Granted Patent B2

US 10,902,067 · App. 13/869,826 · Granted Jan 26, 2021

Inventors: Antonio Magnaghi (Los Angeles, CA); Jeremy Daw (Venice, CA); Jeong-Yoon Lee (Torrance, CA)

Assignee: Leaf Group Ltd.

G06F16/951G06F16/00G06F16/215G06F16/2365G06F16/24578G06Q30/0202

Abstract

Claims (95)

1. A method, comprising:

a computer system communicating over a network with a plurality of web servers and a plurality of user devices;

receiving over the computer network, by the computer system, information from a web server of the plurality of web servers, wherein the information comprises future content to be produced by the web server;

identifying, by the computer system, a topic associated with the information based on one or more of content of websites or data regarding searches performed by users using the plurality of user devices;

receiving from the web server, by the computer system, a plurality of search data sets for a respective plurality of previously-executed searches performed at least via the plurality of user devices, each of the plurality of data sets including one or more links within one or more search results of the respective plurality of previously-executed searches performed at least via the plurality of user devices;

determining, by the computer system for each of the plurality of data sets, a respective similarity score indicative of a level of similarity between the respective search data and the topic, wherein the topic is parsed and analyzed using a part-of speech tagger to identify nouns, verbs, adjectives, and other parts of the topic;

selecting, by the computer system, a subset of search data sets from the plurality of search data sets based on the respective similarity score for each search data set in the subset;

identifying, by the computer system, a first format associated with the topic, wherein the first format comprises a video format type used by the plurality of user devices in displaying content associated with the topic included within one or more of the subset of search data sets;

identifying, by the computer system, a second format associated with the topic, wherein the second format comprises a textual article format type used by the plurality of user devices in displaying content associated with the topic included within one or more of the subset of search data sets;

generating, by the computer system, a first revenue model based on the identified first format and the subset of the search data sets;

generating, by the computer system, a second revenue model based on the identified second format and the subset of the search data sets;

determining, by the computer system, a first score indicative of first predicted revenue generated from the future content of the web server if published in the identified first format associated with the topic using the first revenue model; and

determining, by the computer system, a second score indicative of second predicted revenue generated from the future content of the web server if published in the identified second format associated with the topic using the second revenue model.

2. The method of claim 1 , wherein determining the first score is based on information regarding a distribution platform from which the future content associated with the topic would be provided.

3. The method of claim 1 , further comprising:

determining the first score via a first distribution platform; and

determining the second score via a second distribution platform.

4. The method of claim 2 , wherein the distribution platform includes one or more of:

a software application;

a file transfer protocol site;

a web site;

a peer-to-peer network; and

combinations thereof.

5. The method of claim 1 , wherein determining the first score is based on information regarding revenue previously generated by other content in the identified first format.

6. The method of claim 5 , wherein the information regarding the revenue previously generated by the other content includes information regarding a distribution platform from which the other content was hosted while generating the previous revenue.

7. The method of claim 5 , wherein determining the first score is based on a level of similarity between the other content and the future content.

8. The method of claim 1 , further comprising:

determining a first score indicative of predicted revenue from providing the future content under a first revenue model; and

determining a second score indicative of predicted revenue from providing the future content under a second revenue model.

9. The method of claim 1 , wherein the search data includes search terms.

10. The method of claim 1 , wherein the search data includes a title of online content.

11. The method of claim 1 , wherein the search data includes metrics related to the previously executed search.

12. The method of claim 11 , wherein the metrics include one or more of:

an average position of a search result;

an indicator of a number of times a search result is accessed within a period of time;

a cost associated with providing a search result in relation to a number of times the search result is accessed;

information regarding a user accessing a search result;

information regarding a computing device used by a user accessing a search result;

an age of content associated with a search result;

a ranking of content associated with a search result;

revenue generated by content associated with a search result; and

combinations thereof.

13. The method of claim 1 , further comprising:

ranking the subset of search data sets based on the respective similarity score for each search data set in the subset.

14. The method of claim 1 , further comprising:

receiving, after the future content is hosted, an indication of first actual revenue generated by the future content if published in the identified first format;

receiving, after the future content is hosted, an indication of second actual revenue generated by the future content if published in the identified second format;

comparing the first actual revenue to the first predicted revenue;

comparing the second actual revenue to the second predicted revenue;

storing first results of the comparison between the first actual revenue and the first predicted revenue; and

storing second results of the comparison between the second actual revenue and the second predicted revenue.

15. The method of claim 14 , further comprising:

calculating, based on the stored first results, a first error associated with the first predicted revenue; and

calculating, based on the stored second results, a second error associated with the second predicted revenue.

16. The method of claim 15 , further comprising generating a report that includes:

respective indicators of the first and second predicted revenues;

respective indicators of the first and second actual revenues; and

respective indicators of the first and second errors.

17. The method of claim 15 , further comprising:

receiving information regarding a second topic;

identifying a first format associated with the second topic, wherein the first format associated with the second topic comprises a video format type used in displaying content associated with the second topic;

determining a third score indicative of third predicted revenue produced from generating, in the identified first format for the content associated with the second topic, second future content associated with the second topic if published in the identified first format associated with the second topic using the first revenue model; and

adjusting the third score based on the first error associated with the first predicted revenue.

18. The method of claim 17 , further comprising:

identifying a second format associated with the second topic, wherein the second format associated with the second topic comprises a textual article format type used in displaying content associated with the second topic;

determining a fourth score indicative of fourth predicted revenue produced from generating, in the identified second format for the content associated with the second topic, second future content associated with the second topic if published in the identified second format associated with the second topic using the second revenue model; and

adjusting the fourth score based on the second error associated with the second predicted revenue.

19. A non-transitory, computer-readable medium storing instructions that, when executed, cause a computing device to:

communicate over a network with a plurality of web servers and a plurality of user devices;

receive, over the computer network, information from a web server of the plurality of web servers, wherein the information comprises future content to be produced by the web server;

identify a topic associated with the information based on one or more of content of websites or data regarding searches performed by users using the plurality of user devices;

receive, from the web server, a plurality of search data sets for a respective plurality of previously-executed searches performed at least via the plurality of user devices, each of the plurality of data sets including one or more links within one or more search results of the respective plurality of previously-executed searches performed at least via the plurality of user devices;

determine, for each of the plurality of data sets, a respective similarity score indicative of a level of similarity between the respective search data and the topic, wherein the topic is parsed and analyzed using a part-of speech tagger to identify nouns, verbs, adjectives, and other parts of the topic;

select a subset of search data sets from the plurality of search data sets based on the respective similarity score for each search data set in the subset;

identify a first format associated with the topic, wherein the first format comprises a video format type used by the plurality of user devices in displaying content associated with the topic included within one or more of the subset of search data sets;

identify a second format associated with the topic, wherein the second format comprises a textual article format type used by the plurality of user devices in displaying content associated with the topic included within one or more of the subset of search data sets;

generate a first revenue model based on the identified first format and the subset of the search data sets;

generate a second revenue model based on the identified second format and the subset of the search data sets;

determine a first score indicative of first predicted revenue generated from the future content of the web server if published in the identified first format associated with the topic using the first revenue model; and

determine a second score indicative of second predicted revenue generated from the future content of the web server if published in the identified second format associated with the topic using the second revenue model.

20. A system comprising:

at least one processor; and

memory in communication with the at least one processor and storing instructions that, when executed by the processor, cause the system to:

communicate over a network with a plurality of web servers and a plurality of user devices;

receive, over the computer network, information from a web server of the plurality of web servers, wherein the information comprises future content to be produced by the web server;

identify a topic associated with the information based on one or more of content of websites or data regarding searches performed by users using the plurality of user devices;

receive, from the web server, a plurality of search data sets for a respective plurality of previously-executed searches performed at least via the plurality of user devices, each of the plurality of data sets including one or more links within one or more search results of the respective plurality of previously-executed searches performed at least via the plurality of user devices;

determine, for each of the plurality of data sets, a respective similarity score indicative of a level of similarity between the respective search data and the topic, wherein the topic is parsed and analyzed using a part-of speech tagger to identify nouns, verbs, adjectives, and other parts of the topic;

select a subset of search data sets from the plurality of search data sets based on the respective similarity score for each search data set in the subset;

identify a first format associated with the topic, wherein the first format comprises a video format type used by the plurality of user devices in displaying content associated with the topic included within one or more of the subset of search data sets;

identify a second format associated with the topic, wherein the second format comprises a textual article format type used by the plurality of user devices in displaying content associated with the topic included within one or more of the subset of search data sets;

generate a first revenue model based on the identified first format and the subset of the search data sets;

generate a second revenue model based on the identified second format and the subset of the search data sets;

determine a first score indicative of first predicted revenue generated from the future content of the web server if published in the identified first format associated with the topic using the first revenue model; and

determine a second score indicative of second predicted revenue generated from the future content of the web server if published in the identified second format associated with the topic using the second revenue model.

Assignments (8)