Back to results
US 11,238,080 B2Granted
Aggregating activity data for multiple users
AssigneeGoogle Inc.
InventorsRadhika Malpani, Elin R. Pedersen
Life of this patent
Estimating the term…
Abstract
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for aggregating task data for multiple users. In one aspect, a method includes accessing action trail data that corresponds to a task and resources related to that task, wherein each task relates to one or more related topics and is defined by a sequence of user actions corresponding to the resources related to that task; clustering the action trails based on the action trail data such that each action trail cluster corresponds to a particular task and includes the action trails corresponding to that particular task; and for each action trail cluster, ranking the resources that correspond to the included action trails according to the topics of the particular task.
Claims20
A method performed by data processing apparatus, the method comprising:
- accessing, for each of a plurality of users, data specifying sequences of user actions taken by the user with respect to one or more resources that present content related to a particular task in which the user was engaged, wherein each particular task relates to a set of related topics;
- clustering the sequences of user actions into clusters based on the particular task to which each sequence corresponds, the clustering including:
- generating a respective cluster for each particular task, wherein each cluster corresponds to a respective particular task;
- and
- assigning, to each of the respective clusters, only the sequences of user actions taken by users with respect to one or more resources that present content related to the particular task;
- determining that a given user is engaged in a given task corresponding to a particular cluster based on the given user submitting a search query related to a first topic of the given task;
- and
- in response to determining that the given user is engaged in the given task corresponding to the particular cluster based on the given user submitting the search query related to the first topic of the given task, providing, for presentation to the given user via a user device of the given user, data identifying (i) a query-relevant resource that is responsive to the search query related to the first topic of the given task and (ii) one or more additional resources that are specified by one or more of the sequences of user actions assigned to the particular cluster, wherein the one or more additional resources are related to a second topic of the given task, and wherein providing the data comprises:
- including, in the data, (i) the query-relevant resource that is responsive to the search query related to the first topic and (ii) the one or more additional resources that are related to the second topic, wherein including the one or more additional resources that are related to the second topic is responsive to the one or more additional resources being specified by one or more of the sequences of user actions assigned to the particular cluster for the given task and is responsive to determining that the given user is engaged in the given task corresponding to the particular cluster based on the given user submitting the search query related to the first topic of the given task.
6 more elements
A system comprising:
- a data processing apparatus comprising one or more computers;
- and
- a data store storing instructions that, when executed by the data processing apparatus, cause the data processing apparatus to perform operations comprising:
- accessing, for each of a plurality of users, data specifying sequences of user actions taken by the user with respect to one or more resources that present content related to a particular task in which the user was engaged, wherein each particular task relates to a set of related topics;
- clustering the sequences of user actions into clusters based on the particular task to which each sequence corresponds, the clustering including:
- generating a respective cluster for each particular task, wherein each cluster corresponds to a respective particular task;
- and
- assigning, to each of the respective clusters, only the sequences of user actions taken by users with respect to one or more resources that present content related to the particular task;
- determining, based on a given user submitting multiple queries related to a first topic of a given task corresponding to a particular cluster of the clusters, that the given user is engaged in the given task corresponding to the particular cluster;
- and
- in response to determining that the given user is engaged in the given task corresponding to the particular cluster based on the given user submitting multiple queries related to the first topic of the given task corresponding to the particular cluster, providing, for presentation to the given user via a user device of the given user, data identifying (i) a query-relevant resource that is responsive to the search query related to the first topic of the given task and (ii) one or more additional resources that are specified by one or more sequences of user actions assigned to the particular cluster, wherein the one or more additional resources are related to a second topic of the given task.
8 more elements
A non-transitory computer readable medium comprising instructions that, when executed by a data processing apparatus, cause the data processing apparatus to perform operations comprising:
- accessing, for each of a plurality of users, data specifying sequences of user actions taken by the user with respect to one or more resources that present content related to a particular task in which the user was engaged, wherein each particular task relates to a set of related topics;
- clustering the sequences of user actions into clusters based on the particular task to which each sequence corresponds, the clustering including:
- generating a respective cluster for each particular task, wherein each cluster corresponds to a respective particular task;
- and
- assigning, to each of the respective clusters, only the sequences of user actions taken by users with respect to one or more resources that present content related to the particular task;
- determining that a given user is engaged in a given task corresponding to a particular cluster based on the given user submitting a search query related to a first topic of the given task;
- and
- in response to determining that the given user is engaged in the given task corresponding to the particular cluster based on the given user submitting the search query related to the first topic of the given task, providing, for presentation to the given user via a user device of the given user, data identifying (i) a query-relevant resource that is responsive to the search query related to the first topic of the given task and (ii) one or more additional resources that are specified by one or more sequences of user actions assigned to the particular cluster, wherein the one or more additional resources are related to a second topic of the given task, and wherein providing the data comprises:
- including, in the data, (i) the query-relevant resource that is responsive to the search query related to the first topic and (ii) the one or more additional resources that are related to the second topic, wherein including the one or more additional resources that are related to the second topic is responsive to the one or more additional resources being specified by one or more of the sequences of user actions assigned to the particular cluster for the given task and is responsive to determining that the given user is engaged in the given task corresponding to the particular cluster based on the given user submitting the search query related to the first topic of the given task.
6 more elements
Dependencies are inferred from the claim text.