Map POI-based scene recognition method and system

Abstract

This invention discloses a scene recognition method and system based on map-based Points of Arrival (POIs), belonging to the field of wireless communication technology. The technical problem this invention aims to solve is how to quickly adapt to the ever-evolving requirements of scene analysis and improve network analysis efficiency. The technical solution adopted is as follows: This method is based on two-dimensional measurement data of time advance (TA) and eNodeB antenna angle of arrival (AOA) from the MRS measurement report, combined with base station baseline engineering parameter data and a GIS POI layer. The two-dimensional measurements are analyzed and separated, converted into GIS map data, and then overlapped, segmented, calculated, converged, and automatically identified scene information with the POI layer. Specifically, this involves: MR measurement report geographic model conversion; POI identification and association; and performance indicator association. The system includes a data acquisition module, a data processing module, a data analysis module, and a result presentation module.

Description

Technical Field

[0001] This invention relates to the field of wireless communication technology, specifically to a scene recognition method and system based on map points of interest (POIs). Background Technology

[0002] Given the current scale of LTE wireless services, the traditional method for locating, analyzing, and processing massive network service data is through signaling data. However, large-scale scenario correlation calculations often require the computation of tens of billions of data points, which is resource-intensive and time-consuming.

[0003] Meanwhile, existing analysis models require complex computations and a large amount of data to locate the scene using signaling data, which is necessary to achieve minute-level output of results on scene correlation.

[0004] Therefore, how to quickly adapt to the ever-evolving requirements of scenario analysis and improve network analysis efficiency is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] The technical objective of this invention is to provide a scene recognition method and system based on map POIs to address the problem of how to quickly adapt to the ever-evolving requirements of scene analysis and improve network analysis efficiency.

[0006] The technical objective of this invention is achieved as follows: a scene recognition method based on map POIs. This method uses two-dimensional measurement data of time advance (TA) and eNodeB antenna angle of arrival (AOA) from the MRS measurement report, combined with base station baseline engineering parameter data and a GIS POI layer. The two-dimensional measurements are analyzed and separated to convert them into GIS map data. This data is then overlapped, segmented, calculated, and aggregated with the POI layer to automatically identify scene information. Specifically:

[0007] MR measurement report geographic model conversion;

[0008] POI identification association;

[0009] Performance metrics are correlated.

[0010] Preferably, the two-dimensional measurement data of time advance (TA) and eNodeB antenna angle of arrival (AOA) in the MRS measurement report refers to the radio measurement data provided by the TD-LTE digital cellular mobile communication network radio operation and maintenance center (OMC-R); when the measurement method adopts periodic measurement, the reporting period is configured when the measurement task is customized; for a measurement, the reporting triggering method is event triggering or periodic triggering.

[0011] Base station baseline engineering parameter data is used to define the base station number and the base station latitude and longitude.

[0012] More ideally, the lead time (TA) is as follows:

[0013] Define the UE's uplink transmission time for its primary cell PUCCH / PUSCH / SRS; in RRC connection state, the eNodeB antenna angle of arrival (AOA) determines the TA adjustment value for each UE based on the measurement of the corresponding UE's uplink transmission. The TA adjustment value ranges from (0,1,2,...,1282)×16Ts; the latest time advance obtained this time is the sum of the previously recorded time advance and the adjustment value obtained by the eNodeB measurement this time;

[0014] The specific algorithm for the time advance TA value is as follows: During the random access process, the eNodeB antenna angle of arrival (AOA) determines the value of the time advance TA by measuring the received pilot signal. The value of the time advance TA ranges from (0, 1, 2, ..., 1282) × 16Ts.

[0015] The time advance (TA) value is used to determine the distance between the UE and the base station, to perform cell coverage analysis, to determine whether adjustments to the cell antenna are needed, and to determine whether the base station's coverage area is reasonable, and whether there are over-coverage or coverage shadow areas. At the same time, the time advance (TA) is used to assist in providing location services.

[0016] More preferably, the eNodeB antenna angle of arrival (AOA) is as follows:

[0017] Define an estimated angle for the user relative to a reference direction in a counterclockwise direction, where the reference direction is specified as true north; this measurement data represents the number of samples of antenna angle of arrival that meet the range conditions within the OMC-R statistical period, counted by interval.

[0018] The specific algorithm for calculating the eNodeB antenna angle of arrival (AOA) is as follows: the whole is 360 degrees. Using the reference direction of true north, the number of samples of antenna angle of arrival that meet the value range conditions within the statistical period are counted in intervals. The value range of the number of samples is (0,...,11).

[0019] The eNodeB antenna angle of arrival (AOA) is used to determine the user's location, provide positioning services, and perform coverage analysis.

[0020] Ideally, the geographic model conversion for MR measurement reports is as follows:

[0021] Each community is subdivided into 132 measurement intervals in two dimensions. Based on the proportion of sampling points, the community KPI indicators are further subdivided into each scenario, and the POI scenario indicator results are accurately aggregated.

[0022] The POI scenario index results are statistically analyzed by two-dimensional superposition of time advance (TA) and eNodeB antenna angle of arrival (AOA): time advance (TA) calculates the distance between the UE terminal and the base station, i.e., the TA0-TA10 interval; eNodeB antenna angle of arrival (AOA) calculates the deviation angle between the UE terminal and the base station, i.e., the AOA0-AOA11 interval.

[0023] Two-dimensional overlay statistics are used to generate information on the business activity areas of customers around the community.

[0024] More specifically, the POI identification association is as follows:

[0025] The time lead time (TA) is used to determine the distance between the UE terminal and the base station from a vertical dimension.

[0026] The eNodeB antenna angle of arrival (AOA) determines the angle between the UE and the base station location in the lateral dimension.

[0027] The location of the base station and the UE terminal is determined by taking the intersection of the time advance (TA) and the eNodeB antenna angle of arrival (AOA).

[0028] By continuously overlaying the two-dimensional measurement data of each base station to form a sampling point cluster dataset, and combining it with the scene base map in the mapinfo layer data, the results are directly overlaid and presented.

[0029] More specifically, the performance metrics are correlated as follows:

[0030] By combining the terminal's location identification information with the cell's performance index data, the index details are refined and then overlaid using a geographic location information algorithm to present the associated performance KPI results in a GIS-like manner.

[0031] Among them, the cell performance indicators include the number of RRC connections, traffic volume, data usage, call completion rate, and call drop rate.

[0032] A scene recognition system based on map POIs, the system includes,

[0033] The data acquisition module is used to collect map data, MR data, base station baseline operating parameter data, and cell performance index data;

[0034] The data processing module is used to preprocess data through GIS parsing, MR normalization, and parameter cleaning.

[0035] The data analysis module is used to analyze and separate the two-dimensional measurement data of time advance (TA) and eNodeB antenna angle of arrival (AOA) in the MRS measurement report, and combine it with the base station reference engineering parameter data and GIS POI layer. The two-dimensional measurement is converted into GIS map data by parsing and separating the data, and the data is then combined with the POI layer for overlapping and segmentation calculation, aggregation and automatic identification of scene information.

[0036] The results display module is used to identify associations through POIs, and combine the terminal's location information and cell performance index data to refine the index information. The results are then overlaid using a geographic location information algorithm to present the associated performance KPI results in a GIS manner.

[0037] An electronic device includes: a memory and at least one processor;

[0038] The memory contains computer programs;

[0039] The at least one processor executes the computer program stored in the memory, causing the at least one processor to perform the map-based POI-based scene recognition method as described above.

[0040] A computer-readable storage medium storing a computer program that can be executed by a processor to implement the map-based POI-based scene recognition method described above.

[0041] The scene recognition method and system based on map POIs of the present invention have the following advantages:

[0042] (i) This invention finds alternative data sources and association rules by associating POI scenes and GIS geographic locations, thereby improving network analysis efficiency and quickly adapting to the ever-evolving requirements of scene analysis.

[0043] (II) Based on the TA (time advance) and AOA (angle of arrival) data, POI data, and cell engineering parameter data in mobile phone measurement, this invention realizes the rapid output of mobile terminal occupancy scenario through GIS association, and analyzes the user scale and flow changes in different scenarios;

[0044] (III) Compared with the traditional method of dividing scene POI by geographical location, the correlation performance KPI results of the present invention are based on the user terminal perspective and are statistically analyzed based on the sampling points of UE activities, which can better reflect the distribution of user activities. Attached Figure Description

[0045] The invention will be further described below with reference to the accompanying drawings.

[0046] Appendix Figure 1 This is a flowchart of a map-based POI-based scene recognition method.

[0047] Appendix Figure 2 This is a structural block diagram of a map-based POI-based scene recognition system.

[0048] Appendix Figure 3 This is a two-dimensional representational distribution map for the measurement report. Detailed Implementation

[0049] The map-based POI-based scene recognition method and system of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0050] Example 1:

[0051] As attached Figure 1 As shown, this embodiment provides a scene recognition method based on map POIs. This method is based on the time advance (TA) and eNodeB antenna angle of arrival (AOA) two-dimensional measurement data from the MRS measurement report, combined with base station baseline engineering parameter data and GIS POI layers. The two-dimensional measurements are parsed and separated, converted into GIS map data, and then overlapped, segmented, calculated, and converged with the POI layers to automatically identify scene information; specifically as follows:

[0052] S1, MR measurement report geographic model conversion;

[0053] S2 and POI identification associations;

[0054] S3, performance index correlation.

[0055] In this embodiment, the two-dimensional measurement data of time advance (TA) and eNodeB antenna angle of arrival (AOA) in the MRS measurement report refers to the wireless measurement data provided by the TD-LTE digital cellular mobile communication network radio operation and maintenance center (OMC-R). When the measurement method adopts periodic measurement, the reporting period is configured when the measurement task is customized. For a measurement, the reporting triggering method is either event triggering or periodic triggering.

[0056] In this embodiment, the base station reference engineering parameter data is used to define the base station number and the base station latitude and longitude.

[0057] The specific timing advance (TA) in this embodiment is as follows:

[0058] Define the UE's uplink transmission time for its primary cell PUCCH / PUSCH / SRS; in RRC connection state, the eNodeB antenna angle of arrival (AOA) determines the TA adjustment value for each UE based on the measurement of the corresponding UE's uplink transmission. The TA adjustment value ranges from (0,1,2,...,1282)×16Ts; the latest time advance obtained this time is the sum of the previously recorded time advance and the adjustment value obtained by the eNodeB measurement this time;

[0059] The specific algorithm for calculating the time advance (TA) is as follows: During random access, the eNodeB antenna angle of arrival (AOA) determines the value of TA by measuring the received pilot signal. The value of TA ranges from (0, 1, 2, ..., 1282) × 16Ts, as shown in the table below.

[0060]

[0061]

[0062] The time advance (TA) value is used to determine the distance between the UE and the base station, to perform cell coverage analysis, to determine whether adjustments to the cell antenna are needed, and to determine whether the base station's coverage area is reasonable, and whether there are over-coverage or coverage shadow areas. At the same time, the time advance (TA) is used to assist in providing location services.

[0063] For example:

[0064] CellId MR.Tadv.00 MR.Tadv.01 … MR.Tadv.44 10026 567 458 … 0 10236 26 900 … 0

[0065] The eNodeB antenna angle of arrival (AOA) in this embodiment is as follows:

[0066] Define an estimated angle for the user relative to a reference direction in a counterclockwise direction, where the reference direction is specified as true north; this measurement data represents the number of samples of antenna angle of arrival that meet the range conditions within the OMC-R statistical period, counted by interval.

[0067] The specific algorithm for calculating the eNodeB antenna angle of arrival (AOA) is as follows: The entire range is 360 degrees. Using the reference direction of true north, the number of samples of antenna angle of arrival that meet the specified range conditions within the statistical period is counted in intervals. The range of the sample count is (0,...,11); as shown in the table below:

[0068]

[0069] The eNodeB antenna's angle of arrival (AOA) is used to determine the user's location, provide positioning services, and perform coverage analysis. For example:

[0070] CellId MR.AOA.00 … MR.AOA.11 10026 567 … 12 10236 231 … 567

[0071] Compared to the traditional method of dividing POIs by geographical location, this achievement takes the user terminal perspective and performs statistics based on the sampling points of UE activities, which can better reflect the distribution of user activities and reasonably divide POI scenarios according to the actual business proportion.

[0072] The specific steps of MR measurement report geographic model conversion in step S1 of this embodiment are as follows:

[0073] S101. Subdivide each community into 132 measurement intervals in two dimensions. Based on the proportion of sampling points, subdivide the community KPI indicators into each scenario and accurately aggregate the POI scenario indicator results.

[0074] S102, POI scenario index results are statistically analyzed by two-dimensional superposition of time advance (TA) and eNodeB antenna angle of arrival (AOA): time advance (TA) calculates the distance between the UE terminal and the base station, i.e., the TA0-TA10 interval; eNodeB antenna angle of arrival (AOA) calculates the deviation angle between the UE terminal and the base station, i.e., the AOA0-AOA11 interval.

[0075] S103. After two-dimensional overlay statistics, information on the business activity area of ​​customers around the community is generated.

[0076] The specific details of POI identification and association in step S2 of this embodiment are as follows:

[0077] S201, Time Advance (TA) determines the distance between the UE terminal and the base station from a vertical dimension;

[0078] S202 and eNodeB antenna angle of arrival (AOA) determine the angle between the UE and the base station location in the lateral dimension;

[0079] S203. The location of the base station and the UE terminal is determined by taking the intersection of the time advance (TA) and the eNodeB antenna angle of arrival (AOA).

[0080] S204. By continuously overlaying the two-dimensional measurement data of each base station to form a sampling point cluster dataset, and combining it with the scene base map in the mapinfo layer data, the results are directly overlaid and presented.

[0081] The two-dimensional measurement data positioning table is shown below:

[0082]

[0083] A two-dimensional distribution table is used to create a coverage distribution layer centered on the latitude and longitude of the base station, which can reflect the distribution of UEs within the base station's coverage area.

[0084] ① As attached Figure 3 As shown, TA has a total of 11 intervals, representing different distances between the UE and the base station, and AOA has a total of 12 intervals, each interval being 30°, representing the estimated angle of the UE relative to the reference direction in the counterclockwise direction;

[0085] ② For indoor distributed antenna system (DAS) sites, coverage is only distinguished based on the latitude and longitude information of the base station, and the two-dimensional measurement distribution calculation rules are not applicable.

[0086] The specific correlations of the performance indicators in step S3 of this embodiment are as follows:

[0087] By combining the terminal's location identification information with the cell's performance index data, the index details are refined and then overlaid using a geographic location information algorithm to present the associated performance KPI results in a GIS-like manner.

[0088] Among them, the cell performance indicators include the number of RRC connections, traffic volume, data usage, call completion rate, and call drop rate.

[0089] Example 2:

[0090] As attached Figure 2 As shown, this embodiment provides a scene recognition system based on map POIs, which includes:

[0091] The data acquisition module is used to collect map data, MR data, base station baseline operating parameter data, and cell performance index data;

[0092] The data processing module is used to preprocess data through GIS parsing, MR normalization, and parameter cleaning.

[0093] The data analysis module is used to analyze and separate the two-dimensional measurement data of time advance (TA) and eNodeB antenna angle of arrival (AOA) in the MRS measurement report, and combine it with the base station reference engineering parameter data and GIS POI layer. The two-dimensional measurement is converted into GIS map data by parsing and separating the data, and the data is then combined with the POI layer for overlapping and segmentation calculation, aggregation and automatic identification of scene information.

[0094] The results display module is used to identify associations through POIs, and combine the terminal's location information and cell performance index data to refine the index information. The results are then overlaid using a geographic location information algorithm to present the associated performance KPI results in a GIS manner.

[0095] Example 3:

[0096] This invention also provides an electronic device, including: a memory and a processor;

[0097] The memory stores the instructions executed by the computer.

[0098] The processor executes computer execution instructions stored in the memory, causing the processor to perform the map-based POI-based scene recognition method in any embodiment of the present invention.

[0099] The processor can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor can be a microprocessor or any conventional processor.

[0100] Memory is used to store computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory, and by accessing data stored in the memory. Memory can mainly include a program storage area and a data storage area. The program storage area can store the operating system, at least one application program required for a function, etc.; the data storage area can store data created based on the use of the terminal, etc. In addition, memory can also include high-speed random access memory, and can also include non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart memory cards (SMC), secure digital cards (SD cards), flash memory cards, at least one disk storage device, flash memory devices, or other volatile solid-state storage devices.

[0101] Example 4:

[0102] This invention also provides a computer-readable storage medium storing multiple instructions, which are loaded by a processor to cause the processor to execute the map-based POI-based scene recognition method according to any embodiment of this invention. Specifically, a system or apparatus equipped with a storage medium may be provided, on which software program code implementing the functions of any of the above embodiments is stored, and the computer (or CPU or MPU) of the system or apparatus may read and execute the program code stored in the storage medium.

[0103] In this case, the program code read from the storage medium can itself implement the function of any of the above embodiments, and therefore the program code and the storage medium storing the program code constitute part of the present invention.

[0104] Storage media embodiments for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RYM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, program code can be downloaded from a server computer via a communication network.

[0105] Furthermore, it should be clear that not only can the program code read by the computer be executed, but also the operating system or other components operating on the computer can be instructed based on the program code to perform some or all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0106] Furthermore, it is understood that the program code read from the storage medium is written to the memory set in the expansion board inserted into the computer or to the memory set in the expansion unit connected to the computer. Then, based on the instructions of the program code, the CPU or other components installed on the expansion board or expansion unit execute some and all of the actual operations, thereby realizing the function of any of the embodiments described above.

[0107] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A scene recognition method based on map POIs, characterized in that, This method is based on two-dimensional measurement data of time advance (TA) and eNodeB antenna angle of arrival (AOA) from the MRS measurement report. Combined with base station baseline engineering parameters and GIS POI layers, the two-dimensional measurements are analyzed and separated, converted into GIS map data, and then overlapped, segmented, calculated, and aggregated with the POI layers to automatically identify scene information. The details are as follows: MR measurement report geographic model conversion; POI identification association; Performance metrics correlation; Among them, the two-dimensional measurement data of time advance (TA) and eNodeB antenna angle of arrival (AOA) based on the MRS measurement report refers to the wireless measurement data provided by the TD-LTE digital cellular mobile communication network radio operation and maintenance center; when the measurement method adopts periodic measurement, the reporting period is configured when the measurement task is customized; for a measurement, the report triggering method adopts event triggering or periodic triggering. Base station baseline engineering parameter data is used to define the base station number and base station latitude and longitude; The specific time lead time (TA) is as follows: Define the UE's uplink transmission time for its primary cell PUCCH / PUSCH / SRS; in RRC connection state, the eNodeB antenna angle of arrival (AOA) determines the TA adjustment value for each UE based on the measurement of the corresponding UE's uplink transmission. The TA adjustment value ranges from (0, 1, 2, ..., 1282) × 16Ts; the latest time advance obtained this time is the sum of the previously recorded time advance and the adjustment value obtained by the eNodeB measurement this time. The specific algorithm for the time advance (TA) value is as follows: During the random access process, the eNodeB antenna angle of arrival (AOA) determines the value of the time advance (TA) by measuring the received pilot signal. The value of the time advance (TA) ranges from (0, 1, 2, ..., 1282) × 16Ts. The time advance (TA) value is used to determine the distance between the UE and the base station, to perform cell coverage analysis, to determine whether the cell antenna needs to be adjusted, and to determine whether the base station's coverage area is reasonable, and whether there are over-coverage and coverage shadow areas. At the same time, the time advance (TA) is used to assist in providing location services. The eNodeB antenna angle of arrival (AOA) is as follows: Define an estimated angle for the user relative to a reference direction in a counterclockwise direction, where the reference direction is specified as true north; this measurement data represents the number of samples of antenna angle of arrival that meet the range conditions within the OMC-R statistical period, counted by interval. The specific algorithm for calculating the eNodeB antenna angle of arrival (AOA) is as follows: the whole is 360 degrees. Using the reference direction of true north, the number of samples of antenna angle of arrival that meet the value range conditions within the statistical period are counted in intervals. The range of the number of samples is (0, ..., 11). The eNodeB antenna angle of arrival (AOA) is used to determine the user's location, provide positioning services, and perform coverage analysis. The specific details of the geographic model conversion in the MR measurement report are as follows: Each community is subdivided into 132 measurement intervals in two dimensions. Based on the proportion of sampling points, the community KPI indicators are further subdivided into each scenario, and the POI scenario indicator results are accurately aggregated. The POI scenario index results are statistically analyzed by two-dimensional superposition of time advance (TA) and eNodeB antenna angle of arrival (AOA): time advance (TA) calculates the distance between the UE terminal and the base station, i.e., the TA0-TA10 interval; eNodeB antenna angle of arrival (AOA) calculates the deviation angle between the UE terminal and the base station, i.e., the AOA0-AOA11 interval. Two-dimensional overlay statistics are used to generate information on the business activity area of ​​customers around the community. The specific details of POI identification and association are as follows: The time lead time (TA) is used to determine the distance between the UE terminal and the base station from a vertical dimension. The eNodeB antenna angle of arrival (AOA) determines the angle between the UE and the base station location in the lateral dimension. The location of the base station and the UE terminal is determined by taking the intersection of the time advance (TA) and the eNodeB antenna angle of arrival (AOA). By continuously overlaying the two-dimensional measurement data of each base station, a clustered dataset of sampling points is formed. Combined with the scene base map in the mapinfo layer data, the results are directly overlaid and presented. The specific correlations between the performance metrics are as follows: By combining the terminal's location identification information with the cell's performance index data, the index details are refined and then overlaid using a geographic location information algorithm to present the associated performance KPI results in a GIS-like manner. Among them, the cell performance indicators include the number of RRC connections, traffic volume, data usage, call completion rate, and call drop rate. 2.A map POI based scene recognition system, characterized in that, This system is used to implement the map-based POI-based scene recognition method as described in claim 1; The system includes, The data acquisition module is used to collect map data, MR data, base station baseline operating parameter data, and cell performance index data; The data processing module is used to preprocess data through GIS parsing, MR normalization, and parameter cleaning. The data analysis module is used to analyze and separate the two-dimensional measurement data of time advance (TA) and eNodeB antenna angle of arrival (AOA) in the MRS measurement report, and combine it with the base station reference engineering parameter data and GIS POI layer. The two-dimensional measurement is converted into GIS map data by parsing and separating the data, and the data is then combined with the POI layer for overlapping and segmentation calculation, aggregation and automatic identification of scene information. The results display module is used to identify associations through POIs, and combine the terminal's location information and cell performance index data to refine the index information. The results are then overlaid using a geographic location information algorithm to present the associated performance KPI results in a GIS manner.

3. An electronic device, comprising: include: Memory and at least one processor; The memory contains computer programs; The at least one processor executes the computer program stored in the memory, causing the at least one processor to perform the scene recognition method based on map POI as described in claim 1.

4. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that can be executed by a processor to implement the map-based POI-based scene recognition method as described in claim 1.

Images