CN108055661B - Telephone number blacklist establishing method and device based on communication network - Google Patents

Telephone number blacklist establishing method and device based on communication network Download PDF

Info

Publication number
CN108055661B
CN108055661B CN201711275807.6A CN201711275807A CN108055661B CN 108055661 B CN108055661 B CN 108055661B CN 201711275807 A CN201711275807 A CN 201711275807A CN 108055661 B CN108055661 B CN 108055661B
Authority
CN
China
Prior art keywords
imei
telephone numbers
corresponding relation
telephone
user equipment
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.)
Expired - Fee Related
Application number
CN201711275807.6A
Other languages
Chinese (zh)
Other versions
CN108055661A (en
Inventor
卢禹锟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Qihoo Technology Co Ltd
Original Assignee
Beijing Qihoo Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Qihoo Technology Co Ltd filed Critical Beijing Qihoo Technology Co Ltd
Priority to CN201711275807.6A priority Critical patent/CN108055661B/en
Publication of CN108055661A publication Critical patent/CN108055661A/en
Application granted granted Critical
Publication of CN108055661B publication Critical patent/CN108055661B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W8/00—Network data management
    • H04W8/26—Network addressing or numbering for mobility support
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
    • H04W12/12—Detection or prevention of fraud

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computer Security & Cryptography (AREA)
  • Databases & Information Systems (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The invention discloses a method and a device for establishing a phone number blacklist based on a communication network, wherein the method comprises the following steps: establishing a first corresponding relation between a telephone number and an IMEI by collecting the IMEI of user equipment and a call record corresponding to the IMEI; scoring the IMEI according to attribute information of a plurality of dimensions of the IMEI, and obtaining statistical characteristics of the telephone number according to scoring results; obtaining a second corresponding relation between the telephone numbers according to the first corresponding relation between the telephone numbers and the IMEI; calculating scores of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers; and establishing a phone number blacklist according to the scores of all phone numbers. Under the condition of protecting the privacy of the user, the invention establishes various corresponding relations among the telephone numbers by utilizing the collected IMEI of the user equipment and the corresponding call records. And calculating and scoring according to the statistical characteristics of the telephone numbers and the corresponding relation between the telephone numbers so as to obtain a telephone number blacklist.

Description

Telephone number blacklist establishing method and device based on communication network
Technical Field
The invention relates to the field of communication, in particular to a method and a device for establishing a phone number blacklist based on a communication network.
Background
At present, the financial loan business develops rapidly, particularly the short-term small loan business, because of the lower amount, does not need guarantee and mortgage, the procedure is simple, the loan can be issued quickly, the loan user can obtain the money conveniently and quickly, and the user demand is solved. For the financial platform, the loan amount is small, theoretically, the loan users have repayment capacity, and the credit judgment of a single loan user is biased to the repayment willingness degree of the loan user. However, when the loan user is actually a fraudulent user, the key to the financial loan schedule is to detect users who have a history of fraud and not to pay those users.
In the prior art, when detecting whether a loan user is a fraud user, direct communication contact between a mobile phone number and a mobile phone number is obtained generally by obtaining address book information of the loan user, and whether the loan user is a possible fraud user is judged according to the communication contact. The obtaining of the address book information of the loan user relates to the privacy information of the loan user, so that a method for judging the user based on a communication network and establishing a telephone number blacklist to better identify the user is needed on the premise of protecting the privacy of the user.
Disclosure of Invention
In view of the above, the present invention has been made to provide a method and apparatus for establishing a blacklist of telephone numbers based on a communication network that overcomes or at least partially solves the above-mentioned problems.
According to an aspect of the present invention, there is provided a phone number blacklist establishing method based on a communication network, including:
establishing a first corresponding relation between a telephone number and an IMEI by collecting the IMEI of user equipment and a call record corresponding to the IMEI; the first corresponding relation is the corresponding relation between a telephone number and n IMEIs, wherein n is greater than or equal to 1;
scoring the IMEI according to attribute information of a plurality of dimensions of the IMEI, and obtaining statistical characteristics of the telephone number according to scoring results;
obtaining a second corresponding relation between the telephone numbers according to the first corresponding relation between the telephone numbers and the IMEI; the second corresponding relation is specifically the corresponding relation between one telephone number and m telephone numbers, and m is greater than or equal to 1;
calculating scores of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers;
and establishing a phone number blacklist according to the scores of all phone numbers.
Optionally, the establishing the first corresponding relationship between the phone number and the IMEI by collecting the IMEI of the user equipment and the call record corresponding thereto further includes:
collecting the IMEI of the user equipment;
according to the IMEI of the user equipment, collecting the call records of the user equipment, obtaining the telephone number of the incoming call and/or the outgoing call of the user equipment, and establishing a third corresponding relation between the IMEI and the telephone number of the incoming call and/or the outgoing call of the user equipment; wherein, the third corresponding relation is the corresponding relation between an IMEI and d telephone numbers, and d is greater than or equal to 1;
and establishing a first corresponding relation between the telephone number and the IMEI according to the third corresponding relation.
Optionally, the method further comprises: collecting attribute information of a plurality of dimensions of the IMEI;
wherein, the attribute information of a plurality of dimensions of IMEI comprises the attribute information of at least one of the following dimensions:
user behavior information in user equipment corresponding to the IMEI;
the information of the installed application list in the user equipment corresponding to the IMEI;
information whether the IMEI belongs to the IMEI blacklist.
Optionally, obtaining the second corresponding relationship between the phone numbers according to the first corresponding relationship between the phone numbers and the IMEI further includes:
collecting telephone numbers used by user equipment corresponding to the IMEI, and extracting the IMEI with one-to-one correspondence and the telephone numbers used by the user equipment corresponding to the IMEI;
in the first corresponding relation, the IMEI is replaced by the telephone number which has one-to-one corresponding relation with the IMEI, and a second corresponding relation between the telephone numbers is obtained.
Optionally, the method further comprises:
and further obtaining a second corresponding relation between the telephone numbers by collecting the call records between the telephone numbers.
Optionally, the method further comprises: acquiring label information of part of telephone numbers from a cloud database, and pre-labeling and scoring the part of telephone numbers according to the label information;
calculating the scores of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers specifically comprises the following steps:
and using a machine learning algorithm, taking the pre-labeled scores of part of the telephone numbers as learning targets, and calculating the scores of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers.
Optionally, the method further comprises: and according to the part of telephone numbers with the pre-labeled scores and the second corresponding relation between the telephone numbers, carrying out community division on the corresponding telephone numbers, and taking the result of the community division as the input information of the machine learning algorithm.
According to another aspect of the present invention, there is provided a phone number blacklist establishing apparatus based on a communication network, including:
the first relation module is suitable for establishing a first corresponding relation between the telephone number and the IMEI by collecting the IMEI of the user equipment and the corresponding call records; the first corresponding relation is the corresponding relation between a telephone number and n IMEIs, wherein n is greater than or equal to 1;
the first grading module is suitable for grading the IMEI according to the attribute information of a plurality of dimensions of the IMEI and obtaining the statistical characteristics of the telephone number according to the grading result;
the second relation module is suitable for obtaining a second corresponding relation between the telephone numbers according to the first corresponding relation between the telephone numbers and the IMEI; the second corresponding relation is specifically the corresponding relation between one telephone number and m telephone numbers, and m is greater than or equal to 1;
the second grading module is suitable for calculating grades of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers;
and the blacklist module is suitable for establishing a telephone number blacklist according to the scores of all telephone numbers.
Optionally, the first relation module further comprises:
the first collecting unit is suitable for collecting the IMEI of the user equipment;
the second collecting unit is suitable for collecting the call records of the user equipment according to the IMEI of the user equipment, obtaining the telephone number of the incoming call and/or the outgoing call generated by the user equipment, and establishing a third corresponding relation between the IMEI and the telephone number of the incoming call and/or the outgoing call generated by the user equipment; wherein, the third corresponding relation is the corresponding relation between an IMEI and d telephone numbers, and d is greater than or equal to 1;
and the corresponding unit is suitable for establishing the first corresponding relation between the telephone number and the IMEI according to the third corresponding relation.
Optionally, the apparatus further comprises:
the attribute acquisition module is suitable for collecting attribute information of a plurality of dimensions of the IMEI;
wherein, the attribute information of a plurality of dimensions of IMEI comprises the attribute information of at least one of the following dimensions:
user behavior information in user equipment corresponding to the IMEI;
the information of the installed application list in the user equipment corresponding to the IMEI;
information whether the IMEI belongs to the IMEI blacklist.
Optionally, the second relationship module is further adapted to:
collecting telephone numbers used by user equipment corresponding to the IMEI, and extracting the IMEI with one-to-one correspondence and the telephone numbers used by the user equipment corresponding to the IMEI; in the first corresponding relation, the IMEI is replaced by the telephone number which has one-to-one corresponding relation with the IMEI, and a second corresponding relation between the telephone numbers is obtained.
Optionally, the apparatus further comprises:
and the call collection module is suitable for further obtaining a second corresponding relation between the telephone numbers by collecting call records among the telephone numbers.
Optionally, the apparatus further comprises:
the pre-labeling collection module is suitable for acquiring label information of part of telephone numbers from the cloud database and pre-labeling and scoring the part of the telephone numbers according to the label information;
the second scoring module is further adapted to:
and using a machine learning algorithm, taking the pre-labeled scores of part of the telephone numbers as learning targets, and calculating the scores of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers.
Optionally, the method further comprises:
and the community division module is suitable for carrying out community division on the corresponding telephone numbers according to the part of the telephone numbers with the pre-labeled scores and the second corresponding relation between the telephone numbers, and taking the result of the community division as the input information of the machine learning algorithm.
According to yet another aspect of the present invention, there is provided a computing device comprising: the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the telephone number blacklist establishing method based on the communication network.
According to still another aspect of the present invention, there is provided a computer storage medium having at least one executable instruction stored therein, where the executable instruction causes a processor to perform operations corresponding to the above method for establishing a phone number blacklist based on a communication network.
According to the method and the device for establishing the blacklist of the telephone numbers based on the communication network, a first corresponding relation between the telephone numbers and the IMEI is established by collecting the IMEI of the user equipment and the corresponding call records; the first corresponding relation is the corresponding relation between a telephone number and n IMEIs, wherein n is greater than or equal to 1; scoring the IMEI according to attribute information of a plurality of dimensions of the IMEI, and obtaining statistical characteristics of the telephone number according to scoring results; obtaining a second corresponding relation between the telephone numbers according to the first corresponding relation between the telephone numbers and the IMEI; the second corresponding relation is specifically the corresponding relation between one telephone number and m telephone numbers, and m is greater than or equal to 1; calculating scores of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers; and establishing a phone number blacklist according to the scores of all phone numbers. Under the condition of protecting the privacy of the user, the invention establishes various corresponding relations among the telephone numbers by utilizing the collected IMEI of the user equipment and the corresponding call records. And calculating and scoring according to the statistical characteristics of the telephone numbers and the corresponding relation between the telephone numbers so as to obtain a telephone number blacklist. The invention greatly reduces the exposure rate of the privacy information of the user and reduces the possible privacy disclosure risk. Meanwhile, a machine learning algorithm is combined with the statistical characteristics of the telephone numbers to learn, so that the scores of the telephone numbers are effectively obtained, and a telephone number blacklist is conveniently established.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 shows a flow chart of a method for establishing a blacklist of telephone numbers based on a communication network according to an embodiment of the present invention;
fig. 2 shows a flow chart of a method for establishing a blacklist of telephone numbers based on a communication network according to another embodiment of the present invention;
fig. 3 shows a functional block diagram of a communication network based phone number blacklist establishing apparatus according to an embodiment of the present invention;
fig. 4 shows a functional block diagram of a communication network based phone number blacklist establishing apparatus according to another embodiment of the present invention;
FIG. 5 illustrates a schematic structural diagram of a computing device, according to an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Fig. 1 shows a flow chart of a method for establishing a phone number blacklist based on a communication network according to an embodiment of the present invention. As shown in fig. 1, the method for establishing the phone number blacklist based on the communication network specifically includes the following steps:
step S101, a first corresponding relation between a telephone number and an IMEI is established by collecting the IMEI of the user equipment and a call record corresponding to the IMEI.
The IMEI (International Mobile Equipment Identity) is an "electronic serial number" consisting of 15 digits, which corresponds to each Mobile user Equipment one to one, and is unique worldwide. A mobile user equipment corresponds to a unique IMEI.
The IMEI of the user equipment is collected, and the call records corresponding to the user equipment, namely the call records of incoming calls, outgoing calls, short message receiving and short message sending related to the IMEI of the user equipment, are collected at the same time, so that the telephone number which is in incoming call and/or outgoing call relation with the user equipment is obtained. According to the IMEI of the user equipment and the obtained telephone number in incoming and/or outgoing call relation with the user equipment, a third correspondence between the IMEI and the telephone number in incoming and/or outgoing call relation with the user equipment can be established. The third corresponding relationship is a corresponding relationship between an IMEI and d phone numbers, where d is greater than or equal to 1. The data shown in table 1 is obtained from the IMEI and the telephone number corresponding to the IMEI.
Specifically, as shown in table 1:
IMEI1 telephone number 1 Telephone number 2 ……
IMEI2 Telephone number 2 Telephone number 5 ……
IMEI3 Telephone number 1 Telephone number 3 ……
IMEI4 Telephone number 4 Telephone number 5 ……
…… …… …… ……
TABLE 1
Column 1 is the IMEI of each user equipment, and columns 2 and later are one or more telephone numbers which are used for generating incoming call and/or outgoing call relations with the user equipment corresponding to the IMEI in column 1. From the data in table 1, a third correspondence can be obtained, i.e. IMEI 1: telephone number 1, telephone number 2, … …; IMEI 2: phone number 2, phone number 5, … …; IMEI 3: telephone number 1, telephone number 3, … …; IMEI 4: phone number 4, phone number 5, … …. The third corresponding relation is that the IMEI is taken as the center, and the telephone number related to the IMEI is counted.
According to the third correspondence, a first correspondence of the telephone number and the IMEI may be established. The first corresponding relationship is specifically the corresponding relationship between one telephone number and n IMEIs, and n is greater than or equal to 1. The first corresponding relation is that the IMEI related to the telephone number is counted by taking the telephone number as the center. The data in table 2 is obtained by sorting the third correspondence relation centering on the telephone number.
Specifically, as shown in table 2:
telephone number 1 IMEI1 IMEI7 ……
Telephone number 2 IMEI1 IMEI2 ……
Telephone number 3 IMEI3 …… ……
Telephone number 4 IMEI4 …… ……
Telephone number 5 IMEI2 IMEI4 ……
…… …… …… ……
TABLE 2
Column 1 is each telephone number, and columns 2 and following are each IMEI of the user equipment corresponding to the telephone number in column 1. The first correspondence as shown in table 2, namely telephone number 1: IMEI1, IMEI7, … …; telephone number 2: IMEI1, IMEI2, … …; telephone number 3: IMEI3, … …; telephone number 4: IMEI4, … …; telephone number 5: IMEI2, IMEI4, … ….
And step S102, scoring the IMEI according to the attribute information of a plurality of dimensions of the IMEI, and obtaining the statistical characteristics of the telephone number according to the scoring result.
Collecting attribute information of a plurality of dimensions of the IMEI, wherein the attribute information of the plurality of dimensions of the IMEI comprises attribute information of at least one of the following dimensions: user behavior information in the user equipment corresponding to the IMEI, application list information installed in the user equipment corresponding to the IMEI, information on whether the IMEI belongs to an IMEI blacklist (an IMEI blacklist established in advance according to the collected information), and the like. The attribute information of several dimensions of the IMEI is obtained by collecting behavior information of the user on various applications in the user equipment corresponding to the IMEI (behavior that less frequent call duration may disturb others, and behavior that dialing an abnormally large number of calls every day may disturb others), registration of the user in a loan application, behavior information of applying for loan, credit information of the user in a payment application, loan types installed by the user equipment, application information of payment types, and the like, and application information of some application lists installed by the user equipment and belonging to a preset blacklist (application lists collected in advance, such as a credit application, a bad loan application, and the like).
And dividing the score of the IMEI according to the attribute information of a plurality of dimensions of the IMEI, and scoring the IMEI. And replacing each IMEI in the first corresponding relation with the corresponding score of the IMEI, wherein if the score of the IMEI1 is 3 and the score of the IMEI7 is 0.5, the statistical characteristics of the telephone numbers 1:3,0.5 and … …, namely the telephone number 1, are obtained. And obtaining the statistical characteristics of each telephone number according to the scoring result of each IMEI.
Step S103, according to the first corresponding relation between the telephone number and the IMEI, obtaining a second corresponding relation between the telephone numbers.
And collecting the telephone numbers used by the user equipment corresponding to the IMEI, and extracting the IMEI with one-to-one correspondence and the telephone numbers used by the user equipment corresponding to the IMEI. For example, the telephone number used when the user equipment is registered is not the telephone number in the third corresponding relationship of the IMEI, and the telephone number is the telephone number used by the user equipment in one-to-one correspondence with the IMEI.
In the first corresponding relation, the IMEI is replaced by the telephone number which has one-to-one corresponding relation with the IMEI, and a second corresponding relation between the telephone numbers is obtained. The second correspondence is specifically a correspondence between one telephone number and m telephone numbers, where m is greater than or equal to 1. If the phone number corresponding to the IMEI1 is phone number 5, the phone number corresponding to the IMEI7 is phone number 8, and the second correspondence of phone number 1 is phone number 1: telephone number 5, telephone number 8, … ….
And step S104, calculating scores of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers.
And analyzing the collected statistical characteristics of the telephone numbers by using a machine learning model according to the statistical characteristics of the telephone numbers (the telephone numbers and the corresponding IMEI scores thereof) and the second corresponding relation between the telephone numbers by adopting a supervision and classification algorithm. And analyzing the scores contained in the statistical characteristics of the telephone numbers and the scores contained in the statistical characteristics of the telephone numbers having the second corresponding relation with the telephone numbers to obtain the scores of all the telephone numbers by integrating unsupervised and supervised learning.
And step S105, establishing a phone number blacklist according to the scores of all phone numbers.
And setting up grading threshold values of different intervals according to the grades of all the telephone numbers, and adding the telephone numbers in the grading threshold value interval of the blacklist into the blacklist of the telephone numbers according to the grading threshold values.
According to the method for establishing the blacklist of the telephone numbers based on the communication network, the first corresponding relation between the telephone numbers and the IMEI is established by collecting the IMEI of the user equipment and the corresponding call records; the first corresponding relation is the corresponding relation between a telephone number and n IMEIs, wherein n is greater than or equal to 1; scoring the IMEI according to attribute information of a plurality of dimensions of the IMEI, and obtaining statistical characteristics of the telephone number according to scoring results; obtaining a second corresponding relation between the telephone numbers according to the first corresponding relation between the telephone numbers and the IMEI; the second corresponding relation is specifically the corresponding relation between one telephone number and m telephone numbers, and m is greater than or equal to 1; calculating scores of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers; and establishing a phone number blacklist according to the scores of all phone numbers. Under the condition of protecting the privacy of the user, the invention establishes various corresponding relations among the telephone numbers by utilizing the collected IMEI of the user equipment and the corresponding call records. And calculating and scoring according to the statistical characteristics of the telephone numbers and the corresponding relation between the telephone numbers so as to obtain a telephone number blacklist. The invention greatly reduces the exposure rate of the privacy information of the user and reduces the possible privacy disclosure risk. Meanwhile, a machine learning algorithm is combined with the statistical characteristics of the telephone numbers to learn, so that the scores of the telephone numbers are effectively obtained, and a telephone number blacklist is conveniently established.
Fig. 2 shows a flowchart of a phone number blacklist establishing method based on a communication network according to another embodiment of the present invention. As shown in fig. 2, the method for establishing the phone number blacklist based on the communication network specifically includes the following steps:
step S201, a first corresponding relationship between the phone number and the IMEI is established by collecting the IMEI of the user equipment and the call record corresponding thereto.
Step S202, according to the attribute information of the IMEI with a plurality of dimensions, the IMEI is scored, and the statistical characteristics of the telephone number are obtained according to the scoring result.
Step S203, according to the first corresponding relation between the telephone number and the IMEI, a second corresponding relation between the telephone numbers is obtained.
The above steps refer to steps S101 to S103 in the embodiment of fig. 1, and are not described herein again.
Step S204, a second corresponding relation between the telephone numbers is further obtained by collecting the call records between the telephone numbers.
The third party platform such as incoming call show can be used for collecting the call records among the telephone numbers, and the second corresponding relation among the telephone numbers can be further supplemented according to the call records among the telephone numbers.
Step S205, obtaining tag information of a part of phone numbers from the cloud database, and performing pre-labeling scoring on the part of phone numbers according to the tag information.
For part of the collected telephone numbers, corresponding label information, such as crank calls, express calls, meal delivery calls and the like, is stored in the cloud database, the label information of the part of the telephone numbers is obtained from the cloud database, different scores are corresponding to different label information, and the part of the telephone numbers are conveniently pre-labeled and scored according to the label information.
And step S206, according to the partial telephone numbers with the pre-labeling scores and the second corresponding relation between the telephone numbers, carrying out community division on the corresponding telephone numbers, and taking the result of the community division as the input information of the machine learning algorithm.
For a telephone number that may be in the telephone number blacklist, such as a bad telephone number, generally, there is no user willing to save the bad telephone number in the address list, and the user will not answer the incoming call of the bad telephone number many times. From the view of community structure, the community structure of the bad telephone numbers is of a dotted radiation type, but normal telephone numbers have frequent incoming and outgoing calls with relatives, friends, colleagues and the like, and the community structure of the bad telephone numbers is a compact community structure. In consideration of this, the corresponding telephone numbers may be divided into communities according to the partial telephone numbers with the pre-labeled score and the second correspondence relationship between the telephone numbers, and the telephone numbers in the normal communities should be normal telephone numbers and the telephone numbers in the bad communities should be bad telephone numbers.
The result of community division can also be used as input information of a machine learning algorithm for classifying the telephone numbers and identifying the telephone numbers so as to better obtain the scores of the telephone numbers.
Step S207, using machine learning algorithm, using the pre-labeled scores of part of the telephone numbers as learning targets, and calculating the scores of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers.
And by using a machine learning algorithm, the pre-labeled scores of partial telephone numbers are used as learning targets, training is carried out according to the statistical characteristics and the like of the partial telephone numbers, and the machine learning algorithm for scoring the telephone numbers is learned. The scores of all the telephone numbers are calculated by using the supervised learning algorithm and the unsupervised learning of the statistical characteristics of a large number of telephone numbers without pre-labeled scores and the second corresponding relation between the telephone numbers.
And step S208, establishing a phone number blacklist according to the scores of all phone numbers.
Because the label information comprises different label information such as crank calls, express calls, meal delivery calls and the like, different corresponding pre-labeling scores are set according to the different label information, and correspondingly, different scores of bad telephone numbers, medium telephone numbers (including express and meal delivery telephone numbers) and normal telephone numbers are obtained by utilizing a machine learning algorithm. Based on the different scores, a phone number blacklist may be established. The bad phone number belongs to phone numbers in the phone number blacklist. Furthermore, a telephone number gray list can be established, and intermediary telephone numbers (including express telephone numbers and meal delivery telephone numbers) and the like are put into the telephone number gray list.
According to the method for establishing the phone number blacklist based on the communication network, which is provided by the invention, the partial phone numbers are pre-labeled and scored through the label information of the partial phone numbers. By using a machine learning algorithm, the pre-labeled scores of part of the telephone numbers are used as learning targets, so that the obtained scoring results are more accurate. Furthermore, the telephone numbers are subjected to community division, the result of the community division is used as input information of a machine learning algorithm, the actual situation of the society is fully considered, and the calculated score is more in line with the actual situation. And the scores of all the telephone numbers are calculated according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers by utilizing the machine learning combined with the supervised and unsupervised learning for joint analysis, so that a telephone number blacklist can be established.
Fig. 3 shows a functional block diagram of a communication network based phone number blacklist establishing apparatus according to an embodiment of the present invention. As shown in fig. 3, the device for establishing a phone number blacklist based on a communication network comprises the following modules:
the first relationship module 310 is adapted to establish a first corresponding relationship between the phone number and the IMEI by collecting the IMEI of the user equipment and the call record corresponding thereto.
The IMEI (International Mobile Equipment Identity) is an "electronic serial number" consisting of 15 digits, which corresponds to each Mobile user Equipment one to one, and is unique worldwide. A mobile user equipment corresponds to a unique IMEI.
The first relation module 310 further comprises a first collection unit 311, a second collection unit 312 and a corresponding unit 313.
The first collecting unit 311 is adapted to collect the IMEI of the user equipment.
The second collecting unit 312 is adapted to collect call records of the user equipment according to the IMEI of the user equipment, obtain a phone number that generates an incoming call and/or an outgoing call with the user equipment, and establish a third correspondence between the IMEI and the phone number that generates an incoming call and/or an outgoing call with the user equipment.
The first collecting unit 311 collects the IMEI of the user equipment, and the second collecting unit 312 simultaneously collects the call records corresponding to the user equipment, i.e. the call records related to the IMEI of the user equipment, such as incoming call, outgoing call, short message reception, and short message transmission, so as to obtain the telephone number related to the incoming call and/or outgoing call of the user equipment. The second collecting unit 312 may establish a third corresponding relationship between the IMEI and the telephone number of the incoming and/or outgoing call generated by the user equipment according to the IMEI of the user equipment and the obtained telephone number of the incoming and/or outgoing call generated by the user equipment. The third corresponding relationship is a corresponding relationship between an IMEI and d phone numbers, where d is greater than or equal to 1. Second collecting section 312 obtains data shown in table 1 from the IMEI and the telephone number corresponding to the IMEI. Column 1 is the IMEI of each user equipment, and columns 2 and later are one or more telephone numbers which are used for generating incoming call and/or outgoing call relations with the user equipment corresponding to the IMEI in column 1. The second collecting unit 312 can obtain a third corresponding relationship according to the data in table 1, that is, IMEI 1: telephone number 1, telephone number 2, … …; IMEI 2: phone number 2, phone number 5, … …; IMEI 3: telephone number 1, telephone number 3, … …; IMEI 4: phone number 4, phone number 5, … …. The third corresponding relation is that the IMEI is taken as the center, and the telephone number related to the IMEI is counted.
A corresponding unit 313, adapted to establish a first corresponding relationship between the phone number and the IMEI according to the third corresponding relationship.
The corresponding unit 313 may establish a first corresponding relationship between the phone number and the IMEI according to the third corresponding relationship. The first corresponding relationship is specifically the corresponding relationship between one telephone number and n IMEIs, and n is greater than or equal to 1. The first corresponding relation is that the IMEI related to the telephone number is counted by taking the telephone number as the center. The corresponding unit 313 collates the third correspondence relationship centering on the telephone number to obtain data as in table 2. Column 1 is each telephone number, and columns 2 and following are each IMEI of the user equipment corresponding to the telephone number in column 1. The correspondence unit 313 obtains the first correspondence as shown in table 2, i.e., telephone number 1: IMEI1, IMEI7, … …; telephone number 2: IMEI1, IMEI2, … …; telephone number 3: IMEI3, … …; telephone number 4: IMEI4, … …; telephone number 5: IMEI2, IMEI4, … ….
The first scoring module 320 is adapted to score the IMEI according to the attribute information of the IMEI in several dimensions, and obtain the statistical characteristics of the phone number according to the scoring result.
Optionally, the apparatus further includes an attribute obtaining module 360 adapted to collect attribute information of several dimensions of the IMEI.
The attribute acquiring module 360 collects attribute information of several dimensions of the IMEI, wherein the attribute information of several dimensions of the IMEI includes attribute information of at least one of the following dimensions: user behavior information in the user equipment corresponding to the IMEI, application list information installed in the user equipment corresponding to the IMEI, information on whether the IMEI belongs to an IMEI blacklist (an IMEI blacklist established in advance according to the collected information), and the like. For example, the attribute obtaining module 360 obtains attribute information of a plurality of dimensions of the IMEI by collecting behavior information of the user on various applications in the user equipment corresponding to the IMEI (short frequent call duration may be a behavior disturbing others, and abnormal calls made every day may be a behavior disturbing others), registration of the user in a loan application, behavior information of applying for loan, credit information of the user in a payment application, loan types and payment types installed by the user equipment, and application information of some application lists installed by the user equipment and belonging to a preset blacklist (pre-collected application lists such as a credit application and a bad petty loan application).
The first scoring module 320 divides the score of the IMEI according to the attribute information of the IMEI in several dimensions, and scores the IMEI. The first scoring module 320 replaces each IMEI in the first corresponding relationship with a score of a corresponding IMEI, for example, the score of IMEI1 is 3, the score of IMEI7 is 0.5, and the statistical characteristics of the phone numbers 1:3,0.5, … …, that is, the phone number 1, are obtained. The first scoring module 320 obtains statistical characteristics of each phone number according to the scoring result of each IMEI.
The second relationship module 330 is adapted to obtain a second relationship between the phone numbers according to the first relationship between the phone numbers and the IMEI.
The second relationship module 330 collects the phone numbers used by the user equipment corresponding to the IMEI, and extracts the phone numbers used by the user equipment corresponding to the IMEI and the IMEI having a one-to-one correspondence relationship. If the phone number used during the registration of the user equipment is not the phone number of the third corresponding relationship of the IMEI, the second relationship module 330 considers the phone number as the phone number used by the user equipment corresponding to the IMEI in a one-to-one manner.
In the first corresponding relationship, the second relationship module 330 replaces the IMEI with the phone number having a one-to-one corresponding relationship with the IMEI to obtain a second corresponding relationship between the phone numbers. The second correspondence is specifically a correspondence between one telephone number and m telephone numbers, where m is greater than or equal to 1. If the phone number corresponding to the IMEI1 is phone number 5, the phone number corresponding to the IMEI7 is phone number 8, and the second corresponding relationship obtained by the second relationship module 330 for the phone number 1 is phone number 1: telephone number 5, telephone number 8, … ….
The second scoring module 340 is adapted to calculate scores of all the phone numbers according to the statistical characteristics of the phone numbers and the second corresponding relationship between the phone numbers.
The second scoring module 340 analyzes the collected statistical characteristics of the phone numbers by using a supervised classification algorithm according to the statistical characteristics of the phone numbers (phone numbers and their corresponding IMEI scores) and the second correspondence between the phone numbers by using a machine learning model. The second scoring module 340 integrates unsupervised and supervised learning, and analyzes scores included in the statistical characteristics of the phone numbers and scores included in the statistical characteristics of the phone numbers having the second correspondence with the phone numbers to obtain scores of all the phone numbers.
And a blacklist module 350 adapted to establish a blacklist of telephone numbers according to the scores of all telephone numbers.
The blacklist module 350 sets up scoring thresholds in different intervals according to the scores of all the phone numbers, and according to the scoring thresholds, the phone numbers in the blacklist scoring threshold interval can be added into the phone number blacklist.
According to the telephone number blacklist establishing device based on the communication network, the first corresponding relation between the telephone number and the IMEI is established by collecting the IMEI of the user equipment and the corresponding call records; the first corresponding relation is the corresponding relation between a telephone number and n IMEIs, wherein n is greater than or equal to 1; scoring the IMEI according to attribute information of a plurality of dimensions of the IMEI, and obtaining statistical characteristics of the telephone number according to scoring results; obtaining a second corresponding relation between the telephone numbers according to the first corresponding relation between the telephone numbers and the IMEI; the second corresponding relation is specifically the corresponding relation between one telephone number and m telephone numbers, and m is greater than or equal to 1; calculating scores of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers; and establishing a phone number blacklist according to the scores of all phone numbers. Under the condition of protecting the privacy of the user, the invention establishes various corresponding relations among the telephone numbers by utilizing the collected IMEI of the user equipment and the corresponding call records. And calculating and scoring according to the statistical characteristics of the telephone numbers and the corresponding relation between the telephone numbers so as to obtain a telephone number blacklist. The invention greatly reduces the exposure rate of the privacy information of the user and reduces the possible privacy disclosure risk. Meanwhile, a machine learning algorithm is combined with the statistical characteristics of the telephone numbers to learn, so that the scores of the telephone numbers are effectively obtained, and a telephone number blacklist is conveniently established.
Fig. 4 shows a functional block diagram of a communication network-based phone number blacklist establishing apparatus according to another embodiment of the present invention. As shown in fig. 4, the difference from fig. 3 is that the communication network based phone number blacklist creating apparatus further includes:
the call collection module 370 is adapted to further obtain a second corresponding relationship between the phone numbers by collecting call records between the phone numbers.
The call collection module 370 can collect call records between phone numbers by using a third party platform, such as a caller id. The call collection module 370 may further supplement the second correspondence between the phone numbers according to the call records between the phone numbers.
The pre-labeling collection module 380 is adapted to obtain tag information of a part of telephone numbers from the cloud database, and perform pre-labeling scoring on the part of telephone numbers according to the tag information.
For some of the collected telephone numbers, the corresponding tag information, such as crank calls, express calls, meal delivery calls, and the like, is stored in the cloud database, and the pre-labeling collection module 380 acquires the tag information of some telephone numbers from the cloud database, corresponds to different scores according to different tag information, and conveniently performs pre-labeling scoring on the some telephone numbers according to the tag information.
The community division module 390 is adapted to perform community division on the corresponding phone numbers according to the part of phone numbers with the pre-labeled score and the second corresponding relationship between the phone numbers, and use the result of the community division as the input information of the machine learning algorithm.
For a telephone number that may be in the telephone number blacklist, such as a bad telephone number, generally, there is no user willing to save the bad telephone number in the address list, and the user will not answer the incoming call of the bad telephone number many times. From the view of community structure, the community structure of the bad telephone numbers is of a dotted radiation type, but normal telephone numbers have frequent incoming and outgoing calls with relatives, friends, colleagues and the like, and the community structure of the bad telephone numbers is a compact community structure. In consideration of this, the community division module 390 performs community division on the corresponding phone numbers according to the partial phone numbers with the pre-labeled score and the second correspondence relationship between the phone numbers, where the phone numbers in the normal community are opposite to each other and should be the normal phone numbers, and the phone numbers in the bad community are opposite to each other and should be the bad phone numbers.
The result of community division can also be used as input information of a machine learning algorithm for classifying the telephone numbers and identifying the telephone numbers so as to better obtain the scores of the telephone numbers.
The second scoring module 340 is further adapted to use a machine learning algorithm to learn the machine learning algorithm for scoring telephone numbers by training according to statistical characteristics of some telephone numbers, with the pre-labeled scoring of some telephone numbers as a learning target. The second scoring module 340 calculates scores for all phone numbers using the supervised learning algorithm and unsupervised learning of statistical features of a large number of phone numbers without pre-labeled scores and a second correspondence between phone numbers.
Because the label information includes different label information such as crank calls, express calls, meal delivery calls, and the like, the blacklist module 350 is further adapted to set corresponding different pre-labeled scores according to the different label information, and correspondingly, the second scoring module 340 obtains different scores of bad telephone numbers, intermediary telephone numbers (including express telephone numbers, meal delivery telephone numbers), and normal telephone numbers by using a machine learning algorithm. The blacklist module 350 may establish a blacklist of telephone numbers based on the different scores. The bad phone number belongs to phone numbers in the phone number blacklist. Further, the blacklist module 350 may also establish a telephone number grey list, and place intermediary telephone numbers (including express telephone numbers and meal delivery telephone numbers) into the telephone number grey list.
According to the telephone number blacklist establishing device based on the communication network, provided by the invention, partial telephone numbers are pre-labeled and scored through label information of the partial telephone numbers. By using a machine learning algorithm, the pre-labeled scores of part of the telephone numbers are used as learning targets, so that the obtained scoring results are more accurate. Furthermore, the telephone numbers are subjected to community division, the result of the community division is used as input information of a machine learning algorithm, the actual situation of the society is fully considered, and the calculated score is more in line with the actual situation. And the scores of all the telephone numbers are calculated according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers by utilizing the machine learning combined with the supervised and unsupervised learning for joint analysis, so that a telephone number blacklist can be established.
The present application further provides a non-volatile computer storage medium, where at least one executable instruction is stored in the computer storage medium, and the computer executable instruction can execute the method for establishing a phone number blacklist based on a communication network in any of the above method embodiments.
Fig. 5 is a schematic structural diagram of a computing device according to an embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the computing device.
As shown in fig. 5, the computing device may include: a processor (processor)502, a Communications Interface 504, a memory 506, and a communication bus 508.
Wherein:
the processor 502, communication interface 504, and memory 506 communicate with one another via a communication bus 508.
A communication interface 504 for communicating with network elements of other devices, such as clients or other servers.
The processor 502 is configured to execute the program 510, and may specifically execute relevant steps in the above-described telephone number blacklist establishing method embodiment based on a communication network.
In particular, program 510 may include program code that includes computer operating instructions.
The processor 502 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement an embodiment of the present invention. The computing device includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
And a memory 506 for storing a program 510. The memory 506 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
Program 510 may be specifically configured to cause processor 502 to execute a method for establishing a blacklist of telephone numbers based on a communication network in any of the above-described method embodiments. For specific implementation of each step in the program 510, reference may be made to corresponding steps and corresponding descriptions in units in the above embodiment for establishing a phone number blacklist based on a communication network, which are not described herein again. It can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described devices and modules may refer to the corresponding process descriptions in the foregoing method embodiments, and are not described herein again.
The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of an apparatus for telephone number blacklist establishment based on a communication network according to an embodiment of the present invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Claims (12)

1. A phone number blacklist establishing method based on a communication network comprises the following steps:
establishing a first corresponding relation between a telephone number and an IMEI by collecting the IMEI of user equipment and a call record corresponding to the IMEI; the first corresponding relation is specifically the corresponding relation between one telephone number and n IMEIs, and n is greater than or equal to 1;
scoring the IMEI according to attribute information of a plurality of dimensions of the IMEI, and obtaining statistical characteristics of the telephone number according to scoring results;
obtaining a second corresponding relation between the telephone numbers according to the first corresponding relation between the telephone numbers and the IMEI; the second corresponding relationship is a corresponding relationship between one telephone number and m telephone numbers, wherein m is greater than or equal to 1;
calculating scores of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers;
establishing a phone number blacklist according to the scores of all phone numbers;
the establishing of the first corresponding relationship between the telephone number and the IMEI by collecting the IMEI of the user equipment and the call record corresponding thereto further comprises:
collecting the IMEI of the user equipment;
according to the IMEI of the user equipment, collecting the call records of the user equipment, obtaining the telephone number of the incoming call and/or the outgoing call of the user equipment, and establishing a third corresponding relation between the IMEI and the telephone number of the incoming call and/or the outgoing call of the user equipment; wherein, the third corresponding relation is the corresponding relation between an IMEI and d telephone numbers, and d is greater than or equal to 1;
establishing a first corresponding relation between the telephone number and the IMEI according to the third corresponding relation;
the obtaining of the second corresponding relationship between the telephone numbers according to the first corresponding relationship between the telephone numbers and the IMEI further comprises:
collecting the telephone numbers used by the user equipment corresponding to the IMEI, and extracting the IMEI with one-to-one correspondence and the telephone numbers used by the user equipment corresponding to the IMEI;
in the first corresponding relation, the IMEI is replaced by the telephone number which has one-to-one corresponding relation with the IMEI, and a second corresponding relation between the telephone numbers is obtained.
2. The method of claim 1, wherein the method further comprises: collecting attribute information of a plurality of dimensions of the IMEI;
wherein the attribute information of the IMEI in several dimensions comprises attribute information of at least one of the following dimensions:
user behavior information in user equipment corresponding to the IMEI;
the installed application list information in the user equipment corresponding to the IMEI;
information whether the IMEI belongs to an IMEI blacklist.
3. The method of claim 2, wherein the method further comprises:
and further obtaining a second corresponding relation between the telephone numbers by collecting the call records between the telephone numbers.
4. The method of claim 3, wherein the method further comprises: acquiring label information of part of telephone numbers from a cloud database, and performing pre-labeling scoring on the part of telephone numbers according to the label information;
calculating the scores of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers by using a machine learning algorithm, wherein the scores are specifically as follows:
and using a machine learning algorithm, taking the pre-labeled scores of part of the telephone numbers as learning targets, and calculating the scores of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers.
5. The method according to any one of claims 1-4, wherein the method further comprises: and according to the part of telephone numbers with the pre-labeled scores and the second corresponding relation between the telephone numbers, carrying out community division on the corresponding telephone numbers, and taking the result of the community division as the input information of the machine learning algorithm.
6. A phone number blacklist establishing apparatus based on a communication network, comprising:
the first relation module is suitable for establishing a first corresponding relation between the telephone number and the IMEI by collecting the IMEI of the user equipment and the corresponding call records; the first corresponding relation is specifically the corresponding relation between one telephone number and n IMEIs, and n is greater than or equal to 1;
the first grading module is suitable for grading the IMEI according to the attribute information of a plurality of dimensions of the IMEI and obtaining the statistical characteristics of the telephone number according to the grading result;
the second relation module is suitable for obtaining a second corresponding relation between the telephone numbers according to the first corresponding relation between the telephone numbers and the IMEI; the second corresponding relationship is a corresponding relationship between one telephone number and m telephone numbers, wherein m is greater than or equal to 1;
the second grading module is suitable for calculating grades of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers;
the blacklist module is suitable for establishing a telephone number blacklist according to the scores of all telephone numbers;
the first relationship module further comprises:
the first collecting unit is suitable for collecting the IMEI of the user equipment;
the second collecting unit is suitable for collecting the call records of the user equipment according to the IMEI of the user equipment, obtaining the telephone number of the incoming call and/or the outgoing call generated by the user equipment, and establishing a third corresponding relation between the IMEI and the telephone number of the incoming call and/or the outgoing call generated by the user equipment; wherein, the third corresponding relation is the corresponding relation between an IMEI and d telephone numbers, and d is greater than or equal to 1;
the corresponding unit is suitable for establishing a first corresponding relation between the telephone number and the IMEI according to the third corresponding relation;
the second relationship module is further adapted to:
collecting the telephone numbers used by the user equipment corresponding to the IMEI, and extracting the IMEI with one-to-one correspondence and the telephone numbers used by the user equipment corresponding to the IMEI; in the first corresponding relation, the IMEI is replaced by the telephone number which has one-to-one corresponding relation with the IMEI, and a second corresponding relation between the telephone numbers is obtained.
7. The apparatus of claim 6, wherein the apparatus further comprises:
the attribute acquisition module is suitable for collecting attribute information of a plurality of dimensions of the IMEI;
wherein the attribute information of the IMEI in several dimensions comprises attribute information of at least one of the following dimensions:
user behavior information in user equipment corresponding to the IMEI;
the installed application list information in the user equipment corresponding to the IMEI;
information whether the IMEI belongs to an IMEI blacklist.
8. The apparatus of claim 7, wherein the apparatus further comprises:
and the call collection module is suitable for further obtaining a second corresponding relation between the telephone numbers by collecting call records among the telephone numbers.
9. The apparatus of any of claims 6-8, wherein the apparatus further comprises:
the system comprises a pre-labeling collection module, a pre-labeling scoring module and a pre-labeling scoring module, wherein the pre-labeling collection module is suitable for acquiring label information of part of telephone numbers from a cloud database and pre-labeling and scoring the part of telephone numbers according to the label information;
the second scoring module is further adapted to:
and using a machine learning algorithm, taking the pre-labeled scores of part of the telephone numbers as learning targets, and calculating the scores of all the telephone numbers according to the statistical characteristics of the telephone numbers and the second corresponding relation between the telephone numbers.
10. The apparatus of claim 9, wherein the apparatus further comprises:
and the community division module is suitable for carrying out community division on the corresponding telephone numbers according to the part of the telephone numbers with the pre-labeled scores and the second corresponding relation between the telephone numbers, and taking the result of the community division as the input information of the machine learning algorithm.
11. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the telephone number blacklist establishing method based on the communication network according to any one of claims 1-5.
12. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform operations corresponding to the communication network-based phone number blacklist establishing method according to any one of claims 1 to 5.
CN201711275807.6A 2017-12-06 2017-12-06 Telephone number blacklist establishing method and device based on communication network Expired - Fee Related CN108055661B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201711275807.6A CN108055661B (en) 2017-12-06 2017-12-06 Telephone number blacklist establishing method and device based on communication network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201711275807.6A CN108055661B (en) 2017-12-06 2017-12-06 Telephone number blacklist establishing method and device based on communication network

Publications (2)

Publication Number Publication Date
CN108055661A CN108055661A (en) 2018-05-18
CN108055661B true CN108055661B (en) 2021-02-23

Family

ID=62122303

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711275807.6A Expired - Fee Related CN108055661B (en) 2017-12-06 2017-12-06 Telephone number blacklist establishing method and device based on communication network

Country Status (1)

Country Link
CN (1) CN108055661B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109767076A (en) * 2018-12-17 2019-05-17 平安科技（深圳）有限公司 The generation of blacklist and screening method, device, computer equipment and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106686261A (en) * 2017-01-19 2017-05-17 腾讯科技（深圳）有限公司 Information processing method and system
CN107169629A (en) * 2017-04-17 2017-09-15 四川九洲电器集团有限责任公司 A kind of telecommunication fraud recognition methods and data processing equipment
CN107248082A (en) * 2017-05-23 2017-10-13 北京道隆华尔软件股份有限公司 Support card identification method and device

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160371699A1 (en) * 2015-06-19 2016-12-22 Reginal Robert Proctor Method for Financial Fraud Prevention Through User-Determined Regulations

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106686261A (en) * 2017-01-19 2017-05-17 腾讯科技（深圳）有限公司 Information processing method and system
CN107169629A (en) * 2017-04-17 2017-09-15 四川九洲电器集团有限责任公司 A kind of telecommunication fraud recognition methods and data processing equipment
CN107248082A (en) * 2017-05-23 2017-10-13 北京道隆华尔软件股份有限公司 Support card identification method and device

Also Published As

Publication number Publication date
CN108055661A (en) 2018-05-18

Similar Documents

Publication Publication Date Title
CN110517097B (en) Method, device, equipment and storage medium for identifying abnormal users
US11301855B2 (en) Data verification in transactions in distributed network
CN109034583B (en) Abnormal transaction identification method and device and electronic equipment
CN107872772B (en) Method and device for detecting fraud short messages
US11847662B2 (en) Systems and methods of photo-based fraud protection
CN110909384B (en) Method and device for determining business party revealing user information
CN113412607B (en) Content pushing method and device, mobile terminal and storage medium
CN110139280A (en) Swindle detection method, device and the storage medium of number
CN113206909A (en) Crank call interception method and device
CN113610247A (en) Fault help seeking method and device for freight vehicle, storage medium and terminal
CN110611655B (en) Blacklist screening method and related product
CN111612085A (en) Method and device for detecting abnormal point in peer-to-peer group
CN114445088A (en) Method and device for judging fraudulent conduct, electronic equipment and storage medium
CN108055661B (en) Telephone number blacklist establishing method and device based on communication network
CN113568934A (en) Data query method and device, electronic equipment and storage medium
CN117252429A (en) Risk user identification method and device, storage medium and electronic equipment
CN109711984B (en) Pre-loan risk monitoring method and device based on collection urging
CN111179023A (en) Order identification method and device
CN108898167A (en) It breaks one's promise the display methods and device of number
CN111047341B (en) Information processing method, device, server and terminal equipment
CN111105259B (en) User identification method, device, electronic equipment and storage medium
CN112560961A (en) Target identification method and device based on graph clustering, electronic equipment and storage medium
CN112215386A (en) Personnel activity prediction method and device and computer readable storage medium
CN113313505B (en) Abnormality positioning method and device and computing equipment
CN118096191B (en) Anti-fraud system and method for intelligent user information protection

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
CF01 Termination of patent right due to non-payment of annual fee
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20210223