Predicting user activity based on usage data received from client devices
View Patent ↗A system for determining an interest of a user based on usage data is provided. Usage data corresponding to a plurality of websites accessed by a user is received from one or more computing devices of the user. The received usage data is categorized into a plurality of categories based on character strings that reference the individual websites. What content items from individual websites the user has selected to view is recorded in order to identify one or more items of interest. An activity of the user at a given time period is predicted based on the categorizations, the identified one or more items of interest, and times and duration of times the user viewed the individual websites. The system performs an action at the given time period based on the predicted activity.
1. A non-transitory computer readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform steps comprising:
receiving usage data corresponding to a plurality of websites accessed by a user from one or more computing devices of the user, the usage data including character strings that reference the individual websites viewed by the user;
categorizing the received usage data into a plurality of categories based on the character strings that reference the individual websites;
recording what content items from individual websites the user has selected to view in order to identify one or more items of interest;
predicting an activity of the user at a given time period based on (i) the categorizations, (ii) the identified one or more items of interest, and (iii) times or durations of time the user viewed the individual websites; and
performing an action at the given time period based on the predicted activity;
wherein the plurality of categories are predetermined using one or more external sources.
2. The non-transitory computer readable medium of claim 1 , wherein the instructions further cause the one or more processors to categorize the received usage data into the plurality of categories by retrieving a uniform resource locator (URL) of individual websites of the plurality of websites from the usage data, and parsing the URL of individual websites.
3. The non-transitory computer readable medium of claim 1 , wherein the instructions further cause the one or more processors to record what content items from individual websites the user has selected to view by performing string matching operations on the content items to identify one or more names, words, or phrases that have been predetermined to be items of interest.
4. The non-transitory computer readable medium of claim 1 , wherein the instructions further cause the one or more processors to predict an activity of the user at a given time period by determining the one or more preferences of the user based further on at least one of (i) information corresponding to the one or more computing devices of the user, (ii) information provided by one or more services used by the user, or (iii) information provided by the user.
5. The non-transitory computer readable medium of claim 1 , wherein the instructions further cause the one or more processors to categorize the received usage data into the plurality of categories by assigning a weighting score to one or more of the plurality of categories.
6. The non-transitory computer readable medium of claim 5 , wherein the instructions further cause the one or more processors to predict the activity of the user at the given time period based on the one or more weighting scores assigned to the one or more of the plurality of categories.
7. A system comprising:
one or more memory resources;
a communication interface; and
one or more processors coupled to the one or more memory resources and the communication interface the one or more processors to:
receive usage data corresponding to a plurality of websites accessed by a user from one or more computing devices of the user via the communication interface, the usage data including character strings that reference the individual websites viewed by the user;
categorize the received usage data into a plurality of categories based on the character strings that reference the individual websites, the plurality of categories being predetermined using one or more external sources;
record what content items from individual websites the user has selected to view in order to identify one of more items of interest;
predict an activity of the user at a given time period based on (i) the categorizations, (ii) the identified one or more items of interest, and (iii) the times or the duration of times the user viewed the individual websites;
perform an action at the given time period based on the predicted activity; and
categorize the received usage data into the plurality of categories by retrieving a uniform resource locator (URL) of individual websites of the plurality of websites from the usage data and parsing the URL of individual website.
8. The system of claim 7 , wherein the one or more processors record what content items from individual websites the user has selected to view by performing string matching operations on the content items to identify one or more names, words, or phrases that have been predetermined to be items of interest.
9. The system of claim 7 , wherein the one or more processors predict an activity of the user at a given time period by determining the one or more preferences of the user based further on at least one of (i) information corresponding to the one or more computing devices of the user, information provided by one or more services used by the user, or (iii) information provided by the user.
10. The system of claim 7 , wherein the one or more processors categorize the received usage data into the plurality of categories by assigning a weighting score to one or more of the plurality of categories.
11. The system of claim 10 , wherein the one or more processors predict the activity of the user at the given time period based on the one or more weighting scores assigned to the one or more of the plurality of categories.
12. A method for determining an interest of a user based on content accessed by the user, the method being performed by one or more processors and comprising:
receiving usage data corresponding to a plurality of websites accessed by the user from one or more computing devices of the user, the usage data including character strings that reference the individual websites viewed by the user;
categorizing the received usage data into a plurality of categories based on the character strings that reference the individual websites, wherein categorizing the received usage data includes assigning a weighting score to one or more of the plurality of categories;
recording what content items from individual websites the user has selected to view in order to identify one or more items of interest;
predicting an activity of the user at a given time period used on (i) the categorizations, (ii) the identified one or more items of interest, and (iii) the times or the duration of times the user viewed the individual websites;
performing an action at the given time period based on the predicted activity; and
categorizing the received usage data into the plurality of categories by retrieving a uniform resource locator (URL) of individual websites of the plurality of websites from the usage data, and parsing the URL of individual websites.