User positioning method, apparatus, device, and storage medium

Abstract

The application discloses a user positioning method, and belongs to the field of communication, and aims to improve the accuracy of user positioning. The method comprises the following steps: acquiring AGPS MR data in multiple grids, and performing feature processing on the AGPS MR data to obtain a first feature vector, wherein the AGPS MR data comprises position information of the grid to which the AGPS MR data belongs, and the first feature vector is used for representing the data features of the AGPS MR data; determining a nearest neighbor KNN vector library based on the first feature vector; acquiring ordinary MR data in the multiple grids, performing feature processing on the ordinary MR data to obtain a second feature vector, and using the second feature vector to represent the data features of the ordinary MR data; determining the position information of the grid to which the ordinary MR data belongs based on the second feature vector and the KNN vector library; and determining the position information of a user corresponding to the ordinary MR data based on the position information of the grid to which the ordinary MR data belongs.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of communication, and particularly relates to a user positioning method, device, equipment and storage medium. BACKGROUND

[0002] With the development of 5G scale construction, the number of base stations is increasing day by day, and the pressure of testing is increasing, which is very time-consuming and labor-consuming. And in the face of frequent accidents, it is also a big problem that we cannot test on site every time to provide relevant indicators for network optimization.

[0003] On the other hand, a large number of 5G terminal users do not camp on the 5G network, and currently it is impossible to accurately identify the hot spot area of 5G users in the 4G network, and it is impossible to complete the accurate positioning of 4G / 5G users, so it is also difficult to further fine-tune the 4G / 5G interaction operation parameters to improve the user 5G network camping.

[0004] Therefore, in order to better solve the pain points and difficult problems existing in the 4G / 5G network optimization, it is necessary to propose a high-precision user positioning method. SUMMARY

[0005] The embodiments of the present application provide a user positioning method, which can improve the accuracy of user positioning.

[0006] In a first aspect, the embodiments of the present application provide a user positioning method, which comprises: acquiring network assisted global positioning measurement report AGPS MR data in a plurality of grids, and performing feature processing on the AGPS MR data to obtain a first feature vector, wherein the AGPS MR data comprises position information of a grid to which the AGPS MR data belongs, and the first feature vector is used to represent data features of the AGPS MR data; determining a nearest neighbor KNN vector library based on the first feature vector; acquiring measurement report ordinary MR data in the plurality of grids, performing feature processing on the ordinary MR data to obtain a second feature vector, and the second feature vector is used to represent data features of the ordinary MR data; determining position information of a grid to which the ordinary MR data belongs based on the second feature vector and the KNN vector library; and determining position information of a user corresponding to the ordinary MR data based on the position information of the grid to which the ordinary MR data belongs.

[0007] In a second aspect, the embodiments of the present application provide a user positioning device, which comprises: a first obtaining module, configured to obtain AGPS MR data in a plurality of grids, and perform feature processing on the AGPS MR data to obtain a first feature vector, wherein the AGPS MR data comprises location information of a grid to which the AGPS MR data belongs, and the first feature vector is used to represent data features of the AGPS MR data; a first determining module, configured to determine a KNN vector library based on the first feature vector; a second obtaining module, configured to obtain normal MR data in the plurality of grids, and perform feature processing on the normal MR data to obtain a second feature vector, wherein the second feature vector is used to represent data features of the normal MR data; a second determining module, configured to determine location information of a grid to which the normal MR data belongs based on the second feature vector and the KNN vector library; and a third determining module, configured to determine location information of a user corresponding to the normal MR data based on the location information of the grid to which the normal MR data belongs.

[0008] In a third aspect, the embodiments of the present application provide an electronic device, which comprises a processor, a memory, and a program or instruction stored in the memory and executable on the processor, and the program or instruction is executed by the processor to implement the steps of the method according to the first aspect.

[0009] In a fourth aspect, the embodiments of the present application provide a readable storage medium, which stores a program or instruction, and the program or instruction is executed by a processor to implement the steps of the method according to the first aspect.

[0010] In a fifth aspect, the embodiments of the present application provide a chip, which comprises a processor and a communication interface, the communication interface is coupled with the processor, and the processor is configured to run a program or instruction to implement the method according to the first aspect.

[0011] In the embodiment of the present application, by acquiring network assisted global positioning measurement report AGPS MR data in multiple grids, and performing feature processing on the AGPS MR data, a first feature vector is obtained, the AGPS MR data includes position information of the grid to which the AGPS MR data belongs, and the first feature vector is used to represent data features of the AGPS MR data; a nearest neighbor KNN vector library is determined based on the first feature vector; measurement report ordinary MR data in the multiple grids is acquired, feature processing is performed on the ordinary MR data, and a second feature vector is obtained, the second feature vector is used to represent data features of the ordinary MR data; position information of the grid to which the ordinary MR data belongs is determined based on the second feature vector and the KNN vector library; and position information of a user corresponding to the ordinary MR data is determined based on the position information of the grid to which the ordinary MR data belongs, so that the position information of the user can be determined more accurately. BRIEF DESCRIPTION OF DRAWINGS

[0012] Figure 1 is one of flow diagrams of a user positioning method provided by the embodiment of the present application;

[0013] Figure 2 is a schematic diagram of AGPS MR data in multiple grids provided by the embodiment of the present application;

[0014] Figure 3 is a schematic diagram of a KNN vector library determined based on a first feature vector provided by the embodiment of the present application;

[0015] Figure 4 is another flow diagram of a user positioning method provided by the embodiment of the present application;

[0016] Figure 5 is a schematic diagram of a second feature vector and a KNN vector library provided by the embodiment of the present application;

[0017] Figure 6 is a third flow diagram of a user positioning method provided by the embodiment of the present application;

[0018] Figure 7 is a schematic diagram of a module composition of a user positioning device provided by the embodiment of the present application;

[0019] Figure 8 is a schematic diagram of a structure of a user positioning device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0020] With reference to the drawings and embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0021] The terms "first", "second", and the like in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be exchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second", etc. are generally a class, and are not limited to the number of objects, for example, the first object can be one or more. In addition, "and / or" in the specification and claims indicates at least one of the connected objects, and the character " / ", generally indicates that the front and rear associated objects are in an "or" relationship.

[0022] The user positioning method provided by the embodiments of the present application will be described in detail below in combination with the drawings, specific embodiments and application scenarios.

[0023] Figure 1 An embodiment of the present application provides a user positioning method, which can be executed by an electronic device, which can include a server and / or a terminal device, such as a vehicle-mounted terminal or a mobile phone terminal. In other words, the method can be executed by software or hardware installed in a user positioning device, and the method includes the following steps:

[0024] In step 102, network-assisted global positioning measurement report (AGPS MR) data in a plurality of grids is acquired, and the AGPS MR data is characterized to obtain a first feature vector. The AGPS MR data includes location information of the grid to which the AGPS MR data belongs, and the first feature vector is used to represent the data characteristics of the AGPS MR data.

[0025] The AGPS MR data in the plurality of grids is acquired, wherein the size of each grid can be 10M*10M, 15M*15M or other values, which are not limited here, and the position information of the grid is the position information of the center point of the grid, that is, the position information of the center point of the grid is determined as the position information of the grid. The AGPS MR data is measurement report data acquired based on AGPS, is generated by the target terminal, and is signal information of a serving cell (a serving cell refers to an area covered by a base station or a part of a base station in a communication system) to which the target terminal belongs. The AGPS MR data further includes the position information of the grid to which the AGPS MR data belongs.

[0026] Specifically, the position information of the grid to which the AGPS MR data belongs is the label information of the AGPS MR data, that is, the AGPS MR data is characterized to obtain the first feature vector, and the signal information of the serving cell to which the target terminal belongs is characterized to obtain the data feature (the first feature vector) of the AGPS MR data. The generated first feature vector has the position information of the grid to which the first feature vector belongs. More specifically, the characterization of the AGPS MR data is to unify different signal information in the same AGPS MR data into one-dimensional vector information (the first feature vector), and the generated first feature vector and the AGPS MR data both have labels representing the position information of the grid to which the first feature vector or the AGPS MR data belongs.

[0027] As shown in FIG. 1, the AGPS MR data in the plurality of grids is acquired, wherein the size of each grid can be 10M*10M, 15M*15M or other values, which are not limited here, and the position information of the grid is the position information of the center point of the grid, that is, the position information of the center point of the grid is determined as the position information of the grid. The AGPS MR data is measurement report data acquired based on AGPS, is generated by the target terminal, and is signal information of a serving cell (a serving cell refers to an area covered by a base station or a part of a base station in a communication system) to which the target terminal belongs. The AGPS MR data further includes the position information of the grid to which the AGPS MR data belongs. Figure 2 As shown in FIG. 2, the AGPS MR data in the plurality of grids is acquired, wherein the size of each grid can be 10M*10M, 15M*15M or other values, which are not limited here, and the position information of the grid is the position information of the center point of the grid, that is, the position information of the center point of the grid is determined as the position information of the grid. The AGPS MR data is measurement report data acquired based on AGPS, is generated by the target terminal, and is signal information of a serving cell (a serving cell refers to an area covered by a base station or a part of a base station in a communication system) to which the target terminal belongs. The AGPS MR data further includes the position information of the grid to which the AGPS MR data belongs.

[0028] Step 104: determining a nearest neighbor KNN vector library based on the first feature vector;

[0029] The nearest neighbor KNN algorithm is a basic classification and regression algorithm, and KNN stands for K Nearest Neighbors, that is, the principle of the KNN algorithm is to determine which type x belongs to when predicting a new value x according to the types of the K nearest points to x, wherein the value of K can be determined according to actual conditions.

[0030] After the first feature vectors are determined, a nearest neighbor KNN vector library is determined based on the first feature vectors, and the determined nearest neighbor KNN vector library is used for vector retrieval. Specifically, the plurality of first feature vectors are placed in the same coordinate system, and the nearest neighbor KNN vector library is formed based on the plurality of first feature vectors in the same coordinate system.

[0031] Figure 3 The KNN vector library determined based on the first feature vectors is shown in the schematic diagram, wherein the points a, b, c, d, and e are used to represent the plurality of first feature vectors obtained based on the AGPS MR data, i.e., the plurality of first feature vectors are placed in the same coordinate system, and the points a, b, c, d, and e in Figure 3 and the nearest neighbor KNN vector library shown in Figure 3 .

[0032] Step 106: Obtain measurement report general MR data in the plurality of grids, and perform feature processing on the general MR data to obtain second feature vectors, wherein the second feature vectors are used to represent data features of the general MR data.

[0033] The general MR data in the plurality of grids is obtained, the general MR data is generated by a target terminal, and is signal information of a serving cell (the serving cell refers to an area covered by a base station or a part of a base station in a communication system) to which the target terminal belongs. However, the general MR data does not include position information of a grid to which the general MR data belongs, i.e., the general MR data does not have a label representing the position information of the grid to which the general MR data belongs. That is, the second feature vectors obtained by performing feature processing on the general MR data do not have a label representing the position information of the grid to which the second feature vectors belong.

[0034] Specifically, the feature processing on the general MR data is to perform feature processing on the signal information included in the general MR data, so as to obtain data features (the second feature vectors) of the general MR data, but the generated second feature vectors do not have position information of a grid to which the second feature vectors belong. More specifically, the feature processing on the general MR data is to unify different signal information in the same general MR data into one-dimensional vector information (the second feature vectors), but neither the generated second feature vectors nor the general MR data has a label representing the position information of the grid to which the second feature vectors or the general MR data belong.

[0035] Step 108: Determine position information of a grid to which the general MR data belongs based on the second feature vectors and the KNN vector library.

[0036] After the second feature vector and the KNN vector library are determined, the position information of the grid to which the common MR belongs is determined based on the second feature vector and the KNN vector library, that is, the second feature vector is input to the KNN vector library, then K first feature vectors with similar distances to the second feature vector are determined, and then the position information of the second feature vector is determined according to the position information of the K first feature vectors, and further the position information of the grid to which the common MR data corresponding to the second feature vector belongs is determined, wherein the value of K can be one, two or other values, which are not limited here.

[0037] In step 110, the position information of the user corresponding to the common MR data is determined based on the position information of the grid to which the common MR data belongs.

[0038] After the position information of the grid to which the common MR data belongs is determined, the position information of the grid to which the common MR data belongs is determined as the position information of the common MR data, and further the position information of the user corresponding to the common MR data is determined, that is, the position information of the common MR data is the position information of the user corresponding to the common MR data.

[0039] The user positioning method provided by the embodiment of the application, by acquiring network assisted global positioning measurement report AGPS MR data in a plurality of grids, and performing feature processing on the AGPS MR data to obtain a first feature vector, the AGPS MR data includes position information of a grid to which the AGPS MR data belongs, and the first feature vector is used to represent data features of the AGPS MR data; a KNN vector library is determined based on the first feature vector; measurement report common MR data in the plurality of grids is acquired, feature processing is performed on the common MR data to obtain a second feature vector, the second feature vector is used to represent data features of the common MR data; position information of a grid to which the common MR data belongs is determined based on the second feature vector and the KNN vector library; and position information of a user corresponding to the common MR data is determined based on the position information of the grid to which the common MR data belongs, the position information of the user can be more accurately determined.

[0040] In an implementation manner, the AGPS MR data includes a serving cell signal strength, a serving cell Ts granularity, and a strongest neighbor cell signal strength, the serving cell signal strength is information strength of a serving cell to which the AGPS MR data belongs, the serving cell Ts granularity is a Ts granularity of the serving cell to which the AGPS MR data belongs, and the strongest neighbor cell signal strength is a signal strength of a serving cell with the highest signal strength among serving cells adjacent to the serving cell to which the AGPS MR data belongs.

[0041] The AGPS MR data is characterized to obtain a first feature vector (step 102), which can perform step A:

[0042] Step A: determining the first feature vector based on the serving cell signal strength, the serving cell Ts granularity, and the strongest neighbor cell signal strength.

[0043] The signal strength of the serving cell, the Ts granularity of the serving cell, and the strongest neighbor cell signal strength included in the AGPS MR data are determined. The serving cell signal strength is the signal strength of the serving cell to which the AGPS MR data belongs, the serving cell Ts granularity is the Ts granularity of the serving cell to which the AGPS MR data belongs, and the strongest neighbor cell signal strength is the signal strength of the serving cell with the strongest signal strength among the serving cells adjacent to the serving cell corresponding to the AGPS MR data.

[0044] The first feature vector is determined according to the serving cell signal strength, the serving cell Ts granularity, and the strongest neighbor cell signal strength included in the AGPS MR data, that is, the serving cell signal strength, the serving cell Ts granularity, and the strongest neighbor cell signal strength information in the AGPS MR data are unified into a one-dimensional vector information. Specifically, the first feature vector determined according to the AGPS MR data can be represented as:

[0045] f i =

v0, t0, v nmax

[0046] Wherein, v0 is the signal strength of the serving cell (dBm), t0 is the Ts granularity of the serving cell (TA), v nmax is the strongest neighbor cell signal strength (dBm), f i represents the first feature vector corresponding to the i-th AGPS MR data, and each first feature vector has a label representing the grid position information to which the first feature vector belongs.

[0047] More specifically, when determining the second feature vector according to the ordinary MR data, the second feature vector can be represented as:

[0048] g i =

v0, t0, v nmax

[0049] Wherein, v0 is the signal strength of the serving cell (dBm), t0 is the Ts granularity of the serving cell (TA), v nmax is the strongest neighbor cell signal strength (dBm), g i represents the second feature vector corresponding to the i-th ordinary MR data, but each second feature vector does not have a label representing the grid position information to which the second feature vector belongs.

[0050] Further, when the AGPS MR data is characterized to obtain the first feature vector, the first feature vector can also be determined according to the serving cell signal strength, the serving cell Ts granularity included in the AGPS MR data, the first feature vector can also be determined according to the serving cell signal strength, the strongest neighbor cell signal strength included in the AGPS MR data, and the first feature vector can also be determined according to the serving cell Ts granularity, the strongest neighbor cell signal strength included in the AGPS MR data. Further, the first feature vector can be determined according to one or more of the serving cell signal strength, the serving cell Ts granularity, and the strongest neighbor cell signal strength. Of course, the second feature vector can also be determined according to one or more of the serving cell signal strength, the serving cell Ts granularity, and the strongest neighbor cell signal strength.

[0051] In an implementation manner, the determining the KNN vector library based on the first feature vector (step 104) can perform steps B1-B2:

[0052] Step B1: performing dictionary training based on the first feature vector to determine a first encoding vector and a shared dictionary, the first encoding vector being a sparse matrix corresponding to the first feature vector;

[0053] The goal of dictionary learning is to extract the essential features of things (similar to words or phrases in a dictionary). Dictionary learning is to decompose the original sample into a dictionary matrix and a sparse code matrix, that is, to decompose the first feature vector into a shared dictionary and a first encoding vector, and the first encoding vector is a sparse matrix corresponding to the first feature vector.

[0054] The first feature vector is subjected to dictionary training to determine the first encoding vector and the shared dictionary, that is, the dictionary training is performed based on multiple first feature vectors to determine the first encoding vector and the shared dictionary corresponding to each first feature vector.

[0055] Step B2: determining the KNN vector library based on the first encoding vector.

[0056] After determining the first encoding vector and the shared dictionary, the KNN vector library is determined based on the first feature encoding, and the determined KNN vector library is used for vector retrieval. Specifically, multiple first feature encodings are placed in the same coordinate system, and the nearest neighbor KNN vector library is obtained based on the multiple first feature vectors in the same coordinate system.

[0057] The dictionary training is performed based on the first feature vector to obtain the first encoding vector and the shared dictionary, and the KNN vector library is determined based on the first encoding vector, which can convert the first feature vector into a more distinctive first encoding vector, reduce the complexity of the first feature vector, improve the accuracy of the KNN vector library, and improve the efficiency of data processing.

[0058] In an implementation manner, the position information of the grid to which the common MR data belongs is determined based on the second feature vector and the KNN vector library (step 106), and steps C1-C2 can be performed:

[0059] Step C1: determining a second encoding vector based on the second feature vector and the shared dictionary.

[0060] After determining the nearest neighbor KNN vector library based on the first encoding vector, a second encoding vector can be determined based on the second feature vector and the shared dictionary, that is, the second feature vector is processed based on the shared dictionary to determine the second encoding vector corresponding to each second feature vector.

[0061] Step C2: determining the position information of the grid to which the common MR data belongs based on the second encoding vector and the KNN vector library.

[0062] After determining the second encoding vector, the position information of the grid to which the common MR data belongs is determined based on the second encoding vector and the KNN vector library, that is, the second encoding vector is input into the KNN vector library, so that in the KNN vector library, the K first encoding vectors closest to the second encoding vector are determined, and then the position information of the second encoding vector is determined according to the position information of the K first encoding vectors, and the position information of the grid to which the common MR data belongs is determined. The value of K can be one, three or other values, which are not limited here.

[0063] Specifically, in order to understand the method provided by the embodiments of the present specification, Figure 4 the second flowchart of the user positioning method provided by the embodiments of the present specification, Figure 4 The method shown at least includes the following steps:

[0064] Step 402: acquiring network-assisted global positioning measurement report AGPS MR data in a plurality of grids, and performing feature processing on the AGPS MR data to obtain a first feature vector;

[0065] The AGPS MR data includes the position information of the grid to which the AGPS MR data belongs, and the first feature vector is used to represent the data features of the AGPS MR data.

[0066] Step 404: performing dictionary training based on the first feature vector to determine a first encoding vector and a shared dictionary;

[0067] The first encoding vector is a sparse matrix corresponding to the first feature vector.

[0068] Step 406: determining a KNN vector library based on the first encoding vector;

[0069] Step 408: obtaining measurement report general MR data in the plurality of grids, performing feature processing on the general MR data to obtain a second feature vector;

[0070] The second feature vector is used to represent the data features of the general MR data.

[0071] Step 410: determining a second encoding vector based on the second feature vector and the shared dictionary;

[0072] Step 412: determining the location information of the grid to which the general MR data belongs based on the second encoding vector and the KNN vector library;

[0073] Step 414: determining the location information of the user corresponding to the general MR data based on the location information of the grid to which the general MR data belongs.

[0074] The specific processes of steps 402-414 are described in detail in the above embodiments, which will not be repeated here.

[0075] In an implementation manner, the dictionary training based on the first feature vector, the determination of the first encoding vector and the shared dictionary (step B1) can perform steps D1-D3:

[0076] Step D1: obtaining an initial dictionary, a first control factor and a second control factor, the first control factor being used to determine a first preset region in the initial dictionary, and the second control factor being used to determine an initial dictionary meeting a second preset region;

[0077] Due to the large number of samples of the first feature vector, considering the accuracy and efficiency of coding, the first feature vector can be coded by a local constraint linear algorithm, and the dictionary therein is updated to a shared dictionary, similar features are placed in the front of the coding, and dissimilar features are placed in the rear, so as to enhance the distinguishability of the features and improve the accuracy of classification.

[0078] The objective function of the existing locality-constrained linear coding (LLC) can be written as follows:

[0079]

[0080]

[0081] Wherein, f i ∈R k is a signal feature that needs to be coded, B∈R k×l is a dictionary, and c i∈R l is the first encoding vector for KNN classification. is added to constrain the coefficients of to a local range, i.e. locality is added to guarantee sparsity.

[0082] In order to enhance the first encoding vector c i ∈R l The difference and increase the classification accuracy, on the basis of the above LLC encoding, the cost function is improved, a new encoding method is proposed, the expression is as follows:

[0083]

[0084]

[0085] is the first encoding vector, E i ∈R l is the first encoding vector, E * is a diagonal unit matrix with size *, d is the number of shared words, λ and β are balance factors, B∈R k×l is a shared dictionary, S1 is the first control factor, S2 is the second control factor. The new encoding method can divide the dictionary into private atomic part and shared atomic part through the control factor and so that the private atoms arranged at the front end of the dictionary can be used as much as possible during encoding.

[0086] Step D2: determining the first feature encoding based on the initial dictionary, the first control factor and the second control factor;

[0087] According to the improved cost function, the expression of d i is obtained as follows:

[0088]

[0089] where dist is the Euclidean distance between two column vectors. σ is a weight factor.

[0090] The encoding calculation process through the above cost function is: transformed into a Lagrange extreme value problem, and then the first feature encoding analytical expression is obtained:

[0091]

[0092]

[0093] where Q i = x i 1 T S1-B, G i= diag(d i )S1.

[0094] Step D3: determining a first feature code meeting a first preset condition, and determining the shared dictionary based on the first feature code meeting the first preset condition, wherein the first preset condition is that a first feature code value is less than a threshold value.

[0095] After determining the first feature code, the first feature code with a first feature code value greater than a preset threshold value (the preset threshold value can be 0.01, or 0.02, or other values, which are not specifically limited here) is saved, and the following formula is solved:

[0096]

[0097]

[0098] By gradient descent method, the original codebook is subtracted by the product of the step size and the reciprocal of the above expression, to obtain the expression:

[0099]

[0100] Finally, the column of B ii is replaced by the corresponding column in B i , and the final shared dictionary is output.

[0101] In an implementation manner, the step of determining the position information of the grid to which the normal MR data belongs based on the second encoding vector and the KNN vector library (step C2) can perform steps E1-E3:

[0102] Step E1: determining a plurality of first encoding vectors meeting a second preset condition based on the second encoding vector in the KNN vector library, wherein the second preset condition is that the distance from the second encoding vector is less than a threshold value.

[0103] The second encoding vector is input into the KNN vector library, so as to determine a plurality of first encoding vectors meeting a second preset condition, wherein the second preset condition can be that the distance from the second encoding vector is less than a preset threshold value, and the second preset condition can also be that the three first encoding vectors with the smallest distance from the second encoding vector in the KNN vector library (for example, the distances between the first encoding vectors and the second encoding vector in the KNN vector library are determined, the distances are sorted in ascending order, and the first encoding vectors corresponding to the top three distance values are selected), and the five first encoding vectors with the smallest distance from the second encoding vector can also be selected, which are not specifically limited here.

[0104] Figure 5The diagram shows the second feature vector and the KNN vector library. Points a, b, c, d, and e represent the first feature vector in the KNN vector library, and point f represents the second feature vector input into the KNN vector library. When the second preset condition is that the distance to the second encoded vector is less than a preset threshold, the coverage range of the preset threshold is determined, i.e. Figure 5 The coverage area of ​​the circle is determined, and then the first encoded vectors (i.e., points a, b, and c) whose distance to the second encoded vector f is less than a preset threshold (i.e., the first encoded vector within the circular coverage area) are identified. When the second preset condition is that the three first encoded vectors in the KNN vector library have the smallest distance to the second encoded vector, the distance value between each first encoded vector in the KNN vector library and the second encoded vector is determined and sorted in ascending order. Then, the first encoded vectors corresponding to the three smallest distance values ​​are selected, such as... Figure 5 Points a, b, and c in the diagram.

[0105] Step E2: Determine the location information of the raster to which the second encoded vector belongs based on the AGPS MR data corresponding to the plurality of first encoded vectors;

[0106] After determining the first encoded vector that meets the second preset condition, the position information of the raster to which each first encoded vector belongs is determined based on the AGPS MR data corresponding to multiple first encoded vectors, and the position information of the raster to which the second encoded vector belongs is determined based on the position information of the raster to which each first encoded vector belongs. Since each AGPS MR data contains its own position information, the position information of the first encoded vector corresponding to the AGPS MR data can be determined based on the position information of the AGPS MR data. After determining the position information of each first encoded vector, the position information of the second encoded vector is determined based on the position information of each first encoded vector. Figure 5 As shown, there are 3 first encoding vectors that meet the second preset conditions. Then, the position information of the grid to which the first encoding vector a belongs, the position information of the grid to which the first encoding vector b belongs, and the position information of the grid to which the first encoding vector c belongs are determined. Finally, the position information of the second encoding vector f is determined based on the position information of the three first encoding vectors a, b, and c.

[0107] Specifically, when determining the position information of the second encoding vector based on the position information of the first encoding vector, the position information that appears most frequently among multiple position information of the first encoding vector can be determined as the position information of the second encoding vector. For example, if the position information of point a in the first encoding vector is (X0, Y0), the position information of point b in the first encoding vector is (X0, Y0), and the position information of point c in the first encoding vector is (X1, Y1), then the position information of point f in the second encoding vector can be determined as (X0, Y0).

[0108] Step E3: determining the position information of the common MR data based on the position information of the second encoding vector.

[0109] After the position information of the second encoding vector is determined, the position information of the second encoding vector is determined as the position information of the common MR data. Because the second encoding vector is obtained based on the common MR data, each second encoding vector has corresponding common MR data, i.e., the position information of each common MR data corresponding to the second encoding vector can be determined based on the position information of the second encoding vector.

[0110] In an implementation manner, before the AGPS MR data in the plurality of grids is obtained (step 102), steps F1-F2 can also be performed.

[0111] Step F1: determining the position information of the plurality of grids.

[0112] Specifically, the region with AGPS MR data and / or common MR data is divided according to certain standards, thereby obtaining a plurality of grids with preset specifications. The preset specifications can be 15M*15M, 10M*10M or other specifications. After the plurality of grids are determined, the position information of the center point of each grid is determined, and the position information of the center point of each grid is determined as the position information of the grid.

[0113] Step F2: obtaining AGPS MR data, and determining the position information of the grid to which each AGPS MR data belongs according to the AGPS MR data and the position information of the plurality of grids.

[0114] The AGPS MR data in the grid region is obtained, the grid to which the AGPS MR data belongs is determined according to the position information in the AGPS MR data, and finally the AGPS MR data and the position information of the grid to which the AGPS MR data belongs are associated.

[0115] Further, after the AGPS MR data and the position information of the grid to which the AGPS MR data corresponds are determined, the position information of the grid to which the AGPS MR data belongs is taken as the tag information of the AGPS MR data.

[0116] Specifically, in order to understand the method provided by the embodiments of the present specification, Figure 6 the third flowchart of the user positioning method provided by the embodiments of the present specification, Figure 6 The method shown at least includes the following steps:

[0117] Step 602: determining the position information of the plurality of grids.

[0118] Step 604: obtaining AGPS MR data, and determining location information of a grid to which each AGPS MR data belongs according to the AGPS MR data and the location information of the plurality of grids;

[0119] Step 606: obtaining network-assisted global positioning measurement report AGPS MR data in the plurality of grids;

[0120] The AGPS MR data includes a serving cell signal strength, a serving cell Ts granularity, and a strongest neighbor cell signal strength, the serving cell signal strength is a signal strength of a serving cell to which the AGPS MR data belongs, the serving cell Ts granularity is a Ts granularity of the serving cell to which the AGPS MR data belongs, and the strongest neighbor cell signal strength is a signal strength of a serving cell with the highest signal strength among serving cells adjacent to the serving cell to which the AGPS MR data belongs.

[0121] Step 608: determining the first feature vector based on the serving cell signal strength, the serving cell Ts granularity, and the strongest neighbor cell signal strength;

[0122] Step 610: obtaining an initial dictionary, a first control factor, and a second control factor;

[0123] The first control factor is used to determine a first preset area in the initial dictionary, and the second control factor is used to determine a second preset area in the initial dictionary.

[0124] Step 612: determining a first feature code based on the initial dictionary, the first control factor, and the second control factor;

[0125] Step 614: determining a first feature code meeting a first preset condition, and determining the shared dictionary based on the first feature code meeting the first preset condition;

[0126] The first preset condition is that a first feature code value is less than a threshold value.

[0127] Step 616: determining the KNN vector library based on the first encoding vector;

[0128] Step 618: obtaining measurement report ordinary MR data in the plurality of grids, performing feature processing on the ordinary MR data, and obtaining a second feature vector;

[0129] The second feature vector is used to represent data features of the ordinary MR data.

[0130] Step 620: determining a second encoding vector based on the second feature vector and the shared dictionary;

[0131] Step 622: determining a plurality of first encoding vectors meeting a second preset condition in the KNN vector library based on the second encoding vector;

[0132] Wherein, the second preset condition is that the distance from the second encoding vector is less than a threshold.

[0133] Step 624: determining the position information of the grid to which the second encoding vector belongs based on the AGPS MR data corresponding to the plurality of first encoding vectors;

[0134] Step 626: determining the position information of the grid to which the ordinary MR data belongs based on the position information of the second encoding vector.

[0135] The specific process of the above steps 602-626 has been described in detail in the above embodiment, and will not be repeated here.

[0136] The embodiment obtains network assisted global positioning measurement report AGPS MR data in a plurality of grids, and performs feature processing on the AGPS MR data to obtain a first feature vector, wherein the AGPS MR data includes the position information of the grid to which the AGPS MR data belongs, and the first feature vector is used to represent the data features of the AGPS MR data; determines a KNN vector library based on the first feature vector; obtains measurement report ordinary MR data in the plurality of grids, and performs feature processing on the ordinary MR data to obtain a second feature vector, wherein the second feature vector is used to represent the data features of the ordinary MR data; determines the position information of the grid to which the ordinary MR data belongs based on the second feature vector and the KNN vector library; and determines the position information of a user corresponding to the ordinary MR data based on the position information of the grid to which the ordinary MR data belongs, which can more accurately determine the position information of the user.

[0137] It should be noted that the user positioning method provided in the embodiment of the application can be executed by a user positioning device or a control module in the user positioning device for executing the user positioning method. In the embodiment of the application, the user positioning device is taken as an example to illustrate the user positioning device provided in the embodiment of the application.

[0138] Figure 7 is a structural schematic diagram of a user positioning device according to the embodiment of the application. As shown in Figure 7 the user positioning device includes a first obtaining module 702, a first determining module 704, a second obtaining module 706, a second determining module 708, and a third determining module 710.

[0139] The first obtaining module 702 is configured to obtain AGPS MR data in a plurality of grids, and perform feature processing on the AGPS MR data to obtain a first feature vector, wherein the AGPS MR data comprises location information of a grid to which the AGPS MR data belongs, and the first feature vector is used to represent data features of the AGPS MR data.

[0140] The first determining module 704 is configured to determine a KNN vector library based on the first feature vector.

[0141] The second obtaining module 706 is configured to obtain normal MR data in the plurality of grids, and perform feature processing on the normal MR data to obtain a second feature vector, wherein the second feature vector is used to represent data features of the normal MR data.

[0142] The second determining module 708 is configured to determine location information of a grid to which the normal MR data belongs based on the second feature vector and the KNN vector library.

[0143] The third determining module 710 is configured to determine location information of a user corresponding to the normal MR data based on the location information of the grid to which the normal MR data belongs.

[0144] The user positioning apparatus in the embodiments of the present applicationapplicationbe an apparatus, or a component, an integrated circuit or a chip in a terminal. The apparatusapplicationbe a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic deviceapplicationbe a mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (PDA), etc., and the non-mobile electronic deviceapplicationbe a server, a network attached storage (NAS), a personal computer (PC), a television (TV), a teller machine or a self-service machine, etc., and the embodiments of the present application do not make a specific limitation.

[0145] The user positioning apparatus in the embodiments of the present applicationapplicationbe an apparatus having an operating system. The operating systemapplicationbe an Android operating system, an ios operating system or other possible operating systems, and the embodiments of the present application do not make a specific limitation.

[0146] The user positioning apparatus provided in the embodiments of the present applicationapplicationbe capable of implementing the method embodiments. Figures 1 to 7 The processes implemented in the method embodiments are not repeated here to avoid repetition.

[0147] Based on the same technical concept, the embodiments of the present application also provide an electronic device for executing the user positioning method described above, Figure 8 A structural schematic diagram of an electronic device for implementing various embodiments of the present application. The electronic device can have great differences due to different configurations or performances, and can include a processor 802, a communications interface 804, a memory 806, and a communications bus 808, wherein the processor 802, the communications interface 804, and the memory 806 complete mutual communication through the communications bus 808. The processor 802 can invoke a computer program stored on the memory 806 and executable on the processor 802 to execute the following steps:

[0148] Obtain network assisted global positioning measurement report AGPS MR data in a plurality of grids, and perform feature processing on the AGPS MR data to obtain a first feature vector, wherein the AGPS MR data includes location information of a grid to which the AGPS MR data belongs, and the first feature vector is used to represent data features of the AGPS MR data;

[0149] Determine a KNN vector library based on the first feature vector;

[0150] Obtain measurement report ordinary MR data in the plurality of grids, and perform feature processing on the ordinary MR data to obtain a second feature vector, wherein the second feature vector is used to represent data features of the ordinary MR data;

[0151] Determine location information of a grid to which the ordinary MR data belongs based on the second feature vector and the KNN vector library;

[0152] Determine location information of a user corresponding to the ordinary MR data based on the location information of the grid to which the ordinary MR data belongs.

[0153] In an implementation manner, the AGPS MR data includes a serving cell signal strength, a serving cell Ts granularity, and a strongest neighbor cell signal strength, the serving cell signal strength is information strength of a serving cell to which the AGPS MR data belongs, the serving cell Ts granularity is a Ts granularity of the serving cell to which the AGPS MR data belongs, and the strongest neighbor cell signal strength is a signal strength of a serving cell with the highest signal strength among serving cells adjacent to the serving cell to which the AGPS MR data belongs;

[0154] The feature processing on the AGPS MR data to obtain the first feature vector includes:

[0155] determining the first feature vector based on the serving cell signal strength, the serving cell Ts granularity, and the strongest neighbor cell signal strength.

[0156] In an implementation, the determining the KNN vector library based on the first feature vector comprises:

[0157] performing dictionary training based on the first feature vector to determine a first encoding vector and a shared dictionary, the first encoding vector being a sparse matrix corresponding to the first feature vector;

[0158] determining the KNN vector library based on the first encoding vector.

[0159] In an implementation, the determining the location information of the grid to which the normal MR data belongs based on the second feature vector and the KNN vector library comprises:

[0160] determining a second encoding vector based on the second feature vector and the shared dictionary;

[0161] determining the location information of the grid to which the normal MR data belongs based on the second encoding vector and the KNN vector library.

[0162] In an implementation, the performing dictionary training based on the first feature vector to determine a first encoding vector and a shared dictionary comprises:

[0163] obtaining an initial dictionary, a first control factor, and a second control factor, the first control factor being used to determine a first preset region in the initial dictionary, and the second control factor being used to determine a second preset region in the initial dictionary;

[0164] determining a first feature encoding based on the initial dictionary, the first control factor, and the second control factor;

[0165] determining a first feature encoding meeting a first preset condition, and determining the shared dictionary based on the first feature encoding meeting the first preset condition, wherein the first preset condition is that a value of the first feature encoding is less than a threshold.

[0166] In an implementation, the determining the location information of the grid to which the normal MR data belongs based on the second encoding vector and the KNN vector library comprises:

[0167] determining a plurality of first encoding vectors meeting a second preset condition in the KNN vector library based on the second encoding vector, wherein the second preset condition is that a distance to the second encoding vector is less than a threshold;

[0168] determine the position information of the grid to which the second encoding vector belongs based on the AGPS MR data corresponding to the plurality of first encoding vectors;

[0169] determine the position information of the grid to which the ordinary MR data belongs based on the position information of the second encoding vector.

[0170] In an implementation manner, before the AGPS MR data in the plurality of grids is acquired, the method further includes:

[0171] determine the position information of the plurality of grids;

[0172] acquire the AGPS MR data, and determine the position information of the grid to which each of the AGPS MR data belongs based on the AGPS MR data and the position information of the plurality of grids.

[0173] The specific implementation steps can refer to the steps of the user positioning method embodiments, and the same technical effects can be achieved. To avoid repetition, details are not described herein.

[0174] It should be noted that the electronic device in the embodiments of the present application includes a server, a terminal or other devices other than the terminal.

[0175] The above electronic device structure does not constitute a limitation on the electronic device, and the electronic device can include more or fewer components than the illustration, or combine certain components, or different component arrangements. For example, the input unit can include a graphics processing unit (GPU) and a microphone, and the display unit can be configured as a display panel in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit includes at least one of a touch panel and other input devices. The touch panel is also called a touch screen. Other input devices can include, but are not limited to, a physical keyboard, function keys (such as volume control buttons, on-off buttons, etc.), trackballs, mice, joysticks, and the like, which are not described here.

[0176] The memory can be used to store software programs and various data. The memory can mainly include a first storage area storing programs or instructions and a second storage area storing data, wherein the first storage area can store an operating system, application programs or instructions required by at least one function (such as a sound playing function, an image playing function, etc.), and the like. In addition, the memory can include a volatile memory or a non-volatile memory, or the memory can include both a volatile memory and a non-volatile memory. The non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM), a Static RAM (SRAM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a Double Data Rate SDRAM (DDR SDRAM), an Enhanced SDRAM (ESDRAM), a Synchlink DRAM (SLDRAM), and a Direct Rambus RAM (DRRAM).

[0177] The processor can include one or more processing units; optionally, the processor integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and an application program, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the above-mentioned modem processor can also not be integrated into the processor.

[0178] The embodiments of the present application further provide a readable storage medium, and the readable storage medium stores programs or instructions, which are executed by a processor to implement various processes of the above-mentioned user positioning method embodiments and achieve the same technical effects. To avoid repetition, details are not described herein.

[0179] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes a computer readable storage medium, such as a computer read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0180] The chip provided in the embodiments of the present application includes a processor and a communication interface, the communication interface is coupled with the processor, the processor is used to run programs or instructions, realizes the processes of the above-mentioned user positioning method embodiments, and can achieve the same technical effects. To avoid repetition, details are not described here.

[0181] It should be understood that the chip mentioned in the embodiments of the present application can also be referred to as a system-level chip, a system chip, a chip system, or a system-on-chip chip, etc.

[0182] It should be noted that in this document, the term "comprising" or "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such a process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of additional identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to the order of performing the functions as shown or discussed, but can also include performing the functions in a substantially simultaneous manner or in reverse order, for example, the described method can be performed in an order different from that described, and various steps can also be added, omitted or combined. In addition, the features described with reference to some examples can be combined in other examples.

[0183] From the above description of the embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment method can be realized by means of software and necessary general hardware platform, of course, it can also be realized by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a plurality of instructions for making a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) execute the methods described in various embodiments of the present application.

[0184] The embodiments of the present application are described above with reference to the accompanying drawings, but the present application is not limited to the specific embodiments described above, and the specific embodiments described above are merely illustrative, but not restrictive, and a person of ordinary skill in the art can make many forms under the inspiration of the present application without departing from the purpose of the present application and the scope protected by the claims.

Claims

1. A user positioning method, comprising: obtaining network assisted global positioning system measurement report (AGPS MR) data in a plurality of grids, and performing feature processing on the AGPS MR data to obtain a first feature vector, wherein the AGPS MR data comprises location information of a center point of a grid to which the AGPS MR data belongs, and the first feature vector is used to represent data features of the AGPS MR data; determining a K-nearest neighbor (KNN) vector library based on the first feature vector, wherein each of the first feature vectors has label information representing a location of a center point of a grid to which the first feature vector belongs; obtaining measurement report (MR) data in the plurality of grids, and performing feature processing on the MR data to obtain a second feature vector, wherein the second feature vector is used to represent data features of the MR data; determining location information of a center point of a grid to which the MR data belongs based on the second feature vector and the KNN vector library; determining location information of a user corresponding to the MR data based on the location information of the center point of the grid to which the MR data belongs. 2.The method of claim 1, wherein the AGPS MR data comprises a serving cell signal strength, a serving cell Ts granularity, and a strongest neighbor cell signal strength, wherein the serving cell signal strength is a signal strength of a serving cell to which the AGPS MR data belongs, the serving cell Ts granularity is a Ts granularity of the serving cell to which the AGPS MR data belongs, and the strongest neighbor cell signal strength is a signal strength of a serving cell adjacent to the serving cell to which the AGPS MR data belongs and having a highest signal strength. The feature processing on the AGPS MR data to obtain the first feature vector comprises: determining the first feature vector based on the serving cell signal strength, the serving cell Ts granularity, and the strongest neighbor cell signal strength. 3.The method of claim 1, wherein the determination of the KNN vector library based on the first feature vector comprises: performing dictionary training based on the first feature vector to determine a first coding vector and a shared dictionary, wherein the first coding vector is a sparse matrix corresponding to the first feature vector; and determining the KNN vector library based on the first coding vector. 4.The method of claim 3, wherein the determination of the location information of the center point of the grid to which the MR data belongs based on the second feature vector and the KNN vector library comprises: determining a second coding vector based on the second feature vector and the shared dictionary; and determining the location information of the center point of the grid to which the MR data belongs based on the second coding vector and the KNN vector library. 5.The method of claim 3, wherein the dictionary training based on the first feature vector to determine the first coding vector and the shared dictionary comprises: obtaining an initial dictionary, a first control factor, and a second control factor, wherein the first control factor is used to determine a first preset area in the initial dictionary, and the second control factor is used to determine a second preset area in the initial dictionary. determining a first feature code based on the initial dictionary, the first control factor and the second control factor; determining a first feature code meeting a first preset condition, and determining the shared dictionary based on the first feature code meeting the first preset condition, wherein the first preset condition is that a value of the first feature code is less than a threshold. 6.The method of claim 4, wherein the determining the location information of the grid center point to which the common MR data belongs based on the second encoding vector and the KNN vector library comprises: determining a plurality of first encoding vectors meeting a second preset condition in the KNN vector library based on the second encoding vector, wherein the second preset condition is that a distance to the second encoding vector is less than a threshold; determining the location information of the grid center point to which the second encoding vector belongs based on AGPS MR data corresponding to the plurality of first encoding vectors; determining the location information of the grid center point to which the common MR data belongs based on the location information of the second encoding vector. 7.The method of claim 1, wherein before the acquiring the AGPS MR data in the plurality of grids, the method further comprises: determining the location information of the plurality of grid center points; acquiring the AGPS MR data, and determining the location information of the grid center point to which each of the AGPS MR data belongs based on the AGPS MR data and the location information of the plurality of grid center points. 8.A user positioning apparatus, comprising: a first acquiring module, configured to acquire AGPS MR data in a plurality of grids, and perform feature processing on the AGPS MR data to obtain a first feature vector, wherein the AGPS MR data comprises location information of a grid center point to which the AGPS MR data belongs, and the first feature vector is used to represent data features of the AGPS MR data; a first determining module, configured to determine a KNN vector library based on the first feature vector, wherein each of the first feature vectors has label information representing a location of a grid center point to which the first feature vector belongs; a second acquiring module, configured to acquire common MR data in the plurality of grids, and perform feature processing on the common MR data to obtain a second feature vector, wherein the second feature vector is used to represent data features of the common MR data; a second determining module, configured to determine location information of a grid center point to which the common MR data belongs based on the second feature vector and the KNN vector library; a third determining module, configured to determine location information of a user corresponding to the common MR data based on the location information of the grid center point to which the common MR data belongs.

9. A computer device, comprising: The apparatus comprises: a processor; and a memory arranged to store computer executable instructions configured to be executed by the processor, the executable instructions comprising instructions for performing steps in the method of any one of claims 1 to 7.

10. A storage medium, characterized by The storage medium is configured to store computer executable instructions, the executable instructions causing a computer to perform the method of any one of claims 1 to 7.

Images