CN110136258B - Method, device, equipment and storage medium for determining environment space identifier - Google Patents
Method, device, equipment and storage medium for determining environment space identifier Download PDFInfo
- Publication number
- CN110136258B CN110136258B CN201910405894.5A CN201910405894A CN110136258B CN 110136258 B CN110136258 B CN 110136258B CN 201910405894 A CN201910405894 A CN 201910405894A CN 110136258 B CN110136258 B CN 110136258B
- Authority
- CN
- China
- Prior art keywords
- space
- subspace
- determining
- environment
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Computer Graphics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method, a device and equipment for determining an environment space identifier and a computer readable storage medium. In the scheme, the space outline of the complex space environment is represented by the Thiessen polygon, so that the space outline of the complex space environment has the property of the Thiessen polygon, and after the geometric form description model is obtained based on the Thiessen polygon, the space mark of the position of the user can be quickly and accurately searched through the geometric form description model, a large amount of manpower and material resources are saved, the calculation resources are reduced, and the identification accuracy is improved.
Description
Technical Field
The present invention relates to the field of environment space identifier determination technologies, and in particular, to a method, an apparatus, a device, and a computer-readable storage medium for determining an environment space identifier.
Background
With the development and rapid update and deployment of global positioning systems and wireless local area networks, location-based services provide convenience to people, and people find that location-based services can bring quite convenient services and better user experience, thus increasing the demand for location services. The more concerned about the location-based service and system is a mapping supply system which utilizes a positioning technology to determine the location of a user and then maps environmental space information, namely, geographical identification or surrounding building identification information of the location of the user as context. Distinguishing the identity of different regional spaces in a complex environment, whether indoor or outdoor, is of great help to location-based services and systems. The requirement for distinguishing the complex space environment identification is particularly obvious in places such as airports, large amusement parks and large shopping centers.
In combination with the above situation, it can be seen that researching how to accurately identify the identification of the environmental space where the user is located is a very potential research field. Taking a shopping mall as an example, the shops where the users are located are quickly identified in the shopping mall according to the user positioning information, and the personalized information pushing can be carried out on the users in real time by combining a situation recommendation system. The traditional method for identifying the environment space identifier is to obtain the user position information by using the existing positioning technology (GPS positioning technology, WLAN indoor positioning technology), and identify the environment space identifier where the user is located by using a ranging method. However, the identification based on the ranging method is not accurate, because there may be a situation that the distance between one position and a plurality of different subspaces is equal, and thus the identification of the environment space identifier is wrong.
Disclosure of Invention
The invention aims to provide a method, a device and equipment for determining an environment space identifier and a computer readable storage medium, so as to accurately determine the environment space identifier of a user.
In order to achieve the above object, the present invention provides a method for determining an environmental space identifier, including:
obtaining historical user position data in a complex space environment;
determining Thiessen polygons representing the adjacency relation of each subspace in the complex space environment by utilizing the historical user position data, and generating a space topological relation model based on the Thiessen polygons;
according to the adjacency relation of each subspace in the space topological relation model, a geometric form description model for identifying the environment space identification is established;
and acquiring the current position information of the target user, and determining the space identifier of the subspace where the target user is located according to the position information and the geometric form description model.
Optionally, determining, by using the historical user location data, a thiessen polygon representing a adjacency relationship of each subspace in the complex spatial environment, including:
determining a plurality of subspaces of the complex space environment according to the position information of each user in different areas in the historical user position data;
calculating the mean value of the position information in each subspace, and generating the space object position of each subspace;
generating discrete points of each subspace according to the space object position of each subspace and the space identification of the subspace;
and determining a Thiessen polygon corresponding to the complex space environment by using the discrete points of each subspace.
Optionally, the generating a spatial topological relation model based on the thieson polygon includes:
determining the adjacency relation among the subspaces of the Thiessen polygon by utilizing the adjacency relation of the subspaces of any two discrete points in the Thiessen polygon;
and generating a spatial topological relation model according to the adjacency relation and discrete points of each subspace in the Thiessen polygon.
Optionally, creating a geometric description model for identifying an environmental space identifier according to the adjacency relationship of each subspace in the spatial topological relationship model, including:
creating classifiers for identifying environment space identifiers, wherein the number of the classifiers is the same as the number of the adjacency relations in the space topological relation model;
and training the classifier according to the discrete points of each subspace in the spatial topological relation model to generate the geometric form description model.
Optionally, the obtaining current position information of the target user, and determining a space identifier of a subspace where the target user is located according to the position information and the geometric description model includes:
inputting the position information into the geometric description model;
sequentially judging the position of a target space object closest to the position information through a classifier of the geometric form description model;
and taking the space identifier corresponding to the target space object position as the space identifier of the subspace where the target user is located.
In order to achieve the above object, the present invention further provides an apparatus for determining an environmental space identifier, including:
the position data acquisition module is used for acquiring historical user position data in a complex space environment;
a Thiessen polygon creation module for determining a Thiessen polygon representing an adjacency relationship of each subspace within the complex spatial environment using the historical user location data;
the space topological relation model generating module is used for generating a space topological relation model based on the Thiessen polygon;
the geometric form description model creating module is used for creating a geometric form description model for identifying the environmental space identification according to the adjacency relation of each subspace in the space topological relation model;
and the space identifier recognition module is used for acquiring the current position information of the target user and determining the space identifier of the subspace where the target user is located according to the position information and the geometric form description model.
Optionally, the thiessen polygon creating module includes:
a subspace determination unit, configured to determine, according to location information of each user in different regions in the historical user location data, a plurality of subspaces of the complex space environment;
the space object position calculating unit is used for calculating the average value of the position information in each subspace and generating the space object position of each subspace;
the discrete point generating unit is used for generating discrete points of each subspace according to the space object position of each subspace and the space identification of the subspace;
and the Thiessen polygon generating unit is used for determining the Thiessen polygon corresponding to the complex space environment by using the discrete points of each subspace.
Optionally, the spatial identifier identifying module includes:
a position input unit for inputting the position information into the geometric shape description model;
the target space object position determining unit is used for sequentially judging the target space object position closest to the position information through the classifier of the geometric form description model;
and the space identification determining unit is used for taking the space identification corresponding to the target space object position as the space identification of the subspace where the target user is located.
To achieve the above object, the present invention further provides an apparatus for determining an environmental space identifier, including:
a memory for storing a computer program;
a processor for implementing the steps of the method for determining an identification of an environmental space as described above when executing the computer program.
To achieve the above object, the present invention further provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the method for determining an environment space identifier as described above.
According to the above scheme, the method for determining the environmental space identifier provided by the embodiment of the invention comprises the following steps: obtaining historical user position data in a complex space environment; determining Thiessen polygons representing the adjacent relation of each subspace in the complex space environment by utilizing the historical user position data, and generating a space topological relation model based on the Thiessen polygons; according to the adjacency relation of each subspace in the space topological relation model, a geometric form description model for identifying the environment space identification is established; and acquiring the current position information of the target user, and determining the space identifier of the subspace where the target user is located according to the position information and the geometric form description model.
Therefore, after the geometric form description model is obtained based on the Thiessen polygon, the spatial identification of the position where the user is located can be quickly and accurately found through the geometric form description model, a large amount of manpower and material resources are saved, the calculation resources are reduced, and the identification accuracy is improved.
The invention also discloses a device and equipment for determining the environmental space identifier and a computer readable storage medium, and the technical effects can be realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic diagram of a conventional distance measurement method for identifying a space identifier;
fig. 2 is a schematic flowchart of a method for determining an environmental space identifier according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a spatial topological relation model generated by partitioning a space using a voronoi diagram according to an embodiment of the present invention;
FIG. 4 is a connectivity graph corresponding to the topological relationship model of FIG. 3, as disclosed in an embodiment of the present invention;
FIG. 5 is a schematic diagram of a classifier structure organized by a conventional DAG-SVM algorithm;
FIG. 6 is a schematic diagram of a topology of an improved DAG-SVM algorithm disclosed in the embodiments of the present invention;
FIG. 7 is a schematic view of a triangulation network of the identification space disclosed in the embodiments of the present invention;
FIG. 8 is a Thiessen polygon generated based on triangulation disclosed in an embodiment of the present invention;
fig. 9 is a schematic structural diagram of an apparatus for determining an environmental space identifier according to an embodiment of the present invention;
fig. 10 is a schematic structural diagram of an apparatus for determining an environmental space identifier according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
At present, the traditional method for identifying the environment space identifier is to use the existing positioning technology (GPS positioning technology, WLAN indoor positioning technology) to obtain the user location information, and use a ranging method to identify the environment space identifier where the user is located. That is to say, when the space identifier where the user is located is identified in the conventional manner, the position information obtained by positioning is mainly used for reasoning. However, the existing positioning technology is used for positioning the user, and a distance measurement method is adopted when the space identifier is identified, so that confusion and identification errors occur in the process of identifying the space identifier due to irregular arrangement of the space.
Referring to fig. 1, a schematic diagram of identifying a space identifier by using a conventional ranging method is shown; as shown in fig. 1, the positions of the spaces a, B, C, D, E, and F are determined, the position information of the user a, the user B, the user C, and the user D is obtained by the positioning technology, and if the conventional ranging method is used, the spatial identifiers of the users a and B will be identified incorrectly, while the spatial identifiers of the users C and D will be confused and incorrect.
To solve the problem, the embodiment of the invention discloses a method, a device, equipment and a computer readable storage medium for determining an environment space identifier, wherein a geometric form description model is drawn by using position information, the space identifier where a user is located is determined by the geometric form description model, and the error rate at a multi-space junction is reduced, so that the environment space identifier of the user is accurately determined.
Referring to fig. 2, a method for determining an environmental space identifier according to an embodiment of the present invention includes:
s101, obtaining historical user position data in a complex space environment;
in this embodiment, the complex space environment may refer to a space having a plurality of subspaces adjacent to each other, for example: a large shopping mall is understood as a complex space environment, and each shop in the mall can be understood as a subspace in the complex space environment; furthermore, the historical user position data acquired by the scheme can be understood as position data uploaded by a plurality of users in a certain period of time in the market, and the position data can be obtained by positioning the indoor positions of the users by using a wifi indoor positioning technology. From the plurality of historical user location data, a spatial profile of the complex spatial environment may be obtained.
S102, determining Thiessen polygons representing the adjacent relation of each subspace in the complex space environment by using the historical user position data, and generating a space topological relation model based on the Thiessen polygons;
it should be noted that, in the present solution, the adjacency relation of each subspace in the two-dimensional space in the complex space environment is expressed by the spatial topological relation model, there is no intersection relation in the complex space environment, and the spatial operation is not affected by the intersection relation, so only the spatial adjacency relation is considered in the present solution. Set P = { T) using subspace composition n And (5) representing a complex space environment P, and describing a space topological relation model by using an undirected graph G = < T, E >. The Voronoi diagram is a Thiessen polygon, is a geometric structure widely applied to space segmentation, can clearly express the proximity relation between entities in a plane space, and is an effective tool for solving the geometric problem. A Voronoi diagram consists of spatial objects and Voronoi regions corresponding thereto, which represent a collection of points on a plane closer to the objects than to other objects.
Referring to fig. 3, a schematic diagram of a spatial topological relation model generated by segmenting a space by using a voronoi diagram disclosed in this embodiment is shown, and as can be seen from fig. 3, a complex space environment is divided into 5 subspaces: t = { T = { (T) 1 ,T 2 ,T 3 ,T 4 ,T 5 And the adjacency between subspaces can be expressed as:
E＝{(T 1 ,T 2 ),(T 1 ,T 3 ),(T 1 ,T 4 ),(T 1 ,T 5 ),(T 2 ,T 3 ),(T 3 ,T 4 ),(T 4 ,T 5 ) The spatial topological relation model of the complex spatial environment can be expressed as: g = < T, E >.
As can be seen from the spatial topological relation model, T 1 And T 2 ,T 3 ,T 4 ,T 5 An abutting relationship exists. T is 2 And T 1 、T 3 Has an adjacent relation with T 4 、T 5 There is no adjacency, so T 1 Is followed by the boundary T 2 ,T 3 ,T 4 ,T 5 All relate to, in the same way as T 2 Determination of spatial boundaries only with T 1 、T 3 It is related. It can be seen from the figure that the number of boundaries of each space is related to the number of spaces adjacent to it, which is also one of the properties of the voronoi diagram. Referring to fig. 4, a connectivity graph corresponding to the topological relation model in fig. 3 is provided for this embodiment.
S103, establishing a geometric form description model for identifying the environment space identification according to the adjacency relation of each subspace in the space topological relation model;
according to the adjacency relation of each subspace in the space topological relation model, a geometric form description model for identifying the environment space identification is created, and the method comprises the following steps:
creating classifiers for identifying environment space identifiers, wherein the number of the classifiers is the same as the number of the adjacent relations in the space topological relation model;
and training the classifier according to discrete points of each subspace in the spatial topological relation model to generate the geometric form description model.
It should be noted that, the two-dimensional geometric description of the indoor space is usually a closed geometric figure, and the number of the adjacent spaces of the subspace object determines the number of the sides (such as triangle, quadrangle, etc.) of the geometric figure. The geometry description model describes the geometry of the subspace using a geometry composed of the classification boundaries of the subspace and the adjacent space, and therefore, the problem is translated into a multi-classification task. Currently, a DAG-SVM algorithm is generally used to construct a classifier for the classification problem of N categories, where the DAG-SVM constructs N × (N-1) classifiers, each 2-category SVM classifier constitutes a node of a directed acyclic graph, and each node is a 2-category SVM classifier that maximizes an edge. For example: if the scheme has 5 subspaces, the problem is a classification problem of 5 categories, the topological structure of the corresponding DAG-SVM algorithm is shown in FIG. 5, and FIG. 5 is a schematic diagram of the classifier structure organized by the conventional DAG-SVM algorithm.
It can be seen that, when a conventional DAG-SVM algorithm is used to organize each classifier of 2 classes for a 5-class problem, 10 SVM classifiers need to be constructed, and some 2 classes that are far apart or have no correlation will also construct classifiers, which wastes unnecessary computing resources, for example: space T 2 And a space T 5 Not adjacent, classifier C2 in fig. 5 may not be created at this time.
Namely: spaces with adjacency relations are necessary in the classification problem, but since spaces with separated relations are far away from each other, the calculation in the classification task does not have great influence, so in the embodiment, an improved DAG-SVM classification method based on a space topological relation model is provided, and the method removes 2 types of SVM classification nodes of separated spatial relations based on the adjacency relations of the spaces, so that the number of nodes for constructing the classifier is reduced; in the classifier structure diagram shown in fig. 5, since the adjacent relationship exists:
E＝{(T 1 ,T 2 ),(T 1 ,T 3 ),(T 1 ,T 4 ),(T 1 ,T 5 ),(T 2 ,T 3 ),(T 3 ,T 4 ),(T 4 ,T 5 ) There are only 7 adjacency relations, so in this embodiment, for a 5-class classification problem, only 7 2-class classifier nodes need to be constructed, see fig. 6, which is a schematic diagram of a topology structure of the improved DAG-SVM algorithm provided in this embodiment, thereby reducing the expense of computing resources on the basis of maintaining classification accuracy.
It should be noted that, in the process of describing the spatial geometry, all path classifiers of a certain class need to be used as boundaries of the space, which is done to ensure correct classification and simultaneously restore the spatial geometry to the maximum extent, and consider that all correctly classified paths need to be summarized in a field scene, so that the spatial geometry description is real and effective.
As shown in fig. 6, when determining the category 1, the correct category 1 needs to pass through 4 nodes c1-c2-c3-c7, and only one path is needed to obtain a correct classification result. Therefore, the geometry of the T1 space is described by using the geometry mapped by the T1= { C1-C2-C3-C7} classifier, and it can be seen from the spatial topological relation in fig. 3 that the path classifier C1 is used to determine whether the path classifier is of class 1 or class 5, so that C1 is the boundary classifier of the space T1 and the space T5, and similarly, C2 is the boundary classifier of the space T1 and the space T4, C3 is the boundary classifier of the space T1 and the space T3, and C7 is the boundary classifier of the space T1 and the space T2, and the number of classifiers in the T1 space can reflect the number of adjacent relations in the T1 space, so as to reflect the geometry of the space, as: the T1 space has four classifiers, which means that the T1 space has four adjacent spaces, so that the geometric form of each space can be reflected through the connecting space of each space.
It can be seen that the outline of each subspace can be described through the geometric shape description model, and the identification of each space can also be described, so that the defined subspace can transmit the identification information of the space while retaining the geometric characteristics of the outline of the space. The indoor space information is rich and diverse, the indoor space model is divided into layers with different positions and geometries to improve the expression capacity of the model, and more information is integrated into the model, so that the model can qualitatively and quantitatively express the indoor space to support different types of applications and services.
It should be noted that, after determining the geometric description model corresponding to the complex spatial environment, training each classifier in the model is required, the training process may be performed through discrete points of each subspace, where the discrete points include spatial object positions and spatial identifiers of the space where the discrete points are located, and after training, each classifier can identify the spatial identifiers of the positions where the users are located.
S104, obtaining the current position information of the target user, and determining the space identification of the subspace where the target user is located according to the position information and the geometric form description model.
The method for obtaining the current position information of the target user and determining the space identifier of the subspace where the target user is located according to the position information and the geometric form description model comprises the following steps:
inputting the position information into the geometric shape description model;
sequentially judging the positions of the target space objects closest to the position information through the classifier of the geometric form description model;
and taking the space identifier corresponding to the target space object position as the space identifier of the subspace where the target user is located.
It should be noted that the three processes of S101 to S103 may be processed in an offline stage, that is, in the present scheme, an environment map may be established in the offline stage by using historical user location data provided by crowdsourcing data, where the environment map is an environment map generated by the geometric form description model, and is capable of reflecting the adjacency relation of different subspaces and realizing identification of a spatial identifier of a location where a user is located.
In the current stage of S104, after the position of the user is obtained, the position may be input into a geometric description model, and the spatial identifier of the user is classified by each classifier in the model; for example: the space identifier recognition is performed on the user M in fig. 3 according to the classifier topology shown in fig. 6, first, the classifier c1 determines, according to the position of the user M, that the distance between the position of the user M and the space object position of T5 is smaller than the distance between the position of the user M and the space object position of the space T1, so that the user M belongs to the category 5, and continues to perform the determination by the classifier c4, because the distance between the position of the user M and the space object position of the space T4 is smaller than the distance between the position of the user M and the space object position of the space T5, the user M belongs to the category 4, that is, the space identifier of the position of the user M is the space identifier of the space T4.
In conclusion, in the scheme, the properties of the Thiessen polygons are utilized in the process of calculating the space identifiers, so that when the geometric form description model identifies the space identifiers, the properties of the Thiessen polygons can be utilized, the space identifiers where the users are located can be quickly and accurately identified on the map, a large amount of manpower and material resources are saved, the calculation resources are reduced, and the identification accuracy is improved. The visual map enables the identification of the space where the user is located to be visual and simple.
Based on the foregoing embodiment, in this embodiment, the determining, by using the historical user location data, a thiessen polygon representing an adjacency relationship of each subspace in the complex spatial environment in S102 includes:
determining a plurality of subspaces of the complex space environment according to the position information of each user in different areas in the historical user position data;
calculating the mean value of the position information in each subspace, and generating the space object position of each subspace;
generating discrete points of each subspace according to the space object position of each subspace and the space identification of the subspace; and determining a Thiessen polygon corresponding to the complex space environment by using the discrete points of each subspace.
The generating a spatial topological relation model based on the Thiessen polygon in S102 includes:
determining the adjacency relation among the subspaces of the Thiessen polygon by utilizing the adjacency relation of the subspaces of any two discrete points in the Thiessen polygon;
and generating a spatial topological relation model according to the adjacency relation and discrete points of each subspace in the Thiessen polygon.
In the embodiment, a rapid construction Thiessen polygon algorithm based on a D-triangulation network is used for determining the adjacent relation of each subspace, the complex environment space is divided, so that a topological relation model of each subspace in the complex space environment is constructed, and an undirected graph G = < T, E > is used for storing and displaying the topological relation model of the environment. The activity positions of the users in the space are random, but do not exceed the boundary (such as a wall) of the space, that is, the historical user position data can reflect the position information of a plurality of users in a certain period of time, so that the scheme can describe the outline of the complex space environment through the position information of a plurality of users in the complex space environment, namely, a plurality of subspaces of the complex space environment are determined. By the method, the complex space environment can be divided into a plurality of subspace sets according to actual conditions, and from the geometric shape of the subspace, the topological relation and the geometric form of the subspace in the complex space environment and the relation with the environment can be described. It should be noted that, when determining each subspace, the adjacent relationship and the boundary of the subspace can also be determined by a professional through manual surveying and field measurement, so as to determine each subspace in the complex space environment.
Further, in the scheme, when the spatial object position of each subspace of voronoi is determined, the average value of all user position information in the current subspace is used as the spatial object position of the subspace, and a special point in the space is not selected as the spatial object, so that the spatial object position with a small error can be obtained under the condition of sparse data. If it is with U i (X i ,Y i ,L i ) Indicates the location (X) of the i (i =1,2,3 \8230;, n) th user i ,Y i ) And shop mark information L i Taking the average value of the positions of all users in the same subspace as the space object position in the discrete points forming the subspace, and obtaining the discrete points of the subspace according to the space identification of the subspace
For the space containing each discrete point, passing through T i (X i ,Y i ,L i ) Is represented by (X) i ,Y i ) Is the ith subspace T i Spatial object position of, L i Is the ith subspace T i The spatial identification of (2).
Furthermore, a Thiessen polygon corresponding to the complex space environment is determined according to the discrete points of each subspace, if there are N subspaces in the complex space environment, the Thiessen polygon comprises N mutually adjacent polygons, the edge of the Thiessen polygon containing the discrete points is the edge boundary of the subspace, and the Thiessen polygon generated has the following properties:
1) There is one and only one discrete point within each polygon.
2) Any point (X ', Y') in the complex space environment is located at the point (X) containing the discrete points i ,Y i ) Within a polygon containing no discrete points (X) j ,Y j ) Within the polygon of (1), the inequality:
3) The points (X ', Y') being located at discrete points (X) i ,Y i ) And (X) j ,Y j ) On the common edge of two polygons, then the equation
This is true.
Fig. 7 is a schematic view of a triangulation network of the identification space disclosed in the embodiment of the present invention, and fig. 8 is a schematic view of a thiessen polygon generated based on the triangulation network disclosed in the embodiment of the present invention. The property of the Thiessen polygon ensures that only one space identifier exists in each subspace, and the condition that a plurality of space identifiers exist at the same position can not occur except for adjacent boundaries. And the user in the subspace is ensured to be closest to the discrete point of the subspace, namely, the result of intuitively generating the space identifier on the map is unique.
In the following, the determining apparatus provided by the embodiment of the present invention is introduced, and the determining apparatus described below and the determining method described above may be referred to each other.
Referring to fig. 9, an apparatus for determining an environmental space identifier according to an embodiment of the present invention includes:
a location data obtaining module 100, configured to obtain historical user location data in a complex spatial environment;
a Thiessen polygon creation module 200 configured to determine Thiessen polygons representing adjacency relationships of respective subspaces within the complex spatial environment using the historical user location data;
a spatial topological relation model generating module 300, configured to generate a spatial topological relation model based on the thiessen polygon;
a geometric description model creation module 400, configured to create a geometric description model for identifying an environmental space identifier according to an adjacency relation of each subspace in the spatial topological relation model;
the space identifier recognition module 500 is configured to obtain current location information of a target user, and determine a space identifier of a subspace where the target user is located according to the location information and the geometric description model.
Wherein the Thiessen polygon creation module comprises:
a subspace determination unit, configured to determine multiple subspaces of the complex space environment according to location information of each user in different regions in the historical user location data;
the space object position calculation unit is used for calculating the mean value of the position information in each subspace and generating the space object position of each subspace;
the discrete point generating unit is used for generating discrete points of each subspace according to the space object position of each subspace and the space identification of the subspace;
and the Thiessen polygon generating unit is used for determining the Thiessen polygon corresponding to the complex space environment by using the discrete points of each subspace.
The spatial topological relation model generation module comprises:
the adjacency relation determining unit is used for determining the adjacency relation among the subspaces of the Thiessen polygon by utilizing the adjacency relation of the subspaces where any two discrete points in the Thiessen polygon are positioned;
and the relation model generation unit is used for generating a space topological relation model according to the adjacency relation and discrete points of each subspace in the Thiessen polygon.
Wherein the geometry description model creation module comprises:
the classifier creating module is used for creating classifiers for identifying environment space identifiers, wherein the number of the classifiers is the same as the number of the adjacent relations in the space topological relation model;
and the classifier training module is used for training the classifier according to the discrete points of each subspace in the spatial topological relation model to generate the geometric form description model.
Wherein, the space identification module comprises:
a position input unit for inputting the position information into the geometric shape description model;
a target space object position determining unit, configured to sequentially determine, by using the classifier of the geometric form description model, a target space object position closest to the position information;
and the space identification determining unit is used for taking the space identification corresponding to the target space object position as the space identification of the subspace where the target user is located.
Referring to fig. 10, an embodiment of the present invention further discloses an apparatus 1 for determining an environmental space identifier, including:
a memory 11 for storing a computer program;
a processor 12 for implementing the steps of the method for determining an environmental space identifier according to the above method embodiment when executing the computer program.
In the present embodiment, the device 1 may be a PC (Personal Computer), or may be a terminal device such as a smart phone, a tablet Computer, a palmtop Computer, or a portable Computer.
The device 1 may include a memory 11, a processor 12 and a bus 13.
The memory 11 includes at least one type of readable storage medium, which includes flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a magnetic memory, a magnetic disk, an optical disk, and the like. The memory 11 may in some embodiments be an internal storage unit of the device 1, e.g. a hard disk of the device 1. The memory 11 may also be an external storage device of the device 1 in other embodiments, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), etc. provided on the device 1. Further, the memory 11 may also comprise both internal and external memory units of the device 1. The memory 11 may be used not only to store application software installed in the device 1 and various types of data such as codes of programs that execute the above-described determination methods, but also to temporarily store data that has been output or is to be output.
The processor 12 may be a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor or other data Processing chip in some embodiments, and is used for running program codes stored in the memory 11 or Processing data, such as codes of programs for executing the above-mentioned determination methods, and the like.
The bus 13 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 10, but that does not indicate only one bus or one type of bus.
Further, the device may further comprise a network interface 14, and the network interface 14 may optionally comprise a wired interface and/or a wireless interface (such as a WI-FI interface, a bluetooth interface, etc.), which are generally used for establishing a communication connection between the device 1 and other electronic devices.
Optionally, the device 1 may further comprise a user interface 15, the user interface 15 may comprise a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 15 may further comprise a standard wired interface, a wireless interface. Alternatively, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, or the like. The display, which may also be referred to as a display screen or display unit, is suitable for displaying information processed in the device 1 and for displaying a visual user interface.
Fig. 10 shows only the device 1 with the components 11-15, and it will be understood by those skilled in the art that the structure shown in fig. 10 does not constitute a limitation of the device 1, and may comprise fewer or more components than shown, or a combination of certain components, or a different arrangement of components.
The embodiment of the present invention further discloses a computer readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for determining an environment space identifier according to the embodiment of the foregoing method are implemented.
Wherein the storage medium may include: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
In the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A method for determining an environmental space identifier is characterized by comprising the following steps:
obtaining historical user position data in a complex space environment;
determining Thiessen polygons representing the adjacency relation of each subspace in the complex space environment by utilizing the historical user position data, and generating a space topological relation model based on the Thiessen polygons;
according to the adjacency relation of each subspace in the space topological relation model, a geometric form description model for identifying the environment space identification is established;
and acquiring the current position information of the target user, and determining the space identifier of the subspace where the target user is located according to the position information and the geometric form description model.
2. The method of determining according to claim 1, wherein determining, using the historical user location data, a Thiessen polygon representing a adjacency of respective subspaces within the complex spatial environment comprises:
determining a plurality of subspaces of the complex space environment according to the position information of each user in different areas in the historical user position data;
calculating the average value of the position information in each subspace, and generating the space object position of each subspace;
generating discrete points of each subspace according to the space object position of each subspace and the space identification of the subspace;
and determining a Thiessen polygon corresponding to the complex space environment by using the discrete points of each subspace.
3. The determination method according to claim 2, wherein the generating a spatial topological relation model based on the Thiessen polygon comprises:
determining the adjacency relation among the subspaces of the Thiessen polygon by utilizing the adjacency relation of the subspaces of any two discrete points in the Thiessen polygon;
and generating a spatial topological relation model according to the adjacency relation and discrete points of each subspace in the Thiessen polygon.
4. The determination method according to claim 3, wherein creating a geometric description model for identifying the environment space identifier according to the adjacency relationship of each subspace in the spatial topological relation model comprises:
creating classifiers for identifying environment space identifiers, wherein the number of the classifiers is the same as the number of the adjacency relations in the space topological relation model;
and training the classifier according to discrete points of each subspace in the spatial topological relation model to generate the geometric form description model.
5. The method according to any one of claims 1 to 4, wherein the obtaining current position information of a target user, and determining a spatial identifier of a subspace where the target user is located according to the position information and the geometric description model comprises:
inputting the position information into the geometric shape description model;
sequentially judging the positions of the target space objects closest to the position information through the classifier of the geometric form description model;
and taking the space identifier corresponding to the target space object position as the space identifier of the subspace where the target user is located.
6. An apparatus for determining an environmental space identifier, comprising:
the position data acquisition module is used for acquiring historical user position data in a complex space environment;
a Thiessen polygon creation module for determining a Thiessen polygon representing an adjacency relationship of each subspace within the complex spatial environment using the historical user location data;
the space topological relation model generating module is used for generating a space topological relation model based on the Thiessen polygon;
the geometric form description model creating module is used for creating a geometric form description model for identifying the environment space identification according to the adjacent relation of each subspace in the space topological relation model;
and the space identifier recognition module is used for acquiring the current position information of the target user and determining the space identifier of the subspace where the target user is located according to the position information and the geometric form description model.
7. The determination apparatus of claim 6, wherein the Thiessen polygon creation module comprises:
a subspace determination unit, configured to determine multiple subspaces of the complex space environment according to location information of each user in different regions in the historical user location data;
the space object position calculating unit is used for calculating the average value of the position information in each subspace and generating the space object position of each subspace;
the discrete point generating unit is used for generating discrete points of each subspace according to the space object position of each subspace and the space identification of the subspace;
and the Thiessen polygon generating unit is used for determining the Thiessen polygon corresponding to the complex space environment by using the discrete points of each subspace.
8. The apparatus according to claim 6 or 7, wherein the spatial signature recognition module comprises:
a position input unit for inputting the position information into the geometric shape description model;
the target space object position determining unit is used for sequentially judging the target space object position closest to the position information through the classifier of the geometric form description model;
and the space identification determining unit is used for taking the space identification corresponding to the target space object position as the space identification of the subspace where the target user is located.
9. An environment space identification determination device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the method of determining an identification of an environmental space according to any one of claims 1 to 5 when executing said computer program.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, carries out the steps of the method for determining an identification of an environmental space according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910405894.5A CN110136258B (en) | 2019-05-15 | 2019-05-15 | Method, device, equipment and storage medium for determining environment space identifier |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910405894.5A CN110136258B (en) | 2019-05-15 | 2019-05-15 | Method, device, equipment and storage medium for determining environment space identifier |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110136258A CN110136258A (en) | 2019-08-16 |
| CN110136258B true CN110136258B (en) | 2023-03-10 |
Family
ID=67574475
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910405894.5A Active CN110136258B (en) | 2019-05-15 | 2019-05-15 | Method, device, equipment and storage medium for determining environment space identifier |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110136258B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114280014B (en) * | 2021-11-30 | 2024-06-18 | 杭州迪英加科技有限公司 | Independent charging reagent for AI interpretation |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105338540A (en) * | 2015-12-03 | 2016-02-17 | 广州杰赛科技股份有限公司 | Base station data modeling method and terminal |
| JP2018045602A (en) * | 2016-09-16 | 2018-03-22 | 株式会社東芝 | Space information distribution system, route providing system, mobile apparatus, space information distribution method and program |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101730539B1 (en) * | 2015-05-27 | 2017-04-27 | (주)위니텍 | Providing method for active information based on position and system thereof |
| FI127575B (en) * | 2017-06-19 | 2018-09-14 | Ekahau Oy | Selection tool for access point positions |
-
2019
- 2019-05-15 CN CN201910405894.5A patent/CN110136258B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105338540A (en) * | 2015-12-03 | 2016-02-17 | 广州杰赛科技股份有限公司 | Base station data modeling method and terminal |
| JP2018045602A (en) * | 2016-09-16 | 2018-03-22 | 株式会社東芝 | Space information distribution system, route providing system, mobile apparatus, space information distribution method and program |
Non-Patent Citations (2)
| Title |
|---|
| Voronoi图的研究现状及发展趋势;杨霞等;《中国西部科技》;20091025(第30期);全文 * |
| 空间关系的研究进展;胡圣武等;《测绘科学》;20070220(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110136258A (en) | 2019-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tong et al. | A linear road object matching method for conflation based on optimization and logistic regression | |
| Niu et al. | Resource-efficient and automated image-based indoor localization | |
| CN106980633B (en) | Indoor map data generation method and device | |
| JP2019512668A (en) | Root deviation recognition method, terminal, and storage medium | |
| US9173069B2 (en) | Navigating using an indoor map representation | |
| CN106933867B (en) | Image query method and device | |
| US20220075838A1 (en) | Taxonomy-based system for discovering and annotating geofences from geo-referenced data | |
| CN107092623B (en) | Interest point query method and device | |
| CN111651685A (en) | Interest point obtaining method and device, electronic equipment and storage medium | |
| US20140078150A1 (en) | Generating an indoor map model | |
| CN111832447A (en) | Building drawing component identification method, electronic equipment and related product | |
| CN104618869A (en) | Indoor positioning method and device | |
| CN112328880A (en) | Geographical region clustering method and device, storage medium and electronic equipment | |
| CN110136258B (en) | Method, device, equipment and storage medium for determining environment space identifier | |
| Shahid et al. | Indoor positioning:“an image-based crowdsource machine learning approach” | |
| CN112235714B (en) | POI positioning method and device based on artificial intelligence, computer equipment and medium | |
| Yang et al. | Pattern-mining approach for conflating crowdsourcing road networks with POIs | |
| CN111954874A (en) | Identifying functional regions within a geographic area | |
| CN110688995B (en) | Map query processing method, computer-readable storage medium and mobile terminal | |
| Sun et al. | Predicting future locations with semantic trajectories | |
| CN110213311B (en) | Information pushing method and device | |
| US20220245944A1 (en) | Image-based indoor positioning service system and method | |
| Gao et al. | Indoor map construction via mobile crowdsensing | |
| CN114139069A (en) | Indoor positioning method and system based on voice interaction and electronic equipment | |
| CN106682015B (en) | A kind of recommended method and device of point of interest |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |