CN114520969B - Method, device and equipment for judging number card use and computer storage medium - Google Patents
Method, device and equipment for judging number card use and computer storage medium Download PDFInfo
- Publication number
- CN114520969B CN114520969B CN202011308195.8A CN202011308195A CN114520969B CN 114520969 B CN114520969 B CN 114520969B CN 202011308195 A CN202011308195 A CN 202011308195A CN 114520969 B CN114520969 B CN 114520969B
- Authority
- CN
- China
- Prior art keywords
- card
- main card
- main
- judging
- obtaining
- 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
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000004891 communication Methods 0.000 claims abstract description 30
- 230000003993 interaction Effects 0.000 claims abstract description 22
- 239000013598 vector Substances 0.000 claims description 26
- 230000000694 effects Effects 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 claims description 4
- 230000010354 integration Effects 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 15
- 230000006399 behavior Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000002354 daily effect Effects 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W8/00—Network data management
- H04W8/18—Processing of user or subscriber data, e.g. subscribed services, user preferences or user profiles; Transfer of user or subscriber data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Telephonic Communication Services (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The embodiment of the application provides a method, a device, equipment and a computer storage medium for judging the use of a number card, wherein the method comprises the following steps: extracting all the cards to be screened under the same identity card; judging and obtaining a main card and a non-main card according to the service information of the card to be screened; and judging and obtaining a number card using result according to the communication interaction information of the main card and the non-main card. According to the method for judging the use of the number card, the primary card and the non-primary card under one card and multiple numbers are prejudged according to the service information of the number card, and then the accurate judgment of the use condition of the number card is realized based on communication interaction information.
Description
Technical Field
The application belongs to the technical field of communication data analysis, and particularly relates to a number card use judgment method, device and equipment and a computer storage medium.
Background
With the continuous development of the business of operators, the card number resources cannot actually represent the real user resources. The current operation mode with the card number as the center is difficult to accurately evaluate the value and the demand of the customer, and marketing resources cannot be accurately put in.
The same natural person has the appearance of a plurality of telephone numbers, and the user uses the personal identification card to handle a plurality of number cards and then the service condition is comparatively complicated, probably gives the number card to the use of relatives, places in another cell-phone or idle in intelligent terminal etc. and is unfavorable for the operator to accurately locate and analyze the user. At present, the mode of identifying whether a plurality of mobile phone numbers belong to the same natural person mainly utilizes the identity card registration information, and the problem of low identification accuracy exists.
Therefore, how to accurately identify the user number card situation is a technical problem that needs to be solved by those skilled in the art.
Disclosure of Invention
The embodiment of the application provides a method, a device, equipment and a computer storage medium for judging the use of a number card, which can classify the number card under the existing identity card through daily business rules and accurately judge the use condition of the number card by combining the call similarity of users and the overlapping degree of active track base stations so as to realize the accurate marketing of first-line staff on multiple number card users in the market and save resource investment.
In a first aspect, an embodiment of the present application provides a method for determining usage of a number card, where the method includes:
extracting all the cards to be screened under the same identity card;
judging and obtaining a main card and a non-main card according to the service information of the card to be screened;
and judging and obtaining the number card using result according to the communication interaction information of the main card and the non-main card.
Further, according to the service information of the card to be screened, judging to obtain the main card, including:
judging the main package cost, ARPU of the month of 3 months, DOU of the month of 3 months and MOU of the month of 3 months, wherein the highest card is the main card;
and judging the number card which is transacted with the person who is required to transact business as the main card.
Further, judging to obtain a non-main card according to the service information of the card to be screened, including:
the method comprises the steps that a card to be screened is arranged in a multi-card terminal, and if a card with earlier registration time than the card to be screened exists, the card to be screened is judged to be a non-main card;
and judging that the calling card and the called card generate calling and called calls, and the number card with the average call time longer than the preset call time length is a non-calling card.
Further, according to the communication interaction information between the main card and the non-main card, judging to obtain a number card use result, including:
if the ratio of the non-answering behavior in the conversation behavior of the main card and the non-main card is larger than the preset non-answering threshold, judging that the main card and the non-main card are used by the same person;
if the ratio of the number of the opposite terminal dialed by the user is larger than the preset opposite terminal dialing threshold value, the main card and the non-main card are judged to be used by the same person.
Further, according to the communication interaction information between the main card and the non-main card, judging to obtain a number card use result, including:
acquiring base station data of a main card and a non-main card;
sequencing according to the occurrence times of the base stations, and respectively generating a frequent item set base station sequence list;
calculating a first overlap ratio of a base station frequent item set obtained by the main card and the non-main card;
and if the first contact ratio is greater than the preset activity contact ratio threshold, judging that the main card and the non-main card are used by the same person.
Further, the method further comprises the following steps: the resident base stations of the main card and the non-main card in a preset time period are respectively screened out;
judging the second degree of coincidence of the base station where the main card and the non-main card are located in the same time period;
and if the second overlapping degree is larger than the preset stay overlapping degree threshold value, judging that the main card and the non-main card are used by the same person.
Further, according to the communication interaction information of the main card and the non-main card, judging to obtain a number card using result, including:
screening a data set to be tested consisting of the number cards to be screened;
obtaining a non-main card user sample in a main card, and obtaining a model positive sample; obtaining a non-main card user sample in a non-main card, and obtaining a model negative sample;
respectively calculating the call similarity and the activity track base station coincidence degree of the model positive sample and the model negative sample with the main card;
based on the call similarity and the activity track base station coincidence ratio, establishing a number card recognition neural network model;
li Yonghao card identifies the neural network model, and processes the data set of the card to be screened to obtain the self-use probability vector;
and judging and obtaining a number card using result according to the self probability vector.
Further, respectively calculating the call similarity and the activity track base station coincidence degree of the model positive sample and the model negative sample with the main card, including:
and calculating the overlapping degree of the active track base stations by using an FP-Growth algorithm.
Further, the method further comprises the following steps:
adding a category identification vector into the data set to be detected to obtain a predicted data set; if the card to be screened is the same terminal number card as the main card, the category identification vector is 1; if not, the category identification vector is 0;
establishing an confusion matrix according to the prediction data set and the self-use probability vector;
and obtaining the accuracy rate, recall rate and accuracy rate of the number card using result according to the confusion matrix.
In a second aspect, an embodiment of the present application provides a device for determining usage of a number card, where the device includes:
the data acquisition module is used for extracting all the cards to be screened under the same identity card;
the business rule judging module is used for judging and obtaining the main card and the non-main card according to the business information of the card to be screened;
and the result judging module is used for judging and obtaining the number card using result according to the communication interaction information of the main card and the non-main card.
Further, the result judging module includes:
the communication similarity feature module is used for judging whether the main card and the non-main card are used by the same person according to communication interaction information of the main card and the non-main card;
and the active track base station contact ratio calculating module is used for judging whether the main card and the non-main card are used by the same person according to the contact ratio of the base station information of the main card and the non-main card.
Further, the method further comprises the following steps:
the feature integration model processing module is used for calculating and obtaining a personal card probability vector of the probability that the main card and the non-main card are used by the same person according to the data output by the call similarity feature module and the activity track base station overlap ratio calculation module;
and the effect verification module is used for obtaining the accuracy rate, recall rate and accuracy rate of the number card using result according to the personal card probability vector.
In a third aspect, an embodiment of the present application provides a device for determining usage of a number card, where the device includes:
a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the number card usage judgment method as described above.
In a fourth aspect, an embodiment of the present application provides a computer storage medium having stored thereon computer program instructions that when executed by a processor implement a method for determining usage of a number card as described above.
The method, the device, the equipment and the computer storage medium for judging the use of the number card can pre-judge the main card and the non-main card under one card with multiple numbers according to the service information of the number card, and then realize the accurate judgment of the use condition of the number card based on communication interaction information.
Drawings
In order to more clearly illustrate the technical solution of the embodiments of the present application, the drawings that are needed to be used in the embodiments of the present application will be briefly described, and it is possible for a person skilled in the art to obtain other drawings according to these drawings without inventive effort.
Fig. 1 is a flow chart of a method for judging use of a number card according to an embodiment of the present application;
fig. 2 is a schematic diagram of a voice similarity of a number card calculated in a number card use judging method according to an embodiment of the present application;
FIG. 3 is a diagram illustrating a prefix tree generated based on a base station sequence table in a method for determining use of a number card according to an embodiment of the present application;
FIG. 4 is a flowchart of a method for determining the usage of a number card according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a device for judging use of a number card according to an embodiment of the present application;
fig. 6 is a schematic structural diagram of a number card usage determining device according to an embodiment of the present application.
Detailed Description
Features and exemplary embodiments of various aspects of the present application will be described in detail below, and in order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described in further detail below with reference to the accompanying drawings and the detailed embodiments. It should be understood that the particular embodiments described herein are meant to be illustrative of the application only and not limiting. It will be apparent to one skilled in the art that the present application may be practiced without some of these specific details. The following description of the embodiments is merely intended to provide a better understanding of the application by showing examples of the application.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The prior art scheme is mainly applied to the fields of public security, banks and the like in the same person identification aspect, and has fewer references in the field of operators, and the natural person number card for one-card multi-card users has fewer using and discriminating methods. In the aspect of similarity evaluation among the user number cards, the prior technical scheme does not further carry out multidimensional mining on the conversation behavior and the position characteristics, and the conditions of no combination of the determined number card relation information and the service rule pre-judgment are identified, so that the judging mode is rough and single.
In order to solve the problems in the prior art, the embodiment of the application provides a method, a device, equipment and a computer storage medium for judging the use condition of a number card by a natural person facing a multi-card user.
According to the technical scheme, the natural person identification method based on the call similarity and the activity track is used for classifying the number cards under the existing identity card by combining the call similarity of the user and the activity track base station coincidence degree through daily business rules, accurately judging the service condition of the number cards of the one-card multi-card user, and facilitating the accurate marketing of first-line staff on the multi-number card user in the market so as to save resource investment.
The following first describes a method for using a one-card multi-card user number card provided by the embodiment of the application.
Fig. 1 is a flow chart illustrating a method for determining use of a number card according to an embodiment of the present application. As shown in fig. 1, the method may include the steps of:
s1: extracting all the cards to be screened under the same identity card;
extracting the mobile phone number card under the same identity card, namely the card to be screened, according to the mobile phone number information registered by the operator; and judging the use condition of the number card to be screened, and mainly judging whether the number card is used by the same person.
S2: judging and obtaining a main card and a non-main card according to the service information of the card to be screened;
usually, if the number card is used by the same person, the package cost of the main card is higher, and the package quantity is larger; therefore, the service condition of the number card can be estimated preliminarily according to the service information of the operator of the number card, and the main card and the non-main card can be judged preliminarily.
S3: and judging and obtaining the number card using result according to the communication interaction information of the main card and the non-main card.
And judging the obtained main card and the non-main card based on the mobile phone service information, and combining the communication information between the main card and the non-main card to obtain the service condition of the card to be screened.
For example, a user does not normally make or frequently make calls between own number cards, and if frequent calls exist between the main card and the non-main card, it can be stated that the main card and the non-main card are not used by the same person; in contrast, if no call exists between the main card and the non-main card, and the non-main card has no other communication record, the main card and the non-main card can be judged to be used by the same person.
According to the embodiment, the number cards under the existing identity cards are classified according to the determined number card relation information and business rules in combination with call lines, whether the number cards are used by the same person or not is accurately judged, and accurate marketing of market first-line personnel to multiple number card users is achieved, so that resource investment is saved.
In an embodiment of the present application, the judging of the service information of the card to be screened to obtain the main card may include: judging the main package cost, ARPU of the month of 3 months, DOU of the month of 3 months and MOU of the month of 3 months, wherein the highest card is the main card; and judging the number card which is transacted with the person who is required to transact business as the main card.
Judging that the active card and the non-active card can start from different dimensions:
the service information of the card to be screened is used as a judgment dimension for judging the main card and the non-main card, and the analysis and judgment can be rapidly carried out through the statistical data of the network operators. Where ARPU is average revenue from each user (ARPU-Average Revenue Per User), DOU is average per customer monthly traffic consumption (Discharge Of Usage), MOU is average per user monthly talk time (Minutes Of use). The highest number card among the main package cost, ARPU of 3 months, DOU of 3 months and MOU of 3 months can be judged as the main card.
The method also comprises the step of judging the number card which is transacted with the person in need of transacting business as a main card; and obtaining the main card, setting the main card on the multi-card terminal, and judging the mobile phone terminal IMEI number of the card to be screened as the owner card if the mobile phone terminal IMEI number of the card to be screened is consistent with the mobile phone terminal IMEI number corresponding to the main card.
Judging the non-main card according to the service information of the card to be screened, wherein the non-main card can comprise, but is not limited to, the following dimensions:
the method comprises the steps that a card to be screened is arranged in a multi-card terminal, and if a card with earlier registration time than the card to be screened exists, the card to be screened is judged to be a non-main card;
and judging that the calling card and the called card generate calling and called calls, and the number card with the average call time longer than the preset call time length is a non-calling card.
In this embodiment, the condition of the number card is simply and effectively determined primarily by the conditions of different dimensions.
Referring to fig. 3, fig. 2 is a schematic diagram showing similarity between a number card and a calculation card in a number card usage determining method according to an embodiment of the present application; in one embodiment of the present application, determining the number card usage result according to the communication interaction information between the main card and the non-main card may include:
if the ratio of the non-answering behavior in the conversation behavior of the main card and the non-main card is larger than the preset non-answering threshold, judging that the main card and the non-main card are used by the same person;
if the ratio of the number of the opposite terminal dialed by the user is larger than the preset opposite terminal dialing threshold value, the main card A and the non-main card B are judged to be used by the same person.
And can also be based on the call failure rate: and mining and distinguishing the user number card from the non-user number card based on the number of user calls, wherein if the proportion of the call behaviors of the two number cards is higher, the probability that the cards are used by the same person is higher. The calculation formula is as follows:
the times of the call behavior are represented, including the call answering situation and the call unanswered situation.
Call opposite end similarity: the more the number of the opposite terminal numbers dialed by the user is the same, the more similar the two number cards are proved to be in communication, and the higher the probability of being used by the same person is; the calculation formula is as follows:
and obtaining the classification of the main card and the non-main card according to the preliminary judgment result of the service information, and judging the service condition of the number card based on the communication data between the main card and the non-main card. The method is mainly used for judging whether the main card and the non-main card are used by the same person.
For example, if the same user uses the same identity card to transact two number cards in succession and uses the same person; for operators, if short message pushing marketing, telephone notification marketing and the like are carried out on all the number cards, manpower and material resources are definitely increased, and resource waste is caused. When the service condition of the number card is judged, only the main card is pushed, so that resources are saved and accurate marketing is realized.
Referring to fig. 2 to fig. 3, fig. 2 is a schematic diagram of similarity between calculated number cards in a number card usage determining method according to an embodiment of the present application, and fig. 3 is a prefix tree generated based on a base station sequence table in the number card usage determining method according to an embodiment of the present application;
in one embodiment of the application, the number card using result is judged and obtained according to the communication interaction information between the main card and the non-main card; specifically, the method for judging the mobile track base station according to the overlapping ratio of the active track base station between the active card and the non-active card comprises the following steps:
step N1: acquiring base station data of a main card and a non-main card;
for example: acquiring base station data of users every day, dividing a time period into 6 blocks, and selecting resident base stations of the users in the 6 time periods, wherein the resident base stations are shown in table 1:
| time period | Resident base station |
| 0 point to 4 points | A |
| 4-8 points | B |
| 8-12 points | C |
| 12-16 points | D |
| 16-20 points | E |
| 20 to 24 points | F |
Step N2: sequencing according to the occurrence times of the base stations, and respectively generating a frequent item set base station sequence list;
the method comprises the steps of utilizing a neural network algorithm to mine a frequent item set, sorting a base station sequence table every day for the base station conditions of n days, sorting according to base station sequence information and the occurrence times, eliminating base stations with the occurrence times less than n times, and generating a frequent item set base station sequence table as shown in table 2:
| days (days) | Base station screening |
| 1 | {F，D，E} |
| 2 | {F，D，E} |
| 3 | {F，D，E} |
| 4 | {F，D，E，B} |
| 5 | {F，D，B} |
| 6 | {F，A} |
| … | … |
| n | {F，M} |
Step N3: calculating a first overlap ratio of a base station frequent item set obtained by the main card and the non-main card;
in the step N3, frequent item sets can be mined by utilizing an FP-Growth algorithm for calculating the contact ratio; according to the generated base station sequence table, a prefix tree T is established, and according to the first 5 days (set as working days) of the table, the table is shown in figure 3;
step N4: depth-first traversing T to finally obtain a base station frequent item set P1 = { { F, D }, { F, D, E }, and similarly calculating a base station frequent item set P2 of the workday activity track of the second number;
step N5: calculating the coincidence ratio of the frequent item sets P1 and P2 of the base station, and calculating the coincidence ratio as shown in a formula (1):
step N6: calculating according to the steps N1-N5 to obtain the coincidence ratio values of the working days, the Saturday and the sunday of the two mobile phone numbers, and outputting and forming three dimension indexes: the overlap ratio of the frequent item sets of the workday base station, the overlap ratio of the frequent item sets of the Saturday base station and the overlap ratio of the frequent item sets of the Sunday base station.
If the overlapping ratio of the base stations of the moving track of the two cards is higher, the probability of being used by the same person is higher; specifically, if the contact ratio is greater than a preset activity contact ratio threshold, the main card and the non-main card are judged to be used by the same person.
In one embodiment of the present application, the determination may be made according to the dwell track base station overlap ratio between the active card and the inactive card:
the resident base stations of the main card and the non-main card in a preset time period are respectively screened out;
judging the second degree of coincidence of the base station where the main card and the non-main card are located in the same time period;
and if the second overlapping degree is larger than the preset stay overlapping degree threshold value, judging that the main card and the non-main card are used by the same person.
For example: and calculating and acquiring the base station with the longest residence time in three time periods of busy hours, idle hours and weekends of the working days of the two mobile phone numbers. And (3) injection: the busy day is 7:00am-7:00pm, and the idle day is 7:00pm-7:00am;
the method comprises the steps of respectively matching whether the numbers of the resident base stations in three time periods of busy hours, idle hours and weekends of two mobile phone numbers are consistent, outputting 1 if the numbers are consistent, outputting 0 if the numbers are inconsistent, and outputting to form three dimension indexes: whether the resident base stations are consistent in busy days and idle days, and whether the resident base stations are consistent in weekend days. If the stay track base stations tend to be consistent, the probability of being used by the same person is higher. If the overlapping ratio of the base stations of the moving track of the two cards is higher, the probability of being used by the same person is higher; specifically, if the contact ratio is greater than a preset activity contact ratio threshold, the main card and the non-main card are judged to be used by the same person.
Starting from two dimensions of a flowing track and a staying track, the flowing track is based on a track chain of the current day behavior of a user, the frequent item sets of the base stations of the working days, the Saturday and the sunday of the user are mined through an FP-Growth algorithm, and then the coincidence degree of the frequent item sets of the base stations of two numbers (a main card and a non-main card) is calculated through a coincidence degree formula; the stay base station is used for firstly excavating the resident base stations of the user during busy hours, idle hours and weekends, and then comparing whether the resident base stations of the two numbers are consistent or not, and is used as a basis for judging whether the resident base stations are used by the same person or not.
Referring to fig. 4, fig. 4 is a flowchart of a method for determining usage of a number card according to an embodiment of the present application; in one embodiment of the application, the call similarity characteristics and the contact ratio of the active track base station are integrated on the basis of the number card service information, so as to obtain the probability that the number card is used by the same person. The method can comprise the following steps:
step one: integrating the call similarity characteristics and the data of the activity track base station coincidence degree calculation as a sample to be predictedWherein S is 1 Is a card to be screened under the same identity card, S 3 The number card is not a main card and a non-main card; />m 2 For the sample size, n 1 A field feature number;
step two: screening data set S 1 Non-active card sample S in (1) 2 Obtaining a model positive sample A 1 The method comprises the steps of carrying out a first treatment on the surface of the Screening data set S 2 Obtaining a negative model sample B 1 ；
Step three: based on input positive sample A 1 And negative sample B 1 The data set is used for respectively calculating the call similarity with the main card number and the overlap ratio of the active track base station, and outputting a modeling sample as sample characteristics of a model training test
Step four: inputting a modeling sample B, dividing the modeling sample AB in a ratio of 7:3 to obtain a model training set A 11 、B 11 Model test set A 12 、B 12 ；
Step five: using logistic regression, random forest or GBDT classification algorithms, the training data set A is input 11 And B 11 Model training is performed, and a data set A is tested 12 、B 12 Adjusting optimal parameters and outputting a natural person identification model;
step six: and predicting the data to be predicted in the personal card recognition model of the data set C, outputting a personal card probability vector, and outputting a prediction result of the model.
According to the embodiment, through the service characteristic data and combining with the call behavior similarity and the track overlap ratio condition between the user number cards, the identification models of the personal use number card and the non-personal use number card for the multi-card user are constructed, the identification problem of whether the user uses the number card under one card of the multi-card user is solved, and the natural personal use number card identification function for the one card of the multi-card user is realized.
In one embodiment of the present application, there is also provided a method for verifying an upper prediction result, including the steps of:
inputting a data set C to be predicted and a personal card probability vector p 1 Output diePrediction effect of model.
Step one: adding a row of real category identification vectors y into the data set C to be predicted, if the number card is the same as the main card S 1 If the number is the number of the same terminal, the true category identification vector y=1, if the number is not y=0, the new data set is marked as D;
step two: obtaining a prediction result vector p through the last module 1 Establishing a confusion matrix with the true category identification vector y of the data set D, wherein the confusion matrix is formatted as follows (table 3):
step three: precision (Precision) and Recall (Recall) were calculated as follows (equation 2-equation 3):
step four: and verifying the prediction result of the use condition of the number card according to the precision rate and the recall rate.
The embodiment provides that the primary card and the non-primary card under one license and multiple numbers are pre-judged according to the service information of the number cards, and then the accurate judgment of the service condition of the number cards is realized based on the communication interaction information. Combines the call behavior similarity and the track overlap ratio between the user number cards to construct a number card discrimination model for the personal use and the non-personal use of the multi-card user, solves the recognition problem of whether the number card of the multi-card user is used by the user, the natural person using number card screening function for the one-card multi-card user is realized, whether the number card is used by the same person or not is accurately judged, and the accurate marketing of market first-line personnel to the multi-number card user is realized, so that the resource investment is saved.
Fig. 5 is a schematic structural diagram of a device for determining use of a number card according to an embodiment of the present application. As shown in fig. 5, the apparatus may include a data acquisition module 210, a business rule determination module 220, a result determination module 230, a feature integration model processing module 240, and an effect verification module 250.
The data acquisition module 210 is configured to extract all the cards to be screened under the same identity card;
the service rule judging module 220 is configured to judge, according to the service information of the card to be screened, to obtain a main card and a non-main card;
the result judging module 230 is configured to judge, according to the communication interaction information of the main card and the non-main card, a number card usage result.
The result judgment module 230 includes:
a call similarity feature unit 231 configured to determine whether the main card and the non-main card are used by the same person according to communication interaction information of the main card and the non-main card;
and the activity track base station contact ratio calculating unit 232 is used for judging whether the main card and the non-main card are used by the same person according to the contact ratio of the base station information of the main card and the non-main card.
The feature integration model processing module 240 is configured to calculate, according to the data output by the call similarity feature module and the activity track base station overlap ratio calculating module, a personal card probability vector of the probability that the main card and the non-main card are used by the same person;
the effect verification module 250 is configured to obtain the accuracy rate, recall rate and accuracy rate of the number card use result according to the probability vector of the personal card.
The respective modules/units in the apparatus shown in fig. 5 have functions of implementing the respective steps in fig. 1 to 4, and achieve the corresponding technical effects, and are not described herein for brevity.
Fig. 6 is a schematic diagram of a hardware structure of a number card usage determining device according to an embodiment of the present application.
The in-number card use determination device may include a processor 301 and a memory 302 storing computer program instructions.
In particular, the processor 301 may include a central processing unit (Central Processing Unit, CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured as one or more integrated circuits implementing embodiments of the present application.
Memory 302 may include mass storage for data or instructions. By way of example, and not limitation, memory 302 may comprise a Hard Disk Drive (HDD), floppy Disk Drive, flash memory, optical Disk, magneto-optical Disk, magnetic tape, or universal serial bus (Universal Serial Bus, USB) Drive, or a combination of two or more of the foregoing. In one example, memory 302 may include removable or non-removable (or fixed) media, or memory 302 may be a non-volatile solid state memory. Memory 302 may be internal or external to the integrated gateway disaster recovery device.
In one example, memory 302 may be Read Only Memory (ROM). In one example, the ROM may be mask-programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically Erasable PROM (EEPROM), electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.
Memory 302 may include Read Only Memory (ROM), random Access Memory (RAM), magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical, or other physical/tangible memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors) it is operable to perform the operations described with reference to methods in accordance with aspects of the present disclosure.
The processor 301 reads and executes the computer program instructions stored in the memory 302 to implement the methods/steps S1 to S4 in the embodiments shown in fig. 1 to 4, and achieve the corresponding technical effects achieved by executing the methods/steps in the embodiments shown in fig. 1 to 4, which are not described herein for brevity.
In addition, in combination with the number card usage judgment method in the above embodiment, the embodiment of the present application may be implemented by providing a computer storage medium. The computer storage medium has stored thereon computer program instructions; the computer program instructions, when executed by the processor, implement any of the card usage judgment methods of the above embodiments.
It should be understood that the application is not limited to the particular arrangements and instrumentality described above and shown in the drawings. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between steps, after appreciating the spirit of the present application.
The functional blocks shown in the above-described structural block diagrams may be implemented in hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), suitable firmware, a plug-in, a function card, or the like. When implemented in software, the elements of the application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine readable medium or transmitted over transmission media or communication links by a data signal carried in a carrier wave. A "machine-readable medium" may include any medium that can store or transfer information. Examples of machine-readable media include electronic circuitry, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and the like. The code segments may be downloaded via computer networks such as the internet, intranets, etc.
It should also be noted that the exemplary embodiments mentioned in this disclosure describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above-described steps, that is, the steps may be performed in the order mentioned in the embodiments, or may be performed in a different order from the order in the embodiments, or several steps may be performed simultaneously.
Aspects of the present disclosure are described above 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 block of the flowchart illustrations and/or block diagrams, and combinations of 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, 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, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to being, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware which performs the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In the foregoing, only the specific embodiments of the present application are described, and it will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the systems, modules and units described above may refer to the corresponding processes in the foregoing method embodiments, which are not repeated herein. It should be understood that the scope of the present application is not limited thereto, and any equivalent modifications or substitutions can be easily made by those skilled in the art within the technical scope of the present application, and they should be included in the scope of the present application.
Claims (13)
1. A number card use judging method is characterized by comprising the following steps:
extracting all the cards to be screened under the same identity card;
judging and obtaining a main card and a non-main card according to the service information of the card to be screened;
judging and obtaining a number card using result according to the communication interaction information of the main card and the non-main card;
the method for judging and obtaining the number card using result according to the communication interaction information of the main card and the non-main card comprises the following steps:
screening the data set to be tested consisting of the cards to be screened;
obtaining a non-main card user sample in the main card, and obtaining a model positive sample; obtaining a non-main card user sample in the non-main card, and obtaining a model negative sample;
respectively calculating call similarity and activity track base station coincidence degrees of the model positive sample and the model negative sample with a main card;
based on the call similarity and the active track base station overlap ratio, establishing a number card recognition neural network model;
the number card is utilized to identify a neural network model, and the data set of the number card to be screened is processed to obtain a self-use probability vector;
and judging and obtaining a number card using result according to the self probability vector.
2. The method for judging the use of a card according to claim 1, wherein judging to obtain the main card according to the service information of the card to be screened comprises:
judging the main package cost, ARPU of the month of 3 months, DOU of the month of 3 months and MOU of the month of 3 months, wherein the highest card is the main card;
or, the number card which is required to transact business by the user is judged as the main card.
3. The method for judging the use of a card according to claim 1, wherein judging to obtain a non-main card according to the service information of the card to be screened comprises:
the card to be screened is in the multi-card terminal, and if the card with the registration time earlier than that of the card to be screened exists, the card to be screened is judged to be a non-main card;
and judging to obtain a number card using result according to the communication interaction information of the main card and the non-main card, and further comprising:
if the non-main card and the main card generate main and called calls and the average call time is longer than the preset call time, judging that the main card and the non-main card are not used by the same person.
4. The method according to claim 1, wherein the step of determining a result of use of the number card based on communication interaction information between the main card and the non-main card, further comprises:
if the ratio of the number of times of non-answering in the number of times of talking between the main card and the non-main card is greater than a preset non-answering ratio threshold, judging that the main card and the non-main card are used by the same person;
if the ratio of the number of the opposite terminal dialed by the user is larger than the preset threshold value of the dialing ratio of the opposite terminal, the main card and the non-main card are judged to be used by the same person.
5. The method according to claim 1, wherein the step of determining a result of use of the number card based on communication interaction information between the main card and the non-main card, further comprises:
acquiring base station data of the main card and the non-main card;
sequencing according to the occurrence times of the base stations, and respectively generating a frequent item set base station sequence list;
calculating a first coincidence degree of a base station frequent item set where the main card and the non-main card are positioned;
and if the first contact ratio is larger than a preset activity contact ratio threshold value, judging that the main card and the non-main card are used by the same person.
6. The method for determining the use of a badge as in claim 5, further comprising:
the resident base stations of the main card and the non-main card in a preset time period are respectively screened out;
judging the second degree of coincidence of the resident base station where the main card and the non-main card are positioned in the same time period;
and if the second overlapping degree is larger than a preset stay overlapping degree threshold value, judging that the main card and the non-main card are used by the same person.
7. The method for determining the usage of a card according to claim 1, wherein calculating call similarity and activity trajectory base station overlap ratio between the model positive sample and the model negative sample and the main card, respectively, comprises:
and calculating the overlapping degree of the movable track base station by using an FP-Growth algorithm.
8. The method of determining the use of a badge as in claim 1, further comprising:
adding a category identification vector into the data set to be detected to obtain a predicted data set; if the card to be screened is the same terminal card as the main card, the category identification vector is 1; if not, the category identification vector is 0;
establishing an confusion matrix according to the prediction data set and the self probability vector;
and obtaining the precision and recall ratio of the number card using result according to the confusion matrix.
9. A card use judgment device, characterized by comprising:
the data acquisition module is used for extracting all the cards to be screened under the same identity card;
the business rule judging module is used for judging and obtaining a main card and a non-main card according to the business information of the card to be screened;
the result judging module is used for judging and obtaining the number card using result according to the communication interaction information of the main card and the non-main card;
the result judging module is specifically used for screening the data set to be tested consisting of the number cards to be screened; obtaining a non-main card user sample in the main card, and obtaining a model positive sample; obtaining a non-main card user sample in the non-main card, and obtaining a model negative sample; respectively calculating call similarity and activity track base station coincidence degrees of the model positive sample and the model negative sample with a main card; based on the call similarity and the active track base station overlap ratio, establishing a number card recognition neural network model; the number card is utilized to identify a neural network model, and the data set of the number card to be screened is processed to obtain a self-use probability vector; and judging and obtaining a number card using result according to the self probability vector.
10. The card use judgment device according to claim 9, wherein the result judgment module includes:
the communication similarity feature module is used for judging whether the main card and the non-main card are used by the same person or not according to the communication interaction information of the main card and the non-main card;
and the active track base station contact ratio calculation module is used for judging whether the active card and the non-active card are used by the same person according to the contact ratio of the base station information of the active card and the non-active card.
11. The card use judgment device according to claim 10, further comprising:
the feature integration model processing module is used for calculating and obtaining a personal card probability vector of the probability that the main card and the non-main card are used by the same person according to the data output by the call similarity feature module and the activity track base station coincidence degree calculating module;
and the effect verification module is used for obtaining the precision and recall ratio of the number card using result according to the personal card probability vector.
12. A number card usage judgment device, characterized in that the device comprises: a processor and a memory storing computer program instructions; the processor reads and executes the computer program instructions to implement the method for determining the use of a badge as set forth in any one of claims 1 to 8.
13. A computer storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method of determining the use of a badge as claimed in any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011308195.8A CN114520969B (en) | 2020-11-20 | 2020-11-20 | Method, device and equipment for judging number card use and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011308195.8A CN114520969B (en) | 2020-11-20 | 2020-11-20 | Method, device and equipment for judging number card use and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114520969A CN114520969A (en) | 2022-05-20 |
| CN114520969B true CN114520969B (en) | 2023-10-27 |
Family
ID=81595401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011308195.8A Active CN114520969B (en) | 2020-11-20 | 2020-11-20 | Method, device and equipment for judging number card use and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114520969B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013093555A1 (en) * | 2011-12-21 | 2013-06-27 | Nokia Corporation | An apparatus and method for identifying a plurality of network service cards available for use in a portable communication device |
| CN103841550A (en) * | 2012-11-21 | 2014-06-04 | ***通信集团吉林有限公司 | Method and device for identifying multi-card user |
| US9710636B1 (en) * | 2016-10-20 | 2017-07-18 | International Business Machines Corporation | Digital identity card management |
| CN108990061A (en) * | 2018-07-09 | 2018-12-11 | 中国联合网络通信集团有限公司 | A kind of identification card number anti-theft method, apparatus and system |
| CN109067640A (en) * | 2018-08-29 | 2018-12-21 | 中国联合网络通信集团有限公司 | The method and device of information push |
| CN110633642A (en) * | 2019-08-14 | 2019-12-31 | 深圳市天彦通信股份有限公司 | Identity information verification method and device, terminal equipment and storage medium |
| CN111314851A (en) * | 2018-12-12 | 2020-06-19 | ***通信集团北京有限公司 | Method and device for identifying one person with multiple numbers |
| CN111436017A (en) * | 2018-12-25 | 2020-07-21 | 北京融信数联科技有限公司 | One-person multi-card identification method for mobile users based on clustering algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105872998A (en) * | 2015-12-31 | 2016-08-17 | 乐视移动智能信息技术（北京）有限公司 | Method and system for realizing automatic call forwarding on dual-card dual-standby mobile phone |
-
2020
- 2020-11-20 CN CN202011308195.8A patent/CN114520969B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013093555A1 (en) * | 2011-12-21 | 2013-06-27 | Nokia Corporation | An apparatus and method for identifying a plurality of network service cards available for use in a portable communication device |
| CN103841550A (en) * | 2012-11-21 | 2014-06-04 | ***通信集团吉林有限公司 | Method and device for identifying multi-card user |
| US9710636B1 (en) * | 2016-10-20 | 2017-07-18 | International Business Machines Corporation | Digital identity card management |
| CN108990061A (en) * | 2018-07-09 | 2018-12-11 | 中国联合网络通信集团有限公司 | A kind of identification card number anti-theft method, apparatus and system |
| CN109067640A (en) * | 2018-08-29 | 2018-12-21 | 中国联合网络通信集团有限公司 | The method and device of information push |
| CN111314851A (en) * | 2018-12-12 | 2020-06-19 | ***通信集团北京有限公司 | Method and device for identifying one person with multiple numbers |
| CN111436017A (en) * | 2018-12-25 | 2020-07-21 | 北京融信数联科技有限公司 | One-person multi-card identification method for mobile users based on clustering algorithm |
| CN110633642A (en) * | 2019-08-14 | 2019-12-31 | 深圳市天彦通信股份有限公司 | Identity information verification method and device, terminal equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114520969A (en) | 2022-05-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107248082B (en) | Card maintenance identification method and device | |
| CN106778876B (en) | User classification method and system based on mobile user track similarity | |
| WO2017186090A1 (en) | Communication number processing method and apparatus | |
| CN109640312B (en) | 'Black card' identification method, electronic equipment and computer readable storage medium | |
| CN111222025A (en) | Fraud number identification method and system based on convolutional neural network | |
| CN109688275A (en) | Harassing call recognition methods, device and storage medium | |
| CN110213448B (en) | Malicious number identification method and device, storage medium and computer equipment | |
| CN107092651B (en) | Key character mining method and system based on communication network data analysis | |
| CN111510368B (en) | Family group identification method, device, equipment and computer readable storage medium | |
| CN113961712B (en) | Knowledge-graph-based fraud telephone analysis method | |
| CN111127062A (en) | Group fraud identification method and device based on space search algorithm | |
| CN109474755B (en) | Abnormal telephone active prediction method, system and computer readable storage medium based on sequencing learning and ensemble learning | |
| CN109274834B (en) | Express number identification method based on call behavior | |
| CN113205129B (en) | Cheating group identification method and device, electronic equipment and storage medium | |
| CN114520969B (en) | Method, device and equipment for judging number card use and computer storage medium | |
| CN110677269A (en) | Method and device for determining communication user relationship and computer readable storage medium | |
| CN109525739B (en) | Telephone number identification method and device and server | |
| CN110213449B (en) | Method for identifying roaming fraud number | |
| CN114449106B (en) | Method, device, equipment and storage medium for identifying abnormal telephone number | |
| CN114723554B (en) | Abnormal account identification method and device | |
| CN113194458B (en) | Multi-card treasure number identification method and device | |
| CN113011503B (en) | Data evidence obtaining method of electronic equipment, storage medium and terminal | |
| CN115659217A (en) | Fraud recognition model training method and device, electronic equipment and storage medium | |
| CN115099934A (en) | High-latency customer identification method, electronic equipment and storage medium | |
| CN108564380B (en) | Telecommunication user classification method based on iterative decision tree |
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 |