CN109510903B - Method for identifying international fraud number - Google Patents
Method for identifying international fraud number Download PDFInfo
- Publication number
- CN109510903B CN109510903B CN201811366099.1A CN201811366099A CN109510903B CN 109510903 B CN109510903 B CN 109510903B CN 201811366099 A CN201811366099 A CN 201811366099A CN 109510903 B CN109510903 B CN 109510903B
- Authority
- CN
- China
- Prior art keywords
- call
- calling
- identified
- called
- group
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/42—Systems providing special services or facilities to subscribers
- H04M3/436—Arrangements for screening incoming calls, i.e. evaluating the characteristics of a call before deciding whether to answer it
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Technology Law (AREA)
- Telephonic Communication Services (AREA)
Abstract
A method of identifying an international fraud number, comprising: dividing all call records of the research day into a plurality of call groups according to the international long-distance area number of a calling party and the called area, setting a plurality of investigation time points in one day, calculating the call volume of each call group at each investigation time point, and writing the international long-distance area number of the calling party, the called area and the investigation time points of the call group into the sudden change record of the call volume of the day when the call volume of one call group at the investigation time points exceeds the dynamic warning value of the combined call volume and is more than or equal to the lower limit value of the sudden change of the combined call volume; and step two, extracting the calling record of the calling number to be identified in the research day, and judging whether the international long distance area number, the called number area and the calling time of the calling number to be identified exist in the sudden change record of the calling amount in the day, if so, the calling number to be identified is a suspected international fraud number. The invention belongs to the technical field of information, and can prevent and control the sudden change of the call volume of the international incoming call and accurately identify the international fraud number.
Description
Technical Field
The invention relates to a method for identifying an international fraud number, belonging to the technical field of information.
Background
In recent years, fraud calls have become a focus of social attention, and as national relevant departments and operators have strengthened the supervision and treatment of domestic illegal calls, fraud and other illegal calls are more transferred to international calls, a high rate of fraud calls exists among international calls.
Patent application CN201510740425.0 (application name: a method and apparatus for preventing and controlling international fraud calls, application date: 2015-11-04, applicant: china mobile communication group company) discloses a method and apparatus for preventing and controlling international fraud calls, comprising: collecting international call data; analyzing and identifying the international incoming call data based on call characteristics, and screening the international fraud telephone numbers to be confirmed from the international incoming call data; verifying the international fraud telephone number to be confirmed according to the complaint sample data to obtain the international fraud telephone number; intercepting a call initiated by the international fraud telephone number. The technical scheme needs to analyze and identify the call data of each international incoming call in the whole network, and when the call volume of a certain country to a certain region suddenly increases, the resources of a server for preventing and controlling international fraud calls in the region are greatly occupied and consumed.
Therefore, how to effectively prevent and control the international calls with sudden changes of call volume and accurately identify the international fraud numbers becomes a technical problem which needs to be solved by technicians urgently.
Disclosure of Invention
In view of the above, an object of the present invention is to provide a method for identifying an international fraud number, which can effectively prevent and control an international call with a sudden change in call volume and accurately identify the international fraud number.
In order to achieve the above object, the present invention provides a method of recognizing an international fraud number, comprising:
step one, dividing all call records of a research day into a plurality of call groups according to the international long-distance area number to which a calling number of the call belongs and the area to which a called number belongs, wherein the international long-distance area numbers to which the calling number of all call records in each call group belong are the same, the area to which the called number belongs is also the same, a plurality of investigation time points of sudden change of call quantity are set in one day, calculating the call quantity of each call group at each investigation time point of the research day, and writing the international long-distance area number to which the calling number of the call group belongs, the area to which the called number belongs and the corresponding investigation time points into the sudden change record of the call quantity of the current day when the call quantity of one call group at one investigation time point exceeds a dynamic warning value of the combined call quantity and is more than or equal to a lower limit value of sudden increase of the combined call quantity;
step two, extracting the call record of the calling number to be identified from all the call records of the research day, and judging the call record to be identified
The international toll number to which the other calling number belongs, the area to which the called number belongs in each extracted call record and whether the call time exist in the call quantity mutation record of the day, if so, the calling number to be identified is a suspected international fraud number,
the specific calculation process of the combined call volume dynamic alert value of one call group at one investigation point on the study day is as follows:
step A1, extracting call records in a certain historical time period before the study date, and dividing the call records in the historical time period into a plurality of historical call groups, wherein the international long distance area numbers of the calling numbers of all the call records in each historical call group are the same, and the areas to which the called numbers belong are also the same;
step A2, searching a historical call group having the same international long distance area code to which the calling number belongs and the same area to which the called number belongs as the call group, counting the call volume of the historical call group at the investigation time point every day in a historical time period, then arranging the call volume of the historical call group at the investigation time point every day in the historical time period according to the sequence from small to large, selecting the quarter quantile, the median and the three-quarter quantile of the call volume of the historical call group at the investigation time point in the historical time period, and then calculating the combined call volume dynamic warning value of the call group at the investigation time point on the study day:
wherein the content of the first and second substances,
is the combined call volume dynamic warning value of the ith call group at the jth investigation point on the study day,
is the median of call volume of the historical call group of the international long distance area code to which the calling number belongs and the area to which the called number belongs in the historical time period at the j investigation time point, which has the same calling number with the ith call group,
is one quarter of the calling quantity of the historical calling group which has the same international long distance area number to which the calling number belongs and the area to which the called number belongs at the j investigation time point in the historical time periodThe number of the tertiles is three,
is the quarter-fraction of the calling quantity of the historical calling group of the international long distance area code to which the calling number belongs and the area to which the called number belongs in the historical calling group with the same calling group as the ith calling group at the jth investigation time point in the historical time period, α is an alarm value adjusting coefficient, and the value of the alarm value adjusting coefficient is a real number which is greater than or equal to 1.5.
Compared with the prior art, the invention has the beneficial effects that: the invention can effectively monitor the call quantity mutation condition of a certain area in a certain country, firstly, the call quantity mutation record is obtained from the international call of the whole network, and then, the calling number belonging to the call quantity mutation is analyzed and identified, thereby accurately identifying the international fraud number, the calculation method is simple and easy to implement, and is suitable for popularization and application of the whole network; the invention adopts various time granularities for analysis, constructs a combined call volume dynamic warning value by using the call volume indexes of small time granularities (such as 1 hour), thereby more swiftly capturing the call volume mutation situation, and simultaneously analyzes the calling number which accords with the call volume mutation characteristic by using the communication indexes of larger time granularities (such as 1 day), thereby more accurately describing the fraud behavior characteristic under the condition of reading more call records.
Drawings
FIG. 1 is a flow chart of a method of identifying international fraud numbers of the present invention.
Fig. 2 is a specific flowchart for calculating the dynamic warning value of the combined call volume at an investigation point of the study day for one of the call groups.
Fig. 3 is a specific operation flowchart of writing the international long distance area number to which the calling number of the calling group belongs, the area to which the called number belongs, and the corresponding investigation time point into the call volume mutation record of the day when the call volume of one of the call groups at one investigation time point exceeds the dynamic warning value of the combined call volume and is greater than or equal to the lower limit value of the combined call volume mutation in step one of fig. 1.
FIG. 4 is a flowchart illustrating the detailed operation of setting a research time point and further confirming whether the calling number to be identified is an international fraud number according to a plurality of communication indexes within 24 hours before the research time point when the international long distance area code to which the calling number to be identified belongs, the area to which the called number belongs in the extracted one of the call records, and the call time are judged to be present in the call volume mutation record of the day in step two of FIG. 1.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the accompanying drawings.
As shown in FIG. 1, the present invention provides a method for identifying an international fraud number, comprising:
step one, dividing all call records of a research day into a plurality of call groups according to the international long-distance area number to which a calling number of the call belongs and the area to which a called number belongs, wherein the international long-distance area numbers to which the calling number of all call records in each call group belong are the same, the area to which the called number belongs is also the same, a plurality of investigation time points of sudden change of call quantity are set in one day, calculating the call quantity of each call group at each investigation time point of the research day, and writing the international long-distance area number to which the calling number of the call group belongs, the area to which the called number belongs and the corresponding investigation time points into the sudden change record of the call quantity of the current day when the call quantity of one call group at one investigation time point exceeds a dynamic warning value of the combined call quantity and is more than or equal to a lower limit value of sudden increase of the combined call quantity;
and step two, extracting the call records of the calling number to be identified from all the call records of the current day, judging whether the international long distance area number to which the calling number to be identified belongs, the area to which the called number in each extracted call record belongs and the call time exist in the call quantity mutation record of the current day, and if so, indicating that the calling number to be identified is a suspected international fraud number.
In the first step, a plurality of investigation time points of call quantity mutation are set in a day, and the method may further include:
the method comprises the steps of dividing the time of day into a plurality of time periods according to a preset time interval, wherein the starting node of each time period is an investigation time point. For example, in practical applications, one investigation point may be set every hour. The call quantity mutation refers to the condition that a certain international long distance area code is suddenly increased in a certain area; when judging whether the call volume exceeds the dynamic warning value of the combined call volume, it is also necessary to judge whether the call volume is also greater than or equal to the lower limit value of the sudden increase of the combined call volume.
The combined call volume dynamic alert value of each call group at each examination point on the study day can be calculated according to the call volume of the call group at the corresponding examination point in the historical call records every day. As shown in fig. 2, the specific calculation process of the combined call volume dynamic alert value of one call group at one investigation point on the study day may be as follows:
step A1, extracting call records in a certain historical time period before the study date, and dividing the call records in the historical time period into a plurality of historical call groups, wherein the international long distance area numbers of the calling numbers of all the call records in each historical call group are the same, and the areas to which the called numbers belong are also the same;
step A2, searching a historical call group having the same international long distance area code to which the calling number belongs and the same area to which the called number belongs as the call group, counting the call volume of the historical call group at the investigation time point every day in a historical time period, then arranging the call volume of the historical call group at the investigation time point every day in the historical time period according to the sequence from small to large, selecting the quarter quantile, the median and the three-quarter quantile of the call volume of the historical call group at the investigation time point in the historical time period, and then calculating the combined call volume dynamic warning value of the call group at the investigation time point on the study day:
wherein the content of the first and second substances,
is the combined call volume dynamic warning value of the ith call group at the jth investigation point on the study day,
is the median of call volume of the historical call group of the international long distance area code to which the calling number belongs and the area to which the called number belongs in the historical time period at the j investigation time point, which has the same calling number with the ith call group,
is three quarters of the calling quantity of the historical calling group which has the same international long distance area number to which the calling number belongs and the area to which the called number belongs at the j investigation time point in the historical time period,
the number of the quarter quantiles of the call quantity of the historical call group of the international long distance area code to which the calling number belongs and the area to which the called number belongs in the historical call group with the same calling number as the ith call group at the jth investigation time point in the historical time period, α is a warning value adjusting coefficient which can be used for adjusting the sensitivity degree of the dynamic warning value of the combined call quantity, the value of the dynamic warning value of the combined call quantity is a real number which is greater than or equal to 1.5, and the larger the value of α is, the less sensitive the dynamic warning value of the combined call quantity is.
When a certain calling group has call quantity mutation at one investigation time point, whether call death your call behavior exists can be further analyzed and calculated, and therefore the international long distance area number to which the calling number belongs, the area to which the called number belongs and the investigation time point corresponding to the call quantity mutation caused by international fraud are more accurately obtained. As shown in fig. 3, in the first step, when the call volume of one of the call groups at an investigation point exceeds the dynamic warning value of the combined call volume and is greater than or equal to the lower limit value of the sudden increase of the combined call volume, the international long distance area number to which the calling number of the call group belongs, the area to which the called number belongs, and the corresponding investigation point are written into the sudden change record of the call volume on the day, further comprising:
step B1, when the call volume of one call group at an investigation point exceeds the dynamic warning value of the combined call volume and is more than or equal to the lower limit value of the sudden increase of the combined call volume, selecting n called numbers with the most called times from the call records of the call group at the corresponding investigation point, calculating the called proportion, the average call duration and the average call completing rate of the n called numbers in the call group, wherein the value of n can be set according to the actual service requirement;
step B2, calculating the harassment call-death identification value of the call group at the corresponding investigation time point:
the invention comprises a call group, a call group controller and a communication module, wherein the call group controller is used for controlling the call group controller to be in a call state, and the call group controller is used for controlling the call group controller to be in a call state;
step B3, judging whether the call set has a call death-harassment identification value is _ hsn at the corresponding investigation time point as 1? If yes, the calling group is indicated to have a calling behavior of calling death in the calling record of the corresponding investigation time point, and the process is ended; if not, writing the international long distance area number to which the calling number of the calling group belongs, the area to which the called number belongs and the corresponding investigation time point into the call quantity mutation record of the day.
In the second step, when it is determined that the international long distance area code to which the calling number to be identified belongs, the area to which the called number in the extracted one of the call records belongs, and the call time exist in the call volume mutation record of the day, a research time point may be set, and whether the calling number to be identified is an international fraud number is further determined according to a plurality of communication indexes of the calling number to be identified within 24 hours before the research time point, as shown in fig. 4, the second step further includes the following steps:
In step 23, the international fraud identifier of the calling number to be identified is calculated, and any one or a combination of the following steps may be adopted:
calculating 1 st international fraud identifier of calling number to be identified:
and determine if isgz1 is 1? If yes, the calling number to be identified is a suspected international fraud number, wherein ag _ fcd is the average first-pass call conversation duration of the calling number to be identified, cd _ lsd is the called dispersion of the calling number to be identified, and scr60 is less than 60 seconds of the calling number to be identifiedThe ratio of the short calls of (a) to all calls,
calculating the 2 nd international fraud identifier of the calling number to be identified:
and determine if isgz2 is 1? If so, it indicates that the calling number to be identified is a suspected international fraud number, where cdm is the maximum value of the call duration of the calling number to be identified, zd is the average ring duration of the calling number to be identified,
calculating a 3 rd international fraud identifier of the calling number to be identified:
and determine if isgz3 is 1? If yes, the calling number to be identified is a suspected international fraud number, wherein hcg is the total call interval of the calling number to be identified within one hour, and when the total call interval is calculated, the call interval exceeding 1 hour is not counted, and the time unit is second.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (5)
1. A method of identifying an international fraud number, comprising:
step one, dividing all call records of a research day into a plurality of call groups according to the international long-distance area number to which a calling number of the call belongs and the area to which a called number belongs, wherein the international long-distance area numbers to which the calling number of all call records in each call group belong are the same, the area to which the called number belongs is also the same, a plurality of investigation time points of sudden change of call quantity are set in one day, calculating the call quantity of each call group at each investigation time point of the research day, and writing the international long-distance area number to which the calling number of the call group belongs, the area to which the called number belongs and the corresponding investigation time points into the sudden change record of the call quantity of the current day when the call quantity of one call group at one investigation time point exceeds a dynamic warning value of the combined call quantity and is more than or equal to a lower limit value of sudden increase of the combined call quantity;
step two, extracting the call records of the calling number to be identified from all the call records of the current day, judging whether the international long distance area number to which the calling number to be identified belongs, the area to which the called number in each extracted call record belongs and the call time exist in the call quantity mutation record of the current day, if so, indicating that the calling number to be identified is a suspected international fraud number,
the specific calculation process of the combined call volume dynamic alert value of one call group at one investigation point on the study day is as follows:
step A1, extracting call records in a certain historical time period before the study date, and dividing the call records in the historical time period into a plurality of historical call groups, wherein the international long distance area numbers of the calling numbers of all the call records in each historical call group are the same, and the areas to which the called numbers belong are also the same;
step A2, searching a historical call group having the same international long distance area code to which the calling number belongs and the same area to which the called number belongs as the call group, counting the call volume of the historical call group at the investigation time point every day in a historical time period, then arranging the call volume of the historical call group at the investigation time point every day in the historical time period according to the sequence from small to large, selecting the quarter quantile, the median and the three-quarter quantile of the call volume of the historical call group at the investigation time point in the historical time period, and then calculating the combined call volume dynamic warning value of the call group at the investigation time point on the study day:
wherein the content of the first and second substances,
is the combined call volume dynamic warning value of the ith call group at the jth investigation point on the study day,
is the median of call volume of the historical call group of the international long distance area code to which the calling number belongs and the area to which the called number belongs in the historical time period at the j investigation time point, which has the same calling number with the ith call group,
is three quarters of the calling quantity of the historical calling group which has the same international long distance area number to which the calling number belongs and the area to which the called number belongs at the j investigation time point in the historical time period,
is the quarter-fraction of the calling quantity of the historical calling group of the international long distance area code to which the calling number belongs and the area to which the called number belongs in the historical calling group with the same calling group as the ith calling group at the jth investigation time point in the historical time period, α is an alarm value adjusting coefficient, and the value of the alarm value adjusting coefficient is a real number which is greater than or equal to 1.5.
2. The method of claim 1, wherein in step one, the time points for the call volume mutation are set in a day, and further comprising:
the method comprises the steps of dividing the time of day into a plurality of time periods according to a preset time interval, wherein the starting node of each time period is an investigation time point.
3. The method according to claim 1, wherein in step one, when the call volume of one of the call groups at an investigation point exceeds the dynamic warning value of the combined call volume and is greater than or equal to the lower limit value of the sudden increase of the combined call volume, the international long distance area number to which the calling number of the call group belongs, the area to which the called number belongs, and the corresponding investigation point are written into the sudden change record of the call volume at the day, further comprising:
step B1, when the call volume of one call group at an investigation point exceeds the dynamic warning value of the combined call volume and is more than or equal to the lower limit value of the sudden increase of the combined call volume, selecting n called numbers with the most called times from the call records of the call group at the corresponding investigation point, and calculating the called proportion, the average call duration and the average call completing rate of the n called numbers in the call group;
step B2, calculating the harassment call-death identification value of the call group at the corresponding investigation time point:
the top _ cledr is the called proportion of n called numbers with the most called times in a calling group, the value of the top _ cledr is the ratio of the called times of the n called numbers to the called times of all the called numbers in the calling group, the top _ avgcd is the average call duration of the n called numbers with the most called times, the top _ avgjtr is the average call rate of the n called numbers with the most called times, and the CR, the CD and the JTR are respectively a called proportion threshold, an average call duration threshold and an average call rate threshold for judging whether the numbers are harassment calls;
and B3, judging whether the call death harassment identification value is _ hsn of the call group at the corresponding investigation time point is 1, if not, writing the international long distance area number to which the calling number of the call group belongs, the area to which the called number belongs and the corresponding investigation time point into the call quantity mutation record of the day.
4. The method of claim 1, wherein step two further comprises:
step 21, calculating the number of calls of the calling number to be identified to the called number in the historical time period, and judging whether the number of calls is 0, if so, continuing the next step; if not, the calling number to be identified is not a suspected international fraud number, and the process is ended;
step 22, setting a research time point, using the time point of 24 hours forward from the research time point as an initial time point, then obtaining the call record of the calling number to be identified from the initial time point to the research time point, calculating the calling volume of the calling number to be identified from the initial time point to the research time point, and judging whether the calling volume is greater than or equal to the lower limit value of the calling volume, if so, continuing the next step; if not, the calling number to be identified is not a suspected international fraud number, and the process is ended;
step 23, calculating a plurality of communication indexes from the starting time point to the research time point of the calling number to be identified, and then calculating the international fraud identifier of the calling number to be identified according to the plurality of calculated communication indexes, so as to determine whether the calling number to be identified is a suspected international fraud number.
5. The method as claimed in claim 4, wherein in step 23, the international fraud identifier of the calling number to be identified is calculated by any one or a combination of the following steps:
calculating 1 st international fraud identifier of calling number to be identified:
and judges whether isgz1 is 1, if yes, it indicates that the calling number to be identified is a suspected international fraud number, wherein ag _ fcd is the average first-through calling duration of the calling number to be identified, cd _ lsd is the called dispersion of the calling number to be identified, scr60 is the ratio of short calls of less than 60 seconds of the calling number to be identified in all calls,
calculating the 2 nd international fraud identifier of the calling number to be identified:
and judges whether isgz2 is 1, if yes, it indicates that the calling number to be identified is a suspected international fraud number, where cdm is the maximum value of the call duration of the calling number to be identified, zd is the average ring duration of the calling number to be identified,
calculating a 3 rd international fraud identifier of the calling number to be identified:
and judging whether the isgz3 is 1, if yes, indicating that the calling number to be identified is a suspected international fraud number, wherein hcg is the total call interval of the calling number to be identified within one hour, and when calculating the total call interval, the call interval exceeding 1 hour is not counted, and the time unit is second.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811366099.1A CN109510903B (en) | 2018-11-16 | 2018-11-16 | Method for identifying international fraud number |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811366099.1A CN109510903B (en) | 2018-11-16 | 2018-11-16 | Method for identifying international fraud number |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109510903A CN109510903A (en) | 2019-03-22 |
| CN109510903B true CN109510903B (en) | 2020-08-11 |
Family
ID=65748732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811366099.1A Active CN109510903B (en) | 2018-11-16 | 2018-11-16 | Method for identifying international fraud number |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109510903B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112243067B (en) * | 2019-07-16 | 2021-09-10 | 中国移动通信集团浙江有限公司 | Anti-set dialing method, system, server and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100138416A (en) * | 2009-06-25 | 2010-12-31 | 주식회사 엘지유플러스 | Mobile communication terminal and computer for telephone number searching and registration and controlling method for the same |
| CN102196099A (en) * | 2010-03-10 | 2011-09-21 | 成都市华为赛门铁克科技有限公司 | Voice call detection method and device |
| CN104253908A (en) * | 2014-09-18 | 2014-12-31 | 北京奇虎科技有限公司 | Unknown number grading method, unknown number marking method and unknown number marking device |
| CN104735671A (en) * | 2015-02-27 | 2015-06-24 | 腾讯科技（深圳）有限公司 | Malicious call recognition method and device |
| CN106686264A (en) * | 2016-11-04 | 2017-05-17 | 国家计算机网络与信息安全管理中心 | Method and system for fraud call screening and analyzing |
| CN107046593A (en) * | 2017-04-07 | 2017-08-15 | 北京安云世纪科技有限公司 | A kind of harassing call hold-up interception method and device |
| CN108462785A (en) * | 2017-02-21 | 2018-08-28 | 中国移动通信集团浙江有限公司 | A kind of processing method and processing device of malicious call phone |
-
2018
- 2018-11-16 CN CN201811366099.1A patent/CN109510903B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100138416A (en) * | 2009-06-25 | 2010-12-31 | 주식회사 엘지유플러스 | Mobile communication terminal and computer for telephone number searching and registration and controlling method for the same |
| CN102196099A (en) * | 2010-03-10 | 2011-09-21 | 成都市华为赛门铁克科技有限公司 | Voice call detection method and device |
| CN104253908A (en) * | 2014-09-18 | 2014-12-31 | 北京奇虎科技有限公司 | Unknown number grading method, unknown number marking method and unknown number marking device |
| CN104735671A (en) * | 2015-02-27 | 2015-06-24 | 腾讯科技（深圳）有限公司 | Malicious call recognition method and device |
| CN106686264A (en) * | 2016-11-04 | 2017-05-17 | 国家计算机网络与信息安全管理中心 | Method and system for fraud call screening and analyzing |
| CN108462785A (en) * | 2017-02-21 | 2018-08-28 | 中国移动通信集团浙江有限公司 | A kind of processing method and processing device of malicious call phone |
| CN107046593A (en) * | 2017-04-07 | 2017-08-15 | 北京安云世纪科技有限公司 | A kind of harassing call hold-up interception method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109510903A (en) | 2019-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3324607B1 (en) | Fraud detection on a communication network | |
| CN108924333B (en) | Fraud telephone identification method, device and system | |
| CN106791220B (en) | Method and system for preventing telephone fraud | |
| CN107819747B (en) | Telecommunication fraud association analysis system and method based on communication event sequence | |
| CN106534463B (en) | Strange call processing method and device, terminal and server | |
| CN104038648A (en) | Method and device for recognizing crank calls | |
| CN109688275A (en) | Harassing call recognition methods, device and storage medium | |
| CN108093405A (en) | A kind of fraudulent call number analysis method and apparatus | |
| CN103581976B (en) | The recognition methods of community and device | |
| CN105825129A (en) | Converged communication malicious software identification method and system | |
| CN101389085B (en) | Rubbish short message recognition system and method based on sending behavior | |
| CN111917574A (en) | Social network topology model and construction method thereof, user confidence degree and intimacy degree calculation method and telecommunication fraud intelligent interception system | |
| CN111131627B (en) | Method, device and readable medium for detecting personal harmful call based on streaming data atlas | |
| CN109274834B (en) | Express number identification method based on call behavior | |
| CN110113748B (en) | Crank call monitoring method and device | |
| CN109510903B (en) | Method for identifying international fraud number | |
| CN103139824A (en) | Method and device for identifying very annoying people (VAP) in mobile communication network | |
| CN110167030B (en) | Method, device, electronic equipment and storage medium for identifying crank calls | |
| CN109474755B (en) | Abnormal telephone active prediction method, system and computer readable storage medium based on sequencing learning and ensemble learning | |
| CN108198086B (en) | Method and device for identifying disturbance source according to communication behavior characteristics | |
| CN104883705A (en) | Problem positioning method for data service complaints and device thereof | |
| CN206115541U (en) | System of falsifying is prevented to betting data | |
| CN103124430A (en) | Method and system for locating indoor users | |
| CN100405870C (en) | System for collecting and using user characteristic data to identify user, and method thereof | |
| CN115659217A (en) | Fraud recognition model training method and device, electronic equipment and storage medium |
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 | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 310013 4th floor, No.398 Wensan Road, Xihu District, Hangzhou City, Zhejiang Province Patentee after: Xinxun Digital Technology (Hangzhou) Co.,Ltd. Address before: 310013 4th floor, No.398 Wensan Road, Xihu District, Hangzhou City, Zhejiang Province Patentee before: EB Information Technology Ltd. |