CN116193571A - Mobile network user positioning method and system based on MRO and DPI data association - Google Patents

Abstract

The invention discloses a mobile network user positioning method and a system based on association of MRO and DPI data, which belong to the technical field of mobile network positioning, and the technical problem to be solved by the invention is how to reduce construction cost and improve the accuracy of user position positioning, and the technical scheme is as follows: the method comprises the following steps: acquiring longitude and latitude information of a user, namely OTT positioning, through DPI data of a user plane, and establishing a fingerprint library by using the longitude and latitude of the user extracted by the OTT positioning; user information backfilling of MRO data is realized by using signaling plane DPI data, and finally, the association relation between the MRO data and an OTT fingerprint library is established; based on MR_TA+AoA user positioning or based on MR_TDOA three-point positioning: positioning the longitude and latitude of the user by using parameter information in MRO data through a TA+AoA or TDOA three-point positioning method; and (3) adjusting and optimizing MRO positioning results based on a fingerprint library: and effectively associating the MRO positioning result with the OTT fingerprint library, optimizing and optimizing the MRO positioning result, and improving the accuracy of the MRO positioning result. The system comprises a fingerprint library establishment unit, a positioning unit and a tuning unit.

Description

Mobile network user positioning method and system based on MRO and DPI data association

technical field

The invention relates to the technical field of mobile network positioning, in particular to a mobile network user positioning method and system based on MRO and DPI data association.

Background technique

With the rapid development of the mobile Internet, user location positioning requirements are becoming more and more diverse: in terms of user safety, such as the positioning of the elderly/children lost, forest firefighters; in terms of location marketing, such as precise advertising, regional precision marketing; in terms of security Such as user trajectory tracking, special user electronic fence settings and other fields have needs. The development speed of mobile communication network far exceeds that of desktop Internet. Due to the large number of mobile network users, obtaining location information of mobile terminals to realize various location-related value-added services such as people and objects has become a hot spot in Internet commerce.

The networks that mobile user positioning technology relies on are usually divided into three categories, satellite positioning, WLAN positioning, and mobile network positioning. Satellite positioning is suitable for outdoor scenarios, and WLAN positioning is suitable for indoor scenarios, and the two methods need to cooperate with the transformation of the terminal, which has certain requirements for implementation complexity and construction cost. Mobile network positioning is applicable to both indoor and outdoor scenarios, and with the large-scale construction of the network, the positioning accuracy is getting higher and higher.

With the development of mobile positioning technology, a variety of mobile user positioning solutions have emerged, such as AGPS positioning, TOA&TDOA positioning, TA+AoA positioning, etc. Although AGPS positioning has high accuracy, it needs to rely on GPS hardware modules to support high costs; TOA&TDOA positioning obtains the position of the mobile station by measuring the time difference, and requires additional hardware such as measurement units to be installed in the base station.

Through the comparison of mobile network positioning technology at home and abroad, and the research and study of the technical background of mobile user positioning. It is found that in the MRO (measurement report) on the wireless network side, the signal propagation between the mobile station and the base station will carry data information such as propagation time, signal strength, direction angle, etc. The comprehensive utilization of these information can realize position positioning. However, MRO data has no unique user information and cannot try to identify users. By analyzing the DPI data, it is found that the DPI user plane data, such as the S1-U/N3 interface, contains the user's longitude and latitude, and its source is the location information reported by the WEB/APP. The latitude and longitude of users in the DPI data can be obtained indoors with an accuracy of about 50m, and outdoors with an accuracy of 5-10m or even lower. However, the latitude and longitude in the DPI data can only be obtained by users using certain WEB/APPs, and cannot be implemented for users on the entire network. location targeting.

Therefore, how to reduce the construction cost while improving the accuracy of user location positioning is a technical problem to be solved urgently.

Contents of the invention

The technical task of the present invention is to provide a mobile network user positioning method and system based on the association between MRO and DPI data, so as to solve the problem of how to improve the accuracy of user position positioning while reducing construction costs.

Technical task of the present invention is realized in the following manner, a kind of mobile network user positioning method based on MRO and DPI data association, the method is specifically as follows:

Build a fingerprint library: Obtain user latitude and longitude information through user plane DPI data, that is, OTT positioning (the carrying ratio of latitude and longitude information is about 1-3%), and use the user longitude and latitude extracted by OTT positioning to establish a fingerprint database; at the same time, use DPI data on the signaling plane to realize MRO data Backfill the user information, and finally establish the relationship between the MRO data and the OTT fingerprint database;

User positioning based on MR_TA+AoA or three-point positioning based on MR_TDOA: Use the parameter information in the MRO data to locate the user's latitude and longitude through the three-point positioning method of TA+AoA or TDOA;

Optimization of MRO positioning results based on the fingerprint database: effectively associate the MRO positioning results with the OTT fingerprint database, optimize and tune the MRO positioning results, improve the accuracy of the MRO positioning results, and achieve the goal of precise positioning of the entire network user location.

As a preference, the establishment of the fingerprint database is as follows:

Rely on DPI data to obtain the user's latitude and longitude: connect to the signaling monitoring system of the live network or collect the user's S1-U interface, and obtain the user's latitude and longitude information from the HTTP protocol call list;

Association between DPI data and MR0 data: Use the DPI data on the signaling plane to backfill the user information of the MRO data, and then associate the backfilled MRO with the S1-U interface to obtain the network coverage level and quality value of the user at any latitude and longitude. Information such as distance and azimuth from the base station;

Establish a fingerprint library based on DPI_OTT data: Use a supervised machine learning model to establish a fingerprint feature model based on OTT user location latitude and longitude data.

More preferably, relying on DPI data to obtain the user's latitude and longitude is as follows:

When users use certain APPs for data services, they will exchange information with the server through the S1-U interface through the HTTP protocol, and some of the information includes the user's real latitude and longitude information;

The latitude and longitude information of a certain proportion of users in the entire network can be obtained by collecting and analyzing network data through DPI technology.

More preferably, a supervised machine learning model is used to establish a fingerprint feature model with OTT user location latitude and longitude data as follows:

The user's latitude and longitude data acquired by OTT method is distributed in a grid of 10*10;

Feature extraction of information such as serving cell ID, serving cell RSRP/RSRQ, Tadv, AoA, neighboring cell ID and neighboring cell RSRP/RSRQ, as the feature basis of the machine learning model;

Use a large number of OTT longitude and latitude reported data on the live network to conduct machine learning model fingerprint feature training;

According to the result of feature analysis, a fingerprint library is generated according to the feature identification of the grid, the main cell and the adjacent cell;

Establish a mechanism for updating the fingerprint database: Continuous machine learning is performed through the update of OTT data to improve the accuracy of the fingerprint database.

As a preference, user positioning based on MR_TA+AoA is specifically as follows:

The parameter information of TA+AoA already exists in the MRO data, and the AoA and TA are integrated to perform UE positioning based on a single cell; among them, the formula of the TA+AoA positioning principle is as follows:

Among them, TA represents the time advance; c represents the speed of light, and the value of c is 3.0*10 ⁸ m/s;

The time advance distance corresponding to 1Ts is: (3*108*1/(15000*2048))/2=4.89m, which means distance=propagation speed (speed of light)*1Ts/2 (sum of uplink and downlink paths); MR The reported TA value takes 16TS as the unit, 1TADV=16TS=16*4.89=78.12m; the distance between the terminal UE and the antenna d=78.12*TA, in meters;

The distance calculated based on TA or based on path loss is the distance from the UE to the antenna port, which is a three-dimensional distance, and there is an elevation angle. Under normal circumstances, the height of the UE is lower than the height of the eNB, and the change of the longitude and latitude of the user is a 2-dimensional change. The distance between the UE and the base station is calculated specifically. for:

In the case of ignoring the height of the UE, according to the Pythagorean theorem: L ² +H ² =d ² , the straight-line distance L from the UE to the antenna and the height H of the base station come from the height of the industrial reference station,

The longitude and latitude information of the base station is obtained through the industrial parameters, and the longitude and latitude (X ₀ , Y ₀ ) of the end user can be obtained after conversion.

As a preference, the three-point positioning based on MR_TDOA is specifically as follows:

The characteristics of the three-point positioning algorithm require that the number of effective base stations calculated by the "distance from the terminal to the base station" be three to extract the level value of the main serving cell and the level value of at least two neighboring cells in the MR data, and use the wireless propagation model algorithm to obtain respectively The distance d1 from the terminal to the main serving cell and the distance d2&d3 from the neighboring cell base station;

Use the empirical formula for calculating the 4G path loss to obtain the position of the terminal user from the base station and the base station in the neighboring cell. The empirical formula for calculating the 4G path loss is:

L _COST231-Hata ＝46.3+33.9*log ₁₀ (f _c )-13.82*log ₁₀ (h _b )+(44.9-6.55*log ₁₀ (h)*log ₁₀ (d)+C _M

Among them, f _c is the wireless signal frequency 1500-2000MHZ, the unit is MHz; c _M is the coverage scene correction factor, cover_class coverage scene is rural areas, towns, general urban areas, and core urban areas, and c _M is 0/3/6 respectively; h is The height difference between the terminal and the base station antenna is equal to the height of the base station (transmission antenna height) in the industrial parameter by default, and the unit is m; d is the distance between the base station antenna and the mobile station antenna (antenna coverage distance), and the unit is km;

The latitude and longitude (X ₁ , Y ₁ ) of the terminal user can be obtained after conversion by using the least square method combined with the latitude and longitude information of the base station.

As a preference, the optimization of the MRO positioning results based on the fingerprint database is as follows:

The TA+AoA positioning based on MRO data will cause the TDOA three-point positioning algorithm to be affected by multipath propagation and interference factors in the coverage scene, resulting in the accuracy of user positioning latitude and longitude ranging from 50-1000m. The Euclidean distance algorithm corresponds the MRO positioning result to the fingerprint library grid, searches for the grid whose feature information is closest to the feature information contained in the current MRO positioning result, and finally uses the position of this grid as the position of the corresponding end user;

At the same time, the TA+AOA or TDOA three-point positioning result data under different coverage scenarios (urban/rural/university/office buildings, etc.) are continuously input into the OTT fingerprint database to build a machine learning model, and calculate the MR positioning under different coverage scenarios The result offset parameters in order to further improve the accuracy of MR positioning results.

A mobile network user positioning system based on MRO and DPI data association, the system includes,

The fingerprint library building unit is used to obtain the user's longitude and latitude through the user plane DPI data, that is, OTT positioning (the carrying ratio of the longitude and latitude information is about 1-3%), and the user longitude and latitude extracted by the OTT positioning are used to establish the fingerprint library, and use the signaling plane DPI data Realize the user information backfill of MRO data, and finally establish the association relationship between MRO data and OTT fingerprint database;

The positioning unit is used to use the parameter information in the MRO data to locate the longitude and latitude of the user through the TA+AoA or TDOA three-point positioning method;

The tuning unit is used to effectively associate the MRO positioning result with the OTT fingerprint database, optimize and tune the MRO positioning result, improve the accuracy of the MRO positioning result, and achieve the result goal of precise positioning of the entire network user location.

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

Wherein, a computer program is stored on the memory;

The at least one processor executes the computer program stored in the memory, so that the at least one processor executes the above-mentioned method for locating mobile network users based on the association between MRO and DPI data.

A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and the computer program can be executed by a processor to implement the above-mentioned method for locating mobile network users based on the association between MRO and DPI data.

The mobile network user positioning method and system based on MRO and DPI data association of the present invention have the following advantages:

(1) The present invention realizes user identity backfilling of MRO data by closely combining wireless MRO data with core network DPI data, and at the same time comprehensively adopts a variety of user location positioning methods to scientifically optimize the positioning results to reduce user location offset output accurate user latitude and longitude information;

(2) The present invention effectively combines MRO positioning results with DPI data, comprehensively adopts various positioning methods such as OTT positioning, TA+AoA positioning, and TDOA three-point positioning, so as to realize the location positioning of users in the entire network in a more cost-effective and efficient method;

(3) The present invention effectively combines the MRO data with the DPI data, integrates the Internet-based positioning service (that is, OTT positioning) in the DPI data, and the wireless MRO data positioning TA+AOA positioning or TDOA positioning to form a set of high-quality High-precision, low-cost user location positioning method;

(4) The present invention effectively combines MRO data with DPI data, while reducing construction costs, and improving the accuracy of user location positioning;

(5) The advantages of the present invention based on the user positioning scheme associated with MRO and DPI data are:

① OTT positioning based on DPI data is highly accurate but requires users to use certain APPs to achieve user positioning, which cannot fully meet the user positioning needs of LBS. The correlation of the positioning results (TA+AOA/TDOA three-point positioning) can effectively solve the problem of low positioning coverage, and at the same time effectively improve the positioning accuracy;

②In principle, there is no need to add hardware configuration, it does not affect the production system and the construction cost is low. The MRO data is configured by the base station, and the measurement report is reported to the NMS management system. The MRO can be synchronized from the NMS system; the DPI data is monitored by the live network signaling The system synchronizes data, in principle, no need to add new collection nodes.

Description of drawings

The present invention will be further described below in conjunction with the accompanying drawings.

Accompanying drawing 1 is the flowchart of the mobile network user location method based on MRO and DPI data association;

Accompanying drawing 2 is the schematic diagram of DPI data and MR0 data association;

Accompanying drawing 3 is the schematic diagram that the fingerprint database based on DPI_OTT data is established;

Accompanying drawing 4 is the schematic diagram of TA+AoA positioning;

Figure 5 is a schematic diagram of calculating the distance from the UE to the base station.

Detailed ways

The mobile network user positioning method and system based on the association between MRO and DPI data of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

Example 1:

As shown in Figure 1, the present embodiment provides a mobile network user positioning method based on MRO and DPI data association, the method is as follows:

S1. Build a fingerprint library: Obtain user latitude and longitude information through user plane DPI data, that is, OTT positioning (the carrying ratio of latitude and longitude information is about 1-3%), and use the user longitude and latitude extracted by OTT positioning to establish a fingerprint database; at the same time, use DPI data on the signaling plane to realize Backfill the user information of MRO data, and finally establish the association relationship between MRO data and OTT fingerprint database;

S2. User positioning based on MR_TA+AoA or three-point positioning based on MR_TDOA: use the parameter information in the MRO data to locate the user's latitude and longitude through the TA+AoA or TDOA three-point positioning method;

S3. Optimization of MRO positioning results based on the fingerprint database: effectively associate the MRO positioning results with the OTT fingerprint database, optimize and tune the MRO positioning results, improve the accuracy of the MRO positioning results, and achieve the result goal of precise positioning of user locations across the network .

The establishment of the fingerprint database in step S2 of the present embodiment is specifically as follows:

S201. Relying on DPI data to obtain the user's latitude and longitude: connect to the signaling monitoring system of the live network or collect the user's S1-U interface, and obtain the user's latitude and longitude information from the HTTP protocol bill;

S202. DPI data and MR0 data association: As shown in Figure 2, the MRO itself does not carry the user identity, and uses the S1-MME interface to backfill the user identity information for the MRO. After backfilling the user identity information, the MRO is associated with the S1-U interface, and the user's network coverage level and quality value at a certain latitude and longitude, distance and azimuth from the base station, etc. are obtained;

S203. Establish a fingerprint library based on DPI_OTT data: use a supervised machine learning model to establish a fingerprint feature model based on OTT user location latitude and longitude data.

Among them, the acquisition process of the longitude and latitude position information of the user obtained by the signaling monitoring system of the existing network is as follows:

Extract location information from downlink 2000K messages: extract the latitude and longitude in HTML format in PAYLOAD and the latitude and longitude in text format in PAYLOAD;

Extract the location information from the uplink message: extract the latitude and longitude information in the URL;

The location information extracted from the downlink 2000K message and the location information extracted from the uplink message are converted to the coordinate system, and then the longitude and latitude location information of the user is determined.

The details of obtaining the user's latitude and longitude depending on the DPI data in step S201 of this embodiment are as follows:

S20101. When the user uses certain APPs for data services, the user will exchange information with the server through the S1-U interface through the HTTP protocol, and some information includes the user's real latitude and longitude information;

S20102. Collect and analyze the network data through the DPI technology to obtain the latitude and longitude information of a certain proportion of users in the entire network.

As shown in accompanying drawing 3, the use supervised machine learning model in step S203 of the present embodiment, establishes fingerprint feature model with OTT user location longitude and latitude data specifically as follows:

S20301. Dotting and distributing the user latitude and longitude data obtained in the OTT manner in a grid of 10*10;

S20302. Perform feature extraction based on the serving cell ID, serving cell RSRP/RSRQ, Tadv, AoA, neighboring cell ID, neighboring cell RSRP/RSRQ and other information, as a feature basis for the machine learning model;

S20303. Using a large number of OTT longitude and latitude reported data on the live network, perform fingerprint feature training of the machine learning model;

S20304. According to the result of feature analysis, a fingerprint database is generated according to the feature identifiers of the grid, the main cell and the adjacent cells;

S20305. Establish a fingerprint database update mechanism: perform uninterrupted machine learning through OTT data update to improve the accuracy of the fingerprint database.

The user positioning based on MR_TA+AoA in step S2 of this embodiment is specifically as follows:

TA+AoA parameter information already exists in the MRO data, and AoA and TA are integrated to perform UE positioning based on a single cell; among them, as shown in Figure 4, the formula of the TA+AoA positioning principle is as follows:

Among them, TA represents the time advance; c represents the speed of light, and the value of c is 3.0*10 ⁸ m/s;

The time advance distance corresponding to 1Ts is: (3*108*1/(15000*2048))/2=4.89m, which means distance=propagation speed (speed of light)*1Ts/2 (sum of uplink and downlink paths); MR The reported TA value takes 16TS as the unit, 1TADV=16TS=16*4.89=78.12m; the distance between the terminal UE and the antenna d=78.12*TA, in meters;

The distance calculated based on TA or based on path loss is the distance from the UE to the antenna port, which is a three-dimensional distance and has an elevation angle. Under normal circumstances, the height of the UE is lower than the height of the eNB, and the change of the latitude and longitude of the user is a 2-dimensional change, as shown in Figure 5. Calculate the distance from the UE to the base station as follows:

In the case of ignoring the height of the UE, according to the Pythagorean theorem: L ² +H ² =d ² , the straight-line distance L from the UE to the antenna and the height H of the base station come from the height of the industrial reference station,

The longitude and latitude information of the base station is obtained through the industrial parameters, and the longitude and latitude (X ₀ , Y ₀ ) of the end user can be obtained after conversion.

The three-point positioning based on MR_TDOA in step S2 of this embodiment is specifically as follows:

The characteristics of the three-point positioning algorithm require that the number of effective base stations calculated by the "distance from the terminal to the base station" be three; the level value of the main serving cell and the level value of at least two neighboring cells in the MR data are extracted, and the wireless propagation model algorithm is used to respectively Obtain the distance d1 from the terminal to the main serving cell and the distance d2&d3 from the neighboring cell base station;

Use the empirical formula for calculating the 4G path loss to obtain the position of the terminal user from the base station and the base station in the neighboring cell. The empirical formula for calculating the 4G path loss is:

L _COST231-Hata ＝46.3+33.9*log ₁₀ (f _c )-13.82*log ₁₀ (h _b )+(44.9-6.55*log ₁₀ (h)*log ₁₀ (d)+C _M

Among them, f _c is the wireless signal frequency 1500-2000MHZ, the unit is MHz; c _M is the coverage scene correction factor, cover_class coverage scene is rural areas, towns, general urban areas, and core urban areas, and c _M is 0/3/6 respectively; h is The height difference between the terminal and the base station antenna is equal to the height of the base station (transmission antenna height) in the industrial parameter by default, and the unit is m; d is the distance between the base station antenna and the mobile station antenna (antenna coverage distance), and the unit is km;

The latitude and longitude (X ₁ , Y ₁ ) of the terminal user can be obtained after conversion by using the least square method combined with the latitude and longitude information of the base station.

The tuning of the MRO positioning result based on the fingerprint database in step S3 of this embodiment is specifically as follows:

The TA+AoA positioning based on MRO data will cause the TDOA three-point positioning algorithm to be affected by multipath propagation and interference factors in the coverage scene, resulting in the accuracy of user positioning latitude and longitude ranging from 50-1000m. The Euclidean distance algorithm corresponds the MRO positioning result to the fingerprint library grid, searches for the grid whose feature information is closest to the feature information contained in the current MRO positioning result, and finally uses the position of this grid as the position of the corresponding end user;

At the same time, the TA+AOA or TDOA three-point positioning result data under different coverage scenarios (urban/rural/university/office buildings, etc.) are continuously input into the OTT fingerprint database to build a machine learning model, and calculate the MR positioning under different coverage scenarios The result offset parameters in order to further improve the accuracy of MR positioning results.

Example 2:

This embodiment provides a mobile network user positioning system based on MRO and DPI data association, the system includes:

The fingerprint library building unit is used to obtain the user's longitude and latitude through the user plane DPI data, that is, OTT positioning (the carrying ratio of the longitude and latitude information is about 1-3%), and the user longitude and latitude extracted by the OTT positioning are used to establish the fingerprint library, and use the signaling plane DPI data Realize the user information backfill of MRO data, and finally establish the association relationship between MRO data and OTT fingerprint database;

The positioning unit is used to use the parameter information in the MRO data to locate the longitude and latitude of the user through the TA+AoA or TDOA three-point positioning method;

The tuning unit is used to effectively associate the MRO positioning result with the OTT fingerprint database, optimize and tune the MRO positioning result, improve the accuracy of the MRO positioning result, and achieve the result goal of precise positioning of the entire network user location.

Example 3:

This embodiment also provides an electronic device, including: a memory and a processor;

Wherein, the memory stores computer-executable instructions;

The processor executes the computer-executable instructions stored in the memory, so that the processor executes the method for locating mobile network users based on the association between MRO and DPI data in any embodiment of the present invention.

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 may be a microprocessor or the processor may be any conventional processor or the like.

The memory can be used to store computer programs and/or modules, and the processor implements various functions of the electronic device by running or executing the computer programs and/or modules stored in the memory and calling data stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required by at least one function, etc.; the data storage area may store data created according to 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, internal memory, plug-in hard disks, memory stick cards (SMC), secure digital (SD) cards, flash memory cards, at least A disk storage device, flash memory device, or other volatile solid-state storage device.

Example 4:

This embodiment also provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions are loaded by the processor, so that the processor executes the mobile network user positioning based on the association between MRO and DPI data in any embodiment of the present invention method. Specifically, a system or device equipped with a storage medium may be provided, on which a software program code for realizing the functions of any of the above embodiments is stored, and the computer (or CPU or MPU of the system or device) ) to read and execute the program code stored in the storage medium.

In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, so the program code and the storage medium storing the program code constitute a part of the present invention.

Examples of storage media 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), Tape, non-volatile memory card, and ROM. Alternatively, the program code can be downloaded from a server computer via a communication network.

In addition, it should be clear that not only by executing the program code read by the computer, but also by making the operating system on the computer complete part or all of the actual operations through instructions based on the program code, so as to realize the function of any one of the embodiments.

In addition, it can be understood that the program code read from the storage medium is written into the memory provided in the expansion board inserted into the computer or written into the memory provided in the expansion unit connected to the computer, and then based on the program code The instruction causes the CPU installed on the expansion board or the expansion unit to perform some or all of the actual operations, so as to realize the functions of any one of the above-mentioned embodiments.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than limiting them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: It is still possible to modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the various embodiments of the present invention. scope.

Claims (10)

1. A method for locating mobile network users based on the association of MRO and DPI data, characterized in that the method is specifically as follows: Establishing a fingerprint library: Obtain the user's longitude and latitude information, namely OTT positioning, through the user plane DPI data, and establish a fingerprint library using the user's longitude and latitude extracted by OTT positioning; at the same time, use the signaling plane DPI data to backfill the user information of the MRO data, and finally establish the association relationship between the MRO data and the OTT fingerprint library; Based on MR_TA+AoA user positioning or based on MR_TDOA three-point positioning: Use the parameter information in the MRO data to locate the user's longitude and latitude through the TA+AoA or TDOA three-point positioning method; Fingerprint library-based MRO positioning result tuning: effectively associate the MRO positioning results with the OTT fingerprint library, optimize the MRO positioning results, and improve the accuracy of the MRO positioning results. 2. According to the method for locating mobile network users based on the association of MRO and DPI data according to claim 1, it is characterized in that the fingerprint database is established as follows: Rely on DPI data to obtain user longitude and latitude: connect to the existing network signaling monitoring system or collect user S1-U interface, and obtain user longitude and latitude information from HTTP protocol call records; DPI data is associated with MR0 data: MRO itself does not carry user identification, and the S1-MME interface is used to backfill user identity information for MRO; the MRO after backfilling user identity information is associated with the S1-U interface to obtain the network coverage level and quality value of the user at any longitude and latitude, and the distance and azimuth information from the base station; Establish a fingerprint library based on DPI_OTT data: Use a supervised machine learning model to establish a fingerprint feature model based on the longitude and latitude data of OTT user locations. 3. The method for locating a mobile network user based on the association of MRO and DPI data according to claim 2 is characterized in that the longitude and latitude of the user are obtained by relying on the DPI data as follows: When using the APP for data services, users interact with the server through the HTTP protocol via the S1-U interface, and some of the information contains the user's real latitude and longitude information; By collecting and analyzing network data through DPI technology, we can obtain the longitude and latitude information of the corresponding proportion of users in the entire network. 4. The method for locating a mobile network user based on the association of MRO and DPI data according to claim 2 or 3 is characterized in that a supervised machine learning model is used to establish a fingerprint feature model with the longitude and latitude data of OTT user positioning as follows: The user's longitude and latitude data obtained by OTT is distributed in a 10*10 grid; Extract features based on serving cell ID, serving cell RSRP/RSRQ, Tadv, AoA, neighboring cell ID and neighboring cell RSRP/RSRQ information as feature basis for machine learning model; Use the longitude and latitude data reported by the existing OTT network to train the fingerprint features of the machine learning model; Based on the results of feature analysis, a fingerprint library is generated according to the feature identifiers of the grid, the main cell and the neighboring cells; Establish a fingerprint library update mechanism: Perform uninterrupted machine learning through OTT data updates to improve the accuracy of the fingerprint library. 5. The method for locating a mobile network user based on MRO and DPI data association according to claim 1, wherein the user positioning based on MR_TA+AoA is specifically as follows: The MRO data already contains the parameter information of TA+AoA. AoA and TA are combined to locate the UE based on a single cell. The formula of TA+AoA positioning principle is as follows:

Wherein, TA represents the time advance; c represents the speed of light, and the value of c is 3.0*10 ⁸ m/s; The time advance distance corresponding to 1Ts is: (3*108*1/(15000*2048))/2=4.89m, which means distance = propagation speed (speed of light)*1Ts/2; the TA value reported by MR is in units of 16TS, 1TADV=16TS=16*4.89=78.12m; the distance from the terminal UE to the antenna d=78.12*TA, in meters; The distance calculated based on TA or path loss is the distance from UE to antenna port, which is a three-dimensional distance with elevation angle. Normally, the UE height is lower than the eNB height, while the longitude and latitude of the user change in two dimensions. The distance from UE to base station is calculated as follows: When UE height is ignored, according to the Pythagorean theorem: L ² +H ² =d ² , the straight-line distance L from UE to antenna and the base station height H are derived from the engineering reference station height.

The latitude and longitude information of the base station is obtained through the engineering parameters, and the latitude and longitude (X ₀ , Y ₀ ) of the terminal user can be obtained through conversion. 6. The method for locating a mobile network user based on MRO and DPI data association according to claim 1, characterized in that the MR_TDOA three-point positioning is specifically as follows: Extract the level value of the primary service cell and the level values of at least two neighboring cells in the MR data, and use the wireless propagation model algorithm to obtain the distance d1 from the terminal to the primary service cell and the distance d2&d3 from the neighboring base station respectively; The empirical formula for calculating 4G path loss is used to obtain the location of the terminal user from the base station and the neighboring base station. The empirical formula for calculating 4G path loss is: L _COST231-Hata ＝46.3+33.9*log ₁₀ (f _c )-13.82*log ₁₀ (h _b )+(44.9-6.55*log ₁₀ (h)*log ₁₀ (d)+C _M Among them, f _c is the wireless signal frequency 1500-2000MHZ, unit MHz; c _M is the coverage scenario correction factor, cover_class coverage scenarios are rural, township, general urban area, core urban area, c _M takes values 0/3/6 respectively; h is the height difference between the terminal and the base station antenna, which is equal to the base station height in the engineering parameters by default, unit m; d is the distance between the base station antenna and the mobile station antenna, unit km; The latitude and longitude (X ₁ , Y ₁ ) of the terminal user can be obtained by converting the latitude and longitude information of the base station using the least square method. 7. The method for locating a mobile network user based on the association of MRO and DPI data according to claim 1, characterized in that the MRO positioning result optimization based on the fingerprint library is specifically as follows: The MRO positioning result is mapped to the fingerprint library grid by minimizing the Euclidean distance algorithm, and the grid whose feature information is closest to the feature information contained in the current MRO positioning result is found, and the position of this grid is finally used as the corresponding terminal user's position; At the same time, the TA+AOA or TDOA three-point positioning result data under different coverage scenarios are continuously input into the OTT fingerprint library to build a machine learning model, and the offset parameters of the MR positioning results under different coverage scenarios are calculated. 8. A mobile network user positioning system based on MRO and DPI data association, characterized in that the system includes: The fingerprint library establishment unit is used to obtain the user's longitude and latitude, i.e., OTT positioning, through the user plane DPI data, establish the fingerprint library with the user's longitude and latitude extracted by OTT positioning, and use the signaling plane DPI data to realize the user information backfill of MRO data, and finally establish the association relationship between MRO data and OTT fingerprint library; The positioning unit is used to locate the user's longitude and latitude using the parameter information in the MRO data through the TA+AoA or TDOA three-point positioning method; The tuning unit is used to effectively associate the MRO positioning results with the OTT fingerprint library, optimize and tune the MRO positioning results, and improve the accuracy of the MRO positioning results. 9. An electronic device, comprising: a memory and at least one processor; Wherein, the memory stores a computer program; The at least one processor executes the computer program stored in the memory, so that the at least one processor performs the mobile network user positioning method based on the association of MRO and DPI data as described in any one of claims 1 to 7. 10. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, and the computer program can be executed by a processor to implement the mobile network user positioning method based on the association of MRO and DPI data as described in any one of claims 1 to 7.

Images