CN115942233A

CN115942233A - Scene recognition method and system based on map POI

Info

Publication number: CN115942233A
Application number: CN202211359533.XA
Authority: CN
Inventors: 唐国欢
Original assignee: Inspur Communication Information System Co Ltd
Current assignee: Inspur Communication Information System Co Ltd
Priority date: 2022-11-02
Filing date: 2022-11-02
Publication date: 2023-04-07

Abstract

The invention discloses a scene recognition method and a scene recognition system based on a map POI, which belong to the technical field of wireless communication, solve the technical problem of how to quickly adapt to the continuously developed scene analysis requirement and improve the network analysis efficiency, and adopt the technical scheme that: the method is based on time advance TA and eNodeB antenna arrival angle AOA two-dimensional measurement data in an MRS measurement report, and combines base station reference parameter data and a GIS POI layer, the two-dimensional measurement is analyzed and separated, converted into GIS map data, and overlapped, divided, calculated and aggregated with the POI layer, and scene information is automatically identified; the method comprises the following specific steps: converting an MR measurement report geographic model; POI identification association; and (5) associating the performance indexes. The system comprises a data acquisition module, a data processing module, a data analysis module and a result presentation module.

Description

Scene recognition method and system based on map POI

Technical Field

The invention relates to the technical field of wireless communication, in particular to a scene identification method and a scene identification system based on a map POI.

Background

According to the scale of the current LTE wireless service, the traditional mode realizes the positioning analysis processing of huge network service data, the conventional mode is realized through signaling data, and large-scale scene correlation calculation often needs the calculation scale of billions of data, so that the resource consumption is large, and the time period is long.

Meanwhile, in the existing analysis model, the problems of complex computation degree and huge computation amount caused by a signaling data positioning mode are needed, and the result output of the scene correlation condition at the minute level is realized.

Therefore, how to quickly adapt to the continuously developing scene analysis requirements and improve the network analysis efficiency is a technical problem to be solved urgently at present.

Disclosure of Invention

The technical task of the invention is to provide a scene recognition method and a scene recognition system based on a map POI, so as to solve the problems of how to quickly adapt to continuously developed scene analysis requirements and improve the network analysis efficiency.

The technical task of the invention is realized according to the following mode, a scene recognition method based on map POI is characterized in that the method is based on time advance TA in an MRS measurement report and AOA two-dimensional measurement data of an eNodeB antenna arrival angle, combines base station reference working parameter data and a GIS POI layer, analyzes and separates the two-dimensional measurement, converts the two-dimensional measurement into GIS map data, performs overlapping division calculation and aggregation with the POI layer, and automatically recognizes scene information; the method comprises the following specific steps:

converting the MR measurement report geographic model;

POI identification association;

and associating the performance indexes.

Preferably, the two-dimensional measurement data based on the timing advance TA and the eNodeB antenna arrival angle AOA in the MRS measurement report is wireless measurement data provided by a wireless operation maintenance center (OMC-R) of a TD-LTE digital cellular mobile communication network; when the measurement mode adopts periodic measurement, configuring a reporting period when a measurement task is customized; for one measurement, the report triggering mode adopts event triggering or periodic triggering;

the base station reference parameters are used for defining the station number and the longitude and latitude of the base station.

More preferably, the timing advance TA is specifically as follows:

defining the time for UE to adjust the uplink transmission of a PUCCH/PUSCH/SRS of a main cell; in an RRC connection state, an eNodeB antenna angle of arrival (AOA) determines a TA adjustment value of each UE based on measuring uplink transmission of the corresponding UE, wherein the value range of the TA adjustment value is (0, 1, 2.., 1282) × 16Ts; the latest time lead obtained this time is the sum of the time lead recorded last time and the adjustment value measured by the eNodeB this time;

the specific algorithm of the value of the timing advance TA is as follows: in the random access process, an eNodeB antenna arrival angle AOA determines a value of a timing advance TA by measuring a received pilot signal, wherein the value range of the value of the timing advance TA is (0, 1, 2., 1282) multiplied by 16Ts;

the TA value is used for determining the distance between the UE and the base station, realizing the coverage analysis of the cell, judging whether the antenna of the cell needs to be adjusted, judging whether the coverage area of the base station is reasonable or not, and whether an over-coverage area and a coverage shadow area exist or not, and providing the position service by using the TA assistance.

More preferably, the eNodeB antenna angle of arrival AOA is specifically as follows:

defining an estimated angle of a user in a counterclockwise direction relative to a reference direction, and defining that the reference direction is a true north direction; the measurement data represents the number of samples of the antenna arrival angle which meet the value range condition in the OMC-R statistical period and are counted according to the subareas;

the specific algorithm of the value of the eNodeB antenna angle of arrival AOA is as follows: the integral is 360 degrees, and the number of samples of the arrival angle of the antenna and the value range (0,., 11) of the number of the samples which meet the value range condition in a period and are counted according to the subareas are counted through the north-south direction of the reference direction;

the value of the eNodeB antenna angle of arrival, AOA, is used to determine the bearing where the user is located, provide location services, and perform coverage analysis.

More preferably, the MR measurement report geomodel transformation is specified as follows:

dividing each cell into 132 measurement intervals in a two-dimensional mode, dividing the KPI of the cell into each scene according to the ratio of sampling points, and accurately gathering POI scene index results;

and (3) carrying out two-dimensional superposition statistics on POI scene index results through Time Advance (TA) and eNodeB antenna arrival angle (AOA): calculating the distance between the UE terminal and the base station by the time advance TA, namely a TA0-TA10 interval; calculating the deviation angle of the UE terminal and the base station, namely an AOA0-AOA11 interval, by using an eNodeB antenna arrival angle AOA;

and forming the business activity area information of the customers around the cell after two-dimensional superposition statistics.

Preferably, the POI identification association is specifically as follows:

the time advance TA realizes the distance judgment between the UE terminal and the base station from the longitudinal dimension;

the eNodeB antenna arrival angle AOA realizes the judgment of the included angle between the UE end and the base station position from the transverse dimension;

taking the intersection of the time advance TA and the eNodeB antenna arrival angle AOA to realize the positioning judgment of the positions of the base station and the UE terminal;

two-dimensional measurement data of each base station are continuously overlapped to form a sampling point cluster data set, and a result is directly overlapped and presented by combining a scene base map in mapinfo layer data.

Preferably, the performance index association is as follows:

refining the index condition by combining the condition of the terminal identification position information result and the condition of the cell performance index data, superposing again through a geographic position information algorithm, and presenting the correlation performance KPI result in the scene in a GIS mode;

the cell performance index comprises cell RRC connection number, telephone traffic, flow, call completing rate and call dropping rate.

A map POI based scene recognition system, the system comprising,

the data acquisition module is used for acquiring map data, MR data, base station benchmark parameter data and cell performance index data;

the data processing module is used for preprocessing data in a GIS (geographic information System) analysis, MR (magnetic resonance) normalization and working parameter cleaning mode;

the data analysis module is used for analyzing and separating the two-dimensional measurement based on the time advance TA in the MRS measurement report and the AOA two-dimensional measurement data of the eNodeB antenna arrival angle in combination with the base station reference parameter data and the GIS POI layer, converting the two-dimensional measurement into GIS map data, performing overlapping segmentation calculation and aggregation with the POI layer, and automatically identifying scene information;

and the result display module is used for identifying association through POI, refining the index condition by combining the condition of the terminal identification position information result and the cell performance index data, superposing again through a geographic position information algorithm, and displaying the association performance KPI result in the scene in a GIS mode.

An electronic device, comprising: a memory and at least one processor;

wherein the memory has stored thereon a computer program;

the at least one processor executes the memory-stored computer program to cause the at least one processor to perform the map POI-based scene recognition method as described above.

A computer-readable storage medium having stored thereon a computer program executable by a processor to implement a map POI-based scene recognition method as described above.

The scene recognition method and the scene recognition system based on the map POI have the following advantages that:

according to the method, the replaceable data source and the association rule are searched through the POI scene and the GIS geographic position association rule, the network analysis efficiency is improved, and the continuously developed scene analysis requirements are quickly adapted;

based on TA (time advance) and AOA (antenna arrival angle) data, POI (point of interest) data and cell engineering parameter data in mobile phone measurement, the invention realizes the rapid output of the situation of the mobile phone terminal occupying scene through GIS association, and analyzes the user scale and the flow change situation under different scenes;

compared with the traditional method for dividing the geographical position into the scene POIs, the relevance performance KPI result is counted based on the sampling points of the UE activity from the perspective of the user terminal, and the distribution condition of the user activity can be fed back.

Drawings

The invention is further described below with reference to the accompanying drawings.

FIG. 1 is a flow chart diagram of a scene recognition method based on map POI;

FIG. 2 is a block diagram of a map POI based scene recognition system;

fig. 3 is a two-dimensional mapping of measurement reports.

Detailed Description

The method and system for recognizing a scene based on a map POI according to the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

Example 1:

as shown in fig. 1, this embodiment provides a scene recognition method based on a map POI, which is based on time advance TA in an MRS measurement report and eNodeB antenna arrival angle AOA two-dimensional measurement data, and combines base station reference parameter data and a GIS POI layer, analyzes and separates the two-dimensional measurement, converts the two-dimensional measurement into GIS map data, and performs overlapping division calculation, aggregation and automatic recognition of scene information with the POI layer; the method comprises the following specific steps:

s1, converting an MR measurement report geographic model;

s2, POI identification association;

and S3, associating the performance indexes.

In this embodiment, the two-dimensional measurement data based on the timing advance TA and the eNodeB antenna arrival angle AOA in the MRS measurement report refers to wireless measurement data provided by a TD-LTE digital cellular mobile communication network wireless operation maintenance center (OMC-R); when the measurement mode adopts periodic measurement, configuring a reporting period when a measurement task is customized; for one measurement, the report triggering mode adopts event triggering or periodic triggering;

the base station reference parameters in this embodiment are used to define the base station number and the base station longitude and latitude.

The timing advance TA in this embodiment is specifically as follows:

defining the time for UE to adjust the uplink transmission of a PUCCH/PUSCH/SRS of a main cell; in an RRC connection state, an eNodeB antenna angle of arrival (AOA) determines a TA adjustment value of each UE based on measuring uplink transmission of the corresponding UE, wherein the value range of the TA adjustment value is (0, 1, 2.., 1282) × 16Ts; the latest time lead obtained this time is the sum of the time lead recorded last time and the adjustment value obtained by the measurement of the eNodeB this time;

the specific algorithm of the value of the timing advance TA is as follows: in the random access process, an eNodeB antenna arrival angle AOA determines a value of a time advance TA by measuring a received pilot signal, wherein the value range of the time advance TA is (0, 1, 2.., 1282) × 16Ts; as shown in the following table:

the value of the TA is used for determining the distance between the UE and the base station, realizing the coverage analysis of the cell, judging whether the antenna of the cell needs to be adjusted, judging whether the coverage area of the base station is reasonable, and whether an over-coverage area and a coverage shadow area exist, and providing the position service by using the TA.

For example, the following steps are carried out:

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

the eNodeB antenna angle of arrival AOA in this embodiment is specifically as follows:

the specific algorithm of the value of the antenna angle of arrival AOA of the eNodeB is as follows: the integral is 360 degrees, and the number of samples of the arrival angle of the antenna and the value range (0,., 11) of the number of the samples which meet the value range condition in a period and are counted according to the subareas are counted through the north-south direction of the reference direction; as shown in the following table:

the value of the eNodeB antenna angle of arrival, AOA, is used to determine the position where the user is located, provide location services, and perform coverage analysis. For example, the following steps are carried out:

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

compared with the traditional method for dividing the geographical position into the POI scenes, the achievement starts from the view angle of the user terminal, statistics is carried out based on the sampling points of the UE activities, the distribution condition of the user activities can be fed back, and the POI scenes are divided reasonably according to the actual business proportion condition.

The conversion of the MR measurement report geographic model in step S1 in this embodiment is specifically as follows:

s101, subdividing each cell into 132 measurement intervals in a two-dimensional manner, subdividing the KPI (Key performance indicator) of the cell into each scene according to the ratio of sampling points, and accurately gathering POI scene index results;

s102, counting POI scene index results through two-dimensional superposition of Time Advance (TA) and eNodeB antenna arrival angle (AOA): calculating the distance between the UE terminal and the base station by the time advance TA, namely a TA0-TA10 interval; calculating the deviation angle of the UE terminal and the base station, namely an AOA0-AOA11 interval, by using an eNodeB antenna arrival angle AOA;

and S103, forming service activity area information of the customers around the cell after two-dimensional superposition statistics.

The POI identification association in step S2 of this embodiment is specifically as follows:

s201, the time advance TA realizes the distance judgment between the UE terminal and the base station from the longitudinal dimension;

s202, an eNodeB antenna arrival angle AOA realizes the judgment of an included angle between a UE end and a base station position from a transverse dimension;

s203, obtaining the intersection of the TA and the AOA to realize the positioning judgment of the position of the base station and the UE terminal;

and S204, continuously superposing the two-dimensional measurement data of each base station to form a sampling point cluster data set, and directly superposing to present a result by combining a scene base map in mapinfo layer data.

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

through the two-dimensional distribution table, a coverage distribution layer taking the longitude and latitude of the base station as the center is formed around the base station, and the UE distribution condition can be reflected in the coverage range of the base station:

(1) as shown in fig. 3, TA totally includes 11 sections, each representing a different distance between the UE and the base station, and AOA totally includes 12 sections, each 30 ° representing an estimated angle of the UE in a counterclockwise direction with respect to the reference direction;

(2) and aiming at the indoor branch stations, the coverage condition is distinguished only according to the latitude and longitude information of the base station, and the method is not suitable for the two-dimensional measurement distribution calculation rule.

The correlation of the performance indexes in step S3 in this embodiment is specifically as follows:

Example 2:

as shown in fig. 2, the present embodiment provides a scene recognition system based on map POIs, the system comprising,

the data processing module is used for preprocessing the data in a GIS analysis, MR normalization and working parameter cleaning mode;

and the result display module is used for identifying the association through the POI, refining the index condition by combining the condition of the terminal identification position information result and the cell performance index data, superposing the index condition again through a geographic position information algorithm, and displaying the association performance KPI result in the scene in a GIS mode.

Example 3:

an embodiment of the present invention further provides an electronic device, including: a memory and a processor;

wherein the memory stores computer execution instructions;

the processor executes the computer-executable instructions stored by the memory to cause the processor to perform the map POI-based scene recognition method in any embodiment of the invention.

The processor may be a Central Processing Unit (CPU), but may also be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), array of off-the-shelf programmable gates (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. The processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory may be used to store computer programs and/or modules, and the processor may implement various functions of the electronic device by executing or executing the computer programs and/or modules stored in the memory and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the terminal, and the like. The memory may also include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a memory only card (SMC), a Secure Digital (SD) card, a flash memory card, at least one disk storage period, a flash memory device, or other volatile solid state memory device.

Example 4:

an embodiment of the present invention further provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions are loaded by a processor, so that the processor executes the method for recognizing a scene based on a map POI according to any embodiment of the present invention. Specifically, a system or an apparatus equipped with a storage medium on which software program codes that realize the functions of any of the above-described embodiments are stored may be provided, and a computer (or a CPU or MPU) of the system or the apparatus is caused to read out and execute the program codes stored in the storage medium.

In this case, the program code itself read from the storage medium can realize the functions of any of the above-described embodiments, and thus the program code and the storage medium storing the program code constitute a part of the present invention.

Examples of the storage medium for supplying the program code include a floppy disk, a hard disk, a magneto-optical disk, an optical disk (e.g., CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RYM, DVD-RW, DVD + RW), a magnetic tape, a nonvolatile memory card, and a ROM. Alternatively, the program code may be downloaded from a server computer by a communications network.

Further, it should be clear that the functions of any one of the above-described embodiments may be implemented not only by executing the program code read out by the computer, but also by causing an operating system or the like operating on the computer to perform a part or all of the actual operations based on instructions of the program code.

Further, it is to be understood that the program code read out from the storage medium is written to a memory provided in an expansion board inserted into the computer or to a memory provided in an expansion unit connected to the computer, and then a CPU or the like mounted on the expansion board or the expansion unit is caused to perform part or all of the actual operations based on instructions of the program code, thereby realizing the functions of any of the embodiments described above.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A scene recognition method based on map POI is characterized in that the method is based on time advance TA and eNodeB antenna arrival angle AOA two-dimensional measurement data in an MRS measurement report, combines base station reference parameter data and a GIS POI layer, analyzes and separates the two-dimensional measurement, converts the two-dimensional measurement into GIS map data, performs overlapping division calculation and aggregation with the POI layer, and automatically recognizes scene information; the method comprises the following specific steps:

converting the MR measurement report geographic model;

POI identification association;

and associating the performance indexes.

2. The map POI based scene identification method according to claim 1, wherein based on two-dimensional measurement data of TA and AOA in MRS measurement report, the two-dimensional measurement data refers to wireless measurement data provided by a wireless operation maintenance center of TD-LTE digital cellular mobile communication network; when the measurement mode adopts periodic measurement, configuring a reporting period when a measurement task is customized; for one measurement, the report triggering mode adopts event triggering or periodic triggering;

3. The map POI-based scene recognition method according to claim 1 or 2, wherein the timing advance TA is specifically as follows:

defining the time for UE to adjust the uplink transmission of a PUCCH/PUSCH/SRS of a main cell; in an RRC connected state, an eNodeB antenna angle of arrival (AOA) determines a TA adjustment value of each UE based on measuring uplink transmission of the corresponding UE, wherein the value range of the TA adjustment value is (0, 1, 2., 1282) multiplied by 16Ts; the latest time lead obtained this time is the sum of the time lead recorded last time and the adjustment value obtained by the measurement of the eNodeB this time;

4. The map POI-based scene recognition method according to claim 3, wherein the eNodeB antenna angle of arrival (AOA) is as follows:

defining an estimated angle of a user in a counterclockwise direction relative to a reference direction, and defining that the reference direction is a true north direction; the measurement data represents the number of samples of the antenna arrival angle in accordance with the inter-partition statistic which meet the value range condition in the OMC-R statistic period;

the specific algorithm of the value of the eNodeB antenna angle of arrival AOA is as follows: the integral is 360 degrees, and the number of samples of the antenna arrival angle and the value range of the number of the samples (0,.., 11) which meet the value range condition in a period and are counted according to the subareas are counted through the north direction of the reference direction;

5. The map POI-based scene recognition method according to claim 4, wherein the conversion of the MR measurement report geographic model is specifically as follows:

and forming service activity area information of the customers around the cell after two-dimensional superposition statistics.

6. The map POI-based scene recognition method according to claim 5, wherein the POI recognition association is as follows:

7. The map POI-based scene recognition method according to claim 6, wherein the performance index association is as follows:

8. A scene recognition system based on map POI is characterized in that the system comprises,

the data analysis module is used for analyzing and separating the two-dimensional measurement based on the time advance TA in the MRS measurement report and the AOA two-dimensional measurement data of the eNodeB antenna arrival angle by combining the base station reference parameter data and the GIS POI layer, converting the two-dimensional measurement into GIS map data, performing overlapping segmentation calculation and aggregation on the GIS map layer, and automatically identifying scene information;

9. An electronic device, comprising: a memory and at least one processor;

wherein the memory has stored thereon a computer program;

the at least one processor executing the memory-stored computer program causes the at least one processor to perform the map POI-based scene recognition method of any one of claims 1 to 7.

10. A computer-readable storage medium, in which a computer program is stored, the computer program being executable by a processor to implement the map POI-based scene recognition method according to any one of claims 1 to 7.