International Business Machines Corporation

Yi Bo Zhang

Chen Wang

Xiao Yan Chen

Chun Ying

Yanfeng Zhu

Lei Shi

Yan Zhu

Ping Pan

Pan Ping

A method, apparatus and computer program product for spam message detection. The method includes collecting time domain transmission characteristic of a message source; computing frequency domain transmission characteristic of the message source with the time domain transmission characteristic of the message source; and identifying the message source to be a spammer in response to the frequency domain transmission characteristic of the message source satisfying predefined criteria; wherein the steps of the method are carried out using a computer device. An apparatus and computer program product for carrying out the above method is also provided.

Method and apparatus for spam message detection

A method of determining a spammer includes acquiring, by a processor, short message events associated with a user and dividing them into a plurality of sessions in terms of time; building a social network of the user in each of the sessions, and calculating at least one type of social network characteristic in each of the sessions, respectively; and determining whether the user is a spammer or not according to the social network characteristic.

Determination of a spammer through social network characterization

A system for determining a spammer includes a session division apparatus configured to acquire short message events associated with a user and divide them into a plurality of sessions in terms of time; a social network building and characteristic calculating apparatus configured to build a social network of the user in each of the sessions, and calculate at least one type of social network characteristic in each of the sessions, respectively; and a determination apparatus configured to determine whether the user is a spammer or not according to the social network characteristic.

A method and storage medium with instructions for identifying an association between a Smart Card and a mobile device by selecting card-swiping record pairs from a set of card-swiping records of the Smart Card, each including a card-swiping location and a corresponding card-swiping time; calculating overlap degree in time and location dimensions of the card-swiping record pair and the communication behavior record pair of the mobile phone, which is recorded in a mobile network as a communication log; determining that the card-swiping record pair overlaps with the communication behavior record pair of the mobile phone recorded in the communication log if the overlap degree is greater than a predetermined threshold, and determining that the Smart Card is associated with the mobile phone if each card-swiping record pair of the plurality of card-swiping record pairs overlaps with the communication behavior record pair of the mobile phone recorded in the communication log.

System and method for identifying the association relationship between a smart card and a mobile phone

A method and system for identifying an association between a Smart Card and a mobile device by selecting card-swiping record pairs from a set of card-swiping records of the Smart Card, each including a card-swiping location and a corresponding card-swiping time; calculating overlap degree in time and location dimensions of the card-swiping record pair and the communication behavior record pair of the mobile phone, which is recorded in a mobile network as a communication log; determining that the card-swiping record pair overlaps with the communication behavior record pair of the mobile phone recorded in the communication log if the overlap degree is greater than a predetermined threshold, and determining that the Smart Card is associated with the mobile phone if each card-swiping record pair of the plurality of card-swiping record pairs overlaps with the communication behavior record pair of the mobile phone recorded in the communication log.

System and method of identifying the association relationship between a smart card and a mobile phone

A method and apparatus for spam short message detection. The method includes obtaining sending characteristics of at least two suspected short message sources, judging whether the two suspected short message sources have similar sending characteristics, and determining the two suspected short message sources as spammer if they have similar sending characteristics. A spammer that makes multiple short message sources send short messages alternately can be detected through similar sending characteristics of the short message sources.

Growing community of inventors

Beijing, China

Yi Bo Zhang