CN112307075A - User relationship identification method and device - Google Patents
User relationship identification method and device Download PDFInfo
- Publication number
- CN112307075A CN112307075A CN201910707564.1A CN201910707564A CN112307075A CN 112307075 A CN112307075 A CN 112307075A CN 201910707564 A CN201910707564 A CN 201910707564A CN 112307075 A CN112307075 A CN 112307075A
- Authority
- CN
- China
- Prior art keywords
- user
- identified
- relationship
- communication
- data
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
Abstract
The embodiment of the invention discloses a user relationship identification method and device, and aims to solve the problems of low identification accuracy of the relationship of the curiosity, low application range, high cost and the like in the prior art. The method comprises the following steps: collecting communication data of a user pair to be identified in a first specified time period; determining communication relation data between the user pairs to be identified according to the communication data; and determining whether the user pairs to be identified have the relationship of the curiosity or not by utilizing a pre-established relationship identification model according to the communication relationship data. When the affiliation is identified, the communication data required by the affiliation identification can be collected based on the mobile communication system without additional hardware data, so that the data acquisition cost is low; in addition, the technical scheme determines whether the users to be identified have the relationship of the curiosity by using the pre-established relationship identification model without manually setting related judgment conditions and threshold values, so that the identification efficiency is improved, and the identification accuracy is improved.
Description
Technical Field
The present invention relates to the field of mobile communications technologies, and in particular, to a method and an apparatus for identifying a user relationship.
Background
The rapid development of mobile communication technology has led to the increasing popularity of mobile phones, and mobile communication has become one of the important ways for social interaction. For the mobile communication industry, the identification of the user relationship has very important significance, such as promotion of accurate marketing of family business packages. Abundant call data and MR (measurement report) data in the mobile communication system objectively reflect the social relationship characteristics of a large number of users. The relationship of living in this case is proposed by comparing relationship of blood, geographical, business, interest, etc., and is an interpersonal relationship with living together as a connecting link.
The existing user relationship identification mainly focuses on identification of family relationship, and identification of the household relationship is basically blank. While the relationship of a household is not equivalent to a family relationship, for example, a family relationship generally does not exist between users of a co-tenant. However, most households are selected to live together, so that the relationship between the household and the kindred still has a large overlap, and therefore, when the relationship between the household and the kindred is identified, a family relationship identification method needs to be referred to. Most of the existing family relation identification methods have the defects of low accuracy, low application range, high cost and the like, and the same defects can also occur if the methods are applied to identification of the residential relations.
Disclosure of Invention
The embodiment of the invention provides a user relationship identification method and device, and aims to solve the problems of low identification accuracy of the relationship of the curiosity, low application range, high cost and the like in the prior art.
To solve the above technical problem, the embodiment of the present invention is implemented as follows:
in a first aspect, an embodiment of the present invention provides a user relationship identification method, including:
collecting communication data of a user pair to be identified in a first specified time period; the communication data comprises call ticket data and/or measurement report data of each user in the user pair to be identified;
determining communication relation data between the user pairs to be identified according to the communication data; the communication relation data comprises call behavior characteristics and/or communication environment similarity between the user pairs to be identified;
determining whether the user pair to be identified has a relationship of curiosity or not by utilizing a pre-established relationship identification model according to the communication relationship data; the relationship identification model is obtained by training according to sample communication relationship data among a plurality of sample user pairs and information of whether each sample user pair has a relationship; the relationship of the social relations refers to the relationship of users living in the same geographic space.
In a second aspect, an embodiment of the present invention further provides a user relationship identifying apparatus, including:
the acquisition module is used for acquiring communication data of the user pair to be identified in a first specified time period; the communication data comprises call ticket data and/or measurement report data of each user in the user pair to be identified;
the first determining module is used for determining communication relation data between the user pairs to be identified according to the communication data; the communication relation data comprises call behavior characteristics and/or communication environment similarity between the user pairs to be identified;
the second determining module is used for determining whether the user pair to be identified has a social relationship or not by utilizing a pre-established relationship identification model according to the communication relationship data; the relationship identification model is obtained by training according to sample communication relationship data among a plurality of sample user pairs and information of whether each sample user pair has a relationship; the relationship of the social relations refers to the relationship of users living in the same geographic space.
In a third aspect, an embodiment of the present invention further provides a user relationship identifying device, including:
a memory storing computer program instructions;
a processor which, when executed by the processor, implements a user relationship identification method as in any one of the above.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes instructions, and when the instructions are executed on a computer, the computer is caused to execute the user relationship identification method according to any one of the above.
In the embodiment of the invention, when identifying the affiliation, the technical scheme can collect communication data (including call ticket data and/or measurement report data of each user in a user pair to be identified) required by the affiliation identification based on the mobile communication system, so that the data dimension required by the affiliation identification is rich, the data quality is reliable, and no additional hardware data is needed, therefore, the data acquisition cost is low; in addition, the conversation behavior characteristics and/or the communication environment similarity between the user pairs to be identified can be determined according to the collected communication data, and the conversation behavior characteristics and/or the communication environment similarity can reflect whether the users live in the same geographic space or not to a certain extent, so that the accuracy of identification of the relationship of the edges is realized; moreover, according to the technical scheme, whether the relation to be identified has the relationship of the relationship to be identified is determined by utilizing the pre-established relationship identification model according to the communication relationship data between the pair of the users to be identified, and the relationship of.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments described in the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a user relationship identification method in an embodiment of the present invention.
Fig. 2 is a diagram of the architecture of the collection device for call ticket data and measurement report data according to an embodiment of the present invention.
Fig. 3 is a diagram of a device architecture for determining communication relationship data in an embodiment of the invention.
FIG. 4 is a diagram of a determining device architecture for a relationship recognition model in an embodiment of the present invention.
Fig. 5 is a schematic flow chart of a user relationship identification method in another embodiment of the present invention.
Fig. 6 is a schematic structural diagram of a user relationship identifying apparatus according to an embodiment of the present invention.
Fig. 7 is a schematic structural diagram of a network device applied in one embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a user relationship identification method in an embodiment of the present invention. The method of fig. 1 may include:
s102, collecting communication data of the pair of users to be identified in a first specified time period.
The user pair to be identified comprises two users, and the representation forms of the user pair to be identified can include multiple forms, such as the form of splicing user names of the two users, the form of splicing communication numbers respectively corresponding to the two users, and the like. The communication data comprises call ticket data and/or measurement report data of each user in the user pair to be identified. The call ticket data can be collected by the server of each operator, and the measurement report data can be collected by the network equipment or the base station of each operator.
To ensure the accuracy of identification of the causal relationship, the first specified time period is preferably the last period of time, which may be, for example, the last week, the last month, the last year, etc.
And S104, determining communication relation data between the user pairs to be identified according to the communication data.
The communication relation data comprises call behavior characteristics and/or communication environment similarity between the user pairs to be identified.
And S106, determining whether the user pair to be identified has the affinity relationship by utilizing a pre-established relationship identification model according to the communication relationship data.
The relationship recognition model is obtained by training according to sample communication relationship data among a plurality of sample user pairs and information of whether each sample user pair has a relationship of curiosity; a relationship of a household edge refers to a relationship of a household living in the same geographic space.
In the embodiment of the invention, when identifying the affiliation, the technical scheme can collect communication data (including call ticket data and/or measurement report data of each user in a user pair to be identified) required by the affiliation identification based on the mobile communication system, so that the data dimension required by the affiliation identification is rich, the data quality is reliable, and no additional hardware data is needed, therefore, the data acquisition cost is low; in addition, the conversation behavior characteristics and/or the communication environment similarity between the user pairs to be identified can be determined according to the collected communication data, and the conversation behavior characteristics and/or the communication environment similarity can reflect whether the users live in the same geographic space or not to a certain extent, so that the accuracy of identification of the relationship of the edges is realized; moreover, according to the technical scheme, whether the relation to be identified has the relationship of the relationship to be identified is determined by utilizing the pre-established relationship identification model according to the communication relationship data between the pair of the users to be identified, and the relationship of.
The method of the embodiments of the present invention will be further described with reference to specific embodiments.
In the above embodiment, before performing S102, two users meeting the preset filtering condition may be selected from a large number of users to form a pair of users to be identified.
In one embodiment, in order to improve the recognition efficiency and save the computing resources, the preset screening condition may preferably be: at least N times of calls exist between the users corresponding to the screened communication number pair identification, and the intersection of the call contacts of the two users forming the communication number pair identification is not empty (namely the number of the intersection of the call contacts is not zero); in order to avoid the contingency, the recommended value of N in the above "N calls" is an integer greater than 2.
In the above embodiment, the call ticket data may be used to determine call behavior characteristics between the pair of users to be identified; the measurement report data may be used to determine communication environment similarity between pairs of users to be identified. According to the difference of the communication data and the determined communication relation data, the identification method of the social relationship between the user pairs to be identified is also different. The following describes details of different communication data and the method for identifying the causal relationship corresponding to the different communication relationship data.
In one embodiment, the communication data includes call ticket data. And determining the conversation behavior characteristics between the user pairs to be identified according to the acquired call ticket data, and further determining whether the user pairs to be identified have the affinity relationship or not by utilizing a pre-established relationship identification model according to the conversation behavior characteristics between the user pairs to be identified. The call ticket data can comprise the communication number of each user in the pair of users to be identified, the call time of the two parties, the call duration of the two parties, the calling party and the called party of the call and the like; the call behavior characteristics can comprise the communication number pair identification of the user pair to be identified, the total number of calls, the average call time length, the number of the same contact persons and the like.
Wherein, the total number of calls comprises the total number of calls without distinguishing a calling party and a called party; the communication number pair identification is formed by splicing communication numbers corresponding to two users in the user pair to be identified; the average call time length is equal to the total call time length of the two parties in the first appointed time period divided by the total call times; the number of the same contacts is the number of the same contacts in the call contacts of each user in the user pair to be identified.
In one embodiment, before determining the call behavior characteristics between the pair of users to be identified according to the collected call ticket data, the method further includes: deleting abnormal data in the call ticket data; and/or deleting the designated characters before the communication number; the abnormal data may include non-subscriber numbers, illegal numbers, etc.
Wherein, the non-user number can be an alarm telephone, an enterprise service number and the like; an illegal number may be a number displayed as "unknown number"; the designated characters before the communication number may be country codes (e.g. 86 for china and 31 for the netherlands), area codes, other prefixes (e.g. 12593/17951 for enjoying long distance benefits), etc. for distinguishing different countries.
In the embodiment, by deleting the abnormal data in the ticket data and/or deleting the specified character before the communication number, the irregular communication number and the abnormal data in the ticket data can be reduced, so that only the effective data which is beneficial to identifying the relationship between the two parties is reserved, the calculation of the ineffective data is effectively reduced, and the quality of the communication data is improved.
In one embodiment, when determining the call behavior characteristics between the pair of users to be identified according to the collected call ticket data, the following method can be adopted:
the communication numbers of all users are spliced together according to a preset splicing mode to obtain the communication number pair identification of the user pair to be identified.
The preset splicing mode can be any one of the following modes: sequentially splicing the communication numbers of the users according to the sequence of the names of the users; splicing the communication numbers of the users according to the numerical order of the communication numbers; and so on.
Secondly, counting the total number of calls according to the call records of the call ticket data; the statistical method is that the total call times of the calling party and the called party are not distinguished in the call records.
And thirdly, dividing the total call time length of the user pair to be identified in the first appointed time period by the total call times to obtain the average call time length between the user pair to be identified.
Fourthly, respectively determining the communication contact persons of each user; and carrying out intersection operation on the communication contacts of the users to obtain the number of the same contacts between the pair of users to be identified.
In the embodiment, the communication number pair identification is spliced in a preset mode, so that the communication number pair identification with calculation resources consumed among strangers can be effectively avoided, and the identification efficiency is improved; the total number of times of calls is counted through the call records, so that the average time length of the call times is determined, the call condition between the user pairs to be identified can be objectively reflected, the communication intersection between the user pairs to be identified can be visually seen through the number of the same contacts, and whether the user pairs to be identified have the affiliation relationship or not is reflected.
In one embodiment, the communication data comprises measurement report data. And determining the communication environment similarity between the user pairs to be identified according to the acquired measurement report data, further determining whether the user pairs to be identified have the affiliation relationship or not by utilizing a pre-established relationship identification model according to the communication environment similarity between the user pairs to be identified.
The measurement report data may include a communication number of each user in the to-be-identified user pair, connection time with the serving cell, a cell identification code of the connected serving cell, signal reception power of the serving cell, signal reception quality of the serving cell, signal reception power of a neighboring cell of the serving cell, signal reception quality of the neighboring cell, and the like.
The communication environment similarity may include the same rate of the to-be-identified user to the connected cell identification code, the total time of the to-be-identified user to the connected same cell, the signal receiving power similarity of the to-be-identified user to the connected serving cell, the signal receiving quality similarity of the to-be-identified user to the connected serving cell, the neighbor cell similarity corresponding to the to-be-identified user, the neighbor cell signal receiving power similarity corresponding to the to-be-identified user, the neighbor cell signal receiving quality similarity corresponding to the to-be-identified user, and the like within a second designated time period.
The second designated time period may be a time point set, a time period set, or the like; the second specified time period is a time period of a smaller segment bit within the first specified time period. For example, the second specified time period is the following set of time points: 0 hours per week, 0 hours per month, 0 hours per year, etc.; the second specified time period is the following set of time periods: 0-5 hours per week, 0-5 hours per month, 0-5 hours per year, etc.; if the first specified time period is the last month, the second specified time period may be the 0 th month, the 0 th-5 th month, etc.
In this embodiment, the measurement report data reflects the signal reception power and the signal reception quality of the serving cell and the neighboring cell connected to the user, and can objectively reflect the communication environment in which the user is located, so that the data dimension is rich and the data quality is reliable, and thus a rich and accurate data basis is provided for identifying the affiliation.
In one embodiment, when determining the similarity of the communication environments between the pair of users to be identified according to the collected measurement report data, the following method can be adopted:
determining the same times of the user to be identified to the connected cell identification code in a second specified time period; and dividing the same times of the cell identification codes by the maximum total connection duration of the to-be-identified user pairs in the first specified time period to obtain the same rate of the to-be-identified user pairs in the connected cell identification codes.
Wherein, the maximum total connection duration is: two users in the user pair to be identified are connected with the maximum value in the cell days within a first specified time period; for example, the pair of users to be identified includes user a and user B, the first specified time period is the last month, and the second specified time period is 0 a.m.. Assuming that the same number of times of cell ids connected by the user a and the user B is 16 in 0 early morning of a month, the user a connects to the cell for 25 days in one month, and the user B connects to the cell for 20 days in one month, then the same rate of cell ids connected by the user a and the user B is 16 divided by 25 and is equal to 0.64.
If the second appointed time period is the time point set, dividing the same times of the cell identification codes by the maximum total connection time length of the user pairs to be identified in the first appointed time period to obtain the same rate of the cell identification codes connected by the user pairs to be identified; if the second appointed time period is a time period set, dividing the same times of the cell identification codes by the number of the whole time points in the time period, and then dividing the maximum total connection time length of the user pair to be identified in the first appointed time period to obtain the same rate of the cell identification codes connected by the user pair to be identified.
Determining the same total times of the cell identification codes connected by the users to be identified in the second appointed time period to obtain the total time of the same cell connected by the users to be identified.
And the second appointed time period is a time period set, and the total times of the same identification code of the cell connected by the user to be identified are equal to the total time of the same cell connected by the user to be identified.
Judging whether the service cells connected by the user to be identified are the same in a second appointed time period; if not, determining that the signal receiving power similarity of the user to be identified to the connected service cell is zero; if so, determining the signal receiving power similarity of the user to be identified to the connected serving cell according to a first difference value between the signal receiving powers of the user to be identified to the connected serving cell; wherein the signal received power similarity is inversely related to the first difference.
For example, the pair of users to be identified includes user a and user B, and the second specified time period is 0 a.m. on the first day. Suppose that the signal received power of the serving cell connected by user a at 0 am on the first day is PaThe signal receiving power of the serving cell connected to user B at 0 am of the first day is PbThen, the signal received power similarity of the serving cells connected by the first day in 0 am of the user a and the user B can be expressed as:
by using the above example, assuming that the first specified time period is 0 hour-5 hours in the early morning of the month, according to the above steps, the signal received power similarity of the serving cell connected to the user a and the user B at 0 hour-5 hours in the early morning of each day in one month can be calculated, and the obtained results are summed up, so that the signal received power similarity of the user to be identified to the connected serving cell at 0 hour-5 hours in the early morning of the month can be calculated.
In addition, the following method can be adopted to determine the similarity of the received power of the adjacent cell signal corresponding to the user to be identified in the first specified time period:
firstly, judging whether a user pair to be identified has the same adjacent region in a second specified time period; it should be noted that the neighbor cell signal received power similarity is calculated only for the signal received powers of the same neighbor cells.
Secondly, determining the signal receiving power similarity of the user to be identified to one or more adjacent regions corresponding to the user to be identified according to a first difference value between the signal receiving power of the user to be identified to the one or more adjacent regions corresponding to the user to be identified; wherein the signal received power similarity is inversely related to the first difference.
And thirdly, summing the signal receiving power similarities of the user to be identified to the corresponding one or more adjacent regions to obtain the signal receiving power similarity of the user to be identified to the corresponding adjacent regions in a second designated time period.
And finally, according to the steps, calculating the received power similarity of the adjacent cell signals of each time point in the first designated time period, and summing to obtain the received power similarity of the adjacent cell signals corresponding to the user to be identified in the first designated time period.
Judging whether the service cells connected by the user to be identified are the same in a second appointed time period; if not, determining that the signal receiving quality similarity of the user to be identified to the connected service cell is zero; if so, determining the signal receiving quality similarity of the user to be identified to the connected serving cell according to a second difference value between the signal receiving qualities of the user to be identified to the connected serving cell; wherein the signal reception quality similarity is inversely related to the second difference.
For example, the pair of users to be recognized includes user A and user B, secondThe second designated time period was 0 am the first day. Suppose that the signal reception quality of the serving cell connected by user a at 0 am on the first day is QaThe signal receiving quality of the serving cell connected to the user B at 0 am on the first day is QbThen, the similarity of the signal reception quality of the serving cells connected when the first day of the user a and the user B is 0 in the morning can be expressed as:
by using the above example, assuming that the first specified time period is 0 hour-5 hours in the early morning of the month, according to the above steps, the signal reception quality similarity of the serving cell connected to the user a and the user B at 0 hour-5 hours in the early morning of each day in one month can be calculated, and the obtained results are summed up, so that the signal reception quality similarity of the user to be identified to the connected serving cell at 0 hour-5 hours in the early morning of the month can be calculated.
In addition, the following method can be adopted to determine the similarity of the receiving quality of the signals of the adjacent regions corresponding to the user to be identified in the first specified time period:
firstly, judging whether a user pair to be identified has the same adjacent region in a second specified time period; it should be noted that the neighbor cell signal reception quality similarity is calculated only for the signal reception qualities of the same neighbor cells.
Secondly, determining the signal receiving quality similarity of the user to be identified to the corresponding one or more adjacent cells according to a second difference value between the signal receiving quality of the user to be identified to the corresponding one or more adjacent cells; wherein the signal reception quality similarity is inversely related to the second difference.
And thirdly, summing the signal receiving quality similarities of the user to be identified to one or more corresponding adjacent regions to obtain the signal receiving quality similarity of the user to be identified to the corresponding adjacent regions in a second designated time period.
And finally, according to the steps, calculating the receiving quality similarity of the adjacent cell signals of each time point in the first appointed time period, and summing to obtain the receiving quality similarity of the adjacent cell signals corresponding to the user to be identified in the first appointed time period.
Executing a union set operation on adjacent cells respectively corresponding to each user in the user pair to be identified to obtain an adjacent cell set of the user pair to be identified; determining the number of the same adjacent regions of the user pair to be identified; determining the similarity of the adjacent regions corresponding to the user to be identified according to the ratio of the same number of the adjacent regions to the adjacent region set; and the neighbor similarity is positively correlated with the number of the same neighbors.
The neighbor cell corresponding to each user refers to the neighbor cell of the serving cell to which each user is connected. For example, the number of the same neighbor cells corresponding to the user to be identified at n can be MnIndicating that L can be used for the neighbor cell set corresponding to the user to be identified in nnRepresents; wherein n is a time point. The similarity S of the neighbor cell corresponding to the user pair to be identified in nnThe calculation method of (c) can be expressed as:
for another example, the pair of users to be identified includes user a and user B, and the second specified time period is 0 a.m. on the first day. According to the steps, the number of the corresponding same adjacent regions of the user A and the user B in 0 morning of the first day is M0The neighbor set corresponding to the user A and the user B in 0 morning of the first day is L0The similarity S of the adjacent regions corresponding to the user A and the user B0Comprises the following steps:
by adopting the above example, assuming that the first specified time period is 0 hour-5 hours in the morning of the month, according to the above steps, the similarity of the adjacent regions corresponding to the user a and the user B each day at 0 hour-5 hours in the morning of the month can be calculated, and the obtained results are summed up, so that the similarity of the adjacent regions corresponding to the user a and the user B at 0 hour-5 hours in the morning of the month can be calculated.
In the above embodiment, fig. 2 is an architecture diagram of a device for acquiring call ticket data and measurement report data. The core network equipment is used for collecting call ticket data, the base station controller/wireless network controller and the evolution node B (such as a base station) are used for collecting measurement report data, and the collected communication data is stored in the data storage server. Fig. 3 is a diagram of a device architecture for determining communication relationship data. The data is communication data stored in the data storage server in fig. 2, and the calculated communication relationship data is stored in the communication relationship data storage server.
In one embodiment, the relationship recognition model may be trained as follows:
firstly, collecting sample communication relation data among a plurality of sample user pairs; wherein, each sample user pair is marked with information whether having a relationship of kindred in advance.
And secondly, learning based on sample communication relationship data among a plurality of sample user pairs and information whether each sample user pair has a relationship of curiosity to obtain a relationship identification model.
The supervised machine learning algorithm can be used for learning sample data, such as CART decision tree, the algorithm avoids the requirement on data distribution, and has no requirement on the independence of features. The algorithm uses the Gini index as a criterion of attribute decision splitting, and finds out the logical correspondence or rule between the values of the input variable and the output variable in the data, thereby realizing the prediction of the new data output variable.
In this embodiment, fig. 4 is a diagram of a determined device architecture of the relationship recognition model. The sample communication relation data among the plurality of sample user pairs can form a training data set, the training data set is imported into the machine learning model, and the relation recognition model can be output through learning.
Fig. 5 is a schematic flow chart of a user relationship identification method in another embodiment of the present invention. In this embodiment, it is assumed that the first specified time period is the last month, and the second specified time period is a rest period within the last month, that is, 0 hour-5 hours in the early morning of the last month (hereinafter, referred to as 0 hour-5 hours in the early morning of the month or a month rest period), and the pair of users to be identified includes user a and user B. In this embodiment, both the communication data and the communication relation data can be expressed in the form of a data wide table. The method of fig. 5 may include:
s501, collecting the ticket data and the measurement report data of the user A and the user B in the last month.
The data width table of the measurement report data is shown in table one.
Watch 1
| Name of field | Description of field |
| msisdn | Mobile phone number |
| cellid | Cell identification code |
| starttime | Time of day |
| servingrsrp | Signal received power of serving cell |
| servingrsrq | Signal reception quality of serving cell |
| neighbor1pci | PCI of first neighbor cell |
| neighbor1rsrp | First adjacent cell signal received power |
| neighbor1rsrq | First neighbor cell signal reception quality |
| neighbor2pci | PCI of second neighbor cell |
| neighbor2rsrp | Second neighbor cell signal received power |
| neighbor2rsrq | Second neighbor cell signal reception quality |
| neighborNpci | PCI of Nth neighbor cell |
| neighborNrsrp | Signal receiving power of Nth adjacent cell |
| neighborNrsrq | Signal reception quality of Nth neighbor cell |
And S502, deleting abnormal data in the call ticket data and appointed characters before the communication number.
The abnormal data may include non-subscriber numbers, illegal numbers, etc. The non-user number can be an alarm telephone, an enterprise service number and the like; an illegal number may be a number displayed as "unknown number"; the designated characters before the communication number may be country codes (e.g. 86 for china and 31 for the netherlands), area codes, other prefixes (e.g. 12593/17951 for enjoying long distance benefits), etc. for distinguishing different countries.
For example, the abnormal data may be numbers such as 110, 120, etc., and the characters of the designated class before the communication number may be 86, 010, 17951, etc.
And S503, determining the conversation behavior characteristics and the communication environment similarity between the user A and the user B according to the ticket data and the measurement report data.
Specifically, the calculation method for determining the call behavior characteristics and the communication environment similarity between the user a and the user B is described in the above embodiments, and is not described herein again.
It is assumed that the cell identification codes of the serving cells to which the user a and the user B are connected during the monthly rest period and the signal reception power of each serving cell are shown in table two.
Watch two
| Rest period | User' s | Cell identification code | Signal received power (dB) |
| 0 | A | Cell1 | -88 |
| 0 | B | Cell2 | -85 |
| 1 | A | Cell3 | -89 |
| 1 | B | Cell3 | -67 |
| 2 | A | Cell3 | -87 |
| 2 | B | Cell3 | -86 |
| 3 | A | Cell3 | -85 |
| 3 | B | Cell3 | -87 |
| 4 | A | Cell3 | -90 |
| 4 | B | Cell3 | -85 |
| 5 | A | Cell3 | -88 |
| 5 | B | Without service | - |
Then, according to the calculation method in the above embodiment, it is possible to calculate the signal reception power similarity of the serving cell connected between the user a and the user B at the month rest period of 0 am + the signal reception power similarity of the serving cell connected at 1 am + the signal reception power similarity of the serving cell connected at 2 am + the signal reception power similarity of the serving cell connected at 3 am + the signal reception power similarity of the serving cell connected at 4 am + the signal reception power similarity of the serving cell connected at 5 am ═ 0+1/(1+ | -89- (-67) |/max (| -89|, |) +1/(1+ | -87- (-86) |/max (| -87|, -86|) +1/(1+ | -85- (-87) |/max (| -85|, | -87|) +1/(1+ | -90- (-85) |/max (| -90|, | -85|) +0 ═ 0.8018+0.9886+0.9775+0.9474 ═ 3.7153.
For another example, suppose that the neighboring cell signal received powers corresponding to the user a and the user B in the monthly rest period are as shown in table three.
Watch III
According to the calculation method in the above embodiment, the similarity of the received power of the neighboring signals corresponding to the user a and the user B in the monthly rest period is calculated to be (0.9574+0.9314+0.95+0.9505) + (0.9882+0.9884+1+1+ 0.9895+0.9896) + (0.9684+1+0.9775+0.9778+0.9778+0.9888+0.9406) + (0.956+0.967+0.967+0.9574+0.9681+0.949+0.9592+0.9417) + (0.9667+0.9468+0.9216+0.9314+0.9314+0.932) +0. 30.8712.
And S504, determining whether the user A and the user B have a social relationship or not by utilizing a pre-established relationship identification model according to the conversation behavior characteristics and the communication environment similarity.
In this embodiment, the call behavior characteristics include the following: the communication number pair identification, the total number of calls, the average call time length and the number of the same contact persons; the communication environment similarity includes the following: cell identity code identity rate connected at 0 am of the month, cell identity code identity rate connected at 1 am of the month, cell identity code identity rate connected at 2 am of the month, cell identity code identity rate connected at 3 am of the month, cell identity code identity rate connected at 4 am of the month, cell identity code identity rate connected at 5 am of the month, total duration of the same cells connected at a month rest period, cell identity code identity rate connected at a month rest period, signal reception power similarity of serving cells connected at a month rest period, signal reception quality similarity of serving cells connected at a month rest period, neighbor similarity corresponding at 0 am of the month, neighbor similarity corresponding at 1 am of the month, neighbor similarity corresponding at 2 am of the month, neighbor similarity corresponding at 3 am of the month, neighbor similarity corresponding at 4 am of the month, neighbor similarity corresponding at 5 am, neighbor similarity corresponding to the month, The method comprises the following steps of obtaining the similarity of the adjacent regions corresponding to the month rest period, the similarity of the signal receiving power of the adjacent regions corresponding to the month rest period and the similarity of the signal receiving quality of the adjacent regions corresponding to the month rest period.
In the embodiment, the measurement report data can objectively reflect the communication environment where the user is located in real time, and the data can calculate whether the communication environments where the two users are located in real time are similar, so that whether the two users are located in the same environmental scene can be judged, particularly in a monthly rest period, which is important for judging whether the two users have an affiliation relationship, and the identification accuracy can be improved; by using the relationship identification model, the user relationship of the user can be automatically identified without manually setting related judgment conditions and thresholds, so that the identification efficiency and accuracy are improved.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Fig. 6 is a schematic structural diagram of a user relationship identifying apparatus according to an embodiment of the present invention. Referring to fig. 6, a user relationship recognition apparatus 600 may include:
the acquisition module 610 is used for acquiring communication data of a user pair to be identified in a first specified time period; the communication data comprises call ticket data and/or measurement report data of each user in the user pair to be identified;
the first determining module 620 determines communication relationship data between the pair of users to be identified according to the communication data; the communication relation data comprises call behavior characteristics and/or communication environment similarity between the user pairs to be identified;
the second determining module 630, according to the communication relationship data, determining whether there is a relationship between the pair of users to be identified by using a pre-established relationship identification model; the relation recognition model is obtained by training according to the sample communication relation data among a plurality of sample user pairs and the information whether the sample user pairs have the affinity relation or not; a relationship of a household edge refers to a relationship of a household living in the same geographic space.
In one embodiment, the call ticket data comprises at least one of a communication number, two-party call time, two-party call duration and a call calling party and a call called party; the call behavior characteristics comprise at least one of communication number pair identification, total call times, average call time and the number of the same contact persons.
In one embodiment, the first determination module 620 includes at least one of:
the splicing unit splices the communication numbers of all the users together according to a preset splicing mode to obtain the communication number pair identification of the user pair to be identified;
the computing unit is used for dividing the total call time length of the user pairs to be identified in the first specified time period by the total call times to obtain the average call time length between the user pairs to be identified;
the determining unit is used for respectively determining the communication contact persons of all users; and carrying out intersection operation on the communication contacts of the users to obtain the number of the same contacts between the pair of users to be identified.
In one embodiment, the first determining module 620 further comprises:
a deleting unit, which deletes the abnormal data in the call ticket data; and/or deleting the designated characters before the communication number; wherein the abnormal data includes at least one of a non-subscriber number and an illegal number.
In one embodiment, the measurement report data includes at least one of a communication number, a connection time with a serving cell, a cell identification code of a connected serving cell, a signal reception power of a serving cell, a signal reception quality of a serving cell, a signal reception power of a neighbor cell of a serving cell, a signal reception quality of a neighbor cell;
the communication environment similarity comprises at least one of the same rate of the identification codes of the cells connected by the users to be identified, the total time length of the cells connected by the users to be identified, the signal receiving power similarity of the serving cells connected by the users to be identified, the signal receiving quality similarity of the serving cells connected by the users to be identified, the neighbor cell similarity corresponding to the users to be identified, the neighbor cell signal receiving power similarity corresponding to the users to be identified, and the neighbor cell signal receiving quality similarity corresponding to the users to be identified.
In one embodiment, the second determination module 630 includes at least one of:
the first determining and calculating unit is used for determining the same times of the to-be-identified users to the connected cell identification codes in a second specified time period; dividing the same times of the cell identification codes by the maximum total connection duration of the user pairs to be identified in the first specified time period to obtain the same rate of the cell identification codes connected by the user pairs to be identified;
the first judgment and calculation unit is used for judging whether the users to be identified are the same with the connected service cells in a second specified time period; if not, determining that the signal receiving power similarity of the user to be identified to the connected service cell is zero; if so, determining the signal receiving power similarity of the user to be identified to the connected serving cell according to a first difference value between the signal receiving powers of the user to be identified to the connected serving cell; wherein the signal received power similarity is inversely related to the first difference;
the second judgment and calculation unit is used for judging whether the users to be identified are the same with the connected service cells in a second specified time period; if not, determining that the signal receiving quality similarity of the user to be identified to the connected service cell is zero; if so, determining the signal receiving quality similarity of the user to be identified to the connected serving cell according to a second difference value between the signal receiving qualities of the user to be identified to the connected serving cell; wherein the signal reception quality similarity is inversely related to the second difference;
the second determining and calculating unit is used for executing the union set operation on the adjacent cells respectively corresponding to the users in the user pair to be identified to obtain an adjacent cell set of the user pair to be identified; determining the number of the same adjacent regions of the user pair to be identified; determining the similarity of the adjacent regions corresponding to the user to be identified according to the ratio of the same number of the adjacent regions to the adjacent region set; and the neighbor similarity is positively correlated with the number of the same neighbors.
In one embodiment, the second determination module 630 further comprises,
the acquisition unit is used for acquiring sample communication relation data among a plurality of sample user pairs; wherein, each sample user pair is marked with information whether having a relationship of curiosity in advance;
and the learning unit learns the sample communication relationship data among the plurality of sample user pairs and the information of whether the sample user pairs have the affiliation relationship to obtain the relationship identification model.
The network device provided by the embodiment of the present invention is capable of performing each process implemented by the user relationship identification method in the above method embodiments, and is not described here again to avoid repetition.
In the embodiment of the invention, when identifying the affiliation, the device can collect communication data (including call ticket data and/or measurement report data of each user in a user pair to be identified) required by the affiliation identification based on the mobile communication system, so that the data dimension required by the affiliation identification is rich, the data quality is reliable, and no additional hardware data is needed, therefore, the data acquisition cost is low; in addition, the conversation behavior characteristics and/or the communication environment similarity between the user pairs to be identified can be determined according to the collected communication data, and the conversation behavior characteristics and/or the communication environment similarity can reflect whether the users live in the same geographic space or not to a certain extent, so that the accuracy of identification of the relationship of the edges is realized; moreover, according to the technical scheme, whether the relation to be identified has the relationship of the relationship to be identified is determined by utilizing the pre-established relationship identification model according to the communication relationship data between the pair of the users to be identified, and the relationship of.
Referring to fig. 7, fig. 7 is a structural diagram of a network device applied in the embodiment of the present invention, which can implement details of a user relationship identification method executed by the network device in the above embodiment, and achieve the same effect. As shown in fig. 7, the network device 700 includes: a processor 701, a transceiver 702, a memory 703, a user interface 704 and a bus interface, wherein:
in this embodiment of the present invention, the network device 700 further includes: a computer program stored on the memory 703 and executable on the processor 701, the computer program when executed by the processor 701 performing the steps of:
collecting communication data of a user pair to be identified in a first specified time period; the communication data comprises call ticket data and/or measurement report data of each user in the user pair to be identified;
determining communication relation data between the user pairs to be identified according to the communication data; the communication relation data comprises call behavior characteristics and/or communication environment similarity between the user pairs to be identified;
determining whether the user pairs to be identified have a relationship of curiosity or not by utilizing a pre-established relationship identification model according to the communication relationship data; the relation recognition model is obtained by training according to the sample communication relation data among a plurality of sample user pairs and the information whether the sample user pairs have the affinity relation or not; a relationship of a household edge refers to a relationship of a household living in the same geographic space.
In fig. 7, the bus architecture may include any number of interconnected buses and bridges, with one or more processors, represented by processor 701, and various circuits, represented by memory 703, being linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface. The transceiver 702 may be a number of elements including a transmitter and a receiver that provide a means for communicating with various other apparatus over a transmission medium. The user interface 704 may also be an interface capable of interfacing with a desired device for different user devices, including but not limited to a keypad, display, speaker, microphone, joystick, etc.
The processor 701 is responsible for managing the bus architecture and general processing, and the memory 703 may store data used by the processor 701 in performing operations.
Optionally, the call ticket data includes at least one item of a communication number, two-party call time, two-party call duration and a call calling party and a call called party; the call behavior characteristics comprise at least one of communication number pair identification, total call times, average call time and the number of the same contact persons.
Optionally, the computer program may further implement at least one of the following steps when executed by the processor 701:
splicing the communication numbers of all users together according to a preset splicing mode to obtain communication number pair identifications of the user pairs to be identified;
dividing the total call time length of the user pairs to be identified in the first appointed time period by the total call times to obtain the average call time length between the user pairs to be identified;
respectively determining the communication contact persons of each user; and carrying out intersection operation on the communication contacts of the users to obtain the number of the same contacts between the pair of users to be identified.
Optionally, the computer program may further implement the following steps when executed by the processor 701:
deleting abnormal data in the call ticket data before determining the communication relation data between the user pairs to be identified; and/or deleting the designated characters before the communication number; wherein the abnormal data includes at least one of a non-subscriber number and an illegal number.
Optionally, the measurement report data includes at least one of a communication number, connection time with the serving cell, a cell identification code of the connected serving cell, signal reception power of the serving cell, signal reception quality of the serving cell, signal reception power of a neighboring cell of the serving cell, and signal reception quality of the neighboring cell;
the communication environment similarity comprises at least one of the same rate of the identification codes of the cells connected by the users to be identified, the total time length of the cells connected by the users to be identified, the signal receiving power similarity of the serving cells connected by the users to be identified, the signal receiving quality similarity of the serving cells connected by the users to be identified, the neighbor cell similarity corresponding to the users to be identified, the neighbor cell signal receiving power similarity corresponding to the users to be identified, and the neighbor cell signal receiving quality similarity corresponding to the users to be identified.
Optionally, the computer program may further implement at least one of the following steps when executed by the processor 701: :
determining the same times of the connected cell identification codes of the users to be identified in a second specified time period; dividing the same times of the cell identification codes by the maximum total connection duration of the user pairs to be identified in the first specified time period to obtain the same rate of the cell identification codes connected by the user pairs to be identified;
judging whether the users to be identified are the same with the connected service cells within a second specified time period; if not, determining that the signal receiving power similarity of the user to be identified to the connected service cell is zero; if so, determining the signal receiving power similarity of the user to be identified to the connected serving cell according to a first difference value between the signal receiving powers of the user to be identified to the connected serving cell; wherein the signal received power similarity is inversely related to the first difference;
judging whether the users to be identified are the same with the connected service cells within a second specified time period; if not, determining that the signal receiving quality similarity of the user to be identified to the connected service cell is zero; if so, determining the signal receiving quality similarity of the user to be identified to the connected serving cell according to a second difference value between the signal receiving qualities of the user to be identified to the connected serving cell; wherein the signal reception quality similarity is inversely related to the second difference;
executing union set taking operation on adjacent cells respectively corresponding to each user in the user pair to be identified to obtain an adjacent cell set of the user pair to be identified; determining the number of the same adjacent regions of the user pair to be identified; determining the similarity of the adjacent regions corresponding to the user to be identified according to the ratio of the same number of the adjacent regions to the adjacent region set; and the neighbor similarity is positively correlated with the number of the same neighbors.
Optionally, the computer program may further implement the following steps when executed by the processor 701:
training a relationship recognition model according to the following steps:
collecting sample communication relationship data between a plurality of sample user pairs; wherein, each sample user pair is marked with information whether having a relationship of curiosity in advance;
and learning based on the sample communication relationship data among the plurality of sample user pairs and the information whether the sample user pairs have the affiliation relationship or not to obtain a relationship identification model.
In the embodiment of the invention, when identifying the affiliation, the technical scheme can collect communication data (including call ticket data and/or measurement report data of each user in the pair of users to be identified) required by the affiliation identification based on the mobile communication system, so that the data dimension required by the affiliation identification is rich, the data quality is reliable, and no additional hardware data is needed, therefore, the data acquisition cost is low; in addition, the conversation behavior characteristics and/or the communication environment similarity between the user pairs to be identified can be determined according to the collected communication data, and the conversation behavior characteristics and/or the communication environment similarity can reflect whether the users live in the same geographic space or not to a certain extent, so that the accuracy of identification of the relationship of the edges is realized; moreover, according to the technical scheme, whether the relation to be identified has the relationship of the relationship to be identified is determined by utilizing the pre-established relationship identification model according to the communication relationship data between the pair of the users to be identified, and the relationship of.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the embodiment of the user relationship identification method, and can achieve the same technical effect, and in order to avoid repetition, details are not repeated here. The computer-readable storage medium may be a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (10)
1. A user relationship identification method is characterized by comprising the following steps:
collecting communication data of a user pair to be identified in a first specified time period; the communication data comprises call ticket data and/or measurement report data of each user in the user pair to be identified;
determining communication relation data between the user pairs to be identified according to the communication data; the communication relation data comprises call behavior characteristics and/or communication environment similarity between the user pairs to be identified;
determining whether the user pair to be identified has a relationship of curiosity or not by utilizing a pre-established relationship identification model according to the communication relationship data; the relationship identification model is obtained by training according to sample communication relationship data among a plurality of sample user pairs and information of whether each sample user pair has a relationship; the relationship of the social relations refers to the relationship of users living in the same geographic space.
2. The method of claim 1, wherein the call ticket data comprises at least one of a communication number, a two-party call time, and a call calling party and a called party; the call behavior characteristics comprise at least one of communication number pair identification, total call times, average call time length and the number of the same contact persons.
3. The method according to claim 2, wherein the determining communication relationship data between the pair of users to be identified according to the communication data comprises at least one of:
splicing the communication numbers of the users together according to a preset splicing mode to obtain the communication number pair identification of the user pair to be identified;
dividing the total call duration of the to-be-identified user pair in the first specified time period by the total call times to obtain the average call duration between the to-be-identified user pairs;
respectively determining the communication contact persons of the users; and performing intersection operation on the communication contacts of the users to obtain the number of the same contacts between the user pairs to be identified.
4. The method according to claim 2, wherein before determining the communication relationship data between the pair of users to be identified according to the communication data, further comprising:
deleting abnormal data in the call ticket data; and/or deleting the appointed character before the communication number; wherein the abnormal data includes at least one of a non-user number and an illegal number.
5. The method of claim 1, wherein the measurement report data comprises at least one of a communication number, a connection time with a serving cell, a cell identification code of the connected serving cell, a signal reception power of the serving cell, a signal reception quality of the serving cell, a signal reception power of a neighboring cell of the serving cell, and a signal reception quality of the neighboring cell;
the communication environment similarity comprises at least one of the same rate of the cell identification codes connected by the to-be-identified users in a second designated time period, the total time length of the same cells connected by the to-be-identified users, the signal receiving power similarity of the serving cell connected by the to-be-identified users, the signal receiving quality similarity of the serving cell connected by the to-be-identified users, the neighbor cell similarity corresponding to the to-be-identified users, the neighbor cell signal receiving power similarity corresponding to the to-be-identified users, and the neighbor cell signal receiving quality similarity corresponding to the to-be-identified users.
6. The method according to claim 5, wherein the determining communication relationship data between the pair of users to be identified according to the communication data comprises at least one of:
determining the same times of the cell identification codes connected by the users to be identified in the second appointed time period; dividing the same times of the cell identification codes by the maximum total connection duration of the user pairs to be identified in the first specified time period to obtain the same rate of the cell identification codes connected by the user pairs to be identified;
judging whether the service cells connected by the user to be identified are the same in the second appointed time period; if not, determining that the signal receiving power similarity of the user to be identified to the connected service cell is zero; if so, determining the signal receiving power similarity of the user to be identified to the connected service cell according to a first difference value between the signal receiving powers of the user to be identified to the connected service cell; wherein the signal received power similarity is inversely related to the first difference;
judging whether the service cells connected by the user to be identified are the same in the second appointed time period; if not, determining that the signal receiving quality similarity of the user to be identified to the connected service cell is zero; if so, determining the signal receiving quality similarity of the user to be identified to the connected service cell according to a second difference value between the signal receiving qualities of the user to be identified to the connected service cell; wherein the signal reception quality similarity is inversely related to the second difference;
executing a union set operation on the adjacent cells respectively corresponding to each user in the user pair to be identified to obtain an adjacent cell set of the user pair to be identified; determining the number of the same adjacent regions of the user pair to be identified; determining the neighbor cell similarity corresponding to the user to be identified according to the ratio of the number of the same neighbor cells to the neighbor cell set; wherein the neighbor similarity is positively correlated with the number of the same neighbors.
7. The method of claim 1, wherein the relationship recognition model is trained by:
collecting sample communication relationship data between a plurality of sample user pairs; wherein each of the sample user pairs is pre-marked with information whether or not to have a relationship of involvement;
and learning based on the sample communication relationship data among the plurality of sample user pairs and the information whether the sample user pairs have the affiliation relationship or not to obtain the relationship identification model.
8. A user relationship recognition apparatus, comprising:
the acquisition module is used for acquiring communication data of the user pair to be identified in a first specified time period; the communication data comprises call ticket data and/or measurement report data of each user in the user pair to be identified;
the first determining module is used for determining communication relation data between the user pairs to be identified according to the communication data; the communication relation data comprises call behavior characteristics and/or communication environment similarity between the user pairs to be identified;
the second determining module is used for determining whether the user pair to be identified has a social relationship or not by utilizing a pre-established relationship identification model according to the communication relationship data; the relationship identification model is obtained by training according to sample communication relationship data among a plurality of sample user pairs and information of whether each sample user pair has a relationship; the relationship of the social relations refers to the relationship of users living in the same geographic space.
9. A user relationship recognition device, comprising:
a memory storing computer program instructions;
a processor which, when executed by the processor, implements the user relationship identification method of any of claims 1 to 7.
10. A computer-readable storage medium, comprising instructions which, when run on a computer, cause the computer to perform the user relationship identification method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910707564.1A CN112307075B (en) | 2019-08-01 | 2019-08-01 | User relationship identification method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910707564.1A CN112307075B (en) | 2019-08-01 | 2019-08-01 | User relationship identification method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112307075A true CN112307075A (en) | 2021-02-02 |
| CN112307075B CN112307075B (en) | 2023-09-19 |
Family
ID=74486241
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910707564.1A Active CN112307075B (en) | 2019-08-01 | 2019-08-01 | User relationship identification method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112307075B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113949582A (en) * | 2021-10-25 | 2022-01-18 | 绿盟科技集团股份有限公司 | Network asset identification method and device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102541886A (en) * | 2010-12-20 | 2012-07-04 | 郝敬涛 | System and method for identifying relationship among user group and users |
| WO2014209900A1 (en) * | 2013-06-23 | 2014-12-31 | Intel Corporation | Selective sharing of user information based on contextual relationship information, such as to crowd-source gifts of interest to a recipient |
| CN105142106A (en) * | 2015-07-29 | 2015-12-09 | 西南交通大学 | Traveler home-work location identification and trip chain depicting method based on mobile phone signaling data |
| CN107256231A (en) * | 2017-05-04 | 2017-10-17 | 腾讯科技（深圳）有限公司 | A kind of Team Member's identification equipment, method and system |
| US20170316599A1 (en) * | 2016-05-02 | 2017-11-02 | Tic Talking Holdings Inc. | Facilitation of Depiction of Geographic Relationships Via a User Interface |
| CN109829485A (en) * | 2019-01-08 | 2019-05-31 | 科大国创软件股份有限公司 | A kind of user relationship mining method and system based on mobile data |
| CN109963253A (en) * | 2017-12-25 | 2019-07-02 | 中国移动通信集团上海有限公司 | A kind of recognition methods in user's inhabitation geographical location and device |
-
2019
- 2019-08-01 CN CN201910707564.1A patent/CN112307075B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102541886A (en) * | 2010-12-20 | 2012-07-04 | 郝敬涛 | System and method for identifying relationship among user group and users |
| WO2014209900A1 (en) * | 2013-06-23 | 2014-12-31 | Intel Corporation | Selective sharing of user information based on contextual relationship information, such as to crowd-source gifts of interest to a recipient |
| CN105142106A (en) * | 2015-07-29 | 2015-12-09 | 西南交通大学 | Traveler home-work location identification and trip chain depicting method based on mobile phone signaling data |
| US20170316599A1 (en) * | 2016-05-02 | 2017-11-02 | Tic Talking Holdings Inc. | Facilitation of Depiction of Geographic Relationships Via a User Interface |
| CN107256231A (en) * | 2017-05-04 | 2017-10-17 | 腾讯科技（深圳）有限公司 | A kind of Team Member's identification equipment, method and system |
| CN109963253A (en) * | 2017-12-25 | 2019-07-02 | 中国移动通信集团上海有限公司 | A kind of recognition methods in user's inhabitation geographical location and device |
| CN109829485A (en) * | 2019-01-08 | 2019-05-31 | 科大国创软件股份有限公司 | A kind of user relationship mining method and system based on mobile data |
Non-Patent Citations (1)
| Title |
|---|
| 张继东 等: ""基于地理社交数据的移动社交网络用户社会化关系发现研究"", 《情报理论与实践》, vol. 40, no. 10, pages 69 - 73 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113949582A (en) * | 2021-10-25 | 2022-01-18 | 绿盟科技集团股份有限公司 | Network asset identification method and device, electronic equipment and storage medium |
| CN113949582B (en) * | 2021-10-25 | 2023-05-30 | 绿盟科技集团股份有限公司 | Network asset identification method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112307075B (en) | 2023-09-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110337059B (en) | Analysis algorithm, server and network system for family relationship of user | |
| CN102083010B (en) | Method and equipment for screening user information | |
| CN107613084B (en) | Method, device and system for automatically grouping contacts in address list | |
| CN102215504A (en) | Method and system for identifying class of newly network-accessed user | |
| CN111148018B (en) | Method and device for identifying and positioning regional value based on communication data | |
| CN113412607B (en) | Content pushing method and device, mobile terminal and storage medium | |
| CN111652661B (en) | Mobile phone client user loss early warning processing method | |
| CN113206909A (en) | Crank call interception method and device | |
| CN112307075B (en) | User relationship identification method and device | |
| CN109451334A (en) | User, which draws a portrait, generates processing method, device and electronic equipment | |
| CN111368858B (en) | User satisfaction evaluation method and device | |
| CN102752462B (en) | Method and system for recommending telecommunications service | |
| CN114970495A (en) | Name disambiguation method and device, electronic equipment and storage medium | |
| CN110166635B (en) | Suspicious terminal identification method and suspicious terminal identification system | |
| CN113378073B (en) | User relationship identification method and device | |
| CN112035678A (en) | Bank business knowledge graph construction method and device | |
| CN113205129B (en) | Cheating group identification method and device, electronic equipment and storage medium | |
| CN112488743A (en) | Satisfaction degree prediction method, network equipment and storage medium | |
| CN114866433B (en) | User service perception evaluation method, device, equipment and computer storage medium | |
| CN111385108A (en) | Service processing method, device, equipment and medium | |
| CN112752252B (en) | Cell home location identification method and device | |
| CN115529581A (en) | Off-network user identification method and device | |
| CN110856159B (en) | Method, device and storage medium for determining family circle members | |
| CN116744336A (en) | Cross-operator neighbor cell miss-distribution detection method and device, electronic equipment and medium | |
| CN117793252A (en) | Communication method, device and readable storage medium |
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 |