CN110446167B

CN110446167B - Position estimation method and device

Info

Publication number: CN110446167B
Application number: CN201910538302.7A
Authority: CN
Inventors: 李环; 王教团
Original assignee: Advanced New Technologies Co Ltd
Current assignee: Advanced New Technologies Co Ltd; Advantageous New Technologies Co Ltd
Priority date: 2019-06-20
Filing date: 2019-06-20
Publication date: 2021-01-05
Anticipated expiration: 2039-06-20
Also published as: CN110446167A

Abstract

The present specification provides a position estimation method and a device, wherein the position estimation method includes: acquiring interactive data of a target user and an anchor point, wherein the interactive data carries identification information of the anchor point; under the condition that the interactive data does not contain the position information of the target user, extracting the identification information of the anchor point, and generating an identification ID of the anchor point according to the identification information; collecting interactive data of an anchor historical user and the anchor according to the identification ID of the anchor, extracting position information of the anchor from the interactive data, and calculating the online position of the anchor according to the position information; acquiring a prestored offline position of the anchor point according to the identification ID of the anchor point; inferring a current location of the target user based on the online location and the offline location of the anchor point.

Description

Position estimation method and device

Technical Field

The present disclosure relates to the field of positioning technologies, and in particular, to a position estimation method. The present specification also relates to a position inference apparatus, an electronic device, and a computer-readable storage medium.

Background

The mobile positioning technology is that some parameters of received radio waves are measured by a wireless mobile communication network, and the geographical position of a certain mobile terminal or an individual at a certain time is accurately measured according to a specific algorithm so as to provide related position information service for a mobile terminal user; alternatively, real-time monitoring and tracking is performed. With the development of network technology, in order to better serve users and improve user experience, many service terminals provide service items based on user positions, and thus a server is required to acquire current position information of the users.

In the prior art, a method for a server to obtain user location information mainly includes: 1) acquiring a user position through a positioning device of a user terminal; 2) and deducing the position of the user based on the historical mobile position data, namely acquiring historical track data of the user terminal, and deducing the position of the user terminal by using a prediction model based on the information characteristics extracted at the specific moment of the user.

The prior art user position information acquisition method has the following defects: the method is limited by whether the user actively starts the positioning authority or not, and can not reach the positioning without starting the positioning of part of users, so that the positioning accuracy is very limited, and the defects restrict the intelligent service and application of the service end based on the position and the like.

Disclosure of Invention

In view of this, the embodiments of the present specification provide a position inference method. The present specification also relates to a position estimation apparatus, an electronic device, and a computer-readable storage medium to solve the technical problems of the prior art.

According to a first aspect of embodiments herein, there is provided a position inference method including:

acquiring interactive data of a target user and an anchor point, wherein the interactive data carries identification information of the anchor point;

under the condition that the interactive data does not contain the position information of the target user, extracting the identification information of the anchor point, and generating an identification ID of the anchor point according to the identification information;

collecting interactive data of an anchor historical user and the anchor according to the identification ID of the anchor, extracting position information of the anchor from the interactive data, and calculating the online position of the anchor according to the position information;

acquiring a prestored offline position of the anchor point according to the identification ID of the anchor point;

inferring a current location of the target user based on the online location and the offline location of the anchor point.

Optionally, the collecting interactive data of an anchor historical user and the anchor according to the identification ID of the anchor, extracting location information of the anchor from the interactive data, and calculating the online location of the anchor according to the location information includes:

collecting interactive data of at least one anchor historical user and the anchor in a first preset period according to the identification ID of the anchor;

extracting the associated position information of the at least one anchor point historical user from the interactive data as the position information corresponding to the track point of the anchor point;

calculating the variance value of the position information corresponding to each track point of the anchor point;

and if the variance value is smaller than a preset variance threshold value, calculating the online position of the anchor point according to the position information corresponding to each track point of the anchor point.

Optionally, the interactive data between the anchor historical user and the anchor carries identification information of the at least one anchor historical user;

after the interactive data between the historical anchor point users and the anchor points in a first preset period is collected according to the identification IDs of the anchor points, before the associated position information of the at least one historical anchor point user is extracted from the interactive data to be used as the position information corresponding to the track points of the anchor points, the method further comprises the following steps:

determining the generation time of interactive data of the anchor historical user and the anchor;

acquiring target position information with shortest update time of the anchor historical user and the update time of the target position information with shortest update time according to the identification information of the anchor historical user;

and if the update time of the target position information with the shortest update time and the generation time interval of the interactive data are within a preset time threshold range, taking the target position information as the associated position information of the anchor point historical user.

Optionally, said inferring a current location of the target user based on the online location and the offline location of the anchor point comprises:

acquiring a prestored offline position with the shortest anchor point updating time and the updating time of the offline position with the shortest anchor point updating time according to the identification ID of the anchor point;

judging whether the updating time of the offline position with the shortest updating time of the anchor point is within a preset time threshold range;

and if so, taking the offline position with the shortest anchor point updating time as the current position of the target user.

Optionally, if the update time of the offline position with the shortest anchor update time is not within the preset time threshold range, the following operations are performed:

acquiring the number of track points of the anchor points in a first preset period according to the identification ID of the anchor points;

judging whether the number of the track points of the anchor points in a first preset period is greater than a preset threshold value or not;

and if so, taking the online position of the anchor point as the current position of the target user.

Optionally, if the number of the trace points of the anchor point in the first preset period is not greater than a preset threshold, the following operations are performed:

collecting and generating interactive data of the anchor historical user and the anchor with the shortest time according to the identification ID of the anchor;

and taking the associated position information of the anchor point historical user in the interactive data as the current position of the target user.

Optionally, the offline position of the anchor point is calculated by:

collecting interactive data of at least one anchor point historical user and the anchor point in a second preset period according to the identification ID of the anchor point;

clustering position information corresponding to the track points of the anchor points by adopting a clustering algorithm according to a preset neighborhood radius and the minimum sample point number to obtain at least one cluster;

and under the condition that the number of the clustered clusters after clustering is equal to 1, taking the centroid position of the clustered clusters as the offline position of the anchor point in a second preset period.

Optionally, in a case that the number of clustered clusters after clustering is greater than 1, the method further includes:

acquiring the number of track points contained in each cluster;

confirming abnormal clustering clusters according to the number of track points contained in each clustering cluster, wherein the number of the track points corresponding to the abnormal clustering clusters is smaller than a preset track point number threshold value;

purifying abnormal cluster clusters in the cluster clusters to obtain a target cluster;

and taking the centroid position of the target cluster as the offline position of the anchor point.

Optionally, after the taking the centroid position of the target cluster as the offline position of the anchor point, the method further includes:

calculating the offline position of the anchor point in a third preset period;

calculating the offset between the offline position of the anchor point in the second preset period and the offline position of the anchor point in a third preset period;

calculating the confidence coefficient of the offline position of the anchor point in a second preset period based on the offset;

and under the condition that the confidence coefficient of the offline position of the anchor point is greater than a first preset confidence coefficient threshold value, storing the offline position information of the anchor point.

Optionally, after inferring the current location of the target user based on the online location and the offline location of the anchor point, further comprising:

calculating a confidence level of the current location of the target user;

and returning the current position information of the target user under the condition that the confidence coefficient of the current position of the target user is greater than a second preset confidence coefficient threshold value.

According to another aspect of embodiments herein, there is provided a position estimation apparatus including:

the interactive data acquisition module is configured to acquire interactive data of a target user and an anchor point, wherein the interactive data carries identification information of the anchor point;

an identification ID generation module configured to extract the identification information of the anchor point and generate an identification ID of the anchor point according to the identification information under the condition that the interactive data does not contain the position information of the target user;

the online position calculation module is configured to collect interactive data of an anchor historical user and the anchor according to the identification ID of the anchor, extract position information of the anchor from the interactive data, and calculate the online position of the anchor according to the position information;

the offline position acquisition module is configured to acquire a prestored offline position of the anchor point according to the identification ID of the anchor point;

a current location inference module configured to infer a current location of the target user based on the online location and the offline location of the anchor point.

Optionally, the online position calculation module includes:

the first interactive data acquisition sub-module is configured to collect interactive data of at least one anchor point historical user and the anchor point in a first preset period according to the identification ID of the anchor point;

a location information determination submodule configured to extract associated location information of the at least one anchor point historical user from the interaction data as location information corresponding to the track point of the anchor point;

a variance calculation submodule configured to calculate a variance value of position information corresponding to each trajectory point of the anchor point;

and the online position calculation submodule is configured to calculate the online position of the anchor point according to the position information corresponding to each track point of the anchor point if the variance value is smaller than a preset variance threshold value.

Optionally, the interactive data between the anchor historical user and the anchor carries identification information of the anchor historical user;

the online location calculation module further comprises:

a generation time determination submodule configured to determine a generation time of interactive data of the anchor point historical user and the anchor point;

the information acquisition submodule is configured to acquire target position information with shortest update time of the anchor point historical user and the update time of the target position information with shortest update time according to the identification information of the anchor point historical user;

and the associated position information determining submodule is configured to use the target position information as the associated position information of the anchor point historical user if the update time of the target position information with the shortest update time and the generation time interval of the interactive data are within a preset time threshold range.

Optionally, the current location inference module comprises:

an offline position information obtaining sub-module configured to obtain, according to the identifier ID of the anchor point, a pre-stored offline position with the shortest anchor point update time and the update time of the offline position with the shortest anchor point update time;

the first judgment submodule is configured to judge whether the updating time of the offline position with the shortest updating time of the anchor point is within a preset time threshold range;

if yes, operating a first current position determining submodule;

the first current position determining submodule is configured to use the offline position with the shortest anchor point updating time as the current position of the target user.

Optionally, if the operation result of the first determining sub-module is negative, the following sub-modules are operated:

the track point number acquisition submodule is configured to acquire the number of the track points of the anchor points in a first preset period according to the identification ID of the anchor points;

the second judgment submodule is configured to judge whether the number of the track points of the anchor points in the first preset period is larger than a preset threshold value;

if yes, operating a second current position determining submodule;

the second current location determination submodule is configured to use the online location of the anchor point as the current location of the target user.

Optionally, if the operation result of the second determining sub-module is negative, the following sub-modules are operated:

the interactive data collection sub-module is configured to collect interactive data of the anchor historical user and the anchor with the shortest generation time according to the identification ID of the anchor;

a third current location determining sub-module configured to use the associated location information of the anchor historical user in the interaction data as the current location of the target user.

Optionally, the position inference apparatus further comprises: an offline position calculation module configured to:

Optionally, in a case that the number of clustered clusters after clustering is greater than 1, the offline position calculating module is further configured to:

acquiring the number of track points contained in each cluster;

Optionally, the position inference apparatus further comprises:

a confidence calculation module configured to calculate a confidence of the current location of the target user;

the information returning module is configured to return the current position information of the target user under the condition that the confidence degree of the current position of the target user is greater than a second preset confidence degree threshold value.

According to another aspect of embodiments herein, there is provided an electronic device comprising a memory, a processor and computer instructions stored on the memory and executable on the processor, the processor implementing the steps of the position inference method when executing the instructions.

According to another aspect of embodiments herein, there is provided a computer readable storage medium storing computer instructions which, when executed by a processor, implement the steps of the position inference method.

In the embodiment of the present specification, interactive data of a target user and an anchor point is obtained, where the interactive data carries identification information of the anchor point; under the condition that the interactive data does not contain the position information of the target user, extracting the identification information of the anchor point, and generating an identification ID of the anchor point according to the identification information; collecting interactive data of an anchor historical user and the anchor according to the identification ID of the anchor, extracting position information of the anchor from the interactive data, and calculating the online position of the anchor according to the position information; acquiring a prestored offline position of the anchor point according to the identification ID of the anchor point; inferring a current location of the target user based on the online location and the offline location of the anchor point.

In the embodiment of the specification, the interactive data of the user and the anchor point is obtained, the online position and the offline position of the anchor point are determined according to the relevant information carried in the interactive data, the current position of the target user is further deduced according to the online position and the offline position of the anchor point, the current position of the target user can be obtained without limitation on whether the user actively starts the positioning authority, the difficulty of obtaining the position of the target user by the server is reduced, and meanwhile, the user experience is improved.

Drawings

FIG. 1 is a flow chart of a method of location inference provided by an embodiment of the present application;

FIG. 2 is a flow chart of a position inference method applied to an actual scene according to an embodiment of the present application;

FIG. 3 is a diagram illustrating clustering in a location inference method according to an embodiment of the present application;

FIG. 4 is a schematic structural diagram of a position estimation device provided in an embodiment of the present application;

fig. 5 is a block diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. This application is capable of implementation in many different ways than those herein set forth and of similar import by those skilled in the art without departing from the spirit of this application and is therefore not limited to the specific implementations disclosed below.

The terminology used in the description of the one or more embodiments is for the purpose of describing the particular embodiments only and is not intended to be limiting of the description of the one or more embodiments. As used in one or more embodiments of the present specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It will be understood that, although the terms first, second, etc. may be used herein in one or more embodiments to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first can also be referred to as a second and, similarly, a second can also be referred to as a first without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.

First, the noun terms to which one or more embodiments of the present invention relate are explained.

And (3) mobile payment anchor point: in a mobile payment scene, a user can interactively complete payment and media of related services through a client, wherein the media include but are not limited to two-dimensional codes/bar codes, scanning guns, payment boxes, face scanners, bus and subway card readers, code scanning POS machines and the like. The mobile payment anchor point has an objective description in a physical space, and can expose the position and environmental information of a specific user when interacting with the user.

The following is a related term interpretation in the density clustering algorithm DBSCAN:

density clustering algorithm (DBSCAN): the closeness of the sample set is described based on a set of neighborhoods, and a parameter (e, MinPts) is used to describe how closely the samples of the neighborhood are distributed. Where e describes the neighborhood distance threshold for a sample, and MinPts describes the minimum number of sample points in the neighborhood for which the distance of a sample is e.

Core object: an object is said to be a core object if the number of sample points within the given object Ε domain is greater than or equal to the minimum number of sample points.

The direct density can reach: for sample set D, if sample point q is within e domain of p, and p is a core object, then object q is directly density reachable from object p.

The density can reach: for sample set D, given a string of sample points p1, p2... pn, p ═ p1, q ═ pn, object q is density reachable from object p, provided object pi is density reachable directly from pi-1.

Density connection: for any point o in the sample set D, if there is an object p to object o density reachable and an object q to object o density reachable, then the object q to object p density is connected.

The embodiment of the specification provides a position inference method. The present specification also relates to a position estimation apparatus, an electronic device, and a computer-readable storage medium, which are described in detail in the following embodiments one by one.

FIG. 1 shows a flow diagram of a method of location inference, including steps 102 through 110, according to an embodiment of the present description.

Step 102: and acquiring interactive data of a target user and an anchor point, wherein the interactive data carries identification information of the anchor point.

In an embodiment provided by the present specification, the position inference method may be applied to a mobile payment scenario, where the interaction data is data generated when a user interacts with a mobile payment anchor point, where the mobile payment anchor point includes, but is not limited to, a two-dimensional code/barcode, a scanning gun, a payment box, a face scanner, a bus and subway card swiping machine, a code scanning POS machine, and the like; the types of interactions include, but are not limited to, shopping code-scanning payments, bus card-swiping payments, shopping face-swiping payments, and the like.

Specifically, for example, in a mobile payment scenario, assuming that the mobile payment anchor point is a two-dimensional code of the store a, the target user B scans the two-dimensional code of the store a through a mobile phone terminal to pay after shopping in the store a, and the server acquires interactive data between the target user B and the mobile payment anchor point in real time after payment is completed. And when the payment is carried out, the mobile phone end of the target user B does not start the positioning function, so that the acquired interactive data does not contain the position information of the target user B. Specifically, the acquired interactive data are integrated based on a preset interactive data structure, wherein the preset interactive data structure is shown in table 1.

TABLE 1

An integration result obtained by integrating the acquired interactive data based on the preset interactive data structure is shown in table 2.

TABLE 2

The information available from table 2 includes: the transaction information between the user and the merchant is that the user completes shopping transaction through code scanning payment, the transaction ID is SJ1003, wherein the user is a target user B, the ID of the target user B is YH0123ZBC, the merchant is a shop A, the ID of the shop A is SH80245h, and the two-dimensional code or barcode value is 1234567890.

Step 104: and under the condition that the interactive data does not contain the position information of the target user, extracting the identification information of the anchor point, and generating the identification ID of the anchor point according to the identification information.

In an embodiment provided by this specification, when the interactive data does not include the location information of the target user, the location information of the target user needs to be inferred according to the location information of the anchor point, the identification information of the anchor point is first extracted from the interactive data, and then the identification ID of the anchor point is generated according to the identification information.

Specifically, still taking a mobile payment scenario as an example, as shown in table 2, if the mobile payment anchor point in table 2 is a two-dimensional code, the identification information of the two-dimensional code extracted from table 2 is 1234567890, and the identification information of the two-dimensional code is processed by using a digital digest algorithm to obtain the representation ID of the two-dimensional code, which is EWMX.

Step 106: and collecting interactive data of the anchor historical user and the anchor according to the identification ID of the anchor, extracting the position information of the anchor from the interactive data, and calculating the online position of the anchor according to the position information.

Specifically, the collecting of the interactive data between the anchor historical user and the anchor according to the identifier ID of the anchor, extracting the location information of the anchor from the interactive data, and calculating the online location of the anchor according to the location information may be implemented by:

In an embodiment provided by the present specification, taking the first preset period as 3 minutes as an example, and taking 3 minutes as a period, acquiring interactive data between the anchor historical user and the anchor, where a user carrying location information in the interactive data is regarded as the anchor historical user.

Taking a supermarket shopping payment scene as an example, assuming that the anchor point is a scanning gun, the user scans a two-dimensional code or a bar code displayed by the user by the scanning gun to complete payment after shopping in the supermarket M is completed, assuming that 3 users complete payment within 3 minutes, namely the server can collect 3 groups of interaction data within 3 minutes.

Specifically, the interactive data between the anchor historical user and the anchor carries identification information of the anchor historical user;

after interactive data of at least one anchor historical user and the anchor in a first preset period is collected according to the identifier ID of the anchor, before associated position information of the at least one anchor historical user is extracted from the interactive data and used as position information corresponding to the track point of the anchor, the position information of the anchor historical user needs to be added into the interactive data, and the method can be specifically realized through the following steps:

Following the above example, assuming that 3 users have completed payment within 3 minutes, the payment is respectively for user C, user D and user E, and after the payment is completed by the 3 users, the first set of interaction data, the second set of interaction data and the third set of interaction data are respectively generated, and the generation time is 2019.06.10.11: 12:03, 2019.06.10.11: 12:53 and 2019.06.10.11: 13:58. And after the server collects the 3 groups of interactive data, acquiring the target position information with the shortest updating time of the user according to the identification information of the user carried in the interactive data and acquiring the updating time of the target position information with the shortest updating time.

Assuming that the obtained target location information and the obtained update time of the user C, the user D, and the user E are the shortest: supermarket M (35.780287,104.1374349) at 2019.06.10.11: 12:03 update, subway station N (39.9049841,116.4266645) at 2019.06.10.10: 52:03 update, supermarket M (35.780287,104.1374349) at 2019.06.10.11: 03, updating, wherein the time intervals between the update time of the target position with the shortest update time of the user C and the update time of the user E and the generation time of the first group of interactive data and the third group of interactive data are respectively 0 minute and 2 minutes, and are both within the range of 5 minutes of a preset time threshold, so that the target position information supermarket M is used as the associated position information of the user C and added into the first group of interactive data, and the supermarket M is used as the associated position information of the user E and added into the third group of interactive data; in addition, the time interval between the update time of the target position with the shortest update time of the user D and the generation time of the second group of interactive data is 20 minutes, and is not within the range of 5 minutes of the preset time threshold, so that the associated position information of the user D cannot be added to the second group of interactive data.

In an embodiment provided by this specification, data including target position information of anchor point historical users in the interactive data is valid data, in the above example, the first group of interactive data and the third group of interactive data in 3 groups of interactive data collected by the server are valid data, and associated position information of the users is extracted from the first group of interactive data and the third group of interactive data and is used as position information corresponding to track points of the supermarket M scanning gun, that is, position information of two track points of the supermarket M scanning gun are (35.780287,104.1374349) and (35.780287,104.1374349), respectively; after track point position information is obtained, calculating a variance value of the position information of the two track points; and calculating the variance of the position information of the two track points of the scanning gun according to the variance formula to be 0, wherein the variance is less than a preset variance threshold value of 0.1, and then calculating the online position of the scanning gun according to the position information corresponding to the two track points of the scanning gun.

Specifically, since the position information of the two track points of the supermarket M scanning gun obtained in the above example is consistent, the (35.780287,104.1374349) can be directly used as the online position of the scanning gun.

In practical application, if the acquired anchor point track point position information is inconsistent, the online position of the anchor point can be calculated according to the formula (1).

Wherein l_aIs a set of position information corresponding to each track point of the anchor point in a first preset period,

being the online position of the anchor point, Δ t_iIs a position l_iThe time difference between the collection time and the calculation time, Δ t_kIs a position l_kThe time difference between the collection time and the calculation time.

Specifically, after the server acquires interactive data of a user and an anchor point, the target position information with the shortest update time of the user and the update time of the target position information are acquired according to user identification information in the interactive data, if the time interval between the update time and the time for acquiring the interactive data is within a preset time interval range, the associated position information of the user is added to the interactive data, the interactive data is stored in a database, and the interactive data with the target position information of the user added to the interactive data can be directly acquired from the database when the server acquires the interactive data of at least one anchor point historical user and the anchor point in a first preset period according to the identification ID of the anchor point.

In an embodiment provided by the present description, only the first preset period is 3 minutes, the target location information of the user is latitude and longitude information, the preset time threshold is 5 minutes, and the preset variance threshold is 0.1, which are taken as examples for explanation, in practical application, the above parameters and other example parameters related to the embodiment of the present description may be set according to actual needs, and are not limited herein.

Step 108: and acquiring the prestored offline position of the anchor point according to the identification ID of the anchor point.

In one embodiment provided by the present specification, the offline position of the anchor point is calculated by:

In addition, in case the number of clustered clusters after clustering is greater than 1, the following steps may be performed:

acquiring the number of track points contained in each cluster;

Specifically, for example, in a supermarket shopping payment scenario, assuming that the second preset period is 3 days, acquiring interaction data of at least one anchor historical user and the scanning gun within 3 days, assuming that the collected interaction data is 500 groups, adding location information of the anchor historical user in the collected 500 groups of interaction data, and referring to the method described in the above description for the specific adding method, details are not repeated here. Assuming that the effective interactive data to which the user position information is successfully added is 450 groups, extracting the associated position information of the at least one anchor point historical user from the interactive data to which the user position information is added as the position information corresponding to the track point of the scanning gun; clustering position information corresponding to a track point of a scanning gun by adopting a density clustering algorithm DBSCAN according to a preset neighborhood radius of 200m and the minimum sample point number of 10; judging the number of clustered clusters after clustering; if the number of the cluster clusters is equal to 1, the actual position of the scanning gun can be determined to be stable, and the centroid position of the cluster clusters can be directly used as the off-line position of the scanning gun; if the number of the clustering clusters is larger than 1, the number of the track points contained in each clustering cluster is obtained, the clustering cluster containing the largest number of the track points is determined as a target clustering cluster, and the centroid position of the target clustering cluster is used as the off-line position of the scanning gun.

In an embodiment provided in this specification, after the centroid position of the target cluster is taken as the offline position of the anchor point, the confidence level of the offline position needs to be calculated, which may specifically be implemented by the following steps:

calculating the offline position of the anchor point in a third preset period;

Specifically, following the above example, after the second preset period is 3 days, and the centroid position of the target cluster is taken as the offline position of the scanning gun in the second preset period, assuming that the third preset period is 2 days, the offline position of the scanning gun in the third preset period is determined by the same method, and an offset between the offline position of the scanning gun with the period of 3 days and the offline position of the scanning gun with the period of 2 days is calculated, and the confidence of the offline position of the scanning gun with the period of 3 days is calculated based on the offset, where the specific calculation formula is as follows as formula (2):

wherein, P_offlineAnd Z is a regularization parameter, and the value of Z in practical application can be set according to practical requirements without limitation.

Assuming the offset is 100m and the regularization parameter Z is 200m, P is calculated according to equation (2)_offlineIs 0.25, and assuming that the first preset confidence threshold is 0.1, the confidence P of the anchor point off-line position in the second preset period is_offlineAnd if the value is larger than 0.1, storing the offline position information of the anchor point.

In an embodiment provided in this specification, only the second preset period is 3 days, the third preset period is 2 days, and the first preset confidence threshold is 0.1, which are taken as examples for explanation, in practical applications, the above parameters and other example parameters related to the embodiment of this specification may be set according to actual needs, and are not limited herein.

Step 110: inferring a current location of the target user based on the online location and the offline location of the anchor point.

In one embodiment provided by the present specification, the current location inference method of the target user is shown in table 3.

TABLE 3

According to the position inference method shown in table 3, the conditions that the offline position and the online position of the anchor point satisfy are determined first, and the position inference method corresponding to the type to which the satisfied conditions belong is used to infer the position of the target user, which can be specifically realized by the following steps:

Specifically, assuming that the preset duration threshold is 5 days, and the update time of the offline position with the shortest anchor point update time is 2 days ago, the update time of the offline position with the shortest anchor point update time is within the preset duration threshold range, and if it is determined that the update time meets the condition of T1, the offline position of the anchor point is used as the current position information of the target user.

In addition, if the update time of the offline position with the shortest anchor update time is not within the preset time threshold range, the following operations are performed:

Specifically, if the update time of the offline position with the shortest update time of the anchor point is 6 days ago and is not within the range of 5 days of the preset duration threshold, whether the online position information of the anchor point meets the condition is judged. Assuming that the preset threshold is 5, the first preset period is 3 minutes, if the number of track points of the anchor point obtained within 3 minutes is 6, the number of the track points of the anchor point within the first preset period is greater than the preset threshold, judging that the number of the track points meets the condition of T2, and taking the online position of the anchor point within the first preset period as the current position information of the target user.

In addition, if the number of the trace points of the anchor point in the first preset period is not greater than the preset threshold, the following operations are executed:

Specifically, if the number of the track points of the anchor point within 3 minutes of the first preset period is 4 and is less than 5 preset thresholds, it is determined whether the associated position information of the user has been added to the interactive data with the shortest generation time. Assuming that the associated position information of the user is added to the interactive data with the shortest generation time, and judging that the associated position information meets the condition of T3, taking the associated position information of the anchor point historical user in the interactive data with the shortest generation time as the current position of the target user; if the associated position information of the user is not added in the interactive data with the shortest generation time, the current position of the target user cannot be inferred.

In one embodiment provided by the present specification, after the current location of the target user is inferred, a confidence level of the current location is calculated.

Specifically, if the offline position information of the anchor point meets the TI condition, the calculation formula of the confidence of the current position of the target user is shown in formula (3):

P_anchor＝0.9+0.1*P_offline (3)

wherein, P_anchorIs the confidence of the current position of the target user, P_offlineAnd the confidence coefficient of the anchor point off-line position in the second preset period.

Suppose P_offlineIf the value of (3) is 0.25, P can be obtained by calculation according to the formula (3)_anchorThe value of (D) is 0.925.

If the offline position information of the anchor point meets the condition of T2, the calculation formula of the confidence level of the current position of the target user is shown in equation (4):

wherein, P_anchorAs a confidence level of the current location of the target user,

the number of the track points of the anchor points in the first preset period, E_MIs a preset threshold value, Z, of the number of the track points of the anchor points in a first preset period_EIs a regularization parameter.

If the offline location information of the anchor point satisfies the condition of T3, the calculation formula of the confidence level of the current location of the target user is as shown in equation (5):

wherein, P_anchorAs confidence of the current position of the target user, Δ t_lastlocGenerating the time difference between the collection time and the calculation time of the associated position information of the anchor point historical user in the interactive data of the anchor point historical user and the anchor point with the shortest time.

Assuming that the second predetermined confidence threshold is 0.9, P is calculated according to equation (3)_anchorIf the value of the current position information is larger than the second preset confidence coefficient threshold value, returning the current position information of the target user.

In an embodiment provided by the present specification, an authorization page indicating whether to allow obtaining the location information of the location of the target user is shown to the user without using too many external devices or a server, and the location information of the target user can be reversely inferred by obtaining the location information of the anchor point interacting with the user, that is, the current location of the target user can be obtained without being limited by whether the user actively starts a positioning right, so that the difficulty of obtaining the location of the target user by the server is reduced, and the user experience is improved.

Fig. 2 shows a flowchart of the position inference method in an embodiment of the present specification, which is described by taking an anchor point as a bus imprinter as an example, and is applied to an actual scene, and includes steps 202 to 216.

Step 202: the method comprises the steps of obtaining interactive data of a target user and a bus card swiping machine, wherein the interactive data carries identification information of the bus card swiping machine.

In an embodiment provided by the specification, a target user X gets a bus after swiping a card through a bus swipe card machine through a mobile phone terminal, and a server acquires interactive data of the target user X and the bus swipe card machine in real time after swiping the card. Because the mobile phone end of the target user X does not start the positioning function while swiping the card, the acquired interactive data does not contain the position information of the target user X.

Step 204: judging whether the interactive data contains the position information of the target user or not; if not, go to step 206; if yes, the processing is not required.

Step 206: and extracting the identification information of the bus card swiping machine, and generating the identification ID of the bus card swiping machine according to the identification information.

In an embodiment provided by this specification, under the condition that the interactive data does not include the location information of the target user, the location information of the target user X needs to be inferred according to the location information of the bus card swiping machine, the identification information of the bus card swiping machine is extracted from the interactive data, and then the identification ID of the bus card swiping machine is generated according to the identification information.

Step 208: and collecting interactive data of the historical user and the bus card swiping machine according to the identification ID of the bus card swiping machine.

Step 210: and adding the position information of the historical user in the interactive data.

Specifically, the interactive data of the historical user and the bus card swiping machine carries the identification information of the historical user;

specifically, adding the location information of the historical user in the interactive data can be realized by the following steps:

determining the generation time of the interactive data of the historical user and the bus card swiping machine;

acquiring target position information with the shortest updating time of the historical user and the updating time of the target position information with the shortest updating time according to the identification information of the historical user;

and if the update time of the target position information with the shortest update time and the generation time interval of the interactive data are within a preset time threshold range, taking the target position information as the associated position information of the historical user.

Suppose that the time for generating interactive data after the historical user Y finishes swiping the card is 2019.06.10.19: 08, after the server collects the interactive data, acquiring the target position information with the shortest update time of the historical user Y according to the identification information of the historical user Y carried in the interactive data and acquiring the update time of the target position information with the shortest update time; suppose that the obtained target location information with the shortest update time of the historical user Y and the update time are respectively at 2019.06.10.19 at the bus station Z (52.579063, 78.6492105): 03 updating, wherein the time interval between the updating time of the target position with the shortest updating time of the historical user Y and the generating time of the interactive data is 1 minute and is within 5 minutes of the preset time threshold, and therefore the target position information bus station Z (52.579063,78.6492105) is taken as the associated position information of the historical user Y and added to the interactive data.

Step 212: and extracting the position information of the bus card swiping machine from the interactive data, and calculating the online position of the bus card swiping machine according to the position information.

Specifically, the step of extracting the position information of the bus card swiping machine from the interactive data and calculating the online position of the bus card swiping machine according to the position information can be realized by the following steps:

collecting interactive data of at least one historical user and the bus card swiping machine within 2 minutes according to the identification ID of the bus card swiping machine;

extracting the associated position information of the at least one historical user from the interactive data to be used as the position information corresponding to the track point of the bus card swiping machine;

calculating the variance value of the position information corresponding to each track point of the bus card swiping machine;

and if the variance value is smaller than a preset variance threshold value, calculating the online position of the bus card swiping machine according to the position information corresponding to each track point of the bus card swiping machine.

In one embodiment provided by the present specification, it is assumed that 2 historical users complete the card swiping within 2 minutes, that is, the server can collect 2 sets of interaction data within 2 minutes, and the target location information of the historical users included in the 2 sets of interaction data are (52.579063,78.6492105) and (52.579063,78.6492105), respectively.

Extracting the associated position information of the historical user from the 2 groups of interactive data as the position information corresponding to the two track points of the bus card swiping machine, namely the position information of the two track points is respectively (52.579063,78.6492105), and calculating the variance value of the position information of the two track points; and calculating the variance of the position information of the two track points of the bus card swiping machine according to the variance formula to be 0, wherein the variance is less than a preset variance threshold value of 0.1, and calculating the online position of the bus card swiping machine according to the position information corresponding to the two track points of the bus card swiping machine.

Specifically, if the acquired position information of the two track points of the bus card swiping machine is inconsistent, the online position of the bus card swiping machine can be calculated according to the formula (1).

Step 214: and acquiring the prestored off-line position of the bus card swiping machine according to the identification ID of the bus card swiping machine.

In an embodiment provided by the present specification, the offline position of the bus card swiping machine is calculated by the following method:

collecting interactive data of at least one historical user and the bus card swiping machine within 1 day according to the identification ID of the bus card swiping machine;

assuming that the collected interaction data is 20 sets, the location information of the historical user is added to the 20 sets of collected interaction data. Assuming that effective interactive data of the historical user position information is successfully added into 18 groups, extracting the associated position information of at least one historical user from the interactive data added with the historical user position information as the position information corresponding to the track point of the bus card swiping machine; clustering position information corresponding to a track point of a bus card swiping machine by adopting a density clustering algorithm DBSCAN according to a preset neighborhood radius of 1km and a minimum sample point number of 7; and if the number of the cluster clusters is equal to 1, determining that the actual position of the bus card swiping machine is relatively stable, and directly taking the mass center position of the cluster clusters as the off-line position of the bus card swiping machine.

A schematic diagram of a cluster is shown in fig. 3, where black points and gray points form a sample set, the black points are core points, the corresponding numbers are p1, p2, p3, and p4, the gray points are other sample points except the core points, the radius of the field is 1km, the minimum number of sample points in the neighborhood is 7, and clustering is performed by using a density clustering algorithm to obtain the cluster shown in fig. 3, where the density of p1 to p2 is directly reachable, the density of p2 to p3 is directly reachable, and the density of p3 to p4 is directly reachable, so that the density of p1 from p4 is reachable, and the densities of p1 to p4 are connected, and the density clustering algorithm DBSCAN aims to find the maximum set of density-connected objects, so that the cluster generated after sample clustering is shown in fig. 3, and the number of clusters is equal to 1.

In an embodiment provided by the present specification, the number of clustered clusters after clustering is equal to 1, so that the position of the centroid position q of a clustered cluster is directly used as the offline position of the bus card swiping machine. After the centroid position of the cluster is taken as the off-line position of the bus card swiping machine, the confidence coefficient of the off-line position needs to be calculated, and the method can be specifically realized through the following steps:

calculating the off-line position of the bus card swiping machine within 2 days;

calculating the offset between the offline position of the bus card swiping machine within 1 day and the offline position of the bus card swiping machine within 2 days;

calculating the confidence coefficient of the off-line position of the bus card swiping machine within 1 day based on the offset;

and under the condition that the confidence coefficient of the offline position of the bus card swiping machine is greater than a third preset confidence coefficient threshold value, storing the offline position information of the bus card swiping machine.

Specifically, after the centroid position of the cluster is taken as the offline position of the bus card swiping machine within 1 day, the offline position of the bus card swiping machine within 2 days is determined by the same method, the offset between the offline position of the bus card swiping machine taking 1 day as the period and the offline position of the bus card swiping machine taking 2 days as the period is calculated, the confidence coefficient of the offline position of the bus card swiping machine taking 1 day as the period is calculated based on the offset, and the specific calculation formula is as shown in formula (2).

And if the confidence coefficient of the offline position of the bus card reading machine taking 1 day as the period is greater than a third preset confidence coefficient threshold value, storing the offline position information of the bus card reading machine.

In an embodiment provided by the present description, only the clustering cluster shown in fig. 3 is schematically illustrated, and in practical application, the minimum sample point number, the neighborhood radius, the core point, and the centroid position of the clustering cluster are all determined according to practical situations, which is not limited herein.

Step 216: and deducing the current position of the target user based on the online position and the offline position of the bus card swiping machine.

And judging conditions met by the offline position and the online position of the bus card swiping machine, and deducing the position of the target user according to a position deducing method corresponding to the type of the met conditions.

Specifically, according to the identification ID of the bus card swiping machine, the prestored offline position with the shortest update time of the bus card swiping machine and the update time of the offline position with the shortest update time of the bus card swiping machine are obtained;

judging whether the update time of the off-line position with the shortest update time of the bus card swiping machine is within a preset time threshold range;

and if so, taking the off-line position with the shortest updating time of the bus card swiping machine as the current position of the target user.

Assuming that the preset time length threshold is 5 days, and the update time of the off-line position with the shortest update time of the bus card swiping machine is 2 days before, the update time of the off-line position with the shortest update time of the bus card swiping machine is within the preset time length threshold range, and the off-line position of the bus card swiping machine is taken as the current position information of the target user.

Specifically, if the offline position information of the bus card swiping machine meets the TI condition, the calculation formula of the confidence coefficient of the current position of the target user is shown as formula (3).

In an embodiment provided by the specification, by acquiring the interaction data of the user and the bus card swiping machine, and determining the online and offline positions of the bus card swiping machine according to the relevant information carried in the interaction data, the current position of the target user is inferred through the online and offline positions of the bus card swiping machine and the preset position inference rule, the current position of the target user can be acquired without using too many external devices and without opening a positioning authority by the user, the difficulty of acquiring the position of the target user by a server is reduced, and the user experience is improved.

Corresponding to the above method embodiment, the present specification also provides an embodiment of a position inference device, and fig. 4 shows a schematic structural diagram of the position inference device according to an embodiment of the present specification. As shown in fig. 4, the apparatus includes:

an interactive data obtaining module 402, configured to obtain interactive data between a target user and an anchor point, where the interactive data carries identification information of the anchor point;

an identification ID generation module 404, configured to, in a case that the interactive data does not include the location information of the target user, extract the identification information of the anchor point, and generate an identification ID of the anchor point according to the identification information;

an online position calculation module 406, configured to collect interaction data of an anchor historical user and the anchor according to the identification ID of the anchor, extract position information of the anchor from the interaction data, and calculate an online position of the anchor according to the position information;

an offline position obtaining module 408 configured to obtain a pre-stored offline position of the anchor point according to the identification ID of the anchor point;

a current location inference module 410 configured to infer a current location of the target user based on the online location and the offline location of the anchor point.

Optionally, the online position calculation module includes:

the online location calculation module further comprises:

Optionally, the current location inference module comprises:

if yes, operating a first current position determining submodule;

if yes, operating a second current position determining submodule;

Optionally, if the operation result of the second determination sub-module is negative, the following sub-steps are performed:

acquiring the number of track points contained in each cluster;

Optionally, the offline position calculation module is further configured to:

calculating the offline position of the anchor point in a third preset period;

Optionally, the position inference apparatus further comprises:

The above is a schematic configuration of a position estimation device of the present embodiment. It should be noted that the technical solution of the apparatus and the technical solution of the position estimation method described above belong to the same concept, and details that are not described in detail in the technical solution of the electronic device can be referred to the description of the technical solution of the position estimation method described above.

Fig. 5 shows a block diagram of an electronic device 500 according to an embodiment of the present description. The components of the electronic device 500 include, but are not limited to, a memory 510 and a processor 520. Processor 520 is coupled to memory 510 via bus 530, and database 550 is used to store data.

The electronic device 500 also includes an access device 540, the access device 540 enabling the electronic device 500 to communicate via one or more networks 560. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. The access device 540 may include one or more of any type of network interface, e.g., a Network Interface Card (NIC), wired or wireless, such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.

In one embodiment of the present description, the above-mentioned components of the electronic device 500 and other components not shown in fig. 5 may also be connected to each other, for example, through a bus. It should be understood that the block diagram of the electronic device shown in fig. 5 is for exemplary purposes only and is not intended to limit the scope of the present disclosure. Those skilled in the art may add or replace other components as desired.

The electronic device 500 may be any type of stationary or mobile electronic device, including a mobile computer or mobile electronic device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), a mobile phone (e.g., smartphone), a wearable electronic device (e.g., smartwatch, smartglasses, etc.), or other type of mobile device, or a stationary electronic device such as a desktop computer or PC. The electronic device 500 may also be a mobile or stationary server.

Wherein processor 520 is configured to execute the following computer-executable instructions:

Optionally, the offline position of the anchor point is calculated by:

acquiring the number of track points contained in each cluster;

calculating the offline position of the anchor point in a third preset period;

calculating a confidence level of the current location of the target user;

The above is a schematic scheme of an electronic device of the present embodiment. It should be noted that the technical solution of the electronic device and the technical solution of the position estimation method belong to the same concept, and for details that are not described in detail in the technical solution of the electronic device, reference may be made to the description of the technical solution of the position estimation method.

An embodiment of the present application also provides a computer readable storage medium storing computer instructions that, when executed by a processor, implement the steps of the position inference method as described above.

The above is an illustrative scheme of a computer-readable storage medium of the present embodiment. It should be noted that the technical solution of the storage medium is the same concept as the technical solution of the above-mentioned position estimation method, and for details that are not described in detail in the technical solution of the storage medium, reference may be made to the description of the technical solution of the above-mentioned position estimation method.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The computer instructions comprise computer program code which may be in the form of source code, object code, an executable file or some intermediate form, or the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.

It should be noted that, for the sake of simplicity, the above-mentioned method embodiments are described as a series of acts or combinations, but those skilled in the art should understand that the present application is not limited by the described order of acts, as some steps may be performed in other orders or simultaneously according to the present application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are preferred embodiments and that the acts and modules referred to are not necessarily required in this application.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

The preferred embodiments of the present application disclosed above are intended only to aid in the explanation of the application. Alternative embodiments are not exhaustive and do not limit the invention to the precise embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the application and the practical application, to thereby enable others skilled in the art to best understand and utilize the application. The application is limited only by the claims and their full scope and equivalents.

Claims

1. A method of location inference, comprising:

collecting interactive data of a historical user and the anchor point according to the identification ID of the anchor point, extracting position information of the anchor point from the interactive data, and calculating the online position of the anchor point according to the position information;

2. The method of claim 1, wherein the collecting interaction data of historical users and the anchor point according to the identification ID of the anchor point, extracting location information of the anchor point from the interaction data, and calculating the online location of the anchor point according to the location information comprises:

collecting interactive data of at least one historical user and the anchor point in a first preset period according to the identification ID of the anchor point;

extracting the associated position information of the at least one historical user from the interactive data as the position information corresponding to the track point of the anchor point;

3. The method according to claim 2, wherein the interactive data between the historical user and the anchor point carries identification information of the historical user;

after the interactive data between the at least one historical user and the anchor point in a first preset period is collected according to the identifier ID of the anchor point, before the associated location information of the at least one historical user is extracted from the interactive data as the location information corresponding to the track point of the anchor point, the method further includes:

determining the generation time of the interactive data of the historical user and the anchor point;

4. The method of claim 1, wherein inferring the current location of the target user based on the online location and the offline location of the anchor point comprises:

5. The method of claim 4, wherein if the update time of the offline location with the shortest anchor update time is not within a preset duration threshold, performing the following operations:

6. The method according to claim 5, wherein if the number of the trace points of the anchor point in the first preset period is not greater than a preset threshold, the following operations are performed:

collecting and generating the interactive data of the historical user with the shortest time and the anchor point according to the identification ID of the anchor point;

and taking the associated position information of the historical user in the interactive data as the current position of the target user.

7. The method of claim 1, wherein the offline position of the anchor point is calculated by:

collecting interactive data of at least one historical user and the anchor point in a second preset period according to the identification ID of the anchor point;

8. The method of claim 7, wherein in the case that the number of clustered clusters after clustering is greater than 1, the method further comprises:

acquiring the number of track points contained in each cluster;

9. The method of claim 8, wherein after the taking the centroid position of the target cluster as the offline position of the anchor point, further comprising:

calculating the offline position of the anchor point in a third preset period;

10. The method of claim 1, wherein after inferring the current location of the target user based on the online location and the offline location of the anchor point, further comprises:

calculating a confidence level of the current location of the target user;

11. A position estimation device, comprising:

the online position calculation module is configured to collect interactive data of a historical user and the anchor point according to the identification ID of the anchor point, extract position information of the anchor point from the interactive data, and calculate the online position of the anchor point according to the position information;

12. The apparatus of claim 11, wherein the online location calculation module comprises:

the first interactive data acquisition sub-module is configured to collect interactive data of at least one historical user and the anchor point in a first preset period according to the identification ID of the anchor point;

a location information determination submodule configured to extract associated location information of the at least one historical user from the interaction data as location information corresponding to the locus point of the anchor point;

13. The apparatus according to claim 12, wherein the interactive data between the historical user and the anchor point carries identification information of the historical user;

the online location calculation module further comprises:

a generation time determination submodule configured to determine a generation time of the interaction data of the historical user and the anchor point;

the information acquisition submodule is configured to acquire target position information with the shortest update time of the historical user and the update time of the target position information with the shortest update time according to the identification information of the historical user;

and the associated position information determining submodule is configured to use the target position information as the associated position information of the historical user if the update time of the target position information with the shortest update time and the generation time interval of the interactive data are within a preset time threshold range.

14. The apparatus of claim 11, wherein the current location inference module comprises:

if yes, operating a first current position determining submodule;

15. The apparatus of claim 14, wherein if the first determining sub-module is not operated, then the following sub-modules are operated:

if yes, operating a second current position determining submodule;

16. The apparatus of claim 15, wherein if the second determination sub-module is not operated, then operating the following sub-modules:

the interactive data collection sub-module is configured to collect interactive data of the historical user and the anchor point with the shortest generation time according to the identification ID of the anchor point;

a third current location determination submodule configured to use the associated location information of the historical user in the interaction data as the current location of the target user.

17. The apparatus of claim 11, further comprising: an offline position calculation module configured to:

18. The apparatus of claim 17, wherein in the case that the number of clustered clusters after clustering is greater than 1, the offline position calculation module is further configured to:

acquiring the number of track points contained in each cluster;

19. The apparatus of claim 11, further comprising:

20. An electronic device, comprising:

a memory, a processor;

the memory is to store computer-executable instructions, and the processor is to execute the computer-executable instructions to:

21. A computer-readable storage medium storing computer instructions, which when executed by a processor, perform the steps of the method of any one of claims 1 to 10.