CN114363953B - Method and system for realizing frequent building entrance of user based on multiple data sources - Google Patents
Method and system for realizing frequent building entrance of user based on multiple data sources Download PDFInfo
- Publication number
- CN114363953B CN114363953B CN202110579321.1A CN202110579321A CN114363953B CN 114363953 B CN114363953 B CN 114363953B CN 202110579321 A CN202110579321 A CN 202110579321A CN 114363953 B CN114363953 B CN 114363953B
- Authority
- CN
- China
- Prior art keywords
- building
- user
- card number
- frequent
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a method and a system for realizing building entrance of a user in a residential building on the basis of multiple data sources, which belong to the technical field of building entrance of the user in the residential building, and comprise the steps of building user identification and the like in the residential building range. The invention does not depend on the positioning of the base station, and reduces the influence of high positioning accuracy error rate caused by the switching of the base station and the large coverage area of the base station; the method has the advantages that the frequent floor of the user is analyzed and calculated in an MR fingerprint library positioning mode, the user positioning accuracy is improved, and the accuracy of entering the building in the frequent floor of the user can be intuitively depicted by introducing the concept of the frequent floor and the confidence coefficient of the user; the method of combining the installed address information and the usual ground can be used for considering the screened installed address of the user as the accurate address of the user residence, so that the result of the usual ground entering of the user is optimized, the usual ground entering of the user is realized, and the method can be effectively applied to the scenes of optimizing and accurately marketing the internal operation and maintenance, rendering the external data, supporting the industrial application and the like.
Description
Technical Field
The invention relates to the technical field of building entrance of users in a living place, in particular to a method and a system for realizing building entrance of users in a living place based on various data sources.
Background
Along with the continuous development of the mobile internet of things and the internet of things, various production fields of society continuously generate a large amount of data. The telecom operator is taken as an important owner of big data, and the data has the characteristics of large quantity, multiple types, reality and accuracy; in recent years, the traditional business income of telecom operators is continuously reduced, new business growth points are urgently needed to be expanded, and meanwhile, international operators also actively develop strategy transformation, layout big data and other emerging fields; therefore, the method fully excavates and plays the data value around the current data gold mine, which is a necessary way for the current telecom operators, and the position capability is one of the data core capabilities of a plurality of operators, thereby playing a vital role in optimizing the internal operation and maintenance, accurately marketing, and supporting the external data and the industrial application. Because of the lack of a scientific and effective positioning method, the position accuracy of the user positioning cannot be ensured, and the confidence of the positioning result cannot be provided; because of the lack of support for accurate and efficient data sources, users cannot be located to a particular cell building.
The technology currently in the mainstream of operators and capable of providing more accurate location capability is the fingerprint positioning technology based on MR; MR is known collectively as "Measurement Report", i.e. measurement report. The mobile terminal periodically reports the information such as the downlink signal strength, the quality and the like of the cell where the mobile terminal is located to the base station in a measurement report mode through a control channel at a certain time interval, and the base station uploads the downlink information reported by the terminal and the uplink physical information collected by the base station to a base station controller, and collects and counts the downlink information and the uplink physical information. The MR records radio measurement information such as serving cell/neighbor ID, RSRP, RSRQ, TA, AOA, CQI, MCS, PHR of the UE during service maintenance. The reported MR can be used for triggering events such as switching and the like by a wireless resource control sublayer in the system, and also can be used for system maintenance and observation of the running state of the system; location fingerprints refer to scene features of the location where the user is located.
The traditional method for identifying the building where the user is always located is to analyze and identify the location of the base station, and identify the user into the building corresponding to the periphery through the distribution condition of the base station at night in a period, combining with the GIS information of the building and a cluster analysis algorithm. In the practical application process, there are great limitations. Firstly, from the distribution condition of the base stations, the coverage area of the base stations is larger, and the larger the coverage area can be positioned under the influence of the switching of the base stations, the more the accuracy of identifying the user position is influenced. And secondly, the living place condition of the user every day cannot be analyzed from the living place angle, and the confidence coefficient parameter capable of accurately describing the living building of the user cannot be given. Finally, multidimensional data sources such as installed addresses are not introduced to optimize users to enter the building frequently. Therefore, many scenes such as optimizing and accurately marketing the inner operation and maintenance, rendering the outer data, supporting the industrial application and the like are difficult to apply to actual production and life. Therefore, a method for realizing frequent building entrance of users based on various data sources is provided.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: how to solve the problems that the traditional method for identifying the building where the user always stays is low in user position identification accuracy, cannot give out confidence parameters which can accurately characterize the building where the user stays, and the like, provides a method for realizing the building where the user always stays based on various data sources.
The invention solves the technical problems through the following technical proposal, and the invention comprises the following steps:
s1: building user identification in residential area
Identifying building structures around the user frequent land, and calculating the distance from the user frequent land to each building structure within a set distance range;
s2: master-slave card user information judgment
According to different user numbers corresponding to the same customer id and according to the ordering of the number account opening dates, the number with the earliest account opening time is taken out to be the main card number, and the rest is the auxiliary card number; then, calculating whether the distance from the frequent ground of the auxiliary card number to the frequent ground of the main card number is within a certain range, if so, judging that the auxiliary card number and the main card number are in the same building;
s3: building name and installation address matching
For a user who identifies a building and has an installed address, adopting an analysis mode of combining cosine similarity with the maximum public substring matching rate to analyze and match the building and the installed address, and taking out the building with the highest matching rate as a normally-living building of the user;
s4: confidence judgment of building in range of distance from living place
For a user who identifies building buildings but does not have an installed address, adopting the building with the highest confidence in the surrounding area of the common ground as the common ground building of the user;
s5: directly adopting the user's normally-located position
For users who have no building information in the usual ground, directly taking the longitude and latitude information of the usual ground as the usual ground building of the user;
s6: building update of frequent building by sub-card user
And regarding the correspondence of the identified primary and secondary card numbers, the users with the primary and secondary card numbers can be regarded as being in the same building, and the information of the frequently-lived building of the identified secondary card number users is updated to be consistent with the primary card number.
Further, in the step S1, the distance range is set to be within 200m from the user' S usual ground.
Further, in the step S3, the building and the installed address are both chinese character strings.
Still further, in the step S4, the confidence is a number of days per total number of days of sampling points within 50 meters of the building from the daily living place.
Further, in the step S4, when the cosine similarity is used for the string comparison, each term is assigned a different dimension, and one dimension is represented by a vector, and the value in each dimension corresponds to the frequency of occurrence of the term in the document.
Further, in the step S4, when the similarity of the two strings is compared by using the maximum common substring matching rate, matching the string to be compared with the string to be compared, and if successful, recording the successful matching length; if not, the length is reduced by 1, and matching is continued. And all the successfully matched substrings are accumulated and divided by the matched substrings, the duty ratio is calculated, and the larger the duty ratio is, the more similar the two substrings are.
The invention also provides a system for realizing the frequent floor access of the user based on various data sources, which adopts the method to realize the identification of the frequent floor access of the user, and comprises the following steps:
the building identification module is used for identifying building buildings around the user frequent land and calculating the distance from the user frequent land to each building in a set distance range;
the main and auxiliary card judging module is used for sorting according to different user numbers corresponding to the same customer id and according to the number account opening date, taking out the number with the earliest account opening time as the main card number and the rest as the auxiliary card number; then, calculating whether the distance from the frequent ground of the auxiliary card number to the frequent ground of the main card number is within a certain range, if so, judging that the auxiliary card number and the main card number are in the same building;
the matching module is used for analyzing and matching the building and the installed address by adopting an analysis mode of combining cosine similarity and the maximum public sub-string matching rate for a user who recognizes the building and the installed address, and taking out the building with the highest matching rate as a resident building of the user;
the confidence judging module is used for adopting the building with the highest confidence in the surrounding area of the usual ground as the usual ground building of the user for the user who identifies the building but does not have the installed address;
the module is directly adopted and is used for directly taking the longitude and latitude information of the normally-living land of the user as the normally-living land building of the user for the user who has no building information on the normally-living land;
the updating module is used for updating the information of the normally-living building of the identified auxiliary card number user to be consistent with the main card number, wherein the corresponding relation of the main card number and the auxiliary card number which are identified can be regarded as that the main card number user stays in the same building;
the central processing module is used for sending instructions to other modules to complete related actions;
the building identification module, the main and auxiliary card judgment module, the matching module, the confidence judgment module, the direct adoption module and the updating module are all electrically connected with the central processing module.
Compared with the prior art, the invention has the following advantages: the method for realizing frequent building entrance of the user based on various data sources does not depend on base station positioning, and reduces the influence of high positioning accuracy error rate caused by base station switching and large base station coverage; the method has the advantages that the frequent floor of the user is analyzed and calculated in an MR fingerprint library positioning mode, the user positioning accuracy is improved, and the accuracy of entering the building in the frequent floor of the user can be intuitively depicted by introducing the concept of the frequent floor and the confidence coefficient of the user; the method of combining the installed address information and the usual ground can be used for considering the screened installed address of the user as the accurate address of the user residence, so that the result of the user going into the building on the usual ground is optimized, the usual ground going into the building of the user is realized, the method can be effectively applied to the optimization and the accurate marketing of the internal operation and maintenance, and the method is worth being popularized and used in the scenes of external data rendering, industrial application support and the like.
Drawings
FIG. 1 is a schematic flow diagram in an embodiment of the invention;
FIG. 2 is a schematic diagram of a second embodiment of the present invention;
FIG. 3 is a schematic diagram of a process for implementing step four in an embodiment of the present invention.
Detailed Description
The following describes in detail the examples of the present invention, which are implemented on the premise of the technical solution of the present invention, and detailed embodiments and specific operation procedures are given, but the scope of protection of the present invention is not limited to the following examples.
As shown in fig. 1, this embodiment provides a technical solution: the invention relates to a method for realizing the frequent floor entrance of a user based on various data sources, which realizes the identification of the frequent floor entrance of the user according to the information such as the address of the user broadband installation, the frequent floor location, the GIS information of a building, the users of a main card and a sub card, and the like, and the main data sources and the flow steps are as follows:
description of data sources:
broadband installation address: contains the user number and the installed address;
constant floor: the method comprises the steps of including a user number, a user resident location longitude and a resident location latitude;
the process of obtaining the common place is to obtain the MR measurement report information of the user, and locate the specific position of each MR measurement report of each user based on the matching of the three-point positioning algorithm and the MR fingerprint library.
Firstly, an MR fingerprint library is required to be established, MR data and S1-U data (xdr signaling data contains specific longitude and latitude information, has low association degree and can be used as basic data for library establishment) are taken out and association results are taken out and fall into corresponding 50-meter grids, and characteristic information (comprising average level value, main cell information, neighbor cell information, ta value and the like) of each grid is calculated respectively according to points fallen into the grids, so that the MR fingerprint library is obtained; and in the final positioning process, for each piece of MR measurement report information to be positioned, the characteristic information is matched with an MR fingerprint library, three grids closest to the characteristics of the MR measurement report information are found out according to a three-point positioning algorithm, and the average longitude and latitude of the three grids are calculated to be the final position of the MR measurement report information. Normally taking normal work and rest time, namely 00:00-06:00 and 20:00-24:00 in the early morning, and then analyzing the daily residence place and the daily work place position of a user every day through clustering analysis of the located MR measurement report distribution points in the daily time range;
building GIS information: the method comprises the steps of including cell names, building names and building longitude and latitude sequences;
and (3) a main and auxiliary card user: the method comprises the steps of client id, user mobile phone number and mobile phone number registration time.
The implementation flow is as follows:
step one: building user identification in residential area
The distance from the user to each building is calculated, and building information with the distance within 200 meters is screened out, so that the calculation complexity is reduced. Since the user is relatively accurate from time to time, it is only necessary to calculate the degree of matching of the building within the peripheral range of the time to time, respectively.
Step two: master-slave card user information judgment
As shown in fig. 2, there are a number of users under the same operator, which may be self-service or used by the family. According to different user numbers corresponding to the same customer id and according to the ordering of the number account opening dates, the number with the earliest account opening time is taken out to be the main card number, and the rest is the auxiliary card number. And then calculating whether the distance from the frequent ground of the auxiliary card number to the frequent ground of the main card number is within 50 meters, and if so, considering that the auxiliary card number and the main card number are in the same building.
Step three: building name and installation address matching
For the users who recognize building buildings and have installed addresses, the building buildings and the installed addresses are Chinese character strings, and according to a certain method, the matching can be considered successful as long as the similarity of the character strings is high.
In the step, an analysis mode of combining cosine similarity and the maximum common substring matching rate is actually adopted, and the building with the highest matching rate is taken out.
Cosine similarity: the similarity of the two vectors is evaluated by calculating the cosine value of the included angle of the two vectors, wherein the cosine value is close to 1, the included angle tends to 0, which indicates that the more similar the two vectors are, the cosine value is close to 0, and the included angle tends to 90 degrees, which indicates that the two vectors are more dissimilar. Cosine similarity draws vectors into vector space according to coordinate values. In performing the string comparison, each term is assigned a different dimension, and one dimension is represented by a vector whose value in each dimension corresponds to the frequency with which the term appears in the document.
Maximum common substring match rate: the maximum common substring match rate is used to compare the similarity of two string texts. And matching the character strings to be compared with the character strings to be compared, and if the character strings to be compared are successful, recording the successful matching length. If not, the length is reduced by 1, and matching is continued. And the process is circulated all the time. And accumulating the lengths of all successfully matched sub-strings, dividing the lengths by the lengths of the strings with the matching, and calculating the duty ratio, wherein the larger the duty ratio is, the more similar the two strings are.
The cosine similarity has the advantages that two character strings can be analyzed and compared on the whole, the difference of individual words is ignored, the similarity of the two character strings can be truly reflected, but when the length difference of the two character strings to be compared is large, the cosine similarity has less obvious advantages and even smaller errors can occur; the maximum common sub-string matching rate can split the strings to be compared into a plurality of sub-strings for comparison when two strings are compared, and the method has the advantages that the similarity of the strings is reflected by the relevance of the common sub-strings, and the method is also suitable for the situation that the length difference between the two strings to be compared is large, but the method has the defect that the similarity cannot be analyzed in whole, and only the analysis from the maximum common sub-string fragments is performed. Considering the advantages and disadvantages of two methods of cosine similarity and maximum public sub-string matching rate, comparing the string similarity by giving different weights to each method and combining the advantages of the two methods, and greatly improving the similarity matching accuracy.
Step four: confidence of building in range of distance from constant location
As shown in FIG. 3, for a user who recognizes a building but does not have an installed address, a building with highest confidence in the surrounding area of the usual residence (confidence: days in 50 meters from the building per day/total days of sampling points
Day to day distance of 50 meters from building: the distance of the user from the home to the identified building is in the range of 50 meters per day.
For example, taking data of one month as a basis, the number of days in which a daily living place is within 50 meters from a building is defined as how many days of the daily living places are within 50 meters from the identified building in 30 days of one month; the total number of days at the sampling point is 30 days at the sampling point.
Step five: directly adopting the user's normally-located position
Because of the incomplete factor influence of the building gis information and the influence of lower partial accuracy of the frequent location, partial users have no building information at the frequent location periphery. For the part of users, the longitude and latitude information of the common place is directly taken. The users corresponding to the sub-cards are consistent with the main cards in the building.
Step six: building update of frequent building by sub-card user
And regarding the main and auxiliary card corresponding relation which is identified according to the rule, the main and auxiliary card users can be regarded as being in the same building, and the information of the frequently-lived building of the identified auxiliary card users is updated to be consistent with the main card.
In this embodiment, the residential site includes a resident site and a resident work site, where the resident site is a resident site, that is, a user resident site, that is, a resident work site, that is, a user work site.
The method for realizing frequent building entrance of the user based on various data sources of the embodiment does not depend on base station positioning, and reduces the influence of high positioning accuracy error rate caused by base station switching and large base station coverage; the method has the advantages that the frequent floor of the user is analyzed and calculated in an MR fingerprint library positioning mode, the user positioning accuracy is improved, and the accuracy of entering the building in the frequent floor of the user can be intuitively depicted by introducing the concept of the frequent floor and the confidence coefficient of the user; the method of combining the installed address information and the usual ground can be used for considering the screened installed address of the user as the accurate address of the user residence, so that the result of the user going into the building on the usual ground is optimized, the usual ground going into the building of the user is realized, the method can be effectively applied to the optimization and the accurate marketing of the internal operation and maintenance, and the method is worth being popularized and used in the scenes of external data rendering, industrial application support and the like.
While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (7)
1. A method for realizing frequent entrance of a user into a building based on a plurality of data sources, comprising the following steps:
s1: building user identification in residential area
Identifying building structures around the user frequent land, and calculating the distance from the user frequent land to each building structure within a set distance range;
s2: master-slave card user information judgment
According to different user numbers corresponding to the same customer id and according to the ordering of the number account opening dates, the number with the earliest account opening time is taken out to be the main card number, and the rest is the auxiliary card number; then, whether the distance from the frequent ground of the auxiliary card number to the frequent ground of the main card number is within a preset range is calculated, and if so, the auxiliary card number and the main card number are judged to be in the same building;
s3: building name and installation address matching
For a user who identifies a building and has an installed address, adopting an analysis mode of combining cosine similarity with the maximum public substring matching rate to analyze and match the building and the installed address, and taking out the building with the highest matching rate as a normally-living building of the user;
s4: confidence judgment of building in range of distance from living place
For a user who identifies building buildings but does not have an installed address, adopting the building with the highest confidence in the surrounding area of the common ground as the common ground building of the user;
s5: directly adopting the user's normally-located position
For users who have no building information in the usual ground, directly taking the longitude and latitude information of the usual ground as the usual ground building of the user;
s6: building update of frequent building by sub-card user
And regarding the correspondence of the identified primary and secondary card numbers, the users with the primary and secondary card numbers can be regarded as being in the same building, and the information of the frequently-lived building of the identified secondary card number users is updated to be consistent with the primary card number.
2. The method for realizing frequent floor access of users based on multiple data sources according to claim 1, wherein: in step S1, the distance range is set to be within 200m from the user' S usual ground.
3. The method for realizing frequent floor access of users based on multiple data sources according to claim 1, wherein: in the step S3, the building and the installed address are both chinese character strings.
4. A method for enabling users to enter a building on a constant floor basis based on a plurality of data sources as claimed in claim 3, wherein: in the step S4, the confidence is the number of days per total number of days of the sampling points within 50 meters from the building in daily living places.
5. The method for realizing frequent floor access of the user based on the plurality of data sources according to claim 4, wherein: in the step S4, when the cosine similarity is used for comparing the character strings, each term is assigned to a different dimension, one dimension is represented by a vector, and the value in each dimension corresponds to the frequency of occurrence of the term in the document.
6. The method for realizing frequent floor access of the user based on the plurality of data sources according to claim 5, wherein: in the step S4, when the similarity of the two character string texts is compared by adopting the maximum common sub-character string matching rate, matching the character string to be compared with the character string to be compared, and if successful, recording the successful matching length; if not, the length is reduced by 1, and the matching is continued; and all the successfully matched substrings are accumulated and divided by the matched substrings, the duty ratio is calculated, and the larger the duty ratio is, the more similar the two character strings are.
7. A system for implementing a user to enter a building frequently based on a plurality of data sources, wherein the method of any one of claims 1 to 6 is used to implement the identification of the user to enter the building frequently, comprising:
the building identification module is used for identifying building buildings around the user frequent land and calculating the distance from the user frequent land to each building in a set distance range;
the main and auxiliary card judging module is used for sorting according to different user numbers corresponding to the same customer id and according to the number account opening date, taking out the number with the earliest account opening time as the main card number and the rest as the auxiliary card number; then, calculating whether the distance from the frequent ground of the auxiliary card number to the frequent ground of the main card number is within a certain range, if so, judging that the auxiliary card number and the main card number are in the same building;
the matching module is used for analyzing and matching the building and the installed address by adopting an analysis mode of combining cosine similarity and the maximum public sub-string matching rate for a user who recognizes the building and the installed address, and taking out the building with the highest matching rate as a resident building of the user;
the confidence judging module is used for adopting the building with the highest confidence in the surrounding area of the usual ground as the usual ground building of the user for the user who identifies the building but does not have the installed address;
the module is directly adopted and is used for directly taking the longitude and latitude information of the normally-living land of the user as the normally-living land building of the user for the user who has no building information on the normally-living land;
the updating module is used for updating the information of the normally-living building of the identified auxiliary card number user to be consistent with the main card number, wherein the corresponding relation of the main card number and the auxiliary card number which are identified can be regarded as that the main card number user stays in the same building;
the central processing module is used for sending instructions to other modules to complete related actions;
the building identification module, the main and auxiliary card judgment module, the matching module, the confidence judgment module, the direct adoption module and the updating module are all electrically connected with the central processing module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110579321.1A CN114363953B (en) | 2021-05-26 | 2021-05-26 | Method and system for realizing frequent building entrance of user based on multiple data sources |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110579321.1A CN114363953B (en) | 2021-05-26 | 2021-05-26 | Method and system for realizing frequent building entrance of user based on multiple data sources |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114363953A CN114363953A (en) | 2022-04-15 |
CN114363953B true CN114363953B (en) | 2023-08-29 |
Family
ID=81095923
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110579321.1A Active CN114363953B (en) | 2021-05-26 | 2021-05-26 | Method and system for realizing frequent building entrance of user based on multiple data sources |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114363953B (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20060132134A (en) * | 2005-06-17 | 2006-12-21 | (주)팜미디어 | Method of matching building address and base stations for mobile radio network quality measurement |
GB201301440D0 (en) * | 2013-01-28 | 2013-03-13 | Microsoft Corp | Determining a location of a mobile user terminal |
CN107273833A (en) * | 2017-06-06 | 2017-10-20 | 深圳市至壹科技开发有限公司 | Method and its system for monitoring floating population |
CN109429330A (en) * | 2017-07-03 | 2019-03-05 | ***通信集团安徽有限公司 | Indoor orientation method, device, equipment and medium |
CN109857947A (en) * | 2019-01-28 | 2019-06-07 | 科大国创软件股份有限公司 | A kind of broadband installation site selecting method and system based on GIS map |
CN112188478A (en) * | 2020-09-29 | 2021-01-05 | 浙江新再灵科技股份有限公司 | Resident population data acquisition method based on big data analysis |
-
2021
- 2021-05-26 CN CN202110579321.1A patent/CN114363953B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20060132134A (en) * | 2005-06-17 | 2006-12-21 | (주)팜미디어 | Method of matching building address and base stations for mobile radio network quality measurement |
GB201301440D0 (en) * | 2013-01-28 | 2013-03-13 | Microsoft Corp | Determining a location of a mobile user terminal |
CN107273833A (en) * | 2017-06-06 | 2017-10-20 | 深圳市至壹科技开发有限公司 | Method and its system for monitoring floating population |
CN109429330A (en) * | 2017-07-03 | 2019-03-05 | ***通信集团安徽有限公司 | Indoor orientation method, device, equipment and medium |
CN109857947A (en) * | 2019-01-28 | 2019-06-07 | 科大国创软件股份有限公司 | A kind of broadband installation site selecting method and system based on GIS map |
CN112188478A (en) * | 2020-09-29 | 2021-01-05 | 浙江新再灵科技股份有限公司 | Resident population data acquisition method based on big data analysis |
Non-Patent Citations (1)
Title |
---|
电信行业依托大数据识别客户住址的方法研究;张竞贤;;通讯世界(第04期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN114363953A (en) | 2022-04-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108200644B (en) | Passive indoor positioning method based on network visible view | |
CN105282758A (en) | Self-adaptive dynamic construction method of WIFI indoor positioning system fingerprint database | |
CN110062410B (en) | Cell interruption detection positioning method based on self-adaptive resonance theory | |
CN106951828A (en) | A kind of recognition methods of the urban area functional attributes based on satellite image and network | |
CN113935881A (en) | Population structure analysis method and system based on big data and readable storage medium | |
CN110727752B (en) | Position fingerprint database processing method, device and computer readable storage medium | |
CN103442432A (en) | Fingerprint locating method and server | |
CN114363953B (en) | Method and system for realizing frequent building entrance of user based on multiple data sources | |
CN112867147B (en) | Positioning method and positioning device | |
CN113194474A (en) | Pseudo base station positioning method and device, electronic equipment and readable storage medium | |
CN110049447B (en) | Position information-based partnership analysis method | |
CN111639703A (en) | Method for calculating base station position based on minimum surrounding circle of discrete point set | |
CN115018014B (en) | Machine learning-assisted communication scene classification method based on multi-source information | |
CN110446161A (en) | User identity identification method, device, equipment and storage medium | |
CN114363824B (en) | Commute track depiction method and system based on MR (magnetic resonance) position and road GIS (geographic information System) information | |
CN109769216B (en) | Method and device for grouping users in complex environment based on mobile phone signals | |
CN109993556B (en) | User behavior analysis method and device, computing equipment and storage medium | |
US20210235226A1 (en) | Information processing device | |
CN110730432B (en) | Proximity user identification method, terminal and readable storage medium | |
CN116801374A (en) | Method, system, terminal equipment and medium for identifying abnormal interference source | |
CN113133049B (en) | Method, apparatus, device and medium for determining primary coverage cell | |
CN109639463A (en) | A kind of determination method of Internet of Things monitoring point neighbouring relations | |
CN114095947B (en) | Network coverage evaluation method and device, electronic equipment and storage medium | |
CN116304775B (en) | Intelligent detection method and system for mineral product components | |
CN114363405B (en) | Driver group identification method and system based on Internet surfing bill and MR user track |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |