning algorithm with the optimal parameters is used as the scene recognition model.
  • the scene recognition model can be trained according to the data of one sensor of the electronic device 100 , for example, the scene recognition model can be obtained by training according to the data of the acceleration sensor 180E , or can also be obtained by training according to the data of multiple sensors of the electronic device 100 . , for example, the scene recognition model is obtained by training based on the data of the acceleration sensor 180E and the air pressure sensor 180C, which is not specifically limited in the embodiment of the present application.
  • the training data is pre-collected signal data
  • the signal data is wireless data received by the electronic device 100, such as Wi-Fi signal data, GSM signal data, etc.
  • signal data can have corresponding scene identifiers, and the machine learning algorithm is trained based on the signal data to obtain a scene recognition model.
  • the training data may contain both sensor data and signal data.
  • the machine learning algorithm is trained based on the training data containing both sensor data and signal data to obtain a corresponding scene recognition model.
  • the embodiments of the present application do not specifically limit the type of training data. .
  • whether the current scene is an indoor or outdoor scene may be determined based on sensor data.
  • the outdoor data and indoor data of the sensors of the electronic device 100 can be collected in advance, the outdoor data is marked as outdoor, the indoor data is marked as indoor, and then the outdoor sensor data and the indoor sensor data are used as training
  • the data trains the neural network model to obtain a model for identifying indoor and outdoor scenes.
  • whether the electronic device 100 enters the room from the outdoors can be determined based on the change in the geomagnetic intensity received by the geomagnetic sensor 180D. Since the reinforced concrete structure in the building has a greater interference with the geomagnetic field, the electronic device 100 will be ground after entering the room from the outdoors. The intensity of the magnetic field changes greatly, so whether it is an indoor or outdoor scene can be judged based on the changes in the intensity of the geomagnetic field.
  • whether the electronic device 100 enters the room from the outside can be determined based on the change in the light intensity received by the ambient light sensor 180L.
  • the light intensity of the outdoor environment is usually higher than the light intensity of the room.
  • the light intensity There will be an obvious and continuous conversion process of intensity, and indoor and outdoor scenes can be judged by identifying changes in light intensity.
  • whether the current scene is an indoor or outdoor scene can also be determined based on the signal data received by the electronic device 100. There are usually certain differences between outdoor signal data and indoor signal data. By identifying these differences, indoor decisions can be made. Judgment of external scenes.
  • GSM signals are usually strong, while in indoor environments, GSM signals are usually weak.
  • GSM signals are usually weak.
  • electronic devices move from outdoor environments to indoor environments, the GSM signals received through GSM wireless modules will continue to weaken.
  • identifying the weakening process of GSM signals can identify indoor and outdoor scenes.
  • the number of satellites that can receive positioning signals is larger, while in an indoor environment, the number of satellites that can receive positioning signals is smaller.
  • the indoor and outdoor conditions can be determined by changing the number of satellites that can receive positioning signals. scene recognition.
  • the machine learning algorithm used for indoor and outdoor scene recognition can use algorithms that can currently be used for classification, which can include but are not limited to logistic regression algorithms, decision tree algorithms, neural network algorithms, support vector machines, etc.
  • Human activity recognition is based on sensor data to identify human activities. Human activities are usually typical activities, such as driving, walking, taking the elevator or escalator, walking up the stairs, etc.
  • human activity recognition may use the acceleration sensor 180E and gyroscope built in the electronic device 100
  • the data stream collected by the gyroscope sensor 180B is used to predict human activities.
  • the real-time data stream collected by the acceleration sensor 180E and the gyroscope sensor 180B is usually divided into sub-sequences called windows. These time series data are input into the human activity recognition model to predict the time. Predict human activities corresponding to sequence data.
  • the time series data of the acceleration sensor 180E and the gyroscope sensor 180B in the electronic device 100 carried by humans when performing different activities are collected in advance as training data, and the corresponding time series data are marked according to the actual human activities, and then
  • the training data is input into a neural network model such as a convolutional neural network model or a recursive neural network model for training, and the neural network model with optimal parameters is used as the human activity recognition model.
  • the human activity recognition model is only an example, and does not mean that only the data collected by the acceleration sensor 180E and the gyro sensor 180B can be used to train human activities.
  • the activity recognition model is trained.
  • the human activity recognition model can also be trained using data collected by the acceleration sensor 180E, the air pressure sensor 180C, and the gravity sensor. This embodiment of the present application does not specifically limit this.
  • the human activity recognition model can be any neural network model that can process time series data collected by the built-in sensor of the electronic device 100, such as convolutional neural networks (Convolutional Neural Networks, CNN), recursive neural networks (Recursive Neural Networks, RNN), Long Short-Term Memory Network (Long Short-Term Memory, LSTM), etc.
  • convolutional neural networks Convolutional Neural Networks, CNN
  • recursive neural networks Recursive Neural Networks, RNN
  • Long Short-Term Memory Network Long Short-Term Memory Network
  • whether it is a driving across floors scene can be determined based on data collected by a sensor built into the electronic device 100 .
  • the corresponding cross-floor status data can be determined based on the data stream collected by the sensor, and then the cross-floor status data can be used as training data to train the neural network model to obtain a cross-floor scene recognition model.
  • the cross-floor status data may include but is not limited to: slope, angular velocity, linear velocity, height, driving trajectory, etc.
  • Figure 7 shows the cross-floor status data of the vehicle when crossing the floor. As shown in Figure 7, when the vehicle crosses the floor, it will experience the process from the plane to the gentle slope section, and then to the normal slope section - gentle slope section - plane. , the slope will go through a process from small to large, and then from large to small, accompanied by an increase in height and a change in linear speed. In addition, if the vehicle crosses floors in a curved trajectory, there will also be a corresponding angular velocity.
  • cross-floor status data may be determined based on data streams collected by acceleration sensor 180E and gyro sensor 180B.
  • FIG. 8 shows the vehicle trajectories of different ramp types in the underground garage. As shown in Figure 8, vehicles will experience a large slope change and height drop when crossing floors on a straight long ramp, while on a curved round slope When crossing floors in the middle of the road, there will be a small slope change and height drop, and there will be angular velocity at the same time. When crossing floors in the jump spiral ramp, the angular velocity will last longer, and there will be continuous slope changes and height changes. Therefore, it is necessary to collect sensor data for different ramp types to determine the corresponding cross-floor status data, and train the neural network model based on the corresponding cross-floor status data to obtain a cross-floor scene recognition model capable of identifying multiple ramp types.
  • the cross-floor scene recognition model can be any neural network model that can process time series of cross-floor state data, such as convolutional neural networks (Convolutional Neural Networks, CNN), recursive neural networks (Recursive Neural Networks, RNN), long-term neural network models, etc. Short-term memory network (Long Short-Term Memory, LSTM), etc.
  • convolutional neural networks Convolutional Neural Networks, CNN
  • recursive neural networks Recursive Neural Networks, RNN
  • long-term neural network models etc.
  • Short-term memory network Long Short-Term Memory, LSTM
  • an indoor positioning device is also provided. As shown in Figure 9, the indoor positioning device includes:
  • Determination module 901 is used to determine that the current scene meets the conditions for triggering crowdsourcing data collection
  • the acquisition module 902 is used to acquire the first Wi-Fi fingerprint data from multiple wireless fidelity access points and the geomagnetic data collected by the geomagnetic sensor;
  • the sending module 903 is configured to send the first Wi-Fi fingerprint data and the geomagnetic data collected by the geomagnetic sensor to the second electronic device, so that the second electronic device can locate the first Wi-Fi fingerprint data in the Wi-Fi fingerprint positioning database according to the received first Wi-Fi fingerprint data.
  • Determine the first Wi-Fi positioning position in According to the geomagnetic data the geomagnetic positioning position is determined within the matching range of the geomagnetic positioning determined by the first Wi-Fi positioning position in the geomagnetic positioning database, and the Wi-Fi fingerprint positioning database is updated.
  • FIG. 10 shows a hardware structure block diagram of an electronic device 200 used for an indoor positioning method according to some embodiments of the present application.
  • the electronic device 200 may include one or more processors 201 , a system control logic 202 connected to at least one of the processors 201 , a system memory 203 connected to the system control logic 202 , and A non-volatile memory (NVM) 204 connected to the system control logic 202, and a network interface 206 connected to the system control logic 202.
  • NVM non-volatile memory
  • processor 201 may include one or more single-core or multi-core processors. In some embodiments, processor 201 may include any combination of general-purpose processors and special-purpose processors (eg, graphics processors, applications processors, baseband processors, etc.). In embodiments in which the electronic device 200 adopts an enhanced base station (Evolved Node B, eNB) or a radio access network (Radio Access Network, RAN) controller, the processor 201 may be configured to execute various conforming embodiments. For example, the processor 201 can be used to implement an indoor positioning method.
  • eNB enhanced base station
  • RAN Radio Access Network
  • system control logic 202 may include any suitable interface controller to provide any suitable interface to at least one of the processor 201 and any suitable device or component in communication with system control logic 202 .
  • system control logic 202 may include one or more memory controllers to provide an interface to system memory 203 .
  • System memory 203 may be used to load and store data and/or instructions.
  • the system memory 203 can load the data stored in the Wi-Fi fingerprint positioning database in the embodiment of the present application.
  • the system memory 203 of the electronic device 200 may include any suitable volatile memory, such as a suitable dynamic random access memory (Dynamic Random Access Memory, DRAM).
  • DRAM Dynamic Random Access Memory
  • NVM memory 204 may include one or more tangible, non-transitory computer-readable media for storing data and/or instructions.
  • the NVM memory 204 may include any suitable non-volatile memory such as flash memory and/or any suitable non-volatile storage device, such as a hard disk drive (Hard Disk Drive, HDD), a compact disk (Compact Disc, CD) drive, Digital Versatile Disc (Digital Versatile Disc, DVD) drive at least one.
  • the NVM memory 204 can be used to store data in the geomagnetic positioning database, etc.
  • NVM memory 204 may comprise a portion of storage resources on the device on which electronic device 200 is installed, or it may be accessed by the device but is not necessarily part of the device. For example, NVM memory 204 may be accessed over the network via network interface 206 .
  • system memory 203 and NVM memory 204 may include temporary copies and permanent copies of instructions 205, respectively.
  • the instructions 205 may include: Wi-Fi positioning server update instructions that when executed by at least one of the processors 201 cause the electronic device 200 to implement the method shown in FIG. 6 .
  • instructions 205, hardware, firmware, and/or software components thereof may additionally/alternatively be placed in system control logic 202, network interface 206, and/or processor 201.
  • Network interface 206 may include a transceiver for providing a radio interface for electronic device 200 to communicate with any other suitable device (eg, front-end module, antenna, etc.) over one or more networks.
  • network interface 206 may be integrated with other components of electronic device 200 .
  • network interface 206 may be integrated with at least one of processor 201 , system memory 203 , NVM memory 204 , and a firmware device (not shown) with instructions that when at least one of processor 201 executes the instructions When, the electronic device 200 implements the method as shown in the method embodiment.
  • the network interface 206 may be used to receive Wi-Fi fingerprint data, geomagnetic data, etc. sent by the first electronic device.
  • Network interface 206 may further include any suitable hardware and/or firmware to provide a multiple-input multiple-output radio interface.
  • network interface 206 may be a network adapter, a wireless network adapter, a telephone modem, and/or a wireless modem.
  • processors 201 may be packaged with logic for one or more controllers of the system control logic 202 to form a System In a Package (SiP). In some embodiments, at least one of processor 201 One may be integrated on the same die with logic for one or more controllers for system control logic 202 to form a System on Chip (SoC).
  • SoC System on Chip
  • Electronic device 200 may further include an input/output (I/O) device 207 .
  • the I/O device 207 may include a user interface that enables a user to interact with the electronic device 200; the peripheral component interface is designed to enable peripheral components to also interact with the electronic device 200.
  • the electronic device 200 further includes a sensor for determining at least one of environmental conditions and location information related to the electronic device 200 .
  • the user interface may include, but is not limited to, a display (e.g., a liquid crystal display, a touch screen display, etc.), a speaker, a microphone, one or more cameras (e.g., a still image camera and/or video camera), a flashlight (e.g., LED flash) and keyboard.
  • a display e.g., a liquid crystal display, a touch screen display, etc.
  • a speaker e.g., a speaker
  • a microphone e.g., a microphone
  • one or more cameras e.g., a still image camera and/or video camera
  • a flashlight e.g., LED flash
  • peripheral component interfaces may include, but are not limited to, non-volatile memory ports, audio jacks, and power interfaces.
  • sensors may include, but are not limited to, gyroscope sensors, accelerometers, proximity sensors, ambient light sensors, and positioning units.
  • the positioning unit may also be part of or interact with the network interface 206 to communicate with components of the positioning network (eg, Beidou satellites).
  • FIG. 10 does not constitute a specific limitation on the electronic device 200 .
  • the electronic device 200 may include more or less components than shown in the figures, or combine some components, or separate some components, or arrange different components.
  • the components illustrated may be implemented by hardware or software, or a combination of software and hardware.
  • Embodiments of the mechanisms disclosed in this application may be implemented in hardware, software, firmware, or a combination of these implementation methods.
  • Embodiments of the present application may be implemented as a computer program or program code executing on a programmable system including at least one processor, a storage system (including volatile and non-volatile memory and/or storage elements) , at least one input device and at least one output device.
  • Program code may be applied to input instructions to perform the functions described herein and to generate output information.
  • Output information can be applied to one or more output devices in a known manner.
  • a processing system includes any processor having a processor such as, for example, a Digital Signal Processor (DSP), a microcontroller, an Application Specific Integrated Circuit (ASIC), or a microprocessor. system.
  • DSP Digital Signal Processor
  • ASIC Application Specific Integrated Circuit
  • Program code may be implemented in a high-level procedural language or an object-oriented programming language to communicate with the processing system.
  • assembly language or machine language can also be used to implement program code.
  • the mechanisms described in this application are not limited to the scope of any particular programming language. In either case, the language may be a compiled or interpreted language.
  • IP cores may be stored on tangible computer-readable storage media and provided to multiple customers or production facilities for loading into the manufacturing machines that actually manufacture the logic or processors.
  • the disclosed embodiments may be implemented in hardware, firmware, software, or any combination thereof.
  • the disclosed embodiments may also be implemented as instructions carried on or stored on one or more transitory or non-transitory machine-readable (e.g., computer-readable) storage media, which may be operated by one or more processors Read and execute.
  • instructions may be distributed over a network or through other computer-readable media.
  • machine-readable media may include any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computer), including, but not limited to, floppy disks, optical disks, optical disks, read-only memories (CD-ROMs), magnetic Optical disc, Read Only Memory (ROM), Random Access Memory (RAM), Erasable Programmable Read Only Memory (EPROM), Electrically Erasable Programmable Memory Read memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), magnetic or optical card, flash memory, or used to use the Internet to transmit information through electrical, optical, acoustic or other forms of propagation signals (for example, carrier waves, infrared signals, digital signals etc.) tangible machine-readable storage.
  • Machine-readable media includes any type of machine-readable media suitable for storing or transmitting electronic instructions or information in a form readable by a machine (eg, computer).
  • each unit/module mentioned in each device embodiment of this application is a logical unit/module.
  • a logical unit/module can be a physical unit/module, or it can be a physical unit/module.
  • Part of the module can also be implemented as a combination of multiple physical units/modules.
  • the physical implementation of these logical units/modules is not the most important.
  • the combination of functions implemented by these logical units/modules is what solves the problem of this application. Key technical issues raised.
  • the above-mentioned equipment embodiments of this application do not introduce units/modules that are not closely related to solving the technical problems raised by this application. This does not mean that the above-mentioned equipment embodiments do not exist. Other units/modules.

Landscapes

  • Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Environmental & Geological Engineering (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Geology (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)

Abstract

一种室内定位方法、装置、电子设备及介质。其中，该方法通过确定出当前场景满足触发众包数据采集的条件，获取来自多个无线保真接入点的第一Wi-Fi指纹数据和地磁传感器采集的地磁数据，向后台服务器发送第一Wi-Fi指纹数据和地磁传感器采集的地磁数据，后台服务器根据接收的第一Wi-Fi指纹数据在Wi-Fi指纹定位数据库中确定第一Wi-Fi定位位置，并根据地磁数据在地磁定位数据库中由第一Wi-Fi定位位置确定的地磁定位的匹配范围内确定地磁定位位置，并对Wi-Fi指纹定位数据库进行更新。

Description

室内定位方法、装置、电子设备及介质
本申请要求于2022年05月12日提交中国专利局、申请号为202210517239.0、发明名称为“室内定位方法、装置、电子设备及介质”的中国专利申请的优先权，上述专利的全部内容通过引用结合在本申请中。
技术领域
本申请涉及室内定位领域，特别涉及一种室内定位方法、装置、电子设备及介质。
背景技术
当前，随着室内导航需求的不断增加，室内定位技术成为位置服务(Location-based Services，LBS)领域的研究热点。室内定位技术目前有多种技术实现方法，例如基于无线保真(Wireless Fidelity，Wi-Fi)的方法、基于基站的方法、基于射频识别(Radio Frequency Identification，RFID)的方法、基于蓝牙(BlueTooth)的方法等，基于无线保真的定位方法逐渐成为室内定位技术的主流方法。
现有基于无线保真的室内定位方法包括离线Wi-Fi指纹采集阶段和在线定位阶段，离线Wi-Fi指纹采集阶段中对室内环境不同位置的Wi-Fi指纹进行采集，并将Wi-Fi指纹与位置相对应，Wi-Fi指纹与对应位置组成的一组数据为位置指纹，多个位置指纹构成Wi-Fi指纹定位数据库。在线定位阶段中，用户将当前采集的Wi-Fi指纹提交给定位服务器，通过与Wi-Fi指纹定位数据库的位置指纹进行匹配，将相似度最大的位置指纹对应的位置作为用户当前的位置。
由于基于无线保真的室内定位方法的定位精度受到Wi-Fi指纹定位数据库的位置指纹的质量影响较大，而位置指纹中的Wi-Fi指纹的时效性较差，例如室内格局的改变、Wi-Fi热点位置变化等室内环境变化会造成Wi-Fi指纹的变化，从而导致定位精度下降，因此需要对Wi-Fi指纹定位数据库中的位置指纹进行周期性更新，以人工方式进行更新成本高、效率低，目前多采用众包采集方式对Wi-Fi指纹定位数据库进行更新。
众包采集是一种收集位置指纹的方式，多个用户通过电子设备采集实时位置指纹并提交给Wi-Fi指纹定位数据库用于更新。现有的众包采集通常根据接收的卫星状态或用户在室内场景中处于步行状态作为电子设备上众包采集的触发条件，并通过行人航位推算技术(Pedestrian Dead Reckoning，PDR)来确定触发众包采集时的位置。由于现有的众包采集的触发条件的限制，在室内环境的一些区域如地下车库的出入口、电梯、扶梯等难以有效触发众包数据的采集，使得这些区域对应的众包数据较少。图1和图2示出了现有众包采集方法在地下车库中采集的众包数据的分布情况。如图1所示，图中众包数据的采集集中在中间区域中，图中以虚线标记出的两个区域中众包数据很少，说明这两个区域中难以满足触发众包数据采集的条件。图2中可以看出地下车库的出入口如电梯、扶梯和楼梯所在区域产生的众包数据也很少，说明现有的众包采集方案也难以在这些出入口区域触发众包数据的采集。
室内区域中采集的众包数据太少会导致Wi-Fi指纹定位数据库中相应区域的位置指纹难以及时更新，会降低这些区域的定位精度。另外，行人航位推算技术会随着用户行走距离的增加导致 累计误差越来越大，导致众包数据中位置数据的准确性越来越差，同样会降低定位精度。
发明内容
本申请实施例提供了一种室内定位方法、装置、电子设备及介质，用于解决现有技术中众包数据分布不均匀和位置数据不准确的问题。
第一方面，本申请实施例提供了一种室内定位方法，用于第一电子设备，该方法包括：
确定出当前场景满足触发众包数据采集的条件；
获取来自多个无线保真接入点的第一Wi-Fi指纹数据和地磁传感器采集的地磁数据；
向第二电子设备发送第一Wi-Fi指纹数据和地磁传感器采集的地磁数据，以使第二电子设备根据接收的第一Wi-Fi指纹数据在Wi-Fi指纹定位数据库中确定第一Wi-Fi定位位置，并根据地磁数据在地磁定位数据库中由第一Wi-Fi定位位置确定的地磁定位的匹配范围内确定地磁定位位置，并对Wi-Fi指纹定位数据库进行更新。
可以理解，通常室内定位技术中众包数据的位置为通过PDR技术推算的数据，PDR技术推算的位置会随着时间的增加积累误差，最终导致定位精度下降，然而通过本申请的室内定位方法，能够通过地磁定位来确定众包数据的位置，避免使用PDR技术进行推算，提高了众包数据的位置准确性，进而能够提高定位精度。
通过上述方法，结合了Wi-Fi指纹定位技术和地磁定位技术，先通过快速的Wi-Fi指纹定位得到一个大致的定位位置，再根据该大致的定位位置确定相应的地磁定位匹配范围，地磁数据只需要在确定的地磁定位匹配范围内匹配，能够减少地磁数据进行匹配的数据量，从而提高地磁定位的效率。
在上述第一方面的一种可能的实现中，确定出当前场景满足触发众包数据采集的条件，包括：
获取传感器的传感器数据，并根据传感器数据确定出当前场景满足触发众包数据采集的条件。
通过上述方法，无需增加额外的场景识别设备即可实现当前场景的识别，简化了场景识别的设备环境。
在上述第一方面的一种可能的实现中，获取传感器的传感器数据，并根据传感器数据确定出当前场景满足触发众包数据采集的条件，包括：
获取传感器的传感器数据，并将传感器数据输入预设的场景识别模型，根据场景识别模型的识别结果确定出当前场景满足触发众包数据采集的条件。
通过上述方法，使用人工智能相关的场景识别模型对当前场景进行识别，能够提高场景识别的准确性。
在上述第一方面的一种可能的实现中，将传感器数据输入预设的场景识别模型，根据场景识别模型的识别结果确定出当前场景满足触发众包数据采集的条件，包括：
根据传感器数据，确定跨楼层状态数据；
将跨楼层状态数据输入场景识别模型，根据场景识别模型的识别结果确定当前场景是否为行车跨楼层场景。
通过上述方法，将传感器数据综合整理为跨楼层状态数据，将跨楼层状态数据作为场景识别模型的输入数据，能够提高对行车跨楼层场景识别的准确性。
在上述第一方面的一种可能的实现中，跨楼层状态数据包括：坡度、角速度、线速度、高度和行车轨迹。
在上述第一方面的一种可能的实现中，传感器至少包括如下一种：加速度传感器、陀螺仪传感器、 气压传感器、重力传感器、地磁传感器。
在上述第一方面的一种可能的实现中，传感器数据还包括信号数据，信号数据包括第一电子设备通过无线通信模块接收的数据。
在上述第一方面的一种可能的实现中，第一Wi-Fi指纹数据至少包括无线保真接入点的标识和接收信号强度。
在上述第一方面的一种可能的实现中，当前场景为下列中的至少一种：室内外场景、行车步行切换场景、步行切换场景和行车跨楼层场景。
在上述第一方面的一种可能的实现中，该方法还包括：
接收室内定位指令；
根据室内定位指令获取第二Wi-Fi指纹数据；
向第二电子设备发送第二Wi-Fi指纹数据，以使第二电子设备根据接收的第二Wi-Fi指纹数据在Wi-Fi指纹定位数据库中确定对应的第二Wi-Fi定位位置；
向第一电子设备发送第二Wi-Fi定位位置。
通过上述方法，使用通过众包数据进行数据更新后的Wi-Fi指纹定位数据库进行在线定位，能够提高在线定位的精度。
在上述第一方面的一种可能的实现中，该方法还包括：
接收第二电子设备发送的地磁定位位置；
根据接收的地磁定位位置和第一Wi-Fi指纹数据生成众包数据并向第二电子设备发送，以使第二电子设备根据接收的众包数据对Wi-Fi指纹定位数据库进行更新。
在上述第一方面的一种可能的实现中，地磁定位位置还包括地磁定位误差，当地磁定位误差大于预设的误差阈值时，停止生成众包数据。
通过上述方法，实现对位置不准确的众包数据的筛选，避免使用位置不准确的众包数据对Wi-Fi指纹定位数据库进行更新。
在上述第一方面的一种可能的实现中，该方法还包括：
当满足预设的众包数据采集停止条件时，停止众包数据的采集。
通过上述方法，实现对众包数据采集的控制，避免同一电子设备进行过多的众包数据采集，降低电子设备的功耗。
本申请实施例中提供了室内定位方法，该方法通过确定出当前场景满足触发众包数据采集的条件，获取来自多个无线保真接入点的第一Wi-Fi指纹数据和地磁传感器采集的地磁数据，向后台服务器发送第一Wi-Fi指纹数据和地磁传感器采集的地磁数据，后台服务器根据接收的第一Wi-Fi指纹数据在Wi-Fi指纹定位数据库中确定第一Wi-Fi定位位置，并根据地磁数据在地磁定位数据库中由第一Wi-Fi定位位置确定的地磁定位的匹配范围内确定地磁定位位置，并对Wi-Fi指纹定位数据库进行更新，能够使得采集的众包数据在室内区域中分布更加均匀，众包数据的位置估算也更加准确，能够提高在线定位时的定位精度。
第二方面，本申请实施例提供了一种室内定位方法，用于包括第一电子设备和第二电子设备的系统，该方法包括：
第一电子设备确定出当前场景满足触发众包数据采集的条件；
第一电子设备获取来自多个无线保真接入点的第一Wi-Fi指纹数据和地磁传感器采集的地磁数据并向第二电子设备发送；
第二电子设备根据接收的第一Wi-Fi指纹数据确定第一Wi-Fi定位位置，并根据地磁数据和第一Wi-Fi定位位置确定地磁定位位置，并对Wi-Fi指纹定位数据库进行更新。
在上述第二方面的一种可能的实现中，第二电子设备根据接收的第一Wi-Fi指纹数据确定第一Wi-Fi定位位置，并根据地磁数据和第一Wi-Fi定位位置确定地磁定位位置，包括：
第二电子设备根据接收的第一Wi-Fi指纹数据在Wi-Fi指纹定位数据库中确定第一Wi-Fi定位位置，并根据地磁数据在地磁定位数据库中由第一Wi-Fi定位位置确定的地磁定位的匹配范围内确定地磁定位位置。
在上述第二方面的一种可能的实现中，第二电子设备对Wi-Fi指纹定位数据库进行更新，包括：
第二电子设备向第一电子设备发送地磁定位位置；
第一电子设备根据接收的地磁定位位置和第一Wi-Fi指纹数据生成众包数据并向第二电子设备发送；
第二电子设备根据接收的众包数据对Wi-Fi指纹定位数据库进行更新。
第三方面，本申请实施例提供了一种室内定位装置，该装置包括：
确定模块，用于确定出当前场景满足触发众包数据采集的条件；
获取模块，用于获取来自多个无线保真接入点的第一Wi-Fi指纹数据和地磁传感器采集的地磁数据；
发送模块，用于向第二电子设备发送第一Wi-Fi指纹数据和地磁传感器采集的地磁数据，以使第二电子设备根据接收的第一Wi-Fi指纹数据在Wi-Fi指纹定位数据库中确定第一Wi-Fi定位位置，并根据地磁数据在地磁定位数据库中由第一Wi-Fi定位位置确定的地磁定位的匹配范围内确定地磁定位位置，并对Wi-Fi指纹定位数据库进行更新。
第四方面，本申请实施例提供了一种室内定位系统，该系统包括第一电子设备和第二电子设备，第一电子设备，用于确定出当前场景满足触发众包数据采集的条件，并获取来自多个无线保真接入点的第一Wi-Fi指纹数据和地磁传感器采集的地磁数据并向第二电子设备发送；
第二电子设备，用于根据接收的第一Wi-Fi指纹数据确定第一Wi-Fi定位位置，并根据地磁数据和第一Wi-Fi定位位置确定地磁定位位置，并对Wi-Fi指纹定位数据库进行更新。
第五方面，本申请实施例提供了一种电子设备，该电子设备包括：
存储器，用于存储由电子设备的一个或多个处理器执行的指令，以及处理器，是电子设备的处理器之一，用于执行上述第一方面以及第一方面的各种可能实现中的任意一种室内定位方法。
第六方面，本申请实施例提供了一种可读存储介质，可读存储介质上存储有指令，该指令在电子设备上执行时使电子设备执行上述第一方面以及第一方面的各种可能实现中的任意一种室内定位方法或上述第二方面以及第二方面的各种可能实现中的任意一种室内定位方法。
第七方面，本申请实施例提供了一种计算机程序产品，包括计算机程序/指令，其特征在于，该计算机程序/指令被处理器执行时实现上述第一方面以及第一方面的各种可能实现中的任意一种室内定位方法或上述第二方面以及第二方面的各种可能实现中的任意一种室内定位方法。
附图说明
图1根据本申请的一些实施例，示出了一种地下车库中采集的众包数据的分布情况示意图。
图2根据本申请的一些实施例，示出了另一种地下车库中采集的众包数据的分布情况示意图。
图3根据本申请的一些实施例，示出了一种室内定位方法的场景示意图。
图4根据本申请的一些实施例，示出了一种地磁定位位置与地磁定位误差的示意图
图5根据本申请的一些实施例，示出了一种用于室内定位方法的电子设备的硬件结构图。
图6根据本申请的一些实施例，示出了一种室内定位方法的流程示意图。
图7根据本申请的一些实施例，示出了一种车辆在跨楼层场景中跨楼层过程的示意图。
图8根据本申请的一些实施例，示出了一种车辆在不同坡道类型的行车轨迹示意图。
图9根据本申请的一些实施例，示出了一种室内定位装置的结构示意图。
图10根据本申请的一些实施例，示出了另一种用于室内定位方法的电子设备的硬件结构图。
具体实施方式
本申请的说明性实施例包括但不限于室内定位方法、装置、电子设备及介质。
可以理解，在本申请各实施例中，处理器可以是微处理器、数字信号处理器、微控制器等，和/或其任何组合。根据另一个方面，所述处理器可以是单核处理器，多核处理器等，和/或其任何组合。
可以理解，本申请的室内定位方法适用于用户通过电子设备在室内环境中进行定位的场景。
如前所述，现有的室内定位技术中，采用的是根据手机接收的卫星状态或室内环境中用户处于步行状态作为众包数据采集的触发条件，触发条件限制较多，存在难以在室内环境的部分区域，如出入口、电梯、扶梯、楼梯等触发众包数据采集，以及难以在用户处于非步行状态时触发众包数据采集的问题，进而导致室内定位数据不能及时更新，并且由于PDR技术带来的位置误差导致定位精度不高的问题。
为了解决该问题，本申请实施例提供了一种具有较高定位精度的室内定位方法。具体地，根据来自电子设备内置的多种传感器的传感器数据确定当前场景满足触发众包数据采集的条件，并将获得的来自多个Wi-Fi接入点的Wi-Fi指纹数据和地磁传感器采集的地磁数据提供给后台服务器进行相应的地磁定位得到地磁定位位置，并根据Wi-Fi指纹数据和地磁定位位置对Wi-Fi指纹定位数据库进行更新，能够使得采集的众包数据在室内区域中分布更加均匀，还能够在一些特殊区域进行众包数据采集，众包数据的位置估算也更加准确，进而能够提高在线定位时的定位精度。
下面将结合附图对本申请的实施例作进一步地详细描述。
图3为本申请实施例的室内定位方法中电子设备进行众包数据采集和在线定位的场景的示意图。如图3所示，该场景包括电子设备100、Wi-Fi定位服务器200、地磁定位服务器300和Wi-Fi接入点(Access Point，AP)301、302、303和304。
Wi-Fi接入点301、302、303和304用于向外发送Wi-Fi信号，发送的Wi-Fi信号的强度随着传输距离的增加而减小。Wi-Fi接入点301的媒体访问控制(Media Access Control，MAC)地址为MAC1，Wi-Fi接入点302的MAC地址为MAC2，Wi-Fi接入点303的MAC地址为MAC3，Wi-Fi接入点304的MAC地址为MAC4。
可以理解，图3中的4个Wi-Fi接入点仅仅是一种示例，并不构成对在线定位场景中Wi-Fi接入点数量的限制，本申请的实施例中的Wi-Fi接入点可以为电子设备100能够扫描到的任意数目的Wi-Fi接入点。
进行在线定位时，电子设备100接收Wi-Fi接入点发送的Wi-Fi信号并确定相应的接收信号强度(Received Signal Strength，RSS)，其中，接收的来自Wi-Fi接入点301的信号强度为RSS1，接收的来自Wi-Fi接入点302的信号强度为RSS2，接收的来自Wi-Fi接入点303的信号强度为RSS3，接收的来自Wi-Fi接入点304的信号强度为RSS4。电子设备100将由MAC1和RSS1、MAC2和RSS2、MAC3和RSS3、MAC4和RSS4组成的二元数据作为Wi-Fi定位数据发送给Wi-Fi定位服务器200，由Wi-Fi 定位服务器200根据Wi-Fi定位数据对电子设备100的当前位置进行定位。
Wi-Fi定位服务器200用于接收电子设备100发送的Wi-Fi定位数据，并将Wi-Fi定位数据在预先建立的Wi-Fi指纹定位数据库中进行匹配，确定数据库中与Wi-Fi定位数据相似度最高的Wi-Fi指纹，再根据该Wi-Fi指纹确定电子设备100的当前位置，例如可以将相似度最高的Wi-Fi指纹所对应的位置作为当前位置，也可以对相似度最高的Wi-Fi指纹附近的多条Wi-Fi指纹对应的位置进行相关计算，将计算结果作为电子设备100的当前位置等。
Wi-Fi指纹定位数据库在离线Wi-Fi指纹采集阶段中建立，例如用户可以在室内区域中选取多个参考点的位置，并在每个参考点同时采集多个来自不同Wi-Fi接入点的接收信号强度值，再将多个参考点接收到的Wi-Fi接入点的接收信号强度值、Wi-Fi接入点的MAC地址和参考点的位置组成的三元数据组作为位置指纹存储在Wi-Fi指纹定位数据库中。
在进行众包数据采集时，电子设备100可以通过内置的多种传感器如加速度传感器180E、陀螺仪传感器180B、气压传感器180C、重力传感器等和/或信号指纹数据如地磁数据、Wi-Fi信号数据、蜂窝信号(Global System for Mobile Communications，GSM)数据等识别当前场景是否为触发众包数据采集的场景，通过识别当前场景可以判断用户当前是否在室内并且处于可以提供众包数据的环境中，如果为触发众包数据采集的场景则进行众包数据的采集并提交给Wi-Fi定位服务器200，如果不是触发众包数据采集的场景则无需进行众包数据的采集。
电子设备100采集的众包数据可以包括Wi-Fi接入点的MAC地址、接收信号强度和电子设备100的当前位置。在此，电子设备100将Wi-Fi接入点的MAC地址、接收信号强度作为Wi-Fi指纹发送给Wi-Fi定位服务器200，Wi-Fi定位服务器200根据Wi-Fi指纹确定相应的Wi-Fi定位位置并返回给电子设备100。电子设备100通过内置的地磁传感器180D获取地磁数据，并将地磁数据和Wi-Fi定位位置发送给地磁定位服务器300。地磁定位服务器300根据地磁数据和Wi-Fi定位位置进行定位得到更精确位置并返回给电子设备100，电子设备100将接收的更精确位置作为电子设备100的当前位置。
地磁定位服务器300用于接收电子设备100发送的地磁数据和Wi-Fi定位位置，并根据地磁数据在预先以人工方式采集建立的地磁定位数据库中进行匹配，匹配时不进行地磁定位数据库中所有数据的匹配，而是在由Wi-Fi定位位置所确定的地磁定位的匹配范围中进行匹配。匹配结果包括数据库中与地磁数据最接近的地磁定位位置和相应的地磁定位误差(uncertainty)，地磁定位位置可以使用经纬度数据来表示，地磁定位误差用于描述地磁定位位置的最大误差值，误差值越大表明地磁定位位置越不准确。如图4所示，电子设备100的真实位置可以是图中黑色圈内的任何一点，图中的Y表示地磁定位的不确定性，即地磁定位误差，半径Y越大，黑色圈的范围越大，地磁定位的准确性越差，反之黑色圈的范围越小表明地磁定位的准确性越高。地磁定位服务器300最后将最接近的地磁定位位置和相应的地磁定位误差返回给电子设备100，电子设备100将接收的地磁定位位置作为电子设备100的当前位置。
电子设备100将采集的众包数据发送给Wi-Fi定位服务器200，例如，发送的众包数据可以包括Wi-Fi接入点301的MAC地址MAC1、RSS1、Wi-Fi接入点302的MAC地址MAC2、RSS2、Wi-Fi接入点303的MAC地址MAC3、RSS3、Wi-Fi接入点304的MAC地址MAC4、RSS4和电子设备100的当前位置等。
Wi-Fi定位服务器200用于接收电子设备100发送的众包数据，并根据众包数据生成众包数据库，还可以根据众包数据对Wi-Fi指纹定位数据库中相应的位置指纹进行更新。具体来说，可以根据众包数据中电子设备100的当前位置对Wi-Fi指纹定位数据库中对应位置的Wi-Fi指纹进行更新。
可以理解，Wi-Fi定位服务器200和地磁定位服务器300可以是同一台服务器，也可以是不同的服 务器，本申请实施例对此不作具体限制。
可以理解，本申请实施例中的电子设备可以包括但不限于手机、平板电脑、可穿戴设备、车载设备、增强现实(augmented reality，AR)/虚拟现实(virtual reality，VR)设备、笔记本电脑、超级移动个人计算机(ultra-mobile personal computer，UMPC)、上网本、个人数字助理(personal digital assistant，PDA)等，本申请实施例对电子设备的具体类型不作具体限制。
示例性的，图5示出了电子设备100的结构示意图。电子设备100可以包括处理器110，外部存储器接口120，内部存储器121，通用串行总线(universal serial bus，USB)接口130，充电管理模块140，电源管理模块141，电池142，天线1，天线2，移动通信模块150，无线通信模块160，音频模块170，扬声器170A，受话器170B，麦克风170C，耳机接口170D，传感器模块180，按键190，马达191，指示器192，摄像头193，显示屏194，以及用户标识模块(subscriber identification module，SIM)卡接口195等。其中传感器模块180可以包括压力传感器180A，陀螺仪传感器180B，气压传感器180C，地磁传感器180D，加速度传感器180E，距离传感器180F，接近光传感器180G，指纹传感器180H，温度传感器180J，触摸传感器180K，环境光传感器180L，骨传导传感器180M等。
可以理解的是，本申请实施例示意的结构并不构成对电子设备100的具体限定。在本申请另一些实施例中，电子设备100可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。图示的部件可以以硬件，软件或软件和硬件的组合实现。
处理器110可以包括一个或多个处理单元，其中，不同的处理单元可以是独立的器件，也可以集成在一个或多个处理器中。其中，控制器可以是电子设备100的神经中枢和指挥中心。控制器可以根据指令操作码和时序信号，产生操作控制信号，完成取指令和执行指令的控制。
处理器110中还可以设置存储器，用于存储指令和数据。在一些实施例中，处理器110中的存储器为高速缓冲存储器。该存储器可以保存处理器110刚用过或循环使用的指令或数据。如果处理器110需要再次使用该指令或数据，可从所述存储器中直接调用。避免了重复存取，减少了处理器110的等待时间，因而提高了系统的效率。
在一些实施例中，处理器110可以包括一个或多个接口。接口可以包括集成电路(inter-integrated circuit，I2C)接口，集成电路内置音频(inter-integrated circuit sound，I2S)接口，脉冲编码调制(pulse code modulation，PCM)接口，通用异步收发传输器(universal asynchronous receiver/transmitter，UART)接口，移动产业处理器接口(mobile industry processor interface，MIPI)，通用输入输出(general-purpose input/output，GPIO)接口，用户标识模块(subscriber identity module，SIM)接口，和/或通用串行总线(universal serial bus，USB)接口等。
充电管理模块140用于从充电器接收充电输入。电源管理模块141用于连接电池142，充电管理模块140与处理器110。
电子设备100的无线通信功能可以通过天线1，天线2，移动通信模块150，无线通信模块160，调制解调处理器以及基带处理器等实现。移动通信模块150可以提供应用在电子设备100上的包括2G/3G/4G/5G等无线通信的解决方案。无线通信模块160可以提供应用在电子设备100上的包括无线局域网(wireless local area networks，WLAN)(如无线保真(wireless fidelity，Wi-Fi)网络)，蓝牙(Bluetooth，BT)，全球导航卫星系统(global navigation satellite system，GNSS)，调频(frequency modulation，FM)，近距离无线通信技术(near field communication，NFC)，红外技术(infrared，IR)等无线通信的解决方案。
电子设备100通过GPU，显示屏194，以及应用处理器等实现显示功能。GPU为图像处理的微处理器，连接显示屏194和应用处理器。GPU用于执行数学和几何计算，用于图形渲染。处理器110可 包括一个或多个GPU，其执行程序指令以生成或改变显示信息。
显示屏194用于显示图像，视频等。显示屏194包括显示面板。在一些实施例中，电子设备100可以包括1个或N个显示屏194，N为大于1的正整数。
电子设备100可以通过ISP，摄像头193，视频编解码器，GPU，显示屏194以及应用处理器等实现拍摄功能。
ISP用于处理摄像头193反馈的数据。在一些实施例中，ISP可以设置在摄像头193中。
摄像头193用于捕获静态图像或视频。物体通过镜头生成光学图像投射到感光元件。感光元件可以是在一些实施例中，电子设备100可以包括1个或N个摄像头193，N为大于1的正整数。
数字信号处理器用于处理数字信号，除了可以处理数字图像信号，还可以处理其他数字信号。例如，当电子设备100在频点选择时，数字信号处理器用于对频点能量进行傅里叶变换等。
视频编解码器用于对数字视频压缩或解压缩。电子设备100可以支持一种或多种视频编解码器。
外部存储器接口120可以用于连接外部存储卡，外部存储卡通过外部存储器接口120与处理器110通信，实现数据存储功能。例如将音乐，视频等文件保存在外部存储卡中。
内部存储器121可以用于存储计算机可执行程序代码，所述可执行程序代码包括指令。处理器110通过运行存储在内部存储器121的指令，从而执行电子设备100的各种功能应用以及数据处理。此外，内部存储器121可以包括高速随机存取存储器，还可以包括非易失性存储器。
电子设备100可以通过音频模块170，扬声器170A，受话器170B，麦克风170C，耳机接口170D，以及应用处理器等实现音频功能。例如音乐播放，录音等。
音频模块170用于将数字音频信息转换成模拟音频信号输出，也用于将模拟音频输入转换为数字音频信号。音频模块170还可以用于对音频信号编码和解码。
扬声器170A，也称“喇叭”，用于将音频电信号转换为声音信号。受话器170B，也称“听筒”，用于将音频电信号转换成声音信号。麦克风170C，也称“话筒”，“传声器”，用于将声音信号转换为电信号。耳机接口170D用于连接有线耳机。
压力传感器180A用于感受压力信号，可以将压力信号转换成电信号。陀螺仪传感器180B可以用于确定电子设备100的运动姿态。气压传感器180C用于测量气压。在一些实施例中，电子设备100通过气压传感器180C测得的气压值计算海拔高度，辅助定位和导航。地磁传感器180D包括霍尔传感器。加速度传感器180E可检测电子设备100在各个方向上(一般为三轴)加速度的大小。当电子设备100静止时可检测出重力的大小及方向。还可以用于识别电子设备姿态，应用于横竖屏切换，计步器等应用。距离传感器180F，用于测量距离。电子设备100可以通过红外或激光测量距离。
接近光传感器180G可以包括例如发光二极管(LED)和光检测器，例如光电二极管。发光二极管可以是红外发光二极管。环境光传感器180L用于感知环境光亮度。电子设备100可以根据感知的环境光亮度自适应调节显示屏194亮度。指纹传感器180H用于采集指纹。电子设备100可以利用采集的指纹特性实现指纹解锁，访问应用锁，指纹拍照，指纹接听来电等。温度传感器180J用于检测温度。在一些实施例中，电子设备100利用温度传感器180J检测的温度，执行温度处理策略。触摸传感器180K，也称“触控面板”。触摸传感器180K可以设置于显示屏194，由触摸传感器180K与显示屏194组成触摸屏，也称“触控屏”。骨传导传感器180M可以获取振动信号。
按键190包括开机键，音量键等。按键190可以是机械按键。也可以是触摸式按键。电子设备100可以接收按键输入，产生与电子设备100的用户设置以及功能控制有关的键信号输入。马达191可以产生振动提示。马达191可以用于来电振动提示，也可以用于触摸振动反馈。指示器192可以是指示灯， 可以用于指示充电状态，电量变化，也可以用于指示消息，未接来电，通知等。SIM卡接口195用于连接SIM卡。
以上介绍了电子设备100可能具有的硬件结构，可以理解的是，本申请实施例示意的结构并不构成对电子设备100的具体限定。在本申请另一些实施例中，电子设备100可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。图示的部件可以以硬件，软件或软件和硬件的组合实现。
下面结合上述图5所示的结构，根据图6并结合具体场景，详细介绍本申请的技术方案。如图6所示，本申请的一些实施例中室内定位方法的执行主体可以是电子设备100的处理器，并且可以包括如下步骤：
步骤S601：获取传感器数据和/或信号数据。
本申请的一些实施例中，触发众包数据采集的场景可以包括但不限于：室内外场景、行车步行切换场景、步行切换场景、行车跨楼层场景等。
其中，室内外场景包括用户以驾车或步行方式从室外环境进入室内环境的场景；行车步行切换场景包括在室内环境中，用户从驾车状态切换为下车步行状态的场景；步行切换场景包括用户从同一层步行状态切换为乘坐电梯或扶梯状态、楼梯步行状态的场景；行车跨楼层场景包括用户以驾车方式跨越楼层的场景。
可以理解，为了判断电子设备100是否满足触发众包数据采集的触发条件，通常需要判断电子设备100的当前场景，例如，在判断是否处于室内外场景时，需要知道电子设备100的移动速度、高度、环境光线强度、GSM信号接收强度等，要得到这些状态需要通过电子设备100中内置的加速度传感器180E、陀螺仪传感器180B、气压传感器180C、环境光传感器等传感器或GSM无线模块、Wi-Fi无线模块等采集数据；在判断是否处于行车步行切换场景或步行切换场景时，需要知道电子设备100的移动速度、移动方向、角速度等，要得到这些状态需要通过电子设备100中内置的加速度传感器180E和陀螺仪传感器180B来采集数据；在判断是否处于行车跨楼层场景时，需要知道电子设备100的移动速度、移动方向、角速度、高度等，要得到这些状态需要通过电子设备100中内置的加速度传感器180E、陀螺仪传感器180B、气压传感器180C来采集数据等。
本申请的一些实施例中，用户的电子设备100可以实时采集内置的传感器180的数据，传感器可以包括但不限于：加速度传感器180E、陀螺仪传感器180B、气压传感器180C、重力传感器等，再根据采集的传感器数据通过预先建立的场景识别模型确定电子设备100当前所处的场景。
加速度传感器180E是用于测量加速度的传感器，通常由质量块、阻尼器、弹性元件、敏感元件和适调电路等部分组成，加速度传感器180E在加速过程中，通过对质量块所受惯性力的测量，利用惯性定律获得加速度值。根据传感器敏感元件的不同，常见的加速度传感器包括电容式、电感式、应变式、压阻式、压电式等。
电子设备100使用的陀螺仪传感器180B是用于测量角速度的传感器，工作原理是利用物理学上的科里奥利力，在内部产生微小的电容变化，然后根据测量的电容数据计算出角速度。
气压传感器180C是用于测量大气压强的传感器，有些气压传感器的传感元件是对压强敏感的薄膜，薄膜与柔性电阻连接，气压变化造成薄膜的变形导致柔性电阻的阻值变化，根据测量的阻值确定相应的气压值；有些气压传感器的传感元件是变容式硅膜盒，气压的变化会引起硅膜盒的变形，进而引起硅膜盒平行板电容容量的变化，根据电容值确定气压值。
重力传感器用于测量由于重力引起的加速度，根据压电效应的原理来工作，即通过对加速度造成的 介质变形时产生的电压进行测量来确定相应的加速度值。
可以理解，电子设备100获取的传感器数据可以是一种传感器的数据，也可以是多种传感器的数据，本申请实施例对此不作具体限制。
本申请的一些实施例中，电子设备100可以实时采集通过无线通信模块接收的信号数据，信号数据可以包括但不限于Wi-Fi信号数据、蜂窝信号数据等，再根据信号数据通过预先建立的场景识别模型确定电子设备100当前所处的场景。
步骤S602：根据传感器数据和/或信号数据确定当前场景是否为触发众包数据采集的场景，若是则执行步骤S603，采集众包数据，否则转到步骤S601执行。
在此，电子设备100的当前场景是指电子设备100当前所处的场景模式，由于电子设备100通常由用户携带或放置在用户附近的位置，电子设备100的当前场景可以实质上反映用户所处的环境场景和用户的活动状态场景，这些用户相关的场景可以用于触发电子设备100执行相应的处理。
本申请的一些实施例中，可以将传感器数据和/或信号数据输入预先建立的场景识别模型来获得模型输出结果，并根据模型输出的结果来判断是否属于触发众包数据采集的场景。在此，场景识别模型可以是一种使用机器学习算法的模型，该模型使用传感器数据和/或信号数据作为训练数据对机器学习算法进行训练，在训练完成后得到可以用于进行场景识别的模型。
可以理解，场景识别模型可以是一个或多个，场景识别模型可以是识别多个场景的一个模型，也可以是多个识别相应单独场景的子模型，本申请实施例对此不作具体限制。下文将做详细描述。
步骤S603：采集众包数据。
在确定当前场景是触发众包数据采集的场景之后，电子设备100执行地磁数据获取和Wi-Fi扫描以进行众包数据的采集。
本申请的一些实施例中，电子设备100通过内置的地磁传感器180D获取当前位置的地磁数据，并将获取的地磁数据发送给地磁定位服务器300，地磁定位服务器300将接收的地磁数据在预先建立的地磁定位数据库中匹配，确定地磁数据对应的地磁定位位置和相应的地磁定位误差并返回给电子设备100。
本申请的另外一些实施例中，电子设备100将进行Wi-Fi扫描后得到的Wi-Fi指纹发送给Wi-Fi定位服务器200，Wi-Fi定位服务器200将Wi-Fi指纹在Wi-Fi指纹定位数据库中匹配，确定Wi-Fi定位位置和相应的Wi-Fi定位误差并返回给电子设备100；电子设备100将Wi-Fi定位位置和通过地磁传感器180D获取的当前位置的地磁数据发送给地磁定位服务器300，地磁定位服务器300根据接收的地磁数据在预先建立的地磁定位数据库中由Wi-Fi定位位置确定的地磁定位的匹配范围内匹配，确定地磁数据对应的地磁定位位置和相应的地磁定位误差。通过使用Wi-Fi定位位置来减小地磁数据在地磁定位数据库中匹配时的匹配范围，可以加快地磁定位时的匹配速度，提高地磁定位位置的精度并降低地磁定位误差。
本申请的一些实施例中，地磁定位服务器300将确定的地磁定位位置和相应的地磁定位误差发送给Wi-Fi定位服务器200，Wi-Fi定位服务器200根据接收的Wi-Fi指纹和地磁定位位置对Wi-Fi指纹定位数据库进行更新。
本申请的另外一些实施例中，地磁定位服务器300将确定的地磁定位位置和相应的地磁定位误差发送给电子设备100，由电子设备100根据Wi-Fi指纹和接收的地磁定位位置生成相应的众包数据。
在一些实施例中，电子设备100接收的地磁定位误差超过预设的误差阈值时，电子设备100不生成相应的Wi-Fi众包数据。在此，地磁定位误差超过预设的误差阈值，说明地磁定位的准确性较差，该众包数据对应的地磁定位位置不准确，不能作为有效的众包数据使用。
在一些实施例中，众包数据可以包括但不限于地磁定位位置、Wi-Fi指纹数据等。在此，Wi-Fi指纹数据包括电子设备100当前可以接收到的Wi-Fi接入点的标识如MAC地址和对应的接收信号强度。
在此，根据地磁定位来确定众包数据的位置，可以提高众包数据的位置准确性，进而在在线定位时提高定位的精度。
在一些实施例中，众包数据可以包括当前场景的信息，例如当前场景的标识等，通过在众包数据中加入场景信息，可以根据产生场景对众包数据进行分类。
本申请的一些实施例中，在满足预设的众包采集停止条件时，停止采集众包数据。在此，众包采集停止条件可以根据众包采集需求进行定义，例如“在每个触发众包数据采集的场景中众包采集的触发次数超过预设阈值则停止众包采集”；“电子设备当天的众包采集时间超过预设的时间阈值则停止众包采集”；“电子设备上当天采集的众包数据占有的存储空间超过预设的存储阈值”等。通过设置众包采集停止条件，可以避免电子设备100进行过多的众包采集而导致的过高功耗。
步骤S604：将众包数据提交给Wi-Fi定位服务器200进行数据更新。
本申请的一些实施例中，电子设备100将生成的众包数据发送至Wi-Fi定位服务器200，Wi-Fi定位服务器200检查是否存在Wi-Fi众包数据库，如果不存在，则生成Wi-Fi众包数据库并将接收的众包数据写入，如果存在，直接将接收的众包数据写入Wi-Fi众包数据库。
在一些实施例中，众包数据包括场景的相关信息，可以将众包数据存入对应场景的Wi-Fi众包数据库中，例如，在行车步行切换场景中生成的众包数据存储到对应行车步行切换场景的Wi-Fi众包数据库中，步行切换场景中生成的众包数据存储到对应的步行切换场景的Wi-Fi众包数据库中。通过将不同场景中生成的众包数据分别存储，可以在在线定位时根据实时的场景在对应的场景Wi-Fi众包数据库中查询，能够提高不同场景中的定位精度。
本申请的一些实施例中，可以使用Wi-Fi众包数据库中的众包数据对Wi-Fi指纹定位数据库进行更新。在此，根据众包数据对Wi-Fi指纹定位数据库中的数据进行检测，识别Wi-Fi指纹是否有变化，例如Wi-Fi接入点的新增、减少、老化、移动位置等都会造成Wi-Fi指纹的变化。如果检测到Wi-Fi接入点有变化，并且满足数据更新条件，则使用Wi-Fi众包数据库中的众包数据对Wi-Fi指纹定位数据库进行更新。数据更新条件可以预先设定，例如数据更新周期超过预设的更新周期阈值，或Wi-Fi指纹定位数据库能够匹配的Wi-Fi接入点数量小于预设的接入点阈值等。
在后续的在线定位过程中，电子设备100首先接收Wi-Fi接入点的Wi-Fi指纹如MAC地址、接收信号强度等。在一些实施例中，电子设备100仅使用Wi-Fi指纹定位数据库进行定位，具体来说，电子设备100将Wi-Fi指纹发送给Wi-Fi定位服务器200，Wi-Fi定位服务器200根据Wi-Fi指纹在Wi-Fi指纹定位数据库进行匹配并将匹配得到的Wi-Fi定位位置返回电子设备100，电子设备100将接收的Wi-Fi定位位置直接作为电子设备的当前位置。
在另外一些实施例中，电子设备100使用Wi-Fi指纹定位数据库辅助进行地磁定位，具体来说，电子设备100将Wi-Fi指纹发送给Wi-Fi定位服务器200，Wi-Fi定位服务器200根据Wi-Fi指纹在Wi-Fi指纹定位数据库进行匹配并将匹配得到的Wi-Fi定位位置返回电子设备100。电子设备100再将Wi-Fi定位位置和通过内置的地磁传感器180D采集的地磁数据发送给地磁定位服务器300，地磁定位服务器300根据地磁数据在地磁定位数据库中由Wi-Fi定位位置确定的地磁定位的匹配范围中匹配，并将匹配的更精确的地磁定位位置返回电子设备100，电子设备100将接收到的地磁定位位置作为电子设备的当前位置。
如前所述，在步骤S602中，可以根据电子设备100的传感器数据和/或信号数据来判断场景。具体 来说，是将传感器数据和/或信号数据输入预先建立的场景识别模型来进行场景识别。
在一些实施例中，场景识别模型的训练数据是预先收集的传感器数据，传感器数据可以有对应的场景标识，机器学习算法根据输入的传感器数据输出对应的预测场景，并将输出的预测场景与实际场景进行比对，根据比对结果的损失函数值对机器学习算法的参数进行持续的迭代优化，将得到的参数最优的机器学习算法作为场景识别模型。
可以理解，场景识别模型可以根据电子设备100的一种传感器的数据进行训练得到，例如根据加速度传感器180E的数据进行训练得到场景识别模型，也可以根据电子设备100的多种传感器的数据进行训练得到，例如根据加速度传感器180E和气压传感器180C的数据进行训练得到场景识别模型，本申请实施例对此不做具体限制。
在一些实施例中，训练数据是预先收集的信号数据，信号数据是电子设备100接收的无线数据，例如Wi-Fi信号数据、GSM信号数据等。类似地，信号数据可以有对应的场景标识，机器学习算法根据信号数据进行训练得到场景识别模型。
可以理解，训练数据可以同时包含传感器数据和信号数据，机器学习算法根据同时包含传感器数据和信号数据的训练数据进行训练后得到相应的场景识别模型，本申请实施例对训练数据的类型不作具体限制。
在一些实施例中，各场景的具体判断方式如下：
本申请的一些实施例中，可以根据传感器数据来确定当前是否为室内外场景。在此，可以预先收集电子设备100的传感器在室外的数据和室内的数据，并将室外的数据标记为室外，将室内的数据标记为室内，再将室外的传感器数据和室内的传感器数据作为训练数据对神经网络模型进行训练，从而得到用于识别室内外场景的模型。
例如，可以根据地磁传感器180D接收的地磁强度的变化大小来判断电子设备100是否从室外进入室内，由于建筑物内的钢筋混凝土结构对地磁的干扰较大，因此电子设备100从室外进入室内后地磁场的强度有较大变化，从而可以根据地磁场强度的变化情况来判断是否为室内外场景。
又例如，可以根据环境光传感器180L接收的光线强度的变化来判断电子设备100是否从室外进入室内，室外环境的光强通常要高于室内的光强，电子设备100从室外进入室内时，光照强度会有一个明显且持续的转换过程，通过识别光照强度的变化可以对室内外场景进行判断。
本申请的一些实施例中，还可以根据电子设备100接收的信号数据来确定当前是否为室内外场景，室外的信号数据和室内的信号数据通常存在一定的差异，通过识别这些差异可以做出室内外场景的判断。
例如，室外环境中，GSM信号通常较强，而室内环境中GSM信号通常较弱，电子设备在从室外环境到室内环境的过程中，通过GSM无线模块接收的GSM信号会有一个持续的减弱过程，识别GSM信号的减弱过程可以识别出室内外场景。
又例如，室外环境中，可以接收到定位信号的卫星的数量较多，室内环境中可以接收到定位信号的卫星数量较少，可以通过对可以接收到定位信号的卫星数量的变化情况对室内外场景进行识别。
在此，用于进行室内外场景识别的机器学习算法可以使用当前可以用于进行分类的算法，可以包括但不限于逻辑回归算法、决策树算法、神经网络算法、支持向量机等。
对行车步行切换场景和步行切换场景的识别，可以通过人类活动识别技术进行。人类活动识别(Human activity recognition，HAR)基于传感器的数据来识别人类的活动，人类活动通常是典型活动，例如开车、步行、乘坐电梯或扶梯、楼梯步行等。
本申请的一些实施例中，人类活动识别可以使用电子设备100中内置的加速度传感器180E和陀螺 仪传感器180B采集的数据流来预测人的活动，加速度传感器180E和陀螺仪传感器180B采集的实时数据流通常被分成称为窗口的子序列，将这些时间序列数据输入人类活动识别模型，从而对时间序列数据对应的人类活动进行预测。
在此，预先收集人类在进行不同活动时携带的电子设备100中加速度传感器180E和陀螺仪传感器180B的时间序列数据作为训练数据，并根据人类的实际活动对相应的时间序列数据进行标记，再将训练数据输入神经网络模型如卷积神经网络模型或递归神经网络模型等进行训练，将参数最优的神经网络模型作为人类活动识别模型。
可以理解，使用电子设备100中加速度传感器180E和陀螺仪传感器180B采集的数据来训练人类活动识别模型仅仅是一种示例，并不表示只能使用加速度传感器180E和陀螺仪传感器180B采集的数据对人类活动识别模型进行训练，例如，也可以使用加速度传感器180E、气压传感器180C和重力传感器采集的数据对人类活动识别模型进行训练，本申请实施例对此不作具体限制。
另外，人类活动识别模型可以是任何能够处理电子设备100内置传感器采集的时间序列数据的神经网络模型，例如卷积神经网络(Convolutional Neural Networks，CNN)、递归神经网络(Recursive Neural Network，RNN)、长短期记忆网络(Long Short-Term Memory，LSTM)等。
本申请的一些实施例中，可以根据电子设备100内置的传感器采集的数据来确定是否为行车跨楼层场景。在此，可以根据传感器采集的数据流确定相应的跨楼层状态数据，再将跨楼层状态数据作为训练数据对神经网络模型进行训练，得到跨楼层场景识别模型。
在此，跨楼层状态数据可以包括但不限于：坡度、角速度、线速度、高度和行车轨迹等。图7示出了车辆在跨越楼层过程中跨楼层状态数据，如图7所示，车辆在跨楼层中，会经历从平面到缓坡段，再到正常坡段——缓坡段——平面的过程，坡度会经历从小到大，再从大到小的过程，同时伴随着高度的增加和线速度的变化，另外，如果车辆是以曲线行车轨迹进行跨楼层的，还存在相应的角速度。
在一些实施例中，可以根据加速度传感器180E和陀螺仪传感器180B采集的数据流来确定跨楼层状态数据。
另外，跨楼层场景中可能存在多种坡道类型，例如直线长坡道、倾斜楼板、曲线整圆坡道等，不同的坡道类型对应的跨楼层状态数据不同。图8示出了地下车库中不同坡道类型的车辆行车轨迹，如图8所示，车辆在直线长坡道中跨楼层时会经历一个较大的坡度变化和高度下降，而在曲线整圆坡道中跨楼层时会经历较小的坡度变化和高度下降，同时有角速度，在跳层螺旋坡道中跨楼层时有角速度的时间持续较长，并且有持续的坡度变化和高度变化。因此，需要针对不同的坡道类型采集传感器数据以确定相应的跨楼层状态数据，根据相应的跨楼层状态数据对神经网络模型进行训练，得到具有识别多种坡道类型的跨楼层场景识别模型。
类似地，跨楼层场景识别模型可以是任何能够处理跨楼层状态数据的时间序列的神经网络模型，例如卷积神经网络(Convolutional Neural Networks，CNN)、递归神经网络(Recursive Neural Network，RNN)、长短期记忆网络(Long Short-Term Memory，LSTM)等。
根据本申请的一个实施例，还提供了一种室内定位装置。如图9所示，室内定位装置包括：
确定模块901，用于确定出当前场景满足触发众包数据采集的条件；
获取模块902，用于获取来自多个无线保真接入点的第一Wi-Fi指纹数据和地磁传感器采集的地磁数据；
发送模块903，用于向第二电子设备发送第一Wi-Fi指纹数据和地磁传感器采集的地磁数据，以使第二电子设备根据接收的第一Wi-Fi指纹数据在Wi-Fi指纹定位数据库中确定第一Wi-Fi定位位置，并 根据地磁数据在地磁定位数据库中由第一Wi-Fi定位位置确定的地磁定位的匹配范围内确定地磁定位位置，并对Wi-Fi指纹定位数据库进行更新。
图10根据本申请的一些实施例，示出了一种用于室内定位方法的电子设备200的硬件结构框图。在图10所示的实施例中，电子设备200可以包括一个或多个处理器201，与处理器201中的至少一个连接的系统控制逻辑202，与系统控制逻辑202连接的系统内存203，与系统控制逻辑202连接的非易失性存储器(Non-Volatile Memory,NVM)204，以及与系统控制逻辑202连接的网络接口206。
在一些实施例中，处理器201可以包括一个或多个单核或多核处理器。在一些实施例中，处理器201可以包括通用处理器和专用处理器(例如，图形处理器，应用处理器，基带处理器等)的任意组合。在电子设备200采用增强型基站(Evolved Node B，eNB)或无线接入网(Radio Access Network，RAN)控制器的实施例中，处理器201可以被配置为执行各种符合的实施例。例如，处理器201可以用于实现室内定位方法。
在一些实施例中，系统控制逻辑202可以包括任意合适的接口控制器，以向处理器201中至少一个与系统控制逻辑202通信的、任意合适的设备或组件提供任意合适的接口。
在一些实施例中，系统控制逻辑202可以包括一个或多个存储器控制器，以提供连接到系统内存203的接口。系统内存203可以用于加载以及存储数据和/或指令。例如，系统内存203可以加载本申请实施例中的Wi-Fi指纹定位数据库中存储的数据。
在一些实施例中电子设备200的系统内存203可以包括任意合适的易失性存储器，例如合适的动态随机存取存储器(Dynamic Random Access Memory，DRAM)。
NVM存储器204可以包括用于存储数据和/或指令的一个或多个有形的、非暂时性的计算机可读介质。在一些实施例中，NVM存储器204可以包括闪存等任意合适的非易失性存储器和/或任意合适的非易失性存储设备，例如硬盘驱动器(Hard Disk Drive，HDD)，光盘(Compact Disc，CD)驱动器，数字通用光盘(Digital Versatile Disc，DVD)驱动器中的至少一个。在本申请实施例中，NVM存储器204可以用于存储地磁定位数据库中的数据等。
NVM存储器204可以包括安装电子设备200的装置上的一部分存储资源，或者它可以由设备访问，但不一定是设备的一部分。例如，可以经由网络接口206通过网络访问NVM存储器204。
特别地，系统内存203和NVM存储器204可以分别包括：指令205的暂时副本和永久副本。指令205可以包括：由处理器201中的至少一个执行时导致电子设备200实施如图6所示的方法的Wi-Fi定位服务器更新指令。在一些实施例中，指令205、硬件、固件和/或其软件组件可另外地/替代地置于系统控制逻辑202，网络接口206和/或处理器201中。
网络接口206可以包括收发器，用于为电子设备200提供无线电接口，进而通过一个或多个网络与任意其他合适的设备(如前端模块，天线等)进行通信。在一些实施例中，网络接口206可以集成于电子设备200的其他组件。例如，网络接口206可以集成于处理器201的，系统内存203，NVM存储器204，和具有指令的固件设备(未示出)中的至少一种，当处理器201中的至少一个执行所述指令时，电子设备200实现如方法实施例中示出的方法。在本申请实施例中，网络接口206可以用于接收第一电子设备发送的Wi-Fi指纹数据和地磁数据等。
网络接口206可以进一步包括任意合适的硬件和/或固件，以提供多输入多输出无线电接口。例如，网络接口206可以是网络适配器，无线网络适配器，电话调制解调器和/或无线调制解调器。
在一些实施例中，处理器201中的至少一个可以与用于系统控制逻辑202的一个或多个控制器的逻辑封装在一起，以形成系统封装(System In a Package，SiP)。在一些实施例中，处理器201中的至少 一个可以与用于系统控制逻辑202的一个或多个控制器的逻辑集成在同一管芯上，以形成片上系统(System on Chip，SoC)。
电子设备200可以进一步包括：输入/输出(I/O)设备207。I/O设备207可以包括用户界面，使得用户能够与电子设备200进行交互；外围组件接口的设计使得外围组件也能够与电子设备200交互。在一些实施例中，电子设备200还包括传感器，用于确定与电子设备200相关的环境条件和位置信息的至少一种。
在一些实施例中，用户界面可包括但不限于显示器(例如，液晶显示器，触摸屏显示器等)，扬声器，麦克风，一个或多个相机(例如，静止图像照相机和/或摄像机)，手电筒(例如，发光二极管闪光灯)和键盘。
在一些实施例中，外围组件接口可以包括但不限于非易失性存储器端口、音频插孔和电源接口。
在一些实施例中，传感器可包括但不限于陀螺仪传感器，加速度计，近程传感器，环境光线传感器和定位单元。定位单元还可以是网络接口206的一部分或与网络接口206交互，以与定位网络的组件(例如，北斗卫星)进行通信。
可以理解的是，图10示意的结构并不构成对电子设备200的具体限定。在本申请另外一些实施例中电子设备200可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。图示的部件可以由硬件或软件，或软件和硬件的组合实现。
本申请公开的机制的各实施例可以被实现在硬件、软件、固件或这些实现方法的组合中。本申请的实施例可实现为在可编程系统上执行的计算机程序或程序代码，该可编程系统包括至少一个处理器、存储系统(包括易失性和非易失性存储器和/或存储元件)、至少一个输入设备以及至少一个输出设备。
可将程序代码应用于输入指令，以执行本申请描述的各功能并生成输出信息。可以按已知方式将输出信息应用于一个或多个输出设备。为了本申请的目的，处理系统包括具有诸如例如数字信号处理器(Digital Signal Processor，DSP)、微控制器、专用集成电路(Application Specific Integrated Circuit，ASIC)或微处理器之类的处理器的任何系统。
程序代码可以用高级程序化语言或面向对象的编程语言来实现，以便与处理系统通信。在需要时，也可用汇编语言或机器语言来实现程序代码。事实上，本申请中描述的机制不限于任何特定编程语言的范围。在任一情形下，该语言可以是编译语言或解释语言。
至少一个实施例的一个或多个方面可以由存储在计算机可读存储介质上的表示性指令来实现，指令表示处理器中的各种逻辑，指令在被机器读取时使得该机器制作用于执行本文所述的技术的逻辑。被称为“IP核”的这些表示可以被存储在有形的计算机可读存储介质上，并被提供给多个客户或生产设施以加载到实际制造该逻辑或处理器的制造机器中。
在一些情况下，所公开的实施例可以以硬件、固件、软件或其任何组合来实现。所公开的实施例还可以被实现为由一个或多个暂时或非暂时性机器可读(例如，计算机可读)存储介质承载或存储在其上的指令，其可以由一个或多个处理器读取和执行。例如，指令可以通过网络或通过其他计算机可读介质分发。因此，机器可读介质可以包括用于以机器(例如，计算机)可读的形式存储或传输信息的任何机制，包括但不限于，软盘、光盘、光碟、只读存储器(CD-ROMs)、磁光盘、只读存储器(Read Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、可擦除可编程只读存储器(Erasable Programmable Read Only Memory，EPROM)、电可擦除可编程只读存储器(Electrically Erasable Programmable Read-Only Memory，EEPROM)、磁卡或光卡、闪存、或用于利用因特网以电、光、声或其他形式的传播信号来传输信息(例如，载波、红外信号数字信号等)的有形的机器可读存储器。因此， 机器可读介质包括适合于以机器(例如计算机)可读的形式存储或传输电子指令或信息的任何类型的机器可读介质。
在附图中，可以以特定布置和/或顺序示出一些结构或方法特征。然而，应该理解，可能不需要这样的特定布置和/或排序。而是，在一些实施例中，这些特征可以以不同于说明性附图中所示的方式和/或顺序来布置。另外，在特定图中包括结构或方法特征并不意味着暗示在所有实施例中都需要这样的特征，并且在一些实施例中，可以不包括这些特征或者可以与其他特征组合。
需要说明的是，本申请各设备实施例中提到的各单元/模块都是逻辑单元/模块，在物理上，一个逻辑单元/模块可以是一个物理单元/模块，也可以是一个物理单元/模块的一部分，还可以以多个物理单元/模块的组合实现，这些逻辑单元/模块本身的物理实现方式并不是最重要的，这些逻辑单元/模块所实现的功能的组合才是解决本申请所提出的技术问题的关键。此外，为了突出本申请的创新部分，本申请上述各设备实施例并没有将与解决本申请所提出的技术问题关系不太密切的单元/模块引入，这并不表明上述设备实施例并不存在其它的单元/模块。
需要说明的是，在本专利的示例和说明书中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
虽然通过参照本申请的某些优选实施例，已经对本申请进行了图示和描述，但本领域的普通技术人员应该明白，可以在形式上和细节上对其作各种改变，而不偏离本申请的精神和范围。

Claims (21)

  1. 一种室内定位方法，用于第一电子设备，其特征在于，包括：
    确定出当前场景满足触发众包数据采集的条件；
    获取来自多个无线保真接入点的第一Wi-Fi指纹数据和地磁传感器采集的地磁数据；
    向第二电子设备发送所述第一Wi-Fi指纹数据和所述地磁传感器采集的地磁数据，以使所述第二电子设备根据接收的所述第一Wi-Fi指纹数据在Wi-Fi指纹定位数据库中确定第一Wi-Fi定位位置，并根据所述地磁数据在地磁定位数据库中由所述第一Wi-Fi定位位置确定的地磁定位的匹配范围内确定地磁定位位置，并对所述Wi-Fi指纹定位数据库进行更新。
  2. 根据权利要求1所述的方法，其特征在于，确定出当前场景满足触发众包数据采集的条件，包括：
    获取传感器的传感器数据，并根据所述传感器数据确定出当前场景满足触发众包数据采集的条件。
  3. 根据权利要求2所述的方法，其特征在于，获取传感器的传感器数据，并根据所述传感器数据确定出当前场景满足触发众包数据采集的条件，包括：
    获取传感器的传感器数据，并将所述传感器数据输入预设的场景识别模型，根据所述场景识别模型的识别结果确定出当前场景满足触发众包数据采集的条件。
  4. 根据权利要求3所述的方法，其特征在于，将所述传感器数据输入预设的场景识别模型，根据所述场景识别模型的识别结果确定出当前场景满足触发众包数据采集的条件，包括：
    根据所述传感器数据，确定跨楼层状态数据；
    将所述跨楼层状态数据输入所述场景识别模型，根据所述场景识别模型的识别结果确定当前场景是否为行车跨楼层场景。
  5. 根据权利要求4所述的方法，其特征在于，所述跨楼层状态数据包括：坡度、角速度、线速度、高度和行车轨迹。
  6. 根据权利要求2至5中任一项所述的方法，其特征在于，所述传感器至少包括如下一种：加速度传感器、陀螺仪传感器、气压传感器、重力传感器、地磁传感器。
  7. 根据权利要求2至5中任一项所述的方法，其特征在于，所述传感器数据还包括信号数据，所述信号数据包括所述第一电子设备通过无线通信模块接收的数据。
  8. 根据权利要求1至7中任一项所述的方法，其特征在于，所述第一Wi-Fi指纹数据至少包括所述无线保真接入点的标识和接收信号强度。
  9. 根据权利要求1至7中任一项所述的方法，其特征在于，所述当前场景为下列中的至少一种：
    室内外场景、行车步行切换场景、步行切换场景和行车跨楼层场景。
  10. 根据权利要求1所述的方法，其特征在于，还包括：
    接收室内定位指令；
    根据所述室内定位指令获取第二Wi-Fi指纹数据；
    向所述第二电子设备发送所述第二Wi-Fi指纹数据，以使所述第二电子设备根据接收的所述第二Wi-Fi指纹数据在所述Wi-Fi指纹定位数据库中确定对应的第二Wi-Fi定位位置；
    向所述第一电子设备发送所述第二Wi-Fi定位位置。
  11. 根据权利要求1所述的方法，其特征在于，还包括：
    接收所述第二电子设备发送的所述地磁定位位置；
    根据接收的所述地磁定位位置和所述第一Wi-Fi指纹数据生成众包数据并向所述第二电子设备发送，以使所述第二电子设备根据接收的众包数据对所述Wi-Fi指纹定位数据库进行更新。
  12. 根据权利要求11所述的方法，其特征在于，所述地磁定位位置还包括地磁定位误差，当所述地磁定位误差大于预设的误差阈值时，停止生成所述众包数据。
  13. 根据权利要求1所述的方法，其特征在于，还包括：
    当满足预设的众包数据采集停止条件时，停止所述众包数据的采集。
  14. 一种室内定位方法，用于包括第一电子设备和第二电子设备的系统，其特征在于，包括：
    所述第一电子设备确定出当前场景满足触发众包数据采集的条件；
    所述第一电子设备获取来自多个无线保真接入点的第一Wi-Fi指纹数据和地磁传感器采集的地磁数据并向所述第二电子设备发送；
    所述第二电子设备根据接收的所述第一Wi-Fi指纹数据确定第一Wi-Fi定位位置，并根据所述地磁数据和所述第一Wi-Fi定位位置确定地磁定位位置，并对Wi-Fi指纹定位数据库进行更新。
  15. 根据权利要求14所述的方法，其特征在于，所述第二电子设备根据接收的所述第一Wi-Fi指纹数据确定第一Wi-Fi定位位置，并根据所述地磁数据和所述第一Wi-Fi定位位置确定地磁定位位置，包括：
    所述第二电子设备根据接收的所述第一Wi-Fi指纹数据在所述Wi-Fi指纹定位数据库中确定第一Wi-Fi定位位置，并根据所述地磁数据在地磁定位数据库中由所述第一Wi-Fi定位位置确定的地磁定位的匹配范围内确定地磁定位位置。
  16. 根据权利要求14所述的方法，其特征在于，所述第二电子设备对Wi-Fi指纹定位数据库进行更新，包括：
    所述第二电子设备向所述第一电子设备发送所述地磁定位位置；
    所述第一电子设备根据接收的所述地磁定位位置和所述第一Wi-Fi指纹数据生成众包数据并向所述第二电子设备发送；
    所述第二电子设备根据接收的所述众包数据对Wi-Fi指纹定位数据库进行更新。
  17. 一种室内定位装置，其特征在于，所述装置包括：
    确定模块，用于确定出当前场景满足触发众包数据采集的条件；
    获取模块，用于获取来自多个无线保真接入点的第一Wi-Fi指纹数据和地磁传感器采集的地磁数据；
    发送模块，用于向第二电子设备发送所述第一Wi-Fi指纹数据和所述地磁传感器采集的地磁数据，以使所述第二电子设备根据接收的所述第一Wi-Fi指纹数据在Wi-Fi指纹定位数据库中确定第一Wi-Fi定位位置，并根据所述地磁数据在地磁定位数据库中由所述第一Wi-Fi定位位置确定的地磁定位的匹配范围内确定地磁定位位置，并对所述Wi-Fi指纹定位数据库进行更新。
  18. 一种室内定位系统，其特征在于，包括第一电子设备和第二电子设备，
    所述第一电子设备，用于确定出当前场景满足触发众包数据采集的条件，并获取来自多个无线保真接入点的第一Wi-Fi指纹数据和地磁传感器采集的地磁数据并向所述第二电子设备发送；
    所述第二电子设备，用于根据接收的所述第一Wi-Fi指纹数据确定第一Wi-Fi定位位置，并根据所述地磁数据和所述第一Wi-Fi定位位置确定地磁定位位置，并对Wi-Fi指纹定位数据库进行更新。
  19. 一种电子设备，其特征在于，包括：
    存储器，用于存储由电子设备的一个或多个处理器执行的指令，以及
    处理器，是电子设备的处理器之一，用于执行权利要求1-13中任一项所述的室内定位方法。
  20. 一种可读存储介质，其特征在于，所述可读存储介质上存储有指令，该指令在电子设备上执行时使电子设备执行权利要求1-16中任一项所述的室内定位方法。
  21. 一种计算机程序产品，包括计算机程序/指令，其特征在于，该计算机程序/指令被处理器执行时实现权利要求1-16中任一项所述的室内定位方法。
PCT/CN2023/091676 2022-05-12 2023-04-28 室内定位方法、装置、电子设备及介质 WO2023216933A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210517239.0 2022-05-12
CN202210517239.0A CN117092586A (zh) 2022-05-12 2022-05-12 室内定位方法、装置、电子设备及介质

Publications (1)

Publication Number Publication Date
WO2023216933A1 true WO2023216933A1 (zh) 2023-11-16

Family

ID=88729658

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/091676 WO2023216933A1 (zh) 2022-05-12 2023-04-28 室内定位方法、装置、电子设备及介质

Country Status (2)

Country Link
CN (1) CN117092586A (zh)
WO (1) WO2023216933A1 (zh)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104457751A (zh) * 2014-11-19 2015-03-25 中国科学院计算技术研究所 室内外场景识别方法及系统
CN105722028A (zh) * 2016-01-31 2016-06-29 华南理工大学 基于wifi、磁场两级搜索室内行人定位系统及方法
CN108521627A (zh) * 2018-03-14 2018-09-11 华南理工大学 基于HMM的wifi和地磁融合的室内定位系统及方法
CN108668245A (zh) * 2018-04-13 2018-10-16 哈尔滨工业大学 一种基于WiFi与地磁场数据库的室内定位方法
CN109115205A (zh) * 2018-07-20 2019-01-01 上海工程技术大学 一种基于地磁传感器阵列的室内指纹定位方法及系统
WO2019136918A1 (zh) * 2018-01-11 2019-07-18 华为技术有限公司 一种室内定位的方法、服务器及定位系统
KR20210093078A (ko) * 2020-01-17 2021-07-27 주식회사 에이브로스 사용자위치정보기반 실내측위시스템 및 그의 실내측위방법
CN114111801A (zh) * 2021-12-14 2022-03-01 中国电信股份有限公司 自动启停定位方法、装置、电子设备及存储介质

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104457751A (zh) * 2014-11-19 2015-03-25 中国科学院计算技术研究所 室内外场景识别方法及系统
CN105722028A (zh) * 2016-01-31 2016-06-29 华南理工大学 基于wifi、磁场两级搜索室内行人定位系统及方法
WO2019136918A1 (zh) * 2018-01-11 2019-07-18 华为技术有限公司 一种室内定位的方法、服务器及定位系统
CN108521627A (zh) * 2018-03-14 2018-09-11 华南理工大学 基于HMM的wifi和地磁融合的室内定位系统及方法
CN108668245A (zh) * 2018-04-13 2018-10-16 哈尔滨工业大学 一种基于WiFi与地磁场数据库的室内定位方法
CN109115205A (zh) * 2018-07-20 2019-01-01 上海工程技术大学 一种基于地磁传感器阵列的室内指纹定位方法及系统
KR20210093078A (ko) * 2020-01-17 2021-07-27 주식회사 에이브로스 사용자위치정보기반 실내측위시스템 및 그의 실내측위방법
CN114111801A (zh) * 2021-12-14 2022-03-01 中国电信股份有限公司 自动启停定位方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN117092586A (zh) 2023-11-21

Similar Documents

Publication Publication Date Title
JP7265003B2 (ja) ターゲット検出方法、モデル訓練方法、装置、機器及びコンピュータプログラム
CN111182453B (zh) 定位方法、装置、电子设备及存储介质
KR101437757B1 (ko) 콘텍스트 감지 및 융합을 위한 방법, 장치 및 컴퓨터 프로그램제품
US9807725B1 (en) Determining a spatial relationship between different user contexts
EP2871815B1 (en) Authentication control system, authentication control method, and program
EP3014476B1 (en) Using movement patterns to anticipate user expectations
US9344854B2 (en) Method, storage medium, server, and electronic device for implementing location based service within building
CN112078565B (zh) 氢燃料电池电动汽车的能量管理方法、装置及存储介质
US20120109862A1 (en) User device and method of recognizing user context
US20200027460A1 (en) Communication robot and method for operating the same
CN111696562B (zh) 语音唤醒方法、设备及存储介质
KR101995799B1 (ko) 상황 인지 서비스를 제공하기 위한 장소 인식 장치 및 방법
EP2972657B1 (en) Application-controlled granularity for power-efficient classification
US20230379408A1 (en) Positioning Method and Electronic Device
CN112673367A (zh) 用于预测用户意图的电子设备和方法
WO2023216933A1 (zh) 室内定位方法、装置、电子设备及介质
US20180051989A1 (en) Portable device with improved sensor position change detection
KR20150009833A (ko) 장소 인식을 제어하는 휴대 단말 및 방법
CN113468929A (zh) 运动状态识别方法、装置、电子设备和存储介质
WO2023169487A1 (zh) 定位方法、系统及相关装置
US20190182792A1 (en) Network connection control method by using a user context
WO2023185687A1 (zh) 车辆位置的获取方法及电子设备
WO2023005865A1 (zh) 一种室内地图构建方法以及相关装置
CN117917583A (zh) 定位方法、电子设备及计算机可读存储介质
CN114511779B (zh) 场景图生成模型的训练方法、场景图生成方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23802705

Country of ref document: EP

Kind code of ref document: A1