CN107770777B - Method for identifying recorded fraud calls - Google Patents
Method for identifying recorded fraud calls Download PDFInfo
- Publication number
- CN107770777B CN107770777B CN201710918601.4A CN201710918601A CN107770777B CN 107770777 B CN107770777 B CN 107770777B CN 201710918601 A CN201710918601 A CN 201710918601A CN 107770777 B CN107770777 B CN 107770777B
- Authority
- CN
- China
- Prior art keywords
- calling
- called
- call
- time period
- daily
- 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
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/12—Detection or prevention of fraud
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Computer Networks & Wireless Communication (AREA)
- Telephonic Communication Services (AREA)
- Telephone Function (AREA)
Abstract
A method for identifying a fraud-recorded telephone, comprising: step one, extracting all calling numbers from a call record of a research day, and forming a calling number set to be identified; step two, sequentially extracting each calling number from the set of calling numbers to be identified, forming a time period by a plurality of days including the research day, extracting the call record of each calling number in the time period, and calculating a plurality of communication indexes of each calling number in the time period; and step three, judging the daily calling frequency index grade of each calling number according to the daily calling frequency of the calling number, and judging whether each calling number is a fraud number according to the daily calling frequency index grade of each calling number and a plurality of communication indexes in a time period. The invention belongs to the field of communication, and can effectively identify 'one sound' recording fraud telephones from massive existing network communication data.
Description
Technical Field
The invention relates to a method for identifying a recorded fraud call, belonging to the field of communication.
Background
Currently, there are three main ways to attract the first step of fraud: firstly, lawbreakers post small advertisements or posts on the internet at the street, and after the victims see the fraud information, the lawbreakers actively call the lawbreakers; secondly, lawless persons mass-send fraud short messages to induce the victims to be cheated; third, lawless persons dial the 'one-sound' telephone, and the victim hears the fraud voice information and the contact way of the fraud when dialing back. The first mode is that the victim actively calls out and is difficult to defend; the second way cannot perform effective verification work; therefore, how to effectively identify the third way (i.e., "one sound" sound recording fraud calls) from the massive amount of existing network communication data has become a technical problem generally focused on by technicians.
Some technical solutions for recognizing fraud calls are also proposed, for example, patent application CN 201611110847.0 (application name: a call callback processing method and device, applicant: beijing tiger science and technology ltd., application date: 2016-12-02) provides a call callback method and device, wherein a mobile terminal receives a calling request from a calling terminal and acquires a user number of the calling terminal; the mobile terminal judges whether the user number meets the condition of a preset shielding callback operation; the mobile terminal determines that the user number meets the condition of preset shielding callback operation, the mobile terminal shields the callback operation of the user number, the condition of shielding a suspicious number is set in the mobile terminal, when the suspicious number is in call, according to the shielding condition, fraud screening is carried out on the suspicious number, the callback of the suspicious number is shielded according to a screening result, and when the shielding duration does not reach the preset duration, the user dials the suspicious number, and the mobile terminal can send corresponding reminding messages. The technical scheme is mainly used for screening suspicious telephone numbers of incoming calls for individual users, and completely does not relate to the identification of 'one sound' fraud telephones from the current network communication data.
Therefore, how to effectively identify the 'one-sound' recording fraud telephone from the massive existing network communication data has become a technical problem which needs to be solved by technicians urgently.
Disclosure of Invention
In view of the above, the present invention provides a method for identifying phishing recorded calls, which can effectively identify 'one sound' phishing recorded calls from a large amount of existing network communication data.
In order to achieve the above object, the present invention provides a method for identifying a fraud-recorded telephone, comprising:
step one, extracting all calling numbers from a call record of a research day, and forming a calling number set to be identified;
step two, sequentially extracting each calling number from the set of calling numbers to be identified, then forming a time period by a plurality of days including the research day, extracting the call record of each calling number in the time period, and calculating a plurality of communication indexes of each calling number in the time period, wherein the communication indexes can include but are not limited to: daily calling frequency, call completing rate, original called dispersion, calling occupation ratio of which the calling time is less than the minimum threshold value of normal calling, average calling time, average ringing time and the number of original called fields in calling signaling which are null values;
step three, judging the daily calling frequency index grade of each calling number according to the daily calling frequency of the calling number, then judging whether each calling number is a fraud number according to the daily calling frequency index grade and a plurality of communication indexes in a time period,
the third step further comprises:
step 31, calculating a dispersion stability value discrete _ coarse _ stability _ T and an appearance ratio of the calling early-released tag of each calling number in the time period according to the original called dispersion ori _ discrete _ T of the calling number in the time period and the occurrence frequency calilingrel _ early _ num _ T of the calling early-released tag of a calling result field in a calling signaling, wherein,
ori_discretetis the original called dispersion of the T-th day in the time period, dis _ tie _ num _ T is the number of active days of the calling number in the time period, T is the total number of days in the time period,
calling _ early _ num _ T is the number of times of occurrence of calling early-release labels of calling result fields in calling signaling of the calling number in a time period, and calling _ freq _ T is the calling frequency of the calling number in the time period;
step 32, judging whether the daily calling frequency of the calling number on the current day is (call _ freq _ min, call _ freq _ max) or not]If yes, the calling number belongs to the medium level of daily calling frequency, and fraud suspiciousness of the calling number is calculated:
wherein oc _ null _ T is the number of null values of the original called field in the call signaling in the time period, ratio _ T is the call completing rate in the time period, avg _ alert _ T is the average ringing duration in the time period, ori _ discrete _ T is the original called dispersion in the time period, and then go to step 33, where call _ freq _ min and call _ freq _ max are the minimum threshold and the maximum threshold of the daily call frequency, respectively;
step 33, judging whether Z _ tag is 1 and whether the calingibrel _ early _ rate _ T is less than 0.2, if yes, turning to step 34; if not, adjusting Z _ tag to 0, and then turning to step 34;
step 34, determining whether the Z _ tag is 1, if yes, marking the calling number as a fraud number,
in step 32, when the daily calling frequency of the calling number on the current day is not between (call _ freq _ min, call _ freq _ max), the method further includes:
step 3211, judging whether the daily calling frequency of the calling number on the current day of the research is greater than call _ freq _ max, if so, the calling number belongs to a high level of daily calling frequency, and calculating the fraud suspicion degree of the calling number:
wherein avg _ talk _ T is an average call duration in a time period, avg _ alert _ T is an average ringing duration in the time period, and talk _ below _ T is a call duty ratio of the call duration in the time period being smaller than a normal call minimum threshold, and then go to step 3212;
step 3212, determining whether Z _ tag is 1, and both ori _ discrete _ T and discrete _ coarse _ stability _ T are greater than or equal to 0.9, if yes, going to step 34; if not, adjust Z tag to 0, then go to step 34,
in step 32, when the daily calling frequency of the calling number on the current day is not between (call _ freq _ min, call _ freq _ max), the method further includes:
step 3221, judge whether the daily calling frequency of the calling number in the time period is in [1, call _ freq _ min]If yes, the calling number belongs to a low level of daily calling frequency, and fraud suspected degree of the calling number is calculated:
then go to step 3222;
step 3222, determine whether Z _ tag is 1 and whether containment _ early _ rate _ T is less than 0.2, if yes, go to step 34, if no, adjust Z _ tag to 0, and then go to step 34.
Compared with the prior art, the invention has the beneficial effects that: the invention extracts the call records from the existing network, and then judges whether each calling number is a fraud number according to the daily call frequency index grade of the calling number and a plurality of corresponding communication indexes, thereby effectively identifying 'one sound' recording fraud calls from massive existing network communication data and providing help for communication and public security departments to attack criminals; by analyzing the characteristics of the 'one-sound' sound recording fraud telephone, the fraud number can be a calling party or a called party due to the callback of a cheater, so that the fraud number can be identified from the calling number side and the called number side, and the 'one-sound' sound recording fraud behaviors such as 'rewarding and asking for children' can be effectively attacked comprehensively and accurately.
Drawings
FIG. 1 is a flow chart of an identification method of a fraud-recorded telephone of the present invention.
Fig. 2 is a flow chart of the present invention for identifying a fraud number from the called number side.
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 method for identifying a fraud-recorded telephone of the present invention comprises:
step one, extracting all calling numbers from a call record of a research day, and forming a calling number set to be identified;
step two, sequentially extracting each calling number from the set of calling numbers to be identified, then forming a time period by a plurality of days including the research day, extracting the call record of each calling number in the time period, and calculating a plurality of communication indexes of each calling number in the time period, wherein the communication indexes can include but are not limited to: daily calling frequency, call completing rate, original called dispersion, calling occupation ratio of which the calling time is less than the minimum threshold value of normal calling, average calling time, average ringing time and the number of original called fields in calling signaling which are null values;
the original called field content in the call signaling is a called number dialed by a calling number, the called field content is a called number receiving a calling call, and when call forwarding does not occur, the original called field content is generally a null value;
and step three, judging the daily calling frequency index grade of each calling number according to the daily calling frequency of the calling number, and judging whether each calling number is a fraud number according to the daily calling frequency index grade of each calling number and a plurality of communication indexes in a time period.
The third step can further comprise:
step 31, calculating a dispersion stability value discrete _ coarse _ stability _ T and an appearance ratio of the calling early-released tag of each calling number in the time period according to the original called dispersion ori _ discrete _ T of the calling number in the time period and the occurrence frequency calilingrel _ early _ num _ T of the calling early-released tag of a calling result field in a calling signaling, wherein,
ori_discretetis the original called dispersion of the T-th day in the time period, dis _ tie _ num _ T is the number of active days of the calling number in the time period, T is the total number of days in the time period,
calling _ early _ num _ T is the number of times of occurrence of calling early-release labels of calling result fields in calling signaling of the calling number in a time period, and calling _ freq _ T is the calling frequency of the calling number in the time period;
step 32, judging whether the daily calling frequency of the calling number on the current day is (call _ f)req_min，call_freq_max]Is there? If yes, the calling number belongs to the medium level of daily calling frequency, and fraud suspiciousness of the calling number is calculated:
wherein oc _ null _ T is the number of null values of the original called field in the call signaling in the time period, rate _ T is the call completing rate in the time period, avg _ alert _ T is the average ringing duration in the time period, ori _ discrete _ T is the original called dispersion in the time period, and then go to step 33; if not, go to step 34;
wherein, call _ freq _ min and call _ freq _ max are the minimum threshold and the maximum threshold of daily call frequency, respectively, for example, call _ freq _ min and call _ freq _ max may be set to 3 and 5, respectively;
step 33, determine whether Z _ tag is 1 and whether containment _ early _ rate _ T is less than 0.2? If so, go to step 38; if not, adjusting Z _ tag to 0, and then turning to step 38;
step 34, judging whether the daily calling frequency of the calling number on the current day of the research is greater than call _ freq _ max? If yes, the calling number belongs to a high level of daily calling frequency, and fraud suspiciousness of the calling number is calculated:
wherein avg _ talk _ T is an average call duration in the time period, avg _ alert _ T is an average ringing duration in the time period, and talk _ below _ T is a call duty ratio of the call duration in the time period smaller than a normal call minimum threshold, and then go to step 35; if not, go to step 36;
step 35, determine if Z _ tag is 1 and both ori _ discrete _ T and discrete _ default _ stability _ T are greater than or equal to 0.9? If so, go to step 38; if not, adjusting Z _ tag to 0, and then turning to step 38;
step 36, judging whether the daily calling frequency of the calling number in the time period is dailyAre all in [1, call _ freq _ min ]]Is there? If yes, the calling number belongs to the low level of daily calling frequency, and fraud suspected degree of the calling number is calculated:
then go to step 37; if not, the process is ended;
step 37, determine whether Z _ tag is 1 and whether containment _ early _ rate _ T is less than 0.2? If yes, go to step 38, if no, adjust Z _ tag to 0, then go to step 38;
step 38, determine whether Z _ tag is 1? If so, the calling number is marked as a fraud number.
Since the fraud number may be both the calling party and the called party due to being called back by the fraudster in the call record, the invention can simultaneously identify the fraud number from the called number side in addition to identifying the fraud number from the calling number side of the call record, as shown in fig. 2, the invention also includes:
step A1, extracting the call record of each calling number from the call record of the research day, and calculating a plurality of communication indexes of each calling number as the calling number in the research day, wherein the communication indexes can include but are not limited to daily call frequency, call completing rate, average call duration, average ringing duration, calling releasing rate and called dispersion;
step A2, judging whether all communication indexes of each calling number are in the suspicious threshold range of the callback number, when all communication indexes of the calling number are in the suspicious threshold range of the callback number, adding the calling number into the suspicious set of the callback number, and extracting all calling time and corresponding called number (calling _ time) when the calling number is taken as a calling from the call records of the calling numberj，calledj) Wherein, the closing _ timejIs the call time, called, initiated by the calling number to the jth called numberjIs the j (th) called number called by the calling number, thereby forming the called number data set { (calling _ time) of the calling number1，called1)，(calling_time2，called2)，…,(calling_timeN，calledN) N is the total number of called numbers called by the calling number, then whether all calling indexes of the next calling number are within the suspicious threshold range of the callback number is continuously judged until all calling numbers are judged, and the next step is continued; if not, continuously judging whether all call indexes of the next calling number are within the suspicious threshold range of the callback number or not until all calling numbers are judged, and continuing the next step;
according to the actual measurement of the current network, when the suspicious threshold value range of the callback number is set as follows, the callback number of the fraud call can be effectively identified: the daily calling frequency is (0, 5), the call completing rate is (0, 0.1), the average call duration is (0, 5 s), the average ringing duration is (0, 10 s), the calling releasing rate is [0.6, 1], and the called dispersion is [0.8, 1 ]. that is, when the calling frequency of a certain calling number is less than or equal to 5, the call completing rate is less than or equal to 0.1, the average call duration is less than or equal to 5s, the average ringing duration is less than or equal to 10s, the calling releasing rate is greater than or equal to 0.6, and the called dispersion is greater than or equal to 0.8, the calling number is added into the callback suspicious number set;
step A3, extracting each calling number from the callback number suspicious set, extracting each calling time and corresponding called number one by one from the called number data set of the calling number, then analyzing whether the called number before and after the calling time is used as the calling number called by the calling party, if the called number before the calling time is called by the calling number, indicating that the called number and the calling number are normal, and continuing to extract the next calling time and corresponding called number from the called number data set; if the called number has not called the calling number before the time of the call and the called number has called the calling number after between calls, indicating that the calling number is a fraud number, the calling number is marked as a fraud number, the calling number can be manually dialed for further verification to confirm whether it is a fraud number.
Since the fraud phone may be used as a fishing phone to provide the deceased person with voice and other fraud numbers provided by illegal persons, some deceased persons may dial another strange number that he has never dialed before after hearing the recording, and therefore, step a3 may further include:
and judging whether the called number calls an unfamiliar number after the calling time and the call duration between the called number and the unfamiliar number is larger than a normal call maximum threshold, wherein the unfamiliar number is a number which is not called by the called number before the calling time and does not belong to a special number field such as 114, 400, 95 special service, public inspection and the like, if so, the unfamiliar number is a fraud number provided by a fraud person, and the unfamiliar number is marked as a fraud number.
The method identifies the heavy fund fraud telephone numbers 170 and 171 in the current network, and tests prove that the method achieves better technical effects.
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 (4)
1. A method for identifying a fraud-recorded telephone, comprising:
step one, extracting all calling numbers from a call record of a research day, and forming a calling number set to be identified;
step two, sequentially extracting each calling number from the set of calling numbers to be identified, then forming a time period by a plurality of days including the research day, extracting the call record of each calling number in the time period, and calculating a plurality of communication indexes of each calling number in the time period, wherein the communication indexes include but are not limited to: daily calling frequency, call completing rate, original called dispersion, calling occupation ratio of which the calling time is less than the minimum threshold value of normal calling, average calling time, average ringing time and the number of original called fields in calling signaling which are null values;
step three, judging the daily calling frequency index grade of each calling number according to the daily calling frequency of the calling number, then judging whether each calling number is a fraud number according to the daily calling frequency index grade and a plurality of communication indexes in a time period,
the third step further comprises:
step 31, calculating a dispersion stability value discrete _ coarse _ stability _ T and an appearance ratio of the calling early-released tag of each calling number in the time period according to the original called dispersion ori _ discrete _ T of the calling number in the time period and the occurrence frequency calilingrel _ early _ num _ T of the calling early-released tag of a calling result field in a calling signaling, wherein,
ori_discretetis the original called dispersion of the T-th day in the time period, dis _ tie _ num _ T is the number of active days of the calling number in the time period, T is the total number of days in the time period,
calling _ early _ num _ T is the number of times of occurrence of calling early-release labels of calling result fields in calling signaling of the calling number in a time period, and calling _ freq _ T is the calling frequency of the calling number in the time period;
step 32, judging whether the daily calling frequency of the calling number on the current day is (call _ freq _ min, call _ freq _ max) or not]If yes, the calling number belongs to the medium level of daily calling frequency, and fraud suspiciousness of the calling number is calculated:
wherein oc _ null _ T is the number of null values of the original called field in the call signaling in the time period, ratio _ T is the call completing rate in the time period, avg _ alert _ T is the average ringing duration in the time period, ori _ discrete _ T is the original called dispersion in the time period, and then go to step 33, where call _ freq _ min and call _ freq _ max are the minimum threshold and the maximum threshold of the daily call frequency, respectively;
step 33, judging whether Z _ tag is 1 and whether the calingibrel _ early _ rate _ T is less than 0.2, if yes, turning to step 34; if not, adjusting Z _ tag to 0, and then turning to step 34;
step 34, determining whether the Z _ tag is 1, if yes, marking the calling number as a fraud number,
in step 32, when the daily calling frequency of the calling number on the current day is not between (call _ freq _ min, call _ freq _ max), the method further includes:
step 3211, judging whether the daily calling frequency of the calling number on the current day of the research is greater than call _ freq _ max, if so, the calling number belongs to a high level of daily calling frequency, and calculating the fraud suspicion degree of the calling number:
wherein avg _ talk _ T is an average call duration in a time period, avg _ alert _ T is an average ringing duration in the time period, and talk _ below _ T is a call duty ratio of the call duration in the time period being smaller than a normal call minimum threshold, and then go to step 3212;
step 3212, determining whether Z _ tag is 1, and both ori _ discrete _ T and discrete _ coarse _ stability _ T are greater than or equal to 0.9, if yes, going to step 34; if not, adjust Z tag to 0, then go to step 34,
in step 32, when the daily calling frequency of the calling number on the current day is not between (call _ freq _ min, call _ freq _ max), the method further includes:
step 3221, judge whether the daily calling frequency of the calling number in the time period is in [1, call _ freq _ min]If yes, the calling number belongs to a low level of daily calling frequency, and fraud suspected degree of the calling number is calculated:
then go to step 3222;
step 3222, determine whether Z _ tag is 1 and whether containment _ early _ rate _ T is less than 0.2, if yes, go to step 34, if no, adjust Z _ tag to 0, and then go to step 34.
2. The method of claim 1, further comprising:
step A1, extracting the call record of each calling number from the call record of the research day, and calculating a plurality of communication indexes of each calling number as the calling number in the research day, wherein the communication indexes include but are not limited to daily call frequency, call completing rate, average call duration, average ringing duration, calling releasing rate and called dispersion;
step A2, judging whether all communication indexes of each calling number are in the suspicious threshold range of the callback number, when all communication indexes of the calling number are in the suspicious threshold range of the callback number, adding the calling number into the suspicious set of the callback number, and extracting all calling time and corresponding called number (calling _ time) when the calling number is taken as a calling from the call records of the calling numberj，calledj) Wherein, the closing _ timejIs the call time, called, initiated by the calling number to the jth called numberjIs the j (th) called number called by the calling number, thereby forming the called number data set { (calling _ time) of the calling number1，called1)，(calling_time2，called2)，…,(calling_timeN，calledN) N is the total number of called numbers called by the calling number, then whether all calling indexes of the next calling number are within the suspicious threshold range of the callback number is continuously judged until all calling numbers are judged, and the next step is continued; if not, continuously judging whether all call indexes of the next calling number are within the suspicious threshold range of the callback number or not until all calling numbers are judged, and continuing the next step;
step A3, extracting each calling number from the callback number suspicious set, extracting each calling time and corresponding called number one by one from the called number data set of the calling number, then analyzing whether the called number before and after the calling time is used as the calling number called by the calling party, if the called number before the calling time is called by the calling number, continuing to extract the next calling time and corresponding called number from the called number data set; if the called number has not called the calling number before the time of the call and the called number has called the calling number after between calls, the calling number is marked as a fraud number.
3. The method of claim 2, wherein the suspicious threshold range for callback numbers is set as follows: the daily calling frequency is (0, 5), the call completing rate is (0, 0.1), the average call duration is (0, 5 s), the average ringing duration is (0, 10 s), the calling releasing rate is [0.6, 1], and the called dispersion is [0.8, 1 ].
4. The method of claim 2, wherein step a3 further comprises:
and judging whether the called number calls an unfamiliar number after the calling time and the calling time between the called number and the unfamiliar number is larger than a normal calling maximum threshold, wherein the unfamiliar number is a number which is not called by the called number before the calling time and does not belong to a special number field, and if so, marking the unfamiliar number as a fraud number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710918601.4A CN107770777B (en) | 2017-09-30 | 2017-09-30 | Method for identifying recorded fraud calls |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710918601.4A CN107770777B (en) | 2017-09-30 | 2017-09-30 | Method for identifying recorded fraud calls |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107770777A CN107770777A (en) | 2018-03-06 |
| CN107770777B true CN107770777B (en) | 2020-12-25 |
Family
ID=61266859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710918601.4A Active CN107770777B (en) | 2017-09-30 | 2017-09-30 | Method for identifying recorded fraud calls |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107770777B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110401780B (en) * | 2018-04-25 | 2021-05-11 | 中国移动通信集团广东有限公司 | Method and device for identifying fraudulent calls |
| CN110213448B (en) * | 2018-09-13 | 2021-08-24 | 腾讯科技（深圳）有限公司 | Malicious number identification method and device, storage medium and computer equipment |
| CN109274834B (en) * | 2018-09-27 | 2021-04-20 | 杭州东信北邮信息技术有限公司 | Express number identification method based on call behavior |
| CN109583679A (en) * | 2018-09-30 | 2019-04-05 | 国网浙江长兴县供电有限公司 | A kind of stealing Suspected Degree analysis method of more algorithm fusions |
| CN111131629A (en) * | 2019-12-31 | 2020-05-08 | 宇龙计算机通信科技(深圳)有限公司 | Crank call processing method and device, storage medium and terminal |
| CN114302398B (en) * | 2020-09-23 | 2023-11-21 | 中国移动通信集团重庆有限公司 | Big data-based reserved fraud number identification method and device and computing equipment |
| CN115021937B (en) * | 2022-06-21 | 2024-02-09 | 中国银行股份有限公司 | User identity authentication method, system, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5335278A (en) * | 1991-12-31 | 1994-08-02 | Wireless Security, Inc. | Fraud prevention system and process for cellular mobile telephone networks |
| CN101478591A (en) * | 2008-12-17 | 2009-07-08 | 康佳集团股份有限公司 | Method for preventing incoming call disturbance of mobile phone |
| CN103167501A (en) * | 2011-12-15 | 2013-06-19 | 上海粱江通信系统股份有限公司 | Method for improving identification accuracy rates of crank call number based on called dispersion degree |
| CN105227789A (en) * | 2014-06-12 | 2016-01-06 | 中国移动通信集团公司 | A kind of hold-up interception method of harassing call and device |
| CN106331390A (en) * | 2016-11-23 | 2017-01-11 | 杭州东信北邮信息技术有限公司 | Method and system for identifying fraud number based on call data |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9014359B1 (en) * | 2013-01-11 | 2015-04-21 | Time Warner Cable Enterprises Llc | Generation of phone number lists and call filtering |
| CN106255113A (en) * | 2015-06-10 | 2016-12-21 | 中兴通讯股份有限公司 | The recognition methods of harassing call and device |
| CN106686264B (en) * | 2016-11-04 | 2021-03-02 | 国家计算机网络与信息安全管理中心 | Fraud telephone screening and analyzing method and system |
| CN106937007A (en) * | 2017-04-05 | 2017-07-07 | 广州市景心科技股份有限公司 | System, method and device that a kind of harassing call is reminded |
-
2017
- 2017-09-30 CN CN201710918601.4A patent/CN107770777B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5335278A (en) * | 1991-12-31 | 1994-08-02 | Wireless Security, Inc. | Fraud prevention system and process for cellular mobile telephone networks |
| CN101478591A (en) * | 2008-12-17 | 2009-07-08 | 康佳集团股份有限公司 | Method for preventing incoming call disturbance of mobile phone |
| CN103167501A (en) * | 2011-12-15 | 2013-06-19 | 上海粱江通信系统股份有限公司 | Method for improving identification accuracy rates of crank call number based on called dispersion degree |
| CN105227789A (en) * | 2014-06-12 | 2016-01-06 | 中国移动通信集团公司 | A kind of hold-up interception method of harassing call and device |
| CN106331390A (en) * | 2016-11-23 | 2017-01-11 | 杭州东信北邮信息技术有限公司 | Method and system for identifying fraud number based on call data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107770777A (en) | 2018-03-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107770777B (en) | Method for identifying recorded fraud calls | |
| CN100579150C (en) | Malicious nuisance call screening and interception method | |
| CN106791220B (en) | Method and system for preventing telephone fraud | |
| WO2016197675A1 (en) | Method and apparatus for identifying crank call | |
| CN104244216B (en) | The method and system of real-time blocking fraudulent call in a kind of communication process | |
| CN102572904B (en) | System and method for implementing automatic dial test business | |
| CN102572124A (en) | Method and system for preventing telecommunication fraud by using No.7 signaling message of switch | |
| CN104936182A (en) | A method and system for intelligently controlling fraudulent calls | |
| CN101217820A (en) | An identification system and identification method on disturbance telephone numbers | |
| CN102368853B (en) | Communication event processing method and system thereof | |
| CN110072019A (en) | A kind of method and device shielding harassing call | |
| CN101350957A (en) | Method and equipment for shielding rubbish short message | |
| CN110381219A (en) | A kind of anti-swindle system of communication | |
| CN114169438A (en) | A telecommunication network fraud identification method, device, equipment and storage medium | |
| CN108259680B (en) | Fraud phone identification method, device and server for fraudulent phone identification | |
| CN107231494A (en) | A kind of acquisition methods of user communication characteristic, storage medium and electronic equipment | |
| CN102572059A (en) | Method and system for incoming call processing | |
| US10178225B1 (en) | Contraband wireless communications device identification in controlled-environment facilities | |
| CN106936997B (en) | A kind of rubbish voice recognition methods and system based on social networks map | |
| CN101873618A (en) | Communication monitoring method and device | |
| CN106302942A (en) | A kind of method of intelligent intercept harassing call | |
| KR101306074B1 (en) | Method and system to prevent phishing | |
| CN110113748A (en) | Harassing call monitoring method, device | |
| KR101033870B1 (en) | Spam call processing method and device | |
| CN104754583A (en) | Electronic device having cheat-proof caller identification function and method therefor |
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 |
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. |
|
| CP01 | Change in the name or title of a patent holder |