Method and system for mining image searches to associate images with concepts
A system and method for associating a document with a concept are provided. One or more idea-electronic document associations is identified, wherein each idea-electronic document association is based on a user performance criteria relative to the electronic document and the idea. At least one of the one or more electronic documents is identified with a concept based on the one or more idea-electronic document associations, wherein the concept is related to the one or more ideas.
1. A computer-implemented method, comprising:
identifying, by a computing system, an electronic document associated with an entity;
analyzing, by the computing system, stored information related to previous user selections of the electronic document in graphical user interfaces previously displayed at user devices to determine associations between the electronic document and a first set of terms that describe content of the electronic document;
determining, by the computing system, a second set of terms representing concepts that have been mapped to terms from the first set of terms that describe the content of the electronic document, the second set of terms including at least one term that is not among the first set of terms;
providing, by the computing system, terms from the second set of terms as suggested keywords for a content distribution campaign of the entity, wherein the terms provided from the second set of terms are presented in a graphical user interface at a computing device, wherein the graphical user interface includes at least a first control for selecting suggested keywords and a second control for saving selected suggested keywords to the content distribution campaign;
receiving an indication of a first user selection of a particular keyword from the suggested keywords, wherein the first user selection selects the particular keyword using the first control in the graphical user interface at the computing device; and
in response to a second user selection of the second control in the graphical user interface at the computing device, saving the particular keyword to the content distribution campaign.
2. The computer-implemented method of claim 1 , wherein identifying the electronic document comprises receiving a user input that was entered into the graphical user interface, the user input specifying the electronic document.
3. The computer-implemented method of claim 1 , wherein the electronic document comprises an image.
4. The computer-implemented method of claim 1 , further comprising receiving, by the computing system, a user-specified criterion for selecting suggested keywords, wherein determining the second set of terms that represent the concepts that have been mapped to terms from the first set of terms comprises determining the second set of terms based on the user-specified criterion for selecting suggested keywords.
5. The computer-implemented method of claim 4 , wherein the user-specified criterion for selecting suggested keywords comprises a preference for identifying synonyms as suggested keywords.
6. The computer-implemented method of claim 4 , wherein the user-specified criterion for selecting suggested keywords comprises a preference for identifying keyword variations as suggested keywords.
7. The computer-implemented method of claim 4 , wherein the user-specified criterion for selecting suggested keywords comprises a preference for keywords within a particular natural language.
8. The computer-implemented method of claim 1 , wherein providing terms from the second set of terms as suggested keywords for the content distribution campaign of the entity comprises presenting, in the graphical user interface, the terms from the second set of terms in a list of suggested keywords.
9. The computer-implemented method of claim 1 , wherein providing, by the computing system, terms from the second set of terms as suggested keywords for the content distribution campaign of the entity comprises providing terms as suggested keywords based on at least one of a price or a concept relevance of the terms.
10. The computer-implemented method of claim 1 , further comprising receiving an indication of a user-entered keyword and determining additional keyword suggestions based on the user-entered keyword.
11. The computer-implemented method of claim 1 , wherein determining the second set of terms comprises selecting a term that is determined to be a specific variation of a term from the second set of terms.
12. The computer-implemented method of claim 1 , wherein determining the second set of terms comprises selecting a term that is determined to be a synonym of a term from the first set of terms.
13. The computer-implemented method of claim 1 , wherein the first user selection adds the particular keyword to a list of selected keywords, and the second user selection of the second control in the graphical user interface is operable to save the list of selected keywords to the content distribution campaign.
14. The computer-implemented method of claim 1 , further comprising serving the electronic document in response to a request associated with the particular keyword.
15. The computer-implemented method of claim 1 , wherein the computing system analyzes the information related to the electronic document to determine the first set of terms that describe the content of the electronic document without requiring the computing system to process the document itself, thereby reducing the amount of processing power required of the computing system to categorize the electronic document.
16. A non-transitory computer-readable medium encoded with instructions that, when executed by a processor, cause the processor to perform operations comprising:
identifying an electronic document associated with an entity;
analyzing stored information related to previous user selections of the electronic document in graphical user interfaces previously displayed at user devices to determine associations between the electronic document and a first set of terms that describe content of the electronic document;
determining a second set of terms representing concepts that have been mapped to terms from the first set of terms that describe the content of the electronic document, the second set of terms including at least one term that is not among the first set of terms;
providing terms from the second set of terms as suggested keywords for a content distribution campaign of the entity, wherein the terms provided from the second set of terms are presented in a graphical user interface at a computing device, wherein the graphical user interface includes at least a first control for selecting suggested keywords and a second control for saving selected suggested keywords to the content distribution campaign;
receiving an indication of a first user selection of a particular keyword from the suggested keywords, wherein the first user selection selects the particular keyword using the first control in the graphical user interface at the computing device; and
in response to a second user selection of the second control in the graphical user interface at the computing device, saving the particular keyword to the content distribution campaign.
17. The non-transitory computer-readable medium of claim 16 , wherein identifying the electronic document comprises receiving a user input that was entered into the graphical user interface, the user input specifying the electronic document.
18. The non-transitory computer-readable medium of claim 16 , wherein the electronic document comprises an image.
19. The non-transitory computer-readable medium of claim 16 , wherein providing terms from the second set of terms as suggested keywords for the content distribution campaign of the entity comprises presenting, in the graphical user interface, the terms from the second set of terms in a list of suggested keywords.
20. A system, comprising:
a processor; and
a non-transitory computer-readable medium encoded with instructions that, when executed by the processor, cause the processor to perform operations comprising:
identifying an electronic document associated with an entity;
analyzing stored information related to previous user selections of the electronic document in graphical user interfaces previously displayed at user devices to determine associations between the electronic document and a first set of terms that describe content of the electronic document;
determining a second set of terms representing concepts that have been mapped to terms from the first set of terms that describe the content of the electronic document, the second set of terms including at least one term that is not among the first set of terms;
providing terms from the second set of terms as suggested keywords for a content distribution campaign of the entity, wherein the terms provided from the second set of terms are presented in a graphical user interface at a computing device, wherein the graphical user interface includes at least a first control for selecting suggested keywords and a second control for saving selected suggested keywords to the content distribution campaign;
receiving an indication of a first user selection of a particular keyword from the suggested keywords, wherein the first user selection selects the particular keyword using the first control in the graphical user interface at the computing device; and
in response to a second user selection of the second control in the graphical user interface at the computing device, saving the particular keyword to the content distribution campaign.