Separating intended and non-intended browsing traffic in browsing history
AssigneeAT&T Intellectual Property I, L.P.
InventorsZhengyi Zhou, Christopher Volinsky
Life of this patent
Estimating the term…
Abstract
Facilitating separation of intended and non-intended browsing traffic in browsing history advanced networks (e.g., 4G, 5G, and beyond) is provided herein. Operations of a system can comprise determining respective contradiction values for second-level domains of a group of second-level domains in observed browsing history traffic. The operations can also comprise separating intended network traffic from non-intended network traffic based on the respective contradiction values. The respective contradiction values can indicate levels of inconsistency between the observed browsing history traffic and a determined popularity ranking.
Claims20
A system, comprising:
- a processor;
- and
- a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:
- determining respective contradiction values for second-level domains of a group of second-level domains in observed browsing history traffic;
- and
- separating the observed browsing history traffic into intended network browsing traffic and non-intended network browsing traffic based on the respective contradiction values,
- wherein the intended network browsing traffic comprises information related to user-initiated browsing behavior, and wherein the non-intended network browsing traffic comprises background activity void of the information related to the user-initiated browsing behavior, and
- wherein the respective contradiction values indicate levels of inconsistency between respective popularities of the second-level domains and associated subdomains in the observed browsing history traffic and determined respective popularity rankings of the second-level domains.
A method, comprising:
- evaluating, by a system comprising a processor, respective contradiction scores for second-level domains of a group of second-level domains of observed browsing history traffic;
- and
- identifying, by the system, intended network browsing traffic and non-intended network browsing traffic of the observed browsing history traffic based on the respective contradiction scores,
- wherein the respective contradiction scores indicate a level of inconsistency between the respective popularities of second-level domains of the group of second-level domains and associated subdomains in observed browsing history traffic and respective external popularity rankings of the second-level domains, and
- wherein the identifying comprises determining that the intended network browsing traffic is generated based on a specified request and that the non-intended network browsing traffic is generated based on a passive request.
A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:
- determining, for a first user equipment selected from a group of user equipment associated with a network, respective contradiction values for first domains of first browsing history traffic;
- identifying the first domains as a first group of domains and a second group of domains, wherein the first group of domains comprises domains associated with intentional network traffic, and wherein the second group of domains comprises domains associated with unintentional network traffic, wherein the intentional network traffic is actively initiated based on user input to the first user equipment, and wherein the unintentional network traffic comprises non-user requests initiated by an operating system of the first user equipment;
- and
- applying the first group of domains and the second group of domains to second browsing history traffic associated with a second user equipment selected from the group of user equipment,
- wherein the respective contradiction scores indicate a level of inconsistency between respective popularities of the first domains and associated subdomains in the first browsing history traffic and respective external popularity rankings of the first domains.
Dependencies are inferred from the claim text.