WO2017185664A1 - 一种终端定位方法及网络设备 - Google Patents

一种终端定位方法及网络设备 Download PDF

Info

Publication number
WO2017185664A1
WO2017185664A1 PCT/CN2016/102043 CN2016102043W WO2017185664A1 WO 2017185664 A1 WO2017185664 A1 WO 2017185664A1 CN 2016102043 W CN2016102043 W CN 2016102043W WO 2017185664 A1 WO2017185664 A1 WO 2017185664A1
Authority
WO
WIPO (PCT)
Prior art keywords
historical
terminal
location information
information
telecommunication signal
Prior art date
Application number
PCT/CN2016/102043
Other languages
English (en)
French (fr)
Inventor
袁明轩
曾嘉
童夏良
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
Priority to EP16900172.4A priority Critical patent/EP3419353B1/en
Publication of WO2017185664A1 publication Critical patent/WO2017185664A1/zh
Priority to US16/136,827 priority patent/US10542519B2/en

Links

Images

Classifications

    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
    • H04W64/003—Locating users or terminals or network equipment for network management purposes, e.g. mobility management locating network equipment
    • 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
    • G01S5/02521—Radio frequency fingerprinting using a radio-map
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models
    • G06N5/042—Backward inferencing
    • 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
    • H04W4/021—Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
    • 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
    • H04W4/025—Services making use of location information using location based information parameters
    • 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
    • H04W4/029—Location-based management or tracking services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
    • H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination

Definitions

  • the present application relates to the field of communications technologies, and in particular, to a terminal positioning method and a network device.
  • the Range-Based method refers to a method for determining the actual position of the terminal by calculating the distance from the mobile terminal to the connected base station, and then determining the actual position of the terminal through the triangulation method, wherein the triangulation method refers to the telecommunication signal strength of the three base stations received by the terminal (Radio Signal) Strength, referred to as RSS, estimates the distance between the terminal and the base station, and draws a coverage arc with the distance as the radius. The intersection of the three covered arcs is the position of the terminal.
  • Radio Signal Radio Signal
  • the core step of the method is to calculate the distance between the terminal and the connected base station, and specifically estimate the relationship between the terminal and the base station by the observed telecommunication signal strength and the attenuation of the telecommunication signal in propagation (signal attenuation model in the case of ideal curved surface propagation).
  • the distance because the telecommunications signal strength is usually interfered by factors such as multipath attenuation and non-line of sight blocking, resulting in lower positioning accuracy and large error in triangulation.
  • most terminals only connect less than three base stations. As shown in Table 1, the terminal connects to the base station in the measurement report (MR) of one operator and one day. Percentage of the number of cases:
  • Table 1 Percentage of the number of terminals connected to the base station
  • the existing positioning method calculates the distance between the terminal and the base station to locate the terminal, which may result in low positioning accuracy and large error due to interference received by the telecommunication signal. Therefore, there is a need for a more It is an effective terminal positioning method for improving the accuracy of positioning and reducing positioning error.
  • the present invention provides a terminal positioning method and a network device, which are used to solve the technical problem that the positioning method in the prior art has low positioning accuracy and large error.
  • a terminal positioning method provided by the application includes:
  • the network device acquires the telecommunication signal sampling information of the first terminal at the current time; the first terminal is any terminal located in the target area, and the target area is a predetermined geographical area;
  • the network device predicts, according to the telecommunication signal sampling information of the first terminal at the current time and the prediction model of the target area, location information of the first terminal at the current time; the prediction model is according to the location Determining a plurality of sets of data pairs of at least two historical terminals in the target area; each set of data pairs in the plurality of sets of data includes telecommunication signal sampling information and location information, and telecommunication signal sampling information in the data pair
  • the location information is telecommunication signal sampling information and location information of the same historical terminal at the same historical moment.
  • the prediction model is determined according to multiple sets of data pairs of at least two historical terminals in the target area, and the telecommunication signal sampling information and location information included in the multiple sets of data pairs are directly obtainable in the prior art.
  • Information without additional acquisition, can effectively reduce the positioning cost; and, because the prediction model is obtained through a large amount of data training in the target area, it has strong fault tolerance and error correction capability, and can accurately reflect the terminal.
  • the relationship between the telecommunication signal sampling information and the location information avoids the interference in the prior art due to the multipath attenuation, non-line of sight blocking and other factors of the telecommunication signal strength and the insufficient number of base stations connected to the terminal. Inaccurate problem, therefore, according to the prediction model in the present invention and the telecommunication signal sampling information of the terminal, It can effectively improve the accuracy of terminal positioning and reduce positioning error, and has strong practical value.
  • the prediction model is determined by the network device by:
  • the network device filters, from the telecommunication signal sampling information of the multiple sets of data pairs, a specific telecommunication signal feature that has a correlation degree with a location feature in the location information of the multiple sets of data pairs that is greater than or equal to a first threshold;
  • the network device establishes a functional relationship between the specific telecommunication signal feature and the location feature to obtain the prediction model.
  • the network device trains multiple sets of data pairs to filter out specific telecommunication signal characteristics and establish a functional relationship between specific telecommunication signal features and location features, thereby making the constructed prediction model simpler and more accurate.
  • the network device predicts the location information of the first terminal at the current time according to the telecommunication signal sampling information of the first terminal at the current time and the prediction model of the target area, including:
  • the network device performs operation according to the prediction model and the value corresponding to the specific telecommunication signal feature, and obtains location information of the first terminal at the current time.
  • the network device only needs to obtain the value corresponding to the specific telecommunication signal feature, and can obtain the location information of the first terminal at the current time according to the prediction model, without acquiring additional information, thereby reducing the cost of the positioning and achieving fast positioning. .
  • the specific telecommunication signal feature includes any one or any combination of the first type of signal feature, the second type of signal feature, and the third type of signal feature;
  • the value corresponding to the signal characteristic of the first type is extracted from the telecommunication signal sampling information of the current time at the terminal to be located;
  • the values corresponding to the second type of signal features are calculated according to values corresponding to one or more first type of signal features
  • the value corresponding to the third type of signal feature is obtained by the terminal to be located at the current moment and The initial position information of the adjacent moments of the current time is obtained; the initial position information of the to-be-located terminal at the current moment or the adjacent moment of the current moment is one or More than one first type of signal characteristic and/or a value corresponding to the second type of signal characteristic is computed.
  • the specific telecommunication signal characteristics may include the above three types, the specific telecommunication signal characteristics for positioning are comprehensive, and various telecommunication signal characteristics that may affect the position information of the terminal are fully considered, thereby ensuring positioning accuracy and accuracy. .
  • the multiple sets of data pairs of any one of the at least two historical terminals are obtained according to the following method:
  • the network device acquires the telecommunication signal sampling information of the first historical terminal at the plurality of first historical moments and the location information of the first historical terminal at the plurality of second historical moments;
  • a historical terminal is any one of the at least two historical terminals;
  • the network device Obtaining, by the network device, the first historical terminal according to the telecommunication signal sampling information of the first historical terminal at the first historical moment and the location information of the first historical terminal at the plurality of second historical moments Group data pair.
  • the network device obtains the first information according to the telecommunication signal sampling information of the first historical terminal at the first historical moment and the location information of the first historical terminal at the multiple second historical moments.
  • Multiple sets of data pairs for historical terminals including:
  • the network device determines, according to the first preset rule, a clock correspondence between the plurality of first historical moments of the first historical terminal and the plurality of second historical moments, where the first preset rule is multiple preset rules. Any of the preset rules;
  • the network device Calculating, by the network device, a sum of distances of the first historical terminal and the base station to which the first historical terminal belongs at a plurality of first historical moments for the first preset rule; wherein the first historical terminal
  • the distance from the first historical moment of the plurality of first historical moments of the base station to which the first historical terminal belongs is obtained by the network device determining, according to the clock correspondence, the first a second historical time corresponding to the historical time, and according to the location information of the base station in the telecommunication signal sampling information of the first historical time and the second historical time corresponding to the first historical time Determining, by the location information of the first historical terminal, a distance between the base station and the first historical terminal at a first historical moment;
  • the network device Determining, by the network device, the plurality of sets of data pairs of the first historical terminal according to the correspondence relationship of the target clock; the correspondence between the target clocks is the plurality of preset rules, the first historical terminal and the first The clock corresponding to the base station to which the history terminal belongs has the smallest sum of the distances of the plurality of first historical moments.
  • the clock synchronization problem of the telecommunication signal sampling information and the location information may be fully considered, and the clock and location information according to the telecommunication signal sampling information of the first historical terminal are determined according to various preset rules.
  • the time offset between the clocks is obtained, and the correspondence relationship between the target clocks is obtained.
  • multiple sets of data pairs are determined, and the data used for training the prediction model is processed in this way, so that the prediction model is constructed.
  • the data based on it is more accurate, which makes the constructed prediction model more realistic.
  • the telecommunication signal sampling information of the first historical terminal at the plurality of first historical moments is acquired according to the first frequency; the location information of the first historical terminal at the plurality of second historical moments is according to the first Obtained by two frequencies; the first frequency is smaller than the second frequency;
  • Determining, by the network device, the multiple sets of data pairs of the first historical terminal according to the target clock correspondence including:
  • the network device uses the telecommunication signal sampling information of the first historical terminal at the plurality of first historical moments as the telecommunication signal sampling information in the multiple sets of data pairs, and
  • the location information obtains location information of the plurality of sets of data pairs of the first historical terminal.
  • the difference between the sampling frequency between the telecom signal sampling information and the location information is fully considered, and the location information in the data pair is obtained according to at least the location information of the second historical moment corresponding to the first historical moment, for example, according to the first historical moment.
  • the average value of the position information in the preset time period of the corresponding second historical time is obtained by the position information in the data pair, so that the position information in the data pair is more accurate.
  • the location information of the first historical terminal at the multiple second historical moments includes the first type of location information and/or the second type of location information;
  • the first type of location information is location information obtained by parsing data collected by the network device through the Gn interface;
  • the second type of location information is that after the network device determines the motion track of the first historical terminal according to the first type of location information and the map information of the target area, according to the motion track, any two The position information obtained by interpolation in the adjacent first type of position information.
  • the motion trajectory is fully utilized, and the second type of position information is obtained by interpolation, thereby making the position information more dense, and ensuring the telecommunication signal sampling information at the first historical moment.
  • Corresponding location information exists to facilitate the full use of telecommunication signal sampling information.
  • the application provides a network device, where the network device includes:
  • An acquiring module configured to acquire telecommunication signal sampling information of the first terminal at a current time; the first terminal is any terminal located in the target area, and the target area is a predetermined geographical area;
  • a processing module configured to predict, according to the telecommunication signal sampling information of the first terminal at the current time and the prediction model of the target area, location information of the first terminal at the current time; the prediction model is based on Determining a plurality of sets of data pairs of at least two historical terminals in the target area; each set of data pairs in the plurality of sets of data pairs includes telecommunication signal sampling information and location information, and telecommunication signal sampling information in the data pair And the location information is telecommunication signal sampling information and location information of the same historical terminal at the same historical moment.
  • processing module is further configured to:
  • processing module is specifically configured to:
  • the specific telecommunication signal feature includes any one or any combination of the first type of signal feature, the second type of signal feature, and the third type of signal feature;
  • the value corresponding to the signal characteristic of the first type is extracted from the telecommunication signal sampling information of the current time at the terminal to be located;
  • the values corresponding to the second type of signal features are calculated according to values corresponding to one or more first type of signal features
  • the value corresponding to the third type of signal feature is obtained by initial position information of the to-be-located terminal at the current time and the adjacent time of the current time; the terminal to be located is at the current time or
  • the initial position information of the adjacent time at the current time is obtained by computing the value corresponding to one or more first type signal characteristics and/or second type signal characteristics of the time by the functional relationship.
  • processing module is further configured to:
  • processing module is specifically configured to:
  • the first preset rule Determining, by the first preset rule, a clock correspondence between the plurality of first historical moments of the first historical terminal and the plurality of second historical moments, where the first preset rule is any one of a plurality of preset rules Preset rules;
  • the network device Calculating, by the first preset rule, a sum of distances between the first historical terminal and the base station to which the first historical terminal belongs at a plurality of first historical moments; wherein the first historical terminal and the first The distance of each of the plurality of first historical moments of the base station to which the historical terminal belongs is obtained by: the network device determining, according to the clock correspondence, the first historical moment a second historical time, and determining, according to the location information of the base station in the telecommunication signal sampling information of the first historical time and the location information of the first historical terminal at the second historical time corresponding to the first historical time Determining a distance between the base station and the first historical terminal at a first historical moment;
  • the target clock correspondence Determining, by the target clock correspondence, a plurality of sets of data pairs of the first historical terminal; the target clock correspondence is the plurality of preset rules, where the first historical terminal and the first historical terminal belong The clock correspondence between the sum of the distances of the base stations at the plurality of first historical moments is the smallest.
  • the telecommunication signal sampling information of the first historical terminal at the plurality of first historical moments is acquired according to the first frequency; the location information of the first historical terminal at the plurality of second historical moments is according to the first Obtained by two frequencies; the first frequency is smaller than the second frequency;
  • the processing module is specifically configured to:
  • the location information of the first historical terminal at the multiple second historical moments includes the first type of location information and/or the second type of location information;
  • the first type of location information is location information obtained by parsing data collected by the network device through the Gn interface;
  • the second type of location information is that after the network device determines the motion track of the first historical terminal according to the first type of location information and the map information of the target area, according to the motion track, any two The position information obtained by interpolation in the adjacent first type of position information.
  • the application provides another network device, where the network device includes:
  • a memory for storing the obtained telecommunication signal sampling information of the first terminal at the current time and a prediction model of the target area;
  • the first terminal is any terminal located in the target area, and the target area is a predetermined geographical area
  • the prediction model is determined according to a plurality of sets of data pairs of at least two historical terminals in the target area; each of the plurality of sets of data pairs includes telecommunication signal sampling information and location information, the data
  • the telecommunication signal sampling information and location information of the pair are telecommunication signal sampling information and location information of the same historical terminal at the same historical moment.
  • a processor configured to predict location information of the first terminal at the current time according to the telecommunication signal sampling information of the first terminal at the current time and the prediction model of the target area;
  • the processor is further configured to:
  • the processor is specifically configured to:
  • the specific telecommunication signal feature includes any one or any combination of the first type of signal feature, the second type of signal feature, and the third type of signal feature;
  • the value corresponding to the signal characteristic of the first type is extracted from the telecommunication signal sampling information of the current time at the terminal to be located;
  • the values corresponding to the second type of signal features are calculated according to values corresponding to one or more first type of signal features
  • the value corresponding to the third type of signal feature is obtained by using the initial position information of the terminal to be located at the current time and the current time at the current time; the terminal to be located is in the
  • the initial position information of the previous time or the adjacent time of the current time is obtained by calculating the value corresponding to one or more first type signal features and/or second type signal features of the time by the functional relationship. .
  • the processor is further configured to:
  • the processor is specifically configured to:
  • the first preset rule Determining, by the first preset rule, a clock correspondence between the plurality of first historical moments of the first historical terminal and the plurality of second historical moments, where the first preset rule is any one of a plurality of preset rules Preset rules;
  • the network device Calculating, by the first preset rule, a sum of distances between the first historical terminal and the base station to which the first historical terminal belongs at a plurality of first historical moments; wherein the first historical terminal and the first The distance of each of the plurality of first historical moments of the base station to which the historical terminal belongs is obtained by: the network device determining, according to the clock correspondence, the first historical moment a second historical time, and determining, according to the location information of the base station in the telecommunication signal sampling information of the first historical time and the location information of the first historical terminal at the second historical time corresponding to the first historical time Determining a distance between the base station and the first historical terminal at a first historical moment;
  • the target clock correspondence Determining, by the target clock correspondence, a plurality of sets of data pairs of the first historical terminal; the target clock correspondence is the plurality of preset rules, where the first historical terminal and the first historical terminal belong The clock correspondence between the sum of the distances of the base stations at the plurality of first historical moments is the smallest.
  • the telecommunication signal sampling information of the first historical terminal at the plurality of first historical moments is acquired according to the first frequency; the location information of the first historical terminal at the plurality of second historical moments is according to the first Obtained by two frequencies; the first frequency is smaller than the second frequency;
  • the processor is specifically configured to:
  • the location information of the first historical terminal at the multiple second historical moments includes the first type of location information and/or the second type of location information;
  • the first type of location information is location information obtained by parsing data collected by the network device through the Gn interface;
  • the second type of location information is that after the network device determines the motion track of the first historical terminal according to the first type of location information and the map information of the target area, according to the motion track, any two The position information obtained by interpolation in the adjacent first type of position information.
  • the network device acquires the telecommunication signal sampling information of the first terminal at the current time, where the first terminal is any terminal located in the target area, and the target area is a predetermined geographical area;
  • the telecommunication signal sampling information of the terminal at the current time and the prediction model of the target area predict the position information of the first terminal at the current time.
  • the prediction model is determined according to a plurality of sets of data pairs of at least two historical terminals in the target area, and each of the plurality of sets of data pairs includes telecommunication signal sampling information and location information, due to telecommunication signal sampling information and
  • the location information is directly available in the prior art, and no additional acquisition is required, so the positioning cost can be effectively reduced.
  • the prediction model since the prediction model is obtained by training a large amount of data in the target area, it has strong
  • the fault-tolerant and error-correcting capability can more accurately reflect the relationship between the telecom signal sampling information and the location information of the terminal, which avoids the factors such as multipath attenuation and non-line-of-sight blocking in the prior art. Interference and terminal connection
  • the number of connected base stations is insufficient to cause inaccurate positioning. Therefore, according to the prediction model in the present invention and the telecommunication signal sampling information of the terminal, the positioning accuracy can be effectively improved, the positioning error is reduced, and the positioning error is strong. Practical value.
  • Figure 1 is a schematic diagram of data of a telecommunications pipe of a terminal
  • FIG. 2 is a schematic flowchart of a terminal positioning method provided by the present application.
  • FIG. 3 is a schematic diagram of a construction process of a prediction model in the present application.
  • FIG. 4 is an exemplary diagram of a URL containing location information
  • FIG. 5 is a schematic diagram of a motion trajectory determined according to a first type of location information and map information
  • FIG. 6 is a schematic diagram of determining a second type of location information according to a first type of location information and a motion trajectory
  • FIG. 7 is a schematic diagram of an image of constructing a prediction model in the present application.
  • FIG. 8 is a schematic structural diagram of a terminal positioning apparatus according to the present application.
  • FIG. 9 is a schematic structural diagram of another terminal positioning apparatus provided by the present application.
  • the terminal in the present application may be a device capable of supporting a telecommunication connection, such as a handheld device capable of supporting a telecommunication connection, an in-vehicle device, a wearable device, a computing device, and various forms of User Equipment (UE), a mobile station.
  • UE User Equipment
  • MS Mobile station
  • terminal terminal
  • Terminal Equipment Terminal Equipment
  • UE User Equipment
  • a terminal such as mobile phones, tablets, laptops, desktop computers, and the like.
  • the present application is simply referred to as a terminal.
  • the telecommunications pipe data of the terminal records all the connection, communication and measurement information of the terminal.
  • Figure 1 is a schematic diagram of the telecommunications pipe data of the terminal.
  • the telecommunications pipe data may include Lampsite/Pico, evolved Node B (eNB) or Radio Network Controller (RNC), unified service node (USN), unified packet gateway (UGW), etc.
  • the information related to the present invention is the measurement report collected from the RNC and the OTT (over the top) data collected on the Gn port.
  • the telecommunication channel data of the terminal may specifically include the telecommunication signal sampling information and the location information of the terminal, where the telecommunication signal sampling information of the terminal may include information in the measurement report of the terminal, information collected on the interface, and the information of the base station. Parameter information.
  • the information in the measurement report of the terminal may include Reference Signal Receiving Power (RSRP), Reference Signal Receiving Quality (RSRQ), Signal to Interference plus Noise Ratio (Signal to Interference plus). Noise Ratio (SINR), Timing Advance (TA), evolved Node B Identification (eNB-ID), Cell Identification (CELL ID), and the transmit power of the terminal.
  • the information collected on the interface may include information collected on the Gn interface, the Gi interface, and the EC interface; the parameters of the base station may include the station height of the base station, the frequency band of the base station, the direction angle of the base station, the downtilt angle of the base station, and the latitude and longitude of the base station.
  • Information such as the cell transmission power of the base station; the location information of the terminal is included in the record containing the location information in the telecommunication pipeline data, such as a record generated by running software such as touch media or drip taxi.
  • the positioning method in the prior art also uses telecommunication signal sampling information, but it is only a very small range of use, for example, only the telecommunication in the telecommunication pipeline data is used in the triangulation method. Signal strength, while other telecommunication information such as context information, acceleration, angle, etc. are not effectively used.
  • the applicant considers that the telecom pipeline data contains a large amount of information, and the telecom operators usually provide services for a large number of urban populations. Therefore, telecommunications pipeline data can become important data for obtaining fine-grained spatiotemporal behavior information of urban users.
  • the source has a natural advantage to the group analysis through the telecommunication pipeline data. Further, it is feasible to mine the space-time behavior of the terminal from the telecommunication pipeline data to realize the terminal positioning.
  • this application is based on data mining technology,
  • the telecom signal sampling information and the location information of the terminal in the telecommunication pipeline are analyzed, and the relationship between the telecommunication signal sampling information and the location information of the terminal is determined, that is, the prediction model is obtained, thereby being based on the prediction model and the terminal's telecommunication at the current moment.
  • the signal sampling information predicts the location information of the terminal at the current time.
  • different geographic scopes can be delineated in this application, so that the prediction models for different geographical scopes can be trained for historical data in different geographical ranges. For example, it can be divided according to different urban areas. For example, in Shanghai, different urban areas such as Pudong New Area, Jiading District, Huangpu District, Jinshan District, Xuhui District, Jing'an District and Yangpu District can respectively correspond to different prediction models.
  • the target area in the present application refers to an area having a certain area.
  • the target area refers especially to an area with a dense population or a large flow of people.
  • FIG. 2 exemplarily shows a schematic flowchart of a method for locating a terminal provided by the present application. As shown in FIG. 2, the method includes:
  • Step 201 The network device acquires the telecommunication signal sampling information of the first terminal at the current time; the first terminal is any terminal located in the target area, and the target area is a predetermined geographical area;
  • Step 202 The network device predicts location information of the first terminal at the current time according to the telecommunication signal sampling information of the first terminal at the current time and the prediction model of the target area; the prediction model Determining according to a plurality of sets of data pairs of at least two historical terminals in the target area; each set of data pairs in the plurality of sets of data includes telecommunication signal sampling information and location information, and telecommunication signals in the data pair
  • the sampling information and the location information are telecommunication signal sampling information and location information of the same historical terminal at the same historical moment.
  • the prediction model is determined according to a plurality of sets of data pairs of at least two historical terminals in the target area, and each set of data pairs in the plurality of sets of data includes a telecommunication signal sampling information and a position information prediction model, due to telecommunication signal sampling Information and location information are directly available in the prior art, and no additional acquisition is required, so the positioning cost can be effectively reduced.
  • the prediction model is trained by a large amount of data in the target area, it is strong. Fault tolerance and error correction ability, can It can accurately reflect the relationship between the telecom signal sampling information and the location information of the terminal, which avoids the interference of the telecom signal strength due to multipath attenuation, non-line of sight blocking and the like and the terminal connection in the prior art.
  • the present application it is first necessary to construct a prediction model in the target area, and then locate the terminal according to the prediction model. That is, the present application includes two phases: a first phase, a construction phase of a prediction model, and a second phase, a positioning phase.
  • the network device in the present application may be a server with processing capability.
  • the first phase and the second phase are executed by the same server; or the network device may also be two servers with processing capabilities.
  • the phase and the second phase are each executed by different servers.
  • the first phase and the second phase of the present application are preferably performed by different servers.
  • the first stage the construction phase of the predictive model
  • the prediction model in the present application can be determined by the network device in the following manner:
  • the network device selects, from the telecommunication signal sampling information of the multiple sets of data pairs of the at least two terminals, a specific telecommunication signal whose correlation with the location feature in the location information of the multiple sets of data pairs is greater than or equal to the first threshold. Feature; establishing a functional relationship between the specific telecommunications signal feature and the location feature to obtain the prediction model.
  • the plurality of sets of data pairs of any one of the at least two historical terminals are obtained according to the following method:
  • the network device acquires the telecommunication signal sampling information of the first historical terminal at the plurality of first historical moments and the location information of the first historical terminal at the plurality of second historical moments; a historical terminal is any one of the at least two historical terminals; the network device determines, according to the first preset rule, a plurality of first historical moments and a plurality of second historical moments of the first historical terminal Corresponding relationship, the first preset rule is in multiple preset rules Any predetermined rule; the network device calculates, for the first preset rule, a sum of distances between the first historical terminal and the base station to which the first historical terminal belongs at a plurality of first historical moments, and according to Determining, by the target clock, a plurality of sets of data pairs of the first historical terminal; the target clock corresponding to the plurality of preset rules, the first historical terminal and the base station to which the first historical terminal belongs The clock correspondence between the sum of the distances of the plurality of first historical moments is the smallest.
  • the prediction model is a target area determined according to a plurality of sets of data pairs of at least two historical terminals in the target area, that is, the prediction model is obtained by training a large amount of historical data.
  • the larger the amount of data the closer the training prediction model is to the actual situation, and correspondingly, the data processing amount will be larger, and the processing time will be longer.
  • the application can select appropriate historical data amount by comprehensively considering the factors of the above two aspects, that is, selecting historical data of multiple terminals in a set time period, for example, it can be 8:00-22 of a certain day. :00 Historical data of 1000 terminals in this time period.
  • FIG. 3 is a schematic diagram of a construction process of a prediction model in the present application.
  • the following is an example of training a prediction model by selecting historical data of 1000 historical terminals in a time period from 8:00 to 22:00 on a certain day. Description. As shown in Figure 3, it includes:
  • Step 301 Acquire telecommunication signal sampling information of each historical terminal at a plurality of first historical moments, that is, obtain telecommunication signal sampling information of 1000 historical terminals in a time period of 8:00-22:00, for example, telecommunication signal sampling.
  • Information can be information collected by the RNC.
  • Step 302 Acquire first-type location information of each historical terminal at a plurality of first historical moments, that is, obtain first-class location information of 1000 historical terminals in a time period of 8:00-22:00.
  • the first type of location information is location information obtained by parsing the data collected by the network device through the Gn interface, and specifically, performing deep packet inspection on the data collected through the Gn interface. After the DPI is parsed, a Uniform Resource Locator (URL) is obtained, and then the Global Positioning System (GPS) location information, that is, the first type of location information is obtained.
  • the GPS location information obtained from the URL of the touch media or the drip taxi as shown in FIG. 4, is an example diagram of a URL containing location information.
  • the application is not limited to obtaining location information through the Gn interface, for example, if the operator and an OTT location service If the service provider signs the agreement, it can also directly obtain the location information provided by the OTT location service.
  • step 301 may be performed first to obtain each step.
  • the telecommunication signal sampling information of the historical terminal is then executed in step 302 to obtain the first type of location information of each historical terminal.
  • step 302 may be performed to obtain the first type of location information of each historical terminal, and then step 301 is performed.
  • the sampling frequency of the signal sampling information is different from the sampling frequency of the first type of position information. Further, it may be that the clock of the device that collects the telecommunication signal sampling information is not synchronized with the clock of the device that collects the first type of position information.
  • the sampling frequency of the acquired telecommunication signal sampling information and the first type of position information may be judged, since in general, sampling of telecommunication signal sampling information is performed.
  • the frequency is much larger than the sampling frequency of the first type of position information. Therefore, the following steps in the present application mainly analyze and explain the case where the sampling frequency of the telecommunication signal sampling information is greater than the sampling frequency of the first type of position information.
  • the sampling frequency of the telecommunication signal sampling information is sampled every 8 seconds (the MR record acquired by the RNC is acquired every 8 seconds), and Table 2 is a sampling example of the telecommunication signal sampling information in a time period.
  • Table 2 the first group of telecommunication signal sampling information of the historical terminal is collected at 10:00:00, the second group telecommunication signal sampling information is collected at 10:00:08, and the third group is collected at 10:00:16.
  • the telecommunication signal sampling information, the 10th group telecommunication signal sampling information is collected at 10:00:24, and the 5th group telecommunication signal sampling information is collected at 10:00:32.
  • Table 2 Sample sampling of telecom signal sampling information over a period of time
  • the sampling frequency of the first type of location information is sampled every 1 minute (the location information is reported every 1 minute when the media is touched), and Table 3 is a sampling example of the first type of location information in a time period, as shown in Table 3.
  • the first location information of the historical terminal is collected at 10:00:00
  • the second location information is collected at 10:01:00
  • the third location information is collected at 10:02:00
  • the third location information is collected at 10:03:00.
  • the fourth position information, the fifth position information is collected at 10:04:00.
  • Table 3 Sample sampling of the first type of location information over a period of time
  • the sampling frequency of the telecommunication signal sampling information and the frequency of the position information are greatly different.
  • the first group of telecommunication signal sampling information collected at 10:00:00 can be The first position information collected at 10:00:00 matches, and the telecommunication signal sampling information collected during the time period from 10:00:00 to 10:01:00 cannot find the matching position information.
  • the second type of location information may be introduced in the application, so that the telecommunication signal sampling information can find the matching location information, and then is fully used.
  • step 303 can be performed.
  • Step 303 Determine, according to the first type of location information of each historical terminal and the map information of the target area, the motion trajectory of each historical terminal, and according to the motion trajectory of each historical terminal, pass any two adjacent first type of location information. Uniform interpolation in the middle gives the second type of location information of each historical terminal.
  • the map information of the target area may be stored in advance, and the map information includes location information of the building, location information of the road, and the like.
  • Figure 5 is based on the first type of location information and map letters A schematic diagram of a motion trajectory of a historical terminal determined by the information, wherein the five first types of location information indicated in FIG. 5 may be the five location information collected in Table 3 above. Further, as shown in FIG. 5, The black dot is the first type of location information extracted from the actual URL. According to the location information of the building in the map information, the location information of the road, and the five location information, the motion of the user holding the historical terminal on the road can be predicted. The trajectory, that is, the trajectory of the history terminal.
  • the specific process of predicting the motion trajectory can refer to the prior art. For example, the matching probability of each point in each path to each road segment, the transition probability between the road segments, etc. can be calculated, and then the travel path with the highest probability is calculated, and then the map is obtained. Matching motion trajectory, not specifically introduced here.
  • interpolation may be performed between any two first type of location information according to the predicted motion trajectory of the historical terminal, and the number of specific interpolations may be set according to the situation. For example, 28 values can be inserted between the first location information collected at 10:00:00 and the second location information collected at 10:01:00, that is, 28 second type location information is inserted, thereby making There is a corresponding location information every 2 seconds.
  • FIG. 6 is a schematic diagram of determining a second type of location information according to the first type of location information and motion trajectory. As shown in FIG. 6, between any two first types of location information, three location points are inserted on the determined motion trajectory. The location information of the three location points is the second type of location information.
  • a uniform interpolation method may be adopted, that is, 10: 28 pieces of position information are evenly inserted in the 00:00 to 10:01:00; if the historical trajectory of the historical terminal and the first type of position information are predicted, the motion rate of the historical terminal is estimated. If there is a significant change, then the corresponding uneven interpolation can be performed according to the estimated change.
  • the first type of location information of the historical terminal is sampled every 1 minute, after interpolation, a corresponding position information can be realized every 2 seconds, that is, the time interval between the two location information is relatively For a short time, for such a short time interval, the motion state generally does not change too much, so uniform interpolation is usually adopted.
  • a user holding the historical terminal walks on the road, and each minute has a corresponding first type of location information for two adjacent
  • the first type of location information can be uniformly inserted into the 28 second type of location information according to the predicted motion track of the historical terminal.
  • the clock according to the first type of position information is deviated from the standard clock.
  • the clock according to the first type of position information is relatively
  • the standard clock is one minute faster, and the data in Table 1 and Table 2 are still taken as an example.
  • the location information corresponding to the telecommunication signal sampling information corresponding to 10:00:00 should be the position corresponding to 10:01:00. If the information of the telecommunication signal sampling information corresponding to 10:00:00 should be directly matched to the position information corresponding to 10:00:00, the information will not be considered, and the prediction model and actual situation will be caused.
  • the matching of the telecommunication signal sampling information and the position information can be performed to correct the clock deviation, thereby obtaining a correct match between the telecommunication signal sampling information and the position information, and the specific step 204 can be performed.
  • Step 304 Determine, according to a plurality of preset rules, a plurality of clock correspondences between the plurality of first historical moments of the first historical terminal and the plurality of second historical moments, and calculate the first historical terminal and the plurality of clock correspondences respectively.
  • the sum of the distances of the base stations to which the first historical terminal belongs at a plurality of first historical moments, and further, by comparison, determines the time offset between the clock on which the telecommunication signal sampling information of the first historical terminal is based and the clock on which the position information is based Move the amount to get the target clock correspondence.
  • Table 4 is an example of the obtained telecommunication signal sampling information and location information (including the first type of location information and the second type of location information) of the terminal b, as shown in Table 4.
  • the first group of telecommunication signal sampling information is a telecommunication signal sampling information record corresponding to a clock for collecting telecommunication signal sampling information at 10:00:00
  • (x1, y1) is a position corresponding to a clock for collecting position information at 10:00:00. information record.
  • Table 4 Sample sampling of telecom signal sampling information and position information
  • the telecommunication signal sampling information includes location information of the connected base station of the terminal b, so that the location information of the connection of the terminal b in each group of telecommunication signal sampling information can be obtained.
  • the telecommunication signal sampling information may include one connected base station of the terminal b, and may also include two or more connected base stations of the terminal b. If only one connected base station is included, the location information of the connected base station may be directly involved in subsequent calculation; if two or more connected base stations are included, the connected base station corresponding to the maximum telecommunication signal strength received by the terminal b may be selected.
  • the location information participates in subsequent calculations, or the average location information of two or more connected base stations may be calculated by calculation, and the average location information is involved in subsequent calculations.
  • the preferred manner is to select the location information of the connected base station corresponding to the maximum telecommunication signal strength received by the terminal b to participate in the subsequent calculation.
  • the telecommunication signal sampling information record and the location record at the same time point or different time points may be correspondingly matched according to multiple preset rules, and the corresponding situations are as follows:
  • the corresponding situation under the first preset rule corresponding to the telecommunication signal sampling information record and the position record located in the same row in Table 4, according to the first group of telecommunication signal sampling information, according to the terminal b
  • the location information of the connected base station and the location information record (x1, y1) of the terminal determine the distance between the connected base station and the terminal b of the terminal b, and are marked as the distance a1.
  • the distance between the connected base station of the terminal b and the terminal b is determined, and is marked as the distance a2 to the distance aP, so that the sum of the distances from the distance a1 to the distance aP can be obtained as D1.
  • the first corresponding situation is a direct correspondence at a time point. Therefore, each group of telecommunication signal sampling information can find corresponding position information, but when the misalignment at the time point is performed, part of the data is lost. For example, when the corresponding position is misaligned for 2 seconds (see the second corresponding situation), there is a possibility that the last set of telecommunication signal sampling information has no corresponding position information, and the distance between the connected base station of the terminal b and the terminal b cannot be calculated.
  • the number of calculated distances is one less, and when the sum of the distances calculated according to the situation is compared with the sum of the distances calculated according to the first corresponding situation, there is obviously a deviation; for example, when When the previous misalignment is performed for 2 seconds, there may be no corresponding position information of the first group of telecommunication signal sampling information, and the distance between the connected base station and the terminal b of the terminal b cannot be calculated, thereby causing the calculated number of distances. missing one.
  • partial data close to the sampling start point and the near sampling end point may be disregarded, so that the calculated distance numbers are equal. For example, the present application does not consider when calculating the sum of the distances according to various corresponding situations.
  • the last 1 group or the last 2 sets of telecommunication signal sampling information may be used.
  • the telecommunication signal sampling information record is corresponding to the position record of 2 seconds later, and for the first group telecommunication signal sampling information, according to the connection base station of the terminal b
  • the location information and the location information record (x2, y2) of the terminal b determine the distance between the connected base station of the terminal b and the terminal b, which is marked as the distance b1.
  • the distance between the connected base station of the terminal b and the terminal b is marked as the distance b2 to the distance bP, so that the sum of the distances from the distance b1 to the distance bP can be obtained as D2.
  • the telecommunication signal sampling information record is corresponding to the position record of 4 seconds later, and for the first group of telecommunication signal sampling information, according to the location of the connected base station of the terminal.
  • the information and the location information record (x3, y3) of the terminal determine the distance between the connected base station and the terminal of the terminal, and are marked as the distance c1.
  • the connected base station of the terminal can be determined.
  • the distance from the terminal labeled as distance c2 to distance cP, gives the sum of the distances from distance c1 to distance cP, denoted as D3.
  • three or more corresponding situations may be considered depending on possible clock deviations, and the above three corresponding cases are merely an exemplary representation.
  • the situation of misalignment of 4 seconds, misalignment of 1 minute, and the like may be directly considered, and is not specifically enumerated in the present application.
  • the clock on which the clock and position information on which the telecommunication signal sampling information is based can be determined for the terminal b.
  • the time offset between the two is 4 seconds. If the clock on which the telecommunication signal sampling information of the terminal b is based is the standard clock, the position information is clocked by 4 seconds faster than the standard clock. Considering the above-mentioned time offset, it is possible to determine the third corresponding situation as a corresponding situation that can be correctly matched.
  • Table 7 Sample sampling of telecom signal sampling information and position information (after considering the time offset)
  • the position information directly matching the sampling information of the first group of telecommunication signals is (x3, y3), and the bit directly matching the sampling information of the second group of telecommunication signals
  • the information is (x7, y7)
  • the position information directly matched with the third group of telecommunication signal sampling information is (x11, y11).
  • the location information includes the first type of location information and the second type of location information, wherein the second type of location information is obtained by estimating the interpolation, therefore, in order to improve the accuracy, the location information needs to be further performed in this application.
  • the processing may be performed in step 305.
  • Step 305 Determine an average value of the plurality of pieces of position information in a preset time period in which the historical moment of the second historical moment corresponding to the first historical moment is used as the final location information, and establish a plurality of telecommunication signal samples at the first moment.
  • the correspondence between the information and the final location information obtains a plurality of sets of data pairs of the historical terminal, thereby obtaining a plurality of sets of data pairs of the respective historical terminals.
  • the position information (x2, y2), (x3, y3) in the time period of 2 seconds before and after the second historical time corresponding to the first historical time can be obtained.
  • the average value of (x4, y4) the average value is taken as the final position information of 10:00:00, and the correspondence between the telecommunication signal sampling information of 10:00:00 and the final position information is established, and a Group data pair.
  • the correspondence between it and the position information can be established, and multiple sets of data pairs are obtained; one set of data pairs is the telecommunication signal sampling information of the same historical terminal at the same historical moment. location information.
  • the clock on which the telecommunication signal sampling information is based is based, and in the present application, the clock can be considered from another angle, that is, the clock on which the position information is based is a standard clock.
  • the signal sampling information establishes a data pair. If the sampling frequency of the telecommunication signal sampling information is large or the range of the preset time period is large, the plurality of telecommunication signal sampling information in the preset time period in which the first historical time corresponding to the second historical time is located may also be obtained.
  • the average value is used to establish a data pair. For example, if the preset time period of a historical moment is 8 seconds before and after the historical moment, then For the historical time of 10:00:08, the average value of the first group of telecommunication signal sampling information, the second group of telecommunication signal sampling information, and the third group of telecommunication signal sampling information can be obtained as the historical time of 10:00:08.
  • the final telecommunications signal samples the information and establishes a data pair based on this in a subsequent process.
  • the present application after obtaining a plurality of sets of data pairs, for each set of data pairs, determining the distance between the connected base station and the terminal according to the location information of the connected base station and the final location information of the terminal in the telecommunication signal sampling information, If the distance between the connected base station and the terminal is greater than a preset distance threshold, the pair of data pairs may be determined to be an abnormal data pair, thereby deleting the pair of data pairs.
  • the preset distance threshold may be set by a person skilled in the art according to experience, for example, may be set to 300 meters.
  • step 306 for a plurality of normal data pairs, the prediction model is trained and tested, and finally an effective prediction model is obtained. Since the telecommunication signal sampling information in the data pair includes the full amount of telecommunication signal characteristics, the prediction model determined in the present application fully uses the telecommunication signal sampling information, and sampling the prediction model for positioning is higher than the prior art. positioning accuracy.
  • the prediction model in this application is a regression model.
  • the resulting predictive model is a functional relationship between the characteristics of the particular telecommunications signal in the telecommunications signal sample information and the location features in the location information.
  • the specific telecommunication signal feature refers to the telecommunication signal feature and its extended feature that are closely related to the location feature, and specifically refers to the telecommunication signal feature and its extended feature whose correlation with the location feature is greater than or equal to the first threshold.
  • the relevance of a particular telecommunications signal feature and location feature can be derived from a variety of prior art methods of calculating the correlation between variables, which can be set empirically by those skilled in the art.
  • the specific telecommunication signal features have a strong correlation with the location features.
  • the characteristics of the telecommunication signals other than the characteristics of the specific telecommunication signals are those that have less influence on the positional features. Since the changes of the values corresponding to the characteristics of the telecommunication signals have less influence on the position information, the predicted model may not be considered. These telecommunication signal characteristics make the prediction model simpler and more accurate.
  • a particular telecommunications signal feature includes any one or any combination of a first type of signal characteristic, a second type of signal characteristic, and a third type of signal characteristic.
  • the first type of signal characteristics refers to the location The characteristics of the telecommunication signal with relatively close information, for example, RSRP, RSRQ, SINR, etc.; the values corresponding to the first type of signal characteristics are directly obtained from the collected telecommunication signal sampling information.
  • the second type of signal feature includes an extended feature that is closely related to the position information, for example, a Range-Based positioning calculation result, etc.; the second type of signal feature corresponds to a value corresponding to one or more first type of signal features. The value is calculated.
  • the third type of signal features include secondary expansion features that are closely related to the position information, for example, the speed of the terminal, etc.; the values corresponding to the third type of signal features are obtained based on the initial position information of the terminal at different times predicted by the prediction model. of.
  • the initial location information of the terminal at a moment is obtained according to a value and a prediction model corresponding to the first type of signal characteristics and/or the second type of signal characteristics of the terminal at the moment.
  • the specific telecommunication signal characteristics mainly include the following telecommunication signal characteristics and their extended features, respectively:
  • (1) Single-point telecommunications signal characteristics (first type of signal characteristics).
  • the measurement report of the terminal may include RSRP, RSRQ, SINR, TA, main downlink scrambling code, antenna hanging height, direction angle, mechanical tilt angle, electronic downtilt angle, Information about the total power of the cell, the power of the common pilot channel, the transmit power of the terminal, the location of the base station, etc.
  • the parameters of the base station may include the station height of the base station, the frequency band of the base station, the direction angle of the base station, the downtilt angle of the base station, the latitude and longitude of the base station, and the base station. Information such as cell transmission power.
  • Time window association feature (first type of signal feature). A single-point telecommunications signal characteristic of all telecom signal sampling information in a small time window in which telecommunication signal sampling information is located at a historical moment.
  • the third type of signal characteristics calculated after the preliminary position prediction result is obtained by using the prediction model according to the above telecommunication signal and/or the second type of signal feature.
  • the characteristics of the (1) to (4) types are input to the regression model, the position information corresponding to the telecommunication signal sampling information of the terminal is calculated, and then the moving direction, speed, and acceleration of the terminal are calculated according to the position information of each position information before and after the position information.
  • the value corresponding to the sign is the value corresponding to the third type of signal feature.
  • the position information of the historical moments is tested as the test data for the constructed prediction model. For example, based on the historical data of January 1, 2016 (the telecom signal sampling information and location information of 1000 terminals at multiple times in the time period of 8:00:00-20:00:00), Shanghai was constructed. After the prediction model of Pudong New Area, the telecom signal sampling information and multiples of 1000 terminals in multiple first historical moments in the time period from 8:00:00 to 12:00:00 on January 2, 2016 can be obtained. The position information of the second historical moment is tested as a test data for the prediction model.
  • the specific test process is as follows: taking the test process of a terminal at a historical moment as an example, the location information can be predicted by using the prediction model according to the telecommunication signal sampling information of the terminal at the historical moment, and the predicted location information and the history can be predicted. Comparing the position information in the test data pair corresponding to the time, if the difference is within the preset difference range, determining that the test result of the terminal at the historical time is successful, wherein the preset difference range may be based on experience by a person skilled in the art. For example, the distance between the predicted location information and the location information acquired by the terminal at the moment may be less than or equal to 3 meters. In the same way, all test data is tested.
  • the prediction model is valid, and the terminal can be positioned according to the prediction model. Otherwise, the prediction is needed.
  • the model is revised.
  • the preset ratio value can be set according to experience by a person skilled in the art, for example, can be set to 90%.
  • FIG. 7 is a schematic flow chart of another construction prediction model in the present application.
  • FIG. 7 illustrates, in a more visual manner, the process of constructing a predictive model in the present application, which corresponds to steps 301 to 306 above, and is not specifically described herein.
  • the prediction model is determined according to a plurality of sets of data pairs of at least two historical terminals in the target area, and each of the plurality of sets of data pairs includes telecommunication signal sampling information and location information, Since the telecommunication signal sampling information and the location information are directly available in the prior art, there is no need to additionally collect, so the positioning cost can be effectively reduced; and, since the prediction model is trained by a large amount of data in the target area region, It has strong fault tolerance and error correction capability, and can accurately reflect the relationship between the telecom signal sampling information and the location information of the terminal, which avoids the multipath attenuation of the telecommunication signal strength in the prior art.
  • the problem of non-line-of-sight blocking and other factors and the number of base stations connected to the terminal are insufficient to cause inaccurate positioning. Therefore, according to the prediction model in the present invention and the telecommunication signal sampling information of the terminal, the positioning of the terminal can be effectively improved. Degree, reduce positioning error, has a strong practical value.
  • the prediction model in the target area is acquired.
  • the prediction model refers to a functional relationship between specific telecommunication signal characteristics and location information in the telecommunication signal sampling information of the terminal. If the specific telecommunication signal characteristics include: telecommunication signal feature x1, telecommunication signal feature x2, telecommunication signal feature x3, ...
  • the telecommunication signal characteristic xk the prediction model is a functional relationship between the telecommunication signal characteristic x1, the telecommunication signal characteristic x2, the telecommunication signal characteristic x3, ..., the telecommunication signal characteristic xk and the position information, and the input quantity of the prediction model is the telecommunication signal characteristic.
  • X1, telecommunication signal characteristic x2, telecommunication signal characteristic x3, ..., telecommunication signal characteristic xk the output quantity is predicted position information.
  • the value corresponding to the telecommunication signal feature may be a specific value or may be a information that is not represented by a numerical form.
  • the value corresponding to the reference signal receiving quality at the current time may be obtained as a value corresponding to the telecommunication signal feature; if the telecommunication signal characteristic is connected to the base station ID or other is not in the form of a numerical value.
  • information corresponding to the characteristics of the telecommunication signal can be obtained as a value corresponding to the telecommunication signal feature.
  • Table 9 it is an example of the telecommunication signal sampling information of the collected terminal to be located at the current time.
  • Table 9 Example of telecommunication signal sampling information of the terminal to be located at the current time
  • the input quantity of the obtained prediction model includes k telecommunication signal characteristics, and the more the input input quantity is more complete during the positioning process, the higher the accuracy of the positioning is, the more accurate.
  • the collected terminal to be located may have a value corresponding to the missing part of the feature in the telecommunication signal sampling information at the current time, in the actual process, the input amount that can be obtained may be input by a person skilled in the art according to a specific situation to complete
  • a plurality of telecommunication signal features of the k telecommunication signal features may be input to predict location information of the terminal to be located.
  • the values corresponding to the 15 telecommunication signal characteristics of the 20 telecommunication signal features are obtained, and the values corresponding to the 15 telecommunication signal characteristics are input into the prediction model, which can also predict more accurately.
  • Position information of the terminal to be located if only the values corresponding to the 5 telecommunication signal features of the 20 telecommunication signal features are acquired, the values corresponding to the 5 telecommunication signal features are input into the prediction model, and the predicted to be located is to be located. There is a large error in the location information of the terminal.
  • the value of the obtained telecommunication signal feature should be sufficient, close to the number of input quantities in the prediction model, or the number of values corresponding to the acquired telecommunication signal characteristics.
  • the ratio of the number of input quantities in the prediction model is greater than or equal to the preset ratio; the preset ratio may be set by an expert according to the experience, for example, may be set to 70%.
  • the specific telecommunication signal feature includes any one or any combination of the first type of signal feature, the second type of signal feature, and the third type of signal feature;
  • the first type of signal feature corresponds to a value from the terminal to be located at the current Extracted from the telecommunication signal sampling information of the moment;
  • the second type of signal The value corresponding to the sign is calculated according to the value corresponding to one or more first type of signal features;
  • the value corresponding to the third type of signal feature is the initial position of the terminal at the current time and the current time through the terminal to be located. Obtained by the information; the initial position information of the terminal to be located at one time is calculated by functionally calculating one or more first-type signal features and/or values corresponding to the second type of signal features at the time.
  • the present application preferably includes a specific telecommunication signal feature including a first type of signal feature, a second type of signal feature, and a third type of signal feature.
  • the telecommunication signal feature x1, the telecommunication signal feature x2, the telecommunication signal feature x3, ..., the telecommunication signal feature xn is the first type of signal feature, the telecommunication signal feature xn, the telecommunication signal feature xn+1, the telecommunication signal feature xn+2...
  • the telecommunication signal characteristic xm is the second type of signal feature, the telecommunication signal characteristic xm, the telecommunication signal characteristic xm+1, the telecommunication signal characteristic xm+2, ..., and the telecommunication signal characteristic xk is the third type of signal characteristic.
  • the value corresponding to all or part of the telecommunication signal feature x1, the telecommunication signal feature x2, the telecommunication signal feature x3, and the telecommunication signal feature xn may be based on the collected telecommunication signal sampling information of the current time to be located (ie, the content in Table 9) )get.
  • the values corresponding to RSRP, RSRQ, and SINR can be directly obtained from Table 9.
  • the values corresponding to all or part of the telecommunication signal feature xn, the telecommunication signal feature xn+1, the telecommunication signal feature xn+2, ..., and the telecommunication signal feature xm may be obtained from values corresponding to the already obtained first type of signal characteristics.
  • the telecommunication signal feature xn+1 is a Range-based positioning result, and the corresponding value can be calculated according to the collected signal strength value (the value corresponding to the first type of signal feature) by a positioning method such as triangulation and conjugate curve. .
  • All or part of the telecommunication signal feature xm, the telecommunication signal feature xm+1, the telecommunication signal feature xm+2, ..., the telecommunication signal feature xk can be obtained according to the initial position information of the terminal to be located at the current time and the current time
  • the initial position information of the to-be-positioned terminal at one time is obtained by calculating the value corresponding to one or more first-type signal features and/or second-type signal features of the time by the functional relationship. For example, if the telecommunication signal feature xm is the speed of the terminal to be located, firstly all the first type of signal features and the second type of signal features that have been acquired may be corresponding.
  • the value is input into the prediction model, and then the initial position information of the terminal to be located at the current time is obtained (ie, the rough positioning is performed), and the same method is used to obtain the initial time of the terminal to be located at the current time (the first few moments).
  • the location information may be calculated according to the initial location information of the terminal to be located at the current time and the current time at the current time.
  • the prediction model is input, and finally the position information of the first terminal at the current time is predicted.
  • the value corresponding to the third type of signal feature is obtained by coarse positioning (ie, coarse-grained positioning)
  • the value corresponding to the third type of signal feature is again used as an input of the prediction model, enabling finer-grained positioning. To make the positioning more accurate.
  • a particular telecommunication signal feature includes both a first type of signal characteristic, a second type of signal characteristic, and a third type of signal characteristic.
  • a specific telecommunication signal feature includes the first class.
  • the signal characteristics and the second type of signal characteristics, the specific telecommunication signal characteristics including both the first type of signal characteristics and the third type of signal characteristics, can be implemented with reference to the above situation.
  • the positioning method in the present application is obtained by training according to the telecommunication pipeline data in the stage of constructing the prediction model. In the positioning phase, only the telecommunication signal sampling information of the terminal is acquired, and the positioning can be realized. Therefore, each of the present application The process only needs telecommunication pipe data, does not require the terminal to perform other service requests, and reduces the processing load of the terminal, and the positioning method in the present application does not require the terminal to open GPS, AGPS (Assisted GPS, Assisted Global Positioning System) and other positioning devices. , you can achieve positioning.
  • AGPS Assisted GPS, Assisted Global Positioning System
  • the spatio-temporal information recorded by the telecommunication pipeline data can more accurately describe the behavior of the crowd holding the terminal, and the prediction model constructed by the telecommunication pipeline data can be more accurate. More realistically reflecting the relationship between the telecom signal sampling information and the location information of the terminal, the prediction model can achieve more accurate positioning, and has broad application prospects, for example, in the advertising consulting industry, through positioning According to the outdoor flow data, the advertisement is priced and evaluated.
  • the precise location of the retail store can be realized according to the flow data.
  • the scientific traffic planning according to the flow data can be realized through positioning.
  • the application further provides a network device, and the specific content of the network device can be implemented by referring to the foregoing method.
  • FIG. 8 is a schematic structural diagram of a network device provided by the present application. As shown in FIG. 8, the network device 800 includes:
  • the obtaining module 801 is configured to obtain the telecommunication signal sampling information of the first terminal at the current time; the first terminal is any terminal located in the target area, and the target area is a predetermined geographical area;
  • the processing module 802 is configured to predict, according to the telecommunication signal sampling information of the first terminal at the current time and the prediction model of the target area, location information of the first terminal at the current time; the prediction model is Determining according to a plurality of sets of data pairs of at least two historical terminals in the target area; each set of data pairs in the plurality of sets of data pairs includes telecommunication signal sampling information and location information, and telecommunication signals in the data pair are sampled The information and location information are telecommunication signal sampling information and location information of the same historical terminal at the same historical moment.
  • processing module 802 is further configured to:
  • processing module 802 is specifically configured to:
  • the specific telecommunication signal feature includes a first type of signal feature and a second type of signal feature And any combination or combination of the third type of signal characteristics;
  • the value corresponding to the signal characteristic of the first type is extracted from the telecommunication signal sampling information of the current time at the terminal to be located;
  • the values corresponding to the second type of signal features are calculated according to values corresponding to one or more first type of signal features
  • the value corresponding to the third type of signal feature is obtained by initial position information of the to-be-located terminal at the current time and the adjacent time of the current time; the terminal to be located is at the current time or
  • the initial position information of the adjacent time at the current time is obtained by computing the value corresponding to one or more first type signal characteristics and/or second type signal characteristics of the time by the functional relationship.
  • processing module 802 is further configured to:
  • processing module 802 is specifically configured to:
  • the first preset rule Determining, by the first preset rule, a clock correspondence between the plurality of first historical moments of the first historical terminal and the plurality of second historical moments, where the first preset rule is any one of a plurality of preset rules Preset rules;
  • the network device determines the first according to the clock correspondence a second historical time corresponding to a historical time, and according to the location information of the base station in the telecommunication signal sampling information of the first historical time and the first historical terminal of the second historical time corresponding to the first historical time Position information, determining a distance between the base station and the first historical terminal at a first historical moment;
  • the target clock correspondence Determining, by the target clock correspondence, a plurality of sets of data pairs of the first historical terminal; the target clock correspondence is the plurality of preset rules, where the first historical terminal and the first historical terminal belong The clock correspondence between the sum of the distances of the base stations at the plurality of first historical moments is the smallest.
  • the telecommunication signal sampling information of the first historical terminal at the plurality of first historical moments is acquired according to the first frequency; the location information of the first historical terminal at the plurality of second historical moments is according to the first Obtained by two frequencies; the first frequency is smaller than the second frequency;
  • the processing module 802 is specifically configured to:
  • the location information of the first historical terminal at the multiple second historical moments includes the first type of location information and/or the second type of location information;
  • the first type of location information is location information obtained by parsing data collected by the network device through the Gn interface;
  • the second type of location information is that after the network device determines the motion track of the first historical terminal according to the first type of location information and the map information of the target area, according to the motion track, any two The position information obtained by interpolation in the adjacent first type of position information.
  • the network device acquires the telecommunication signal sampling information of the first terminal at the current time, where the first terminal is any terminal located in the target area, and the target area is a predetermined geographical area;
  • the telecommunication signal sampling information of the terminal at the current time and the prediction model of the target area predict the position information of the first terminal at the current time.
  • the prediction model is determined according to multiple sets of data pairs of at least two historical terminals in the target area, and each set of data pairs includes telecommunication signal sampling information and location information, due to telecommunication signal sampling information and location information.
  • the information can be directly obtained in the prior art without additional acquisition, so the positioning cost can be effectively reduced; and since the prediction model is obtained by training a large amount of data in the target area, it has strong fault tolerance and The error correction capability can more accurately reflect the relationship between the telecom signal sampling information and the location information of the terminal, and well avoids interference in the prior art due to multipath attenuation and non-line of sight blocking. And the problem that the number of base stations connected to the terminal is insufficient to cause inaccurate positioning. Therefore, according to the prediction model in the present invention and the telecommunication signal sampling information of the terminal, the positioning accuracy can be effectively improved, and the positioning error is reduced. Strong practical value.
  • FIG. 9 exemplarily shows a schematic structural diagram of another network device provided by the present application.
  • the network device 900 includes: a memory 901, a processor 902;
  • the memory 901 is configured to store a program.
  • the program can include program code, the program code including computer operating instructions.
  • the memory 901 may be a random access memory (RAM) or a non-volatile memory, such as at least one disk storage. Only one memory is shown in the figure, of course, the memory can also be set to a plurality as needed. Memory 901 can also be a memory in processor 902.
  • the memory 901 stores the following elements, executable modules or data structures, or a subset thereof, or an extended set thereof:
  • Operation instructions include various operation instructions for implementing various operations.
  • Operating system Includes a variety of system programs for implementing various basic services and handling hardware-based tasks.
  • the memory 901 further stores the acquired telecommunication signal sampling information of the first terminal at the current time and a prediction model of the target area; the first terminal is any terminal located in the target area, and the target area is a predetermined geography.
  • An area; the prediction model is determined according to a plurality of sets of data pairs of at least two historical terminals in the target area; each of the plurality of sets of data pairs includes an electric
  • the signal sampling information and the location information, the telecommunication signal sampling information and the location information in the data pair are telecommunication signal sampling information and location information of the same historical terminal at the same historical moment.
  • the processor 902 controls the operation of the network device 900, which may also be referred to as a CPU (Central Processing Unit).
  • the various components of the network device 900 are coupled together by a bus system.
  • the bus system may include a power bus, a control bus, a status signal bus, and the like in addition to the data bus.
  • the various buses are labeled as bus systems in the figure. For ease of representation, only the schematic drawing is shown in FIG.
  • Processor 902 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the foregoing method may be completed by an integrated logic circuit of hardware in the processor 902 or an instruction in a form of software.
  • the processor 902 described above may be a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or discrete hardware. Component.
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA field programmable gate array
  • the methods, steps, and logical block diagrams disclosed in the embodiments of the present application can be implemented or executed.
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the steps of the method disclosed in the embodiments of the present application may be directly implemented by the hardware decoding processor, or may be performed by a combination of hardware and software modules in the decoding processor.
  • the software module can be located in a conventional storage medium such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like.
  • the storage medium is located in the memory 901, and the processor 902 reads the information in the memory 901 and performs the following steps in conjunction with its hardware:
  • processor 902 is further configured to:
  • processor 902 is specifically configured to:
  • the specific telecommunication signal feature includes any one or any combination of the first type of signal feature, the second type of signal feature, and the third type of signal feature;
  • the value corresponding to the signal characteristic of the first type is extracted from the telecommunication signal sampling information of the current time at the terminal to be located;
  • the values corresponding to the second type of signal features are calculated according to values corresponding to one or more first type of signal features
  • the value corresponding to the third type of signal feature is obtained by initial position information of the to-be-located terminal at the current time and the adjacent time of the current time; the terminal to be located is at the current time or
  • the initial position information of the adjacent time at the current time is obtained by computing the value corresponding to one or more first type signal characteristics and/or second type signal characteristics of the time by the functional relationship.
  • processor 902 is further configured to:
  • processor 902 is specifically configured to:
  • the first preset rule Determining, according to the first preset rule, a plurality of first historical moments of the first historical terminal and multiple a clock correspondence relationship of the second historical time, where the first preset rule is any one of a plurality of preset rules;
  • the network device Calculating, by the first preset rule, a sum of distances between the first historical terminal and the base station to which the first historical terminal belongs at a plurality of first historical moments; wherein the first historical terminal and the first The distance of each of the plurality of first historical moments of the base station to which the historical terminal belongs is obtained by: the network device determining, according to the clock correspondence, the first historical moment a second historical time, and determining, according to the location information of the base station in the telecommunication signal sampling information of the first historical time and the location information of the first historical terminal at the second historical time corresponding to the first historical time Determining a distance between the base station and the first historical terminal at a first historical moment;
  • the target clock correspondence Determining, by the target clock correspondence, a plurality of sets of data pairs of the first historical terminal; the target clock correspondence is the plurality of preset rules, where the first historical terminal and the first historical terminal belong The clock correspondence between the sum of the distances of the base stations at the plurality of first historical moments is the smallest.
  • the telecommunication signal sampling information of the first historical terminal at the plurality of first historical moments is acquired according to the first frequency; the location information of the first historical terminal at the plurality of second historical moments is according to the first Obtained by two frequencies; the first frequency is smaller than the second frequency;
  • the processor 902 is specifically configured to:
  • the location information of the first historical terminal at the multiple second historical moments includes the first type of location information and/or the second type of location information;
  • the first type of location information is location information obtained by parsing data collected by the network device through the Gn interface;
  • the second type of location information is that the network device is based on the first type of location information and the destination After the map information of the target area determines the motion track of the first history terminal, the obtained position information is interpolated in any two adjacent first type position information according to the motion track.
  • the network device acquires the telecommunication signal sampling information of the first terminal at the current time, where the first terminal is any terminal located in the target area, and the target area is predetermined. a geographic area; the network device predicts location information of the first terminal at the current moment according to the telecommunication signal sampling information of the first terminal at the current time and the prediction model of the target area.
  • the prediction model is determined according to a plurality of sets of data pairs of at least two historical terminals in the target area, and each of the plurality of sets of data pairs includes telecommunication signal sampling information and location information, due to telecommunication signal sampling information and The location information is directly available in the prior art, and no additional acquisition is required, so the positioning cost can be effectively reduced.
  • the prediction model is obtained by training a large amount of data in the target area, it has strong The fault-tolerant and error-correcting capability can more accurately reflect the relationship between the telecom signal sampling information and the location information of the terminal, which avoids the factors such as multipath attenuation and non-line-of-sight blocking in the prior art.
  • the interference and the number of base stations connected to the terminal are insufficient to cause inaccurate positioning. Therefore, according to the prediction model in the present invention and the telecommunication signal sampling information of the terminal, the positioning accuracy can be effectively improved, and the positioning error can be reduced. Has a strong practical value.
  • embodiments of the present invention can be provided as a method, or a computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or a combination of software and hardware. Moreover, the invention can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) including computer usable program code.
  • the computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture comprising the instruction device.
  • the apparatus implements the functions specified in one or more blocks of a flow or a flow and/or block diagram of the flowchart.
  • These computer program instructions can also be loaded onto a computer or other programmable data processing device such that a series of operational steps are performed on a computer or other programmable device to produce computer-implemented processing for execution on a computer or other programmable device.
  • the instructions provide steps for implementing the functions specified in one or more of the flow or in a block or blocks of a flow diagram.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Medical Informatics (AREA)
  • Mobile Radio Communication Systems (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)
  • Telephonic Communication Services (AREA)

Abstract

一种终端定位方法及网络设备，网络设备获取第一终端在当前时刻的电信信号采样信息，其中，第一终端为位于目标区域内的任一终端，目标区域为预定的地理区域；网络设备根据第一终端在当前时刻的电信信号采样信息以及目标区域的预测模型，预测得到第一终端在所述当前时刻的位置信息。本申请中，预测模型是通过目标区域内的大量数据训练得到的，具有较强的容错和纠错能力，能够较为准确地反映出终端的电信信号采样信息和位置信息之间的关系，因此，根据本发明中的预测模型和终端的电信信号采样信息进行定位，有效提高终端定位的准确度，降低了定位误差，具有较强的实用价值。

Description

一种终端定位方法及网络设备
本申请要求在2016年4月29日提交中国专利局、申请号为201610289359.4、发明名称为“一种终端定位方法及网络设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及通信技术领域，尤其涉及一种终端定位方法及网络设备。
背景技术
随着移动设备和移动互联网的普及，终端定位技术也在不断发展。目前，常用的一种终端定位方法为基于测控的定位方法Range-Based。Range-Based方法是指通过计算移动终端到连接基站的距离，然后通过三角定位技术确定终端实际位置的方法，其中，三角定位法是指通过终端接收到的三个基站的电信信号强度(Radio Signal Strength，简称RSS)，估算出终端与基站的距离，并以此距离为半径画出一个覆盖圆弧，三个覆盖圆弧的交叉点即为终端的位置。该方法的核心步骤是计算终端和所连接基站的距离，具体可通过观测到的电信信号强度和电信信号在传播中的衰减(理想曲面传播情况下的信号衰减模型)来估计终端与基站之间的距离，然而，由于电信信号强度通常会受到多径衰减、非视距阻挡等因素的干扰，从而导致三角定位的定位精度较低，误差较大。且，根据对实际记录的统计，大多数终端只连接少于3个基站，如表1所示，为统计某运营商一天和三天的测量报告(Measurement Report，简称MR)记录中终端连接基站的个数所占百分比情况：
表1：终端连接基站的个数所占百分比
Figure PCTCN2016102043-appb-000001
通过对表1进行分析可知，大多数终端连接的基站只有1个或2个，从而进一步导致了采用三角定位等算法对终端进行定位时定位不准确的问题。
综上所述，现有的定位方法通过计算终端与基站之间的距离来对终端进行定位会由于电信信号收到干扰而导致定位精度低、误差大的问题，因此，目前亟需一种更为有效的终端定位方法，用于提高定位的准确度，降低定位误差。
发明内容
本申请提供一种终端定位方法及网络设备，用以实现解决现有技术中的定位方法存在定位精度较低、误差较大的技术问题。
本申请提供的一种终端定位方法，包括：
网络设备获取第一终端在当前时刻的电信信号采样信息；所述第一终端为位于目标区域内的任一终端，所述目标区域为预定的地理区域；
所述网络设备根据所述第一终端在当前时刻的电信信号采样信息以及所述目标区域的预测模型，预测得到所述第一终端在所述当前时刻的位置信息；所述预测模型是根据所述目标区域内的至少两个历史终端的多组数据对确定的；所述多组数据对中的每组数据对包括电信信号采样信息和位置信息，所述数据对中的电信信号采样信息和位置信息为同一历史终端在同一历史时刻的电信信号采样信息和位置信息。
如此，由于预测模型是根据目标区域内的至少两个历史终端的多组数据对确定的，且多组数据对中包括的电信信号采样信息和位置信息均为现有技术中可直接获取到的信息，而无需再额外采集，因此能够有效降低定位成本；且，由于预测模型是通过目标区域区域内的大量数据训练得到的，具有较强的容错和纠错能力，能够较为准确地反映出终端的电信信号采样信息和位置信息之间的关系，很好地避免了现有技术中由于电信信号强度受到多径衰减、非视距阻挡等因素的干扰以及终端连接的基站个数不足而导致定位不准确的问题，因此，根据本发明中的预测模型和终端的电信信号采样信息进行定位， 能够有效提高终端定位的准确度，降低定位误差，具有较强的实用价值。
可选地，所述预测模型由所述网络设备通过以下方式确定：
所述网络设备从所述多组数据对的电信信号采样信息中，筛选出与所述多组数据对的位置信息中的位置特征的相关度大于或等于第一阈值的特定电信信号特征；
所述网络设备建立所述特定电信信号特征与所述位置特征之间的函数关系，得到所述预测模型。
如此，网络设备通过对多组数据对进行训练，筛选出特定电信信号特征，并建立特定电信信号特征与位置特征之间的函数关系，从而使得构建出的预测模型更为简单准确。
可选地，所述网络设备根据所述第一终端在当前时刻的电信信号采样信息以及所述目标区域的预测模型，预测得到所述第一终端在所述当前时刻的位置信息，包括：
所述网络设备至少根据所述待定位终端在所述当前时刻的电信信号采样信息，得到所述特定电信信号特征对应的值；
所述网络设备根据所述预测模型和所述特定电信信号特征对应的值进行运算，得到所述第一终端在当前时刻的位置信息。
如此，网络设备只需获取到特定电信信号特征对应的值，便可根据预测模型得到第一终端在当前时刻的位置信息，而无需再获取额外的信息，从而能够降低定位的成本，实现快速定位。
可选地，所述特定电信信号特征包括第一类信号特征、第二类信号特征和第三类信号特征中的任一种或任意组合；
所述第一类信号特征对应的值是从所述待定位终端在所述当前时刻的电信信号采样信息中提取得到的；
所述第二类信号特征对应的值是根据一个或一个以上的第一类信号特征对应的值进行运算得到的；
所述第三类信号特征对应的值是通过所述待定位终端在所述当前时刻和 所述当前时刻的相邻时刻的初始位置信息得到的；所述待定位终端在所述当前时刻或所述当前时刻的相邻时刻的初始位置信息是通过所述函数关系对该时刻的一个或一个以上的第一类信号特征和/或第二类信号特征对应的值进行运算得到的。
如此，由于特定电信信号特征可包括上述三种类型，从而使得用于定位的特定电信信号特征较为全面，充分考虑各种可能影响终端的位置信息的电信信号特征，进而保证定位的精度和准确性。
可选地，所述至少两个历史终端中的任一历史终端的多组数据对根据如下方法得到：
针对第一历史终端，所述网络设备获取所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息；所述第一历史终端为所述至少两个历史终端中的任一历史终端；
所述网络设备根据所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对。
可选地，所述网络设备根据所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对，包括：
所述网络设备根据第一预设规则，确定所述第一历史终端的多个第一历史时刻与多个第二历史时刻的时钟对应关系，所述第一预设规则为多个预设规则中的任一预设规则；
所述网络设备针对所述第一预设规则，计算所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和；其中，所述第一历史终端与所述第一历史终端所属的基站在所述多个第一历史时刻中的每个第一历史时刻的距离通过以下方法得到：所述网络设备根据所述时钟对应关系，确定所述第一历史时刻对应的第二历史时刻，并根据所述第一历史时刻的电信信号采样信息中的基站的位置信息及所述第一历史时刻对应的第二历史时 刻的所述第一历史终端的位置信息，确定所述基站与所述第一历史终端在第一历史时刻的距离；
所述网络设备根据目标时钟对应关系，确定所述第一历史终端的多组数据对；所述目标时钟对应关系为所述多个预设规则中，所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和最小的时钟对应关系。
如此，充分考虑所采集到的电信信号采样信息和位置信息可能存在的时钟不同步问题，根据多种预设规则，确定出第一历史终端的电信信号采样信息所依据的时钟与位置信息所依据的时钟之间的时间偏移量，得到目标时钟对应关系，进而根据目标时钟对应关系，确定出多组数据对，通过这种方式对用于训练预测模型的数据进行处理，使得构建预测模型所依据的数据更准确，进而使得构建出的预测模型更符合实际情况。
可选地，所述第一历史终端在多个第一历史时刻的电信信号采样信息是按照第一频率获取到的；所述第一历史终端在多个第二历史时刻的位置信息是按照第二频率获取到的；所述第一频率小于所述第二频率；
所述网络设备根据目标时钟对应关系，确定所述第一历史终端的多组数据对，包括：
所述网络设备将所述第一历史终端在多个第一历史时刻的电信信号采样信息分别作为所述多组数据对中的电信信号采样信息，以及
所述网络设备根据所述目标时钟对应关系，得到所述多个第一历史时刻对应的多个第二历史时刻，并至少根据所述多个第一历史时刻对应的多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对中的位置信息。
如此，充分考虑电信信号采样信息和位置信息之间采样频率的差异，并至少根据第一历史时刻对应的第二历史时刻的位置信息得到数据对中的位置信息，例如，可根据第一历史时刻对应的第二历史时刻的预设时间段内的位置信息的平均值得到数据对中的位置信息，从而使得数据对中的位置信息更为准确。
可选地，所述第一历史终端在多个第二历史时刻的位置信息包括第一类位置信息和/或第二类位置信息；
所述第一类位置信息为对所述网络设备通过Gn口采集到的数据进行解析得到的位置信息；
所述第二类位置信息为所述网络设备根据所述第一类位置信息和所述目标区域的地图信息确定出所述第一历史终端的运动轨迹后，根据所述运动轨迹，在任意两个相邻的第一类位置信息中插值得到的位置信息。
如此，考虑到第一类位置信息可能存在采样频率较低的问题，充分利用运动轨迹，通过插值得到第二类位置信息，从而使得位置信息更为密集，确保第一历史时刻的电信信号采样信息均存在对应的位置信息，便于充分利用电信信号采样信息。
本申请提供一种网络设备，该网络设备包括：
获取模块，用于获取第一终端在当前时刻的电信信号采样信息；所述第一终端为位于目标区域内的任一终端，所述目标区域为预定的地理区域；
处理模块，用于根据所述第一终端在当前时刻的电信信号采样信息以及所述目标区域的预测模型，预测得到所述第一终端在所述当前时刻的位置信息；所述预测模型是根据所述目标区域内的至少两个历史终端的多组数据对确定的；所述多组数据对中的每组数据对包括电信信号采样信息和位置信息，所述数据对中的电信信号采样信息和位置信息为同一历史终端在同一历史时刻的电信信号采样信息和位置信息。
可选地，所述处理模块还用于：
从所述多组数据对的电信信号采样信息中，筛选出与所述多组数据对的位置信息中的位置特征的相关度大于或等于第一阈值的特定电信信号特征；
建立所述特定电信信号特征与所述位置特征之间的函数关系，得到所述预测模型。
可选地，所述处理模块具体用于：
至少根据所述待定位终端在所述当前时刻的电信信号采样信息，得到所 述特定电信信号特征对应的值；
根据所述预测模型和所述特定电信信号特征对应的值进行运算，得到所述待定位终端在当前时刻的位置信息。
可选地，所述特定电信信号特征包括第一类信号特征、第二类信号特征和第三类信号特征中的任一种或任意组合；
所述第一类信号特征对应的值是从所述待定位终端在所述当前时刻的电信信号采样信息中提取得到的；
所述第二类信号特征对应的值是根据一个或一个以上的第一类信号特征对应的值进行运算得到的；
所述第三类信号特征对应的值是通过所述待定位终端在所述当前时刻和所述当前时刻的相邻时刻的初始位置信息得到的；所述待定位终端在所述当前时刻或所述当前时刻的相邻时刻的初始位置信息是通过所述函数关系对该时刻的一个或一个以上的第一类信号特征和/或第二类信号特征对应的值进行运算得到的。
可选地，所述处理模块还用于：
根据如下方法得到所述至少两个历史终端中的任一历史终端的多组数据对：
针对第一历史终端，获取所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息；所述第一历史终端为所述至少两个历史终端中的任一历史终端；
根据所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对。
可选地，所述处理模块具体用于：
根据第一预设规则，确定所述第一历史终端的多个第一历史时刻与多个第二历史时刻的时钟对应关系，所述第一预设规则为多个预设规则中的任一预设规则；
针对所述第一预设规则，计算所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和；其中，所述第一历史终端与所述第一历史终端所属的基站在所述多个第一历史时刻中的每个第一历史时刻的距离通过以下方法得到：所述网络设备根据所述时钟对应关系，确定所述第一历史时刻对应的第二历史时刻，并根据所述第一历史时刻的电信信号采样信息中的基站的位置信息及所述第一历史时刻对应的第二历史时刻的所述第一历史终端的位置信息，确定所述基站与所述第一历史终端在第一历史时刻的距离；
根据目标时钟对应关系，确定所述第一历史终端的多组数据对；所述目标时钟对应关系为所述多个预设规则中，所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和最小的时钟对应关系。
可选地，所述第一历史终端在多个第一历史时刻的电信信号采样信息是按照第一频率获取到的；所述第一历史终端在多个第二历史时刻的位置信息是按照第二频率获取到的；所述第一频率小于所述第二频率；
所述处理模块具体用于：
将所述第一历史终端在多个第一历史时刻的电信信号采样信息分别作为所述多组数据对中的电信信号采样信息，以及
根据所述目标时钟对应关系，得到所述多个第一历史时刻对应的多个第二历史时刻，并至少根据所述多个第一历史时刻对应的多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对中的位置信息。
可选地，所述第一历史终端在多个第二历史时刻的位置信息包括第一类位置信息和/或第二类位置信息；
所述第一类位置信息为对所述网络设备通过Gn口采集到的数据进行解析得到的位置信息；
所述第二类位置信息为所述网络设备根据所述第一类位置信息和所述目标区域的地图信息确定出所述第一历史终端的运动轨迹后，根据所述运动轨迹，在任意两个相邻的第一类位置信息中插值得到的位置信息。
本申请提供另一种网络设备，该网络设备包括：
存储器，用于存储获取到的第一终端在当前时刻的电信信号采样信息和目标区域的预测模型；所述第一终端为位于目标区域内的任一终端，所述目标区域为预定的地理区域；所述预测模型是根据所述目标区域内的至少两个历史终端的多组数据对确定的；所述多组数据对中的每组数据对包括电信信号采样信息和位置信息，所述数据对中的电信信号采样信息和位置信息为同一历史终端在同一历史时刻的电信信号采样信息和位置信息。
处理器，用于根据所述第一终端在当前时刻的电信信号采样信息以及所述目标区域的预测模型，预测得到所述第一终端在所述当前时刻的位置信息；
可选地，所述处理器还用于：
从所述多组数据对的电信信号采样信息中，筛选出与所述多组数据对的位置信息中的位置特征的相关度大于或等于第一阈值的特定电信信号特征；
建立所述特定电信信号特征与所述位置特征之间的函数关系，得到所述预测模型。
可选地，所述处理器具体用于：
至少根据所述待定位终端在所述当前时刻的电信信号采样信息，得到所述特定电信信号特征对应的值；
根据所述预测模型和所述特定电信信号特征对应的值进行运算，得到所述待定位终端在当前时刻的位置信息。
可选地，所述特定电信信号特征包括第一类信号特征、第二类信号特征和第三类信号特征中的任一种或任意组合；
所述第一类信号特征对应的值是从所述待定位终端在所述当前时刻的电信信号采样信息中提取得到的；
所述第二类信号特征对应的值是根据一个或一个以上的第一类信号特征对应的值进行运算得到的；
所述第三类信号特征对应的值是通过所述待定位终端在所述当前时刻和所述当前时刻的相邻时刻的初始位置信息得到的；所述待定位终端在所述当 前时刻或所述当前时刻的相邻时刻的初始位置信息是通过所述函数关系对该时刻的一个或一个以上的第一类信号特征和/或第二类信号特征对应的值进行运算得到的。
可选地，所述处理器还用于：
根据如下方法得到所述至少两个历史终端中的任一历史终端的多组数据对：
针对第一历史终端，获取所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息；所述第一历史终端为所述至少两个历史终端中的任一历史终端；
根据所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对。
可选地，所述处理器具体用于：
根据第一预设规则，确定所述第一历史终端的多个第一历史时刻与多个第二历史时刻的时钟对应关系，所述第一预设规则为多个预设规则中的任一预设规则；
针对所述第一预设规则，计算所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和；其中，所述第一历史终端与所述第一历史终端所属的基站在所述多个第一历史时刻中的每个第一历史时刻的距离通过以下方法得到：所述网络设备根据所述时钟对应关系，确定所述第一历史时刻对应的第二历史时刻，并根据所述第一历史时刻的电信信号采样信息中的基站的位置信息及所述第一历史时刻对应的第二历史时刻的所述第一历史终端的位置信息，确定所述基站与所述第一历史终端在第一历史时刻的距离；
根据目标时钟对应关系，确定所述第一历史终端的多组数据对；所述目标时钟对应关系为所述多个预设规则中，所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和最小的时钟对应关系。
可选地，所述第一历史终端在多个第一历史时刻的电信信号采样信息是按照第一频率获取到的；所述第一历史终端在多个第二历史时刻的位置信息是按照第二频率获取到的；所述第一频率小于所述第二频率；
所述处理器具体用于：
将所述第一历史终端在多个第一历史时刻的电信信号采样信息分别作为所述多组数据对中的电信信号采样信息，以及
根据所述目标时钟对应关系，得到所述多个第一历史时刻对应的多个第二历史时刻，并至少根据所述多个第一历史时刻对应的多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对中的位置信息。
可选地，所述第一历史终端在多个第二历史时刻的位置信息包括第一类位置信息和/或第二类位置信息；
所述第一类位置信息为对所述网络设备通过Gn口采集到的数据进行解析得到的位置信息；
所述第二类位置信息为所述网络设备根据所述第一类位置信息和所述目标区域的地图信息确定出所述第一历史终端的运动轨迹后，根据所述运动轨迹，在任意两个相邻的第一类位置信息中插值得到的位置信息。
本发明的上述实施例中，网络设备获取第一终端在当前时刻的电信信号采样信息，其中，第一终端为位于目标区域内的任一终端，目标区域为预定的地理区域；网络设备根据第一终端在当前时刻的电信信号采样信息以及目标区域的预测模型，预测得到第一终端在所述当前时刻的位置信息。本申请中，预测模型是根据目标区域内的至少两个历史终端的多组数据对确定的，多组数据对中的每组数据对包括电信信号采样信息和位置信息，由于电信信号采样信息和位置信息均为现有技术中可直接获取到的信息，而无需再额外采集，因此能够有效降低定位成本；且，由于预测模型是通过目标区域区域内的大量数据训练得到的，具有较强的容错和纠错能力，能够较为准确地反映出终端的电信信号采样信息和位置信息之间的关系，很好地避免了现有技术中由于电信信号强度受到多径衰减、非视距阻挡等因素的干扰以及终端连 接的基站个数不足而导致定位不准确的问题，因此，根据本发明中的预测模型和终端的电信信号采样信息进行定位，能够有效提高终端定位的准确度，降低定位误差，具有较强的实用价值。
附图说明
为了更清楚地说明本申请中的技术方案，下面将对实施例描述中所需要使用的附图作简要介绍。
图1为终端的电信管道数据示意图；
图2为本申请提供的一种终端定位方法的流程示意图；
图3为本申请中预测模型的构建流程示意图；
图4为含有位置信息的URL的示例图；
图5为根据第一类位置信息和地图信息确定的运动轨迹示意图；
图6为根据第一类位置信息和运动轨迹确定第二类位置信息示意图；
图7为本申请中构建预测模型的形象示意图；
图8为本申请提供的一种终端定位装置的结构示意图；
图9为本申请提供的另一种终端定位装置的结构示意图。
具体实施方式
为了使本发明的目的、技术方案和优点更加清楚，下面将结合附图对本发明作进一步地详细描述。
本申请中的终端可以为能够支持电信连接的设备，比如能够支持电信连接的手持设备、车载设备、可穿戴设备、计算设备，以及各种形式的用户设备(User Equipment，简称UE)，移动台(Mobile station，简称MS)，终端(terminal)，终端设备(Terminal Equipment)等。具体来说，比如手机、平板电脑、便携式电脑、台式机电脑等。为方便描述，本申请中简称为终端。
终端的电信管道数据记录了终端的所有连接、通信和测量等信息。图1为终端的电信管道数据示意图。如图1所示，电信管道数据中可包括通过 Lampsite/Pico、演进型基站(evolved Node B，eNB)或无线网络控制器(Radio Network Controller，RNC)、统一服务节点(unified service node,USN)、统一分组网关(unified packet gateway，UGW)等采集的信息，和本发明相关的是从RNC上采集的测量报告和Gn口上采集的OTT(over the top)数据。
本申请中，终端的电信管道数据具体可包括终端的电信信号采样信息和位置信息，其中，终端的电信信号采样信息可包括终端的测量报告中的信息、接口上采集到的信息，以及基站的参数信息。其中，终端的测量报告中的信息可包括参考信号接收功率(Reference Signal Receiving Power，简称RSRP)、参考信号接收质量(Reference Signal Receiving Quality，简称RSRQ)、信号与干扰加噪声比(Signal to Interference plus Noise Ratio，简称SINR)、时间提前量(Timing Advance，简称TA)、演进型基站标识(evolved Node B Identification，简称eNB-ID)、小区标识(CELL Identification，简称CELL ID)，终端的发射功率等；接口上采集到的信息可包括Gn接口、Gi接口、EC接口上采集到的信息；基站的参数可包括基站的站高、基站的频段、基站的方向角、基站的下倾角、基站的经纬度和基站的小区发射功率等信息；终端的位置信息包含在电信管道数据中含有位置信息的记录中，比如运行触动传媒、滴滴打车等软件产生的记录等。
通过对现有技术进行分析可知，现有技术中的定位方法虽然也使用了电信信号采样信息，但仅是一种极小范围的使用，例如三角定位法中仅使用了电信管道数据中的电信信号强度，而其它的电信信息比如上下文信息、加速度、角度等均没有被有效地使用。
基于上述情况，申请人考虑到，电信管道数据中包含着大量的信息，且电信运营商通常为城市大量的人口提供服务，因此，电信管道数据可成为获取城市用户细粒度时空行为信息的重要数据源，且通过电信管道数据对群体分析有着天然的优势，进一步地，从电信管道数据中挖掘出终端的时空行为进而实现终端定位，具有较强的可行性。
为实现对电信管道数据的充分合理使用，本申请中基于数据挖掘技术， 对电信管道中终端的电信信号采样信息和位置信息进行分析，确定出终端的电信信号采样信息和位置信息之间的关系，即得到预测模型，从而可基于该预测模型和终端在当前时刻的电信信号采样信息，预测出终端在当前时刻的位置信息。
为使得预测模型具有更强的针对性，预测结果更为准确，本申请中可划定不同的地理范围，从而针对不同地理范围内的历史数据训练得到针对不同地理范围的预测模型。例如，可以根据不同的城区来进行划分，以上海市为例，针对浦东新区、嘉定区、黄浦区、金山区、徐汇区、静安区、杨浦区等不同的城区可分别对应不同的预测模型。
下面以一个目标区域内的终端定位为例进行介绍。本申请中的目标区域是指具有一定面积的区域，为方便统计多个终端在多个历史时刻的电信信号采样信息和位置信息，目标区域尤其是指人口较为密集或人流量较大的区域。
为实现目标区域内的终端定位，图2示例性示出了本申请提供的一种终端定位方法的流程示意图，如图2所示，该方法包括：
步骤201，网络设备获取第一终端在当前时刻的电信信号采样信息；所述第一终端为位于目标区域内的任一终端，所述目标区域为预定的地理区域；
步骤202，所述网络设备根据所述第一终端在当前时刻的电信信号采样信息以及所述目标区域的预测模型，预测得到所述第一终端在所述当前时刻的位置信息；所述预测模型是根据所述目标区域内的至少两个历史终端的多组数据对确定的；所述多组数据对中的每组数据对包括电信信号采样信息和位置信息，所述数据对中的电信信号采样信息和位置信息为同一历史终端在同一历史时刻的电信信号采样信息和位置信息。
本申请中，预测模型是根据目标区域内的至少两个历史终端的多组数据对确定的，多组数据对中的每组数据对包括电信信号采样信息和位置信息预测模型，由于电信信号采样信息和位置信息均为现有技术中可直接获取到的信息，而无需再额外采集，因此能够有效降低定位成本；且，由于预测模型是通过目标区域内的大量数据训练得到的，具有较强的容错和纠错能力，能 够较为准确地反映出终端的电信信号采样信息和位置信息之间的关系，很好地避免了现有技术中由于电信信号强度受到多径衰减、非视距阻挡等因素的干扰以及终端连接的基站个数不足而导致定位不准确的问题，因此，根据本发明中的预测模型和终端的电信信号采样信息进行定位，能够有效提高终端定位的准确度，降低定位误差，具有较强的实用价值。
本申请中，首先需要构建目标区域内的预测模型，然后根据预测模型对终端进行定位。即，本申请包括两个阶段：第一阶段，预测模型的构建阶段；第二阶段，定位阶段。
本申请中的网络设备可以为一个具有处理能力的服务器，此时，第一阶段和第二阶段由同一服务器执行；或者，网络设备也可以为两个具有处理能力的服务器，此时，第一阶段和第二阶段分别由不同的服务器执行。为降低服务器的处理负担，提高处理效率，本申请优选第一阶段和第二阶段分别由不同的服务器执行。
下面分别针对两个阶段进行具体说明。
第一阶段，预测模型的构建阶段
具体地，本申请中的预测模型可由所述网络设备通过以下方式确定：
所述网络设备从至少两个终端的多组数据对的电信信号采样信息中，筛选出与所述多组数据对的位置信息中的位置特征的相关度大于或等于第一阈值的特定电信信号特征；建立所述特定电信信号特征与所述位置特征之间的函数关系，得到所述预测模型。
其中，所述至少两个历史终端中的任一历史终端的多组数据对根据如下方法得到：
针对第一历史终端，所述网络设备获取所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息；所述第一历史终端为所述至少两个历史终端中的任一历史终端；所述网络设备根据第一预设规则，确定所述第一历史终端的多个第一历史时刻与多个第二历史时刻的时钟对应关系，所述第一预设规则为多个预设规则中的 任一预设规则；所述网络设备针对所述第一预设规则，计算所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和，并根据目标时钟对应关系，确定所述第一历史终端的多组数据对；所述目标时钟对应关系为所述多个预设规则中，所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和最小的时钟对应关系。
由上述内容可知，本申请中，预测模型是根据目标区域内的至少两个历史终端的多组数据对确定的目标区域，即预测模型是通过对大量的历史数据进行训练得到的。通常情况下，数据量越大，训练得到的预测模型越接近实际情况，相应地，也会导致数据处理量也会较大，处理消耗的时间较长。本申请可由本领域技术人员综合考虑上述两个方面的因素来选取适当的历史数据量，即选取设定时间段内的多个终端的历史数据，例如，可以为某一天的8:00-22:00这一时间段内的1000个终端的历史数据。
图3为本申请中预测模型的构建流程示意图，以下结合图3，以选取某一天的8:00-22:00这一时间段内的1000个历史终端的历史数据来训练预测模型为例进行说明。如图3所示，包括：
步骤301，获取各个历史终端在多个第一历史时刻的电信信号采样信息，即获取8:00-22:00这一时间段内，1000个历史终端的电信信号采样信息，例如，电信信号采样信息可以为RNC采集的信息。
步骤302，获取各个历史终端在多个第一历史时刻的第一类位置信息，即获取8:00-22:00这一时间段内，1000个历史终端的第一类位置信息。本申请中，第一类位置信息为对所述网络设备通过Gn口采集到的数据进行解析得到的位置信息，具体地，对通过Gn口采集到的数据进行深度包检测(Deep Packet Inspection，简称DPI)解析后，得到统一资源定位符(Uniform Resource Locator，简称URL)，进而得到全球定位系统(Global Positioning System，简称GPS)位置信息，即第一类位置信息。例如，从触动传媒或滴滴打车的URL中得到的GPS位置信息，如图4所示，为含有位置信息的URL的示例图。然而，本申请并不局限于通过Gn口获取位置信息，例如，若运营商和某OTT位置服 务提供商签署协议，则也可以直接获取OTT位置服务提供的位置信息。
需要说明的是，对于上述步骤301和步骤302，步骤的编号仅为一种执行过程的示例性说明，本申请不对各个步骤做明确具体的先后顺序限定，例如，可先执行步骤301，获取各个历史终端的电信信号采样信息，然后再执行步骤302，获取各个历史终端的第一类位置信息；或者，也可先执行步骤302，获取各个历史终端的第一类位置信息，然后再执行步骤301，获取各个历史终端的电信信号采样信息；又或者，同时执行步骤301和步骤302，即同步获取各个历史终端的电信信号采样信息和第一类位置信息。
由于各个终端的电信信号采样信息和第一类位置信息分别记录在电信管道数据的不同部分，且电信信号采样信息和第一类位置信息分别是由不同的设备采集的，因此会有可能出现电信信号采样信息的采样频率和第一类位置信息的采样频率不同，进一步地，还有可能会出现采集电信信号采样信息的设备的时钟与采集第一类位置信息的设备的时钟不同步。
考虑到这些问题，针对于不同采样频率的情形，在步骤302后，可对获取到的电信信号采样信息和第一类位置信息的采样频率进行判断，由于一般情况下，电信信号采样信息的采样频率远远大于第一类位置信息的采样频率，因此，本申请中的下述步骤中主要针对电信信号采样信息的采样频率大于第一类位置信息的采样频率这一情况进行分析说明。
例如，针对于一个历史终端，电信信号采样信息的采样频率为每8秒钟采样一次(RNC采集的MR记录每8秒获取一次)，表2为一个时间段内电信信号采样信息的采样示例，如表2所示，10:00:00采集到该历史终端的第1组电信信号采样信息，10:00:08采集到第2组电信信号采样信息，10:00:16采集到第3组电信信号采样信息，10:00:24采集到第4组电信信号采样信息，10:00:32采集到第5组电信信号采样信息。
表2：一个时间段内电信信号采样信息的采样示例
Figure PCTCN2016102043-appb-000002
Figure PCTCN2016102043-appb-000003
例如，第一类位置信息的采样频率为每1分钟采样一次(触动传媒每1分钟上报一次位置信息)，表3为一个时间段内第一类位置信息的采样示例，如表3所示，10:00:00采集到该历史终端的第1个位置信息，10:01:00采集到第2个位置信息，10:02:00采集到第3个位置信息，10:03:00采集到第4个位置信息，10:04:00采集到第5个位置信息。
表3：一个时间段内第一类位置信息的采样示例
Figure PCTCN2016102043-appb-000004
根据表2和表3的内容可知，电信信号采样信息的采样频率和位置信息的采用频率相差很大，在时钟同步的情况下，若直接将电信信号采样信息与第一类位置信息进行匹配，则会导致大量的电信信号采样信息无法找到匹配的位置信息，从而无法在训练预测模型的过程中被充分使用，例如，在10:00:00采集到的第1组电信信号采样信息可与在10:00:00采集到的第1个位置信息匹配，而在10:00:00至10:01:00这一时间段内采集的电信信号采样信息无法找到匹配的位置信息。针对这一情况，本申请中可引入第二类位置信息，以使得电信信号采样信息均能找到匹配的位置信息，进而被充分使用，具体可执行步骤303。
步骤303，根据各个历史终端的第一类位置信息和目标区域的地图信息确定各个历史终端的运动轨迹，根据所述各个历史终端的运动轨迹，通过在任意两个相邻的第一类位置信息中均匀插值得到各个历史终端的第二类位置信息。
本申请中，目标区域的地图信息可以为预先存储的，地图信息中包括建筑物的位置信息、道路的位置信息等。图5为根据第一类位置信息和地图信 息确定的一个历史终端的运动轨迹示意图，其中，图5中所标示的5个第一类位置信息可以为上述表3中所采集到的5个位置信息，进一步地，如图5所示，黑点为实际URL中抽取的第一类位置信息，根据地图信息中的建筑物的位置信息、道路的位置信息以及5个位置信息，可预测出持有该历史终端的用户在道路上的运动轨迹，即该历史终端的运动轨迹。预测运动轨迹的具体过程可参照现有技术，例如，可以计算一个路径中每个点到每个路段的匹配概率，路段之间的转移概率等，然后计算出概率最大的行走路径，进而得到地图匹配的运动轨迹，此处不做具体介绍。
为使得位置信息更为密集，可根据预测出的该历史终端的运动轨迹，在任意两个第一类位置信息之间进行插值，具体插值的个数可根据情况进行设置。例如，可在10:00:00采集到的第一个位置信息和10:01:00采集到的第二个位置信息之间插入28个值，即插入28个第二类位置信息，从而使得每隔2秒钟便有一个对应的位置信息。
图6为根据第一类位置信息和运动轨迹确定第二类位置信息示意图，如图6所示，在任意两个第一类位置信息之间，在已经确定的运动轨迹上插入三个位置点，该三个位置点的位置信息即为第二类位置信息。具体插值时，若根据已经预测出的终端的运动轨迹，以及各个第一类位置信息，估算出该历史终端的运动速率并未发生太大的变化，则可采用均匀插值的方法，即10:00:00到10:01:00的这一段路程中均匀插入28个位置信息；若根据已经预测出的该历史终端的运动轨迹，以及各个第一类位置信息，估算出该历史终端的运动速率发生了明显的变化，则此时可根据估算出的变化情况，进行相应的不均匀插值。
本申请中，由于历史终端的第一类位置信息为每1分钟采样一次，经过插值后，可实现每隔2秒钟便有一个对应的位置信息，即两个位置信息之间的时间间隔较为短暂，对于这样较短的时间间隔，运动状态一般不会发生太大的变化，因此通常可采用均匀插值的方式。例如，持有该历史终端的用户行走在道路上，每1分钟会有一个对应的第一类位置信息，对于两个相邻的 第一类位置信息，可根据预测出该历史终端的运动轨迹，在其中均匀插入28个的第二类位置信息。
上述内容为针对采样频率不同的问题，通过插值的方式予以解决。现针对可能存在的时钟不同步的问题进行具体的分析。
以终端a为例，若终端a的电信信号采样信息所依据的时钟为标准时钟，然而第一类位置信息所依据的时钟与标准时钟存在偏差，例如，第一类位置信息所依据的时钟相对于标准时钟快1分钟，仍以表1和表2中数据为例，在这种情况下，10:00:00对应的电信信号采样信息应匹配的位置信息为10:01:00对应的位置信息，若是未考虑到时钟不同步的问题，而直接将10:00:00对应的电信信号采样信息应匹配的位置信息为10:00:00对应的位置信息，则会导致预测模型与实际情况存在偏差，从而使得根据预测模型预测出的终端位置不准确。针对这一情况，本申请中可通过进行电信信号采样信息与位置信息的匹配，以校正时钟偏差，从而得到电信信号采样信息与位置信息之间的正确匹配，具体可执行步骤204。
步骤304，根据多个预设规则，确定第一历史终端的多个第一历史时刻与多个第二历史时刻的多种时钟对应关系，针对多种时钟对应关系，分别计算第一历史终端与第一历史终端所属的基站在多个第一历史时刻的距离之和，进而通过比较，确定出第一历史终端的电信信号采样信息所依据的时钟与位置信息所依据的时钟之间的时间偏移量，得到目标时钟对应关系。
具体地，以一个终端(终端b)为例，表4为获取到的终端b的电信信号采样信息以及位置信息(包括第一类位置信息和第二类位置信息)示例，如表4所示，第1组电信信号采样信息为采集电信信号采样信息的时钟在10:00:00对应的电信信号采样信息记录，(x1，y1)为采集位置信息的时钟在10:00:00对应的位置信息记录。
表4：电信信号采样信息和位置信息的采样示例
采样时间 电信信号采样信息记录 位置信息记录
10:00:00 第1组电信信号采样信息 (x1，y1)
10:00:02   (x2，y2)
10:00:04   (x3，y3)
10:00:06   (x4，y4)
10:00:08 第2组电信信号采样信息 (x5，y5)
10:00:10   (x6，y6)
10:00:12   (x7，y7)
10:00:14   (x8，y8)
10:00:16 第3组电信信号采样信息 (x9，y9)
…… …… ……
本申请中，电信信号采样信息中包括有终端b的连接基站的位置信息，从而可获知每组电信信号采样信息中终端b的连接的位置信息。需要说明的是，电信信号采样信息中可能包括终端b的一个连接基站，也可能包括终端b的两个或两个以上的连接基站。若仅包括一个连接基站，则可直接将连接基站的位置信息参与后续的计算；若包括两个或两个以上的连接基站，则可选取终端b接收到的最大电信信号强度对应的连接基站的位置信息参与后续的计算，或者，也可以通过计算得到两个或两个以上的连接基站的平均位置信息，并将该平均位置信息参与后续的计算。本申请中，为减少计算的复杂度，对于两个或两个以上的连接基站的情形，优选的方式为选取终端b接收到的最大电信信号强度对应的连接基站的位置信息参与后续的计算。
由于可能存在时钟不同步的问题，可根据多个预设规则，尝试将相同时间点或不同时间点的电信信号采样信息记录和位置记录进行对应，具体对应情形如下：
第一种预设规则下的对应情形：将表4中位于同一行的电信信号采样信息记录和位置记录进行对应，针对第1组电信信号采样信息，根据终端b的 连接基站的位置信息以及终端的位置信息记录(x1，y1)，确定出终端b的连接基站与终端b之间的距离，标记为距离a1，同理，针对各组电信信号采样信息，均可确定出终端b的连接基站与终端b之间的距离，标记为距离a2至距离aP，从而可得到距离a1至距离aP的距离之和，记为D1。
需要说明的是，第一种对应情形为时间点上的直接对应，因此，各组电信信号采样信息均能找到对应位置信息，然而当进行时间点上的错位对应时，会导致部分数据丢失，例如，当往后错位2秒进行对应(见第二种对应情形)时，有可能导致最后一组电信信号采样信息无对应位置信息，则无法计算终端b的连接基站与终端b之间的距离，从而导致计算出的距离个数少一个，则将根据该种情形计算出的距离之和与根据第一种对应情形计算出的距离之和进行比较时，明显会存在偏差；又例如，当往前错位2秒进行对应时，有可能导致第一组电信信号采样信息无对应位置信息，则无法计算终端b的连接基站与终端b之间的距离，从而也会导致计算出的距离个数少一个。考虑到上述情形，本申请中，可不考虑接近采样起点和接近采样终点的部分数据，从而使得计算出的距离个数相等，例如，本申请在根据各种对应情形计算距离之和时，不考虑最后1组或最后2组电信信号采样信息。
第二种预设规则下的对应情形：如表5所示，将电信信号采样信息记录和晚2秒钟的位置记录进行对应，针对第1组电信信号采样信息，根据终端b的连接基站的位置信息以及终端b的位置信息记录(x2，y2)，确定出终端b的连接基站与终端b之间的距离，标记为距离b1，同理，针对各组电信信号采样信息，均可确定出终端b的连接基站与终端b之间的距离，标记为距离b2至距离bP，从而可得到距离b1至距离bP的距离之和，记为D2。
表5：电信信号采样信息记录和位置记录的对应关系
Figure PCTCN2016102043-appb-000005
Figure PCTCN2016102043-appb-000006
第三种预设规则下的对应情形：如表6所示，将电信信号采样信息记录和晚4秒钟的位置记录进行对应，针对第1组电信信号采样信息，根据终端的连接基站的位置信息以及终端的位置信息记录(x3，y3)，确定出终端的连接基站与终端之间的距离，标记为距离c1，同理，针对各组电信信号采样信息，均可确定出终端的连接基站与终端之间的距离，标记为距离c2至距离cP，从而可得到距离c1至距离cP的距离之和，记为D3。
表6：电信信号采样信息记录和位置记录的对应关系
Figure PCTCN2016102043-appb-000007
Figure PCTCN2016102043-appb-000008
通常情况下，根据可能存在的时钟偏差，可考虑三种或三种以上的对应情形，上述三种对应情形仅为一种示例性表示。具体在考虑对应情形时，也可以直接考虑错位4秒、错位1分钟等情形，本申请中不再具体列举。
针对上述列举的三种情形，比较D1、D2、D3的大小关系，若通过比较确定出D3为最小值，则可确定对于终端b，电信信号采样信息所依据的时钟与位置信息所依据的时钟之间的时间偏移量为4秒，若以终端b的电信信号采样信息所依据的时钟为标准时钟，则位置信息所依据的时钟比标准时钟快4秒。考虑到上述时间偏移量后，可得将第三种对应情形确定为能够正确匹配的对应情形。
根据第三种情形，将位置信息所依据的时钟减去4秒钟的时间偏移量后，得到图表6所示的电信信号采样信息与位置信息的采样示例。
表7：电信信号采样信息和位置信息的采样示例(考虑时间偏移量后)
采样时间 电信信号采样信息记录 位置信息记录
10:00:00 第1组电信信号采样信息 (x3，y3)
10:00:02   (x4，y4)
10:00:04   (x5，y5)
10:00:06   (x6，y6)
10:00:08 第2组电信信号采样信息 (x7，y7)
10:00:10   (x8，y8)
10:00:12   (x9，y9)
10:00:14   (x10，y10)
10:00:16 第3组电信信号采样信息 (x11，y11)
…… …… ……
进一步地，根据第三种对应情形，可确定出与第1组电信信号采样信息直接匹配的位置信息为(x3，y3)，与第2组电信信号采样信息直接匹配的位 置信息为(x7，y7)，与第3组电信信号采样信息直接匹配的位置信息为(x11，y11)。
本申请中，由于位置信息包括第一类位置信息和第二类位置信息，其中，第二类位置信息为通过估算插值得到的，因此，为提高准确率，本申请中需要对位置信息做进一步的处理，具体可执行步骤305。
步骤305，求取一个历史终端在第一历史时刻对应的第二历史时刻所在的预设时间段内的多个位置信息的平均值作为最终的位置信息，建立多个第一时刻的电信信号采样信息与最终的位置信息之间的对应关系，得到该历史终端的多组数据对，进而得到各个历史终端的多组数据对。
例如，对于10:00:00这一第一历史时刻，可求取该第一历史时刻对应的第二历史时刻前后2秒这一时间段内的位置信息(x2，y2)、(x3，y3)、(x4，y4)的平均值，将平均值作为10:00:00最终的位置信息，并建立10:00:00的电信信号采样信息与最终的位置信息之间的对应关系，得到一组数据对。同理，针对每一组电信信号采样信息，均可建立其与位置信息之间的对应关系，得到多组数据对；一组数据对即为同一历史终端在同一历史时刻的电信信号采样信息和位置信息。
需要说明的是，上述是以电信信号采样信息所依据的时钟为标准时钟进行说明的，本申请中，也可以从另一角度，即位置信息所依据的时钟为标准时钟的情形来考虑。
上述得到的一组数据对中的位置信息是根据终端在第二历史时刻所在的预设时间段(前后两秒)内获取到的M(M＝3)个位置信息确定的，由于，在与第二历史时刻对应的第一历史时刻所在的预设时间段(前后两秒)内仅有一个电信信号采样信息(即该历史时刻采集到的电信信号采样信息)，因此，可直接使用该电信信号采样信息建立数据对。若电信信号采样信息的采样频率较大或者预设时间段的范围较大时，也可以求取与第二历史时刻对应的第一历史时刻所在的预设时间段内的多个电信信号采样信息的平均值，来建立数据对。例如，若一个历史时刻的预设时间段为该历史时刻的前后8秒，则 对于10:00:08这一历史时刻，可求取第1组电信信号采样信息、第2组电信信号采样信息、第3组电信信号采样信息的平均值作为10:00:08这一历史时刻最终的电信信号采样信息，并在后续过程中基于此建立数据对。
进一步地，由于采集到的大量数据中难免会出现一些误差较大的数据，即异常数据，若不对异常数据进行处理，则很容易导致运算结果存在偏差。因此，本申请中，在得到多组数据对后，针对每组数据对，根据电信信号采样信息中的连接基站的位置信息和终端最终的位置信息，确定连接基站和终端之间的距离，若连接基站和终端之间的距离大于预设的距离阈值，则可确定该组数据对为异常数据对，从而删除该组数据对。其中，预设的距离阈值可由本领域技术人员根据经验设置，例如，可以设置为300米。
步骤306，针对多组正常的数据对，训练得到预测模型，并进行测试，最终得到有效的预测模型。由于数据对中的电信信号采样信息包括了全量的电信信号特征，因此，本申请中确定出的预测模型充分使用了电信信号采样信息，采样该预测模型进行定位相对于现有技术具有更高的定位精度。
具体地，本申请中的预测模型为回归模型。通过多组正常的数据对进行训练后，得到的预测模型为电信信号采样信息中的特定电信信号特征与位置信息中的位置特征之间的函数关系。其中，特定电信信号特征是指与位置特征的关系较为密切的电信信号特征及其扩展特征，具体是指与位置特征的相关度大于或等于第一阈值的电信信号特征及其扩展特征。特定电信信号特征和位置特征的相关度可由多种现有技术中计算变量之间的相关度的方法得到，第一阈值可由本领域技术人员根据经验设置。也就是说，特定电信信号特征与位置特征有较强的关联关系。而除特定电信信号特征以外的电信信号特征为一些对位置特征的影响较小的特征，由于这些电信信号特征对应的值的变化对位置信息的影响较小，因此，构建的预测模型中可不考虑这些电信信号特征，以使得预测模型更为简单准确。
本申请中，特定电信信号特征包括第一类信号特征、第二类信号特征和第三类信号特征中的任一种或任意组合。其中，第一类信号特征是指与位置 信息的关系较为密切的电信信号特征，例如，RSRP、RSRQ、SINR等；第一类信号特征对应的值是直接从采集到的电信信号采样信息中得到的。第二类信号特征包括与位置信息的关系较为密切的一次扩展特征，例如，Range-Based定位计算结果等；第二类信号特征对应的值是根据一个或一个以上的第一类信号特征对应的值进行运算得到的。第三类信号特征包括与位置信息的关系较为密切的二次扩展特征，例如，终端的速度等；第三类信号特征对应的值是根据预测模型预测出的终端在不同时刻的初始位置信息得到的。其中，终端在一个时刻的初始位置信息是根据终端在该时刻的第一类信号特征和/或第二类信号特征对应的值和预测模型得到的。本申请中，特定电信信号特征主要包括以下电信信号特征及其扩展特征，分别为：
(1)单点电信信号特征(第一类信号特征)。主要为终端的测量报告中的信息以及基站的参数，其中，终端的测量报告中可包括RSRP、RSRQ、SINR、TA、主下行扰码、天线挂高、方向角、机械倾角、电子下倾角、小区总功率、公共导频信道功率、终端的发射功率、基站位置等信息；基站的参数可包括基站的站高、基站的频段、基站的方向角、基站的下倾角、基站的经纬度和基站的小区发射功率等信息。
(2)时间窗关联特征(第一类信号特征)。一个历史时刻的电信信号采样信息所在的小时间窗内所有电信信号采样信息的单点电信信号特征。
(3)Range-Based定位计算结果(第二类信号特征)。
(4)单点关联特征(第二类信号特征)。主要为一个历史时刻的电信信号采样信息和其它信息的关联特征，如表8所示，给出了一组这类特征设计的示例。
表8：单点关联特征设计示例
Figure PCTCN2016102043-appb-000009
Figure PCTCN2016102043-appb-000010
(5)根据以上电信信号和/或第二类信号特征使用预测模型取得初步位置预测结果后计算得到的第三类信号特征。比如，将第(1)至(4)类特征输入到回归模型，计算出终端的电信信号采样信息对应的位置信息，然后根据各个位置信息前后时刻的位置信息计算终端的移动方向、速度、加速度等特 征对应的值，即为第三类信号特征对应的值。
需要说明的是，上述五种电信信号及其扩展特征仅为示例性说明，在实际应用中，可根据需要在上述五种电信信号及其扩展特征的基础上进行增删，本申请对此不做具体限定。
本申请中，在步骤206中构建出预测模型后，为保证后续定位的准确性，需再次获取另一历史时间段内的至少终端在多个第一历史时刻的电信信号采样信息和多个第二历史时刻的位置信息，作为测试数据，对构建出的预测模型进行测试。例如，根据2016年1月1日的历史数据(8:00:00-20:00:00这一时间段内的1000个终端在多个时刻的电信信号采样信息和位置信息)，构建出上海浦东新区的预测模型后，可获取2016年1月2日8:00:00-12:00:00这一时间段内的1000个终端在多个第一历史时刻的电信信号采样信息和多个第二历史时刻的位置信息作为测试数据对预测模型进行测试。
具体测试过程为：以一个终端在一个历史时刻的测试过程为例，可根据该终端在该历史时刻的电信信号采样信息，采用预测模型预测出位置信息，并将预测出的位置信息与该历史时刻对应的测试数据对中的位置信息进行比较，若差异在预设的差异范围内，则确定该终端在该历史时刻的测试结果成功，其中，预设的差异范围可由本领域技术人员根据经验设置，例如，可以为预测出的位置信息与该终端在该时刻获取到的位置信息之间距离小于等于3米。以同样的方式，对所有测试数据进行测试，若测试结果成功的比例大于预设的比例值，则说明该预测模型是有效的，后续可根据该预测模型对终端进行定位，否则，需对预测模型进行修正。其中，预设的比例值可由本领域技术人员根据经验设置，例如，可设置为90％。
图7为本申请中另一种构建预测模型的流程示意图。图7以更形象的方式示意出了本申请中构建预测模型的过程，其与上述步骤301至步骤306相对应，此处不再具体说明。
本申请中，预测模型是根据目标区域内的至少两个历史终端的多组数据对确定的，多组数据对中的每组数据对包括电信信号采样信息和位置信息， 由于电信信号采样信息和位置信息均为现有技术中可直接获取到的信息，而无需再额外采集，因此能够有效降低定位成本；且，由于预测模型是通过目标区域区域内的大量数据训练得到的，具有较强的容错和纠错能力，能够较为准确地反映出终端的电信信号采样信息和位置信息之间的关系，很好地避免了现有技术中由于电信信号强度受到多径衰减、非视距阻挡等因素的干扰以及终端连接的基站个数不足而导致定位不准确的问题，因此，根据本发明中的预测模型和终端的电信信号采样信息进行定位，能够有效提高终端定位的准确度，降低定位误差，具有较强的实用价值。
第二阶段，定位阶段
构建出有效的预测模型后，可进入定位阶段，也即投入使用阶段。
具体地，当需要对目标区域内的终端进行定位时，获取目标区域内的预测模型。其中，预测模型指终端的电信信号采样信息中的特定电信信号特征与位置信息之间的函数关系，若特定电信信号特征包括：电信信号特征x1、电信信号特征x2、电信信号特征x3、……、电信信号特征xk，则预测模型为电信信号特征x1、电信信号特征x2、电信信号特征x3、……、电信信号特征xk与位置信息之间的函数关系，预测模型的输入量为电信信号特征x1、电信信号特征x2、电信信号特征x3、……、电信信号特征xk，输出量为预测的位置信息。
采集第一终端在当前时刻的电信信号采样信息，具体包括电信信号特征及电信信号特征对应的值，其中，电信信号特征对应的值可以为具体的数值，也可以为不是以数值形式表示的信息。例如，电信信号特征为参考信号接收质量时，则可获取参考信号接收质量在当前时刻对应的数值，作为电信信号特征对应的值；若电信信号特征为连接基站ID或其它不是以数值的形式来表示的电信信号特征时，则可获取该类电信信号特征对应的信息，作为电信信号特征对应的值。如表9所示，为采集到的待定位终端在当前时刻的电信信号采样信息示例。
表9：待定位终端在当前时刻的电信信号采样信息示例
电信信号特征 对应的值
RSRP **
RSRQ **
SINR **
机械倾角 缺失
终端的发射功率 **
参考信号接收质量 **
信号与干扰加噪声比 **
…… ……
如上所述，获取到的预测模型的输入量包括k个电信信号特征，在定位过程中，输入的输入量越多越完整，则定位的精度越高越准确。考虑到采集的待定位终端在当前时刻的电信信号采样信息中可能存在缺失部分特征对应的值的情况，实际过程中，可由本领域技术人员根据具体的情形输入能够获取到的输入量，以完成待定位终端的定位，例如，可输入k个电信信号特征中的多个电信信号特征，预测出待定位终端的位置信息。例如，若k＝20，实际过程中，获取到20个电信信号特征中的15个电信信号特征对应的值，则将这15个电信信号特征对应的值输入预测模型，也能够较为准确地预测出待定位终端的位置信息；然而，若仅获取到20个电信信号特征中的5个电信信号特征对应的值，则将这5个电信信号特征对应的值输入预测模型，预测出的待定位终端的位置信息会存在较大误差。也就是说，为保证定位的准确性，获取到的电信信号特征对应的值应足够多，接近预测模型中的输入量的个数，或者与获取到的电信信号特征对应的值的个数与预测模型中的输入量的个数的比值大于等于预设比值；预设比值可由本领域技术人员根据经验设置，例如，可设置为70％。本申请中，特定电信信号特征包括第一类信号特征、第二类信号特征和第三类信号特征中的任一种或任意组合；第一类信号特征对应的值是从待定位终端在当前时刻的电信信号采样信息中提取得到的；第二类信号特 征对应的值是根据一个或一个以上的第一类信号特征对应的值进行运算得到的；第三类信号特征对应的值是通过待定位终端在当前时刻和当前时刻的相邻时刻的初始位置信息得到的；待定位终端在一个时刻的初始位置信息是通过函数关系对该时刻的一个或一个以上的第一类信号特征和/或第二类信号特征对应的值进行运算得到的。
为保证定位的精度和准确性，本申请优选，特定电信信号特征同时包括第一类信号特征、第二类信号特征和第三类信号特征。
假设，电信信号特征x1、电信信号特征x2、电信信号特征x3……、电信信号特征xn为第一类信号特征，电信信号特征xn、电信信号特征xn+1、电信信号特征xn+2……、电信信号特征xm为第二类信号特征，电信信号特征xm、电信信号特征xm+1、电信信号特征xm+2……、电信信号特征xk为第三类信号特征。
其中，全部或部分电信信号特征x1、电信信号特征x2、电信信号特征x3……、电信信号特征xn对应的值可根据采集到的待定位当前时刻的电信信号采样信息(即表9中的内容)得到。例如，RSRP、RSRQ、SINR对应的值可直接从表9中获取到。
全部或部分电信信号特征xn、电信信号特征xn+1、电信信号特征xn+2……、电信信号特征xm对应的值可根据已经得到的第一类信号特征对应的值得到。例如，电信信号特征xn+1为Range-based定位结果，其对应的值可根据采集到的信号强度值(第一类信号特征对应的值)，通过三角定位、共轭曲线等定位方法计算得到。
全部或部分的电信信号特征xm、电信信号特征xm+1、电信信号特征xm+2……、电信信号特征xk可根据待定位终端在当前时刻和当前时刻的相邻时刻的初始位置信息得到的；所述待定位终端在一个时刻的初始位置信息是通过所述函数关系对该时刻的一个或一个以上的第一类信号特征和/或第二类信号特征对应的值进行运算得到的。例如，电信信号特征xm为待定位终端的速度，则首先可将所有已经获取到的第一类信号特征和第二类信号特征对应 的值输入预测模型，进而得到待定位终端在当前时刻的初始位置信息(即进行粗略的定位)，采用同样的方法，得到待定位终端在当前时刻的相邻时刻(前几个时刻)的初始位置信息，根据待定位终端在当前时刻和当前时刻的相邻时刻的初始位置信息，可以计算出终端的速度。
通过上述过程，获取到第一类信号特征、第二类信号特征和第三类信号特征分别对应的值后，输入预测模型，最终预测出第一终端在当前时刻的位置信息。本申请中，由于第三类信号特征对应的值是通过粗略定位(即粗粒度定位)后得到的，将第三类信号特征对应的值再次作为预测模型的输入，能够实现更细粒度的定位，使得定位的精度更高。
上述内容为针对特定电信信号特征同时包括第一类信号特征、第二类信号特征和第三类信号特征的情形所做的说明，其它多种情形，例如，特定电信信号特征同时包括第一类信号特征和第二类信号特征、特定电信信号特征同时包括第一类信号特征和第三类信号特征，均可参照上述情形实施。
本申请中的定位方法，在构建预测模型阶段，是根据电信管道数据进行训练得到的，在定位阶段，只需获取到终端的电信信号采样信息，便可实现定位，因此，本申请中的各个过程仅需要电信管道数据，不需要终端进行其它的服务请求，降低了终端的处理负担，且本申请中的定位方法不需要终端开启GPS、AGPS(Assisted GPS，辅助全球卫星定位系统)等定位装置，即可实现定位。
由于电信终端的通信/数据活动都会留下电信管道数据，因此，电信管道数据所记录的时空信息能更准确的表述持有终端的人群行为，通过电信管道数据构建出的预测模型也能够更准确更切实际地反映出终端的电信信号采样信息和位置信息之间的关系，采用该预测模型能够实现更准确的定位，且具有广泛的应用前景，例如，在广告咨询行业中，通过定位可实现根据室外人流数据对广告进行定价和效果评估；在零售选址行业中，通过定位可实现根据人流数据进行零售店精确选址；在交通规划行业中，通过定位可实现根据人流数据科学交通规划；在旅游行业中，可实现根据人流变化调整运营策略； 在道路救援中，通过定位可实现根据位置定位提供道路提醒和道路救援；在公共安全行业中，通过定位可实现根据公共场所人流预测、监控和安全疏导；在搜索导航行业中，通过定位可实现利用室内数据提供室内导航。
针对上述方法流程，本申请还提供一种网络设备，该网络设备的具体内容可以参照上述方法实施。
图8示例性示出了本申请提供的一种网络设备的结构示意图，如图8所示，该网络设备800包括：
获取模块801，用于获取第一终端在当前时刻的电信信号采样信息；所述第一终端为位于目标区域内的任一终端，所述目标区域为预定的地理区域；
处理模块802，用于根据所述第一终端在当前时刻的电信信号采样信息以及所述目标区域的预测模型，预测得到所述第一终端在所述当前时刻的位置信息；所述预测模型是根据所述目标区域内的至少两个历史终端的多组数据对确定的；所述多组数据对中的每组数据对包括电信信号采样信息和位置信息，所述数据对中的电信信号采样信息和位置信息为同一历史终端在同一历史时刻的电信信号采样信息和位置信息。
可选地，所述处理模块802还用于：
从所述多组数据对的电信信号采样信息中，筛选出与所述多组数据对的位置信息中的位置特征的相关度大于或等于第一阈值的特定电信信号特征；
建立所述特定电信信号特征与所述位置特征之间的函数关系，得到所述预测模型。
可选地，所述处理模块802具体用于：
至少根据所述待定位终端在所述当前时刻的电信信号采样信息，得到所述特定电信信号特征对应的值；
根据所述预测模型和所述特定电信信号特征对应的值进行运算，得到所述待定位终端在当前时刻的位置信息。
可选地，所述特定电信信号特征包括第一类信号特征、第二类信号特征 和第三类信号特征中的任一种或任意组合；
所述第一类信号特征对应的值是从所述待定位终端在所述当前时刻的电信信号采样信息中提取得到的；
所述第二类信号特征对应的值是根据一个或一个以上的第一类信号特征对应的值进行运算得到的；
所述第三类信号特征对应的值是通过所述待定位终端在所述当前时刻和所述当前时刻的相邻时刻的初始位置信息得到的；所述待定位终端在所述当前时刻或所述当前时刻的相邻时刻的初始位置信息是通过所述函数关系对该时刻的一个或一个以上的第一类信号特征和/或第二类信号特征对应的值进行运算得到的。
可选地，所述处理模块802还用于：
根据如下方法得到所述至少两个历史终端中的任一历史终端的多组数据对：
针对第一历史终端，获取所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息；所述第一历史终端为所述至少两个历史终端中的任一历史终端；
根据所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对。
可选地，所述处理模块802具体用于：
根据第一预设规则，确定所述第一历史终端的多个第一历史时刻与多个第二历史时刻的时钟对应关系，所述第一预设规则为多个预设规则中的任一预设规则；
针对所述第一预设规则，计算所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和；其中，所述第一历史终端与所述第一历史终端所属的基站在所述多个第一历史时刻中的每个第一历史时刻的距离通过以下方法得到：所述网络设备根据所述时钟对应关系，确定所述第 一历史时刻对应的第二历史时刻，并根据所述第一历史时刻的电信信号采样信息中的基站的位置信息及所述第一历史时刻对应的第二历史时刻的所述第一历史终端的位置信息，确定所述基站与所述第一历史终端在第一历史时刻的距离；
根据目标时钟对应关系，确定所述第一历史终端的多组数据对；所述目标时钟对应关系为所述多个预设规则中，所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和最小的时钟对应关系。
可选地，所述第一历史终端在多个第一历史时刻的电信信号采样信息是按照第一频率获取到的；所述第一历史终端在多个第二历史时刻的位置信息是按照第二频率获取到的；所述第一频率小于所述第二频率；
所述处理模块802具体用于：
将所述第一历史终端在多个第一历史时刻的电信信号采样信息分别作为所述多组数据对中的电信信号采样信息，以及
根据所述目标时钟对应关系，得到所述多个第一历史时刻对应的多个第二历史时刻，并至少根据所述多个第一历史时刻对应的多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对中的位置信息。
可选地，所述第一历史终端在多个第二历史时刻的位置信息包括第一类位置信息和/或第二类位置信息；
所述第一类位置信息为对所述网络设备通过Gn口采集到的数据进行解析得到的位置信息；
所述第二类位置信息为所述网络设备根据所述第一类位置信息和所述目标区域的地图信息确定出所述第一历史终端的运动轨迹后，根据所述运动轨迹，在任意两个相邻的第一类位置信息中插值得到的位置信息。
本发明的上述实施例中，网络设备获取第一终端在当前时刻的电信信号采样信息，其中，第一终端为位于目标区域内的任一终端，目标区域为预定的地理区域；网络设备根据第一终端在当前时刻的电信信号采样信息以及目标区域的预测模型，预测得到第一终端在所述当前时刻的位置信息。本申请 中，预测模型是根据目标区域内的至少两个历史终端的多组数据对确定的，多组数据对中的每组数据对包括电信信号采样信息和位置信息，由于电信信号采样信息和位置信息均为现有技术中可直接获取到的信息，而无需再额外采集，因此能够有效降低定位成本；且，由于预测模型是通过目标区域区域内的大量数据训练得到的，具有较强的容错和纠错能力，能够较为准确地反映出终端的电信信号采样信息和位置信息之间的关系，很好地避免了现有技术中由于电信信号强度受到多径衰减、非视距阻挡等因素的干扰以及终端连接的基站个数不足而导致定位不准确的问题，因此，根据本发明中的预测模型和终端的电信信号采样信息进行定位，能够有效提高终端定位的准确度，降低定位误差，具有较强的实用价值。
基于相同构思，图9示例性示出了本申请提供的另一种网络设备的结构示意图。如图9所示，该网络设备900包括：存储器901，处理器902；
其中，存储器901，用于存放程序。具体地，程序可以包括程序代码，程序代码包括计算机操作指令。存储器901可能为随机存取存储器(random access memory，简称RAM)，也可能为非易失性存储器(non-volatile memory)，例如至少一个磁盘存储器。图中仅示出了一个存储器，当然，存储器也可以根据需要，设置为多个。存储器901也可以是处理器902中的存储器。
存储器901存储了如下的元素，可执行模块或者数据结构，或者它们的子集，或者它们的扩展集：
操作指令：包括各种操作指令，用于实现各种操作。
操作系统：包括各种系统程序，用于实现各种基础业务以及处理基于硬件的任务。
存储器901中还存储有获取到的第一终端在当前时刻的电信信号采样信息和目标区域的预测模型；所述第一终端为位于目标区域内的任一终端，所述目标区域为预定的地理区域；所述预测模型是根据所述目标区域内的至少两个历史终端的多组数据对确定的；所述多组数据对中的每组数据对包括电 信信号采样信息和位置信息，所述数据对中的电信信号采样信息和位置信息为同一历史终端在同一历史时刻的电信信号采样信息和位置信息。
处理器902控制网络设备900的操作，处理器902还可以称为CPU(Central Processing Unit，中央处理单元)。具体的应用中，网络设备900的各个组件通过总线系统耦合在一起，其中总线系统除包括数据总线之外，还可以包括电源总线、控制总线和状态信号总线等。但是为了清楚说明起见，在图中将各种总线都标为总线系统。为便于表示，图9中仅是示意性画出。
上述本申请实施例揭示的方法可以应用于处理器902中，或者由处理器902实现。处理器902可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法的各步骤可以通过处理器902中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器902可以是通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器901，处理器902读取存储器901中的信息，结合其硬件执行以下步骤：
根据所述第一终端在当前时刻的电信信号采样信息以及所述目标区域的预测模型，预测得到所述第一终端在所述当前时刻的位置信息。
可选地，所述处理器902还用于：
从所述多组数据对的电信信号采样信息中，筛选出与所述多组数据对的位置信息中的位置特征的相关度大于或等于第一阈值的特定电信信号特征；
建立所述特定电信信号特征与所述位置特征之间的函数关系，得到所述预测模型。
可选地，所述处理器902具体用于：
至少根据所述待定位终端在所述当前时刻的电信信号采样信息，得到所述特定电信信号特征对应的值；
根据所述预测模型和所述特定电信信号特征对应的值进行运算，得到所述待定位终端在当前时刻的位置信息。
可选地，所述特定电信信号特征包括第一类信号特征、第二类信号特征和第三类信号特征中的任一种或任意组合；
所述第一类信号特征对应的值是从所述待定位终端在所述当前时刻的电信信号采样信息中提取得到的；
所述第二类信号特征对应的值是根据一个或一个以上的第一类信号特征对应的值进行运算得到的；
所述第三类信号特征对应的值是通过所述待定位终端在所述当前时刻和所述当前时刻的相邻时刻的初始位置信息得到的；所述待定位终端在所述当前时刻或所述当前时刻的相邻时刻的初始位置信息是通过所述函数关系对该时刻的一个或一个以上的第一类信号特征和/或第二类信号特征对应的值进行运算得到的。
可选地，所述处理器902还用于：
根据如下方法得到所述至少两个历史终端中的任一历史终端的多组数据对：
针对第一历史终端，获取所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息；所述第一历史终端为所述至少两个历史终端中的任一历史终端；
根据所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对。
可选地，所述处理器902具体用于：
根据第一预设规则，确定所述第一历史终端的多个第一历史时刻与多个 第二历史时刻的时钟对应关系，所述第一预设规则为多个预设规则中的任一预设规则；
针对所述第一预设规则，计算所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和；其中，所述第一历史终端与所述第一历史终端所属的基站在所述多个第一历史时刻中的每个第一历史时刻的距离通过以下方法得到：所述网络设备根据所述时钟对应关系，确定所述第一历史时刻对应的第二历史时刻，并根据所述第一历史时刻的电信信号采样信息中的基站的位置信息及所述第一历史时刻对应的第二历史时刻的所述第一历史终端的位置信息，确定所述基站与所述第一历史终端在第一历史时刻的距离；
根据目标时钟对应关系，确定所述第一历史终端的多组数据对；所述目标时钟对应关系为所述多个预设规则中，所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和最小的时钟对应关系。
可选地，所述第一历史终端在多个第一历史时刻的电信信号采样信息是按照第一频率获取到的；所述第一历史终端在多个第二历史时刻的位置信息是按照第二频率获取到的；所述第一频率小于所述第二频率；
所述处理器902具体用于：
将所述第一历史终端在多个第一历史时刻的电信信号采样信息分别作为所述多组数据对中的电信信号采样信息，以及
根据所述目标时钟对应关系，得到所述多个第一历史时刻对应的多个第二历史时刻，并至少根据所述多个第一历史时刻对应的多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对中的位置信息。
可选地，所述第一历史终端在多个第二历史时刻的位置信息包括第一类位置信息和/或第二类位置信息；
所述第一类位置信息为对所述网络设备通过Gn口采集到的数据进行解析得到的位置信息；
所述第二类位置信息为所述网络设备根据所述第一类位置信息和所述目 标区域的地图信息确定出所述第一历史终端的运动轨迹后，根据所述运动轨迹，在任意两个相邻的第一类位置信息中插值得到的位置信息。
从上述内容可以看出：本发明的上述实施例中，网络设备获取第一终端在当前时刻的电信信号采样信息，其中，第一终端为位于目标区域内的任一终端，目标区域为预定的地理区域；网络设备根据第一终端在当前时刻的电信信号采样信息以及目标区域的预测模型，预测得到第一终端在所述当前时刻的位置信息。本申请中，预测模型是根据目标区域内的至少两个历史终端的多组数据对确定的，多组数据对中的每组数据对包括电信信号采样信息和位置信息，由于电信信号采样信息和位置信息均为现有技术中可直接获取到的信息，而无需再额外采集，因此能够有效降低定位成本；且，由于预测模型是通过目标区域区域内的大量数据训练得到的，具有较强的容错和纠错能力，能够较为准确地反映出终端的电信信号采样信息和位置信息之间的关系，很好地避免了现有技术中由于电信信号强度受到多径衰减、非视距阻挡等因素的干扰以及终端连接的基站个数不足而导致定位不准确的问题，因此，根据本发明中的预测模型和终端的电信信号采样信息进行定位，能够有效提高终端定位的准确度，降低定位误差，具有较强的实用价值。
本领域内的技术人员应明白，本发明的实施例可提供为方法、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本申请的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图 一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
尽管已描述了本发明的优选实施例，但本领域内的技术人员一旦得知了基本创造性概念，则可对这些实施例作出另外的变更和修改。所以，所附权利要求意欲解释为包括优选实施例以及落入本发明范围的所有变更和修改。
显然，本领域的技术人员可以对本发明进行各种改动和变型而不脱离本发明的精神和范围。这样，倘若本发明的这些修改和变型属于本发明权利要求及其等同技术的范围之内，则本发明也意图包含这些改动和变型在内。

Claims (24)

  1. 一种终端定位方法，其特征在于，该方法包括：
    网络设备获取第一终端在当前时刻的电信信号采样信息；所述第一终端为位于目标区域内的任一终端，所述目标区域为预定的地理区域；
    所述网络设备根据所述第一终端在当前时刻的电信信号采样信息以及所述目标区域的预测模型，预测得到所述第一终端在所述当前时刻的位置信息；所述预测模型是根据所述目标区域内的至少两个历史终端的多组数据对确定的；所述多组数据对中的每组数据对包括电信信号采样信息和位置信息，所述数据对中的电信信号采样信息和位置信息为同一历史终端在同一历史时刻的电信信号采样信息和位置信息。
  2. 如权利要求1所述的方法，其特征在于，所述预测模型由所述网络设备通过以下方式确定：
    所述网络设备从所述多组数据对的电信信号采样信息中，筛选出与所述多组数据对的位置信息中的位置特征的相关度大于或等于第一阈值的特定电信信号特征；
    所述网络设备建立所述特定电信信号特征与所述位置特征之间的函数关系，得到所述预测模型。
  3. 如权利要求2所述的方法，其特征在于，所述网络设备根据所述第一终端在当前时刻的电信信号采样信息以及所述目标区域的预测模型，预测得到所述第一终端在所述当前时刻的位置信息，包括：
    所述网络设备至少根据所述待定位终端在所述当前时刻的电信信号采样信息，得到所述特定电信信号特征对应的值；
    所述网络设备根据所述预测模型和所述特定电信信号特征对应的值进行运算，得到所述第一终端在当前时刻的位置信息。
  4. 如权利要求3所述的方法，其特征在于，所述特定电信信号特征包括第一类信号特征、第二类信号特征和第三类信号特征中的任一种或任意组合；
    所述第一类信号特征对应的值是从所述待定位终端在所述当前时刻的电信信号采样信息中提取得到的；
    所述第二类信号特征对应的值是根据一个或一个以上的第一类信号特征对应的值进行运算得到的；
    所述第三类信号特征对应的值是通过所述待定位终端在所述当前时刻和所述当前时刻的相邻时刻的初始位置信息得到的；所述待定位终端在所述当前时刻或所述当前时刻的相邻时刻的初始位置信息是通过所述函数关系对该时刻的一个或一个以上的第一类信号特征和/或第二类信号特征对应的值进行运算得到的。
  5. 如权利要求1至4中任一项所述的方法，其特征在于，所述至少两个历史终端中的任一历史终端的多组数据对根据如下方法得到：
    针对第一历史终端，所述网络设备获取所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息；所述第一历史终端为所述至少两个历史终端中的任一历史终端；
    所述网络设备根据所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对。
  6. 如权利要求5所述的方法，其特征在于，所述网络设备根据所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对，包括：
    所述网络设备根据第一预设规则，确定所述第一历史终端的多个第一历史时刻与多个第二历史时刻的时钟对应关系，所述第一预设规则为多个预设规则中的任一预设规则；
    所述网络设备针对所述第一预设规则，计算所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和；其中，所述第一历史终端与所述第一历史终端所属的基站在所述多个第一历史时刻中的每个第一历史时刻的距离通过以下方法得到：所述网络设备根据所述时钟对应关系， 确定所述第一历史时刻对应的第二历史时刻，并根据所述第一历史时刻的电信信号采样信息中的基站的位置信息及所述第一历史时刻对应的第二历史时刻的所述第一历史终端的位置信息，确定所述基站与所述第一历史终端在第一历史时刻的距离；
    所述网络设备根据目标时钟对应关系，确定所述第一历史终端的多组数据对；所述目标时钟对应关系为所述多个预设规则中，所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和最小的时钟对应关系。
  7. 如权利要求6所述的方法，其特征在于，所述第一历史终端在多个第一历史时刻的电信信号采样信息是按照第一频率获取到的；所述第一历史终端在多个第二历史时刻的位置信息是按照第二频率获取到的；所述第一频率小于所述第二频率；
    所述网络设备根据目标时钟对应关系，确定所述第一历史终端的多组数据对，包括：
    所述网络设备将所述第一历史终端在多个第一历史时刻的电信信号采样信息分别作为所述多组数据对中的电信信号采样信息，以及
    所述网络设备根据所述目标时钟对应关系，得到所述多个第一历史时刻对应的多个第二历史时刻，并至少根据所述多个第一历史时刻对应的多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对中的位置信息。
  8. 如权利要求7所述的方法，其特征在于，所述第一历史终端在多个第二历史时刻的位置信息包括第一类位置信息和/或第二类位置信息；
    所述第一类位置信息为对所述网络设备通过Gn口采集到的数据进行解析得到的位置信息；
    所述第二类位置信息为所述网络设备根据所述第一类位置信息和所述目标区域的地图信息确定出所述第一历史终端的运动轨迹后，根据所述运动轨迹，在任意两个相邻的第一类位置信息中插值得到的位置信息。
  9. 一种网络设备，其特征在于，该网络设备包括：
    获取模块，用于获取第一终端在当前时刻的电信信号采样信息；所述第一终端为位于目标区域内的任一终端，所述目标区域为预定的地理区域；
    处理模块，用于根据所述第一终端在当前时刻的电信信号采样信息以及所述目标区域的预测模型，预测得到所述第一终端在所述当前时刻的位置信息；所述预测模型是根据所述目标区域内的至少两个历史终端的多组数据对确定的；所述多组数据对中的每组数据对包括电信信号采样信息和位置信息，所述数据对中的电信信号采样信息和位置信息为同一历史终端在同一历史时刻的电信信号采样信息和位置信息。
  10. 如权利要求9所述的网络设备，其特征在于，所述处理模块还用于：
    从所述多组数据对的电信信号采样信息中，筛选出与所述多组数据对的位置信息中的位置特征的相关度大于或等于第一阈值的特定电信信号特征；
    建立所述特定电信信号特征与所述位置特征之间的函数关系，得到所述预测模型。
  11. 如权利要求10所述的网络设备，其特征在于，所述处理模块具体用于：
    至少根据所述待定位终端在所述当前时刻的电信信号采样信息，得到所述特定电信信号特征对应的值；
    根据所述预测模型和所述特定电信信号特征对应的值进行运算，得到所述待定位终端在当前时刻的位置信息。
  12. 如权利要求11所述的网络设备，其特征在于，所述特定电信信号特征包括第一类信号特征、第二类信号特征和第三类信号特征中的任一种或任意组合；
    所述第一类信号特征对应的值是从所述待定位终端在所述当前时刻的电信信号采样信息中提取得到的；
    所述第二类信号特征对应的值是根据一个或一个以上的第一类信号特征对应的值进行运算得到的；
    所述第三类信号特征对应的值是通过所述待定位终端在所述当前时刻和 所述当前时刻的相邻时刻的初始位置信息得到的；所述待定位终端在所述当前时刻或所述当前时刻的相邻时刻的初始位置信息是通过所述函数关系对该时刻的一个或一个以上的第一类信号特征和/或第二类信号特征对应的值进行运算得到的。
  13. 如权利要求9至12中任一项所述的网络设备，其特征在于，所述处理模块还用于：
    根据如下方法得到所述至少两个历史终端中的任一历史终端的多组数据对：
    针对第一历史终端，获取所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息；所述第一历史终端为所述至少两个历史终端中的任一历史终端；
    根据所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对。
  14. 如权利要求13所述的网络设备，其特征在于，所述处理模块具体用于：
    根据第一预设规则，确定所述第一历史终端的多个第一历史时刻与多个第二历史时刻的时钟对应关系，所述第一预设规则为多个预设规则中的任一预设规则；
    针对所述第一预设规则，计算所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和；其中，所述第一历史终端与所述第一历史终端所属的基站在所述多个第一历史时刻中的每个第一历史时刻的距离通过以下方法得到：所述网络设备根据所述时钟对应关系，确定所述第一历史时刻对应的第二历史时刻，并根据所述第一历史时刻的电信信号采样信息中的基站的位置信息及所述第一历史时刻对应的第二历史时刻的所述第一历史终端的位置信息，确定所述基站与所述第一历史终端在第一历史时刻的距离；
    根据目标时钟对应关系，确定所述第一历史终端的多组数据对；所述目标时钟对应关系为所述多个预设规则中，所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和最小的时钟对应关系。
  15. 如权利要求14所述的网络设备，其特征在于，所述第一历史终端在多个第一历史时刻的电信信号采样信息是按照第一频率获取到的；所述第一历史终端在多个第二历史时刻的位置信息是按照第二频率获取到的；所述第一频率小于所述第二频率；
    所述处理模块具体用于：
    将所述第一历史终端在多个第一历史时刻的电信信号采样信息分别作为所述多组数据对中的电信信号采样信息，以及
    根据所述目标时钟对应关系，得到所述多个第一历史时刻对应的多个第二历史时刻，并至少根据所述多个第一历史时刻对应的多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对中的位置信息。
  16. 如权利要求15所述的网络设备，其特征在于，所述第一历史终端在多个第二历史时刻的位置信息包括第一类位置信息和/或第二类位置信息；
    所述第一类位置信息为对所述网络设备通过Gn口采集到的数据进行解析得到的位置信息；
    所述第二类位置信息为所述网络设备根据所述第一类位置信息和所述目标区域的地图信息确定出所述第一历史终端的运动轨迹后，根据所述运动轨迹，在任意两个相邻的第一类位置信息中插值得到的位置信息。
  17. 一种网络设备，其特征在于，该网络设备包括：
    存储器，用于存储获取到的第一终端在当前时刻的电信信号采样信息和目标区域的预测模型；所述第一终端为位于目标区域内的任一终端，所述目标区域为预定的地理区域；所述预测模型是根据所述目标区域内的至少两个历史终端的多组数据对确定的；所述多组数据对中的每组数据对包括电信信号采样信息和位置信息，所述数据对中的电信信号采样信息和位置信息为同一历史终端在同一历史时刻的电信信号采样信息和位置信息；
    处理器，用于根据所述第一终端在当前时刻的电信信号采样信息以及所述目标区域的预测模型，预测得到所述第一终端在所述当前时刻的位置信息。
  18. 如权利要求17所述的网络设备，其特征在于，所述处理器还用于：
    从所述多组数据对的电信信号采样信息中，筛选出与所述多组数据对的位置信息中的位置特征的相关度大于或等于第一阈值的特定电信信号特征；
    建立所述特定电信信号特征与所述位置特征之间的函数关系，得到所述预测模型。
  19. 如权利要求18所述的网络设备，其特征在于，所述处理器具体用于：
    至少根据所述待定位终端在所述当前时刻的电信信号采样信息，得到所述特定电信信号特征对应的值；
    根据所述预测模型和所述特定电信信号特征对应的值进行运算，得到所述待定位终端在当前时刻的位置信息。
  20. 如权利要求19所述的网络设备，其特征在于，所述特定电信信号特征包括第一类信号特征、第二类信号特征和第三类信号特征中的任一种或任意组合；
    所述第一类信号特征对应的值是从所述待定位终端在所述当前时刻的电信信号采样信息中提取得到的；
    所述第二类信号特征对应的值是根据一个或一个以上的第一类信号特征对应的值进行运算得到的；
    所述第三类信号特征对应的值是通过所述待定位终端在所述当前时刻和所述当前时刻的相邻时刻的初始位置信息得到的；所述待定位终端在所述当前时刻或所述当前时刻的相邻时刻的初始位置信息是通过所述函数关系对该时刻的一个或一个以上的第一类信号特征和/或第二类信号特征对应的值进行运算得到的。
  21. 如权利要求17至20中任一项所述的网络设备，其特征在于，所述处理器还用于：
    根据如下方法得到所述至少两个历史终端中的任一历史终端的多组数据 对：
    针对第一历史终端，获取所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息；所述第一历史终端为所述至少两个历史终端中的任一历史终端；
    根据所述第一历史终端在多个第一历史时刻的电信信号采样信息及所述第一历史终端在多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对。
  22. 如权利要求21所述的网络设备，其特征在于，所述处理器具体用于：
    根据第一预设规则，确定所述第一历史终端的多个第一历史时刻与多个第二历史时刻的时钟对应关系，所述第一预设规则为多个预设规则中的任一预设规则；
    针对所述第一预设规则，计算所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和；其中，所述第一历史终端与所述第一历史终端所属的基站在所述多个第一历史时刻中的每个第一历史时刻的距离通过以下方法得到：所述网络设备根据所述时钟对应关系，确定所述第一历史时刻对应的第二历史时刻，并根据所述第一历史时刻的电信信号采样信息中的基站的位置信息及所述第一历史时刻对应的第二历史时刻的所述第一历史终端的位置信息，确定所述基站与所述第一历史终端在第一历史时刻的距离；
    根据目标时钟对应关系，确定所述第一历史终端的多组数据对；所述目标时钟对应关系为所述多个预设规则中，所述第一历史终端与所述第一历史终端所属的基站在多个第一历史时刻的距离之和最小的时钟对应关系。
  23. 如权利要求22所述的网络设备，其特征在于，所述第一历史终端在多个第一历史时刻的电信信号采样信息是按照第一频率获取到的；所述第一历史终端在多个第二历史时刻的位置信息是按照第二频率获取到的；所述第一频率小于所述第二频率；
    所述处理器具体用于：
    将所述第一历史终端在多个第一历史时刻的电信信号采样信息分别作为所述多组数据对中的电信信号采样信息，以及
    根据所述目标时钟对应关系，得到所述多个第一历史时刻对应的多个第二历史时刻，并至少根据所述多个第一历史时刻对应的多个第二历史时刻的位置信息，得到所述第一历史终端的多组数据对中的位置信息。
  24. 如权利要求23所述的网络设备，其特征在于，所述第一历史终端在多个第二历史时刻的位置信息包括第一类位置信息和/或第二类位置信息；
    所述第一类位置信息为对所述网络设备通过Gn口采集到的数据进行解析得到的位置信息；
    所述第二类位置信息为所述网络设备根据所述第一类位置信息和所述目标区域的地图信息确定出所述第一历史终端的运动轨迹后，根据所述运动轨迹，在任意两个相邻的第一类位置信息中插值得到的位置信息。
PCT/CN2016/102043 2016-04-29 2016-10-13 一种终端定位方法及网络设备 WO2017185664A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP16900172.4A EP3419353B1 (en) 2016-04-29 2016-10-13 Method for positioning terminal, and network device
US16/136,827 US10542519B2 (en) 2016-04-29 2018-09-20 Terminal positioning method and network device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610289359.4 2016-04-29
CN201610289359.4A CN107333232B (zh) 2016-04-29 2016-04-29 一种终端定位方法及网络设备

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/136,827 Continuation US10542519B2 (en) 2016-04-29 2018-09-20 Terminal positioning method and network device

Publications (1)

Publication Number Publication Date
WO2017185664A1 true WO2017185664A1 (zh) 2017-11-02

Family

ID=60161835

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/102043 WO2017185664A1 (zh) 2016-04-29 2016-10-13 一种终端定位方法及网络设备

Country Status (4)

Country Link
US (1) US10542519B2 (zh)
EP (1) EP3419353B1 (zh)
CN (2) CN107333232B (zh)
WO (1) WO2017185664A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110907977A (zh) * 2018-09-17 2020-03-24 中兴通讯股份有限公司 一种信息处理方法、装置和计算机存储介质
CN111277947A (zh) * 2018-12-04 2020-06-12 中兴通讯股份有限公司 小区经纬度预测方法、装置、服务器、基站及存储介质
CN111585672A (zh) * 2020-04-28 2020-08-25 深圳中科国威信息系统技术有限公司 认知无线电的工作信道确定方法、介质、终端和装置
US20210325523A1 (en) * 2018-08-14 2021-10-21 Robert Bosch Gmbh Method and apparatus for detecting signal propagation type
WO2023236979A1 (zh) * 2022-06-10 2023-12-14 维沃移动通信有限公司 定位模型的选择方法、终端及网络侧设备

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109951814B (zh) * 2017-12-20 2021-11-19 中国电信股份有限公司 定位方法、装置以及计算机可读存储介质
CN108495364B (zh) * 2018-02-09 2020-07-07 北京天元创新科技有限公司 移动终端的定位方法及装置
CN108513251B (zh) * 2018-02-13 2020-08-04 北京天元创新科技有限公司 一种基于mr数据的定位方法及系统
CN108520028B (zh) * 2018-03-27 2021-05-07 北京邮电大学 基于dpi数据的用户地理位置特征提取方法及系统
CN109660469B (zh) * 2018-10-23 2022-09-02 惠州Tcl移动通信有限公司 同步变化网络信号的方法、终端及具有存储功能的装置
CN109672466B (zh) * 2018-12-12 2022-02-18 广州极飞科技股份有限公司 信号数据处理方法、装置、计算机设备及存储介质
CN110290582B (zh) * 2019-05-22 2020-10-30 浙江工业大学 一种基于seq2seq框架的基站标号轨迹预测方法
CN111132029B (zh) * 2019-10-16 2022-03-01 张苏 基于地形约束的定位方法及装置
CN110839201B (zh) * 2019-10-28 2021-01-15 宜通世纪科技股份有限公司 管道数据处理方法、发送装置、接收装置和存储介质
CN113055901B (zh) * 2019-12-27 2022-09-16 中国电信股份有限公司 一种终端定位的方法和装置
CN113449207B (zh) * 2020-03-24 2024-09-06 花瓣云科技有限公司 电子设备定位的方法、装置、服务器、系统以及存储介质
CN111565062B (zh) * 2020-04-15 2023-03-17 中国联合网络通信集团有限公司 一种波束切换方法和装置
CN113630712B (zh) * 2020-04-22 2023-04-28 中国移动通信集团四川有限公司 一种定位方法、装置及设备
CN112203284B (zh) * 2020-09-07 2023-10-17 北京遥感设备研究所 终端位置自适应的多小区联合资源分配方法、装置和系统
CN112203285B (zh) * 2020-09-07 2023-10-17 北京遥感设备研究所 一种多小区联合协同传输控制方法、装置和系统
CN112351384B (zh) * 2020-09-10 2022-09-27 小灵狗出行科技有限公司 一种车辆定位数据修正方法、装置及设备
CN112738718B (zh) * 2021-03-29 2021-07-06 江苏云松智汇机电科技有限公司 一种基于lsa的时空大数据轨迹匹配方法
CN115460537A (zh) * 2021-06-08 2022-12-09 中移(上海)信息通信科技有限公司 基站定位方法、装置及网络设备
WO2024174176A1 (zh) * 2023-02-23 2024-08-29 华为技术有限公司 一种通信方法及装置
CN116227929B (zh) * 2023-03-07 2024-03-19 广州爱浦路网络技术有限公司 通信数据的分析方法、装置、设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060128401A1 (en) * 2004-12-09 2006-06-15 Evolium S.A.S. Information providing system based on action history by push type service
CN101986757A (zh) * 2010-11-05 2011-03-16 中兴通讯股份有限公司 一种移动终端的定位方法及装置
CN102111871A (zh) * 2009-12-23 2011-06-29 中国移动通信集团公司 基于小区标识定位技术的终端定位方法及装置
CN104469676A (zh) * 2014-11-21 2015-03-25 北京拓明科技有限公司 一种移动终端的定位方法及系统

Family Cites Families (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5043736B1 (en) 1990-07-27 1994-09-06 Cae Link Corp Cellular position location system
US5293645A (en) 1991-10-04 1994-03-08 Sharp Microelectronics Technology, Inc. Apparatus and method for locating mobile and portable radio terminals in a radio network
US5913170A (en) 1994-11-16 1999-06-15 Highwaymaster Communications, Inc. Locating system and method using a mobile communications network
AU4979096A (en) 1995-02-24 1996-09-11 Global Locating Systems, Inc. Locating device and system using cellular technologies
US5895436A (en) 1996-04-26 1999-04-20 Savoie; Paul-Andreroland Vehicle tracking system using cellular network
DE60138493D1 (de) 2001-12-27 2009-06-04 Nokia Corp System, verfahren und übergangseinrichtung zur lokalisierung eines mobilen endgerätes
US7151446B2 (en) 2003-08-01 2006-12-19 Spectrum Tracking Systems, Inc. System for tracking and locating an object using a cellular network
FR2865605B1 (fr) 2004-01-26 2006-04-28 Cit Alcatel Procede de localisation assistee de terminaux mobiles de communication d'un reseau cellulaire, par utilisation d'un canal de transport ussd
US8421675B2 (en) 2006-12-07 2013-04-16 Digimarc Corporation Systems and methods for locating a mobile device within a cellular system
US8554247B2 (en) * 2008-11-13 2013-10-08 Glopos Fzc Method and system for refining accuracy of location positioning
IL200158A (en) 2009-07-30 2014-12-31 Verint Systems Ltd System and methods for locating communication terminals on cellular networks
WO2011058499A1 (en) 2009-11-12 2011-05-19 Sriram Kannan Methods for profiling cellular network towers and locating mobile communication device, and tools therefrom
CN102111872B (zh) * 2009-12-23 2013-11-20 中国移动通信集团公司 基于指纹定位技术的定位方法及装置
WO2011097414A1 (en) 2010-02-03 2011-08-11 Nextivity, Inc. Location finding in cellular network with repeater
EP2485546B1 (en) 2011-02-03 2017-03-22 Realcell Limited System and method for locating a cellular communication device
US8971924B2 (en) 2011-05-23 2015-03-03 Apple Inc. Identifying and locating users on a mobile network
US9232378B2 (en) 2012-07-03 2016-01-05 Qualcomm Incorporated Locating a victim via a first responder's device
CN102901975A (zh) 2012-10-18 2013-01-30 中兴通讯股份有限公司 一种移动终端和获取移动终端位置信息的方法
CN115130021A (zh) * 2013-03-15 2022-09-30 美国结构数据有限公司 用于提供位置信息的装置、系统和方法
CN104080163A (zh) * 2013-03-28 2014-10-01 北京百度网讯科技有限公司 一种用于确定无线接入设备的接入位置信息的方法和设备
US9374799B2 (en) 2013-12-23 2016-06-21 Cellco Partnership Mobile device locating using long term evolution signals
CN103906233A (zh) * 2014-03-31 2014-07-02 黄卿 一种定位数据采集、处理方法及装置
US10440503B2 (en) * 2014-07-16 2019-10-08 TUPL, Inc. Machine learning-based geolocation and hotspot area identification
JP6534808B2 (ja) * 2014-11-28 2019-06-26 株式会社デンソーテン レーダ装置、および、信号処理方法
CN104968045B (zh) * 2015-05-22 2018-11-09 清华大学 基于指纹的室内定位方法及定位装置
CN105282758A (zh) * 2015-09-06 2016-01-27 华南理工大学 WiFi室内定位系统指纹数据库自适应动态构建方法
CN105338489B (zh) * 2015-11-17 2018-08-14 中国电子科技集团公司第五十四研究所 一种用于室内定位的智能终端及蓝牙室内定位系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060128401A1 (en) * 2004-12-09 2006-06-15 Evolium S.A.S. Information providing system based on action history by push type service
CN102111871A (zh) * 2009-12-23 2011-06-29 中国移动通信集团公司 基于小区标识定位技术的终端定位方法及装置
CN101986757A (zh) * 2010-11-05 2011-03-16 中兴通讯股份有限公司 一种移动终端的定位方法及装置
CN104469676A (zh) * 2014-11-21 2015-03-25 北京拓明科技有限公司 一种移动终端的定位方法及系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3419353A4 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210325523A1 (en) * 2018-08-14 2021-10-21 Robert Bosch Gmbh Method and apparatus for detecting signal propagation type
US11791911B2 (en) * 2018-08-14 2023-10-17 Robert Bosch Gmbh Method and apparatus for detecting signal propagation type
CN110907977A (zh) * 2018-09-17 2020-03-24 中兴通讯股份有限公司 一种信息处理方法、装置和计算机存储介质
CN110907977B (zh) * 2018-09-17 2024-05-24 深圳市中兴通讯技术服务有限责任公司 一种信息处理方法、装置和计算机存储介质
CN111277947A (zh) * 2018-12-04 2020-06-12 中兴通讯股份有限公司 小区经纬度预测方法、装置、服务器、基站及存储介质
CN111277947B (zh) * 2018-12-04 2023-05-02 中兴通讯股份有限公司 小区经纬度预测方法、装置、服务器、基站及存储介质
CN111585672A (zh) * 2020-04-28 2020-08-25 深圳中科国威信息系统技术有限公司 认知无线电的工作信道确定方法、介质、终端和装置
WO2023236979A1 (zh) * 2022-06-10 2023-12-14 维沃移动通信有限公司 定位模型的选择方法、终端及网络侧设备

Also Published As

Publication number Publication date
US20190021068A1 (en) 2019-01-17
CN107466103B (zh) 2020-06-02
EP3419353A4 (en) 2019-07-03
EP3419353A1 (en) 2018-12-26
CN107333232A (zh) 2017-11-07
CN107333232B (zh) 2020-02-21
EP3419353B1 (en) 2024-09-25
CN107466103A (zh) 2017-12-12
US10542519B2 (en) 2020-01-21

Similar Documents

Publication Publication Date Title
WO2017185664A1 (zh) 一种终端定位方法及网络设备
CN103068035B (zh) 一种无线网络定位方法、装置及系统
US9867067B2 (en) Measurement module
CN110166943B (zh) 终端位置信息的处理方法
US8478280B1 (en) Minimum coverage area of wireless base station determination
US9749805B2 (en) Methods, wireless device and network node for managing positioning method based on prediction
US20150324704A1 (en) Method and apparatus for participatory sensing data collection
WO2020207096A1 (zh) 一种5g场景下的定位方法、定位平台及用户终端
CN103822638B (zh) 用户位置信息的处理方法和装置
CN104821956B (zh) 基于电子设备或应用的定位方法和装置
WO2014107526A1 (en) Methods and systems for dynamic detection of consumer venue walk-ins
CN108293193A (zh) 一种用于完成路测数据的高效计算方法
US9942900B1 (en) System and method for improved band-channel scanning and network switching
US11304172B2 (en) Site estimation based on crowd sourced data
US20160295373A1 (en) Mobility determination using likelihood estimation
CN108541011B (zh) 无线网络信号覆盖区域的强度分析方法和装置
CN105338487B (zh) 用于多遍地理定位的技术
CN103900585A (zh) 兴趣点规划方法和装置
EP4086653A1 (en) Improving device position accuracy with network-based crowdsourcing
JP2016048529A (ja) 携帯端末を所持したユーザの滞在判定が可能な装置、プログラム及び方法
WO2015084154A1 (en) A system and method for locating a mobile device
CN116266899A (zh) 跟踪区边界信息的处理方法、装置、电子设备和可读介质
CN112911506A (zh) 网络切换方法、装置、计算机设备和可读存储介质
KR101161983B1 (ko) 이동통신 단말기의 위치 정보를 산출하는 위치 관리 서버 및 그 산출 방법
CN114363806B (zh) 一种高精度5g三角定位方法

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 2016900172

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2016900172

Country of ref document: EP

Effective date: 20180918

NENP Non-entry into the national phase

Ref country code: DE

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

Ref document number: 16900172

Country of ref document: EP

Kind code of ref document: A1