Terminal positioning method and network device

• US 10,542,519 B2
• Filed: 09/20/2018
• Issued: 01/21/2020
• Est. Priority Date: 04/29/2016
• Status: Active Grant

• Current Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Inventors: Yuan, Mingxuan, Zeng, Jia, Tong, Xialiang
• Primary Examiner(s): Obayanju, Omoniyi
• Application Number:
  US16/136,827
• Publication Number:
  US 20190021068A1
• Time in Patent Office: Days
• CPC Class Codes: G01S 5/02521 using a radio-map
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/042 Backward inferencing
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
• CPC Class Codes: H04W 64/00 Locating users or terminals or network equipment for network management purposes, e.g. mobility management
• CPC Class Codes: H04W 64/003 locating network equipment

Abstract

A terminal positioning method and a network device, where the network device obtains radio signal sampling information of a first terminal at a current moment. The first terminal is any terminal in a target region, and the target region is a preset geographic region. The network device obtains position information of the first terminal at the current moment by prediction based on the radio signal sampling information of the first terminal at the current moment and a predictive model of the target region. The predictive model is obtained by extensive data training in the target region, has relatively strong error tolerance and error-correction capabilities, and can accurately reflect a relationship between radio signal sampling information and position information of a terminal. Terminal positioning accuracy is effectively improved.

Claims

1. A terminal positioning method, comprising:

obtaining, by a network device, radio signal sampling information of a first terminal at a current moment, the first terminal being any terminal in a target region, and the target region being a preset geographic region; and

obtaining, by the network device, position information of the first terminal at the current moment by prediction based on the radio signal sampling information of the first terminal at the current moment and a predictive model of the target region, the predictive model being determined based on a plurality of data pairs of at least two historical terminals in the target region, the data pairs of any historical terminal of the at least two historical terminals being obtained based on radio signal sampling information of a historical terminal at a plurality of first historical moments and position information of the historical terminal at a plurality of second historical moments, the radio signal sampling information of the historical terminal at the first historical moments being obtained based on a first frequency, the position information of the historical terminal at the second historical moments being obtained based on a second frequency, the first frequency being less than the second frequency, each data pair of the data pairs comprising one piece of radio signal sampling information of the radio signal sampling information of the historical terminal at the first historical moments and position information, and the position information in each data pair corresponding to the one piece of radio signal sampling information of the radio signal sampling information of the historical terminal at the first historical moments.

2. The method of claim 1, wherein determining the predictive model comprises:

obtaining, by the network device by screening from radio signal sampling information in the data pairs, a specified radio signal feature whose relevance to a position feature in position information in the data pairs is greater than or equal to a first threshold; and

establishing, by the network device, a function relationship between the specified radio signal feature and the position feature to obtain the predictive model.

3. The method of claim 2, wherein obtaining the position information of the first terminal at the current moment comprises:

obtaining, by the network device based on the radio signal sampling information of the first terminal at the current moment, a value corresponding to the specified radio signal feature; and

performing, by the network device, calculation based on the predictive model and the value corresponding to the specified radio signal feature to obtain the position information of the first terminal at the current moment.

4. The method of claim 3, wherein the specified radio signal feature comprises any one or any combination of a first-type signal feature, a second-type signal feature, or a third-type signal feature, a value corresponding to the first-type signal feature being extracted from the radio signal sampling information of the first terminal at the current moment, a value corresponding to the second-type signal feature being calculated based on a value corresponding to one or more first-type signal features, a value corresponding to the third-type signal feature being obtained using initial position information of the first terminal at the current moment and initial position information of the first terminal at an adjacent moment of the current moment, and the initial position information of the first terminal at the current moment or the initial position information of the first terminal at the adjacent moment of the current moment being obtained by calculating, by the network device using the function relationship, a value corresponding to one or more first-type signal features or a value corresponding to one or more second-type signal features.

5. The method of claim 1, wherein the position information of the historical terminal at the second historical moments comprises first-type position information and second-type position information, the first-type position information comprising position information obtained by parsing data collected by the network device through a Gn interface, and the second-type position information comprising position information obtained after the network device determines a moving track of the historical terminal based on the first-type position information and map information of the target region, and performs interpolation in any two pieces of adjacent first-type position information based on the moving track.

6. The method of claim 1, wherein the position information of the historical terminal at the second historical moments comprises first-type position information, and the first-type position information comprising position information obtained by parsing data collected by the network device through a Gn interface.

7. The method of claim 1, wherein the position information of the historical terminal at the second historical moments comprises second-type position information, the second-type position information comprising position information obtained after the network device determines a moving track of the historical terminal based on first-type position information and map information of the target region, and performs interpolation in any two pieces of adjacent first-type position information based on the moving track, and the first-type position information comprising position information obtained by parsing data collected by the network device through a Gn interface.

8. A terminal positioning method, comprising:

obtaining, by a network device, radio signal sampling information of a historical terminal at a plurality of first historical moments and position information of the historical terminal at a plurality of second historical moments, the radio signal sampling information of the historical terminal at the first historical moments being obtained based on a first frequency, the position information of the historical terminal at the second historical moments being obtained based on a second frequency, and the first frequency being less than the second frequency; and

obtaining, by the network device, a plurality of data pairs of the historical terminal based on the radio signal sampling information of the historical terminal at the first historical moments and the position information of the historical terminal at the second historical moments, each data pair of the data pairs comprising one piece of radio signal sampling information of the radio signal sampling information of the historical terminal at the first historical moments and position information, and the position information in each data pair corresponding to one piece of radio signal sampling information of the radio signal sampling information of the historical terminal at the first historical moments.

9. The method of claim 8, wherein obtaining the position information of the historical terminal at the second historical moments comprises:

obtaining, by the network device, a first-type position information of the historical terminal;

determining, by the network device, a moving track of the historical terminal based on the first-type position information and map information of a target region, the target region comprising a preset geographic region;

obtaining, by the network device, a second-type position information by performing interpolation in any two pieces of adjacent first-type position information based on the moving track; and

setting, by the network device, the second-type position information as the position information of the historical terminal at the second historical moments.

10. The method of claim 9, wherein obtaining the first-type position information of the historical terminal comprises obtaining, by the network device, the first-type position information by parsing Over The Top (OTT) data collected through a Gn interface.

11. The method of claim 8, wherein obtaining the data pairs of the historical terminal comprises:

determining, by the network device, a target clock correspondence between the first historical moments and the second historical moments; and

obtaining, by the network device, the data pairs of the historical terminal based on the target clock correspondence.

12. The method of claim 11, wherein determining the target clock correspondence comprises:

determining, by the network device, a clock correspondence between the first historical moments of the historical terminal and the second historical moments of the historical terminal according to a first preset rule, the first preset rule comprising any one of a plurality of preset rules;

determining, by the network device based on the clock correspondence, a second historical moment corresponding to a first historical moment;

determining, by the network device, a distance between a base station and the historical terminal at each of the first historical moments based on position information of the base station in radio signal sampling information at each of the first historical moment and position information of the historical terminal at the second historical moment corresponding to the first historical moment;

calculating, by the network device for the first preset rule, a sum of distances between the base station and the historical terminal at the first historical moments; and

determining, by the network device, a clock correspondence in which the sum of distances between the base station and the historical terminal at the first historical moments is minimum in the preset rules as the target clock correspondence between the first historical moments and the second historical moments.

13. The method of claim 11, wherein obtaining the data pairs of the historical terminal comprises:

separately setting, by the network device, the radio signal sampling information of the historical terminal at the first historical moments as radio signal sampling information in the data pairs;

obtaining, by the network device based on the target clock correspondence, the second historical moments corresponding to the first historical moments; and

obtaining, by the network device, position information in the data pairs of the historical terminal based on at least one of the position information at the second historical moments corresponding to the first historical moments.

14. A network device, comprising:

a memory configured to store instructions; and

a processor coupled to the memory, the instructions causing the processor to be configured to;

obtain radio signal sampling information of a first terminal at a current moment and a predictive model of a target region, the first terminal being any terminal in the target region, the target region being a preset geographic region, the predictive model being determined based on a plurality of data pairs of at least two historical terminals in the target region, the data pairs of any historical terminal of the at least two historical terminals being obtained based on radio signal sampling information of a historical terminal at a plurality of first historical moments and position information of the historical terminal at a plurality of second historical moments, the radio signal sampling information of the historical terminal at the first historical moments being obtained based on a first frequency, the position information of the historical terminal at the second historical moments being obtained based on a second frequency, the first frequency being less than the second frequency, each data pair of the data pairs comprising one piece of radio signal sampling information of the radio signal sampling information of the historical terminal at the first historical moments and position information, and the position information in each data pair corresponding to the one piece of radio signal sampling information of the radio signal sampling information of the historical terminal at the first historical moments; and

obtain position information of the first terminal at the current moment by prediction based on the radio signal sampling information of the first terminal at the current moment and the predictive model of the target region.

15. The network device of claim 14, wherein the instructions further cause the processor to be configured to:

obtain, by screening from radio signal sampling information in the data pairs, a specified radio signal feature whose relevance to a position feature in position information in the data pairs is greater than or equal to a first threshold; and

establish a function relationship between the specified radio signal feature and the position feature to obtain the predictive model.

16. The network device of claim 15, wherein the instructions further cause the processor to be configured to:

obtain, based on the radio signal sampling information of the first terminal at the current moment, a value corresponding to the specified radio signal feature; and

perform calculation based on the predictive model and the value corresponding to the specified radio signal feature to obtain the position information of the first terminal at the current moment.

17. The network device of claim 16, wherein the specified radio signal feature comprises any one or any combination of a first-type signal feature, a second-type signal feature, or a third-type signal feature, a value corresponding to the first-type signal feature being extracted from the radio signal sampling information of the first terminal at the current moment, a value corresponding to the second-type signal feature being calculated based on a value corresponding to one or more first-type signal features, a value corresponding to the third-type signal feature being obtained using initial position information of the first terminal at the current moment and initial position information of the first terminal at an adjacent moment of the current moment, and the initial position information of the first terminal at the current moment or the initial position information of the first terminal at the adjacent moment of the current moment being obtained by calculating, using the function relationship, a value corresponding to one or more first-type signal features or a value corresponding to one or more second-type signal features.

18. The network device of claim 14, wherein the position information of the historical terminal at the second historical moments comprises first-type position information and second-type position information, the first-type position information comprising position information obtained by parsing data collected by the network device through a Gn interface, and the second-type position information comprising position information obtained after the network device determines a moving track of the historical terminal based on the first-type position information and map information of the target region, and performs interpolation in any two pieces of adjacent first-type position information based on the moving track.

19. The network device of claim 14, wherein the position information of the historical terminal at the second historical moments comprises first-type position information or second-type position information, the first-type position information comprising position information obtained by parsing data collected by the network device through a Gn interface, and the second-type position information comprising position information obtained after the network device determines a moving track of the historical terminal based on the first-type position information and map information of the target region, and performs interpolation in any two pieces of adjacent first-type position information based on the moving track.

20. A network device, comprising:

a memory configured to store computer program instructions; and

a processor coupled to the memory, the computer program instructions causing the processor to be configured to;

obtain radio signal sampling information of a historical terminal at a plurality of first historical moments and position information of the historical terminal at a plurality of second historical moments, the radio signal sampling information of the historical terminal at the first historical moments being obtained based on a first frequency, the position information of the historical terminal at the second historical moments being obtained based on a second frequency, and the first frequency being less than the second frequency; and

obtain a plurality of data pairs of the historical terminal based on the radio signal sampling information of the historical terminal at the first historical moments and the position information of the historical terminal at the second historical moments, each data pair of the data pairs comprising one piece of radio signal sampling information of the radio signal sampling information of the historical terminal at the first historical moments and position information, and the position information in each data pair corresponding to one piece of radio signal sampling information of the radio signal sampling information of the historical terminal at the first historical moments.