CN110677269B - Method and device for determining communication user relationship and computer readable storage medium - Google Patents
Method and device for determining communication user relationship and computer readable storage medium Download PDFInfo
- Publication number
- CN110677269B CN110677269B CN201810711771.XA CN201810711771A CN110677269B CN 110677269 B CN110677269 B CN 110677269B CN 201810711771 A CN201810711771 A CN 201810711771A CN 110677269 B CN110677269 B CN 110677269B
- Authority
- CN
- China
- Prior art keywords
- user
- information
- communication
- users
- user group
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L41/5061—Network service management, e.g. ensuring proper service fulfilment according to agreements characterised by the interaction between service providers and their network customers, e.g. customer relationship management
- H04L41/5064—Customer relationship management
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Telephonic Communication Services (AREA)
Abstract
The disclosure relates to a method and a device for determining a communication user relationship and a computer readable storage medium, and relates to the technical field of big data. The method of the present disclosure comprises: determining the closeness measurement information among users in a user group according to the communication record information, wherein the user group comprises any user pair corresponding to the communication record information; classifying the user groups according to the closeness measurement information corresponding to the user groups; and further determining the relationship between the users according to the classification result. The method adopts a big data processing method, can analyze the relation of two users communicating randomly in the whole network, and realizes parallel analysis of the relation of the users in the whole network by classifying a large number of user groups and then determining the user relation, so that repeated and cyclic operation can not occur, and the analysis efficiency is improved.
Description
Technical Field
The present disclosure relates to the field of big data technologies, and in particular, to a method and an apparatus for determining a communication user relationship, and a computer-readable storage medium.
Background
The mining of the communication user relationship has good application value, and operators can provide richer and high-quality services for users by using the relationship between communication users, such as family packages, harassing call shielding and the like.
At present, the communication relation analysis technology mainly completes analysis through a target individual address list and a communication ticket. Namely, a communication relation analysis model of a single person is established for a specified person.
Disclosure of Invention
The inventor finds that: at present, aiming at personal communication relation analysis, relation analysis of massive users in the whole network is difficult to realize, if the relation of the users in the whole network is decomposed into individual analysis relations one by one, a large amount of repeated and cyclic operation is generated, huge consumption is extremely difficult to realize, and data storage and updating are very difficult.
One technical problem to be solved by the present disclosure is: how to efficiently realize the user relationship analysis of the whole network scale.
According to some embodiments of the present disclosure, there is provided a method for determining a communication user relationship, including: determining the closeness measurement information among the users in the user group according to the communication record information, wherein the user group comprises any two users corresponding to the communication record information; classifying the user groups according to the closeness measurement information corresponding to the user groups; and determining the relation among the users in the user group according to the classification result.
In some embodiments, the affinity measure information between users includes: the intimacy degree of one-time communication between users; determining the affinity measure information between the users in the user group according to the communication record information comprises: and determining the density of the current communication between the users according to the communication record information values in the one-time communication between the users and the weights corresponding to the communication record information values.
In some embodiments, the affinity measure information further includes: historical cumulative osculating degree; the historical accumulated density of the first user to the second user in the user group is determined according to the density of each communication between the first user and the second user and the current communication direction weight.
In some embodiments, the affinity measure information further includes: a user dependency; the user dependence of a first user on a second user in the user group is determined by comparing the sum of historical cumulative affinities of the first user on all users according to the historical cumulative affinity of the first user on the second user.
In some embodiments, classifying the user groups according to the closeness measurement information corresponding to all the user groups includes: inputting the closeness measurement information corresponding to the user group into a pre-trained machine learning model, and determining a core relationship user group and a non-core relationship user group; and classifying the core relation user group.
In some embodiments, classifying the user groups according to the closeness measure information corresponding to the user groups includes: and inputting the closeness measurement information corresponding to the user group into a pre-trained classification model to classify the user group.
In some embodiments, communicating the record information includes: at least one item of communication time interval information, user position information, call duration information and ringing duration information among users; the method further comprises the following steps: collecting communication information of a user, wherein the communication information comprises: at least one item of information in signaling record information, short message record information and call ticket information; and extracting at least one of the user number, the starting time, the response time, the ending time, the roaming position, the source office direction, the acquisition position and the protocol type from the communication information, and generating communication record information.
In some embodiments, classifying the user group further comprises: classifying the non-core relation user group; the method further comprises the following steps: and forming a classified user relation network by matching users in the core relation user group and the non-core relation user group with the same classification.
According to other embodiments of the present disclosure, there is provided a communication user relationship determining apparatus, including: the system comprises an affinity information determining module, a communication recording information determining module and an affinity measuring module, wherein the affinity information determining module is used for determining affinity measuring information among users in a user group according to the communication recording information, and the user group comprises two users corresponding to the communication recording information; the classification module is used for classifying the user groups according to the closeness measurement information corresponding to the user groups; and the relationship determining module is used for determining the relationship among the users in the user group according to the classification result.
In some embodiments, the affinity measure information between users includes: the intimacy degree of one-time communication between users; and the density information determining module is used for determining the density of the current communication between the users according to the communication record information values in the one-time communication between the users and the weights corresponding to the communication record information values.
In some embodiments, the affinity measure information further includes: historical cumulative osculating degree; the historical accumulated density of the first user to the second user in the user group is determined according to the density of each communication between the first user and the second user and the current communication direction weight.
In some embodiments, the affinity measure information further includes: a user dependency; the user dependence of a first user on a second user in the user group is determined by comparing the sum of historical cumulative affinities of the first user on all users according to the historical cumulative affinity of the first user on the second user.
In some embodiments, the classification module is configured to input affinity measurement information corresponding to the user group into a pre-trained machine learning model, and determine a core relationship user group and a non-core relationship user group; and classifying the core relation user group.
In some embodiments, the classification module is configured to input the closeness measurement information corresponding to the user group into a pre-trained classification or clustering model to classify the user group.
In some embodiments, communicating the record information includes: at least one item of communication time interval information, user position information, call duration information and ringing duration information among users; the device also includes: the data acquisition processing module is used for acquiring user communication information, and the communication information comprises: at least one item of information in signaling record information, short message record information and call ticket information; and extracting at least one of the user number, the starting time, the response time, the ending time, the roaming position, the source office direction, the acquisition position and the protocol type from the communication information, and generating communication record information.
In some embodiments, the classification module is further configured to classify the group of non-core relational users; the device also includes: and the relation network determining module is used for forming a classified user relation network by matching users in the same classified core relation user group and non-core relation user group.
According to still other embodiments of the present disclosure, there is provided an apparatus for determining a communication user relationship, including: a memory; and a processor coupled to the memory, the processor configured to perform the method of determining a communication user relationship of any of the foregoing embodiments based on instructions stored in the memory device.
According to still further embodiments of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program, wherein the program, when executed by a processor, implements the method for determining a communication user relationship of any of the foregoing embodiments.
The method determines the closeness measuring information corresponding to each user group according to the communication record information, classifies the user groups according to the closeness measuring information, and determines the relationship among the users according to the classification result. The method adopts a big data processing method, can analyze the relation of two users communicating randomly in the whole network, and realizes parallel analysis of the relation of the users in the whole network by classifying a large number of user groups and then determining the user relation, so that repeated and cyclic operation can not occur, and the analysis efficiency is improved.
Other features of the present disclosure and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 illustrates a flow diagram of a method of determining a communication user relationship of some embodiments of the present disclosure.
Fig. 2 is a flow chart illustrating a method for determining a communication user relationship according to another embodiment of the disclosure.
Fig. 3 shows a schematic structural diagram of a device for determining a communication user relationship according to some embodiments of the disclosure.
Fig. 4 is a schematic structural diagram of a communication user relationship determination apparatus according to another embodiment of the present disclosure.
Fig. 5 is a schematic structural diagram of a communication user relationship determination apparatus according to still other embodiments of the present disclosure.
Fig. 6 shows a schematic structural diagram of a communication user relationship determination apparatus according to still other embodiments of the present disclosure.
Detailed Description
The technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
The present disclosure provides a method for determining a communication user relationship, which is described below with reference to fig. 1.
Fig. 1 is a flow chart of some embodiments of a method for determining a communication user relationship according to the present disclosure. As shown in fig. 1, the method of this embodiment includes: steps S102 to S106.
And step S102, determining the closeness measurement information among the users in the user group according to the communication record information.
The communication record information may be generated from the communication information. The communication information may be at least one of signaling record information, short message record information and call ticket information collected in a communication network. The signaling record information can reflect the whole communication process of the user, can display the information of voice communication and the like which are not answered, can make up the communication information which does not generate cost and is absent in the ticket information, and further improves the accuracy of the subsequent analysis of the user relationship. At least one of the number of the user (including the calling and the called), the starting time, the response time, the ending time, the roaming position, the source office direction, the collecting position and the protocol type can be extracted from the communication information to be used for generating the communication record information. The roaming position, the source office direction and the collecting position can be used for determining user position information. The protocol type may distinguish between the type of network signaling or protocol, etc.
In some embodiments, communicating the record information includes: at least one item of communication time interval information, user position information, call duration information, ringing duration information and communication type among users.
Each communication record corresponds to two users, namely a calling user and a called user, and the two users can form a user group, namely the user group comprises any two users corresponding to the communication record information. Further, for each piece of communication record information, the closeness of the corresponding user group in this communication can be calculated. For example, the density of the current communication between the users is determined according to the communication record information values in the communication between the users and the weights corresponding to the communication record information values. The following formula can be used to calculate the closeness of one communication between users.
D＝f(m1*Ti,m2*Po,m3*Ci,…) (1)
F (-) in equation (1) represents a function, which may be, for example, an addition of several factors. Ti is a communication time interval information value between users (for example, the communication time interval information value can be divided into working time and non-working time, and different values are respectively assigned), Po is a user position information value, and can represent the relative position of the user (for example, different values can be respectively assigned to the same base station, the same city or different places), Ci is a communication time information value (for example, ringing time length, conversation time length, and different time length ranges can be divided, and different values are respectively assigned), m is1、m2、m3Weights corresponding to different communication record information values, respectively. The formula (1) may further include other communication record information values and corresponding weights, for example, communication types and corresponding weights, which communication record information values are specifically selected, and how the weights are set, and the communication record information values may be flexibly configured according to different requirements.
The setting of the communication record information value can be dynamically adjusted according to the analysis requirements and scenes. For example, when a user group having a family relationship is mainly analyzed, the inter-user communication period information value corresponding to the working time may be adjusted to be lower than the inter-user communication period information value corresponding to the non-working time. By such adjustment, the communication performed during the non-operation time can be made more closely associated, which means that the communication performed during the non-operation time by two users is made more closely associated, and these users are more likely to be classified into user groups having a family relationship during the subsequent analysis.
The affinity of each communication between the users may be used as the affinity measurement information between the users, and in some embodiments, the affinity measurement information may further include: the history accumulates the degree of closeness. In some embodiments, the historical cumulative affinity of the first user to the second user in the user group is determined according to the affinity of each communication between the first user and the second user and the weight of the communication direction. The historical cumulative affinity of the first user for the second user may be calculated according to the following formula.
DA＝∑Di*Ki (2)
Wherein D isiIndicating the degree of closeness of the ith communication, KiFor a corresponding communication direction weight, for example, the outgoing communication direction weight is higher than the incoming communication direction weight. As can be seen from the above formula, for two users, such as a and B, the historical cumulative density of a to B and the historical cumulative density of B to a are different due to the influence of the communication direction weight, and therefore, the information of the affinity measure may include: the historical accumulated closeness of the first user to the second user in the user group, and the historical accumulated closeness of the second user to the first user.
In some embodiments, the affinity measure information further includes: the user dependency. In some embodiments, the user dependency of a first user on a second user in a group of users is determined from historical cumulative affinity between the first user and the second user, versus a sum of historical cumulative affinity between the first user and all users. The user dependency of the first user on the second user may be calculated according to the following formula.
YD1＝DA/Dtotal (3)
In the formula (3), DARepresenting the historical cumulative closeness, D, between the first user and the second usertotalRepresenting the sum of the historical cumulative affinities of the first user across all users.
In some embodiments, the affinity measure information further includes: and averaging the user dependence in a preset time. In some embodiments, the average user dependency of the first user on the second user in the user group is determined according to an average value of the user dependency of the first user on the second user within a preset time, for example, the average value of the user dependency of the first user on the second user every month within half a year is counted.
In some embodiments, the affinity measure information further includes: at least one item of information of the number of outgoing calls, the number of incoming calls, the starting time and the final time.
And step S104, classifying the user groups according to the closeness measurement information corresponding to the user groups.
In step S102, multiple items of closeness measurement information corresponding to the user group may be determined, and the user group may be classified according to preset rules. For example, setting thresholds corresponding to different affinity measurement information, and comparing the affinity measurement information corresponding to the user group with the thresholds, thereby determining the classification of the user group. For example, a user group whose affinity measure is below a certain threshold may be determined to be an abnormal relationship, such as a nuisance call, etc. The preset rules may be applied in conjunction with dynamic adjustment of the value of the communication record information. For example, it is mainly desired to analyze a user group having a family relationship, adjust an inter-user communication period information value corresponding to an operating time to be lower than an inter-user communication period information value corresponding to a non-operating time, and set a user location information value corresponding to the city to be higher. Further, if the number of times of communication between two users in the non-working period and the same city is large, the historical cumulative density, the dependency degree and the like are higher than those between other users, and the two users can be determined as the family relationship by setting thresholds of the historical cumulative density, the dependency degree and the like. The specific preset rule can be set according to statistical experience.
In some embodiments, the closeness measurement information corresponding to the user group may be input into a pre-trained classification or clustering model to classify the user group. For example, a clustering model may be applied to classify a group of users. The closeness measurement information corresponding to the user group can include a plurality of closeness measurement vectors, and the user group can be gathered into different classes by inputting the closeness measurement vectors into the clustering model. The clustering algorithm is an existing algorithm and is not described herein again.
Furthermore, in order to reduce the calculated amount and obtain a more accurate classification result, the closeness measurement information corresponding to the user group can be input into a pre-trained machine learning model to determine a core relation user group and a non-core relation user group; the core relational user group is further classified. The core relation user group, namely the user group with close communication relation, can remove the non-core relation user group which is only performed for a few times, thereby reducing the calculation amount. The machine learning model is, for example, a decision tree model. The decision tree model is an existing algorithm and is not described herein again.
And step S106, determining the relation among the users in the user group according to the classification result.
And after classifying the users, determining the user relationship according to the characteristics of the user group of each class. For example, the user relationship is determined by analyzing the communication characteristics of a class of user groups and comparing the communication characteristics with a preset threshold value. For example, a user group in the same city, who communicates for a long time, probably at a high rate, during work hours, may be determined as a work relationship.
In some embodiments, the non-core relational user groups may also be classified; and forming a classified user relation network by matching users in the core relation user group and the non-core relation user group with the same classification. For the classification of the non-core relational user group, the same classification method as the core relational user group may be adopted. In the same classification, the same users appear in different user groups, and the user groups can be associated to form a user relationship network. For example, a and B are family relationships, B and C are family relationships, and a family relationship may be determined A, B, C.
The method of the embodiment can realize the relation analysis of the user based on the signaling data without depending on privacy data such as a terminal address book and the like. The method is not aimed at one-time analysis of a target individual, but supports core relation mining and classification of any number of the whole network with any user facing the whole network, and is low in implementation cost. The problems that according to the traditional technology, an individual relationship network is established one by taking an individual node as a center, and reconnection needs a large amount of circulation and recursive convergence, the calculation amount is large, and relationship data are difficult to store are solved. The communication data can be dynamically updated, and the management cost is low. The method of the embodiment realizes the user relationship analysis through algorithms such as a big data technology and a machine learning model, is simple, easy to realize, more accurate, capable of finding unknown relationships and practical in the aspect of differentiated management.
Further embodiments of the communication user relationship determination method of the present disclosure are described below in conjunction with fig. 2.
Fig. 2 is a flowchart of another embodiment of a method for determining a communication subscriber relationship according to the present disclosure. As shown in fig. 2, the method of this embodiment includes: steps S202 to S212.
Step S202, collecting communication information.
The communication information includes: at least one item of information in the signaling record information, the short message record information and the call ticket information. The data can be collected through a data collecting and processing module, the convergence of the data (including signaling records, short message records, Call tickets and the like) of the original Call Detail Record (CDR) Database of communication is completed, and the data collecting and processing module has a network real-time transmission interface and supports the preprocessing and storage of data files.
In step S204, the related information is extracted to generate communication record information.
Preprocessing of communication data, including for example, cleansing, deduplication, number format specification reconciliation, loading into the cluster database, may be accomplished using an Extract Transform Load (ETL) module.
And step S206, determining the closeness measurement information among the users in the user group according to the communication record information.
The method can adopt a big data distributed computing cluster, a basic computing capability platform for carrying data ETL and running a relation analysis module, and adopts a Hadoop + Spark cluster open source technical architecture to support the quasi-real-time batch processing of mass data. And storing relevant information in the user relationship analysis process by utilizing a database, wherein the database comprises a data warehouse and a dynamic relational data database, an ETL table, various analysis tables, configuration parameters, a relational data table and the like. For example, a communication record affinity table may be stored, which may include: the calling and called numbers, the number of outgoing calls, the number of incoming calls, the sum of historical cumulative closeness of the user to all users, the starting time, the last time, etc. may be stored in a closeness measurement information table, which may include: the calling party, the called party, the starting time, the last time, the calling times, the accumulated density, the user dependence and the user average dependence can be used as index keywords according to the combination of the calling party and the called party. An affinity table, a communication record table, a core relationship user group table, etc. for each communication may also be stored.
And S208, inputting the closeness measurement information corresponding to the user group into a pre-trained machine learning model, and determining a core relation user group and a non-core relation user group.
And step S210, inputting the closeness measurement information corresponding to the core relationship user group into a pre-trained classification or clustering model, and classifying the core relationship user group.
The steps S206-S210 can be executed by adopting a relational analysis module, and the pipelined processing, the step-by-step analysis and the screening are realized through a layered model, so that the problems of a large number of repeated cycles or recursion and large association processing are avoided, and the operation intensity and the system resource pressure are greatly reduced.
And step S212, determining the relationship among the users in the core relationship user group according to the classification result.
In some embodiments, the non-core relational user groups may also be classified; and forming a classified user relation network by matching users in the core relation user group and the non-core relation user group with the same classification.
The relationship of the core relationship user group and the user relationship network can be presented by utilizing the relationship data maintenance management module to dynamically update and manage data and query various data.
The method of the embodiment can support online parallel computation and real-time dynamic update of large-batch user relationships; and the core relation is directly mined for classification, and the target classification and the quick retrieval of the individual relation network are supported. The superposition system based on the communication network is built by adopting a free open-source technology architecture, and is low in implementation cost and rapid in deployment. The method of the embodiment can be carried out aiming at different application scenes, and is low in implementation difficulty, wide in application range and high in value.
Some application examples of the present disclosure are described below.
Suppose there are six people in the network, a, B, C, D, E, F, where AB, CD are relatives and friends, AC is a business partner, E is a service phone, and F is a harassment/fraud phone.
The system carries out dynamic quantitative analysis through the communication data of the users in the whole network within a certain time based on a user relationship analysis model, and carries out identification and classification of the core relationship user group.
Because relatives and friends have stable mutual call records, mainly in non-working periods and holidays, the call quality is higher, and after certain time accumulation, the distance and the interdependency value are higher, the system divides a core relationship user group with strong relationship of AB and CD according to the distance and the interdependency value;
as the business cooperative relationship has a specific interactive communication mode, the system can obtain the AC as a stronger core relationship group mainly in working days and working periods and with certain distance value and dependence;
the customer service telephone is mainly called, the calling quality is high, the average distance is small (although the quantity is large, the calling distance coefficient is small), the dependence on other people is not strong due to the fact that the calling is passive calling, and the calling is abnormal, so that the system can identify the customer service telephone E;
the harassing call is mainly called out, the call quality is low, the active call is highly dependent on others, the average distance value is large, and the harassing call can be identified by the system under an abnormal condition. And finally outputting a result: { a, B, relatives and friends; c, D, relatives and friends; a, C, commercial; e, other (customer service); f, Exception }
The present disclosure also provides a device for determining a communication user relationship, which is described below with reference to fig. 3.
Fig. 3 is a block diagram of some embodiments of a communication subscriber relationship determination apparatus of the present disclosure. As shown in fig. 3, the apparatus 30 of this embodiment includes: affinity information determination module 302, classification module 304, and relationship determination module 306. These three modules may be combined to form the relationship analysis module mentioned in the above embodiments.
And an affinity information determining module 302, configured to determine, according to the communication record information, affinity measurement information between users in a user group, where the user group includes two users corresponding to the communication record information.
In some embodiments, communicating the record information includes: at least one item of communication time interval information, user position information, call duration information and ringing duration information among users;
in some embodiments, the affinity measure information between users includes: the intimacy degree of one-time communication between users; the affinity information determining module 302 is configured to determine the affinity of the current communication between the users according to the information values of each communication record in one communication between the users and the weights corresponding to the information values of each communication record.
In some embodiments, the affinity measure information further includes: historical cumulative osculating degree; the historical accumulated closeness of the first user to the second user in the user group is determined according to the closeness of each historical communication between the first user and the second user and the communication direction weight.
In some embodiments, the affinity measure information further includes: a user dependency; the user dependence of a first user on a second user in the user group is determined by comparing the sum of historical cumulative affinities of the first user on all users according to the historical cumulative affinity of the first user on the second user.
And the classification module 304 is configured to classify the user group according to the closeness measurement information corresponding to the user group.
In some embodiments, the classification module 304 is configured to input the closeness measure information corresponding to the user group into a pre-trained classification or clustering model to classify the user group.
In some embodiments, the classification module 304 is configured to input the affinity measurement information corresponding to the user group into a pre-trained machine learning model, and determine a core relationship user group and a non-core relationship user group; and classifying the core relation user group.
And a relation determining module 306, configured to determine a relation between users in the user group according to the classification result.
Fig. 4 is a block diagram of another embodiment of a communication subscriber relationship determination apparatus of the present disclosure. As shown in fig. 4, the apparatus 40 of this embodiment includes: the affinity information determining module 402, the classifying module 404, the relationship determining module 406, the affinity information determining module 302, the classifying module 304, and the relationship determining module 306 have similar functions; and a data acquisition processing module 408.
The data collection processing module 408 is configured to collect communication information of the user, where the communication information includes: at least one item of information in signaling record information, short message record information and call ticket information; and extracting at least one of the user number, the starting time, the response time, the ending time, the roaming position, the source office direction, the acquisition position and the protocol type from the communication information, and generating communication record information.
In some embodiments, the classification module 404 is also used to classify the non-core group of relational users. The apparatus 40 further comprises: the relationship network determining module 410 is configured to form a classified user relationship network by matching users in the core relationship user group and the non-core relationship user group of the same classification. This module may constitute a relationship analysis module 400.
Further, the apparatus for determining a communication user relationship may further include: the specific functions of the data ETL module 412, the database 414, the relationship data maintenance management module 416, etc. may refer to the foregoing embodiments.
The determination means of the communication user relationship in the embodiment of the present disclosure may be implemented by various computing devices or computer systems, and is described below with reference to fig. 5 and fig. 6.
Fig. 5 is a block diagram of some embodiments of a communication subscriber relationship determination apparatus of the present disclosure. As shown in fig. 5, the apparatus 50 of this embodiment includes: a memory 510 and a processor 520 coupled to the memory 510, the processor 520 configured to perform a method of determining a communication user relationship in any of the embodiments of the present disclosure based on instructions stored in the memory 510.
Fig. 6 is a block diagram of another embodiment of a communication subscriber relationship determining apparatus according to the present disclosure. As shown in fig. 6, the apparatus 60 of this embodiment includes: memory 610 and processor 620 are similar to memory 510 and processor 520, respectively. Input/output interfaces 630, network interfaces 640, storage interfaces 650, etc. may also be included. These interfaces 630, 640, 650 and the connections between the memory 610 and the processor 620 may be, for example, via a bus 660. The input/output interface 630 provides a connection interface for input/output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 640 provides a connection interface for various networking devices, such as a database server or a cloud storage server. The storage interface 650 provides a connection interface for external storage devices such as an SD card and a usb disk.
As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only exemplary of the present disclosure and is not intended to limit the present disclosure, so that any modification, equivalent replacement, or improvement made within the spirit and principle of the present disclosure should be included in the scope of the present disclosure.
Claims (16)
1. A method of determining a communication user relationship, comprising:
determining the closeness measurement information among users in a user group according to the communication record information, wherein the user group comprises any two users corresponding to the communication record information, and the communication record information comprises: communication time interval information, user position information, call duration information and ringing duration information among users;
classifying the user groups according to the closeness measurement information corresponding to the user groups;
determining the relation between users in the user group according to the classification result;
wherein the information of the closeness measure among the users comprises: the degree of closeness of each communication between users; the determining of the closeness measurement information among the users in the user group according to the communication record information includes:
and determining the density of each communication between the users according to each communication record information value in each communication between the users and the weight corresponding to each communication record information value.
2. The determination method according to claim 1,
the affinity measure information further includes: historical cumulative osculating degree;
the historical accumulated density of a first user to a second user in a user group is determined according to the density of each communication between the first user and the second user and the current communication direction weight.
3. The determination method according to claim 2,
the affinity measure information further includes: a user dependency;
and the user dependence of a first user on a second user in the user group is determined by comparing the sum of the historical accumulated closeness of the first user on all users according to the historical accumulated closeness of the first user on the second user.
4. The determination method according to claim 1,
the classifying the user groups according to the closeness measurement information corresponding to all the user groups comprises:
inputting the closeness measurement information corresponding to the user group into a pre-trained machine learning model, and determining a core relationship user group and a non-core relationship user group;
and classifying the core relation user group.
5. The determination method according to claim 1,
the classifying the user groups according to the closeness measurement information corresponding to the user groups comprises:
and inputting the closeness measurement information corresponding to the user group into a pre-trained classification or clustering model to classify the user group.
6. The determination method according to claim 1,
the method further comprises the following steps:
collecting user communication information, wherein the communication information comprises: at least one item of information in signaling record information, short message record information and call ticket information;
and extracting at least one item of the user number, the starting time, the response time, the ending time, the roaming position, the source office direction, the acquisition position and the protocol type from the communication information, and generating communication record information.
7. The determination method according to claim 4,
the classifying the user group further comprises:
classifying the non-core relation user group;
the method further comprises the following steps:
and forming a classified user relation network by matching users in the core relation user group and the non-core relation user group with the same classification.
8. An apparatus for determining a communication user relationship, comprising:
the system comprises an affinity information determining module and an affinity measuring module, wherein the affinity information determining module is used for determining affinity measuring information among users in a user group according to communication record information, the user group comprises any two users corresponding to the communication record information, and the communication record information comprises: communication time interval information, user position information, call duration information and ringing duration information among users;
the classification module is used for classifying the user groups according to the closeness measurement information corresponding to the user groups;
the relation determining module is used for determining the relation among the users in the user group according to the classification result;
wherein the information of the closeness measure among the users comprises: the density information determining module is used for determining the density of each communication between the users according to each communication record information value in each communication between the users and the weight corresponding to each communication record information value.
9. The determination apparatus according to claim 8,
the affinity measure information further includes: historical cumulative osculating degree;
the historical accumulated density of a first user to a second user in a user group is determined according to the density of each communication between the first user and the second user and the current communication direction weight.
10. The determination apparatus according to claim 9,
the affinity measure information further includes: a user dependency;
and the user dependence of a first user on a second user in the user group is determined by comparing the sum of the historical accumulated closeness of the first user on all users according to the historical accumulated closeness of the first user on the second user.
11. The determination apparatus according to claim 8,
the classification module is used for inputting the closeness measurement information corresponding to the user group into a pre-trained machine learning model and determining a core relation user group and a non-core relation user group; the core user group is classified.
12. The determination apparatus according to claim 8,
and the classification module is used for inputting the closeness measurement information corresponding to the user group into a pre-trained classification or clustering model to classify the user group.
13. The determination apparatus according to claim 8,
the device further comprises:
the data acquisition processing module is used for acquiring communication information of a user, wherein the communication information comprises: at least one item of information in signaling record information, short message record information and call ticket information; and extracting at least one item of the user number, the starting time, the response time, the ending time, the roaming position, the source office direction, the acquisition position and the protocol type from the communication information, and generating communication record information.
14. The determination apparatus according to claim 11,
the classification module is also used for classifying the non-core relation user group;
the device further comprises:
and the relation network determining module is used for forming a classified user relation network by matching users in the core relation user group and the non-core relation user group which are in the same classification.
15. An apparatus for determining a communication user relationship, comprising:
a memory; and
a processor coupled to the memory, the processor configured to perform the method of determining a communication user relationship of any of claims 1-7 based on instructions stored in the memory device.
16. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810711771.XA CN110677269B (en) | 2018-07-03 | 2018-07-03 | Method and device for determining communication user relationship and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810711771.XA CN110677269B (en) | 2018-07-03 | 2018-07-03 | Method and device for determining communication user relationship and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110677269A CN110677269A (en) | 2020-01-10 |
| CN110677269B true CN110677269B (en) | 2022-05-13 |
Family
ID=69065799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810711771.XA Active CN110677269B (en) | 2018-07-03 | 2018-07-03 | Method and device for determining communication user relationship and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110677269B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111860655B (en) * | 2020-07-23 | 2023-05-30 | 中国联合网络通信集团有限公司 | User processing method, device and equipment |
| CN112163885A (en) * | 2020-09-29 | 2021-01-01 | 贵州力创科技发展有限公司 | User relationship mining method and system based on mobile communication data |
| CN114979369A (en) * | 2022-04-14 | 2022-08-30 | 马上消费金融股份有限公司 | Abnormal call detection method and device, electronic equipment and storage medium |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100527682C (en) * | 2003-11-12 | 2009-08-12 | 株式会社日立制作所 | Conversation Qo S controller |
| CN104636439B (en) * | 2015-01-04 | 2018-07-03 | 中国联合网络通信集团有限公司 | A kind of method and device for analyzing user's social relationships |
| CN106791221B (en) * | 2016-12-06 | 2019-05-31 | 北京邮电大学 | A kind of kith and kin's circle relation recognition method based on call |
| CN107729940A (en) * | 2017-10-20 | 2018-02-23 | 北京工业大学 | A kind of user bill big data base station connection information customer relationship estimates method |
| CN107958423A (en) * | 2017-12-20 | 2018-04-24 | 广东宜通世纪科技股份有限公司 | User's social relationships analysis method and storage medium, server-side |
-
2018
- 2018-07-03 CN CN201810711771.XA patent/CN110677269B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN110677269A (en) | 2020-01-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103605791B (en) | Information transmission system and information-pushing method | |
| CN109640312B (en) | 'Black card' identification method, electronic equipment and computer readable storage medium | |
| CN110337059B (en) | Analysis algorithm, server and network system for family relationship of user | |
| CN110677269B (en) | Method and device for determining communication user relationship and computer readable storage medium | |
| US8788438B2 (en) | Method performed in a computer system for aiding the assessment of an influence of a user in or interacting with a communication system by applying social network analysis, SNA, functions, a computer system, computer program and computer program product | |
| CN110889526B (en) | User upgrade complaint behavior prediction method and system | |
| CN112333342B (en) | Intelligent voice calling method, device, equipment and storage medium | |
| CN113961712B (en) | Knowledge-graph-based fraud telephone analysis method | |
| CN109145050B (en) | Computing device | |
| CN107784511A (en) | A kind of customer loss Forecasting Methodology and device | |
| CN113206909A (en) | Crank call interception method and device | |
| CN108776857A (en) | NPS short messages method of investigation and study, system, computer equipment and storage medium | |
| CN115952398B (en) | Traditional calculation method, system and storage medium based on data of Internet of things | |
| US10439919B2 (en) | Real time event monitoring and analysis system | |
| US9398441B2 (en) | Method and apparatus for identifying re-subscribed user | |
| KR100601885B1 (en) | Call recommender system for outbound call center | |
| KR101568800B1 (en) | Real-time issue search word sorting method and system | |
| CN112601228B (en) | Method and device for detecting card number and computer readable storage medium | |
| CN115062002A (en) | Streaming data processing method and device | |
| CN114268939B (en) | Abnormal user identification method in mobile communication and intelligent device | |
| Ghotekar | Analysis and Data Mining of Call Detail Records using Big Data Technology | |
| CN113517990A (en) | Method and device for predicting net recommendation value NPS (network neutral density System) | |
| Albadawi et al. | Telecom churn prediction model using data mining techniques | |
| JP7368897B1 (en) | information processing equipment | |
| CN111242147A (en) | Method and device for identifying close contact and frequent active area |
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 |