CN114430442B - Fraud number identification and analysis method based on artificial intelligence - Google Patents
Fraud number identification and analysis method based on artificial intelligence Download PDFInfo
- Publication number
- CN114430442B CN114430442B CN202210353571.8A CN202210353571A CN114430442B CN 114430442 B CN114430442 B CN 114430442B CN 202210353571 A CN202210353571 A CN 202210353571A CN 114430442 B CN114430442 B CN 114430442B
- Authority
- CN
- China
- Prior art keywords
- credit score
- telephone
- telephone number
- score
- fraud
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/22—Arrangements for supervision, monitoring or testing
- H04M3/2281—Call monitoring, e.g. for law enforcement purposes; Call tracing; Detection or prevention of malicious calls
Abstract
The invention discloses a fraud number identification and analysis method based on artificial intelligence, which comprises the following steps: acquiring a telephone number with high liveness; counting the times of the telephone dialing behavior and the times of the telephone answering behavior of the telephone number; setting a first score value and a second score value for the telephone number, scoring the first score value according to the times of the telephone dialing action, and scoring the second score value according to the times of the telephone answering action; rating a first credit score W1 for the telephone number; monitoring all the following call behaviors of the telephone number; setting a third divisor and a fourth divisor for the telephone number; rating a second credit score W2 for the telephone number; whether the phone number is a fraud number is judged according to the sum size of the first credit score W1 and the second credit score W2. Through the mode, whether the phone number is a fraud number or not can be judged through credit scores, some new fraud numbers can be identified at the first time, and troubles are solved for broad users.
Description
Technical Field
The invention relates to the technical field of Internet, in particular to a fraud number identification and analysis method based on artificial intelligence.
Background
With the maturity of mobile communication networks, the time-space range of mutual communication is expanded, which brings great convenience to users, but also brings serious problems of communication privacy information disclosure and the like, for example, many website registrations or outgoing consumptions require users to fill in telephone numbers, so that the telephone numbers are easily disclosed to lawless persons, which causes that users often receive harassing calls such as advertisements, promotion, fraud and the like and some junk short messages, and brings much trouble to users.
In the traditional mode, workers judge that the telephone number is not a fraud number manually, judge by depending on user complaints and some blacklists and are not judged in the true sense, and particularly, the telephone number cannot be identified for the first time for some new fraud numbers, so that great troubles are brought to vast users.
Disclosure of Invention
The invention mainly solves the technical problem of providing an artificial intelligence-based fraud number identification and analysis method, which can judge whether a telephone number is a fraud number through credit score, can identify some new fraud numbers at the first time and solves troubles for broad users.
In order to solve the technical problems, the invention adopts a technical scheme that: provided is an artificial intelligence-based fraud number recognition analysis method, which is characterized by comprising the following steps: acquiring a telephone number with high liveness in a first preset time period, wherein the first preset time period is the occurred time; counting the times of the telephone dialing action and the times of the telephone answering action of the telephone number in a first preset time period; setting a first point value and a second point value for the telephone number, scoring the first point value according to the times of the telephone dialing action and scoring the second point value according to the times of the telephone answering action, wherein the first point value is increased by 1 point every 1 time of the telephone dialing action, and the second point value is increased by 1 point every 1 time of the telephone answering action; assessing a first credit score W1 for the telephone number according to the formula L = | L1-L2| wherein L is a first absolute value, L1 is a first score value, L2 is a second score value, the smaller the first absolute value L, the higher the first credit score W1, the larger the first absolute value L, the smaller the first credit score W1; monitoring all call behaviors of the telephone number in a next second preset time period, wherein the call behaviors comprise a call making behavior and a call answering behavior, the second preset time period is non-occurrence time, and the first preset time period and the second preset time period belong to continuous occurrence time; setting a third decimal value and a fourth decimal value for the telephone number, wherein a one-time calling behavior exists in a next second preset time period, a 1 point is added to the third decimal value of the telephone number, a one-time answering behavior exists, and a 1 point is added to the fourth decimal value of the telephone number; after the second preset time is over, evaluating a second credit score W2 for the telephone number according to a formula S = | S1-S2| wherein S is a second absolute value, S1 is a third fractional value, S2 is a fourth fractional value, the smaller the second absolute value S is, the higher the second credit score W2 is, the larger the second absolute value S is, and the smaller the second credit score W2 is; and judging whether the telephone number is a fraud number according to the sum of the first credit score W1 and the second credit score W2, wherein the smaller the sum of the first credit score W1 and the second credit score W2 is, the more likely the telephone number belongs to the fraud number, and when the first credit score W1 is smaller than the first evaluation value, the second credit score W2 is smaller than the second evaluation value, and the sum of the first credit score W1 and the second credit score W2 is smaller than the third evaluation value, the telephone number is judged to be the fraud number.
Further, the method further comprises: setting a third credit score W3 for the telephone number; evaluating a third credit score W3 for the phone number according to whether the phone number is bound with user information, wherein 1 score is added to the third credit score when the phone number is bound with an ID code, 1 score is added to the third credit score when the phone number is bound with a real name corresponding to the ID code, and 1 score is added to the third credit score when the phone number is bound with a registered address corresponding to the ID code; when it is determined that the phone number is not judged to be a fraud number through the first credit score W1 and the second credit score W2, it is judged whether the phone number is a fraud number according to the size of the third credit score W3, wherein when the third credit score W3 is 0 or less than 0, the phone number is judged to be a fraud number, and when the third credit score W3 is more than 0, the phone number is judged not to be a fraud number.
Furthermore, the name of the account holder corresponding to the ID code bound to the phone number is different from the name bound to the phone number, which is the credit score W3 minus 1, and the address of the account holder corresponding to the ID code bound to the phone number is different from the registration address bound to the phone number, which is the credit score W3 minus 1.
Further, the method further comprises: setting a fourth credit score W4 for the telephone number; evaluating a fourth credit score W4 for the telephone number according to the number of the bankcards bound by the telephone number, wherein each time the telephone number is bound with a bankcard, 1 is added to the fourth credit score W4; when it is determined that the phone number is not judged to be a fraud number through the first credit score W1, the second credit score W2 and the third credit score W3, it is judged whether the phone number is a fraud number according to the size of the fourth credit score W4, wherein when the fourth credit score W4 is 0 or less than 0 minutes, the phone number is judged to be a fraud number, and when the fourth credit score W4 is greater than 0 minutes, the phone number is judged not to be a fraud number.
Furthermore, the name corresponding to the account holder corresponding to the bank card bound by the phone number is different from the name corresponding to the ID code bound by the phone number, which is the fourth credit score W4 minus 1.
Further, the bank card bound with the telephone number has no deposit and frequently transfers out immediately after receiving money, and the fourth credit score W4 is reduced by 1.
Further, the method further comprises: setting a fifth credit score W5 and a sixth credit score W6 for the telephone number; assessing a fifth credit W5 for the telephone number based on the broadband traffic package customized for the telephone number, wherein the telephone number is customized with a traffic package of 30 points added to the fifth credit W5 and the telephone number has broadband traffic used daily of 1 point added to the sixth credit W6, and assessing a sixth credit W6 for the telephone number based on the broadband traffic used daily by the telephone number; when it is determined that the phone number is not judged to be a fraud number through the first credit score W1, the second credit score W2, the third credit score W3 and the fourth credit score W4, it is judged whether the phone number is a fraud number according to the magnitude of the sum of the fifth credit score W5 and the sixth credit score W6.
Further, within one month, when the sum of the fifth credit score W5 and the sixth credit score W6 is greater than 45 minutes, it is determined that the phone number is not a fraud number, and when the fifth credit score W5 is 0 minutes and the sixth credit score W6 is less than 5 minutes, it is determined that the phone number is a fraud number.
Further, the method further comprises: setting a seventh credit score W7 for the telephone number; upon determining that the telephone number is not determined to be a fraud number by the first credit score W1, the second credit score W2, the third credit score W3, the fourth credit score W4, the fifth credit score W5, and the sixth credit score W6, assessing a seventh credit score W7 for the telephone number by the location at which the act of dialing a telephone was undertaken, wherein dialing a telephone call per location changes adds 1 score to the seventh credit score W7; when the seventh credit score W7 is less than the preset score within the preset time, the phone number is determined to be a fraud number.
The beneficial effects of the invention are: different from the situation of the prior art, the fraud number identification and analysis method based on artificial intelligence disclosed by the invention comprises the following steps: acquiring a telephone number with high liveness; counting the times of the telephone dialing behavior and the times of the telephone answering behavior of the telephone number; setting a first score value and a second score value for the telephone number, scoring the first score value according to the times of the telephone dialing action and scoring the second score value according to the times of the telephone answering action; rating a first credit score W1 for the telephone number according to the formula L = | L1-L2 |; monitoring all the following call behaviors of the telephone number; setting a third numerical value and a fourth numerical value for the telephone number; rating a second credit score W2 for the telephone number according to the formula S = | S1-S2 |; whether the phone number is a fraud number is judged according to the sum size of the first credit score W1 and the second credit score W2. Through the mode, whether the telephone number is a fraud number can be judged through credit scores, and some new fraud numbers can be identified at the first time, so that troubles are solved for vast users.
Drawings
FIG. 1 is a schematic flow chart of a first embodiment of the artificial intelligence-based fraud number identification and analysis method of the present invention;
FIG. 2 is a schematic flow chart illustrating a second embodiment of the fraud number identification and analysis method based on artificial intelligence of the present invention;
FIG. 3 is a schematic flow chart illustrating a fraud number identification and analysis method based on artificial intelligence according to a third embodiment of the present invention;
fig. 4 is a schematic flow chart of a fourth embodiment of the fraud number identification and analysis method based on artificial intelligence of the present invention.
Detailed Description
Referring to fig. 1, the present invention discloses a fraud number identification and analysis method based on artificial intelligence, which comprises the following steps:
step S101: and acquiring the telephone number with high liveness in the first preset time period.
Preferably, the first preset time period is a time that has occurred.
It should be understood that the phone number with high liveness may specifically refer to a phone number with a relatively large number of phone dialing actions and a relatively small number of phone answering actions in a certain time period, for example, a phone number with a liveness which has a number of phone dialing actions exceeding 100 and a number of phone answering actions not exceeding 10 in a week is a phone number with high liveness.
Further, in some embodiments, the phone number with high activity may specifically refer to a phone number with a relatively large number of phone dialing actions and a relatively small number of phone receiving actions in a certain period of time in an area with fraud. That is, as long as it is determined that a fraud is present in a certain area, a telephone number with a relatively large number of telephone dialing actions and a relatively small number of telephone answering actions belongs to a telephone number with a high activity in the certain area, and the telephone number has a fraud suspicion.
Step S102: and counting the times of the telephone dialing action and the times of the telephone answering action of the telephone number in a first preset time period.
Step S103: and setting a first score value and a second score value for the telephone number, scoring the first score value according to the times of the telephone dialing action, and scoring the second score value according to the times of the telephone answering action.
Specifically, in a first preset time period, the first score value is increased by 1 score every 1 time of the call-making action, and the second score value is increased by 1 score every 1 time of the call-answering action. If the behavior of making a call for 90 times exists in the first preset time period, the first score value is 90 minutes, and if the behavior of answering the call for 10 times exists, the second score value is 10 minutes.
Step S104: a first credit W1 is rated for the telephone number according to the formula L = | L1-L2 |.
Wherein L is a first absolute value, L1 is a first fractional value, and L2 is a second fractional value.
Preferably, the smaller the first absolute value L, the higher the first credit score W1, and the larger the first absolute value L, the smaller the first credit score W1. It should be appreciated that the higher the first credit score W1, the more unproblematic the telephone number.
It should be appreciated that fraudulent telephone numbers all behave as making more calls and receiving fewer calls, making much more calls than receiving calls, and normal telephone numbers all behave in a manner comparable to making and receiving calls.
Step S105: and monitoring all call behaviors of the telephone number in the next second preset time period.
It should be understood that before executing step S105, it is determined whether the first absolute value L is relatively large, such as determining whether the first absolute value L is greater than a preset standard value, if so, step S105 is executed, and if not, step S105 is not executed. That is, if the first absolute value L is larger (i.e. the first absolute value L is larger than the predetermined standard value), it indicates that the number of times of the telephone number having the action of making a call is larger and the number of times of the action of receiving a call is smaller, which indicates that the telephone number has a fraud suspicion but needs to continue to monitor, so step S105 is continuously performed.
Preferably, the call behavior includes a call-making behavior and a call-answering behavior, the second preset time period is a non-occurrence time, and the first preset time period and the second preset time period belong to continuously-occurrence times.
Step S106: setting a third fractional value and a fourth fractional value for the telephone number, wherein a one-time calling action exists in a second preset time period, a 1 point is added to the third fractional value of the telephone number, a one-time answering action exists, and a 1 point is added to the fourth fractional value of the telephone number.
That is, the third point value of the telephone number is added with 1 point by adding one dialing action, and the fourth point value of the telephone number is added with 1 point by adding one answering action.
Step S107: and after the second preset time is over, evaluating a second credit score W2 for the telephone number according to the formula S = | S1-S2 |.
Wherein S is a second absolute value, S1 is a third fractional value, and S2 is a fourth fractional value.
Preferably, the smaller the second absolute value S, the higher the second credit score W2, and the larger the second absolute value S, the smaller the second credit score W2. It should be appreciated that the higher the second credit score W2, the more problematical the telephone number may prove.
Step S108: whether the phone number is a fraud number is judged according to the sum size of the first credit score W1 and the second credit score W2.
Preferably, the smaller the sum of the first credit score W1 and the second credit score W2, the more likely the phone number is to belong to a fraud number, and the larger the sum of the first credit score W1 and the second credit score W2, the less suspected the phone number is to belong to a fraud number.
Specifically, when the first credit W1 is smaller than the first evaluation value, the second credit W2 is smaller than the second evaluation value, and the sum of the first credit W1 and the second credit W2 is smaller than a third evaluation value, which is larger than the first evaluation value and the second evaluation value, the phone number is judged as a fraud number.
Further, as shown in fig. 2, the artificial intelligence based fraud number identification analysis method further includes the steps of:
step S201: a third credit score W3 is set for the telephone number.
Step S202: a third credit score W3 is assessed for the telephone number depending on whether the telephone number has user information bound to it.
And adding 1 point to the third credit when the telephone number is bound with the ID code, adding 1 point to the third credit when the telephone number is bound with the real name corresponding to the ID code, and adding 1 point to the third credit when the telephone number is bound with the registration address corresponding to the ID code. It should be understood that normal phone numbers need to bind the real user name and ID code, and only fraudulent phone numbers will not bind user information.
Step S203: upon determining that the phone number is not judged to be a fraud number through the first credit score W1 and the second credit score W2, it is judged whether the phone number is a fraud number according to the sum size of the first credit score W1, the second credit score W2 and the third credit score W3.
Preferably, when the third credit score W3 is 0 minutes, the telephone number is determined to be a fraud number, and when the third credit score W3 is greater than 0 minutes, the telephone number is determined not to be a fraud number. That is, when the phone number is not determined to be a fraud number by the first credit score W1 and the second credit score W2, it is further determined whether the phone number is a fraud number by the third credit score W3.
Further, when the name of the account holder corresponding to the ID code bound to the phone number is different from the name bound to the phone number, the credit score is W3 minus 1, and the address of the account holder corresponding to the ID code bound to the phone number is different from the registered address bound to the phone number, which is W3 minus 1. Preferably, when the third credit score W3 is lower than 0 score, the phone number is determined to be a fraud number.
Further, as shown in fig. 3, the artificial intelligence based fraud number identification analysis method further includes the steps of:
step S301: a fourth credit score W4 is set for the telephone number.
Step S302: a fourth credit score W4 is assessed for the telephone number based on the number of bank cards to which the telephone number is bound.
Wherein, each time the telephone number is bound with a bank card, 1 is added to the fourth credit score W4. It should be understood that the normal phone number is bound to the bank card of the user and is used for receiving information such as the verification code, and therefore the normal phone number is bound to a plurality of bank cards.
Step S303: when it is determined that the phone number is not judged to be a fraud number through the first credit score W1, the second credit score W2 and the third credit score W3, it is judged whether the phone number is a fraud number according to the size of the fourth credit score W4.
Wherein, when the fourth credit score W4 is 0 minutes, the telephone number is judged as a fraud number, and when the fourth credit score W4 is greater than 0 minutes, the telephone number is judged not as a fraud number.
Further, the name corresponding to the account holder corresponding to the bank card bound by the phone number is different from the name corresponding to the ID code bound by the phone number, which is the fourth credit score W4 minus 1. Preferably, when the fourth credit score W4 is lower than 0 score, the phone number is determined to be a fraud number.
Further, the bank card bound with the telephone number has no deposit and frequently transfers out immediately after receiving money, and the fourth credit score W4 is reduced by 1. It should be appreciated that if the phone number belongs to a fraud number, the corresponding bank card will immediately be turned away after receiving the money.
Further, as shown in fig. 4, the artificial intelligence based fraud number identification analysis method further includes the steps of:
step S401: a fifth credit score W5 and a sixth credit score W6 are set for the phone number.
Step S402: a fifth credit W5 is rated for the telephone number according to the broadband traffic package customized for the telephone number and a sixth credit W6 is rated for the telephone number according to the broadband traffic used by the telephone number each day.
Wherein, the telephone number is customized with a flow package which is added 30 points to the fifth credit W5, and the telephone number has the use broadband flow every day which is added 1 point to the sixth credit W6. It should be appreciated that normal phone numbers are typically bound to wide traffic packages and are used almost daily, while fraudulent phone numbers are specifically used to make calls, are not used to make normal traffic, and are not used to customize wide traffic packages.
Step S403: when it is determined that the phone number is not judged to be a fraud number through the first credit score W1, the second credit score W2, the third credit score W3 and the fourth credit score W4, it is judged whether the phone number is a fraud number according to the magnitude of the sum of the fifth credit score W5 and the sixth credit score W6.
Preferably, within one month, the phone number is judged not to be a fraud number when the sum of the fifth credit score W5 and the sixth credit score W6 is greater than 45 minutes, and judged to be a fraud number when the fifth credit score W5 is 0 and the sixth credit score W6 is less than 5 minutes.
Further, the artificial intelligence based fraud number identification and analysis method further comprises the following steps:
step S501: a seventh credit score W7 is set for the telephone number.
Step S502: upon determining that the telephone number is not judged to be a fraud number by the first credit score W1, the second credit score W2, the third credit score W3, the fourth credit score W4, the fifth credit score W5 and the sixth credit score W6, a seventh credit score W7 is assessed for the telephone number by the location at which the telephone activity was dialed.
Wherein, every time the position is changed to make a call, 1 point is added to the seventh credit score W7. It should be appreciated that fraud numbers are mostly fixed and dialed in one location, while normal telephone numbers are constantly changing locations.
Step S503: when the seventh credit score W7 is less than the preset score within the preset time, the phone number is determined to be a fraud number.
If the number of calls made exceeds the predetermined number and the seventh credit score W7 is less than 5 minutes in a week, the phone number is determined to be a fraud number. Alternatively, when the number of times of dialing the phone number exceeds the preset number and the seventh credit score W7 is less than 5 minutes in a day, the phone number is determined to be a fraud number.
In conclusion, the invention can judge whether the telephone number is a fraud number or not through the credit score, can identify some new fraud numbers at the first time, and solves the trouble for the majority of users.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes performed by the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (9)
1. A fraud number identification and analysis method based on artificial intelligence is characterized by comprising the following steps:
acquiring a telephone number with high liveness in a first preset time period, wherein the first preset time period is the occurred time;
counting the times of the telephone dialing action and the times of the telephone answering action of the telephone number in a first preset time period;
setting a first point value and a second point value for the telephone number, scoring the first point value according to the times of the telephone dialing action and scoring the second point value according to the times of the telephone answering action, wherein the first point value is increased by 1 point every 1 time of the telephone dialing action, and the second point value is increased by 1 point every 1 time of the telephone answering action;
assessing a first credit score W1 for the telephone number according to the formula L = | L1-L2| wherein L is a first absolute value, L1 is a first score value, L2 is a second score value, the smaller the first absolute value L, the higher the first credit score W1, the larger the first absolute value L, the smaller the first credit score W1;
monitoring all call behaviors of the telephone number in a second next preset time period, wherein the call behaviors comprise a call dialing behavior and a call answering behavior, the second preset time period is non-occurring time, and the first preset time period and the second preset time period belong to continuously occurring time;
setting a third decimal value and a fourth decimal value for the telephone number, wherein a behavior of adding one-time dialing exists in a second preset time period, a behavior of adding 1 point to the third decimal value of the telephone number, a behavior of adding one-time answering exists, and a behavior of adding 1 point to the fourth decimal value of the telephone number;
after the second preset time is over, evaluating a second credit score W2 for the telephone number according to a formula S = | S1-S2| wherein S is a second absolute value, S1 is a third fractional value, S2 is a fourth fractional value, the smaller the second absolute value S is, the higher the second credit score W2 is, the larger the second absolute value S is, and the smaller the second credit score W2 is;
and judging whether the telephone number is a fraud number according to the sum of the first credit score W1 and the second credit score W2, wherein the smaller the sum of the first credit score W1 and the second credit score W2 is, the more likely the telephone number belongs to the fraud number, and when the first credit score W1 is smaller than the first evaluation value, the second credit score W2 is smaller than the second evaluation value, and the sum of the first credit score W1 and the second credit score W2 is smaller than the third evaluation value, the telephone number is judged to be the fraud number.
2. The method of claim 1, further comprising:
setting a third credit score W3 for the telephone number;
evaluating a third credit score W3 for the phone number according to whether the phone number is bound with user information, wherein the third credit score is added with 1 when the phone number is bound with an identity ID code, the third credit score is added with 1 when the phone number is bound with a real name corresponding to the identity ID code, and the third credit score is added with 1 when the phone number is bound with a registration address corresponding to the identity ID code;
when it is determined that the phone number is not judged to be a fraud number through the first credit score W1 and the second credit score W2, it is judged whether the phone number is a fraud number according to the size of the third credit score W3, wherein when the third credit score W3 is 0 or less than 0, the phone number is judged to be a fraud number, and when the third credit score W3 is more than 0, the phone number is judged not to be a fraud number.
3. The method of claim 2, wherein the name of the owner corresponding to the ID code bound to the phone number is different from the name bound to the phone number, and is W3 minus 1, and the address of the owner corresponding to the ID code bound to the phone number is different from the registered address bound to the phone number, and is W3 minus 1.
4. The method of claim 3, further comprising:
setting a fourth credit score W4 for the telephone number;
evaluating a fourth credit score W4 for the telephone number according to the number of the bank cards bound by the telephone number, wherein each time a bank card is bound by the telephone number, 1 score is added to the fourth credit score W4;
when it is determined that the phone number is not judged to be a fraud number through the first credit score W1, the second credit score W2 and the third credit score W3, it is judged whether the phone number is a fraud number according to the size of the fourth credit score W4, wherein when the fourth credit score W4 is 0 or less than 0 minutes, the phone number is judged to be a fraud number, and when the fourth credit score W4 is greater than 0 minutes, the phone number is judged not to be a fraud number.
5. The method according to claim 4, wherein the name corresponding to the account holder corresponding to the bank card bound to the phone number is different from the name corresponding to the ID code bound to the phone number, which is the fourth credit score W4 minus 1.
6. The method as claimed in claim 5, wherein the bank card bound with the telephone number has no deposit and is frequently transferred out immediately after receiving money, and the fourth credit score W4 is reduced by 1.
7. The method of claim 6, further comprising:
setting a fifth credit score W5 and a sixth credit score W6 for the telephone number;
assessing a fifth credit W5 for the telephone number according to the broadband traffic package customized for the telephone number, and assessing a sixth credit W6 for the telephone number according to the broadband traffic used by the telephone number each day, wherein the telephone number is customized with a traffic package with a score of W5 plus 30 for the fifth credit and a score of W6 plus 1 for the sixth credit with broadband traffic used by the telephone number each day;
when it is determined that the phone number is not judged to be a fraud number through the first credit score W1, the second credit score W2, the third credit score W3 and the fourth credit score W4, it is judged whether the phone number is a fraud number according to the magnitude of the sum of the fifth credit score W5 and the sixth credit score W6.
8. The method of claim 7, wherein within one month, the phone number is determined not to be a fraud number when the sum of the fifth credit score W5 and the sixth credit score W6 is greater than 45 minutes, and the phone number is determined to be a fraud number when the fifth credit score W5 is 0 and the sixth credit score W6 is less than 5 minutes.
9. The method of claim 8, further comprising:
setting a seventh credit score W7 for the telephone number;
upon determining that the telephone number is not determined to be a fraud number by the first credit score W1, the second credit score W2, the third credit score W3, the fourth credit score W4, the fifth credit score W5 and the sixth credit score W6, assessing a seventh credit score W7 for the telephone number by the location at which the telephone was dialed in the act, wherein the seventh credit score W7 is incremented by 1 per location change of dialing the telephone;
when the seventh credit score W7 is less than the preset score within the preset time, the phone number is determined to be a fraud number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210353571.8A CN114430442B (en) | 2022-04-02 | 2022-04-02 | Fraud number identification and analysis method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210353571.8A CN114430442B (en) | 2022-04-02 | 2022-04-02 | Fraud number identification and analysis method based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114430442A CN114430442A (en) | 2022-05-03 |
| CN114430442B true CN114430442B (en) | 2022-07-15 |
Family
ID=81314270
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210353571.8A Active CN114430442B (en) | 2022-04-02 | 2022-04-02 | Fraud number identification and analysis method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114430442B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110401780A (en) * | 2018-04-25 | 2019-11-01 | 中国移动通信集团广东有限公司 | A kind of method and device identifying fraudulent call |
| US10785369B1 (en) * | 2019-09-26 | 2020-09-22 | T-Mobile Usa, Inc. | Multi-factor scam call detection and alerting |
| CN114169439A (en) * | 2021-12-08 | 2022-03-11 | 中国电信股份有限公司 | Abnormal communication number identification method and device, electronic equipment and readable medium |
| CN114189866A (en) * | 2021-11-09 | 2022-03-15 | 武汉绿色网络信息服务有限责任公司 | Multi-card fraud detection method and device |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108256993A (en) * | 2017-12-29 | 2018-07-06 | 浪潮天元通信信息系统有限公司 | A kind of credit score appraisal procedure and credit score Evaluation Platform |
| CN114169438A (en) * | 2021-12-08 | 2022-03-11 | 恒安嘉新（北京）科技股份公司 | Telecommunication network fraud identification method, device, equipment and storage medium |
-
2022
- 2022-04-02 CN CN202210353571.8A patent/CN114430442B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110401780A (en) * | 2018-04-25 | 2019-11-01 | 中国移动通信集团广东有限公司 | A kind of method and device identifying fraudulent call |
| US10785369B1 (en) * | 2019-09-26 | 2020-09-22 | T-Mobile Usa, Inc. | Multi-factor scam call detection and alerting |
| CN114189866A (en) * | 2021-11-09 | 2022-03-15 | 武汉绿色网络信息服务有限责任公司 | Multi-card fraud detection method and device |
| CN114169439A (en) * | 2021-12-08 | 2022-03-11 | 中国电信股份有限公司 | Abnormal communication number identification method and device, electronic equipment and readable medium |
Non-Patent Citations (1)
| Title |
|---|
| 李文涛等.数据挖掘在语音诈骗防控领域的创新应用.《电信科学》.2017, * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114430442A (en) | 2022-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101098532B1 (en) | Method for Preventing Voice Phishing on Mobile Telecommunication Terminal | |
| US9143592B2 (en) | Mobile terminal and method for displaying contact list in order of priority levels | |
| CN108810290B (en) | Method and system for recognizing fraud calls | |
| CN110611929A (en) | Abnormal user identification method and device | |
| CN110213448A (en) | Malice number identification method, device, storage medium and computer equipment | |
| CN110505623B (en) | Method, system and server for processing marked number complaint | |
| CN104580649A (en) | Method and system for checking automatic speech service content | |
| CN114430442B (en) | Fraud number identification and analysis method based on artificial intelligence | |
| CN102857993A (en) | Communication processing method and device and first communication terminal | |
| TWI507009B (en) | System and method of smartphone for preventing fraud | |
| CN104754583A (en) | Electronic device having cheat-proof caller identification function and method therefor | |
| CN104506743A (en) | Method and device for dynamically intercepting call | |
| CN106162586A (en) | Method for limiting incoming call, device and system | |
| CN109087197A (en) | A kind of change recognition methods of number and device | |
| KR20130083286A (en) | System for processing spam for mobile phone | |
| CN115767551A (en) | Harassment fraud call identification method, device, equipment and storage medium | |
| CN103685779B (en) | A kind of user satisfaction management system and the method carrying out call manager thereof | |
| CN108769434A (en) | Call processing method, apparatus and system | |
| CN114168423A (en) | Abnormal number calling monitoring method, device, equipment and storage medium | |
| CN101695187B (en) | Call pretreatment method and device thereof | |
| CN107733900A (en) | One kind communication network users abnormal call behavioral value method for early warning | |
| CN112261654B (en) | Method and system for generating mobile phone number white list in telecommunication anti-fraud process | |
| CN104660834A (en) | Junk call protection method and device | |
| CN113556430B (en) | Outbound system and outbound method | |
| CN107707776A (en) | For intercepting the method and device of Inbound Calls |
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 |