A method for locating the accurate position of a communication base station based on APP data

Abstract

The present invention discloses a method for accurately locating a communication base station based on APP data, and relates to the field of intelligent communication technology. Specifically, after extracting the APP data, the data is first preliminarily cleaned to ensure the accuracy of the data column; then the format conversion and data cleaning are performed again before the data is stored in the database. After the data is stored in the database, the random forest preprocessing method is used to process the data, and reasonable and effective data is screened out according to the test data cycle. The optimal value calculation function is used to calculate the optimal value of the system parameter and then enter the next step. The screened data is isolated forest processed to effectively extract effective information from the complex information. The method locates the accurate position of the communication base station based on the APP data, does not require the active participation of the user, and can be widely used in remote mountainous areas, scenic spots, large-scale activity venues and other areas where monitoring personnel are difficult to conduct field inspections.

Description

Technical Field

[0001] The present invention relates to the field of intelligent communication technology, and in particular to a method for accurately locating a communication base station based on APP data. Background Art

[0002] A series of problems are often encountered in the process of base station management. For example, the GPS location reported by users using smart terminal APP is not accurate, because in actual situations, the signals received and sent by the base station are likely to be blocked by various residential buildings, shopping malls, subways and other buildings in the city, and are also likely to be isolated by mountains, cliffs and trees in the wild, resulting in errors in the positioning data reported by users. The switching between different base station CIs is not in line with the norm, and network signal delays and base station switching will cause data loss and abnormalities, so the reported data will have great errors and mistakes, which is not conducive to the accurate positioning of the base station. For daily base station management work, especially when urban management departments confirm the action route of target personnel based on GPS positioning, it causes great trouble and consumes a lot of manpower and material resources excessively. Therefore, the industry is in urgent need of a scientific and effective method that can achieve the purpose of base station management and positioning under the premise of low-cost investment.

[0003] In the field of base station management, the available user APP data is increasing, and the research on APP data characteristics is becoming more and more in-depth. However, the traditional calculation method is mostly to directly use the original data uploaded by the APP for calculation, without doing too much analysis and processing of the data source. Due to the incompleteness, abnormality and error of the data, it will directly lead to the error of the final calculation result, which will add trouble to the city management department and increase its work difficulty. The advantage of APP data processing is that the data source is broad. The smartphone APP of a large number of users is the largest source of information. A large number of social groups can effectively guarantee the coverage and coverage strength of the collected signals, avoid errors caused by less and poor data, and effectively identify the construction location of the operator's base station, the direction of the community, the adjustment of equipment power, etc. However, when the base station information is not accurate enough and the coverage is not wide enough, the traditional data processing method will have problems with this phenomenon of missing information, abnormality or even error, and its efficiency will be greatly reduced or even errors will occur. It is impossible to accurately locate the base station location, which will cause great trouble for the city management department to manage the city.

[0004] Therefore, we propose a method to locate the exact position of the communication base station based on APP data to solve the above problems. Summary of the invention

[0005] The present invention provides a method for locating the accurate position of a communication base station based on APP data, which utilizes the operator, base station LAC, base station CI and GPS location data reported in real time by mobile terminal users using APP, and uses artificial intelligence calculation methods and big data processing technology to calculate the accurate geographical location of the base station, thereby solving the problem of inaccurate positioning of the communication base station caused by the method proposed in the above background technology using mobile phone GPS positioning and analyzing the original data uploaded by APP.

[0006] The present invention provides the following technical solutions: a method for accurately locating a communication base station based on APP data, the technical process being: cleaning and preprocessing APP data and inserting the data into a database; distinguishing base station types (2 / 3 / 4 / 5G) according to base station CI range types, and deleting data without operator codes and data longitude and latitude in uploaded CI data; calculating base station number ENBID based on different base station type CIs; filtering out records in which the user reported GPS value is greater than n (optimal value) when calling database data; using an isolation forest algorithm to process the data of each base station, using a box plot and an interquartile range method to filter out abnormal data, and performing targeted calculation processing on base stations under different situations to improve their calculation accuracy; calculating the centroid position of all points under each base station, that is, the base station position; using an optimal value selection function to calculate the best positioning point; calculating the base station coverage contour; and calculating the base station thermal coverage.

[0007] Compared with the prior art, the present invention has the following beneficial effects:

[0008] 1. This method of locating the accurate position of communication base stations based on APP data obtains the user's APP data time period, cleans, converts, organizes and stores the data, and performs isolation forest preprocessing on the stored data; at the same time, cleans the operator's industrial parameter data, distinguishes 4G and 5G data, and stores them separately. Download the OSM area boundary longitude and latitude and read the data table to compare the two parts of data and take the intersection, calculate the minimum distance between the two points, and present the base station page display in different ranges, different operators, and different regions on the map. This method can obtain and use APP data information to the greatest extent, conduct in-depth data mining and processing, obtain the meaning behind the information, clean data in multiple directions from multi-dimensional data, and obtain the most accurate base station location.

[0009] 2. This method of locating the exact position of communication base stations based on APP data is based on the APP data and OSM data developed by the public security departments in-depth cooperation with operators. It does not require the active participation of users and can be widely used in remote mountainous areas, scenic spots, large-scale event venues and other areas where it is difficult for monitoring personnel to conduct on-site inspections. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1It is a schematic diagram of the technical principle flow chart of the present invention. DETAILED DESCRIPTION

[0011] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0012] The present invention provides an embodiment: please refer to Figure 1 A method for accurately locating a communication base station based on APP data adopts a variety of artificial intelligence data processing methods including isolation forest. After the APP data is extracted, it is not used directly, but the data is first preliminarily cleaned to ensure the accuracy of the data column; then the format is converted and the data is cleaned again before entering the database. After entering the database, the random forest preprocessing method is used to process the data. Reasonable and effective data are screened out according to the test data cycle. The optimal value calculation function is used to calculate the optimal value of the system parameter and then enter the next step. The isolated forest processing is performed on the screened data to effectively extract the effective information from the complex information, and the latitude and longitude information under the OSM map is combined to realize the precise positioning of base stations in different ranges, different operators and different regions.

[0013] This method locates the exact position of the communication base station based on APP data. It locates the exact position of the base station with the greatest accuracy by integrating and analyzing the base station device information connected to the APP data on the user's mobile device and multiple heterogeneous data such as the obtained base station position.

[0014] Specifically, the following steps are included: Step 1: Acquire the APP data time period including but not limited to the base station number ENBID, base station CI number, operator name and GPS location data.

[0015] Step 2: Clean the APP data to ensure the accuracy of the data columns and insert the cleaned data table into the database.

[0016] Step 3: Read the data stored in step 2, call the isolation forest function for preprocessing, convert the read geographic information data file into the type required by the compiled language, and delete the part of the information data where the operator number is empty and the reported CI latitude and longitude are empty.

[0017] APP data isolation forest preprocessing includes: APP monthly data query, query result table generation, APP data reporting location table generation, CI reporting statistics table, APP data set removal, and screening of specific types of CI. Isolation forest to find abnormal scores in

[0018] c(n)=2H(n-1)-(2(n-1) / n), H(i) is the harmonic number, which can be estimated as ln(i)+0.5772156649, Where x is the xth isolated tree and n is the total number of isolated trees.

[0019] Distinguish base station types (2 / 3 / 4 / 5G) according to the base station CI range type, delete data without operator code and data longitude and latitude in uploaded CI data; calculate base station number ENBID based on different base station type CI, filter out records where the user reported GPS greater than n when calling database data, and the value of n is the optimal number obtained by the optimal value calculation function, use the isolation forest algorithm to process the data of each base station, and use the interquartile range method to construct a data box plot, classify the data in the data set, and obtain values ​​in the range of minimum quantile value to maximum quantile value. The quantile value standard is obtained by fine-tuning parameters according to different data quality and mobile phone communication standards, that is, filtering out abnormal data, so that the data can be denoised more specifically according to different base station types, different geographical features, different signal coverage ranges, and different base station powers.

[0020] Step 4: The storage table cleans and converts the data content in the database, stores the processed data in the database, and starts multiple processes to perform isolation forest processing on the above data, and performs targeted calculation processing on base stations under different situations to improve its calculation accuracy.

[0021] Step 5. Clean the artificial parameter data of the three operators and store them separately according to CI. CI is the range information of the longitude and latitude of APP users. Select some required fields, select 4G and 5G base stations, generate a new table after processing, and process the table data to include longitude and latitude fields. The data processing work on the table includes deduplication, screening, reordering, and calculation of the scores and label values ​​of the obtained longitude and longitude.

[0022] Step 6. According to the longitude and latitude of the regional boundary downloaded from OSM, select the geographic data within the regional range, store them in the database, and process them. Geographic data processing includes calculating the distance between two points on the earth, including converting the physical geographic longitude and latitude into radians, establishing a relationship between the distances between the two points according to the average radius of the earth and the trigonometric function relationship formula, and calculating the actual distance between the two points on the earth (lon1, lat1) and (lon2, lat2):

[0023]

[0024] Step 7: Intersect the processed table data with the data downloaded from OSM, calculate the distance between all two points, and select the minimum distance.

[0025] Step 8. Add APP data longitude and latitude columns and industrial parameter longitude and latitude columns to the table, and store them after coordinate system conversion.

[0026] Step 9: Select base stations with correction distances in different ranges, different operators, and different areas in the database for page display.

[0027] Base station number calculation formula includes: 2G / 3G / 4G base station number calculation formula (Round down the result); 5G base station number calculation formula (The result is rounded down).

[0028] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for locating the exact position of a communication base station based on APP data, characterized in that: The following steps are involved: Step 1: Obtain the APP data time period; Step 2: Clean the APP data to ensure the accuracy of the data column and store the cleaned data table in the database; Step 3: read the data stored in step 2, call the isolation forest function for preprocessing, and filter out the data where the number of GPS points reported by the base station data user CI is greater than n, and the value of n is the optimal number obtained by the optimal value calculation function; Step 4: The storage table cleans and converts the data content in the database, stores the processed data in the database, and starts multiple processes to perform isolation forest processing on the above data; Step 5: Clean the human parameter data of the three operators, store them separately according to CI, select some required fields, select 4G and 5G base stations, generate a new table after processing, and process the table data to include longitude and latitude fields; Step 6: According to the longitude and latitude of the regional boundaries downloaded from OSM, the geographic data within the regional scope is screened out, stored in the database, and processed; Step 7: Intersect the processed table data with the data downloaded from OSM, calculate the distance between all two points, and select the minimum distance; Step 8. Add APP data longitude and latitude columns and engineering parameter longitude and latitude columns to the table, convert the coordinate system and store them in the database; Step 9: Select base stations with correction distances in different ranges, different operators, and different areas in the database for page display.

2. According to claim 1, a method for locating the accurate position of a communication base station based on APP data is characterized in that: The APP data includes but is not limited to base station number ENBID, base station CI number, operator name and GPS location data.

3. According to claim 1, a method for locating the accurate position of a communication base station based on APP data is characterized in that: The data preprocessing in step three includes: converting the read geographic information data file into the type required by the compilation language, and deleting the part of the information data where the operator number is empty and the reported CI latitude and longitude are empty.

4. According to claim 2, a method for locating the accurate position of a communication base station based on APP data is characterized in that: The base station number calculation formula includes: 2G / 3G / 4G base station number calculation formula And the 5G base station number calculation formula All results are rounded down.

5. According to claim 1, a method for locating the accurate position of a communication base station based on APP data is characterized in that: The CI is the range information composed of the longitude and latitude of the APP user.

6. According to claim 1, a method for locating the exact position of a communication base station based on APP data is characterized in that: In step 5, a list of longitudes and latitudes is established, and data processing work on the table includes deduplication, screening, reordering, and calculation of scores and label values ​​for the obtained longitudes and latitudes.

7. According to claim 1, a method for locating the exact position of a communication base station based on APP data is characterized in that: The APP data isolation forest preprocessing includes: APP monthly data query, generation of query result table, generation of APP data reporting location table, CI reporting statistics table, APP data set removal, screening of specific types of CI, isolation forest to find abnormal scores Where c(n) = 2H(n-1)-(2(n-1) / n), H(i) is the harmonic number, which can be estimated as ln(i)+0.5772156649, Where x is the xth isolated tree and n is the total number of isolated trees.

8. According to claim 1, a method for locating the accurate position of a communication base station based on APP data is characterized in that: The geographic data processing includes calculating the distance between two points on the earth, including converting the physical geographic longitude and latitude into radians, establishing a relationship between the distances between the two points according to the average radius of the earth and the trigonometric function relationship formula, and calculating the actual distance between the two points on the earth (lon1, lat1) and (lon2, lat2):

9. The method for locating the accurate position of a communication base station based on APP data according to claim 1, characterized in that: When the isolation forest algorithm is used to process the data of each base station, the box plot and interquartile range method are used to filter out abnormal data.

Images