Scoring items

• US 8,989,450 B1
• Filed: 08/08/2014
• Issued: 03/24/2015
• Est. Priority Date: 01/13/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Rosenberg, Charles, Rowley, Henry A., Malpani, Radhika
• Primary Examiner(s): AZARIAN, SEYED H
• Application Number:
  US14/454,891
• Time in Patent Office: 228 Days
• Field of Search: 382/103, 382/112, 382/100, 382135-140, 382155-161, 382/168, 382/176, 382/173, 382/181, 382/190, 382/194, 382/199, 382/209, 382/232, 382/254, 382/274, 382/276, 382/305, 382/312, 382/310, 382/165, 707/706, 706/14, 706/13, 709/224
• US Class Current: 382/112
• CPC Class Codes: G06F 18/256 of results relating to different input data, e.g. multimodal recognition

Abstract

A system identifies an image and determines whether the image contains inappropriate content based on first data associated with the image, second data associated with a document that contains the image or refers to the image, and/or third data associated with a group of documents with which the image is associated.

Claims

1. A method comprising:

identifying, by one or more server devices, an item associated with a web site,

the web site including a first web page and a second web page,

the first web page containing or referring to the item;

generating, by one or more server devices, a score, for the item, that represents a likelihood that the item corresponds to inappropriate content,

the score being based on a content of the item and based on;

a content of the first web page,

a content of another item associated with the web site, or

a content of the second web page; and

associating, by one or more server devices, a tag with the item based on the score,

the tag indicating whether to provide information regarding the item for display when the item is identified based on a search query.

2. The method of claim 1, where associating the tag with the item includes:

determining that the score exceeds a threshold; and

associating the tag with the item based on determining that the score exceeds the threshold.

3. The method of claim 1, where generating the score includes:

extracting a feature relating to the content of the item,

the feature including information identifying a portion of the item that includes a particular color; and

generating a particular score based on the feature,

the score, generated for the item, being generated based on the particular score.

4. The method of claim 3, where the particular color includes a skin-tone color.

5. The method of claim 1, where generating the score includes:

determining a quantity of words, included in the content of the first web page, relating to inappropriate content; and

determining a particular score based on the quantity of words,

the score, generated for the item, being generated based on the particular score.

6. The method of claim 1, further comprising:

identifying information regarding a plurality of items based on the search query,

the plurality of items including the item;

determining, based on the tag, that the item includes the inappropriate content;

removing, based on determining that the item includes the inappropriate content, the information regarding the item from the information regarding the plurality of items to obtain information regarding a remaining one or more items; and

providing the information regarding the remaining one or more items for display.

7. The method of claim 6, where removing the information regarding the item comprises:

determining a preference, of a user associated with the search query, relating to inappropriate content; and

removing the information regarding the item, from the information regarding the plurality of items, based on the preference indicating that items, including inappropriate content, are not to be provided to the user.

8. A system comprising:

one or more server devices to;

identify an item associated with a web site,

the web site including a first web page and a second web page,

the first web page containing or referring to the item;

generate a score, for the item, that represents a likelihood that the item corresponds to inappropriate content,

the score being based on a content of the item and based on;

a content of the first web page,

a content of another item associated with the web site, or

a content of the second web page,

the score indicating whether to provide information regarding the item for display when the item is identified based on a search query; and

store information associating the item and the score.

9. The system of claim 8, where, when generating the score, the one or more server devices are to:

determine a quantity of words, included in at least one of the content of the first web page or the content of the second web page, relating to inappropriate content; and

determine one or more particular scores based on the quantity of words,

the score, generated for the item, being generated based on the one or more particular scores.

10. The system of claim 8, where, when generating the score, the one or more server devices are to:

generate a first score based on a feature relating to the content of the item,

the feature, relating to the content of the item, including information identifying a portion of the item that includes a particular color,

the score, generated for the item, being generated based on the first score.

11. The system of claim 10, where, when generating the score, the one or more server devices are further to:

generate a second score based on a feature relating to the content of the other item,

the feature, relating to the content of the other item, including information identifying a portion of the other item that includes the particular color,

the score, generated for the item, being generated based on the first score and the second score.

12. The system of claim 10, where the one or more server devices are further to:

receive the search query from a device of a user;

identify information regarding a plurality of items based on the search query,

the plurality of items including the item;

determine, based on the score, that the item includes the inappropriate content;

remove, based on determining that the item includes the inappropriate content, the information regarding the item from the information regarding the plurality of items to obtain information regarding a remaining one or more items; and

provide, to the device, the information regarding the remaining one or more items for display.

13. The system of claim 12, where, when removing the information regarding the item, the one or more server devices are further to:

determine, based on information regarding the user, that the inappropriate content is not to be provided to the user; and

remove the information regarding the item, from the information regarding the plurality of items, based on determining that the inappropriate content is not to be provided to the user.

14. A non-transitory computer-readable medium for storing instructions, the instructions comprising:

one or more instructions that, when executed by one or more processors, cause the one or more processors to;

identify an item associated with a web site,

the web site including a first web page and a second web page,

the first web page containing or referring to the item;

generate a score, for the item, that represents a likelihood that the item corresponds to inappropriate content,

the score being based on a content of the item and based on;

a content of the first web page,

a content of another item associated with the web site, or

a content of the second web page,

the score indicating whether to provide information regarding the item for display when the item is identified based on a search query; and

store information regarding the item and the score.

15. The non-transitory computer-readable medium of claim 14, where the one or more instructions to generate the score include:

one or more instructions to determine a first score based on a quantity of words, included in the first web page, relating to inappropriate content,

the score being generated based on the first score.

16. The non-transitory computer-readable medium of claim 15, where the one or more instructions to generate the score further include:

one or more instructions to determine a second score based on a quantity of words, included in the second web page, relating to inappropriate content,

the score being generated based on the first score and the second score.

17. The non-transitory computer-readable medium of claim 14, where the instructions further comprise:

one or more instructions to receive the search query from a device of a user;

one or more instructions to identify information regarding a plurality of items based on the search query,

the plurality of items including the item;

one or more instructions to determine, based on the score, that the item includes the inappropriate content;

one or more instructions to remove, based on determining that the item includes the inappropriate content, the information regarding the item from the information regarding the plurality of items to obtain information regarding a remaining one or more items; and

one or more instructions to provide, to the device, the information regarding the remaining one or more items for display.

18. The non-transitory computer-readable medium of claim 14, where the instructions further comprise:

one or more instructions to generate a particular score based on a feature relating to the content of the item,

the feature, relating to the content of the item, including information identifying a portion of the item that includes a particular color,

the score, generated for the item, being generated based on the particular score.

19. The non-transitory computer-readable medium of claim 14, where the instructions further comprise:

one or more instructions to generate a particular score based on a feature relating to the content of the item,

the feature, relating to the content of the item, including information identifying a quantity of faces detected in the item,

the score, generated for the item, being generated based on the particular score.

20. The non-transitory computer-readable medium of claim 14, where the instructions further comprise:

one or more instructions to determine that the score exceeds a threshold; and

one or more instructions to associate a tag with the item based on determining that the score exceeds the threshold,

the tag indicating whether to provide the information regarding the item for display when the item is identified based on the search query.