Method for determining relative location of terminal, and base station and computer-readable medium

Abstract

Provided in the present disclosure is a method for determining the relative location of a terminal. The method comprises: acquiring a set of time series feature vectors, wherein the set of time series feature vectors comprises a time series feature vector of at least one terminal, and the time series feature vector is composed of feature values ​​of at least one key performance indicator of the terminal that correspond to a plurality of moments; determining at least one terminal group on the basis of the set of time series feature vectors; and determining the relative location between terminal groups on the basis of the relationship between time series feature vectors corresponding to the terminal groups. Further provided in the present disclosure are a base station and a computer-readable storage medium.

Description

Method for determining relative position of terminal, base station and computer-readable medium

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to Chinese patent application No. 202311001906.0 filed with the China Patent Office on August 9, 2023, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The present disclosure relates to, but is not limited to, the field of communication technology. Background Art

[0004] The operating length of high-speed rail lines reaches 28,000 kilometers, and the length under construction reaches 12,000 kilometers. With the development of communication technology and mobile terminal equipment, users have increasingly higher requirements for networks in specific scenarios (such as high-speed rail) in recent years. Ensuring the user experience of high-speed rail users has become one of the main goals of mobile operators.

[0005] To ensure a better user experience for high-speed rail users, network operators and equipment vendors have two key initiatives: First, they are establishing dedicated network services for high-speed rail users and optimizing their technical support. For example, in the high-speed rail scenario, base stations can identify high-speed rail users, thereby ensuring that mobile devices on the train remain within dedicated network coverage areas. Second, in research on base station algorithms for identifying high-speed rail users, the user experience of dedicated high-speed rail networks is enhanced by identifying their location.

[0006] However, it is currently impossible to accurately identify the relative positions of high-speed rail users. In other words, the current communication network is not able to perceive the user distribution in specific communication scenarios (such as high-speed rail), resulting in a lack of important input dimensions during network optimization. As a result, when adaptively configuring uplink and downlink control channel resources and service channel resources, inaccurate uplink and downlink configuration occurs, which has a significant impact on high-speed rail trajectory identification.

[0007] Summary of the Invention

[0008] Embodiments of the present disclosure provide a method for determining the relative position of a terminal, a base station, and a computer-readable medium.

[0009] In a first aspect, an embodiment of the present disclosure provides a method for determining the relative position of a terminal, comprising: obtaining a set of timing feature vectors, wherein the set of timing feature vectors includes a timing feature vector of at least one of the terminals, and the timing feature vector is composed of feature values ​​of at least one key performance indicator of the terminal corresponding to multiple moments; determining at least one terminal grouping based on the set of timing feature vectors; and determining the relative positions between each of the terminal groups based on the relationship between the timing feature vectors corresponding to each of the terminal groups.

[0010] In a second aspect, an embodiment of the present disclosure provides a base station, comprising: one or more processors; a memory on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the relative position determination method of the terminal described in the first aspect of the embodiment of the present disclosure.

[0011] In a third aspect, an embodiment of the present disclosure provides a computer-readable medium having a computer program stored thereon. When the program is executed by a processor, the processor implements the method for determining the relative position of the terminal described in the first aspect of the embodiment of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] FIG1 is a flow chart of a method for determining a relative position of a terminal according to an embodiment of the present disclosure;

[0013] FIG2 is a flowchart of some steps in another method for determining the relative position of a terminal according to an embodiment of the present disclosure;

[0014] FIG3 is a flow chart of a preset clustering algorithm for determining terminal grouping in an embodiment of the present disclosure;

[0015] FIG4 is a flowchart of some steps in another method for determining the relative position of a terminal according to an embodiment of the present disclosure;

[0016] FIG5 is a flowchart of some steps in another method for determining the relative position of a terminal according to an embodiment of the present disclosure;

[0017] FIG6 is a flow chart of determining the relative positions of terminals according to an embodiment of the present disclosure;

[0018] FIG7 is a flowchart of some steps in another method for determining the relative position of a terminal according to an embodiment of the present disclosure;

[0019] FIG8 is a schematic structural diagram of a base station according to an embodiment of the present disclosure;

[0020] FIG9 is a result diagram of a computer-readable medium according to an embodiment of the present disclosure;

[0021] FIG10 is a flowchart of a portion of steps in an embodiment of a method for determining a relative position of a terminal according to an embodiment of the present disclosure;

[0022] FIG11 is a flowchart of another part of the steps in an embodiment of a method for determining a relative position of a terminal according to an embodiment of the present disclosure;

[0023] 12 is a flowchart of some steps in an embodiment of another method for determining the relative position of a terminal according to an embodiment of the present disclosure;

[0024] FIG13 is a flowchart of some steps in an embodiment of another method for determining the relative position of a terminal in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] To enable those skilled in the art to better understand the technical solution of the present disclosure, the relative position determination method of a terminal, a base station, and a computer-readable medium provided by the present disclosure are described in detail below with reference to the accompanying drawings.

[0026] Example embodiments will be described more fully hereinafter with reference to the accompanying drawings, but the example embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth in this disclosure. Rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the scope of this disclosure to those skilled in the art.

[0027] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0028] As used in this disclosure, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0029] The terms used in this disclosure are only used to describe specific embodiments and are not intended to limit the disclosure. As used in this disclosure, the singular forms "a," "an," and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements, and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups thereof is not excluded.

[0030] Unless otherwise defined, all terms (including technical and scientific terms) used in this disclosure have the same meanings as those commonly understood by those skilled in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this disclosure, and will not be interpreted as having an idealized or overly formal meaning unless expressly defined in this disclosure.

[0031] FIG1 is a flowchart of a method for determining a relative position of a terminal according to an embodiment of the present disclosure.

[0032] In a first aspect, referring to FIG1 , an embodiment of the present disclosure provides a method for determining a relative position of a terminal, the method comprising:

[0033] S1. Acquire a set of time series feature vectors, wherein the set of time series feature vectors includes a time series feature vector of at least one terminal, and the time series feature vector is composed of feature values ​​of at least one key performance indicator of the terminal corresponding to multiple time moments;

[0034] S2. Determine at least one terminal group according to the set of timing feature vectors;

[0035] S3. Determine relative positions between the terminal groups based on the relationship between the time series feature vectors corresponding to the terminal groups.

[0036] In an embodiment of the present disclosure, the method for determining the relative position of a terminal can be applied to, for example, a high-speed rail communication scenario, which has the characteristics of a large linear span and a fast terminal movement speed within the coverage area of ​​the base station, but the application scenario of the method is not limited thereto, and can be any other communication scenario with this characteristic. The application environment of the method is an adaptive optimization scenario of terminal relative position identification driven by data of NR (New Radio), LTE (Long Term Evolution), FDD (Frequency Division Duplexing), and TDD (Time Division Duplexing). Based on the characteristics of this scenario, analyzing multiple key performance indicators that affect the determination of relative position can effectively improve the accuracy and reduce the judgment error of the relative position.

[0037] Among them, the set of timing feature vectors describes the characteristic values ​​of at least one key performance indicator of at least one terminal at multiple moments, and the key performance indicator is an indicator related to the relative position of the terminal selected based on the scheduling data analysis within the scene; among them, the multiple moments of the timing feature vector refer to moments separated by a preset time interval, and the preset time interval can be determined according to actual conditions.

[0038] The embodiments of the present disclosure do not impose any special restrictions on the relationship between the time series feature vectors. It can be a statistical value representing the time series feature vector corresponding to each terminal in the terminal group, such as the median, average, etc., or it can be the time series feature vector corresponding to the cluster center of the terminal group.

[0039] The relative positions between terminal groups are to regard the terminals in the group as a whole, take one terminal group as a reference, and describe the position of another terminal group relative to the reference. The present disclosure uses the relative positions between terminal groups as the relative positions between the terminals in the terminal group. The relative positions can be fixed or not, and will change with the change of the reference.

[0040] The embodiment of the present disclosure determines the relative position of the terminal by a time series feature vector composed of multiple feature values ​​corresponding to at least one selected key performance indicator, and can accurately judge the relative position between terminals from multiple dimensions, thereby improving the recognition of the terminal. In addition, the method is deployed in a base station, and the relative position of the terminal is identified on the base station side, without the need to use external data and / or measurement report data for relative position identification, which is more efficient.

[0041] In some embodiments, the key performance indicator includes at least one of frequency offset, cell portion, timing advance, transmit power, and super cell identifier. Key performance indicators include essential and supplementary indicators. In some examples, frequency offset, cell portion (CP), and timing advance (TA) are essential indicators, while transmit power and super cell identity document (ID) are supplementary indicators. CP reflects the cell in which the terminal is located, and TA reflects the distance between the terminal and the base station. Timing advance can be the same or different at different times.

[0042] In the embodiments of the present disclosure, a Key Performance Indicator (KPI) is an indicator related to the relative position of terminals, obtained through analysis. The KPI describes the characteristic quantities associated with the relative positions of multiple terminals moving at high speed within the coverage area of ​​a base station. The characteristic values ​​of the KPI can be used to quantitatively measure the positional relationships between the corresponding terminals. The characteristic values ​​of the KPI corresponding to different moments in time form a time series feature vector.

[0043] On the basis of necessary indicators, auxiliary indicators are added to determine the relative position of the terminal from multiple dimensions, which improves the recognition.

[0044] Key performance indicators are obtained by analyzing and selecting features related to the relative position of the terminal. For example, the characteristic values ​​of the terminal with respect to the key performance indicators at different times can be used to determine the positional relationship between the terminal and the base station. The characteristic values ​​of the key performance indicators of the terminal at different times can be used to define a timing characteristic vector. The timing characteristic vector includes the characteristic values ​​of necessary indicators (such as frequency deviation, CP, and Ta), and can also include the characteristic values ​​of auxiliary indicators (such as transmit power, super cell ID, etc.).

[0045] In some embodiments, referring to FIG. 2 , S1 may include:

[0046] S11. Obtain characteristic values ​​of at least one key performance indicator of each terminal corresponding to multiple moments, and determine a time series characteristic vector of each terminal;

[0047] S12: Construct a set of time series feature vectors based on the time series feature vector of at least one terminal.

[0048] In this embodiment, analysis is performed based on various scheduling data collected by the base station to obtain key performance indicators related to the relative positions between terminals, and the characteristic values ​​of the key performance indicators are used at different times to construct a time series feature vector; the scheduling data refers to the scheduling resource data allocated to the terminal by the network side and the resource data reported by the service when the terminal communicates within the coverage area of ​​the base station.

[0049] The time series feature vector of each terminal includes the feature values ​​of at least one key performance indicator corresponding to multiple moments. For example, the time series feature vector of the terminal UE1 is [f 1t1 ,f 1t2 ,f 1t3 ,......,f 1t9 ,f 1t10 ], where f 1t1 Indicates the frequency offset of UE1 at time t1.

[0050] In one example, the timing feature vectors of terminals in a high-speed rail scenario are determined. A base station collects high-speed rail wireless dispatch data, which primarily describes the dispatch resource data allocated to terminals by the network when users use the terminals on the train, as well as the resource data reported by the terminals during service. Key performance indicators related to the relative position of the terminals in the high-speed rail wireless dispatch data are analyzed and selected, and timing feature vectors are constructed using the eigenvalues ​​of the key performance indicators at multiple time points.

[0051] In some embodiments, determining at least one terminal group according to the set of timing feature vectors includes:

[0052] According to the set of time series feature vectors, clustering processing is performed on the terminals using a preset clustering algorithm to obtain at least one terminal group.

[0053] The embodiments of the present disclosure do not limit the preset clustering algorithm, which may be k-means (k-means clustering algorithm), GMM (Gaussian Mixture Model), etc.

[0054] Clustering is based on the degree of similarity or difference between each terminal's time series feature vector and the cluster center within the time series feature vector set. In some examples, the degree of similarity or difference between each terminal's time series feature vector and the cluster center can be quantified by calculating the distance or similarity between the terminal and the cluster center. The resulting terminal groups are diverse, and the terminals within each terminal group are similar.

[0055] The clustering results (i.e., terminal groupings) follow the following clustering rules: the feature vectors of each terminal within a class are similar, while the feature vectors of each terminal between classes are different. Each class is a terminal group. Intra-class similarity refers to the similarity of the time series feature vectors of terminals within a terminal group of the same class, centered around the time series feature vector of the cluster center of that terminal group. Inter-class difference refers to the difference of the time series feature vectors of the cluster centers of terminal groups of different classes.

[0056] It is worth noting that when the terminals are grouped by a preset clustering algorithm, the relationship between the timing feature vectors corresponding to the terminal group can be the relationship between the cluster center timing feature vectors corresponding to the terminal group, and the cluster center can represent the center position or average position of the timing feature vectors of all terminals in its terminal group.

[0057] Referring to Figure 3, in some embodiments, in the high-speed rail communication scenario, the base station collects the timing feature vectors of multiple user terminals within its coverage area, constructs a timing feature vector data set (that is, a set of timing feature vectors), and clusters the user terminals according to the number of high-speed rail carriages k through a preset clustering algorithm to obtain k terminal groups; there are differences in the cluster center timing feature vectors corresponding to the cluster centers of the k terminal groups, and there are similarities in the cluster center timing feature vectors of each terminal in each terminal group and its corresponding cluster center, that is, the terminal characteristics within the class are similar, and the terminal characteristics between classes are different.

[0058] In some embodiments, determining at least one terminal group according to the set of timing feature vectors includes:

[0059] According to the set of time series feature vectors, the terminals are classified by a preset classifier to obtain at least one terminal group.

[0060] The embodiments of the present disclosure do not limit the preset classifier, which may be a recursive neural network classifier, an attention mechanism classifier, etc. In some examples, the preset classifier is obtained by neural network training.

[0061] The classification process is based on the degree of similarity or difference between the timing feature vectors of each terminal in the timing feature vector set, or the degree of similarity or difference between the timing feature vector of each terminal in the timing feature vector set and a preset number of reference feature vectors. In some examples, the degree of similarity or difference can be quantified by calculating the distance or similarity between the two. The terminal groups obtained by classification are different from each other, and the terminals contained in each terminal group are similar.

[0062] The classification rules followed by terminal grouping are: the feature vectors of each terminal within a class are similar, and the feature vectors of each terminal between classes are different. Similarity within a class refers to the similarity between the time series feature vectors of each terminal within the same class, or the similarity between the time series feature vectors of each terminal within the same class and a preset reference feature vector. Difference between classes refers to the statistical value of the reference feature vectors of terminal groups of different classes, which shows differences. This statistical value can be used to represent the central value or average value of the time series feature vectors of each terminal within the terminal group.

[0063] In some embodiments, before clustering the terminals using a preset clustering algorithm according to the set of time series feature vectors to obtain at least one terminal group, the method further includes:

[0064] Obtaining a preset number of terminal groups;

[0065] The step of clustering the terminals using a preset clustering algorithm according to the set of time series feature vectors to obtain at least one terminal group includes:

[0066] According to the set of time series feature vectors, the terminals are clustered into a preset number of terminal groups using a preset clustering algorithm.

[0067] In this embodiment, the preset number of terminal groups is pre-set and can be fixed or dynamically changing. In some examples, in a high-speed rail communication scenario, the preset number is set to the total number of high-speed rail carriages. In other examples, the base station determines the preset number of terminal groups in response to an input instruction, and the input instruction can be used to indicate the preset number of terminal groups.

[0068] In some embodiments, when the terminal is located on a high-speed rail, the preset number is the number of carriages on the high-speed rail.

[0069] In an embodiment of the present disclosure, in a high-speed rail communication scenario, each terminal is located on the high-speed rail, and the preset number is determined as the number of carriages of the high-speed rail. Each terminal in each terminal group can be considered as a terminal located in the same carriage.

[0070] In some embodiments, referring to FIG. 4 , S3 includes:

[0071] S31. Determine a cluster center time series feature vector corresponding to the cluster center of the terminal group as the time series feature vector corresponding to the terminal group;

[0072] S32: Determine relative positions between the terminal groups according to the relationship between the cluster center time series feature vectors corresponding to the terminal groups.

[0073] In this embodiment, the cluster center of a terminal group is the center of the terminal group obtained by a preset clustering algorithm. It can represent the average or central characteristics of this terminal group. The cluster center can be used to understand the characteristics of each cluster (i.e., terminal group) and can be used as a representative of each cluster for subsequent analysis or calculation. Here, the cluster center time series feature vector of the cluster center represents the time series feature vector corresponding to its terminal group. The relationship between the cluster center time series feature vectors is used as the relationship between the time series feature vectors corresponding to each terminal group to determine the relative positions of the terminal groups.

[0074] The embodiments of the present disclosure do not limit the type of relationship between cluster center time series feature vectors. It can be a numerical value relationship or a numerical absolute value relationship, etc., which can be determined based on the actual situation of the KPI.

[0075] In some embodiments, referring to FIG. 5 , S32 includes:

[0076] S321. Determine the order of the plurality of terminal groups according to the relationship between the cluster core timing feature vectors corresponding to the respective terminal groups, wherein the relationship between the cluster core timing feature vectors represents the positional relationship of the terminal groups relative to the base station;

[0077] S322: Determine relative positions between the terminal groups according to the order of the plurality of terminal groups.

[0078] In this embodiment, the positional relationship of terminal groups relative to a base station is determined using the base station as a reference and terminal groups as units. Sorting criteria can be based on the magnitude, positive or negative value, and other factors of the cluster center time series feature vectors. The ranking of multiple terminal groups represents the positional order of the terminal groups, thereby determining the relative positions of the terminal groups. In some examples, the ranking can represent the hierarchical order of the terminal groups.

[0079] The principle of sorting terminal groups is as follows: taking clusters as units, counting the time series feature vectors of the cluster centers of each cluster, using the eigenvalues ​​of the constructed time series feature vectors to sort the clusters and determine the relative position relationship of the terminal groups in each cluster.

[0080] Referring to Figure 6, in some examples, in the high-speed rail communication scenario, k clusters are obtained by clustering, each cluster corresponds to a terminal group, and feature analysis is performed on the terminals corresponding to each cluster in turn to obtain the cluster level of the terminal group, and the cluster levels are sorted to determine the relative position relationship of the terminal groups, thereby determining the relative positions between the terminal groups.

[0081] In some embodiments, referring to FIG. 7 , S321 includes:

[0082] S3211: Compare the cluster center time series feature vectors corresponding to the terminal groups to obtain a comparison result, where the comparison result reflects the orientation and distance of the terminal group relative to the base station;

[0083] S3212: Determine the order of the plurality of terminal groups according to the comparison result.

[0084] In this embodiment, the base station is used as a reference and the position and distance of each terminal relative to the base station are determined by comparison. The position here can be determined according to the displacement direction of each terminal, such as the movement direction away from the base station on one side and the movement direction close to the base station on the other side.

[0085] In some embodiments, determining the order of the plurality of terminal groups according to the comparison result includes:

[0086] Determine, based on the comparison result, a displacement direction of the terminal group relative to the base station, to obtain a first number of terminal groups whose displacement directions are close to the base station and a second number of terminal groups whose displacement directions are far from the base station;

[0087] According to the distance of the comparison result, the first number of terminal groups are sorted according to a first preset order, and the second number of terminal groups are sorted according to a second preset order; the first preset order reflects that the distance of the terminal group relative to the base station decreases in sequence, and the second preset order reflects that the distance of the terminal group relative to the base station increases in sequence.

[0088] In an embodiment of the present disclosure, a cluster center time series feature vector includes feature values ​​of a KPI of a terminal group corresponding to multiple time points. Based on the feature values ​​at the multiple time points, a displacement direction of the terminal group can be determined. The terminal groups are divided according to the displacement directions, and the displacement directions are determined to be a first number of terminal groups far away from the base station and a second number of terminal groups close to the base station.

[0089] The terminal groups are sorted according to their displacement directions. The first number of terminal groups far away from the base station are sorted from large to small according to distance, and the smaller the distance, the closer they are to the base station; the second number of terminal groups close to the base station are sorted from small to large according to distance, and the smaller the distance, the closer they are to the base station; the minimum distance value of the sorted first number of terminal groups and the minimum distance value of the sorted second number of terminal groups are spliced ​​to obtain the sorting of multiple terminal groups.

[0090] In some examples, the total number of terminal groups is N. The sign of the frequency offset can reflect the displacement direction of the terminal group, and the value of the frequency offset can reflect the distance of the terminal relative to the base station. When the KPI corresponding to the cluster center timing eigenvector is frequency offset, the terminal group sorting process is as follows:

[0091] Based on the N terminal groups, k terminal groups whose cluster center timing characteristic vectors corresponding to the frequency offset are positive, and (Nk) terminal groups whose cluster center timing characteristic vectors corresponding to the frequency offset are negative are determined; wherein the k terminal groups with positive frequency offsets indicate that the terminal groups are close to the base station, and the (Nk) terminal groups with negative frequency offsets indicate that the terminal groups are far away from the base station;

[0092] Arrange the k terminal groups in the i-th position according to the descending order of the cluster center time series feature vectors, and obtain the ranking of the k terminal groups, where i is taken from 1 to k;

[0093] Arrange the (Nk) terminal groups in the jth position according to the absolute value of the cluster center time series feature vector from small to large, and obtain the ranking of the (Nk) terminal groups, where j is taken from (k+1) to N in sequence, i, j, k, N are all positive integers, 0 <k≤N。

[0094] In one example, taking the high-speed rail with 10 carriages all traveling towards a base station as an example, the relative position of each terminal is determined as follows.

[0095] Based on the time series feature vector set, a preset clustering algorithm is used. The preset number of clusters is the number of carriages (i.e., 10), and the clustering result is determined to be 10 terminal groups. The terminal groups have similarities within each cluster and differences between clusters.

[0096] Determine the cluster core timing feature vector of the cluster core of each terminal group, and analyze the KPIs (time, frequency offset, CP, Ta) that constitute the cluster core timing feature vector.

[0097] Traverse the 10 terminal groups, sort the terminal groups according to the cluster center timing feature vectors, and sort the 10 terminal groups in descending order of frequency deviation and Ta, that is, the frequency deviation of the cluster center timing feature vector of the a-th terminal group is greater than the frequency deviation of the cluster center timing feature vector of the (a+1)-th terminal group, and the Ta feature value of the cluster center timing feature vector of the a-th terminal group is greater than the Ta feature value of the cluster center timing feature vector of the (a+1)-th terminal group. In this way, the position of the leftmost carriage of the high-speed rail corresponds to the position of the terminal in the first terminal group.

[0098] Repeat the above process until all 10 terminal groups are sorted, and determine the sorting status of each terminal group. The sorting status reflects the position of the terminal in the terminal group corresponding to the position of the carriage from left to right.

[0099] According to the sorting situation, the relative positions of the terminals on the high-speed rail are determined in terminal grouping units.

[0100] In another example, taking a high-speed rail with 10 carriages crossing a base station (i.e., the displacement direction of some carriages is away from the base station, and the displacement direction of other carriages is close to the base station) as an example, the relative position of each terminal is determined as follows.

[0101] Based on the time series feature vector set, a preset clustering algorithm is used. The preset number of clusters is the number of carriages (i.e., 10), and the clustering result is determined to be 10 terminal groups. The terminal groups have similarities within each cluster and differences between clusters.

[0102] Determine the cluster core timing feature vector of the cluster core of each terminal group, and analyze the KPIs (time, frequency offset, CP, Ta) that constitute the cluster core timing feature vector.

[0103] Traverse the 10 terminal groups and sort them according to the cluster center timing eigenvector. The frequency offset corresponding to the terminal group on the high-speed rail on one side of the base station is positive, and the frequency offset corresponding to the terminal group on the other side of the base station is negative. That is, the orientation of the terminal group relative to the base station is divided according to the cluster center timing eigenvector.

[0104] Sort the x terminal groups with positive frequency deviations in descending order of frequency deviation and Ta, that is, the frequency deviation of the cluster center timing feature vector of the first terminal group is greater than the frequency deviation of the cluster center timing feature vector of other terminal groups, and the Ta feature quantity of the cluster center timing feature vector of the first terminal group is greater than the Ta feature quantity of the cluster center timing feature vector of other terminal groups. At the same time, the frequency deviation of the cluster center timing feature vector of the bth terminal group is greater than the frequency deviation of the cluster center timing feature vector of the (b+1)th terminal group, and the Ta feature quantity of the cluster center timing feature vector of the bth terminal group is greater than the Ta feature quantity of the cluster center timing feature vector of the (b+1)th terminal group. In this way, the positions of the terminals in the 1st to xth terminal groups corresponding to the positions of the carriages on one side of the high-speed rail are determined.

[0105] The (10-x) terminal groups with negative frequency deviation are sorted in ascending order according to the absolute value of the frequency deviation and Ta, that is, the absolute value of the frequency deviation of the cluster center timing feature vector of the 10th terminal group is greater than the absolute value of the frequency deviation of the cluster center timing feature vector of other terminal groups, and the Ta feature quantity of the cluster center timing feature vector of the 10th terminal group is greater than the Ta feature quantity of the cluster center timing feature vector of other terminal groups. At the same time, the absolute value of the frequency deviation of the cluster center timing feature vector of the (c+1)th terminal group is greater than the absolute value of the frequency deviation of the cluster center timing feature vector of the cth terminal group, and the Ta feature quantity of the cluster center timing feature vector of the (c+1)th terminal group is greater than the Ta feature quantity of the cluster center timing feature vector of the cth terminal group. In this way, the position of the terminal in the (x+1)th to 10th terminal groups corresponding to the position of the carriage on the other side of the high-speed rail is determined.

[0106] Repeat the above process until all 10 terminal groups are sorted, and determine the sorting status of each terminal group. The sorting status reflects the position of the terminal in the terminal group corresponding to the position of the carriage from left to right.

[0107] According to the sorting situation, the relative positions of the terminals on the high-speed rail are determined in terminal grouping units.

[0108] In another example, taking the high-speed rail with 10 carriages all traveling away from the base station as an example, the relative position of each terminal is determined as follows.

[0109] Based on the time series feature vector set, a preset clustering algorithm is used. The preset number of clusters is the number of carriages (i.e., 10), and the clustering result is determined to be 10 terminal groups. The terminal groups have similarities within each cluster and differences between clusters.

[0110] Determine the cluster core timing feature vector of the cluster core of each terminal group, and analyze the KPIs (time, frequency offset, CP, Ta) that constitute the cluster core timing feature vector.

[0111] Traverse 10 terminal groups and sort the terminal groups according to the cluster core timing feature vectors, that is, the absolute value of the frequency deviation of the cluster core timing feature vector of the 10th terminal group is greater than the absolute value of the frequency deviation of the cluster core timing feature vectors of other terminal groups, and the Ta feature quantity of the cluster core timing feature vector of the 10th terminal group is greater than the Ta feature quantity of the cluster core timing feature vectors of other terminal groups. At the same time, the absolute value of the frequency deviation of the cluster core timing feature vector of the (d+1)th terminal group is greater than the absolute value of the frequency deviation of the cluster core timing feature vector of the dth terminal group, and the Ta feature quantity of the cluster core timing feature vector of the (d+1)th terminal group is greater than the Ta feature quantity of the cluster core timing feature vector of the dth terminal group. In this way, the positions of the terminals in the 1st to 10th terminal groups corresponding to the positions of the high-speed rail cars are determined.

[0112] Repeat the above process until all 10 terminal groups are sorted, and determine the sorting status of each terminal group. The sorting status reflects the position of the terminal in the terminal group corresponding to the position of the carriage from left to right.

[0113] According to the sorting situation, the relative positions of the terminals on the high-speed rail are determined in terminal grouping units.

[0114] In some embodiments, after determining the relative positions of the terminal groups based on the relationship between the timing feature vectors corresponding to the terminal groups, the method further includes:

[0115] Channel resources are configured according to the relative positions and service requirements of the terminal groups.

[0116] In this embodiment, the network is optimized based on the relative positions of each terminal group. Channel resources, including uplink channel resources, downlink channel resources, and service channel resources, are configured based on different service requirements, including those for uplink and downlink channels. Channel resources can be adaptively configured. In some examples, adaptive configuration is performed by a network optimization module whose input is the relative positions of each terminal group.

[0117] Based on the accurate determination of the relative positions between terminal groups, the uplink and downlink service demands of the terminals in the scenario are accurately identified, and uplink and downlink control channel resources and service channel resources are adaptively configured, thereby improving the user experience in the scenario.

[0118] In the embodiments of the present disclosure, key performance indicators include not only necessary indicators but also auxiliary indicators. These indicators are all associated with determining relative positions, and the relative positions of terminals can be identified from multiple dimensions. In addition, after constructing a set of timing feature vectors, the relative positions of the terminals are determined based on the positional relationship of the terminals relative to the base station through analysis of the key performance indicators, thereby improving the accuracy of relative position determination.

[0119] The embodiments of the present disclosure analyze and determine the KPIs associated with relative positions based on the scheduling data collected by the base station, group the terminals using clustering or classifiers, perceive the relative position relationship of the terminals in the scenario, and use this as input to identify uplink and downlink service needs and adaptively configure control channel resources and service channel resources.

[0120] The method for determining the relative position of terminals includes a data collection and analysis module, a grouping module, and a network optimization module. The data collection and analysis module is used to analyze and select KPIs related to user locations from the scheduling data collected by the base station, and construct a set of time series feature vectors; the grouping module is used to group terminals using clustering or classifiers, with the number of high-speed rail carriages as the total number of groups, and analyze the time series feature vectors of each terminal group based on the grouping to determine the relative position relationship of the terminals; the network optimization module is used to configure channel resources based on relative positions and business needs.

[0121] In the second aspect, referring to Figure 8, an embodiment of the present disclosure provides a base station, which includes: one or more processors 801; a memory 802, on which one or more programs are stored, and when the one or more programs are executed by one or more processors, the one or more processors implement any of the above-mentioned methods for determining the relative position of the terminal; one or more I / O interfaces 803, connected between the processor and the memory, and configured to implement information interaction between the processor and the memory.

[0122] Among them, the processor 801 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 802 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically such as SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read-write interface) 803 is connected between the processor 801 and the memory 802, and can realize information exchange between the processor 801 and the memory 802, including but not limited to a data bus (Bus), etc.

[0123] In some embodiments, the processor 801 , the memory 802 , and the I / O interface 803 are connected to each other via a bus 804 , and further connected to other components of the computing device.

[0124] The structure shown in FIG8 is for illustration only and does not limit the structure of the above-mentioned base station. For example, the base station may include more or fewer components than those shown in FIG8 , or may have a configuration different from that shown in FIG8 .

[0125] In a third aspect, referring to FIG9 , an embodiment of the present disclosure provides a computer-readable medium having a computer program stored thereon. When the program is executed by a processor, the processor implements any of the above-mentioned methods for determining the relative position of a terminal.

[0126] In order to enable those skilled in the art to more clearly understand the technical solutions provided by the embodiments of the present disclosure, the technical solutions provided by the embodiments of the present disclosure are described in detail below through exemplary embodiments:

[0127] In the first embodiment, referring to FIG10 and FIG11 , the base station performs adaptive configuration for network optimization in a high-speed rail communication scenario:

[0128] The base station collects high-speed rail wireless dispatching data, analyzes and selects KPIs related to the relative position of the terminal, and uses KPIs to construct time series feature vectors at different time sequences. The time series feature vectors constitute a time series feature vector set.

[0129] According to the set of time series feature vectors, the terminals are clustered to obtain k terminal groups. The intra-class features of each terminal group are similar, and the inter-class features are different.

[0130] A feature analysis is performed on each terminal group to determine the ranking of each terminal group, and based on the ranking of the terminal groups, the relative position relationship of each terminal group is determined.

[0131] Channel resources are allocated based on the relative positions of the terminal groups to optimize the network.

[0132] In the second embodiment, in a high-speed rail communication scenario, the base station uses the k-means algorithm to determine the relative position relationship between terminals, thereby adaptively configuring network optimization:

[0133] First, a set of time series feature vectors is constructed. The base station collects high-speed rail wireless scheduling data, analyzes and selects KPIs related to the relative position of the terminal, and uses KPIs to construct time series feature vectors at different time series. The time series feature vectors constitute a set of time series feature vectors.

[0134] Then, referring to Figures 12 and 6, the k-means algorithm is used to cluster each terminal according to the set of time series feature vectors. The number of clusters is the number of carriages. Terminals with similar feature vectors are clustered into one category, and the terminal characteristic vectors within each cluster show differences. Based on the clustering results of the k-means algorithm, the time series feature vector characteristics of each type of terminal are analyzed, and the relative position relationship of each type of terminal is determined based on the cluster cluster, and then the relative position relationship of each type of terminal group is sorted.

[0135] Finally, the relative position relationship of each type of terminal group is input into the network optimization module as one of the network optimization inputs. According to different uplink and downlink service requirements, uplink and downlink control channel resources and service channel resources are adaptively configured.

[0136] In a third embodiment, in a high-speed rail communication scenario, a base station uses a GMM algorithm to determine the relative position relationship between terminals, thereby adaptively configuring network optimization.

[0137] First, a set of time series feature vectors is constructed. The base station collects high-speed rail wireless scheduling data, analyzes and selects KPIs related to the relative position of the terminal, and uses KPIs to construct time series feature vectors at different time series. The time series feature vectors constitute a set of time series feature vectors.

[0138] Then, referring to Figures 13 and 6, the GMM algorithm is used to cluster each terminal according to the set of time series feature vectors. The number of clusters is the number of carriages. Terminals with similar feature vectors are clustered into one category, and the terminal characteristic vectors within each cluster show differences. According to the clustering results of the GMM algorithm, the time series feature vector characteristics of each type of terminal are analyzed, and the relative position relationship of each type of terminal is determined based on the cluster cluster, and then the relative position relationship of each type of terminal group is sorted.

[0139] Finally, the relative position relationship of each type of terminal group is input into the network optimization module as one of the network optimization inputs. According to different uplink and downlink service requirements, uplink and downlink control channel resources and service channel resources are adaptively configured.

[0140] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware implementations, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As is well known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable, and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically embodies computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0141] The present disclosure has disclosed example embodiments, and although specific terms are employed, they are used and should be interpreted only in a general illustrative sense and not for purposes of limitation. In some instances, it will be apparent to those skilled in the art that, unless otherwise expressly indicated, features, characteristics, and / or elements described in conjunction with a particular embodiment may be used alone or in combination with features, characteristics, and / or elements described in conjunction with other embodiments. Therefore, it will be understood by those skilled in the art that various changes in form and detail may be made without departing from the scope of the present disclosure as set forth in the appended claims.

Claims

1. A method for determining a relative position of a terminal, comprising: Acquire a set of time series feature vectors, wherein the set of time series feature vectors includes at least one time series feature vector of the terminal, and the time series feature vector is composed of feature values ​​of at least one key performance indicator of the terminal corresponding to multiple moments; Determining at least one terminal group according to the set of timing feature vectors; The relative positions between the terminal groups are determined according to the relationship between the time sequence feature vectors corresponding to the terminal groups.

2. The method for determining the relative position of a terminal according to claim 1, wherein: Get the terminal's timing feature vector set, including: Acquire characteristic values ​​of at least one key performance indicator of each of the terminals corresponding to multiple time periods, and determine a time series characteristic vector of each of the terminals; A set of timing feature vectors is constructed according to the timing feature vector of at least one terminal.

3. The method for determining the relative position of a terminal according to claim 1, wherein: Determining at least one terminal group according to the set of timing feature vectors includes: According to the set of time series feature vectors, clustering processing is performed on the terminals by using a preset clustering algorithm to obtain at least one terminal group.

4. The method for determining the relative position of a terminal according to claim 3, wherein: Before clustering the terminals according to the set of time series feature vectors by using a preset clustering algorithm to obtain at least one terminal group, the method further includes: Obtaining a preset number of terminal groups; According to the set of time series feature vectors, clustering the terminals by a preset clustering algorithm to obtain at least one terminal group includes: According to the set of time series feature vectors, the terminals are clustered into a preset number of terminal groups by using a preset clustering algorithm.

5. The method for determining the relative position of a terminal according to claim 4, wherein: When the terminal is located on a high-speed rail, the preset number is the number of carriages of the high-speed rail.

6. The method for determining the relative position of a terminal according to claim 1, wherein: Determining at least one terminal group according to the set of timing feature vectors includes: According to the set of time series feature vectors, the terminals are classified by a preset classifier to obtain at least one terminal group.

7. The method for determining the relative position of a terminal according to any one of claims 3 to 6, wherein: Determining relative positions between the terminal groups according to the relationship between the time series feature vectors corresponding to the terminal groups includes: Determine a cluster center time series feature vector corresponding to the cluster center of the terminal group as the time series feature vector corresponding to the terminal group; The relative positions between the terminal groups are determined according to the relationship between the cluster-center time series feature vectors corresponding to the terminal groups.

8. The method for determining the relative position of a terminal according to claim 7, wherein: Determining the relative positions between the terminal groups according to the cluster core timing feature vector includes: Determine the order of the plurality of terminal groups according to the relationship between the cluster core timing feature vectors corresponding to the respective terminal groups, wherein the relationship between the cluster core timing feature vectors represents the position relationship of the terminal groups relative to the base station; The relative positions between the terminal groups are determined according to the ranking of the plurality of terminal groups.

9. The method for determining the relative position of a terminal according to claim 7, wherein: Determining the order of the plurality of terminal groups according to the relationship between the cluster center time sequence feature vectors corresponding to the respective terminal groups includes: Comparing the cluster center time sequence feature vectors corresponding to each of the terminal groups to obtain a comparison result, wherein the comparison result reflects the orientation and distance of the terminal group relative to the base station; According to the comparison result, the order of the plurality of terminal groups is determined.

10. The method for determining the relative position of a terminal according to claim 9, wherein: Determining the order of the plurality of terminal groups according to the comparison result includes: Determine, according to the comparison result, a displacement direction of the terminal group relative to the base station, and obtain a first number of terminal groups whose displacement directions are close to the base station and a second number of terminal groups whose displacement directions are far from the base station; According to the distance of the comparison result, the first number of terminal groups are sorted according to a first preset order, and the second number of terminal groups are sorted according to a second preset order; the first preset order reflects that the distances of the terminal groups relative to the base station decrease in sequence, and the second preset order reflects that the distances of the terminal groups relative to the base station increase in sequence.

11. The method for determining the relative position of a terminal according to any one of claims 1 to 6, wherein: The key performance indicator includes at least one of frequency deviation, partial cell, timing advance, transmit power and super cell identifier.

12. The method for determining the relative position of a terminal according to any one of claims 1 to 6, wherein: After determining the relative positions between the terminal groups according to the relationship between the time series feature vectors corresponding to the terminal groups, the method further includes: Channel resources are configured according to the relative positions and service requirements between the terminal groups.

13. A base station, comprising: one or more processors; A memory having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the relative position determination method of the terminal according to any one of claims 1 to 12.

14. A computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the processor implements the method for determining the relative position of a terminal according to any one of claims 1 to 12.

Images