CN108282860B

CN108282860B - Data processing method and device

Info

Publication number: CN108282860B
Application number: CN201710007155.1A
Authority: CN
Inventors: 王挺; 刘文吉; 梁秀娟; 周兴围; 章翔; 常锋; 郭宝
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Group Shanxi Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Group Shanxi Co Ltd
Priority date: 2017-01-05
Filing date: 2017-01-05
Publication date: 2020-07-17
Anticipated expiration: 2037-01-05
Also published as: CN108282860A

Abstract

The invention relates to a data processing method and a data processing device. The method comprises the following steps: determining a resident cell of a user in a target time period according to the XDR data; determining longitude and latitude information of the user by utilizing a pre-established MR fingerprint database and MR data; and screening out data for determining the position where the user resides in the target time period from the communication data of the user in the target time period according to the resident cell and the latitude and longitude information. According to the embodiment of the invention, the sampled data of the user moving at a slow speed around the indoor scene can be screened and eliminated, so that the resident position of the user can be accurately determined by using the data.

Description

Data processing method and device

Technical Field

The present invention relates to the field of communications technologies, and in particular, to a data processing method and apparatus for mobile communications.

Background

According to the statistics of network complaint records, more than 90% of complaint reasons of long-term evolution (L TE) network users are reflected in the network quality problems of the resident positions of the users, such as homes, units, schools and the like, which show that the high sensitivity of the users to L TE network quality and the perception that network satisfaction is intensively reflected in the resident positions of the users are basically indoor scenes.

In mobile communication using L TE technology, there are several ways to locate indoor users, one way is to identify indoor users based on cell groups and to match Measurement Report (MR) information, i.e. to group cells with handover relations, and to determine indoor users by the fact that the user's activity range is within the cell group within a specific time (e.g. T20 minutes) and the activity radius is smaller than X meters, and finally to locate L TE indoor users by means of such user MR ticket simulation.

The other mode can be based on establishing an indoor user fingerprint library and matching MR information, wherein the indoor user fingerprint library is established through indoor user characteristics (coverage scenes, levels, change rates, user movement rates and the like of a main service cell and an adjacent cell, APP longitude and latitude information and the like), MR similar to the indoor user is filtered out through matching of MR types according with the characteristics of the fingerprint library, and finally the position of L TE indoor users is positioned through MR call bill simulation.

Disclosure of Invention

The embodiment of the invention provides a data processing method and a data processing device, which can screen and eliminate the sampled data of a user moving at a slow speed around an indoor scene, so that the resident position of the user can be accurately determined by using the data.

One embodiment of the present invention provides a data processing method, including: determining a resident cell of a user in a target time period according to the XDR data; determining longitude and latitude information of the user by utilizing a pre-established MR fingerprint database and MR data; and screening out data for determining the position where the user resides in the target time period from the communication data of the user in the target time period according to the resident cell and the latitude and longitude information.

Optionally, the step of determining a resident cell of the terminal in the target time period according to the XDR data includes: determining the residence frequency of the terminal in each cell in a target time period according to signaling characteristic data in the XDR data; and determining the cell corresponding to the residence frequency greater than the preset threshold value as the resident cell of the target time period.

Optionally, the step of determining the frequency of camping in each cell of the terminal according to the signaling feature data in the XDR data includes: determining the residence frequency of the terminal in an idle state according to signaling characteristic data in XDR data received by an S1_ MME interface; and/or determining the residence frequency of the terminal in the service state according to the signaling characteristic data in the XDR data received by the S1_ U interface.

Optionally, the MR fingerprint database is built by: correlating and combining the MR data and the XDR data of multiple days in a target time period through a common triple of the MR data and the XDR data; and creating the MR fingerprint database according to the merged data.

Optionally, the step of determining longitude and latitude information of the user by using a pre-established MR fingerprint database and MR data includes: determining signal strengths of a local cell and a neighboring cell of the MR data; searching a position where the characteristic information is closest to the characteristic information contained in the current MR data in an MR fingerprint database of the MR data home main service cell; and determining the longitude and latitude of the position as the determined longitude and latitude information of the user.

Optionally, the step of screening, according to the residential cell and the longitude and latitude information, data for determining a location where the user is resident in the target time period from the communication data of the user in the target time period includes: carrying out association combination on a resident cell of a user in a target time period and longitude and latitude information of the user according to the user, the time period and the cell; and determining the data of the resident position of the user in the target time period by cleaning and removing the positioning longitude and latitude information of the resident cell at the ticket time point recorded by the S1-MME and the S1-U ticket outside the resident cell in the target time period.

Optionally, the method further comprises: cleaning the data by calculating the dispersion of the data obtained by screening; and determining the resident building position of the user in the target time period by combining the cleaned data with a map processing program.

Another embodiment of the present invention also provides a data processing apparatus, including: resident district determining element, longitude and latitude information determining element and data processing unit, wherein: a resident cell determining unit, which determines the resident cell of the user in the target time period according to the XDR data; the longitude and latitude information determining unit is used for determining the longitude and latitude information of the user by utilizing a pre-established MR fingerprint database and MR data; and the data processing unit is used for screening out data for determining the position where the user resides in the target time period from the communication data of the user in the target time period according to the resident cell and the latitude and longitude information.

Optionally, the apparatus further comprises an MR fingerprint database establishing unit; the MR fingerprint database establishing unit associates and merges the MR data and the XDR data in a target time period for multiple days through a triple shared by the MR data and the XDR data, and establishes the MR fingerprint database according to the merged data.

Optionally, the resident cell determining unit determines the resident frequency of the terminal in each cell in the target time period according to the signaling feature data in the XDR data; and determining the cell corresponding to the residence frequency greater than the preset threshold value as the resident cell of the target time period.

By adopting the data processing method and the data processing device provided by the embodiment of the invention, the resident cell of the user in the target time period is determined according to the XDR data, and the longitude and latitude information of the user is determined by utilizing the pre-established MR fingerprint database and the MR data, so that the data for determining the resident position of the user in the target time period can be screened from the communication data of the user in the target time period according to the resident cell and the longitude and latitude information. According to the technical scheme of the embodiment of the invention, the sampled data of the user moving at a slow speed around the indoor scene can be screened and eliminated, so that the resident position of the user can be accurately determined by using the data.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, are included for purposes of illustration and are not to be construed as limiting the invention to the specific details shown. In the drawings:

fig. 1 is a schematic flow chart of a specific implementation of a data processing method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of the correlation of MR data and XDR data provided by an embodiment of the present invention;

FIG. 3 is a schematic diagram of data cleansing provided by an embodiment of the present invention;

FIG. 4 is a schematic diagram of a method for determining a user's resident building provided by an embodiment of the present invention;

fig. 5 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present invention.

Detailed Description

Exemplary embodiments of the present invention will be described below with reference to the accompanying drawings. It is clear that the described embodiments are only a partial implementation thereof, not a complete possible implementation. Other implementations, which are readily apparent to those of ordinary skill in the art based on the embodiments disclosed herein, are also within the scope of the claimed invention.

One embodiment of the invention provides a data processing method. The flow diagram of the method is shown in fig. 1 and comprises the following steps.

Step S11: and determining the resident cell of the user in the target time period according to the XDR data.

The XDR data is a detailed record of signaling and service generated for the signaling monitoring platform and the signaling application after being processed based on the full data, where the full data includes all contents of the acquired link, including the full signaling data of the control plane and the full service data of the user plane. In an actual communication procedure, the XDR data may include signaling XDR (also referred to as signaling feature data) which is a detailed record of signaling procedures generated based on the collected control plane signaling, and service XDR (also referred to as XDR call data) which is a detailed record of service transmission procedures generated based on the collected user plane service data.

The time period may be divided in various ways. For example, one day may be divided into 24 time periods in units of hours, or one day may be divided into a working time period (e.g., 9 to 12 points, 14 to 17 points), a leisure time period (17 to 24 points, 12 to 14 points), and a rest time period (0 to 9 points), and so on. Due to different working and living modes of users, the periodic tide position rules of different users are different, and the business models and perceptions of the users in the daytime (corresponding to working time periods), the evening (corresponding to leisure time periods) and the night (corresponding to rest time periods) are obviously different. Other dividing ways can be adopted to divide the day into other time periods according to factors such as occupation and age of the user.

In one embodiment, the user's resident location scenes are partitional clustered as shown in Table 1.

TABLE 1

According to one embodiment, determining the resident cell of the user in the target time period may be performed as follows: determining the resident frequency of the user in each cell in a target time period according to signaling characteristic data in the XDR data, and then determining the cell corresponding to the resident frequency greater than a preset threshold (for example, 1 hour) as a resident cell of the target time period.

In the L TE communication technology, in order to determine the camping frequency of the terminal in each cell in the target time period, the camping frequency of the terminal in each cell in the target time period can be determined according to the signaling characteristic data in the XDR data received in the S1-U interface and the S1-MME interface, and the camping frequency can reflect the camping time of the terminal (or the user of the terminal) in the corresponding cell.

For example, the frequency of camping when the terminal is in the idle state (referred to as idle camping frequency) may be determined according to the XDR signaling characteristic data of the S1_ MME interface, or the frequency of camping when the terminal is in the service state (referred to as service camping frequency) may be determined according to the XDR signaling characteristic data of the S1_ U interface, or the total frequency of camping may be determined by combining the XDR signaling characteristic data received in the two interfaces.

Based on the S1_ MME message, in the idle state, the longest signaling interval is at least a periodic "Tracking Area Update (TAU)" duration (the duration is 54 minutes according to the T3412 timer of the L TE specification), so that the user must trigger TAU with TAU _ TYPE ═ 3 within 1 hour of the continuous idle state.

Therefore, the number of times of the XDR signaling characteristic data of the S1_ MME interface can be determined as the frequency of camping of the terminal in the idle state, so as to count the camping time of the user of the terminal in the corresponding cell.

The user can generate related service ticket records in the service state. Similar to the idle algorithm, the call ticket records generated by the user in the hour period of the cell can be recorded as 1 residence frequency, and the signaling can be used for judging the residence cell of the user in the service state. For example, when the user generates the S1-U call ticket record in a specific time period of a single day in a 3-hour time period of the same cell, the service state residence frequency in the cell is considered to be 3. The system may screen the highest N cells with a frequency greater than 2 (N may be, for example, 3, 4, or other values); if the same frequency occurs, the cell with the largest number of message records can be selected again.

Therefore, the frequency of camping of the terminal in the service state can be determined according to the XDR signaling characteristic data of the S1_ U interface.

In addition, the total camping frequency of the sum of the idle camping frequency and the service camping frequency may also be used as the camping frequency of the user in the corresponding cell in the determined target time period.

And determining the cell corresponding to the residence frequency larger than the preset threshold value as the resident cell of the target time period. When the residence frequency is greater than the preset threshold, it indicates that the user has performed a long stay in the cell, and the cell may be determined as a resident cell in the target time period. The preset threshold may be set according to actual needs, for example, may be set to 3, 4, or other values.

To further increase the accuracy of the determined resident cells, an investigation period (e.g., 15 days or otherwise) may be determined. In the investigation period, determining a to-be-selected residential cell in each target time period, and if a certain cell in a predetermined proportion (for example, 50%) or more of the days in the investigation period is all the residential cells in the target time period, determining the cell as the residential cell in the target time period.

For example, within 15 consecutive days, the user has at least 8 days at 9: 00-11: 00 and 14: 00-17: when the idle residence frequency plus the service residence frequency in the same cell is not less than 3 in the time period of 00, the cell can be determined as a daytime resident cell of the user; within these 15 days there were at least 8 days at 17: 00-24: when the idle residence frequency plus the service residence frequency in the same cell is not less than 3 in the time period of 00, the cell can be determined as an evening resident cell of the user; within these 15 days, at least 8 days are at 0: 00-9: when the idle residence frequency plus the service residence frequency in the same cell is not less than 3 in the time period of 00, the cell can be determined as a night resident cell of the user.

The method can effectively eliminate the non-resident cell output of regular service generated by users in tide (such as on the way of going to and from work) and similar scenes, thereby ensuring that the determined resident cell is more accurate. In a further embodiment, holidays may also be eliminated from the survey cycle to reduce similar regularity effects.

Due to the characteristics of the wireless network, there may be multiple cell coverage phenomena in the resident location of the user at a specific time, and thus there may be multiple resident locations CI. In one embodiment, a threshold N (e.g., 3, 4, or other value) may be set for the number of resident locations. In the plurality of resident locations CI, no more than N cells may be selected, sorted according to the number of days of occurrence and the time period frequency, as a user resident location cell cluster, in which one or more cells may be located.

The multi-scenario resident location of the user may be output by modeling, such as shown in Table 2.

TABLE 2

Step S12: and determining the longitude and latitude information of the user by utilizing a pre-established MR fingerprint database and MR data.

The MR fingerprint database may be created in advance. In one embodiment, the MR fingerprint database may be created through steps S121 and S122.

And step S121, carrying out correlation and combination on L TE MR data and XDR data of multiple days in the same time range under the analysis region.

In one embodiment, the triplets UE-S1AP-ID, MME GROUP ID and MME code parameter common to MR data and XDR data shown in fig. 2 may be utilized in conjunction with a timestamp and a cell for MR and XDR association to obtain relevant data. According to an example embodiment, the data may include some or all of the fields shown in table 3.

Subscriber (IMSI)

Time of day

CI

AOA

TA

RSRP

Neighboring CI

Neighbor cell RSRP

APP reporting longitude and latitude

……

TABLE 3

Step S122: and creating an MR fingerprint database based on the APP GPS reported by the user and the field test data according to the data obtained in the step S121.

The data of the database can be automatically accumulated and updated, and the MR fingerprint database can be utilized to locate the user record of the user MR data which accords with the rules of the fingerprint database.

Table 4 shows some exemplary fields of the MR fingerprint database created in step S122.

Longitude (G)

Latitude

TA

AOA

SC RSRP

N1 RSRP

N2 RSRP

N3 RSRP

TABLE 4

The URI field in the XDR file of the HTTP ticket in the S1-U can intercept the longitude and latitude reported by part of the APP. The effective APP longitude and latitude can be associated by adopting a Time sliding search mode within n seconds according to the process Start Time (Procedure Start Time) and the process End Time (Procedure End Time) of the call ticket and data in the MRO, invalid data outside n seconds are removed, the MR and XDR data of the same user are associated, and information such as RSRP, adjacent RSRP, RSRQ, TA, RIP, AOA and the like when the user reports the APP longitude and latitude is obtained. In this way, the user APP longitude and latitude and the wireless environment (MR model) can be associated, and an MR fingerprint library that is automatically accumulated and updated is implemented.

After the MR fingerprint database is created, simulation positioning can be performed according to the wireless propagation model of the MR data by using the created MR fingerprint database.

According to one embodiment, the user of the MR data may be positioned to the simulated location by a minimum euclidean distance algorithm. For example, for an MR data record to be located, the signal strengths of its own cell and neighboring cells can be determined, and then in the fingerprint set of the MR home main serving cell, the position where the characteristic information is closest to the characteristic information contained in the current MR is searched, and this position is used as the position of the MR data record. Namely, key value search is carried out by taking the main service cell as a key (key), and only a fingerprint library meeting the matching of the main service cell is extracted; suppose that for the ith MRO data, K primary neighbor cell IDs are included, correspondingReference signal power is noted as RSRP_i，kSelecting K main adjacent cells in the jth fingerprint database information for comparison, and marking the corresponding reference signal power as RSRP_j，kThen, the normalized euclidean distance matching between the ith MRO data and the jth fingerprint library information can be expressed by the following formula (1).

Then, for the full set of fingerprint library sequence numbers denoted as J, the minimized normalized euclidean distance matching algorithm for matching the ith MRO data to the s-th fingerprint library can be represented by the following formula (2).

Correspondingly, the ith MRO data can be considered to be matched with the position corresponding to the s fingerprint database, and the data is sorted and then added with longitude and latitude information to be output.

An example of the latitude and longitude of the finally output MR data record is shown in table 5.

Subscriber (IMSI)

Time of day

CI

AOA

TA

RSRP

Neighboring CI

Neighbor cell RSRP

Latitude and longitude

……

TABLE 5

Step S13: and screening out data for determining the position where the user resides in the target time period from the communication data of the user in the target time period according to the resident cell and the latitude and longitude information.

In one embodiment, step S13 may include steps S131 and S132.

S131: and carrying out association combination on the resident cell of the user in the target time period and the longitude and latitude information of the user according to the user, the time period and the cell.

S132: and determining the data of the resident position of the user in the target time period by cleaning and removing the positioning longitude and latitude information of the resident cell at the ticket time point recorded by the S1-MME and the S1-U ticket outside the resident cell in the target time period.

The screening of the communication data can meet the requirement that the signaling call tickets generated by the user over a specified time (for example, 1 hour) are all in the cell within the range of the cell group where the user resides, so as to avoid the situation that the user resides around the resident location for a short time.

After the data are screened out, the simulated longitude and latitude set of the resident position of the user in various target time periods (such as day, night and night) is obtained, as shown in table 6, so that the accurate position of the user in the target time period can be accurately determined by using the data.

TABLE 6

The data processing method provided by the embodiment of the invention determines the resident cell of the user in the target time period according to the XDR data, and determines the latitude and longitude information of the user by utilizing the pre-established MR fingerprint database and the MR data, so that the data for determining the resident position of the user in the target time period can be screened out from the communication data of the user in the target time period according to the resident cell and the latitude and longitude information. The method can screen and eliminate the sampled data of the user moving around the indoor scene and at a slow speed, so that the resident position of the user can be accurately determined by using the data.

According to the embodiment of the invention, the multi-scene resident positions of the user are modeled, so that the resident indoor positions of the user are accurately filtered and positioned. Compared with the traditional positioning algorithm based on mobile network data, the target pertinence is more definite, and the positioning is more accurate; compared with mass test simulation and software positioning SDK methods, the method can save larger cost and has the advantages of reducing maintenance difficulty and the like. The method can improve the accuracy of the static user positioning only based on the mobile network data to a greater extent, can find out key guarantee user groups under the network, and provides low-cost and more effective support for the network quality evaluation of the user resident position, the complaint reduction and the satisfaction improvement.

Although the above description of the embodiment is made in the order of step S11 to step S13, this is not limitative. The method may include more or fewer steps, or the order of the steps may be reversed (e.g., step S12 is performed before step S11 is performed).

For example, after the communication data is filtered in step S13, the filtered data may be cleaned, so as to further increase the accuracy of the user' S resident location determined by using the data.

For example, the discrete degree calculation can be carried out according to a 10-meter × 10-meter (or other value) area, and the filtering eliminates sampling points which are sparse (for example, the MR simulation longitude and latitude sampling number is divided by a fixed sample area which is smaller than a threshold value proportion, as shown by two areas on the right half part of the figure 3).

In an embodiment, the resident building position of the user in the target time period can be determined according to the cleaned data and the matching of the longitude and latitude sampling concentration and the geographic building by combining a map processing program. FIG. 4 shows a related example; the figure shows five buildings in a general box shape and the user's resident building location can be determined as the area shown in the left half of the oval.

Embodiments of the present invention also provide a data processing apparatus, which may correspond to the method described above. As shown in fig. 5, the apparatus 50 may include a resident cell determining unit 501, a latitude and longitude information determining unit 502, and a data processing unit 503. The resident cell determining unit 501 determines a resident cell of the user in a target time period according to the XDR data; a latitude and longitude information determination unit 502 for determining the latitude and longitude information of the user by using a pre-established MR fingerprint database and MR data; the data processing unit 503 is configured to screen, according to the residential cell and the longitude and latitude information, data used for determining a location where the user is resident in the target time period from the communication data of the user in the target time period.

Since the apparatus 50 adopts the same inventive concept as embodiment 1, the problems of the prior art can be solved, and will not be described herein.

The residential cell determination unit 501 may determine a residential cell of the terminal in a target time period from XDR data. For example, the camping frequency of the terminal in each cell in the target time period may be determined according to the signaling characteristic data in the XDR data, and the cell corresponding to the camping frequency greater than the preset threshold may be determined as the resident cell in the target time period.

In practical application, the camping frequency of the terminal in the idle state may be determined according to signaling characteristic data in XDR data received by the S1_ MME interface, or the camping frequency of the terminal in the service state may be determined according to signaling characteristic data in XDR data received by the S1_ U interface, or the sum of the idle camping frequency and the service camping frequency.

The apparatus 50 may further comprise an MR fingerprint database building unit which may build the MR fingerprint database by: and associating and merging the MR data and the XDR data in a target time period for multiple days through a common triple of the MR data and the XDR data, and creating the MR fingerprint database according to the merged data.

The latitude and longitude information determination unit 502 may determine latitude and longitude information of the user by using a pre-established MR fingerprint database and MR data, for example, determine signal strengths of a local cell and a neighboring cell of the MR data; searching a position where the characteristic information is closest to the characteristic information contained in the current MR data in an MR fingerprint database of the MR data home main service cell; and determining the longitude and latitude of the position as the determined longitude and latitude information of the user.

The data processing unit 503 may screen, according to the residential cell and the longitude and latitude information, data for determining a location where the user is resident in the target time period from the communication data of the user in the target time period. For example, a resident cell of a user in a target time period and longitude and latitude information of the user may be associated and combined according to the user, a time period and a cell; and determining the data of the resident position of the user in the target time period by cleaning and removing the positioning longitude and latitude information of the resident cell at the ticket time point recorded by the S1-MME and the S1-U ticket outside the resident cell in the target time period.

The apparatus may further comprise a data cleansing unit and a resident location determination unit. The data cleaning unit can clean the data by calculating the dispersion of the data obtained by screening. The resident position determining unit can determine the resident building position of the user in the target time period through the cleaned data and a map processing program.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. The data processing device 50 may take the form of an entirely hardware, an entirely software, or a combination of software and hardware implementations. And may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) containing computer-usable program code.

In the technical scheme described herein, the user periodic tide category clustering is performed by extracting the mobile management data and information in the control plane and service plane signaling of the user in idle state and service state, and the user resident position (cell cluster) modeling is established; correlating the S1 signaling with the MR data, and correcting the MR wireless transmission simulation positioning data by creating an APP longitude and latitude and an actual test data correction fingerprint database to obtain full user-level positioning data; therefore, the indoor positioning, service, MR and other related information of various scene resident positions of the user can be obtained through algorithm correlation.

The description herein makes reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

The foregoing description is only exemplary of the invention and is not intended to be limiting. Various modifications and alterations will occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims.

Claims

1. A data processing method, comprising:

determining a resident cell of a user in a target time period according to the XDR data;

determining longitude and latitude information of the user by utilizing a pre-established MR fingerprint database and MR data;

screening out data for determining the position where the user resides in the target time period from the communication data of the user in the target time period according to the resident cell and the latitude and longitude information;

the step of determining the resident cell of the terminal in the target time period according to the XDR data comprises the following steps:

determining the residence frequency of the terminal in each cell in a target time period according to signaling characteristic data in the XDR data;

and determining the cell corresponding to the residence frequency greater than the preset threshold value as the resident cell of the target time period.

2. The method as claimed in claim 1, wherein the step of determining the frequency of camping of the terminal in each cell according to the signaling characteristic data in the XDR data comprises:

determining the residence frequency of the terminal in an idle state according to signaling characteristic data in XDR data received by an S1_ MME interface; and/or

And determining the residence frequency of the terminal in the service state according to the signaling characteristic data in the XDR data received by the S1_ U interface.

3. The method of claim 1, wherein the MR fingerprint database is created by:

correlating and combining the MR data and the XDR data of multiple days in a target time period through a common triple of the MR data and the XDR data;

and creating the MR fingerprint database according to the merged data.

4. The method of claim 1, wherein the step of determining latitude and longitude information of the user using a pre-established MR fingerprint database and MR data comprises:

determining signal strengths of a local cell and a neighboring cell of the MR data;

searching a position where the characteristic information is closest to the characteristic information contained in the current MR data in an MR fingerprint database of the MR data home main service cell;

and determining the longitude and latitude of the position as the determined longitude and latitude information of the user.

5. The method of claim 1, wherein the step of screening the communication data of the user in the target time period according to the resident cell and the latitude and longitude information comprises:

carrying out association combination on a resident cell of a user in a target time period and longitude and latitude information of the user according to the user, the time period and the cell;

and determining the data of the resident position of the user in the target time period by cleaning and removing the positioning longitude and latitude information of the resident cell at the ticket time point recorded by the S1-MME and the S1-U ticket outside the resident cell in the target time period.

6. The method of claim 1, wherein the method further comprises:

cleaning the first data by calculating the dispersion of the first data obtained by screening to obtain second data;

and determining the resident building position of the user in the target time period by combining the second data with a map processing program.

7. A data processing apparatus, comprising:

a resident cell determining unit, which determines the resident cell of the user in the target time period according to the XDR data;

the longitude and latitude information determining unit is used for determining the longitude and latitude information of the user by utilizing a pre-established MR fingerprint database and MR data;

the data processing unit is used for screening out data for determining the position where the user resides in the target time period from the communication data of the user in the target time period according to the resident cell and the longitude and latitude information;

the resident cell determining unit determines the resident frequency of the terminal in each cell in the target time period according to the signaling characteristic data in the XDR data, and determines the cell corresponding to the resident frequency greater than a preset threshold value as the resident cell in the target time period.

8. The apparatus of claim 7, further comprising an MR fingerprint database creation unit, wherein the MR fingerprint database creation unit associates and merges MR data and XDR data of multiple days in a target time period by a triplet common to the MR data and the XDR data, and creates the MR fingerprint database according to the merged data.