30results about How to "No privacy involved" patented technology

The invention relates to the technical field of Internet application, in particular to a transport-layer-characteristic-based traffic classification method for the Internet application. The method comprises the following steps of: acquiring a data packet which serves as training data, and constructing a classifier by utilizing transport layer characteristics of a data stream extracted from the data packet; and classifying the data stream extracted from a subsequently acquired data packet by utilizing the constructed classifier. The application type of the stream can be identified only by extracting the transport layer characteristics of the stream without knowing load contents such as a port number, a characteristic field and the like of the data packet. The privacy of a user is uninvolved, and a dynamic-port-number-based or encrypted stream can be identified by the technology. Moreover, the method is highly accurate and integral, novel application can be identified and the user can be prompted to check suspected virus attack streams.

The invention provides a user association method across website based on username similarity. The steps comprise: 1) filtering characters in a plurality of usernames, just reserving English letters and numbers; 2) finding out characteristics of the processed usernames, and obtaining self-information values of the characteristics, according to the self-information values, obtaining self-information vectors; 3) according to the self-information vectors, obtaining similarity among the plurality of usernames, if the similarity is larger than a given threshold value [tau], determining that the plurality of usernames belong to a same user. Through the similarity among the plurality of usernames, the method determines whether the usernames belong to the same user, and accounts belonging to the same user on different websites can be associated.

Smartphone usage context recognition method based on touch behavior sequence, which defines 9 kinds of touch operations, extracts 9 kinds of touch operation attributes (touch start and end time, etc.) , taking 32 continuous operations as a basic touch interaction sequence; then use the long short-term memory network and attention mechanism to model, to realize the judgment and statistics of the user's use of the mobile phone situation. In the present invention, the basic touch interaction sequence is input into the two-way long-short-term memory network model of the superimposed attention mechanism for situation recognition, and realizes the judgment of the user's mobile phone situation including shopping, social interaction, browsing, learning, short video, game, etc. Realize the subdivision of multiple scenarios in the user's smartphone application, and count the usage time of each scenario within a certain period of time, so as to provide a direct basis for users to know the usage duration of their smartphones in various scenarios.

The invention discloses a K-anonymity incentive mechanism based on local reputation storage. When a user requests an LBS needing privacy protection, a request for taking part in forming an anonymity region is sent to nearby users in a broadcasting mode, and a service provider list is obtained through returned information; through a third party cloud server, both parties send newly generated reputation certificates to each other and achieve verification, and a service provider verifies all old certificates of the service requester; after the verification is passed, the anonymity region is formed; after an inquiry service is finished, the both parties perform evaluation mutually, a public key is attached to the received reputation certificates of the other party, and then the certificates are sent back to be stored by the other party after signature, so that reputation values are accumulated. Reputation of all nodes is stored locally in a reputation certificate mode, reputation is obtained through providing anonymity services for the adjacent nodes and accumulated, in the future trade, and the anonymity services can be provided for the nodes only after the nodes reach certain reputation threshold values.

The invention discloses a search method for an IP address of an Internet data center based on traffic behavior characteristics. According to the unique traffic behavior characteristics of the Internet data center, the IP of the Internet data center is mined in large-scale network flow information, thereby comprehensively extracting, Describe the business bearing content of the Internet data center and the connection relationship between them, and prove that the specific IP can be effectively mined from the big data flow information according to the flow behavior characteristics.

The present invention relates to a method and system for identifying mobile malicious users based on communication behavior rules. Sampling data, using the behavior pattern analysis in the mobile communication behavior analysis model to extract the user's call behavior characteristics, short message behavior characteristics and time distribution characteristics; based on the preprocessed mobile communication sampling data, using the communication network analysis in the mobile communication behavior analysis model Extract the user's social attribute features; based on the extracted user behavior pattern features and the extracted user social attribute features, build a mobile malicious user identification model; the present invention can analyze the user's behavior rules based on the desensitized data, and identify whether the user is a mobile malicious user The user has good timeliness and can identify mobile malicious users with high accuracy without involving the user's personal privacy.