CN111182453A

CN111182453A - Positioning method, positioning device, electronic equipment and storage medium

Info

Publication number: CN111182453A
Application number: CN202010089283.7A
Authority: CN
Inventors: 李翔; 李欣; 刘畅; 张鑫; 黄强; 弥朋
Original assignee: Tencent Technology Shenzhen Co Ltd
Current assignee: Tencent Technology Shenzhen Co Ltd
Priority date: 2020-02-12
Filing date: 2020-02-12
Publication date: 2020-05-19
Anticipated expiration: 2040-02-12
Also published as: CN111182453B

Abstract

The application discloses a positioning method, a positioning device, electronic equipment and a storage medium, and belongs to the technical field of networks. According to the method and the device, the wireless signal information in the positioning request is obtained by responding to the positioning request of the terminal, the fingerprint information of the wireless signals stored in the wireless signal fingerprint library is sequenced according to the sequence of the matching degree between the wireless signal information and the wireless signal information from large to small, the fingerprint sequencing result corresponding to the wireless signal information is obtained, the alternative fingerprint information of the positioning process at this time is screened from the wireless signal fingerprint library based on the type of the fingerprint information in the fingerprint sequencing result, the alternative fingerprint information is the fingerprint information which is screened according to the fingerprint sequencing result and has stronger pertinence with the positioning process at this time, the terminal is positioned based on the alternative fingerprint information, and the positioning accuracy of the positioning process can be improved.

Description

Positioning method, positioning device, electronic equipment and storage medium

Technical Field

The present application relates to the field of network technologies, and in particular, to a positioning method, an apparatus, an electronic device, and a storage medium.

Background

With the development of network technology, users have more and more demands for location services, where indoor location refers to location positioning in an indoor environment, for example, a floor and a store where the user is located in a mall, and common indoor location methods include WiFi (Wireless Fidelity) location technology, bluetooth location technology, infrared location technology, and the like.

In the WiFi positioning technology, a fingerprint library is usually constructed based on WiFi fingerprint information acquired manually, meanwhile, a fingerprint matching model is trained by using training data, in a positioning stage, a terminal of a user sends a positioning request carrying a current WiFi list to a server, the server inputs the current WiFi list into the fingerprint matching model, WiFi fingerprint information with the highest matching degree is output, position data corresponding to the WiFi fingerprint information with the highest matching degree is determined as positioning data of the terminal, the positioning data is returned to the terminal, and in the positioning process based on the WiFi fingerprint information, the positioning precision is low.

Disclosure of Invention

The embodiment of the application provides a positioning method, a positioning device, electronic equipment and a storage medium, and positioning accuracy in a positioning process can be improved. The technical scheme is as follows:

in one aspect, a positioning method is provided, and the method includes:

responding to a positioning request of a terminal, and acquiring wireless signal information in the positioning request;

sorting the fingerprint information of the wireless signals stored in a wireless signal fingerprint library according to the sequence of the matching degree with the wireless signal information from large to small to obtain a fingerprint sorting result corresponding to the wireless signal information, wherein the matching degree is used for expressing the distance between the positioning position corresponding to the wireless signal information and the position indicated by the fingerprint information;

and screening alternative fingerprint information of the current positioning process from the wireless signal fingerprint library based on the type of the fingerprint information in the fingerprint sorting result, and positioning the terminal based on the alternative fingerprint information, wherein the type of the fingerprint information comprises store fingerprint information and indoor fingerprint information, the store fingerprint information is the fingerprint information of the wireless signal scanned at the position of a store, and the indoor fingerprint information is the fingerprint information of the wireless signal scanned at the indoor position of a non-store area.

In a possible implementation manner, the sorting the fingerprint information of the wireless signals stored in the wireless signal fingerprint database in order of the matching degree with the wireless signal information from large to small to obtain the fingerprint sorting result corresponding to the wireless signal information includes:

inputting the wireless signal information into a sorting model, acquiring the characteristic vector of the wireless signal information through the sorting model, predicting the matching probability of the wireless signal information and the fingerprint information in the wireless signal fingerprint database through the characteristic vector of the wireless signal information, and sorting the fingerprint information in the wireless signal fingerprint database according to the sequence of the matching probability from large to small to obtain the fingerprint sorting result.

In one possible embodiment, before the inputting the wireless signal information into the ranking model, the method further comprises:

the method comprises the steps of collecting at least one indoor positioning data and at least one positioning log data of at least one sample place, wherein one sample place comprises at least one shop and a non-shop area, one indoor positioning data comprises wireless signal information scanned when positioning is initiated from the non-shop area of the sample place, and one positioning log data comprises wireless signal information scanned when positioning is initiated from the sample place;

screening the at least one positioning log data to obtain at least one target log data, wherein one target log data comprises wireless signal information scanned when positioning is initiated in a shop of a sample place;

creating the wireless signal fingerprint database based on first indoor positioning data in the at least one indoor positioning data and first target log data in the at least one target log data, wherein the first indoor positioning data is indoor positioning data used for creating fingerprint information, and the first target log data is target log data used for creating fingerprint information;

training an initial sequencing model based on second indoor positioning data in the at least one indoor positioning data, second target log data in the at least one target log data and the wireless signal fingerprint database to obtain the sequencing model.

In one possible embodiment, the acquiring at least one indoor positioning data of at least one sample site comprises:

dividing a non-store area in any sample place according to a virtual grid to obtain at least one grid sub-area of the non-store area, wherein one grid sub-area corresponds to one virtual grid;

and acquiring at least one positioning data of the at least one grid subregion to obtain at least one indoor positioning data.

In a possible implementation manner, the filtering the at least one positioning log data to obtain at least one target log data includes:

and in response to the fact that a hotspot is connected, the connected hotspot is located in any shop of any sample place, at least one hotspot of the shop is included in the wireless signal information of the positioning log data, and the signal strength of any hotspot of the shop in the wireless signal information of the positioning log data exceeds a strength threshold, determining any positioning log data as target log data.

In one possible embodiment, the creating the wireless signal fingerprint library based on first indoor positioning data of the at least one indoor positioning data and first target log data of the at least one target log data comprises:

aggregating a plurality of first indoor positioning data acquired by collecting the grid subareas for a plurality of times to any grid subarea of a non-shop area in any sample place to obtain indoor fingerprint information of the grid subareas;

aggregating a plurality of first target log data corresponding to the shops in a target time period for any shop in any sample place to obtain shop fingerprint information of the shop;

and acquiring a wireless signal fingerprint database based on the indoor fingerprint information and the shop fingerprint information.

In one possible embodiment, the training an initial ranking model based on a second indoor positioning data of the at least one indoor positioning data, a second target log data of the at least one target log data, and the wireless signal fingerprint database, and the obtaining the ranking model includes:

constructing at least one training sample based on the second indoor positioning data, the second target log data and the wireless signal fingerprint database, wherein one training sample corresponds to one second indoor positioning data or second target log data and one fingerprint information;

and training the initial ranking model through the at least one training sample to obtain the ranking model.

In a possible implementation manner, the screening, from the wireless signal fingerprint database, alternative fingerprint information of the present positioning process based on the type of the fingerprint information in the fingerprint sorting result includes:

responding to the fact that a front target position in the fingerprint sorting result is shop fingerprint information, and determining indoor fingerprint information corresponding to the shop fingerprint information of the front target position as alternative fingerprint information; or the like, or, alternatively,

and in response to the fact that the target position before sorting in the fingerprint sorting result is indoor fingerprint information, determining the indoor fingerprint information in the wireless signal fingerprint database as alternative fingerprint information.

In one possible embodiment, the method further comprises:

and updating the fingerprint information in the wireless signal fingerprint database at intervals of target time length, and positioning based on the updated fingerprint information in the wireless signal fingerprint database.

In one aspect, a positioning method is provided, which is applied to a terminal, and the method includes:

sending a positioning request to a server in response to a positioning trigger operation based on a positioning interface, wherein the positioning interface is used for displaying an electronic map, the positioning request carries wireless signal information which is currently scanned by the terminal, the positioning request is used for acquiring positioning data returned based on the wireless signal information from the server, and the positioning data is obtained by positioning the terminal through alternative fingerprint information obtained by screening the server based on the type of the fingerprint information in a fingerprint sorting result corresponding to the wireless signal information;

and responding to the positioning data returned by the server, and displaying the position of the terminal in the electronic map of the positioning interface.

In one aspect, there is provided a positioning apparatus, the apparatus comprising:

the acquisition module is used for responding to a positioning request of a terminal and acquiring wireless signal information in the positioning request;

the sorting module is used for sorting the fingerprint information of the wireless signals stored in the wireless signal fingerprint database according to the sequence of the matching degree with the wireless signal information from large to small to obtain a fingerprint sorting result corresponding to the wireless signal information, and the matching degree is used for indicating the distance between the positioning position corresponding to the wireless signal information and the position indicated by the fingerprint information;

and the screening and positioning module is used for screening alternative fingerprint information of the current positioning process from the wireless signal fingerprint library based on the type of the fingerprint information in the fingerprint sorting result, and positioning the terminal based on the alternative fingerprint information, wherein the type of the fingerprint information comprises store fingerprint information and indoor fingerprint information, the store fingerprint information is the fingerprint information of the wireless signal scanned by the position where the store is located, and the indoor fingerprint information is the fingerprint information of the wireless signal scanned by the indoor position where the store is located in a non-store area.

In one possible implementation, the sorting module is configured to:

In one possible embodiment, the apparatus further comprises:

the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring at least one indoor positioning data and at least one positioning log data of at least one sample place, one sample place comprises at least one store and a non-store area, one indoor positioning data comprises wireless signal information scanned when positioning is initiated from the non-store area of the sample place, and one positioning log data comprises wireless signal information scanned when positioning is initiated from the sample place;

the screening module is used for screening the at least one positioning log data to obtain at least one target log data, and the target log data comprises wireless signal information scanned when positioning is initiated in a shop of a sample place;

a creating module, configured to create the wireless signal fingerprint database based on first indoor positioning data in the at least one indoor positioning data and first target log data in the at least one target log data, where the first indoor positioning data is indoor positioning data used for creating fingerprint information, and the first target log data is target log data used for creating fingerprint information;

and the training module is used for training an initial sequencing model based on second indoor positioning data in the at least one indoor positioning data, second target log data in the at least one target log data and the wireless signal fingerprint database to obtain the sequencing model.

In one possible embodiment, the acquisition module is configured to:

In one possible embodiment, the screening module is configured to:

In one possible implementation, the creation module is configured to:

In one possible embodiment, the training module is configured to:

In one possible embodiment, the screening location module is configured to:

In one possible embodiment, the apparatus further comprises:

and the updating and positioning module is used for updating the fingerprint information in the wireless signal fingerprint database at intervals of target time length and positioning based on the updated fingerprint information in the wireless signal fingerprint database.

In one aspect, a positioning apparatus is provided and applied to a terminal, the apparatus includes:

the sending module is used for responding to a positioning trigger operation based on a positioning interface, sending a positioning request to a server, wherein the positioning interface is used for displaying an electronic map, the positioning request carries wireless signal information which is scanned by the terminal currently, the positioning request is used for obtaining positioning data returned based on the wireless signal information from the server, and the positioning data is obtained by positioning the terminal through alternative fingerprint information obtained by screening the server based on the type of the fingerprint information in a fingerprint sorting result corresponding to the wireless signal information;

and the display module is used for responding to the positioning data returned by the server and displaying the position of the terminal in the electronic map of the positioning interface.

In one aspect, an electronic device is provided, which includes one or more processors and one or more memories, and at least one program code is stored in the one or more memories, and loaded by the one or more processors and executed to implement the operations performed by the positioning method according to any of the above possible implementations.

In one aspect, a storage medium is provided, in which at least one program code is stored, and the at least one program code is loaded and executed by a processor to implement the operations performed by the positioning method according to any of the above possible implementations.

The beneficial effects brought by the technical scheme provided by the embodiment of the application at least comprise:

acquiring wireless signal information in a positioning request in response to the positioning request of a terminal, sequencing fingerprint information of wireless signals stored in a wireless signal fingerprint library according to the sequence of the matching degree with the wireless signal information from large to small to obtain a fingerprint sequencing result corresponding to the wireless signal information, and screening alternative fingerprint information of the positioning process from the wireless signal fingerprint library based on the type of the fingerprint information in the fingerprint sequencing result because the matching degree is used for representing the distance between the positioning position corresponding to the wireless signal information and the position indicated by the fingerprint information, wherein the type of the fingerprint information comprises store fingerprint information and indoor fingerprint information, the store fingerprint information is the fingerprint information of the wireless signal scanned at the position, and the indoor fingerprint information is the fingerprint information of the wireless signal scanned at the indoor position in a non-store area, the alternative fingerprint information is the fingerprint information which is screened out according to the type of the fingerprint information in the fingerprint sorting result and has stronger pertinence with the positioning process, the terminal is positioned based on the alternative fingerprint information, and the positioning accuracy in the positioning process can be improved.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

Fig. 1 is a schematic diagram of an implementation environment of a positioning method according to an embodiment of the present application;

fig. 2 is an interaction flowchart of a positioning method provided in an embodiment of the present application;

FIG. 3 is a flowchart of a training method for a ranking model according to an embodiment of the present disclosure;

fig. 4 is a schematic diagram of a partition grid sub-region provided in an embodiment of the present application;

FIG. 5 is a schematic diagram illustrating a method for filtering target log data according to an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of a method for obtaining training samples according to an embodiment of the present disclosure;

fig. 7 is a schematic diagram of a positioning method provided in an embodiment of the present application;

FIG. 8 is a schematic structural diagram of a positioning device according to an embodiment of the present disclosure;

FIG. 9 is a schematic structural diagram of a positioning device according to an embodiment of the present disclosure;

fig. 10 is a schematic structural diagram of an electronic device provided in an embodiment of the present application;

fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

To make the objects, technical solutions and advantages of the present application more clear, embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

The terms "first," "second," and the like in this application are used for distinguishing between similar items and items that have substantially the same function or similar functionality, and it should be understood that "first," "second," and "nth" do not have any logical or temporal dependency or limitation on the number or order of execution.

The term "at least one" in this application means one or more, and the meaning of "a plurality" means two or more, for example, a plurality of first locations means two or more first locations.

Hereinafter, terms related to the present application are explained.

Indoor positioning: the method is to realize position location in an indoor place, and when a user is indoors, the position of the user indoors can be estimated according to environmental information (including but not limited to surrounding WiFi signals, bluetooth signals, air pressure, geomagnetism, and the like) collected by a user terminal, for example, which floor and which store in a mall the user is located can be determined through an indoor location technology.

Signal Strength (RSSI): the received signal strength indicator is used for indicating the signal strength of a wireless signal (for example, a WiFi signal) received by the terminal, and a WiFi chip on the terminal can basically provide the signal strength of the WiFi signal at present, and optionally, the unit of the signal strength may be db (decibel).

Fingerprint information: the fingerprint identification method and the fingerprint identification device can represent characteristic information of uniqueness of a certain positioning position, information such as WiFi signals and signal intensity, Bluetooth signals and signal intensity, air pressure and geomagnetism around the positioning position collected at each positioning position has certain uniqueness, and the fingerprint identification method and the fingerprint identification device can be used for constructing fingerprint information of the positioning position.

Virtual network: in the embodiment of the application, a virtual network is adopted to divide a non-store area in a sample site, so that the discretized grid sub-areas can be obtained, and as long as fingerprint information of each discretized grid sub-area is constructed, positioning service can be provided in the whole sample site (whole indoor space), for example, when the sample site is a mall, the non-store area can refer to a corridor area of the mall.

WiFi hotspot: the WiFi access points are deployed in a mall, a store, or an individual, a user may use a terminal to connect to the WiFi hotspots to obtain internet access services, and attribute information of each WiFi hotspot may include a WiFi name and a MAC Address (media access Control Address, also referred to as a local area network Address).

Based on the above noun explanation, for any indoor place, WiFi fingerprint information can be divided into store WiFi fingerprints and corridor WiFi fingerprints according to different collection areas, at present, store WiFi fingerprints and corridor WiFi fingerprints are mainly constructed by manual collection, and manual collection of WiFi fingerprints is limited on one hand, and on the other hand, labor cost is high, especially for some large shopping malls, manual collection of each store WiFi fingerprint and each corridor WiFi fingerprint brings great cost, and if the store WiFi fingerprints are not collected for saving labor cost, a positioning result is greatly deviated and positioning accuracy is reduced, and because the manual collection period is usually long, and the situations of store decoration, relocation, equipment replacement and the like cannot be expected, the WiFi fingerprints collected by manual collection are difficult to respond to the transformation of the situations quickly, and timeliness is low, it also results in degraded positioning performance.

In addition, since the two types of fingerprint information (store WiFi fingerprint and corridor WiFi fingerprint) have obvious differences in the aspects of acquisition mode, acquisition cycle, coverage and the like, in the related art, different types of fingerprint information are participated in the positioning process (especially in the fingerprint matching process) in the same mode, which may result in that better positioning accuracy cannot be obtained.

In view of this, the embodiment of the present application provides a positioning method, which provides a mechanism for integrating positioning for differences between store WiFi fingerprints (i.e., store fingerprint information) and corridor WiFi fingerprints (i.e., indoor fingerprint information), and different positioning strategies are respectively adopted for a case where the degree of matching with the store WiFi fingerprints is high and a case where the degree of matching with the corridor WiFi fingerprints is high, so as to improve positioning accuracy.

Further, when training the sequencing model of sequencing based on matching degree, can be through analysis and washing to historical positioning log data, shop wiFi fingerprint in the market is excavated and found out automatically, do not need artifical the collection, also greatly reduced the cost of fingerprint collection, and with the shop wiFi fingerprint of automatic establishment and the corridor wiFi fingerprint of artifical the collection provide location service together, even when making the user be located the shop that artifical fingerprint of gathering does not cover and initiate the location request, still can pinpoint out user's position, avoid producing great location cheaply, promote positioning accuracy. And because the WiFi fingerprint of the shop is automatically constructed by adopting the latest positioning log data, the problem of fingerprint transformation caused by the relocation, decoration, equipment replacement and the like of the shop can be quickly responded.

Fig. 1 is a schematic diagram of an implementation environment of a positioning method according to an embodiment of the present application. Referring to fig. 1, the implementation environment may include a terminal 101 and a server 102, where the terminal 101 and the server 102 are both electronic devices.

The terminal 101 may be configured to initiate a positioning request, an application program may be installed on the terminal 101, the application program is configured to provide a positioning service, for example, the application program may be at least one of a map application, a taxi taking application, a navigation application, a social application, or a take-away application, the embodiment of the present application is not specifically limited to the type of the application program, the terminal 101 may display a positioning interface in the application program, the positioning interface may include an electronic map, in response to a positioning trigger operation of a user based on the positioning interface, the terminal 101 acquires currently scanned wireless signal information (for example, at least one WiFi signal and respective signal strength), encapsulates the wireless signal information in the positioning request, and sends the positioning request to the server 102, so that the server 102 returns positioning data obtained based on the wireless signal information to the terminal 101 in response to the positioning request, after the terminal 101 receives the positioning data, the current position of the terminal 101 can be displayed in the electronic map of the positioning interface.

The terminal 101 and the server 102 may be connected through a wired network or a wireless network.

The server 102 may be used to provide location services, and the server 102 may include at least one of a server, a plurality of servers, a cloud computing platform, or a virtualization center. Alternatively, the server 102 may undertake primary computational tasks and the terminal 101 may undertake secondary computational tasks; or, the server 102 undertakes the secondary computing work, and the terminal 101 undertakes the primary computing work; alternatively, the terminal 101 and the server 102 perform cooperative computing by using a distributed computing architecture.

When a positioning request of any terminal 101 is received, the server 102 may analyze the positioning request to obtain wireless signal information carried in the positioning request, so as to determine positioning data of the terminal 101 based on the wireless signal information, specifically, the server 102 may sort, according to a sequence of a matching degree with the wireless signal information from large to small, fingerprint information of a wireless signal stored in a wireless signal fingerprint library to obtain a fingerprint sorting result, and based on the fingerprint sorting result, select, from the wireless signal fingerprint library, alternative fingerprint information of the present positioning process to obtain alternative fingerprint information of the present positioning process, and position the terminal 101 based on the alternative fingerprint information.

Optionally, the terminal 101 may refer to one of a plurality of terminals in general, and the device type of the terminal 101 includes but is not limited to: at least one of a vehicle-mounted terminal, a television, a smart phone, a smart speaker, a tablet computer, an electronic book reader, an MP3(Moving picture Experts Group Audio Layer III, motion picture Experts compression standard Audio Layer 3) player, an MP4(Moving picture Experts Group Audio Layer IV, motion picture Experts compression standard Audio Layer 4) player, a laptop portable computer, or a desktop computer. The following embodiments are exemplified in the case where the terminal includes a smartphone.

Those skilled in the art will appreciate that the number of terminals 101 described above may be greater or fewer. For example, the number of the terminals 101 may be only one, or the number of the terminals 101 may be several tens or hundreds, or more. The number and the device type of the terminals 101 are not limited in the embodiment of the present application.

Fig. 2 is an interaction flowchart of a positioning method according to an embodiment of the present application. Referring to fig. 2, the embodiment is applied to an interaction process between a terminal 101 and a server 102, and may include the following steps:

201. the terminal responds to the positioning triggering operation of a user based on a positioning interface, sends a positioning request to the server, the positioning interface is used for displaying an electronic map, and the positioning request carries the wireless signal information which is scanned by the terminal currently.

The positioning request is used to obtain positioning data returned by the server based on the wireless signal information, where the positioning data is obtained by positioning the terminal by the server based on the candidate fingerprint information obtained by screening the fingerprint sorting result corresponding to the wireless signal information, and a specific positioning process will be described in detail in steps 202 to 205 below.

An application program may be installed on the terminal, and the application program is used for providing a positioning service, for example, the application program may be at least one of a mapping application, a taxi taking application, a navigation application, a social contact application, or a take-away application, and the embodiment of the present application does not specifically limit the type of the application program.

The terminal may display a positioning interface in the application program, the positioning interface may include an electronic map, optionally, a user may input a positioning trigger operation based on the positioning interface displayed by the terminal, add a "my location" option in the electronic map, and determine that the positioning trigger operation is detected in response to a touch operation of the user on the "my location" option, optionally, the terminal may also automatically input the positioning trigger operation based on the positioning interface, for example, the positioning trigger operation is automatically triggered after the terminal displays the electronic map. The terminal responds to a positioning triggering operation (manual triggering by a user or automatic triggering by the terminal) based on a positioning interface, acquires currently scanned wireless signal information (such as at least one WiFi signal and respective signal strength), packages the wireless signal information in a positioning request, and sends the positioning request to the server.

In the foregoing process, taking the wireless signal as a WiFi signal as an example for illustration, the wireless signal information in the positioning request may be in a form of a list, and the related information of all WiFi signals currently scanned by the terminal may form a list, where each piece of wireless signal information in the list at least needs to include a MAC address and a signal strength RSSI of a certain WiFi signal. In an indoor place, according to the difference of the position of the terminal, the scanned WiFi signals may be different, and even if the same WiFi signal is scanned, the signal strength of the WiFi signal may also be different, so that the positioning data of the terminal can be predicted by constructing a wireless signal fingerprint database of each positioning position of the indoor place and comparing the wireless signal information scanned at the current position with the fingerprint information of the wireless signal stored in the wireless signal fingerprint database, and the purpose of performing indoor positioning on the terminal is achieved.

202. The server responds to the positioning request of the terminal and acquires the wireless signal information in the positioning request.

In the above process, after receiving any request, the server may analyze a first target field of the request, determine the request as a positioning request if the first target field carries positioning identification information, and analyze a second target field of the positioning request to obtain the wireless signal information. The first target field or the second target field may be any field of the positioning request, for example, the first target field may be a request header field, and the second target field may be a request body field.

203. The server sorts the fingerprint information of the wireless signals stored in the wireless signal fingerprint database according to the sequence of the matching degree with the wireless signal information from large to small, and a fingerprint sorting result corresponding to the wireless signal information is obtained.

The matching degree is used for indicating the distance between the positioning position corresponding to the wireless signal information and the position indicated by the fingerprint information, wherein the higher the matching degree is, the closer the positioning position of the terminal is to the position indicated by the fingerprint information, and conversely, the lower the matching degree is, the farther the positioning position of the terminal is to the position indicated by the fingerprint information.

In some embodiments, the server may input the wireless signal information into a ranking model, obtain a feature vector of the wireless signal information through the ranking model, predict a matching probability between the wireless signal information and the fingerprint information in the wireless signal fingerprint database through the feature vector of the wireless signal information, and rank the fingerprint information in the wireless signal fingerprint database according to a sequence of the matching probability from large to small to obtain the fingerprint ranking result.

Alternatively, the above-mentioned ranking model may be any machine learning model capable of ranking fingerprint information, and the ranking model may include at least one of GB (Gradient Boosting), GBDT (Gradient Boosting decision Tree), XGBoost (eXtreme Gradient Boosting) or LR (Logistic Regression) models.

Taking the ordering model as an XGBoost model as an example, the XGBoost model is a strong learner integrated by a plurality of weak learners, wherein the weak learners may be CART (Classification And Regression Tree) or linear classifiers (gbinear). The weak learners are taken as CART as an example, the server inputs wireless signal information into an XGboost model, extracts a feature vector of the wireless signal information through the XGboost model, inputs the feature vector into the weak learners, each weak learner can perform feature splitting on the feature vector to obtain leaf nodes of a decision tree where the weak learner is located, as each weak learner corresponds to a constraint condition, for the leaf nodes which meet the constraint condition, the weak learner outputs a leaf node score which is larger than 0, for the leaf nodes which do not meet the constraint condition, the weak learner outputs a leaf node score which is smaller than 0, the process is repeatedly executed, the weak learners output a plurality of leaf node scores, and the matching probability between the wireless signal information and any fingerprint information can be obtained by weighting the leaf node scores, the matching probabilities are equivalent to the fact that the degree of closeness between the wireless signal information and the fingerprint information is scored, the higher the score is, the closer the distance between the positions indicated by the wireless signal information and the fingerprint information is, so that the fingerprint information can be sorted according to the sequence from the big to the small of the matching probability, and the fingerprint sorting result is output.

In the process, the matching probability between the wireless signal information and each fingerprint information is calculated through the sequencing model, each fingerprint information is sequenced according to the sequence from the big to the small of the matching probability, the fingerprint sequencing result is obtained, and the accuracy of the sequencing process can be improved.

204. And the server screens the alternative fingerprint information of the current positioning process from the wireless signal fingerprint database based on the type of the fingerprint information in the fingerprint sorting result.

Optionally, the types of fingerprint information in the wireless signal fingerprint library may include store fingerprint information and indoor fingerprint information, where the store fingerprint information is fingerprint information of a wireless signal scanned at a location where a store is located, the indoor fingerprint information is fingerprint information of a wireless signal scanned at an indoor location in a non-store area, taking an indoor place as an example, the store fingerprint information is fingerprint information of a wireless signal scanned at each store location in a mall, and the indoor fingerprint information is fingerprint information of a wireless signal scanned at each corridor location in the mall.

In some embodiments, the server may filter the alternative fingerprint information, including the following two cases:

in case one, the server determines indoor fingerprint information corresponding to store fingerprint information of a front target position as alternative fingerprint information in response to that the front target position in the fingerprint sorting result is the store fingerprint information.

In the above process, the number of bits of the previous target bit may be any positive integer, for example, the previous target bit is the first bit, the previous two bits, the previous three bits, and the like, and the number of bits of the previous target bit is not specifically limited in this embodiment of the application.

If the front target positions are store fingerprint information, the server can determine the store fingerprint information with the first ranking, determine at least one piece of indoor fingerprint information with the distance between the indoor position and the store position indicated by the store fingerprint information with the first ranking smaller than a distance threshold from the wireless signal fingerprint library, and determine the at least one piece of indoor fingerprint information as alternative fingerprint information.

Taking the former target position as the first position for explanation, if the first position in the fingerprint sorting result is store fingerprint information, assuming that the store fingerprint information corresponds to the target store, then according to the position information of the target store, at least one indoor fingerprint information with the distance between the indoor position and the position information of the target store smaller than the distance threshold is screened out from the wireless signal fingerprint database, the at least one indoor fingerprint information is determined as the alternative fingerprint information, and the positioning is performed by using the alternative fingerprint information, the positioning method is equivalent to screening out the indoor fingerprint information closer to the target store from the wireless signal fingerprint database as the alternative fingerprint information, so that the positioning is performed only based on the alternative fingerprint information, the accuracy of the positioning process can be improved, the positioning mode in this case can also be vividly called as 'constrained positioning', the distance threshold may be any value greater than or equal to 0, for example, the distance threshold may be 15 meters, at this time, indoor fingerprint information within 15 meters from the location information of the target store participates in the current constrained positioning, and indoor fingerprint information other than 15 meters from the location information of the target store does not participate in the current constrained positioning.

And in case II, the server responds to the condition that the target position before the sorting in the fingerprint sorting result is the indoor fingerprint information, and determines the indoor fingerprint information in the wireless signal fingerprint database as the alternative fingerprint information.

If the front target positions are all indoor fingerprint information, the server can directly determine all indoor fingerprint information in the wireless signal fingerprint database as alternative fingerprint information.

In some embodiments, if the front target location includes both indoor fingerprint information and store fingerprint information, then if the number of indoor fingerprint information in the front target location is greater than the number of store fingerprint information, the candidate fingerprint information may be filtered in the manner of case two, and optionally, if the number of store fingerprint information in the front target location is greater than the number of indoor fingerprint information and less than the number of store fingerprint information, the candidate fingerprint information may be filtered in the manner of case one.

In the process, different alternative fingerprint information can be screened from the wireless signal fingerprint library according to different types of wireless signal information of front target positions in the fingerprint sorting result, if the front target positions are store fingerprint information, indoor fingerprint information of indoor positions close to the store positions can be determined as the alternative fingerprint information, so that constraint is added to subsequent positioning steps, the positioning accuracy can be improved by the constraint positioning mode, if the front target positions are the indoor fingerprint information, the possibility that the terminal is located in a non-store area is high, at the moment, all the indoor fingerprint information is determined as the alternative fingerprint information, the screening range of the positioning positions can be expanded, and the positioning accuracy can also be improved.

205. And the server positions the terminal based on the alternative fingerprint information to obtain positioning data of the terminal, and sends the positioning data to the terminal.

In some embodiments, in the process of positioning the terminal based on the candidate fingerprint information, the server may input the wireless signal information and the candidate fingerprint information into a fingerprint matching model, obtain a degree of similarity between the wireless signal information and each candidate fingerprint information through the fingerprint matching model, perform weighting processing on a position indicated by each candidate fingerprint information according to the degree of similarity, obtain position information indicated by the wireless signal information, and determine the position information indicated by the wireless signal information as the positioning data of the terminal.

Optionally, the similarity may be an expression form of an euclidean distance, a cosine similarity, or another similarity between the wireless signal information and the candidate fingerprint information, and this embodiment of the present application does not specifically limit the expression form of the similarity.

Optionally, the fingerprint matching model may include at least one of a KNN (K-Nearest Neighbor) model, an SVM (Support Vector Machine), or a neural network, and the embodiment of the present application does not specifically limit the type of the fingerprint matching model.

In some embodiments, the server can also update the fingerprint information in the wireless signal fingerprint database at intervals of target time, and perform positioning based on the updated fingerprint information in the wireless signal fingerprint database, so that when WiFi of a shop changes due to decoration, relocation, equipment replacement and other reasons, the fingerprint information of corresponding WiFi in the wireless signal fingerprint database can be updated in time, the timeliness of the fingerprint information in the wireless signal fingerprint database is guaranteed, and the positioning performance of the terminal can be improved.

206. And the terminal responds to the positioning data returned by the server and displays the position of the terminal in the electronic map of the positioning interface.

In the above process, after the terminal receives the positioning data, the terminal may map the positioning data to a location point in the electronic map, and display identification information of the terminal on the location point of the electronic map, where the identification information may be, for example, a color dot, or the identification information may also be a picture (e.g., a head portrait) set by a user, and the content of the identification information is not specifically limited in the embodiment of the application.

All the above optional technical solutions may be combined arbitrarily to form the optional embodiments of the present disclosure, and are not described herein again.

The method provided by the embodiment of the application obtains the wireless signal information in the positioning request by responding to the positioning request of the terminal, sorts the fingerprint information of the wireless signals stored in the wireless signal fingerprint library according to the sequence from the big matching degree to the small matching degree between the wireless signal information to obtain the fingerprint sorting result corresponding to the wireless signal information, and selects and obtains the alternative fingerprint information of the positioning process from the wireless signal fingerprint library based on the type of the fingerprint information in the fingerprint sorting result because the matching degree is used for representing the distance between the positioning position corresponding to the wireless signal information and the position indicated by the fingerprint information, wherein the type of the fingerprint information comprises store fingerprint information and indoor fingerprint information, the store fingerprint information is the fingerprint information of the wireless signals scanned by the position where the store is located, the indoor fingerprint information is the fingerprint information of wireless signals scanned from indoor positions in a non-shop area, the alternative fingerprint information is the fingerprint information which is screened out according to the type of the fingerprint information in the fingerprint sorting result and has stronger pertinence with the current positioning process, the terminal is positioned based on the alternative fingerprint information, and the positioning accuracy in the positioning process can be improved.

In the above embodiment, a strategy for performing positioning between a terminal and a server through an interactive process is provided, after the server receives a positioning request from the terminal, the server inputs wireless signal information in the positioning request into a sorting model, sorts fingerprint information according to a sequence from a large matching degree to a small matching degree between the fingerprint information and the wireless signal information through the sorting model, outputs a fingerprint sorting result, screens alternative fingerprint information of the positioning process based on the fingerprint sorting result, for different fingerprint sorting results, if a front target position is fingerprint store information, determines at least one indoor fingerprint information having a corresponding relation with the store fingerprint information as alternative fingerprint information, which is equivalent to performing a filtering and coarse screening on the indoor fingerprint information, such a positioning process is called as constrained positioning, if a front target position is indoor fingerprint information, determines all indoor fingerprint information as alternative fingerprint information, therefore, different alternative fingerprint information for the positioning can be screened out according to different types of the fingerprint information in the fingerprint sequencing result, so that the alternative fingerprint information adopted in the positioning process has higher pertinence, the more accurate positioning position can be positioned, and the positioning accuracy of the positioning process is improved.

Fig. 3 is a flowchart of a training method for a ranking model according to an embodiment of the present application, please refer to fig. 3, which is applied to a server, and the embodiment includes the following steps:

301. the server collects at least one indoor positioning data and at least one positioning log data of at least one sample site.

The sample site may include at least one store and a non-store area, the indoor positioning data includes wireless signal information scanned when positioning is initiated from the non-store area of the sample site, and the positioning log data includes wireless signal information scanned when positioning is initiated from the sample site.

For example, any sample place may be a mall, the wireless signal information scanned by the user when initiating positioning in a corridor area of the mall is referred to as indoor positioning data, the wireless signal information scanned by the user when initiating positioning in the mall is referred to as positioning log data, the indoor positioning data is usually manually collected and used for calibrating fingerprint information of the corridor area, and the positioning log data can be obtained by collecting historical positioning logs sent by each terminal in the mall.

In some embodiments, the server may take the following approaches when collecting the indoor positioning data: dividing a non-store area in any sample place according to a virtual grid to obtain at least one grid sub-area of the non-store area, wherein one grid sub-area corresponds to one virtual grid; and carrying out at least one time of positioning data acquisition on the at least one grid subregion to obtain at least one indoor positioning data.

In the above-mentioned in-process, when carrying out the location data collection to each grid subregion, can arrange the operation personnel to carry out manual collection, also can arrange the robot to carry out automatic acquisition, this application embodiment does not carry out concrete restriction to the mode of gathering the location data.

Fig. 4 is a schematic diagram of a grid sub-area division method provided in an embodiment of the present application, and please refer to fig. 4, which illustrates a sample shop 400, wherein the market 400 includes a shop area 401 and a corridor area 402 (non-shop area), the corridor area 402 is divided into a plurality of adjacent grid sub-areas by using a virtual grid, the size of each grid sub-area is the same, for example, the size of each grid sub-area may be 5 meters by 5 meters, the corridor area 402 may be divided according to a virtual grid of 5 meters by 5 meters for each floor of the market, so as to obtain a plurality of grid sub-areas of 5 meters by 5 meters, as shown in fig. 4, the central position of each grid sub-area in the corridor area 402 representing a certain floor is shown, during the collection process, at least one service person may be arranged to use at least one terminal, in a walking or static manner in each grid sub-area, the method includes acquiring at least one WiFi signal and signal strength around a position scanned in a grid subregion for multiple times, and since the at least one WiFi signal and signal strength scanned can be represented in a list form, hereinafter referred to as a "WiFi information list" for short, for example, the number of scans for each grid subregion may be 4-8, and the above scanning process may be implemented using at least two terminals, and in the WiFi information list recorded in the scanning process, for any WiFi signal, the following information of the WiFi signal may be recorded: the MAC address of the WiFi signal, the signal strength RSSI and the longitude and latitude coordinates of the grid sub-area where the WiFi signal is located. For example, a WiFi information list recorded during one scan (which may be simply referred to as "scan record") may be represented in the following form:

{"wifis":[{"mac":"abcd9876efgh","rssi":-41},{"mac":"abcd9876lmnp","rssi":-48},{"mac":"abcd9876ijkl","rssi":-49}],"latitude":39.1231231,"longitude":116.1231231}

wherein, latitude and longtude record the latitude and longitude of the collected grid subarea respectively.

In the above example, the MAC addresses and respective signal strengths of three WiFi signals scanned in a certain grid sub-area are protected in one scan record, and the longitude and latitude coordinates of the currently acquired grid sub-area are also recorded.

In the above process, the server divides the non-store area according to the virtual grid, discretizing the non-store area to obtain discrete grid sub-areas, respectively collecting the positioning data of each grid sub-area at least once, and obtaining the indoor positioning data of each grid sub-area.

In some embodiments, the server may not divide the non-store area according to a virtual grid, but may directly divide the non-store area into at least one discretized collection location point, perform at least one time of collection of the positioning data on each collection location point, and also be capable of discretizing the continuous space, and use the limited indoor positioning data collected for the limited locations to construct fingerprint information of each location of the whole non-store area (continuous space). That is to say, regardless of whether the discretization unit is a grid sub-area or a collection position point, as long as the fingerprint information of each unit after discretization can be constructed, the indoor position calibration of the non-store area can be realized, and the embodiment of the present application does not specifically limit the discretization manner of the non-store area.

In some embodiments, when the server collects the location log data, since the server can provide a location service for the at least one terminal, the location log data generated when the at least one terminal initiates a location request in the at least one sample location every day may be recorded, and the target log data generated when location is initiated in the store may be obtained by filtering the location log data in step 302.

Optionally, each piece of location log data at least includes a location request time, a MAC address of a connected WiFi hotspot (if no connection can be set to null), and a list of scanned surrounding WiFi information (including a MAC address and signal strength of each WiFi signal), for example, one piece of location log data may be represented as follows:

{"time":"2019-01-01 00:00:00","wlan":"shopapmac123","wifis":[{"mac":"abcd9876efgh","rssi":-41},{"mac":"abcd9876lmnp","rssi":-48},{"mac":"abcd9876ijkl","rssi":-49}]}

wherein, the wlan field records the MAC address of the WiFi hotspot connected when the positioning request is sent.

302. The server screens the at least one positioning log data to obtain at least one target log data, wherein one target log data comprises wireless signal information scanned when positioning is initiated in a shop of a sample place.

In the process, before the positioning log data is screened, WiFi hotspot information in at least one store in the at least one sample place can be acquired, in the acquisition process, all WiFi hotspot information arranged in each store can be acquired in a manual labeling mode, WiFi hotspot information in each store can be automatically mined through technologies such as computer matching and the like, the manual labeling mode is not repeated here, and for the case of automatic mining, the server can determine each WiFi hotspot information corresponding to each store according to the similarity between the WiFi hotspot name and the store name. For each store, the WiFi hotspot information for its store may include at least the following: the method comprises the following steps of carrying out calculation on the MAC addresses of all WiFi hotspots in the shop, the longitude and latitude coordinates of the center position of the shop, the MAC address of the WiFi hotspot 1 in the shop, the MAC address … … of the WiFi hotspot 2 in the shop and the like until the MAC addresses of all WiFi hotspots arranged in the shop are recorded.

After the WiFi hotspot information of each store is collected, the server may screen the positioning log data to obtain target log data by the following method: the server responds to the situation that a connected hotspot is displayed in any positioning log data, the connected hotspot is located in any shop of any sample place, at least one hotspot of the shop is included in the wireless signal information of the positioning log data, and the signal strength of any hotspot of the shop in the wireless signal information of the positioning log data exceeds a strength threshold value, and determines any positioning log data as target log data.

Fig. 5 is a schematic diagram of screening target log data provided in an embodiment of the present application, please refer to fig. 5, in which, for any positioning request log 501 (i.e. positioning log data), in step 502, it is determined whether the positioning request log 501 connects a WiFi hotspot when a positioning request is issued, if the positioning request log does not connect the WiFi hotspot, the positioning log data is discarded, otherwise, if the positioning request log 501 connects the WiFi hotspot, in step 503, it is determined whether a MAC address of the WiFi hotspot can be mapped to a certain store according to a mapping relationship between the MAC address of the WiFi hotspot and the store, if the WiFi hotspot cannot be mapped to the certain store, the positioning log data is discarded, otherwise, if the WiFi hotspot can be mapped to the certain store, step 504 is performed, it is assumed that the store to which the connected WiFi hotspot is mapped is marked as store a, and in step 504, it is determined whether a maximum signal intensity of the WiFi hotspot in a WiFi information list recorded in the positioning log data is greater than an intensity, if the intensity is less than or equal to the intensity threshold, discarding the positioning log data, otherwise, if the intensity is greater than the intensity threshold, executing step 505, and in step 505, adding the positioning log data into the target log data corresponding to the shop a.

The intensity threshold may be any real number, for example, the intensity threshold may be set to-60 db.

In the process, the mapping relation between the MAC address of the WiFi hotspot and the stores is established according to the acquired WiFi hotspot information of each store. Optionally, the identification information of each store and the MAC address of the WiFi hotspot of each store may be stored in a form of a key value pair, and when mapping is performed, the MAC address of the connected WiFi hotspot recorded in the positioning log is used as an index to query whether there is identification information of a store corresponding to the MAC address of the connected WiFi hotspot, and if the identification information of a store is queried, it is determined that the connected WiFi hotspot can be mapped to a certain store, otherwise, if the identification information of a store is not queried, it is determined that the connected WiFi hotspot cannot be mapped to a certain store.

Optionally, a mapping table of the MAC address of the WiFi hotspot and the store may be constructed in a table form according to the collected WiFi hotspot information of each store, and during mapping, whether an entry identical to the MAC address of the connected WiFi hotspot exists in the MAC address column of the WiFi hotspot in the mapping table is queried, and if the entry identical to the MAC address of the connected WiFi hotspot exists, it is determined that the connected WiFi hotspot can be mapped to a certain store, otherwise, it is determined that the connected WiFi hotspot cannot be mapped to a certain store.

303. The server creates the wireless signal fingerprint database based on first indoor positioning data in the at least one indoor positioning data and first target log data in the at least one target log data, wherein the first indoor positioning data is indoor positioning data used for creating fingerprint information, and the first target log data is target log data used for creating the fingerprint information.

In the above process, the server may randomly determine, from the indoor positioning data, part of the indoor positioning data for each grid subregion as first indoor positioning data, and determine the rest of the indoor positioning data in the indoor positioning data as second indoor positioning data, where the first indoor positioning data is used to construct indoor fingerprint information of an indoor position of a non-store region, and the second indoor positioning data is used to put into the following step 304 to train the ranking model.

The following discussion is made for the construction process of the indoor fingerprint information and the store fingerprint information respectively:

1) for any grid subregion of a non-store region in any sample place, the server aggregates a plurality of first indoor positioning data acquired by collecting the grid subregion for a plurality of times to obtain indoor fingerprint information of the grid subregion.

In the above process, each grid subregion may usually undergo at least one time of positioning data acquisition to obtain at least one first indoor positioning data, each first indoor positioning data at least includes the WiFi information lists scanned this time, and the fingerprint information of the grid subregion may be constructed by aggregating the WiFi information lists, for example, the fingerprint information of one grid subregion at least includes the following contents: the number of the WiFi signals included in the fingerprint information is not specifically limited in the embodiment of the present invention. The appearance frequency of a certain WiFi signal is the number of times the WiFi signal is scanned divided by the total number of times the WiFi signal is scanned in the grid subarea.

For example, the fingerprint information for a grid sub-region may be represented in the form:

{"wifis":[{"mac":"abcd9876efgh","rssi":-41.3,"frq":0.9},{"mac":"abcd9876lmnp","rssi":-48.7,"frq":0.5},{"mac":"abcd9876ijkl","rssi":-49.5,"frq":0.4}],"latitude":39.1231231,"longitude":116.1231231,"layer":"F1"}

2) for any shop in any sample place, the server aggregates a plurality of first target log data corresponding to the shop in a target time period to obtain shop fingerprint information of the shop.

In the above process, for each store, a part of target log data generated when positioning is initiated in the store is randomly selected as first target log data, the first target log data are screened to obtain first target log data within a target time period, and the first target log data within the target time period are aggregated to obtain store fingerprint information, where the target time period may be any historical time period, for example, the target time period may be one month from the current time.

For example, the store fingerprint information of a store may include at least the following: the number of the WiFi signals contained in the fingerprint information is not specifically limited in the embodiment of the application. The appearance frequency of a certain WiFi signal is a value obtained by dividing the number of times the WiFi signal is scanned by the total number of times the WiFi signal is scanned in the store.

3) And the server acquires a wireless signal fingerprint database based on the indoor fingerprint information and the shop fingerprint information.

In the above process, the server performs the step 1) for each grid subregion to obtain indoor fingerprint information of each grid subregion, performs the step 2) for each store to obtain store fingerprint information of each store, and stores all indoor fingerprint information and all store fingerprint information into the database, thereby constructing the wireless signal fingerprint database.

304. The server trains the initial sequencing model based on second indoor positioning data in the at least one indoor positioning data, second target log data in the at least one target log data and the wireless signal fingerprint database to obtain a sequencing model.

In some embodiments, the server may perform training of the ranking model by the following sub-steps:

3041. the server constructs at least one training sample based on the second indoor positioning data, the second target log data and the wireless signal fingerprint database, wherein one training sample corresponds to one second indoor positioning data or second target log data and one fingerprint information.

In the above process, the second indoor positioning data refers to data in the indoor positioning data except the first indoor positioning data, and the second target log data refers to data in the target log data except the first target log data, that is, neither the second indoor positioning data nor the second target log data participate in the creation process of the wireless signal fingerprint database.

The server may screen out data in a historical time period from the second indoor positioning data and the second target log data, where the historical time period may be a time period before any current time, such as three days before the current time.

In some embodiments, data in a historical time period may also be directly selected from the positioning log data, target log data generated when positioning is initiated in the store is selected from the data in the historical time period according to the screening manner in step 302, data participating in the wireless signal fingerprint database is filtered from the target log data, that is, second target log data may be obtained, and the positioning position of each second target log data is set as the center position of the corresponding store.

In some embodiments, the positioning data may be collected again for each grid subregion of the non-store area, and the collected data is used as the second indoor positioning data, in the collection process, the collection frequency of each grid subregion is greater than or equal to 1, and meanwhile, the longitude and latitude coordinates of the collection position and the scanned WiFi information list (including at least one WiFi signal and signal strength) need to be recorded, which is similar to the collection process in step 301, and is not described here again.

In the above process, the second indoor positioning data and the second target log data may correspond to at least one sample location, and the number and the type of the sample locations are not specifically limited in this embodiment of the application, for example, the sample location may be a mall, an office building, and the like, and the number of the sample locations may be 3, it should be noted that the trained ranking model may be applied to other locations, and has a certain generalization capability, and is not limited to the sample location during training, and of course, a ranking model may also be trained for each location, and the positioning accuracy of the ranking model may be improved.

The second indoor positioning data and the second target log data may be collectively referred to as "original training data", for example, the second target log data within 3 days before the current time and the second indoor positioning data obtained by performing 1-time manual acquisition on each grid sub-region may be used as the original training data, and any one piece of original training data may be represented as follows:

{"wifis":[{"mac":"abcd9876efgh","rssi":-41},{"mac":"abcd9876lmnp","rssi":-48},{"mac":"abcd9876ijkl","rssi":-49}],"latitude":39.1231231,"longitude":116.1231231,"layer":"F1"}

the lattude domain and the longtude domain respectively record the latitude and the longitude of the real position of the original training data, wherein the real position of the second target log data is the central position of the corresponding shop, the real position of the second indoor positioning data is manually marked, and the layer domain records the acquisition floor where the original training data is located.

In the above process, the server obtains original training data based on the second target log data and the second indoor positioning data, and then may construct a training sample based on the original training data and the wireless signal fingerprint library, specifically, the server may combine each original training data with each fingerprint information (whether store fingerprint information or indoor fingerprint information) in the wireless signal fingerprint library to form a training sample, and if the wireless signal fingerprint library includes M store fingerprint information and N indoor fingerprint information, for each original training data, combine with the M store fingerprint information and the N indoor fingerprint information, respectively, and may generate M + N training samples, where M and N are integers greater than or equal to 0.

After the training samples are constructed, the label information of the training samples needs to be determined for each training sample, and the label information of each training sample can be determined based on the distance between the real position of the original training data and the position indicated by the fingerprint information, for example, for any training sample, if the distance between the real position of the original training data in the training sample and the position indicated by the fingerprint information in the training sample is less than or equal to a target threshold value, determining the label information of the training sample as a 'positive sample', otherwise, if the distance between the real position of the original training data in the training sample and the position indicated by the fingerprint information in the training sample is greater than the target threshold value, determining the label information of the training sample as a 'negative sample', the target threshold may be any value greater than or equal to 0, for example, the target threshold may be 5 meters.

In some embodiments, in addition to the label information, a feature vector of each training sample may be extracted, and optionally, for each training sample, the server may obtain the feature vector of the training sample based on a WiFi information list of original training data in the training sample and a WiFi information list of fingerprint information in the training sample, where the feature vector is used to represent similarity between the original training data in the training sample and the fingerprint information.

In some embodiments, the feature vector may be a 30-dimensional feature vector, which is described by taking a training sample as an example, where the training sample includes original training data and fingerprint information, and WiFi information lists are recorded in the original training data and the fingerprint information, respectively, and the feature vector of the training sample may be obtained by analyzing and processing the WiFi information lists of the original training data and the fingerprint information, where a meaning of each dimension in the 30-dimensional feature vector of the training sample may be as follows:

1. the ratio of the number of WiFi signals shared in the original training data and the fingerprint information to the total number of WiFi signals in the fingerprint information is obtained.

2. The number of WiFi signals that are common in the original training data and the fingerprint information and have a signal strength (RSSI) greater than or equal to-60 db in the fingerprint information is a proportion of the total number of WiFi signals in the fingerprint information that have all signal strengths greater than or equal to-60 db.

3. The number of WiFi signals that are common in the original training data and the fingerprint information and have a signal strength (RSSI) of less than-60 db and greater than or equal to-70 db in the fingerprint information is a proportion of the total number of WiFi signals in the fingerprint information that have all signal strengths of less than-60 db and greater than or equal to-70 db.

4. The number of WiFi signals that are common in the original training data and the fingerprint information and have a signal strength (RSSI) of less than-70 db and greater than or equal to-80 db in the fingerprint information is a proportion of the total number of WiFi signals in the fingerprint information that have all signal strengths of less than-70 db and greater than or equal to-80 db.

5. The ratio of the number of WiFi signals shared by the original training data and the fingerprint information and having a signal strength (RSSI) of less than-80 db in the fingerprint information to the total number of WiFi signals having all signal strengths of less than-80 db in the fingerprint information.

6. The ratio of the number of WiFi signals shared in the original training data and the fingerprint information to the total number of WiFi signals in the original training data.

7. The number of WiFi signals that are common in the original training data and the fingerprint information and have a signal strength (RSSI) greater than or equal to-60 db in the original training data is a proportion of the total number of WiFi signals in the original training data that have all signal strengths greater than or equal to-60 db.

8. The number of WiFi signals that are common in the original training data and the fingerprint information and have a signal strength (RSSI) of less than-60 db and greater than or equal to-70 db in the original training data is a proportion of the total number of WiFi signals in the original training data having all signal strengths of less than-60 db and greater than or equal to-70 db.

9. The number of WiFi signals that are common in the original training data and the fingerprint information and have a signal strength (RSSI) of less than-70 db and greater than or equal to-80 db in the original training data is a proportion of the total number of WiFi signals in the original training data having all signal strengths of less than-70 db and greater than or equal to-80 db.

10. The number of WiFi signals common to the original training data and the fingerprint information and having a signal strength (RSSI) of less than-80 db in the original training data is a proportion of the total number of WiFi signals in the original training data having all signal strengths of less than-80 db.

11. Mean RSSI of signal strength differences for all WiFi signals common in the original training data and fingerprint information_meanWherein RSSI_meanCan be expressed as the following equation:

wherein L is the number of all common WiFi signals in the original training data and the fingerprint information, i is an integer greater than or equal to 1 and less than or equal to L, and RSSI_diRepresents the signal strength, RSSI, of the ith common WiFi signal in the original training data_fiIndicates the signal strength, abs (RSSI) of the ith common WiFi signal in the fingerprint information_di-RSSI_fi) Representation calculation (RSSI)_di-RSSI_fi) Absolute value of (a).

12. The raw training data and the average of the signal strength differences of all WiFi signals that are common in the fingerprint information and in which the signal strength (RSSI) is greater than or equal to-60 db.

13. The average of the signal strength differences of WiFi signals that are common to all of the raw training data and the fingerprint information and in which the signal strength (RSSI) is greater than or equal to-70 db and less than-60 db.

14. The average of the signal strength differences of WiFi signals that are common to all of the raw training data and the fingerprint information and in which the signal strength (RSSI) is greater than or equal to-80 db and less than-70 db.

15. The average of the signal strength differences of WiFi signals that are common to all of the raw training data and the fingerprint information and have a signal strength (RSSI) in the fingerprint information that is less than-80 db.

16. The average of the signal strength differences for WiFi signals that are common to all of the raw training data and the fingerprint information and have a signal strength (RSSI) in the raw training data that is greater than or equal to-60 db.

17. The average of the signal strength differences for WiFi signals that are common to all of the raw training data and the fingerprint information and have a signal strength (RSSI) in the raw training data that is greater than or equal to-70 db and less than-60 db.

18. The average of the signal strength differences for WiFi signals that are common to all of the raw training data and the fingerprint information and have a signal strength (RSSI) in the raw training data that is greater than or equal to-80 db and less than-70 db.

19. The average of the signal strength differences for WiFi signals that are common to all of the raw training data and the fingerprint information and have a signal strength (RSSI) in the raw training data that is less than-80 db.

20. Weighted mean RSSI of signal strength differences for all WiFi signals common in the raw training data and fingerprint information_{mean_w}Wherein the weight of each common WiFi signal is the occurrence frequency of the WiFi signal recorded in the fingerprint information and the RSSI_{mean_w}Can be expressed as the following equation:

wherein L is the number of all common WiFi signals in the original training data and the fingerprint information, i is an integer greater than or equal to 1 and less than or equal to L, and RSSI_diRepresents the signal strength, RSSI, of the ith common WiFi signal in the original training data_fiIndicates the signal strength, abs (RSSI) of the ith common WiFi signal in the fingerprint information_di-RSSI_fi) Representation calculation (RSSI)_di-RSSI_fi) Absolute value of, w_iIndicating the frequency of occurrence of the ith common WiFi signal recorded in the fingerprint information.

21. And the original training data and the weighted average of the signal strength differences of all the WiFi signals which are common in the fingerprint information and have the signal strength (RSSI) of more than or equal to-60 db in the fingerprint information are obtained, wherein the weight of each common WiFi signal is the occurrence frequency of the WiFi signal recorded in the fingerprint information.

22. And the weighted average of the signal strength differences of all the WiFi signals which are common in the original training data and the fingerprint information and have the signal strength (RSSI) of more than or equal to-70 db and less than-60 db in the fingerprint information, wherein the weight of each common WiFi signal is the occurrence frequency of the WiFi signal recorded in the fingerprint information.

23. And the weighted average of the signal strength differences of all the WiFi signals which are common in the original training data and the fingerprint information and have signal strength (RSSI) of more than or equal to-80 db and less than-70 db in the fingerprint information, wherein the weight of each common WiFi signal is the occurrence frequency of the WiFi signal recorded in the fingerprint information.

24. And the weighted average of the signal strength differences of all the WiFi signals which are common in the original training data and the fingerprint information and have the signal strength (RSSI) of less than-80 db in the fingerprint information is adopted, wherein the weight of each common WiFi signal is the occurrence frequency of the WiFi signal recorded in the fingerprint information.

25. And the weighted average of the signal strength differences of all the WiFi signals which are common in the original training data and the fingerprint information and have the signal strength (RSSI) of more than or equal to-60 db in the original training data is adopted, wherein the weight of each common WiFi signal is the occurrence frequency of the WiFi signal recorded in the fingerprint information.

26. And weighted average of signal strength differences of all the WiFi signals which are common in the original training data and the fingerprint information and have signal strength (RSSI) which is greater than or equal to-70 db and less than-60 db in the original training data, wherein the weight of each common WiFi signal is the occurrence frequency of the WiFi signal recorded in the fingerprint information.

27. And weighted average of signal strength differences of all the WiFi signals which are common in the original training data and the fingerprint information and have signal strength (RSSI) which is greater than or equal to-80 db and less than-70 db in the original training data, wherein the weight of each common WiFi signal is the occurrence frequency of the WiFi signal recorded in the fingerprint information.

28. And the weighted average of the signal strength differences of all the WiFi signals which are common in the original training data and the fingerprint information and have the signal strength (RSSI) of less than-80 db in the original training data is adopted, wherein the weight of each common WiFi signal is the occurrence frequency of the WiFi signal recorded in the fingerprint information.

29. The number of positive sequence WiFi signal pairs in the training sample is a proportion of the total number of WiFi signal pairs.

In the above process, for all WiFi signals common to the original training data and the fingerprint information, any two WiFi signals may form a WiFi signal pair. If L (L is more than or equal to 0) WiFi signals are totally generated, L (L-1)/2 WiFi signal pairs can be generated, if the magnitude relation of the signal intensity of one WiFi signal pair in the original training data is consistent with the magnitude relation of the signal intensity in the fingerprint information, the WiFi signal is symmetrical to be a positive sequence pair, otherwise, the WiFi signal is called a negative sequence pair.

For example, for a WiFi signal pair formed by any two common WiFi signals, assuming that the two WiFi signals included in the WiFi signal pair are denoted as WiFi _ a and WiFi _ b, respectively, the positive sequence pair needs to satisfy the following conditions: sign (RSSI)_ad-RSSI_bd)×sign(RSSI_af-RSSI_bf) And if not, determining the sequence as a reverse sequence pair.

Wherein the RSSI_adIndicating that WiFi _ a is originalSignal strength, RSSI, in training data_bdRepresents the signal strength, RSSI, of WiFi _ b in the original training data_afRepresents the signal strength, RSSI, of WiFi _ a in the fingerprint information_bfRepresents the signal strength, sign (RSSI) of WiFi _ b in the fingerprint information_ad-RSSI_bd) Representation acquisition (RSSI)_ad-RSSI_bd) Symbol of (a), (b), (c), (d), (_ad-RSSI_bd) Is a positive number, then sign (RSSI)_ad-RSSI_bd) A value of 1, if (RSSI)_ad-RSSI_bd) Is negative, then sign (RSSI)_ad-RSSI_bd) The value is-1, if sign (RSSI)_ad-RSSI_bd) Is 0, then sign (RSSI)_ad-RSSI_bd) Taking the value 0, sign (RSSI) for the same reason_af-RSSI_bf) Representation acquisition (RSSI)_af-RSSI_bf) The symbols of (1) are not described herein in detail.

30. The number of reverse-order WiFi signal pairs in the training sample is a proportion of the total number of WiFi signal pairs.

The dimension 30 feature is a proportion of a reverse WiFi signal pair corresponding to the dimension 29 feature, which is not described herein.

It should be noted that, in the embodiment of the present application, only a feature vector with 30 dimensions is taken as an example for description, a user may define feature vectors with more or fewer dimensions according to business requirements, and the embodiment of the present application does not specifically limit the number of dimensions and the meaning of the dimensions of the feature vectors.

Fig. 6 is a schematic diagram of a training sample acquisition method according to an embodiment of the present invention, please refer to fig. 6, the wireless signal fingerprint database can be divided into an indoor artificial WiFi fingerprint database 601 (assumed to include M indoor fingerprint information) and a store WiFi fingerprint database 602 (assumed to include N store fingerprint information) according to types of fingerprint information, the original training data 603 includes at least one of an indoor positioning request log (second target log data) or an artificially acquired indoor positioning data (second indoor positioning data), each original training data 603 can be represented in the form of "[ location true value, WiFi information list ]", and at least one training sample 604 can be constructed according to the indoor artificial WiFi fingerprint database 601, the store WiFi fingerprint database 602 and the original training data 603, wherein one original training data 603 and one fingerprint information (or indoor fingerprint information, or store fingerprint information) may constitute a training sample 604. Further, a feature vector 605 of each training sample 604 is calculated, a distance 606 between a true position (i.e., a true position value) of the original training data 603 in each training sample 604 and a fingerprint position (i.e., a position indicated by the fingerprint information) is calculated, taking a target threshold of 5 meters as an example, whether the calculated distance 606 is greater than 5 meters is determined, if the calculated distance is greater than 5 meters, the current training sample 604 is marked as a negative sample 607, that is, "[ feature vector, 0 ]" is stored, and if the calculated distance is less than or equal to 5 meters, the current training sample 604 is marked as a positive sample 608, that is, "[ feature vector, 1 ]" is stored.

3042. And the server trains the initial sequencing model through the at least one training sample to obtain a sequencing model.

In the above process, after obtaining the label information and the feature vector of the at least one training sample, the server may input the feature vector of the at least one training sample into an initial ranking model, respectively predict at least one matching probability between original training data and fingerprint information in the at least one training sample through the feature vector of the at least one training sample, determine a loss function value of the current iteration process based on the at least one matching probability and the label information of the at least one training sample, perform parameter adjustment on the initial ranking model if the loss function value is greater than a loss threshold, perform the above training process based on the model after parameter adjustment, otherwise, stop training if the loss function value is less than or equal to the loss threshold, and obtain a model adopted in the current iteration process as the ranking model.

The obtaining of the matching probability of the initial ranking model is similar to that in step 203 of the above embodiment, and is not described herein again.

Optionally, the initial ranking model may be any machine learning model capable of ranking fingerprint information, and the ranking model may include at least one of GB (Gradient Boosting), GBDT (Gradient Boosting decision Tree), XGBoost (eXtreme Gradient Boosting) or LR (Logistic Regression) models. Taking the initial ordering model as XGBoost as an example, the hyper-parameter during initialization may be set as follows: the maximum depth of the tree is 6, the weight of the maximum leaf node is 1, the learning rate is 0.1, and the rest super parameters are set as default values, only a setting example of the super parameters is provided here, a user can configure different super parameters and different initial sequencing models according to business requirements, and the type of the sequencing model and the setting mode of the super parameters are not specifically limited in the embodiment of the application.

According to the method provided by the embodiment of the application, the indoor positioning data and the positioning log data are collected, the target log data generated when positioning is initiated in a shop are screened out from the positioning log data, the wireless signal fingerprint library is constructed based on the first indoor positioning data and the first target log data, the sequencing model is trained based on the second indoor positioning data, the second target log data and the wireless signal fingerprint library, a machine learning model used for sequencing fingerprint information in the wireless signal fingerprint library according to the matching degree between the second indoor positioning data and the input wireless signal information can be trained offline, the sequencing model is put into an online positioning process, the accuracy rate of sequencing in the positioning process can be improved, and therefore the positioning accuracy is improved.

Fig. 7 is a schematic diagram of a positioning method according to an embodiment of the present application, please refer to fig. 7, which is described in conjunction with an offline training process and an online positioning process, taking a sample location as an example, the embodiment includes the following steps:

firstly, preparing basic data.

Service personnel can be dispatched to manually collect WiFi fingerprint information of a corridor area of a shopping mall (collecting indoor positioning data, acquiring indoor fingerprint information and creating an indoor artificial WiFi fingerprint database 701), and in addition, mapping relations 702 between WiFi hotspots in the shopping mall and shops are manually collected, namely which WiFi hotspots are included in each shop and what MAC addresses of the WiFi hotspots are.

Second, collect the location log (history location request log 703) of the user.

Each piece of positioning log data at least comprises information of whether a WiFi hotspot is connected, the connected WiFi hotspot information (the name of the WiFi hotspot, the MAC address of the WiFi hotspot and the signal strength RSSI of the WiFi), and a scanned surrounding WiFi information list, wherein the WiFi information list comprises the MAC address and the signal strength RSSI of each WiFi signal.

And thirdly, selecting a target time period, and cleaning the data of the positioning log of the target time period.

In the above process, the positioning log data corresponding to the positioning request sent from the shop within the target time period is obtained by screening, the positioning log data obtained by screening are determined as first target log data, and the shop fingerprint information of each shop is obtained by aggregation according to the first target log data of each shop, so as to construct the shop WiFi fingerprint database 704.

And fourthly, an off-line training stage.

And (2) constructing an indoor training sample 705[ position true value, WiFi information list ] collected manually by utilizing second indoor positioning data, constructing a training sample 706[ shop position, WiFi information list ] in the shop by utilizing second target log data, training a sequencing model 707 by utilizing the two training samples and a wireless signal fingerprint library (the indoor WiFi fingerprint library can be considered to comprise a shop fingerprint library and a manually collected corridor area), wherein the sequencing model 707 can sequence all shop fingerprint information and indoor fingerprint information, and the fingerprint information in the front of the sequencing indicates that the distance between the positioning position of the input wireless signal information and the position indicated by the fingerprint information is closer.

And fifthly, in an online positioning stage.

The positioning request of any terminal utilizes the trained sequencing model 707 in the off-line training stage to sequence the store fingerprint information and the indoor fingerprint information in the mall, assuming that the front target position is the first position, at this time, if the first sequence is the indoor fingerprint information, only all the manually acquired indoor fingerprint information is adopted as the alternative fingerprint information, the terminal is positioned based on the alternative fingerprint information, if the first sequence is the store fingerprint information, the manually acquired indoor fingerprint information with the distance between the indication position and the center position of the store not more than 15 meters is taken as the alternative fingerprint information, and the terminal is positioned based on the alternative fingerprint information (called as constrained positioning).

When positioning is performed based on the alternative fingerprint information, according to the fingerprint matching model 708 obtained by training the initial fingerprint matching model, the alternative fingerprint information and WiFi information in the positioning request are input into the fingerprint matching model 708, one or more pieces of fingerprint information with the similarity degree greater than the similarity threshold are determined, one or more fingerprint positions corresponding to the one or more pieces of fingerprint information are obtained, weighting processing is performed on the one or more fingerprint positions, a final positioning coordinate is calculated, and the final positioning coordinate is used as positioning data of the terminal.

Sixthly, a periodic updating stage.

At one end of the interval, the store fingerprint repository is updated with the last month of location log data.

The method provided by the embodiment of the application has the advantages that the server can automatically construct the shop fingerprint information of shops without manually collecting positioning data by analyzing and cleaning historical positioning log data, and is instructive, because a large amount of labor cost is brought if the positioning data is manually collected for each shop in an indoor place in an actual scene, and the collected positioning data can be out of order soon due to decoration, moving, equipment replacement and the like of the shops, a large amount of human resources are required to be arranged regularly to collect the positioning data, in the embodiment of the application, target log data are screened out based on the positioning log data, so that the automatic filling of the shop fingerprint information of shops which are not manually collected can be realized, the invalid shop fingerprint information can be found out in time, and the shop fingerprint information can be updated, therefore, the automatically filled store fingerprint information and the indoor fingerprint information of the non-store area can be combined to provide indoor positioning service together, the situation of large positioning deviation is avoided, and the service range and the positioning precision of the positioning service are greatly improved.

In this case, even if the user makes a positioning request in a store in which there is no arrangement for a serviceman to acquire fingerprint information, the user can be positioned near the store because the store fingerprint information of the store is automatically filled in, and of course, the user can be positioned near the real position if the user makes a positioning request in a non-store area in which there is no arrangement for a serviceman to acquire fingerprint information.

In a test scenario, when positioning is performed by using the positioning method provided by the embodiment of the application, in the process of performing indoor positioning in more than 10 marketplaces, only for positioning requests sent by testers in the shops, after store fingerprint information is filled, when positioning is performed based on a constrained positioning strategy, the positioning accuracy can be improved by at least 1.5 meters on average.

Fig. 8 is a schematic structural diagram of a positioning apparatus according to an embodiment of the present application, please refer to fig. 8, where the apparatus includes:

an obtaining module 801, configured to respond to a positioning request of a terminal, and obtain wireless signal information in the positioning request;

a sorting module 802, configured to sort, according to a sequence from a large matching degree to a small matching degree between the wireless signal information and the wireless signal information, fingerprint information of a wireless signal stored in a wireless signal fingerprint library to obtain a fingerprint sorting result corresponding to the wireless signal information, where the matching degree is used to indicate a distance between a positioning position corresponding to the wireless signal information and a position indicated by the fingerprint information;

and the screening and positioning module 803 is configured to screen candidate fingerprint information in the current positioning process from the wireless signal fingerprint library based on the type of the fingerprint information in the fingerprint sorting result, and position the terminal based on the candidate fingerprint information, where the type of the fingerprint information includes store fingerprint information and indoor fingerprint information, the store fingerprint information is fingerprint information of a wireless signal scanned at a location where a store is located, and the indoor fingerprint information is fingerprint information of a wireless signal scanned at an indoor location where a non-store area is located.

The device provided by the embodiment of the application obtains the wireless signal information in the positioning request by responding to the positioning request of the terminal, sorts the fingerprint information of the wireless signals stored in the wireless signal fingerprint library according to the sequence from large matching degree to small matching degree between the wireless signal information to obtain the fingerprint sorting result corresponding to the wireless signal information, and selects and obtains the alternative fingerprint information of the positioning process from the wireless signal fingerprint library based on the type of the fingerprint information in the fingerprint sorting result because the matching degree is used for representing the distance between the positioning position corresponding to the wireless signal information and the position indicated by the fingerprint information, wherein the type of the fingerprint information comprises store fingerprint information and indoor fingerprint information, and the store fingerprint information is the fingerprint information of the wireless signals scanned at the position of the store, the indoor fingerprint information is the fingerprint information of wireless signals scanned from indoor positions in a non-shop area, the alternative fingerprint information is the fingerprint information which is screened out according to the type of the fingerprint information in the fingerprint sorting result and has stronger pertinence with the current positioning process, the terminal is positioned based on the alternative fingerprint information, and the positioning accuracy in the positioning process can be improved.

In one possible implementation, the ordering module 802 is configured to:

inputting the wireless signal information into a sorting model, acquiring a feature vector of the wireless signal information through the sorting model, predicting the matching probability of the wireless signal information and the fingerprint information in the wireless signal fingerprint database through the feature vector of the wireless signal information, and sorting the fingerprint information in the wireless signal fingerprint database according to the sequence of the matching probability from large to small to obtain the fingerprint sorting result.

In a possible embodiment, based on the apparatus composition of fig. 8, the apparatus further comprises:

the creating module is used for creating the wireless signal fingerprint database based on first indoor positioning data in the at least one indoor positioning data and first target log data in the at least one target log data, wherein the first indoor positioning data is indoor positioning data used for creating fingerprint information, and the first target log data is target log data used for creating the fingerprint information;

and the training module is used for training the initial sequencing model based on second indoor positioning data in the at least one indoor positioning data, second target log data in the at least one target log data and the wireless signal fingerprint database to obtain the sequencing model.

In one possible embodiment, the acquisition module is configured to:

and carrying out at least one time of positioning data acquisition on the at least one grid subregion to obtain at least one indoor positioning data.

In one possible embodiment, the screening module is configured to:

and in response to the fact that any positioning log data shows that a hotspot is connected, the hotspot connected to is located in any shop at any sample place, at least one hotspot of the shop is included in the wireless signal information of the positioning log data, and the signal strength of any hotspot of the shop in the wireless signal information of the positioning log data exceeds a strength threshold, determining any positioning log data as target log data.

In one possible embodiment, the creation module is configured to:

aggregating a plurality of first indoor positioning data acquired by collecting the grid subareas for a plurality of times to any grid subarea of a non-shop area in any sample place to obtain indoor fingerprint information of the grid subarea;

aggregating a plurality of first target log data corresponding to the shop in a target time period for any shop in any sample place to obtain shop fingerprint information of the shop;

In one possible embodiment, the training module is configured to:

In one possible implementation, the screening and positioning module 803 is configured to:

and in response to the fact that the target position before sorting in the fingerprint sorting result is the indoor fingerprint information, determining the indoor fingerprint information in the wireless signal fingerprint database as alternative fingerprint information.

It should be noted that: in the positioning device provided in the above embodiment, only the division of the functional modules is exemplified in the positioning, and in practical applications, the functions may be distributed by different functional modules according to needs, that is, the internal structure of the electronic device is divided into different functional modules to complete all or part of the functions described above. In addition, the positioning apparatus and the positioning method provided by the above embodiments belong to the same concept, and specific implementation processes thereof are detailed in the positioning method embodiments and are not described herein again.

Fig. 9 is a schematic structural diagram of a positioning apparatus according to an embodiment of the present application, please refer to fig. 9, the apparatus is applied to a terminal, and the apparatus includes:

a sending module 901, configured to send, in response to a location trigger operation based on a location interface, a location request to a server, where the location interface is used to display an electronic map, the location request carries currently scanned wireless signal information of the terminal, the location request is used to obtain, from the server, location data returned based on the wireless signal information, and the location data is obtained by locating the terminal by using alternative fingerprint information obtained by screening, by the server, the type of fingerprint information in a fingerprint ranking result corresponding to the wireless signal information;

a display module 902, configured to respond to the positioning data returned by the server, and display the location of the terminal in the electronic map of the positioning interface.

The device provided by the embodiment of the application sends a positioning request to the server by responding to a positioning trigger operation based on the positioning interface, so that the server can return positioning data based on wireless signal information carried by the positioning request, the positioning data is obtained by positioning the terminal by alternative fingerprint information obtained by screening the server based on the type of the fingerprint information in a fingerprint sorting result corresponding to the wireless signal information, wherein the type of the fingerprint information comprises shop fingerprint information and indoor fingerprint information, the shop fingerprint information is the fingerprint information of the wireless signal scanned at the position of the shop, the indoor fingerprint information is the fingerprint information of the wireless signal scanned at the indoor position in a non-shop area, and the alternative fingerprint information is the fingerprint information which is screened according to the fingerprint sorting result and has stronger pertinence with the current positioning process, the positioning data obtained based on the alternative fingerprint information has higher positioning precision, the position of the terminal is displayed in the electronic map of the positioning interface in response to the positioning data returned by the server, and the positioning precision can be improved while more accurate positioning data is displayed.

Fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present application, and the electronic device is taken as an example for explanation. The terminal 1000 can be: a smart phone, a tablet computer, an MP3 player (Moving Picture experts Group Audio Layer III, motion video experts compression standard Audio Layer 3), an MP4 player (Moving Picture experts Group Audio Layer IV, motion video experts compression standard Audio Layer 4), a notebook computer, or a desktop computer. Terminal 1000 can also be referred to as user equipment, portable terminal, laptop terminal, desktop terminal, or the like by other names.

In general, terminal 1000 can include: a processor 1001 and a memory 1002.

Processor 1001 may include one or more processing cores, such as a 4-core processor, an 8-core processor, and so forth. The processor 1001 may be implemented in at least one hardware form of a DSP (Digital Signal Processing), an FPGA (Field-Programmable Gate Array), and a PLA (Programmable Logic Array). The processor 1001 may also include a main processor and a coprocessor, where the main processor is a processor for processing data in an awake state, and is also referred to as a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 1001 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the display screen. In some embodiments, the processor 1001 may further include an AI (Artificial Intelligence) processor for processing a computing operation related to machine learning.

Memory 1002 may include one or more computer-readable storage media, which may be non-transitory. The memory 1002 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In some embodiments, a non-transitory computer readable storage medium in the memory 1002 is used to store at least one instruction for execution by the processor 1001 to implement the positioning method provided by various embodiments herein.

In some embodiments, terminal 1000 can also optionally include: a peripheral interface 1003 and at least one peripheral. The processor 1001, memory 1002 and peripheral interface 1003 may be connected by a bus or signal line. Various peripheral devices may be connected to peripheral interface 1003 via a bus, signal line, or circuit board. Specifically, the peripheral device includes: at least one of radio frequency circuitry 1004, touch screen display 1005, camera assembly 1006, audio circuitry 1007, positioning assembly 1008, and power supply 1009.

The peripheral interface 1003 may be used to connect at least one peripheral related to I/O (Input/Output) to the processor 1001 and the memory 1002. In some embodiments, processor 1001, memory 1002, and peripheral interface 1003 are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor 1001, the memory 1002, and the peripheral interface 1003 may be implemented on separate chips or circuit boards, which are not limited by this embodiment.

The Radio Frequency circuit 1004 is used for receiving and transmitting RF (Radio Frequency) signals, also called electromagnetic signals. The radio frequency circuitry 1004 communicates with communication networks and other communication devices via electromagnetic signals. The radio frequency circuit 1004 converts an electrical signal into an electromagnetic signal to transmit, or converts a received electromagnetic signal into an electrical signal. Optionally, the radio frequency circuit 1004 comprises: an antenna system, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, a subscriber identity module card, and so forth. The radio frequency circuit 1004 may communicate with other terminals via at least one wireless communication protocol. The wireless communication protocols include, but are not limited to: metropolitan area networks, various generation mobile communication networks (2G, 3G, 4G, and 5G), Wireless local area networks, and/or WiFi (Wireless Fidelity) networks. In some embodiments, the rf circuit 1004 may further include NFC (Near Field Communication) related circuits, which are not limited in this application.

The display screen 1005 is used to display a UI (User Interface). The UI may include graphics, text, icons, video, and any combination thereof. When the display screen 1005 is a touch display screen, the display screen 1005 also has the ability to capture touch signals on or over the surface of the display screen 1005. The touch signal may be input to the processor 1001 as a control signal for processing. At this point, the display screen 1005 may also be used to provide virtual buttons and/or a virtual keyboard, also referred to as soft buttons and/or a soft keyboard. In some embodiments, display screen 1005 can be one, providing a front panel of terminal 1000; in other embodiments, display 1005 can be at least two, respectively disposed on different surfaces of terminal 1000 or in a folded design; in still other embodiments, display 1005 can be a flexible display disposed on a curved surface or on a folded surface of terminal 1000. Even more, the display screen 1005 may be arranged in a non-rectangular irregular figure, i.e., a shaped screen. The Display screen 1005 may be made of LCD (Liquid Crystal Display), OLED (Organic Light-Emitting Diode), and the like.

The camera assembly 1006 is used to capture images or video. Optionally, the camera assembly 1006 includes a front camera and a rear camera. Generally, a front camera is disposed at a front panel of the terminal, and a rear camera is disposed at a rear surface of the terminal. In some embodiments, the number of the rear cameras is at least two, and each rear camera is any one of a main camera, a depth-of-field camera, a wide-angle camera and a telephoto camera, so that the main camera and the depth-of-field camera are fused to realize a background blurring function, and the main camera and the wide-angle camera are fused to realize panoramic shooting and VR (Virtual Reality) shooting functions or other fusion shooting functions. In some embodiments, camera assembly 1006 may also include a flash. The flash lamp can be a monochrome temperature flash lamp or a bicolor temperature flash lamp. The double-color-temperature flash lamp is a combination of a warm-light flash lamp and a cold-light flash lamp, and can be used for light compensation at different color temperatures.

The audio circuit 1007 may include a microphone and a speaker. The microphone is used for collecting sound waves of a user and the environment, converting the sound waves into electric signals, and inputting the electric signals to the processor 1001 for processing or inputting the electric signals to the radio frequency circuit 1004 for realizing voice communication. For stereo sound collection or noise reduction purposes, multiple microphones can be provided, each at a different location of terminal 1000. The microphone may also be an array microphone or an omni-directional pick-up microphone. The speaker is used to convert electrical signals from the processor 1001 or the radio frequency circuit 1004 into sound waves. The loudspeaker can be a traditional film loudspeaker or a piezoelectric ceramic loudspeaker. When the speaker is a piezoelectric ceramic speaker, the speaker can be used for purposes such as converting an electric signal into a sound wave audible to a human being, or converting an electric signal into a sound wave inaudible to a human being to measure a distance. In some embodiments, the audio circuit 1007 may also include a headphone jack.

A location component 1008 is employed to locate a current geographic location of terminal 1000 for navigation or LBS (location based Service). The positioning component 1008 may be a positioning component based on the GPS (global positioning System) in the united states, the beidou System in china, the graves System in russia, or the galileo System in the european union.

Power supply 1009 is used to supply power to various components in terminal 1000. The power source 1009 may be alternating current, direct current, disposable batteries, or rechargeable batteries. When the power source 1009 includes a rechargeable battery, the rechargeable battery may support wired charging or wireless charging. The rechargeable battery may also be used to support fast charge technology.

In some embodiments, terminal 1000 can also include one or more sensors 1010. The one or more sensors 1010 include, but are not limited to: acceleration sensor 1011, gyro sensor 1012, pressure sensor 1013, fingerprint sensor 1014, optical sensor 1015, and proximity sensor 1016.

Acceleration sensor 1011 can detect acceleration magnitudes on three coordinate axes of a coordinate system established with terminal 1000. For example, the acceleration sensor 1011 may be used to detect components of the gravitational acceleration in three coordinate axes. The processor 1001 may control the touch display screen 1005 to display a user interface in a landscape view or a portrait view according to the gravitational acceleration signal collected by the acceleration sensor 1011. The acceleration sensor 1011 may also be used for acquisition of motion data of a game or a user.

The gyro sensor 1012 may detect a body direction and a rotation angle of the terminal 1000, and the gyro sensor 1012 and the acceleration sensor 1011 may cooperate to acquire a 3D motion of the user on the terminal 1000. From the data collected by the gyro sensor 1012, the processor 1001 may implement the following functions: motion sensing (such as changing the UI according to a user's tilting operation), image stabilization at the time of photographing, game control, and inertial navigation.

Pressure sensor 1013 may be disposed on a side frame of terminal 1000 and/or on a lower layer of touch display 1005. When pressure sensor 1013 is disposed on a side frame of terminal 1000, a user's grip signal on terminal 1000 can be detected, and processor 1001 performs left-right hand recognition or shortcut operation according to the grip signal collected by pressure sensor 1013. When the pressure sensor 1013 is disposed at a lower layer of the touch display screen 1005, the processor 1001 controls the operability control on the UI interface according to the pressure operation of the user on the touch display screen 1005. The operability control comprises at least one of a button control, a scroll bar control, an icon control and a menu control.

The fingerprint sensor 1014 is used to collect a fingerprint of the user, and the processor 1001 identifies the user according to the fingerprint collected by the fingerprint sensor 1014, or the fingerprint sensor 1014 identifies the user according to the collected fingerprint. Upon identifying that the user's identity is a trusted identity, the processor 1001 authorizes the user to perform relevant sensitive operations including unlocking a screen, viewing encrypted information, downloading software, paying, and changing settings, etc. Fingerprint sensor 1014 can be disposed on the front, back, or side of terminal 1000. When a physical key or vendor Logo is provided on terminal 1000, fingerprint sensor 1014 can be integrated with the physical key or vendor Logo.

The optical sensor 1015 is used to collect the ambient light intensity. In one embodiment, the processor 1001 may control the display brightness of the touch display screen 1005 according to the intensity of the ambient light collected by the optical sensor 1015. Specifically, when the ambient light intensity is high, the display brightness of the touch display screen 1005 is increased; when the ambient light intensity is low, the display brightness of the touch display screen 1005 is turned down. In another embodiment, the processor 1001 may also dynamically adjust the shooting parameters of the camera assembly 1006 according to the intensity of the ambient light collected by the optical sensor 1015.

Proximity sensor 1016, also known as a distance sensor, is typically disposed on a front panel of terminal 1000. Proximity sensor 1016 is used to gather the distance between the user and the front face of terminal 1000. In one embodiment, when proximity sensor 1016 detects that the distance between the user and the front surface of terminal 1000 gradually decreases, processor 1001 controls touch display 1005 to switch from a bright screen state to a dark screen state; when proximity sensor 1016 detects that the distance between the user and the front of terminal 1000 is gradually increased, touch display screen 1005 is controlled by processor 1001 to switch from a breath-screen state to a bright-screen state.

Those skilled in the art will appreciate that the configuration shown in FIG. 10 is not intended to be limiting and that terminal 1000 can include more or fewer components than shown, or some components can be combined, or a different arrangement of components can be employed.

Fig. 11 is a schematic structural diagram of an electronic device provided in an embodiment of the present application, taking the electronic device as a server for example, where the server 1100 may generate relatively large differences due to different configurations or performances, and may include one or more processors (CPUs) 1101 and one or more memories 1102, where the memory 1102 stores at least one program code, and the at least one program code is loaded and executed by the processors 1101 to implement the positioning method provided in each of the embodiments. Of course, the server 1100 may also have components such as a wired or wireless network interface, a keyboard, and an input/output interface, so as to perform input/output, and the server 1100 may also include other components for implementing device functions, which are not described herein again.

In an exemplary embodiment, a computer readable storage medium, such as a memory, including at least one program code, which is executable by a processor in a terminal to perform the positioning method in the above embodiments, is also provided. For example, the computer-readable storage medium may be a ROM (Read-Only Memory), a RAM (Random-Access Memory), a CD-ROM (Compact Disc Read-Only Memory), a magnetic tape, a floppy disk, an optical data storage device, and the like.

It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.

The above description is only exemplary of the present application and should not be taken as limiting, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method of positioning, the method comprising:

2. The method of claim 1, wherein the sorting the fingerprint information of the wireless signals stored in the wireless signal fingerprint database according to the sequence of the matching degree with the wireless signal information from large to small to obtain the fingerprint sorting result corresponding to the wireless signal information comprises:

3. The method of claim 2, wherein prior to entering the wireless signal information into a ranking model, the method further comprises:

4. The method of claim 3, wherein the acquiring at least one indoor positioning data for at least one sample site comprises:

5. The method of claim 3, wherein the filtering the at least one positioning log data to obtain at least one target log data comprises:

6. The method of claim 3, wherein creating the wireless signal fingerprint library based on a first indoor positioning data of the at least one indoor positioning data and a first target log data of the at least one target log data comprises:

7. The method of claim 3, wherein training an initial ranking model based on second indoor positioning data of the at least one indoor positioning data, second target log data of the at least one target log data, and the wireless signal fingerprint library, the obtaining the ranking model comprises:

8. The method according to claim 1, wherein the screening of the wireless signal fingerprint database for candidate fingerprint information of the present positioning process based on the type of fingerprint information in the fingerprint sorting result comprises:

9. The method of claim 1, further comprising:

10. A positioning method is applied to a terminal, and the method comprises the following steps:

11. A positioning device, the device comprising:

12. The apparatus of claim 11, wherein the ordering module is configured to:

13. A positioning device, applied to a terminal, the device comprising:

14. An electronic device, comprising one or more processors and one or more memories having at least one program code stored therein, the at least one program code being loaded and executed by the one or more processors to perform operations performed by a positioning method according to any one of claims 1 to 9 or 10.

15. A storage medium having stored therein at least one program code, which is loaded and executed by a processor to perform operations performed by the positioning method according to any one of claims 1 to 9 or 10.