Disclosure of Invention
In view of the above, embodiments of the present invention are directed to a method and an apparatus for identifying a permanent station of a mobile subscriber, which at least partially solve one of the above problems.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a first aspect of an embodiment of the present invention provides a method for identifying a permanent station of a mobile subscriber, including:
acquiring a courier user; the courier user is a mobile user of which the user is a courier;
extracting express delivery call records from the call records of the courier users; the express delivery interaction record is a call record during express delivery;
analyzing the express delivery call record to acquire the proximity relation of different mobile users communicating with the courier user;
taking the permanent station of the first mobile user of the first network as the permanent station of the second mobile user of the second network; the first mobile user and the second mobile user have the proximity relation and are different mobile users communicating with the courier user.
Based on the above scheme, the acquiring the courier user includes:
and analyzing the call records and excavating the courier users.
Based on the scheme, the analyzing the call records and the mining the communication identification of the courier comprise at least one of the following steps:
determining the mobile user with the call time length less than the first preset call time length and the number of calls more than the preset number as the courier user in a preset time period;
determining that the mobile user who has communicated with not less than a preset number of different mobile users in the preset time is the courier user;
and determining that the mobile user with the switching frequency greater than the preset frequency in the cell is the courier user in the preset time.
Based on the above scheme, the extracting of the express delivery call record from the call record of the courier user includes:
extracting the call record of the courier user;
and determining the call records of which the call duration is less than a second preset duration in the call records as the express delivery call records.
Based on the above scheme, the analyzing the express delivery call record to obtain the proximity relation of different mobile users who communicate with the courier user includes:
clustering express delivery call records by taking a time interval as a variable to form a cluster;
and confirming any two mobile users which are communicated with the courier user in the cluster meeting the preset condition as the mobile users with the proximity relation.
Based on the above scheme, the determining any two mobile users in the cluster meeting the preset condition and talking with the courier user as mobile users having the proximity relationship includes:
and if the longest time interval of any two call records in the cluster is smaller than a preset time interval, determining that all the mobile users in the cluster, which have calls with the courier user, are the mobile users with the proximity relation.
A second aspect of the embodiments of the present invention provides a device for identifying a permanent station of a mobile subscriber, including:
the system comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a courier user; the courier user is a mobile user of which the user is a courier;
the extraction unit is used for extracting express delivery call records from the call records of the courier users; the express delivery interaction record is a call record during express delivery;
the analysis unit is used for analyzing the express delivery call record and acquiring the proximity relation of different mobile users who communicate with the courier user;
the determining unit is used for taking the permanent station of the first mobile user of the first network as the permanent station of the second mobile user of the second network; the first mobile user and the second mobile user have the proximity relation and are different mobile users communicating with the courier user.
Based on the scheme, the obtaining unit is specifically used for analyzing the call records and mining the courier users.
Based on the foregoing solution, the obtaining unit is specifically configured to execute at least one of the following:
determining the mobile user with the call time length less than the first preset call time length and the number of calls more than the preset number as the courier user in a preset time period;
determining that the mobile user who has communicated with not less than a preset number of different mobile users in the preset time is the courier user;
and determining that the mobile user with the switching frequency greater than the preset frequency in the cell is the courier user in the preset time.
Based on the above scheme, the extracting unit is specifically configured to extract the call record of the courier user; and determining the call records of which the call duration is less than a second preset duration in the call records as the express delivery call records.
Based on the scheme, the analysis unit is specifically used for clustering express delivery call records by taking a time interval as a variable to form a cluster; and confirming any two mobile users which are communicated with the courier user in the cluster meeting the preset condition as the mobile users with the proximity relation.
Based on the above scheme, the analysis unit is specifically configured to determine that all the mobile users in the cluster communicating with the courier user are the mobile users having the proximity relationship if the longest time interval between any two call records in the cluster is smaller than a predetermined time interval.
According to the method and the device for identifying the permanent station of the mobile user, provided by the embodiment of the invention, the mobile users using different communication networks but having the proximity relation can be screened out by utilizing the particularity of the courier industry, and the permanent station of the mobile user of the second network is determined by utilizing the permanent place of the mobile user of the first network; obviously, the permanent premises of the mobile user of the second network can be simply and conveniently determined, the problem that the permanent premises of the mobile user of the second network cannot be determined due to information gaps of different network users in the prior art is solved, and the method and the device have the characteristics of simplicity and convenience in implementation and high accuracy.
Detailed Description
The technical solution of the present invention is further described in detail with reference to the drawings and the specific embodiments of the specification.
As shown in fig. 1, the present embodiment provides a method for identifying a permanent station of a mobile subscriber, including:
step S110: acquiring a courier user; the courier user is a mobile user of which the user is a courier;
step S120: extracting express delivery call records from the call records of the courier users; the express delivery interaction record is a call record during express delivery;
step S130: analyzing the express delivery call record to acquire the proximity relation of different mobile users communicating with the courier user;
step S140: taking the permanent station of the first mobile user of the first network as the permanent station of the second mobile user of the second network; the first mobile user and the second mobile user have the proximity relation and are different mobile users communicating with the courier user.
The embodiment can be applied to various electronic devices with information processing capability, such as a network side server or a cloud server with data analysis capability.
In step S110, a courier user is to be obtained, and a specific obtaining method may include receiving the courier user from another electronic device, and also includes self-analyzing to determine the courier user; and determining the courier user according to the identity information reported by the mobile user. The obtaining of the courier user at least comprises obtaining a communication identifier of the courier user; the communication identifier may include a mobile communication number, which is a communication number called a mobile phone number.
The call records of the courier user will be analyzed in step S120. And (6) extracting express delivery call records. Usually, when the courier carries out express delivery, the courier can inform the phone in advance to inform the courier, and the phone duration is also shorter usually, can extract according to the characteristics of the conversation when the express delivery is mutual express delivery the express delivery conversation record.
In step S130, courier delivery call records are analyzed to determine that different mobile users who have a call with the same courier user have a proximity relationship with a geographic location. For example, when a courier sends a courier to a cell a, the courier needs to send couriers to a mobile user B and a mobile user C respectively; before the express delivery is finally delivered to the mobile user B and the mobile user C, the mobile user B and the mobile user C are respectively communicated with, obviously, because both are in the cell a, the courier may respectively communicate with the mobile user B and the mobile user C within a very short time, obviously, the time interval between the two communications is very small, and it can be considered that the mobile user B and the mobile user C have a proximity relationship, and the proximity relationship can be embodied in a proximity relationship that the ordinary premises of the mobile user B and the mobile user C have geographic positions.
In step S140, the regular premises of the first mobile subscriber of the first network is used as the regular premises of the second mobile subscriber of the second network, so that the regular premises of the mobile subscriber of the second network can be determined easily. In this embodiment, the permanent premises of the first mobile subscriber of the first network may determine the permanent premises of the first mobile subscriber by analyzing the resident cell of the first mobile subscriber. In the embodiment of the invention, the permanent station can be the position where the user is located most of the time. The first network and the second network may be networks of different communication systems, and may also be networks of different operators. The mobile subscriber of the first network may be a home network subscriber, and the mobile subscriber of the second network may be a heterogeneous network mobile subscriber.
The step S140 may specifically include:
step S141: and screening out the first mobile users of the first network from the mobile users with the proximity relation. The first network may be a communication network of any operator, for example, a china mobile subscriber, which is called a first network mobile subscriber;
step S142: obtaining residence parameters such as residence time of the first application user in each first network cell, and determining the permanent residence of the first mobile user;
step S143: and according to the proximity relation, taking the permanent station of the first mobile user as the permanent station of the second mobile user of the second network.
Of course, in a specific implementation, the implementation manner of the step S140 is various, and is not limited to any one of the above.
In short, by adopting the method of the embodiment, not only the permanent site of the mobile subscriber of the first network can be determined, but also the permanent site of the mobile subscriber of the second network can be approximately determined through the proximity relation between the mobile subscriber of the second network and the mobile subscriber of the first network, and meanwhile, the method has the characteristics of simplicity and convenience in implementation and high accuracy.
In some embodiments, the step S110 may include: and analyzing the call records and excavating the courier users. In this embodiment, the step S110 is to analyze the call records of the server itself, for example, analyze the call records of all mobile users in the first network, and dig out the courier user; specific implementation manners are various, and three possible implementation manners are provided as follows:
the first method is as follows:
the step S110 may include: and determining the mobile user with the call time length less than the first preset call time length and the number of calls more than the preset number as the courier user in the preset time period. In this embodiment, the predetermined time period may be an operating time period. The working time period may include working hours from 8 am to 18 pm or 17 pm of a day. Due to the fact that express delivery is required to be delivered, express delivery persons can continuously get or send the express delivery at home in the working time, the express delivery persons may need to frequently communicate with express receiving persons or express sending persons, the number of times of communication of the express delivery persons in one day is large, and the number of times of communication is far larger than that of common persons. Therefore, in the embodiment, the courier user can be screened out according to the number of calls of each mobile user. For example, when it is detected that the mobile user D has a number of calls up to 50 times per day in the working hours, and the number of calls per time is not more than 1 minute or 30 seconds, it is very likely that the mobile user may be able to be a courier user that can be preliminarily determined, and the mobile user may be directly determined as a courier user or an alternative user to the courier user.
The second method comprises the following steps:
the step S110 may include:
and determining that the mobile user who has communicated with not less than the preset number of different mobile users in the preset time is the courier user. The predetermined time here may be the operating time as well. The courier can communicate with different users, and the courier user is determined and screened by utilizing the characteristic in the method. The predetermined number may be a threshold value of 100, 200, or 300, and the specific threshold value may be determined according to the number of calls of one courier.
The third method comprises the following steps:
the step S110 may include:
and determining that the mobile user with the switching frequency greater than the preset frequency in the cell is the courier user in the preset time. Due to the continuous movement of the courier, the frequency of movement in different mobile communication cells may be much greater than the frequency of handover of mobile users who normally stay in a fixed place. Therefore, in this embodiment, the user whose switching frequency in the cell is greater than the predetermined frequency can be screened out as the courier user or the candidate user of the courier user.
In particular implementations, the courier user may be determined in one or more of the three manners described above. For example, any two of three ways may be combined: for example, a mobile subscriber whose call duration is less than a first predetermined duration is selected as the courier subscriber, the number of calls being greater than a predetermined number of times within a predetermined time period, and the number of calls being made with no less than a predetermined number of different mobile subscribers within the predetermined time period, and/or the frequency of handover in the cell being greater than a predetermined frequency within the predetermined time period.
Of course, the above is merely an example, and the specific determination of the courier user is not limited to the above manner.
In some embodiments, the step S120 may include:
extracting the call record of the courier user;
and determining the call records of which the call duration is less than a second preset duration in the call records as the express delivery call records.
The courier may contact the person who sends or receives the express, and usually the person who sends or receives the express opens the door, so the call time is very short, for example, several seconds. Therefore, in this embodiment, the call record with the call duration shorter than the second predetermined duration can be used as the express delivery call record. In this embodiment, the second predetermined time period may be equal to the first predetermined time period, or may be less than the first predetermined time period, and is preferably less than the first predetermined time period. The second predetermined period of time may be 30 seconds, or 25 seconds, or 20 seconds, etc. in this embodiment.
Further, as shown in fig. 2, the step S130 may include:
step S131: clustering call records in express delivery by taking time intervals as variables to form a cluster;
step S132: and confirming any two mobile users which are communicated with the courier user in the cluster meeting the preset condition as the mobile users with the proximity relation.
In this embodiment, the time interval of the call time is a variable, and the express delivery call records are clustered. There are various ways of clustering, such as K-means clustering, etc. Through clustering, call records with smaller call time intervals can be aggregated into a cluster. In this embodiment, the cluster is equivalent to an aggregation, and includes a plurality of call records with concentrated call time intervals. In this embodiment, the mobile users who have a call with the same courier user in all call records in the cluster meeting the preset condition are selected as the mobile users having a proximity relationship.
For example, the step S132 may include: and if the longest time interval of any two call records in the cluster is smaller than a preset time interval, determining that all the mobile users in the cluster, which have calls with the courier user, are the mobile users with the proximity relation. For example, if the most frequent time interval between any two adjacent call records in a cluster is less than a predetermined time interval, for example, a time interval of 5 minutes, 4 minutes, or 6 minutes, the opposite call user of the courier user in all call records in the cluster can be regarded as a mobile user having a proximity relationship. Therefore, the embodiment can easily determine the mobile users having the proximity relation from the time dimension according to the time adjacency of the call records. In this embodiment, the most frequent time interval of any two call records is smaller than the predetermined time interval, and in a specific implementation, the time interval of any two call records may also be smaller than the predetermined time interval, the cluster may be considered as a cluster meeting a preset condition, and the mobile users in two adjacent call records in the cluster, which have a call with the courier user, may all be considered as mobile users having a proximity relationship.
As shown in fig. 3, the present embodiment provides a mobile subscriber permanent station identification device, including:
an obtaining unit 110, configured to obtain a courier user; the courier user is a mobile user of which the user is a courier;
an extracting unit 120, configured to extract a courier delivery call record from the call record of the courier user; the express delivery interaction record is a call record during express delivery;
an analyzing unit 130, configured to analyze the express delivery call record, and obtain a proximity relationship between different mobile users who have called the courier user;
a determining unit 140, configured to use a permanent premises of a first mobile subscriber of a first network as a permanent premises of a second mobile subscriber of a second network; the first mobile user and the second mobile user have the proximity relation and are different mobile users communicating with the courier user.
The mobile subscriber premises station identification device provided by the embodiment can correspond to one or more servers with information processing functions.
The obtaining unit 110 may correspond to a communication interface, which may be a wired interface or a wireless interface, capable of receiving information from other electronic devices, thereby obtaining the courier user. Of course, the obtaining unit 110 may correspond to a processor, and the processor may perform data analysis by executing a data analysis instruction, so as to obtain the courier user.
The extraction unit 120, the analysis unit 130, and the determination unit 140 may all correspond to a processor or a processing circuit. The processor may include a central processing unit, a microprocessor, a digital signal processor, an application processor, a programmable array, or the like, and may implement the functions of the above units through the execution of pre-portable code. The extracting unit 120, the analyzing unit 130, and the determining unit 140 may correspond to one processor in common or may correspond to different processors.
In short, the device provided by the embodiment can simply and conveniently identify the regular premises of the mobile subscriber of the second network, solves the problem that the regular premises of the mobile subscriber of the second network cannot be identified in the prior art, and has the characteristics of simple and convenient implementation and simple structure.
In some embodiments, the obtaining unit 110 is specifically configured to analyze the call records and mine the courier user. In this embodiment, the obtaining unit 110 specifically corresponds to a processor or a processing circuit, and is configured to analyze the call record by itself and mine the courier user. Specifically, the obtaining unit 110 is specifically configured to execute at least one of the following: determining the mobile user with the call time length less than the first preset call time length and the number of calls more than the preset number as the courier user in a preset time period; determining that the mobile user who has communicated with not less than a preset number of different mobile users in the preset time is the courier user; and determining that the mobile user with the switching frequency greater than the preset frequency in the cell is the courier user in the preset time. Through the above analysis, the get-single language 110 can simply and conveniently get the courier user.
In some embodiments, the extracting unit 120 is specifically configured to extract the call record of the courier user; and determining the call records of which the call duration is less than a second preset duration in the call records as the express delivery call records. According to the method and the device, the express delivery call records are selected according to the call duration, and the method and the device have the advantages of being simple and convenient to achieve and accurate in result.
In other embodiments, the analysis unit 130 is specifically configured to cluster the express delivery call records by using a time interval as a variable to form a cluster; and confirming any two mobile users which are communicated with the courier user in the cluster meeting the preset condition as the mobile users with the proximity relation. In the present embodiment, the analysis unit 130 selects mobile users having a proximity relationship through clustering; in a specific implementation process, the analysis unit 130 may also determine whether a proximity relationship exists between any two mobile users by comparing the inter-call time one by one; but through the clustering mode, the calculated amount can be greatly reduced, the determination efficiency is improved, and the calculation power consumption is reduced.
For example, the analysis unit 130 is specifically configured to determine that all mobile users in the cluster that have a call with the courier user are mobile users having the proximity relationship if the longest time interval between any two call records in the cluster is smaller than a predetermined time interval. In this embodiment, the analysis unit 130 can simply screen out the cluster meeting the preset condition, and consider any two mobile users in the cluster as mobile users having a proximity relationship. Of course, the analysis unit 130 may also regard the mobile subscriber talking with the courier user in the two adjacent call records as the mobile subscriber having the proximity relationship when the time interval between any two adjacent call records is smaller than the predetermined time interval.
Several specific examples are provided below in connection with the above embodiments:
example one:
as shown in fig. 4, the present example provides a mobile subscriber permanent station identification device, including: the system comprises a courier user generation unit 201, a call detail list processing unit 202, a proximity relation analysis unit 203 and a permanent station identification unit 204. The courier user generation unit 201 is used to identify a courier user. And the detailed call list processing unit 202 is configured to analyze a call record in the detailed call list of the courier user and extract an express delivery call record. And the proximity relation analysis unit 203 is used for determining the mobile users of the proximity relation. The permanent station identification unit 204 is configured to determine a permanent station of the mobile subscriber, for example, a permanent station of the mobile subscriber of the first network is used, and a permanent station of the mobile subscriber of the second network is determined.
For example, the courier user generating unit 201 is specifically configured to identify a courier user through a data mining method, and the core model processing rule may include one or more of the following:
(1) the proportion of the short-time call times (less than 30 seconds) in the working time (from 8 am to 17 pm) to the total call times exceeds a certain threshold (50%);
(2) during working hours, the system is communicated with a large number of different users (more than 300 months);
(3) frequent cell location shifts occur during operation.
And cleaning and denoising the data to obtain the mobile phone number of the courier user.
This unit also supports importing confirmed courier user cell phone numbers from the outside.
The courier user generation unit 201 in this example may correspond to the aforementioned acquisition unit 110.
For example, the call detail processing unit 202 may be configured to search the call detail according to the mobile phone number of the courier user, identify the call detail delivered by the courier, and generate a delivery record table of the courier and the buyer or the seller. The call detail processing unit 202 herein may correspond to the aforementioned extraction unit 120. The interaction record table may include the aforementioned express delivery interaction call record.
In some cases, the proximity relation parsing unit 203 may be configured to parse the courier delivery record table to generate a proximity relation model of the mobile user buyer. Here, the proximity relation analyzing unit 203 may correspond to the analyzing unit 130.
In some cases, the resident location identification unit 204 may be configured to copy, among the mobile users in proximity relationship with each other, the permanent premises of the unknown second network user to the already identified permanent premises of the first network mobile user, so as to identify the resident location of the second network user. The resident location identifying unit 204 provided in this example corresponds to the aforementioned determining unit 140.
Example two:
as shown in fig. 5, the present example provides a method for identifying a permanent station of a mobile subscriber, including:
step 101: the identification of the number of the courier and the import of the courier specifically comprise the following steps: and identifying the courier user through a data mining method, and acquiring the mobile phone number of the courier user. Or importing the confirmed mobile phone number of the courier user from the outside.
Step 102: processing the call detail list, judging whether a courier calls when delivering the express, and if so, generating an interaction record table; the method specifically comprises the following steps: and circularly searching the call detail list of the courier at the time of delivery in the call detail list by using the courier number acquired in the step 101. Processing rules: during the short-time courier number calling call (less than 30 seconds) during working hours (8 am to 17 pm), if the retrieval is successful, the delivery record list is inserted. After the delivery record table is generated, step 103 is executed.
Step 103: sorting the delivery record table, judging whether concentrated delivery records exist, and if yes, generating a proximity relation table, which specifically comprises the following steps: analyzing the delivery record table generated in the step 102, and mining a centralized delivery record, wherein the algorithm of the centralized delivery record is as follows:
(1) clustering analysis is carried out by taking the time interval as a variable, and the delivery records are clustered;
(2) judging whether the maximum time interval of the plurality of delivery records of the step 1 cluster is lower than a certain threshold (5 minutes), if so, generating a proximity relation table, as shown in table 1:
TABLE 1
It is obvious that in the above proximity relation table, a mobile subscriber with a small talk time interval is a mobile subscriber with proximity relation. After the proximity relation table is generated, step 104 is performed.
Step 104: permanent premises replication, which may include: and copying the resident place of the unknown second network user to the recognized resident place of the first network mobile user for the mobile users in the adjacent relationship with each other, thereby recognizing the resident place of the second network user.
TABLE 2
Table 2 is a list of the permanent premises of the different mobile subscribers determined after table 1. It is apparent that in table 2, the permanent premises of both mobile subscriber B and mobile subscriber C of the second network are set as the permanent premises of mobile subscriber a of the first network.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may be separately used as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the method embodiments may be implemented by hardware related to program instructions, and the program may be stored in a computer readable storage medium, and when executed, the program performs the steps including the method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.