WO2017211153A1 - 一种基于指纹进行定位的方法、装置及计算机存储介质 - Google Patents

一种基于指纹进行定位的方法、装置及计算机存储介质 Download PDF

Info

Publication number
WO2017211153A1
WO2017211153A1 PCT/CN2017/083462 CN2017083462W WO2017211153A1 WO 2017211153 A1 WO2017211153 A1 WO 2017211153A1 CN 2017083462 W CN2017083462 W CN 2017083462W WO 2017211153 A1 WO2017211153 A1 WO 2017211153A1
Authority
WO
WIPO (PCT)
Prior art keywords
signal
positioning
fingerprint
wireless signal
index table
Prior art date
Application number
PCT/CN2017/083462
Other languages
English (en)
French (fr)
Inventor
曾刚
王东
谭余
熊壮
Original Assignee
中兴通讯股份有限公司
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 中兴通讯股份有限公司 filed Critical 中兴通讯股份有限公司
Publication of WO2017211153A1 publication Critical patent/WO2017211153A1/zh

Links

Images

Classifications

    • 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
    • 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
    • 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

Definitions

  • the present invention relates to the field of position location technology, and in particular, to a method and apparatus for positioning based on a fingerprint and a computer storage medium.
  • Fingerprint positioning is a very important positioning technology in the field of positioning technology.
  • fingerprint positioning technology is not limited by indoor and outdoor, and is widely used.
  • Fingerprint positioning is to use a wireless signal at a certain location to establish a unique fingerprint feature to achieve positional positioning.
  • the amount of fingerprint database constructed is getting larger and larger, which leads to very low efficiency of location matching, which seriously restricts the development and application of fingerprint location technology.
  • a method of establishing a base station identification set in a sampling point area can filter most unrelated fingerprint records when matching.
  • the method needs to preset the second base station identifier set, and then matches the signal strength of the corresponding base station in the second base station identifier set to find an optimal matching result.
  • the matching of the second base station identification set is not introduced, and the efficiency of finding the matching algorithm still has problems.
  • embodiments of the present invention are directed to a method, an apparatus, and a computer storage medium for positioning based on a fingerprint, which are intended to solve the problem of low efficiency of fingerprint library search matching.
  • an embodiment of the present invention provides a method for performing positioning based on a fingerprint, where the method includes:
  • the mobile terminal is located according to the fingerprint feature record of the primary neighbor signal combination obtained by searching in the geographic fingerprint index table.
  • establishing the geographic fingerprint index table includes:
  • a geographic fingerprint index table is established by performing mapping processing by combining the fingerprint feature record with the primary neighbor cell signal.
  • the establishing the fingerprint feature record by collecting the wireless signal feature comprises:
  • the geographical location is divided into positioning areas to obtain a plurality of positioning areas;
  • a fingerprint feature record is established by filtering the wireless signal features in each positioning grid.
  • the obtaining is based on a primary zone signal and a neighboring zone signal of each wireless signal.
  • the main neighbor signal combination includes:
  • the main neighborhood signal combination is obtained by combining the obtained main area signal with the adjacent area signal.
  • the searching in the pre-established geographic fingerprint index table by using the combination of the primary area signal and the neighboring area signal for positioning includes:
  • the positioning of the mobile terminal according to the fingerprint feature record of the primary neighbor signal combination obtained by searching in the geographic fingerprint index table includes:
  • the fingerprint feature record matching the matching is obtained in the geographic fingerprint index table
  • an embodiment of the present invention provides an apparatus for performing positioning based on a fingerprint, where the apparatus includes:
  • Decomposing the wireless signal module configured to: when receiving the wireless signal for positioning sent by the mobile terminal, decomposing the main area signal and the neighboring area signal for positioning from the wireless signal;
  • a search module configured to search in a pre-established geographic fingerprint index table with the combination of the primary zone signal and the neighboring zone signal for positioning;
  • the positioning module is configured to locate the mobile terminal according to the fingerprint feature record of the primary neighbor signal combination obtained by searching in the geographic fingerprint index table.
  • the apparatus further includes a geographic fingerprint index table establishing module, the geographic The fingerprint index table establishing module is configured to collect a fingerprint feature record by collecting wireless signal features, obtain a primary neighbor region signal combination according to the primary region signal and the neighbor region signal of each wireless signal, and record the fingerprint feature by The main neighboring area signal combination performs mapping processing to establish a geographic fingerprint index table.
  • the geographic fingerprint index table establishing module is configured to collect wireless signal features on a geographic location, and perform positioning area division on the geographic location according to the collected wireless signal characteristics to obtain multiple positioning areas, and By locating each positioning area, multiple positioning grids are obtained, and fingerprint feature records are established by filtering the wireless signal features in each positioning grid.
  • the geographic fingerprint index table establishing module is specifically configured to obtain a main area signal and a neighboring area signal by decomposing the wireless signal in the positioning grid, and obtain the main area signal and the neighboring The zone signals are combined to obtain a primary neighbor zone signal combination.
  • the search module is specifically configured to: obtain a primary neighbor signal combination for positioning by combining the main area signal for positioning and a neighboring area signal;
  • the table searches for the same primary neighbor signal combination that is combined with the primary neighbor signal for positioning.
  • the positioning module is specifically configured to: according to the searched primary neighbor signal combination, obtain a fingerprint feature record matching the geographic fingerprint index table; according to the obtained fingerprint feature record, Find a corresponding positioning grid in the plurality of fingerprint feature records that are created to locate the mobile terminal.
  • the embodiment of the present invention further provides a computer storage medium, where the computer storage medium stores computer executable instructions, where the computer executable instructions are used to perform fingerprint based positioning according to an embodiment of the present invention.
  • the fingerprint database is searched in the estimated area, and then the fingerprint fingerprint table can be quickly used to converge the searched fingerprint feature record, and the effect is obviously better than other calculations. law.
  • a fast search and location service can be realized, which makes the entire positioning process simple.
  • FIG. 1 is a flowchart of a method for positioning based on a fingerprint according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of an apparatus for positioning based on a fingerprint according to an embodiment of the present invention
  • FIG. 3 is a flowchart of a method for creating a geographic fingerprint index table according to an embodiment of the present invention
  • FIG. 4 is a flowchart of a method for searching and positioning by using a geographic fingerprint index table according to an embodiment of the present invention
  • FIG. 5 is a structural block diagram of an apparatus for creating a geographic fingerprint index table and a search and location function according to an embodiment of the present invention
  • FIG. 6 is a diagram showing an example of wireless signal propagation attenuation according to an embodiment of the present invention.
  • FIG. 7 is a schematic diagram of propagation of multiple sets of wireless signals according to an embodiment of the present invention.
  • FIG. 8 is a schematic diagram of a method for recording a geographic fingerprint index table for creating a wireless signal according to an embodiment of the present invention
  • FIG. 9 is a diagram showing an example of region division of a voronoi diagram algorithm according to an embodiment of the present invention.
  • FIG. 1 is a flowchart of a method for performing positioning based on a fingerprint according to an embodiment of the present invention. As shown in FIG. 1 , the method includes:
  • Step S101 When receiving the wireless signal for positioning sent by the mobile terminal, decomposing the main area signal and the neighboring area signal for positioning from the wireless signal;
  • Step S102 Searching in the pre-established geographic fingerprint index table on the condition that the main area signal for positioning and the adjacent area signal combination are used;
  • Step S103 Locating the mobile terminal according to the fingerprint feature record of the primary neighbor cell signal combination obtained by searching in the geographic fingerprint index table.
  • the establishing the geographic fingerprint index table includes: establishing a fingerprint feature record by collecting wireless signal features; obtaining a primary neighbor region signal combination according to the primary region signal and the neighbor region signal of each wireless signal; and recording the fingerprint feature by recording the fingerprint feature Mapping processing is performed in combination with the primary neighbor signal to establish a geographic fingerprint index table.
  • the collecting the feature of the wireless signal to establish the fingerprint feature record includes: collecting wireless signal features on the geographic location; and performing location segmentation on the geographic location according to the collected wireless signal features to obtain multiple positioning A plurality of positioning grids are obtained by meshing each positioning area; fingerprint characteristic records are established by filtering the wireless signal features in each positioning grid.
  • the obtaining, according to the main area signal and the neighboring area signal of each wireless signal, the main neighboring area signal combination includes: decomposing the wireless signal in the positioning grid to obtain a main area signal and a neighbor The zone signal is obtained by combining the obtained main zone signal with the adjacent zone signal to obtain a primary neighbor zone signal combination.
  • the searching in the pre-established geographic fingerprint index table by using the primary area signal for positioning and the neighboring area signal combination as a condition includes: performing the primary area signal and the adjacent area signal for positioning Combining, obtaining a primary neighbor signal combination for positioning; searching the geographic fingerprint index table for the same primary neighbor signal combination as the primary neighbor signal combination for positioning.
  • the locating the mobile terminal according to the fingerprint feature record of the primary neighbor cell signal combination searched in the geographic fingerprint index table includes: obtaining, according to the searched primary neighbor cell signal combination, the geographic fingerprint index table And matching the fingerprint feature record; searching, according to the obtained fingerprint feature record, a corresponding positioning grid in the plurality of established fingerprint feature records, so as to locate the mobile terminal.
  • FIG. 2 is a schematic diagram of a device for performing positioning based on a fingerprint according to an embodiment of the present invention.
  • the method includes: an exploded wireless signal module 201, a search module 202, and a positioning module 203.
  • the decomposed wireless signal module 201 is configured to receive wireless for positioning after receiving the mobile terminal a signal, a main area signal for positioning and a neighboring area signal are decomposed from the wireless signal;
  • the search module 202 is configured to use the main area signal for positioning in a pre-established geographic fingerprint index table And the neighboring area signal combination is searched for condition;
  • the positioning module 203 is configured to locate the mobile terminal according to the fingerprint feature record of the primary neighboring area signal combination obtained by searching in the geographic fingerprint index table.
  • the embodiment of the present invention further includes a geographic fingerprint index table establishing module 204 (not shown in FIG. 2), and the geographic fingerprint index table establishing module 204 is configured to establish a fingerprint feature record by collecting wireless signal features, according to each wireless signal. The primary area signal and the neighboring area signal are combined to obtain a primary neighboring area signal, and a mapping process is performed by combining the fingerprint feature record with the primary neighboring area signal to establish a geographic fingerprint index table.
  • the geographic fingerprint index table establishing module 204 is configured to collect wireless signal features on a geographic location, and perform positioning area division on the geographic location according to the collected wireless signal features to obtain multiple positioning areas.
  • the geographic fingerprint index table establishing module 204 is specifically configured to obtain a main area signal and a neighboring area signal by decomposing the wireless signal in the positioning grid, and obtain the main area signal and The neighboring cell signals are combined to obtain a signal combination of the primary neighboring cells.
  • the search module 202 is specifically configured to: obtain a primary neighbor signal combination for positioning by combining the primary area signal and the neighboring area signal used for positioning;
  • the index table searches for the same primary neighbor signal combination as the primary neighbor signal combination for positioning.
  • the positioning module 203 is specifically configured to: according to the searched primary neighbor cell signal combination, obtain a fingerprint feature record matching the geographic fingerprint index table; according to the obtained fingerprint feature record, Searching a corresponding positioning grid among the plurality of fingerprint feature records that are created to locate the mobile terminal.
  • the above-mentioned decomposition wireless signal module 201, the search module 202, the positioning module 203, and the geographic fingerprint index table module establishment 204 may be a central processing unit (CPU) and a digital signal located on a device based on fingerprint positioning.
  • DSP Digital Signal Processor
  • MCU Micro Control Unit
  • MPU Microprocessor Unit
  • FPGA Field-Programmable Gate Array
  • the embodiment of the present invention includes an offline database construction phase and an online location search phase. It should be noted that the primary region in the following corresponds to the primary region signal in the above; the neighboring region in the following corresponds to the neighboring region signal in the above.
  • FIG. 3 is a flowchart of a method for creating a geographic fingerprint index table according to an embodiment of the present invention.
  • the offline database construction process is as shown in FIG. 3, and includes the following steps:
  • Step S301 Collect wireless signal sample samples.
  • the wireless signal samples are collected, and the wireless signal features of the sampled sample points can be automatically generated by means of manual acquisition or by a simulation tool, and the wireless signal feature collection of each sampled sample point can be completed by a combination of the two. jobs.
  • Step S302 dividing the area by using a graph algorithm.
  • the principle of regional division is as follows: the amount of fingerprint data collected in each area is as uniform as possible; the area of each area is as uniform as possible; the shape of the divided area is relatively regular.
  • the commonly selected area division map algorithm has a voronoi diagram (also called a Tyson polygon diagram), and the central point of the administrative area can be selected as the triangle vertex in the voronoi diagram, and the voronoi diagram is constructed to divide the geographical area. Then, the wireless signal feature records collected in the previous step are divided into various regions in the voronoi diagram, so that each region can independently construct a fingerprint database.
  • Step S303 meshing, filtering the sampling points, and establishing the fingerprint database of the area.
  • each area of the voronoi diagram select the appropriate side length for meshing, usually according to the positioning accuracy requirements and the grid size that best represents the characteristics of the wireless signal, such as 5 meters side length or 10 meters side length. Since the acquired wireless signal feature record has position information, it can correspond to each of the divided grids. Then, for the wireless signal feature data collected in each grid, the abnormal sampling samples are filtered to establish a fingerprint feature record. Gaussian filtering algorithms can usually be used to filter abnormal sampling samples and establish fingerprint feature records. Therefore, each region in the voronoi diagram creates a fingerprint library.
  • the latitude and longitude coordinate scale is selected as the method of mesh division, and the latitude and longitude scale can be regarded as the precision selection of the latitude and longitude, that is, the selection of the grid size.
  • the collected samples in each grid are selected, and the Gaussian filtering algorithm is used to filter and filter the difference points, and the main wireless signal features are retained to represent the grid, that is, the wireless signal fingerprint feature records of the grid are formed.
  • RSSI represents the signal strength of the wireless signal in the grid
  • ⁇ represents the variance of the wireless signal received by the grid
  • ⁇ represents the average of the wireless signals received by the grid
  • n represents within the grid The number of received wireless signals
  • i represents the ith wireless signal, and the value of i is in the range of 0 to n.
  • Step S304 Create an index table of the area.
  • the wireless signal fingerprint feature in each square the first few wireless signals with the highest signal strength are selected as the main area, and the remaining ones are used as the neighboring areas.
  • Each main area is combined with the remaining neighboring areas, and a mapping relationship with the grid is established, and finally the index of the wireless signal fingerprint feature of the grid is obtained. That is to say, since there are differences in the plurality of wireless signals received in each grid, the wireless signals are divided into a main area and a plurality of neighboring areas.
  • the primary zone represents the primary fingerprint feature of the grid
  • the neighboring zone represents the secondary fingerprint feature of the grid. Therefore, a combination of the primary area and the neighboring area is used as an index of the fingerprint record, and is saved as an index table record.
  • the index table can reduce the retrieval range of the fingerprint feature record and improve the fingerprint positioning speed.
  • the index table is obtained by indexing the wireless signal fingerprint features in all the grids.
  • each region in the voronoi diagram creates an index table.
  • FIG. 4 is a flowchart of a method for searching and locating by using a geographic fingerprint index table according to an embodiment of the present invention.
  • the online positioning search process is as shown in FIG. 4, and includes the following steps:
  • Step S401 Calculate the attribution area by using a graph algorithm.
  • the main area and the adjacent area in the positioning condition find the location of the main area and the adjacent area, and then calculate the position of the center point of the main area and the adjacent area, and preset an error radius to form a circle. Then, on the area map divided by the graph algorithm, the coverage of the circle where the center point is located is mapped, that is, the target area to be found.
  • Step S402 Find an index table in the area.
  • the main area and the neighboring area are divided according to the wireless signal of the positioning point, and each main area is combined with each adjacent area, and the mapped grid is searched in the index table.
  • Step S403 Statistics fingerprint recording.
  • Step S404 Calculate the Euclidean distance and find the set of fingerprint feature records with the smallest value.
  • the Euclidean distance is calculated from the signal strength of the anchor point, and the corresponding grid of the wireless signal fingerprint feature record with the smallest Euclidean distance is selected, and the position of the grid is used as the final positioning. result.
  • the location condition of the area where the voronoi diagram is selected may be the area where the primary base station is located. According to the wireless signal characteristics of the positioning point, it is divided into a main area and a plurality of neighboring areas. Searching the index table with the combination of the primary area and the neighboring area, all the fingerprint feature records including the combination of the primary neighboring area can be found; similarly, searching for the index table in the condition that all the primary areas and the neighboring areas in the positioning condition are combined The fingerprint feature record of all the main neighboring regions of the current anchor point can be found.
  • the method reduces the search range of the wireless signal feature fingerprint database; and then counts the number of times the primary neighboring cell combination appears.
  • the statistical method is to count the number of occurrences of each fingerprint record and the fingerprint record with the most occurrences in the result of combining the search index tables in multiple primary neighboring areas, and the fingerprint record matches the main area and the neighboring area, that is, the matching degree.
  • the best set of records finally, based on the signal strength of the anchor point, and the set of fingerprint feature records found in the previous step, calculate the Euclidean distance on the signal strength component to find the fingerprint feature with the smallest Euclidean distance. Record the corresponding grid, which is the grid with the highest matching degree, and use the grid position as the final positioning result.
  • FIG. 5 is a structural block diagram of an apparatus for creating a geographic fingerprint index table and a search and location function according to an embodiment of the present invention.
  • the device includes: a wireless signal collection module 501, a region division module 502, and a fingerprint library module. 503. Create an index table module 504, an area search module 505, a fingerprint feature search module 506, and an optimal matching fingerprint module 507.
  • the wireless signal collection module 501 is configured to collect wireless signal features in a geographic location by using a handheld terminal, where the wireless signal features include: location information, a base station cell, and a strong signal. Degree, Wireless Fidelity (WIFI) signal and its signal strength. It can be collected multiple times to collect accurate wireless signal characteristics, and can also be combined with software simulation to implement wireless signal acquisition module, that is, using the simulation tool to automatically generate regional wireless signal characteristics.
  • WIFI Wireless Fidelity
  • the area dividing module 502 is configured to select some points according to a certain rule on the area of the area where the fingerprint data is collected, and then divide the area according to the voronoi diagram algorithm.
  • the method of selecting points on a plane is usually to select the center point of the area. That is to say, in the large-scale fingerprint positioning, the wireless signal feature data collected on a large area is divided into multiple blocks according to the area, and the blocks are separately processed.
  • the commonly used zoning graph algorithm has a vornoi partitioning method, which consists of a set of contiguous polygons that form a vertical bisector of a line connecting two adjacent points. The area divided by this method, the area and the area are continuous, and the polygons constituting the area are relatively regular.
  • the fingerprint library module 503 is configured to filter abnormal wireless signal characteristics in the grid and calculate a fingerprint feature record of the grid.
  • the fingerprint feature records include attributes such as grid location information, main area and signal strength, multiple neighboring areas and signal strength, main service WIFI signal and signal strength, neighboring area WIFI and signal strength.
  • Gaussian filtering algorithm can be used to select the signal intensity of the acquired signal for Gaussian calculation, and the fingerprint feature record of the grid is obtained.
  • a fingerprint library is created to describe the wireless signal fingerprint characteristics of the area.
  • the created fingerprint library module 503 includes a mesh division of a wireless signal acquisition area and a wireless signal fingerprint feature extraction method.
  • Meshing divides the area using latitude and longitude scales, and the wireless signal acquisition samples in the same grid have the same latitude and longitude scale.
  • the wireless signal feature extraction method uses a Gaussian filtering algorithm to extract the main wireless signal features in the grid and filter the abnormal wireless signal characteristics.
  • the creation index table module 504 is configured to record the wireless signal fingerprint feature generated by the grid in each fingerprint database, divide the main area and the adjacent area of the record, and construct the fingerprint feature by using a combination of the main area and the neighboring area.
  • the index of the record, and the index corresponds to the grid.
  • An index of each wireless signal fingerprint feature record in each grid is saved to create an index table to provide a quick lookup of the fingerprint feature record service.
  • the area searching module 505 is configured to estimate the target area by estimating the area where the positioning point is located by using the location of the primary area and the neighboring area in the positioning condition, and then mapping to the area division map when the fingerprint database is mapped. That is to say, in the fingerprint positioning, the range of the positioning point is estimated according to the positioning condition, and the area where the positioning point is located can be estimated according to the location of the main area and the neighboring area in the positioning condition, and then the fingerprint positioning is performed in the estimated area. Find matches.
  • the fingerprint feature search module 506 is configured to search for an optimal set of fingerprint feature records. Match the search fingerprint library on the index table corresponding to the found target area. In the fingerprint location, for the wireless signal characteristics of the location, find the main area and the neighboring area, construct the primary neighboring area combination, find the fingerprint feature record containing the combination of the primary neighboring area in the index table, and then count the group with the most occurrences.
  • the grid is the grid that matches the primary zone and the neighboring zone.
  • the optimal matching fingerprint module 507 is configured to solve an optimal matching fingerprint feature record.
  • the wireless signal fingerprint feature record of a set of grids found by the fingerprint feature search module 506 calculates the Euclidean distance from the wireless signal feature of the anchor point, and the grid position corresponding to a wireless signal fingerprint feature record with the smallest Euclidean distance is used as the final Positioning results.
  • the foregoing wireless signal collection module 501, the area division module 502, the creation fingerprint library module 503, the creation index table module 504, the area search module 505, the fingerprint feature search module 506, and the optimal matching fingerprint module 507 may be located at Implementation of a CPU, DSP, MCU, MPU, or FPGA on a device that creates a geographic fingerprint index table and finds a location function.
  • the method includes: mesh division, which can uniformly divide an area into a grid by using a latitude and longitude scale on a geographical position; Source, specifically including base station signal transmitting station, wireless WIFI, etc.; wireless signal propagation, wireless signal in the process of propagation, there is attenuation; such as micro-cellular scene,
  • the attenuation model is:
  • PL[dB] represents the signal source with a transmit power of f c , the signal strength after the transmission distance d;
  • f c represents the carrier center frequency in units of MHz;
  • FIG. 7 is a schematic diagram of propagation of multiple sets of wireless signals according to an embodiment of the present invention. As shown in FIG. 7, the wireless signal features formed by each of the plurality of signal sources in each of the regions are samples that need to be collected by the wireless signal acquisition module. .
  • a wireless signal feature fingerprint record may be represented as a set of signal source identification numbers (ID, Identity), and The characteristic fingerprint recorded by the signal strength of the grid, the fingerprint record represents the wireless signal characteristics of the grid, and is unique.
  • the index table may be represented as an index of each wireless signal feature fingerprint record, and the index is represented as a combination of the main area and the neighboring area of the wireless signal feature fingerprint record, and corresponds to a wireless signal feature fingerprint record of the grid, ie, the grid.
  • FIG. 9 is a schematic diagram of an area division of a voronoi diagram algorithm according to an embodiment of the present invention.
  • A, B, C, and D are points on a plane, and a triangle ABC and a triangle are formed according to a nearest neighbor connection rule. ACD. Then make the vertical line of each side separately, as shown by the dotted line in the figure, the three vertical lines of the triangle intersect at one point, that is, point a and point b in the figure.
  • the area formed by the dotted line segment is the area division made by the voronoi diagram algorithm.
  • the solid line in the figure indicates the center line of the area; the dotted line indicates the boundary line of the area.
  • the wireless signal feature fingerprint database can be quickly searched, and the performance requirement is low, the memory occupation is small, and the fingerprint positioning retrieval speed can be improved.
  • Embodiments of the present invention also describe a computer storage medium in which the computer storage medium Computer-executable instructions are stored for performing the fingerprint-based positioning method described in the various embodiments above.
  • the computer storage medium stores one or more programs, and the one or more programs may be executed by one or more processors to implement the following steps:
  • the mobile terminal is located according to the fingerprint feature record of the primary neighbor signal combination obtained by searching in the geographic fingerprint index table.
  • the one or more programs may also be executed by the one or more processors to implement the following steps:
  • a geographic fingerprint index table is established by performing mapping processing by combining the fingerprint feature record with the primary neighbor cell signal.
  • embodiments of the present invention can be provided as a method, system, or computer program product. Accordingly, the present invention can take the form of a hardware embodiment, a 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 and 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.
  • the technical solution of the embodiment of the present invention when receiving the wireless signal for positioning sent by the mobile terminal, decomposes the main area signal and the neighboring area signal for positioning from the wireless signal; and the pre-established geographical fingerprint index table Searching for the combination of the primary zone signal and the neighboring zone signal for positioning; and positioning the mobile terminal according to the fingerprint feature record of the primary neighboring zone signal combination searched in the geographic fingerprint index table;
  • the technical solution of the embodiment of the invention narrows the search range by constructing a geographical fingerprint index table, and can quickly find a suitable fingerprint record, thereby Achieve fast positioning.

Abstract

本发明实施例公开了一种基于指纹进行定位的方法、装置及计算机存储介质，涉及位置定位技术领域，其方法包括：在收到移动终端发送的用于定位的无线信号时，从所述无线信号中分解出用于定位的主区信号和邻区信号；在预先建立的地理指纹索引表中以所述用于定位的主区信号和邻区信号组合为条件进行搜索；根据在地理指纹索引表中搜索得到的主邻区信号组合的指纹特征记录，对所述移动终端进行定位。

Description

一种基于指纹进行定位的方法、装置及计算机存储介质
相关申请的交叉引用
本申请基于申请号为201610402268.7、申请日为2016年06月07日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本发明涉及位置定位技术领域，特别涉及基于指纹进行定位的方法、装置及计算机存储介质。
背景技术
指纹定位是定位技术领域的一种非常重要的定位技术，特别是指纹定位技术不受室内室外限制，应用非常广泛。指纹定位是利用某一位置上的无线信号，建立唯一指纹特征，从而实现位置定位。但随着地理位置的扩展，构建的指纹库数据量越来越大，导致定位匹配查找效率非常低，严重制约了指纹定位技术的发展和应用。
目前也提出了一些方法用来提升指纹定位检索效率。比如：在采样点区域建立基站标识集合的方法，匹配时能够过滤大部分不相关指纹记录。但该方法需要预先设定第二基站标识集合，然后匹配第二基站标识集合中相应基站的信号强度，找出最优匹配结果。该方法中对匹配查找第二基站标识集合并没有介绍，查找匹配算法效率仍然存在问题。
综上所述，随着指纹库数据量越来越大，指纹库的匹配查找效率仍然是一个严重问题。
发明内容
有鉴于此，本发明实施例期望提供一种基于指纹进行定位的方法、装置及计算机存储介质，旨在解决指纹库查找匹配效率低的问题。
本发明实施例的技术方案是这样实现的：
第一方面，本发明实施例提供了一种基于指纹进行定位的方法，所述方法包括：
在收到移动终端发送的用于定位的无线信号时，从所述无线信号中分解出用于定位的主区信号和邻区信号；
在预先建立的地理指纹索引表中以所述用于定位的主区信号和邻区信号组合为条件进行搜索；
根据在地理指纹索引表中搜索得到的主邻区信号组合的指纹特征记录，对所述移动终端进行定位。
在一实施例中，建立所述地理指纹索引表包括：
通过收集无线信号特征，建立指纹特征记录；
根据每个无线信号的主区信号和邻区信号，得到主邻区信号组合；
通过将所述指纹特征记录与所述主邻区信号组合进行映射处理，建立地理指纹索引表。
在一实施例中，所述通过收集无线信号特征，建立指纹特征记录包括：
收集地理位置上的无线信号特征；
根据收集的无线信号特征，对所述地理位置进行定位区域划分，得到多个定位区域；
通过对每个定位区域进行网格划分，得到多个定位网格；
通过对每个定位网格内的无线信号特征进行过滤处理，建立指纹特征记录。
在一实施例中，所述根据每个无线信号的主区信号和邻区信号，得到 主邻区信号组合包括：
通过对所述定位网格内的无线信号进行分解，得到主区信号和邻区信号；
通过将得到的主区信号与邻区信号进行组合，得到主邻区信号组合。
在一实施例中，所述在预先建立的地理指纹索引表中以所述用于定位的主区信号和邻区信号组合为条件进行搜索包括：
通过将所述用于定位的主区信号和邻区信号进行组合，得到用于定位的主邻区信号组合；
在所述地理指纹索引表中搜索与所述用于定位的主邻区信号组合相同的主邻区信号组合。
在一实施例中，所述根据在地理指纹索引表中搜索得到的主邻区信号组合的指纹特征记录，对所述移动终端进行定位包括：
根据搜索到的主邻区信号组合，在地理指纹索引表中得到与其相匹配的指纹特征记录；
根据所得到的指纹特征记录，在所建立的多个指纹特征记录中查找对应的定位网格，以便对所述移动终端进行定位。
第二方面，本发明实施例提供了一种基于指纹进行定位的装置，所述装置包括：
分解无线信号模块，配置为在收到移动终端发送的用于定位的无线信号时，从所述无线信号中分解出用于定位的主区信号和邻区信号；
搜索模块，配置为在预先建立的地理指纹索引表中以所述用于定位的主区信号和邻区信号组合为条件进行搜索；
定位模块，配置为根据在地理指纹索引表中搜索得到的主邻区信号组合的指纹特征记录，对所述移动终端进行定位。
在一实施例中，所述装置还包括地理指纹索引表建立模块，所述地理 指纹索引表建立模块配置为通过收集无线信号特征，建立指纹特征记录，根据每个无线信号的主区信号和邻区信号，得到主邻区信号组合，以及通过将所述指纹特征记录与所述主邻区信号组合进行映射处理，建立地理指纹索引表。
在一实施例中，所述地理指纹索引表建立模块具体配置为收集地理位置上的无线信号特征，根据收集的无线信号特征，对所述地理位置进行定位区域划分，得到多个定位区域，并通过对每个定位区域进行网格划分，得到多个定位网格，以及通过对每个定位网格内的无线信号特征进行过滤处理，建立指纹特征记录。
在一实施例中，所述地理指纹索引表建立模块具体配置为通过对所述定位网格内的无线信号进行分解，得到主区信号和邻区信号，并通过将得到的主区信号与邻区信号进行组合，得到主邻区信号组合。
在一实施例中，所述搜索模块，具体配置为：通过将所述用于定位的主区信号和邻区信号进行组合，得到用于定位的主邻区信号组合；在所述地理指纹索引表中搜索与所述用于定位的主邻区信号组合相同的主邻区信号组合。
在一实施例中，所述定位模块，具体配置为：根据搜索到的主邻区信号组合，在地理指纹索引表中得到与其相匹配的指纹特征记录；根据所得到的指纹特征记录，在所建立的多个指纹特征记录中查找对应的定位网格，以便对所述移动终端进行定位。
第三方面，本发明实施例还提供了一种计算机存储介质，所述计算机存储介质中存储有计算机可执行指令，所述计算机可执行指令用于执行本发明实施例所述的基于指纹进行定位的方法。
根据本发明实施例提供的方案，在预估区域内查找指纹库，然后利用地理指纹索引表可以快速收敛查找的指纹特征记录，效果明显优于其它算 法。通过在各个区域内创建指纹库和索引表，可以实现快速查找定位服务，使得整个定位过程实现简单。
附图说明
图1是本发明实施例提供的一种基于指纹进行定位的方法流程图；
图2是本发明实施例提供的一种基于指纹进行定位的装置示意图；
图3是本发明实施例提供的创建地理指纹索引表的方法流程图；
图4是本发明实施例提供的利用地理指纹索引表进行查找定位的方法流程图；
图5是本发明实施例提供的具有创建地理指纹索引表和查找定位功能的设备的结构框图；
图6是本发明实施例提供的无线信号传播衰减的示例图；
图7是本发明实施例提供的多组无线信号的传播示意图；
图8是本发明实施例提供的创建无线信号的地理指纹索引表的记录方法示意图；
图9是本发明实施例提供的voronoi图算法区域划分示例图。
具体实施方式
以下结合附图对本发明的优选实施例进行详细说明，应当理解，以下所说明的优选实施例仅用于说明和解释本发明，并不用于限定本发明。
图1是本发明实施例提供的一种基于指纹进行定位的方法流程图，如图1所示，包括：
步骤S101：在收到移动终端发送的用于定位的无线信号时，从所述无线信号中分解出用于定位的主区信号和邻区信号；
步骤S102：在预先建立的地理指纹索引表中以所述用于定位的主区信号和邻区信号组合为条件进行搜索；
步骤S103：根据在地理指纹索引表中搜索得到的主邻区信号组合的指纹特征记录，对所述移动终端进行定位。
其中，建立所述地理指纹索引表包括：通过收集无线信号特征，建立指纹特征记录；根据每个无线信号的主区信号和邻区信号，得到主邻区信号组合；通过将所述指纹特征记录与所述主邻区信号组合进行映射处理，建立地理指纹索引表。作为一种实施方式，所述通过收集无线信号特征，建立指纹特征记录包括：收集地理位置上的无线信号特征；根据收集的无线信号特征，对所述地理位置进行定位区域划分，得到多个定位区域；通过对每个定位区域进行网格划分，得到多个定位网格；通过对每个定位网格内的无线信号特征进行过滤处理，建立指纹特征记录。作为一种实施方式，所述根据每个无线信号的主区信号和邻区信号，得到主邻区信号组合包括：通过对所述定位网格内的无线信号进行分解，得到主区信号和邻区信号；通过将得到的主区信号与邻区信号进行组合，得到主邻区信号组合。
其中，所述在预先建立的地理指纹索引表中以所述用于定位的主区信号和邻区信号组合为条件进行搜索包括：通过将所述用于定位的主区信号和邻区信号进行组合，得到用于定位的主邻区信号组合；在所述地理指纹索引表中搜索与所述用于定位的主邻区信号组合相同的主邻区信号组合。
其中，所述根据在地理指纹索引表中搜索得到的主邻区信号组合的指纹特征记录，对所述移动终端进行定位包括：根据搜索到的主邻区信号组合，在地理指纹索引表中得到与其相匹配的指纹特征记录；根据所得到的指纹特征记录，在所建立的多个指纹特征记录中查找对应的定位网格，以便对所述移动终端进行定位。
图2是本发明实施例提供的一种基于指纹进行定位的装置示意图，如图2所示，包括：分解无线信号模块201、搜索模块202以及定位模块203。所述分解无线信号模块201，配置为在收到移动终端发送的用于定位的无线 信号时，从所述无线信号中分解出用于定位的主区信号和邻区信号；所述搜索模块202，配置为在预先建立的地理指纹索引表中以所述用于定位的主区信号和邻区信号组合为条件进行搜索；所述定位模块203，配置为根据在地理指纹索引表中搜索得到的主邻区信号组合的指纹特征记录，对所述移动终端进行定位。
本发明实施例还包括地理指纹索引表建立模块204(在图2中未示出)，所述地理指纹索引表建立模块204配置为通过收集无线信号特征，建立指纹特征记录，根据每个无线信号的主区信号和邻区信号，得到主邻区信号组合，以及通过将所述指纹特征记录与所述主邻区信号组合进行映射处理，建立地理指纹索引表。作为一种实施方式，所述地理指纹索引表建立模块204具体配置为收集地理位置上的无线信号特征，根据收集的无线信号特征，对所述地理位置进行定位区域划分，得到多个定位区域，并通过对每个定位区域进行网格划分，得到多个定位网格，以及通过对每个定位网格内的无线信号特征进行过滤处理，建立指纹特征记录。作为一种实施方式，所述地理指纹索引表建立模块204具体配置为通过对所述定位网格内的无线信号进行分解，得到主区信号和邻区信号，并通过将得到的主区信号与邻区信号进行组合，得到主邻区信号组合。
作为一种实施方式，所述搜索模块202，具体配置为：通过将所述用于定位的主区信号和邻区信号进行组合，得到用于定位的主邻区信号组合；在所述地理指纹索引表中搜索与所述用于定位的主邻区信号组合相同的主邻区信号组合。
作为一种实施方式，所述定位模块203，具体配置为：根据搜索到的主邻区信号组合，在地理指纹索引表中得到与其相匹配的指纹特征记录；根据所得到的指纹特征记录，在所建立的多个指纹特征记录中查找对应的定位网格，以便对所述移动终端进行定位。
在实际应用中，上述分解无线信号模块201、搜索模块202以及定位模块203、地理指纹索引表模块建立204可由位于基于指纹进行定位的装置上的中央处理器(CPU，Central Processing Unit)、数字信号处理器(DSP，Digital Signal Processor)、微控制单元(MCU，Microcontroller Unit)、微处理器单元(MPU，Microprocessor Unit)或可编程门阵列(FPGA，Field－Programmable Gate Array)等实现。
本领域技术人员应当理解，本实施例的基于指纹进行定位的装置中各模块的功能，可参照实施例所述的基于指纹进行定位的方法的相关描述而理解。
本发明实施例包括离线建库阶段和在线定位查找阶段，需要说明的是，下文中的主区与上文中的主区信号对应；下文中的邻区与上文中的邻区信号对应。
其中，图3是本发明实施例提供的创建地理指纹索引表的方法流程图，离线建库流程如图3所示，包括以下步骤：
步骤S301：收集无线信号采样样本。
根据需要定位的区域，收集无线信号样本，可以通过人工采集的方式，也可以通过仿真工具自动生成采样样本点的无线信号特征，还可以两者结合的方式完成各个采样样本点的无线信号特征收集工作。
步骤S302：采用图算法划分区域。
选择合适的图算法，对地理位置进行区域划分。区域划分的原则是：各个区域采集的指纹数据量尽量均匀；各区域的面积尽量均匀；划分区域的形状相对规则。通常选择的区域划分图算法有voronoi图(又叫泰森多边形图)，可选择行政区域的中心点作为voronoi图中的三角形顶点，构建voronoi图，划分地理位置区域。然后把上一步骤采集到的无线信号特征记录，划分到voronoi图中的各个区域中，从而每个区域可独立构建指纹库。
步骤S303：网格划分，过滤采样点，建立该区域指纹库。
在voronoi图的每个区域内，选择合适的边长做网格划分，通常根据定位精度要求和最能代表无线信号特征的网格大小进行划分，比如5米边长或者10米边长等。由于采集的无线信号特征记录带有位置信息，可以对应到划分的每个网格中。然后对每个网格中采集的无线信号特征数据，过滤异常采样样本，建立指纹特征记录。通常可使用高斯过滤算法，过滤异常采样样本，建立指纹特征记录。因此，voronoi图中的每个区域都创建一张指纹库。也就是说，选择经纬度坐标刻度作为网格划分的方法，经纬度刻度可看作经纬度的精度选择，也即是网格大小的选择。选择每一个网格内的采集样本，通过高斯过滤算法，筛选过滤差异点，保留主要无线信号特征，用来代表该网格，即形成该网格的无线信号指纹特征记录。
特别的，通过高斯过滤算法筛选无线信号特征的过程如下描述：
a、选择网格内的采样样本。
b、解析每次采集的每一个无线信号，对每个无线信号做高斯过滤，保留RSSI(Received Signal Strength Indication，接收的信号强度指示)的取值范围为[0.15σ+μ,3.09σ+μ]的无线信号。
Figure PCTCN2017083462-appb-000001
Figure PCTCN2017083462-appb-000002
式中，RSSI表示该无线信号在该网格的信号强度；σ表示该网格接收到的无线信号的方差；μ表示该网格接收到的无线信号的平均值；n表示在该网格内接收到的无线信号的数量；i表示第i个无线信号，i的值在0～n范围内。
c、将该范围的RSSI值全部取出计算平均值，即为该无线信号的最终RSSI值，代表了该无线信号在该网格内的信号特征。
d、把该网格内的所有无线信号都按b～c步骤执行，即可得到该网格最终的无线信号指纹特征。
步骤S304：创建该区域的索引表。
对每个方格内的无线信号指纹特征，选取信号强度最大的前几个无线信号作为主区，剩余的作为邻区。对每一个主区分别与剩余的邻区组合，并建立与该网格的映射关系，最终得到该网格的无线信号指纹特征的索引。也就是说，由于每个网格内接收的多个无线信号存在差异，对这些无线信号划分为主区和多个邻区。主区代表了该网格的主要的指纹特征，邻区代表该网格的次要指纹特征。因此，使用主区和邻区的组合，作为该指纹记录的索引，保存为索引表记录。该索引表能够缩小指纹特征记录的检索范围，提升指纹定位速度。
对所有网格内的无线信号指纹特征都建立索引，即可得到索引表。特别的，voronoi图中的每个区域创建一个索引表。
其中，图4是本发明实施例提供的利用地理指纹索引表进行查找定位的方法流程图，在线定位查找流程如图4所示，包括以下步骤：
步骤S401：采用图算法计算归属区域。
根据定位条件中的主区、邻区，找到主区、邻区所在的位置，然后计算主区和邻区的中心点所在位置，预设一个误差半径，形成一个圆。然后在图算法划分的区域图上，映射出该中心点所在的圆的覆盖范围，即是所要找的目标区域。
步骤S402：查找区域内的索引表。
根据定位点的无线信号划分主区和邻区，并把每一个主区与每一个邻区分别组合，在索引表中查找映射的网格。
步骤S403：统计指纹记录。
统计网格出现次数最多的一组无线信号指纹特征记录，也就是该网格 上无线信号与定位点的无线信号最匹配的一组无线信号指纹特征。
步骤S404：计算欧式距离，找出值最小的那组指纹特征记录。
对找到的这一组无线信号指纹特征记录，与定位点的信号强度计算欧氏距离，选择欧氏距离最小的一条无线信号指纹特征记录对应的网格，把该网格的位置作为最终的定位结果。
也就是说，首先，根据定位条件选择voronoi图中的某一个或几个区域，然后在选定区域内查找索引表。其中，选择voronoi图的区域的定位条件可以是主基站所在区域。根据定位点的无线信号特征，划分为主区和多个邻区。以主区和邻区的组合搜索索引表，可找到包含该主邻区组合的所有指纹特征记录；同理，以定位条件中所有的主区和邻区的组合为条件，在索引表中搜索，可以找到当前定位点的所有主邻区组合的指纹特征记录，该方法缩小了无线信号特征指纹库的查找范围；然后，统计主邻区组合出现的次数。统计的方法是，在多个主邻区组合搜索索引表的结果中，统计每一条指纹记录出现的次数，出现次数最多的指纹记录，该指纹记录匹配主区和邻区最多，也就是匹配度最好的一组记录；最后，根据定位点的信号强度，与上一步骤中找到的一组指纹特征记录，在信号强度分量上计算欧氏距离，找出欧氏距离最小的那条指纹特征记录对应的网格，即为匹配度最高的网格，把该网格位置作为最终的定位结果。
图5是本发明实施例提供的具有创建地理指纹索引表和查找定位功能的设备的结构框图，如图5所示，该设备包括：无线信号采集模块501、区域划分模块502、创建指纹库模块503、创建索引表模块504、区域查找模块505、指纹特征查找模块506以及求最优匹配指纹模块507。
下面对各模块详细说明：
其中，所述无线信号采集模块501，配置为可利用手持终端采集地理位置上的无线信号特征，无线信号特征包括：位置信息、基站小区、信号强 度、无线保真(WIFI，Wireless FIdelity)信号及其信号强度等。可多次采集以收集准确的无线信号特征，也可结合软件仿真的方式实现无线信号采集模块，即利用仿真工具自动生成区域的无线信号特征。
所述区域划分模块502，配置为在采集指纹数据所在的区域平面上，按照一定的规则选取一些点，然后按照voronoi图算法划分区域。通常在平面上选择点的方法是选择区域的中心点。也就是说，在大规模指纹定位中，对大区域上采集的无线信号特征数据，按区域划分为多块，分块分别处理。通常使用的区域划分图算法有vornoi分区法，该方法是由一组连接两邻点直线的垂直平分线组成的连续多边形构成。使用该方法划分的区域，区域与区域是连续的，且构成区域的多边形是相对规则的。
所述创建指纹库模块503，配置为过滤网格内异常的无线信号特征，并计算该网格的指纹特征记录。指纹特征记录包含的属性有：网格位置信息，主区及信号强度，多个邻区及信号强度，主服务WIFI信号及信号强度，邻区WIFI及信号强度。可使用高斯过滤算法，选择采集信号的信号强度做高斯计算，得到网格的指纹特征记录。在每一个划分的区域内，创建一张指纹库，用于描述该区域的无线信号指纹特征。具体地说，该创建指纹库模块503包含了无线信号采集区域的网格划分和无线信号指纹特征提取方法。网格划分可使用经纬度刻度对区域进行网格划分，在同一个网格内的无线信号采集样本具有相同的经纬度刻度。无线信号特征提取方法使用了高斯过滤算法，提取网格内主要的无线信号特征，过滤异常的无线信号特征。
所述创建索引表模块504，配置为对每一张指纹库中网格生成的无线信号指纹特征记录，划分该记录的主区和邻区，使用主区和邻区的组合构建出该指纹特征记录的索引，并且该索引与网格对应。保存每一个网格内的每一条无线信号指纹特征记录的索引，从而创建索引表，以便提供快速查找该指纹特征记录服务。
所述区域查找模块505，配置为通过定位条件中的主区和邻区所在位置，预估定位点所在的区域，然后映射到指纹库时的区域划分图上，从而确定目标区域。也就是说，在指纹定位时，根据定位条件预估定位点所在的范围，并根据定位条件中主区、邻区所在位置可以预估定位点所在的区域，然后在预估区域内做指纹定位查找匹配。
所述指纹特征查找模块506，配置为查找最优的一组指纹特征记录。在找到的目标区域对应的索引表上，匹配查找指纹库。指纹定位时，对于定位的无线信号特征，找出主区和邻区，构建主邻区组合，在索引表中查找包含该主邻区组合的指纹特征记录，然后统计出现次数最多的一组网格，即为主区和邻区匹配的网格。
所述求最优匹配指纹模块507，配置为求解最优匹配指纹特征记录。在指纹特征查找模块506找到的一组网格的无线信号指纹特征记录，与定位点的无线信号特征计算欧氏距离，把欧氏距离最小的一条无线信号指纹特征记录对应的网格位置作为最终的定位结果。
在实际应用中，上述无线信号采集模块501、区域划分模块502、创建指纹库模块503、创建索引表模块504、区域查找模块505、指纹特征查找模块506以及求最优匹配指纹模块507可由位于具有创建地理指纹索引表和查找定位功能的设备上的CPU、DSP、MCU、MPU或FPGA等实现。
本领域技术人员应当理解，本实施例的具有创建地理指纹索引表和查找定位功能的设备中各模块的功能，可参照实施例所述的离线建库流程和在线定位查找流程的相关描述而理解。
图6是本发明实施例提供的无线信号传播衰减的示例图，如图6所示，包括：网格划分，利用经纬度在地理位置上的刻度，可以均匀的把一片区域划分网格；无线信号源，具体的包括基站信号发射台，无线WIFI等；无线信号的传播，无线信号在传播过程中，存在衰减；比如微蜂窝场景下， 其衰减模型为：
PL[dB]＝-35.4+26log10(d)+20log10(fc)
其中，PL[dB]表示发射功率为fc的信号源，经过传输距离d后的信号强度；fc表示载波中心频率，单位MHz；d表示传输距离，单位米(m)，取值范围>＝20m。
图7是本发明实施例提供的多组无线信号的传播示意图，如图7所示，多个信号源在区域每个网格形成的无线信号特征，即为无线信号采集模块需要收集的采样样本。
图8是本发明实施例提供的创建无线信号的地理指纹索引表的记录方法示意图，如图8所示，无线信号特征指纹记录可表示为一组由信号源标识号(ID，Identity)，和其在该网格的信号强度共同组成的特征指纹记录，该指纹记录代表了该网格的无线信号特征，具有唯一性。索引表可表示为每一条无线信号特征指纹记录的索引，索引表示为无线信号特征指纹记录的主区和邻区的组合，并且与网格即网格的一条无线信号特征指纹记录对应。指纹定位时，先搜索索引表主区和邻区的组合条件，可快速找到无线信号特征指纹记录，避免了指纹库的遍历查找，提升检索效率。
图9是本发明实施例提供的voronoi图算法区域划分示例图，如图9所示，图中A、B、C、D是平面上的点，按照最近邻点相连规则，构成三角形ABC和三角形ACD。然后分别做每一条边的中垂线，如图中虚线所示，三角形的三条中垂线交于一点，即图中的a点和b点。由虚线段构成的区域，则是voronoi图算法做出的区域划分。
其中，图中实线表示区域中心点连线；虚线表示区域划分边界线。
根据本发明实施例提供的方案，可快速查找无线信号特征指纹库，而且对性能要求低，内存占用少，能够提升指纹定位检索速度。
本发明实施例还记载了一种计算机存储介质，所述计算机存储介质中 存储有计算机可执行指令，所述计算机可执行指令用于执行前述各个实施例所述的基于指纹进行定位的方法。
作为一种实施方式，所述计算机存储介质存储有一个或者多个程序，所述一个或者多个程序可被一个或者多个处理器执行，以实现以下步骤：
在收到移动终端发送的用于定位的无线信号时，从所述无线信号中分解出用于定位的主区信号和邻区信号；
在预先建立的地理指纹索引表中以所述用于定位的主区信号和邻区信号组合为条件进行搜索；
根据在地理指纹索引表中搜索得到的主邻区信号组合的指纹特征记录，对所述移动终端进行定位。
作为一种实施方式，所述一个或者多个程序还可被所述一个或者多个处理器执行，以实现以下步骤：
通过收集无线信号特征，建立指纹特征记录；
根据每个无线信号的主区信号和邻区信号，得到主邻区信号组合；
通过将所述指纹特征记录与所述主邻区信号组合进行映射处理，建立地理指纹索引表。
本领域技术人员应当理解，本实施例的计算机存储介质中各程序的功能，可参照实施例所述的基于指纹进行定位的方法的相关描述而理解。
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、系统、或计算机程序产品。因此，本发明可采用硬件实施例、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和光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、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。
尽管上文对本发明进行了详细说明，但是本发明不限于此，本技术领域技术人员可以根据本发明的原理进行各种修改。因此，凡按照本发明原理所作的修改，都应当理解为落入本发明的保护范围。
工业实用性
本发明实施例的技术方案在收到移动终端发送的用于定位的无线信号时，从所述无线信号中分解出用于定位的主区信号和邻区信号；在预先建立的地理指纹索引表中以所述用于定位的主区信号和邻区信号组合为条件进行搜索；根据在地理指纹索引表中搜索得到的主邻区信号组合的指纹特征记录，对所述移动终端进行定位；本发明实施例的技术方案通过构建地理指纹索引表，缩小了查找范围，能够快速查找到合适的指纹记录，从而 实现快速定位。

Claims (13)

  1. 一种基于指纹进行定位的方法，所述方法包括：
    在收到移动终端发送的用于定位的无线信号时，从所述无线信号中分解出用于定位的主区信号和邻区信号；
    在预先建立的地理指纹索引表中以所述用于定位的主区信号和邻区信号组合为条件进行搜索；
    根据在地理指纹索引表中搜索得到的主邻区信号组合的指纹特征记录，对所述移动终端进行定位。
  2. 根据权利要求1所述的方法，其中，建立所述地理指纹索引表包括：
    通过收集无线信号特征，建立指纹特征记录；
    根据每个无线信号的主区信号和邻区信号，得到主邻区信号组合；
    通过将所述指纹特征记录与所述主邻区信号组合进行映射处理，建立地理指纹索引表。
  3. 根据权利要求2所述的方法，其中，所述通过收集无线信号特征，建立指纹特征记录包括：
    收集地理位置上的无线信号特征；
    根据收集的无线信号特征，对所述地理位置进行定位区域划分，得到多个定位区域；
    通过对每个定位区域进行网格划分，得到多个定位网格；
    通过对每个定位网格内的无线信号特征进行过滤处理，建立指纹特征记录。
  4. 根据权利要求3所述的方法，其中，所述根据每个无线信号的主区信号和邻区信号，得到主邻区信号组合包括：
    通过对所述定位网格内的无线信号进行分解，得到主区信号和邻区信号；
    通过将得到的主区信号与邻区信号进行组合，得到主邻区信号组合。
  5. 根据权利要求4所述的方法，其中，所述在预先建立的地理指纹索引表中以所述用于定位的主区信号和邻区信号组合为条件进行搜索包括：
    通过将所述用于定位的主区信号和邻区信号进行组合，得到用于定位的主邻区信号组合；
    在所述地理指纹索引表中搜索与所述用于定位的主邻区信号组合相同的主邻区信号组合。
  6. 根据权利要求5所述的方法，其中，所述根据在地理指纹索引表中搜索得到的主邻区信号组合的指纹特征记录，对所述移动终端进行定位包括：
    根据搜索到的主邻区信号组合，在地理指纹索引表中得到与其相匹配的指纹特征记录；
    根据所得到的指纹特征记录，在所建立的多个指纹特征记录中查找对应的定位网格，以便对所述移动终端进行定位。
  7. 一种基于指纹进行定位的装置，所述装置包括：
    分解无线信号模块，配置为在收到移动终端发送的用于定位的无线信号时，从所述无线信号中分解出用于定位的主区信号和邻区信号；
    搜索模块，配置为在预先建立的地理指纹索引表中以所述用于定位的主区信号和邻区信号组合为条件进行搜索；
    定位模块，配置为根据在地理指纹索引表中搜索得到的主邻区信号组合的指纹特征记录，对所述移动终端进行定位。
  8. 根据权利要求7所述的装置，其中，所述装置还包括地理指纹索引表建立模块，配置为通过收集无线信号特征，建立指纹特征记录，根据每个无线信号的主区信号和邻区信号，得到主邻区信号组合，以及通过将所述指纹特征记录与所述主邻区信号组合进行映射处理，建立地理指纹索引 表。
  9. 根据权利要求8所述的装置，其中，所述地理指纹索引表建立模块具体配置为收集地理位置上的无线信号特征，根据收集的无线信号特征，对所述地理位置进行定位区域划分，得到多个定位区域，并通过对每个定位区域进行网格划分，得到多个定位网格，以及通过对每个定位网格内的无线信号特征进行过滤处理，建立指纹特征记录。
  10. 根据权利要求9所述的装置，其中，所述地理指纹索引表建立模块具体配置为通过对所述定位网格内的无线信号进行分解，得到主区信号和邻区信号，并通过将得到的主区信号与邻区信号进行组合，得到主邻区信号组合。
  11. 根据权利要求10所述的装置，其中，所述搜索模块，具体配置为：通过将所述用于定位的主区信号和邻区信号进行组合，得到用于定位的主邻区信号组合；在所述地理指纹索引表中搜索与所述用于定位的主邻区信号组合相同的主邻区信号组合。
  12. 根据权利要求11所述的装置，其中，所述定位模块，具体配置为：根据搜索到的主邻区信号组合，在地理指纹索引表中得到与其相匹配的指纹特征记录；根据所得到的指纹特征记录，在所建立的多个指纹特征记录中查找对应的定位网格，以便对所述移动终端进行定位。
  13. 一种计算机存储介质，所述计算机存储介质中存储有计算机可执行指令，所述计算机可执行指令用于执行权利要求1至6任一项所述的基于指纹进行定位的方法。
PCT/CN2017/083462 2016-06-07 2017-05-08 一种基于指纹进行定位的方法、装置及计算机存储介质 WO2017211153A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610402268.7A CN107484240B (zh) 2016-06-07 2016-06-07 一种基于指纹进行定位的方法及装置
CN201610402268.7 2016-06-07

Publications (1)

Publication Number Publication Date
WO2017211153A1 true WO2017211153A1 (zh) 2017-12-14

Family

ID=60577588

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/083462 WO2017211153A1 (zh) 2016-06-07 2017-05-08 一种基于指纹进行定位的方法、装置及计算机存储介质

Country Status (2)

Country Link
CN (1) CN107484240B (zh)
WO (1) WO2017211153A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10863452B2 (en) 2018-12-12 2020-12-08 Rohde & Schwarz Gmbh & Co. Kg Method and radio for setting the transmission power of a radio transmission
WO2021036829A1 (zh) * 2019-08-30 2021-03-04 华为技术有限公司 一种定位、离线指纹库的生成方法及装置
CN113411745A (zh) * 2021-06-29 2021-09-17 北京红山信息科技研究院有限公司 基于主邻区信号的指纹定位方法、装置、设备及存储介质

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109996270B (zh) * 2017-12-31 2022-03-04 中国移动通信集团湖北有限公司 网络覆盖分析方法、装置、设备及介质
TWI672063B (zh) * 2018-03-23 2019-09-11 中華電信股份有限公司 基於長期演進－無線區域網路聚合的無線網路定位方法及系統
CN110719602B (zh) * 2018-07-11 2023-03-28 中国电信股份有限公司 指纹定位方法和装置
CN111148028B (zh) * 2019-08-08 2021-08-24 广东小天才科技有限公司 一种定位纠偏方法及服务器
CN114648784B (zh) * 2022-05-23 2022-09-09 深圳创元智能软件科技有限公司 指纹库预匹配的指纹验证方法、装置、设备及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101547506A (zh) * 2009-02-17 2009-09-30 华中科技大学 基于信号接收强度信息指纹的gsm网络定位用户方法
CN102932911A (zh) * 2012-09-26 2013-02-13 上海顶竹通讯技术有限公司 位置指纹定位方法及定位系统
WO2013159835A1 (en) * 2012-04-27 2013-10-31 Telefonaktiebolaget L M Ericsson (Publ) Method and apparatus for mobile positioning
CN103476118A (zh) * 2013-09-29 2013-12-25 哈尔滨工业大学 一种用于实时监控的wlan室内位置指纹定位方法
CN105338619A (zh) * 2014-08-08 2016-02-17 中兴通讯股份有限公司 定位方法及装置

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100984688B1 (ko) * 2007-04-23 2010-10-01 삼성전자주식회사 광대역 무선통신 시스템에서 사용자 입력을 통한 소형 기지국의 위치 설정 장치 및 방법
US8155023B2 (en) * 2008-09-26 2012-04-10 Texas Instruments Incorporated MIMO with reserved subframes in primary and secondary base stations
GB2472595B (en) * 2009-08-11 2012-01-11 Ubiquisys Ltd Creating neighbour cell lists
US8892124B2 (en) * 2010-11-05 2014-11-18 Telefonaktiebolaget L M Ericsson (Publ) Method and devices for positioning information reporting
WO2012119427A1 (zh) * 2011-08-30 2012-09-13 华为技术有限公司 一种蜂窝网络定位方法、服务平台、定位移动台和系统
CN103634810B (zh) * 2013-12-24 2017-04-12 英国Ranplan无线网络设计公司 一种室内无线网络覆盖问题区域定位的方法
CN104469676B (zh) * 2014-11-21 2018-03-02 北京拓明科技有限公司 一种移动终端的定位方法及系统
CN105142215B (zh) * 2015-08-07 2018-12-21 成都亚讯星科实业有限公司 用于多维度用户位置定位计算的方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101547506A (zh) * 2009-02-17 2009-09-30 华中科技大学 基于信号接收强度信息指纹的gsm网络定位用户方法
WO2013159835A1 (en) * 2012-04-27 2013-10-31 Telefonaktiebolaget L M Ericsson (Publ) Method and apparatus for mobile positioning
CN102932911A (zh) * 2012-09-26 2013-02-13 上海顶竹通讯技术有限公司 位置指纹定位方法及定位系统
CN103476118A (zh) * 2013-09-29 2013-12-25 哈尔滨工业大学 一种用于实时监控的wlan室内位置指纹定位方法
CN105338619A (zh) * 2014-08-08 2016-02-17 中兴通讯股份有限公司 定位方法及装置

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10863452B2 (en) 2018-12-12 2020-12-08 Rohde & Schwarz Gmbh & Co. Kg Method and radio for setting the transmission power of a radio transmission
WO2021036829A1 (zh) * 2019-08-30 2021-03-04 华为技术有限公司 一种定位、离线指纹库的生成方法及装置
CN113411745A (zh) * 2021-06-29 2021-09-17 北京红山信息科技研究院有限公司 基于主邻区信号的指纹定位方法、装置、设备及存储介质
CN113411745B (zh) * 2021-06-29 2023-07-07 北京红山信息科技研究院有限公司 基于主邻区信号的指纹定位方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN107484240A (zh) 2017-12-15
CN107484240B (zh) 2020-03-13

Similar Documents

Publication Publication Date Title
WO2017211153A1 (zh) 一种基于指纹进行定位的方法、装置及计算机存储介质
US9179435B2 (en) Filtering and clustering crowd-sourced data for determining beacon positions
CN107547633B (zh) 一种用户常驻点的处理方法、装置和存储介质
CN108520023A (zh) 一种基于混合聚类算法的雷暴核识别及追踪方法
CN109672973B (zh) 一种基于最强ap的室内定位融合方法
CN109963285B (zh) 确定小区覆盖范围的方法、装置、电子设备和存储介质
CN112543419B (zh) 一种基于密度聚类的用户轨迹预测方法及装置
CN107463585B (zh) 指纹数据入库处理方法及装置
CN110719602B (zh) 指纹定位方法和装置
WO2017000498A1 (zh) 干扰源的定位方法及装置
CN106156332B (zh) 基于选定时间段及选定区域筛选进出车辆的方法
WO2018000881A1 (zh) 一种定位方法、服务器及终端
CN108566620B (zh) 一种基于wifi的室内定位方法
WO2020024597A1 (zh) 室内定位方法和装置
CN108770057B (zh) 预定指纹库的确定方法及指纹定位方法、装置、存储介质
CN111475746B (zh) 兴趣点位置挖掘方法、装置、计算机设备和存储介质
CN110727752B (zh) 位置指纹库处理方法、设备及计算机可读存储介质
CN103913720A (zh) 一种面向非特定Wi-Fi设备的室内定位方法
CN106922017B (zh) 定位方法以及终端
CN103177189A (zh) 一种众源位置签到数据质量分析方法
WO2016033946A1 (zh) Wcdma网络小区软切换带的识别方法、设备、系统和存储介质
CN110933631B (zh) 基于wifi位置指纹的室内定位方法
CN106528559B (zh) 一种位置信息的提供方法和设备
CN104023389A (zh) 一种快速ap匹配定位方法
CN114554535B (zh) 共覆盖小区对智能识别方法、装置、设备及存储介质

Legal Events

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

Ref document number: 17809592

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17809592

Country of ref document: EP

Kind code of ref document: A1