Method and system for selecting images based on user contextual information in response to search queries

1. A computer-implemented method for searching and selecting images, the method comprising:

receiving a content item that was searched and identified based on a first set of one or more keywords determined based on a search query received from a client device over a network;

searching in an image store to identify a plurality of images based on the first set of keywords and a second set of one or more keywords associated with the content item;

ranking the plurality of images based on a user context obtained at a time when the search query was received, including determining that a user of the client device is at a predetermined type of location based on a geographic location that was determined based on the user context; and, in response to the predetermined type of location, increasing a ranking of an image with a lower or less edge feature;

generating a composite content item by incorporating an image selected from the ranked images with the content item, wherein the selected image is ranked above a predetermined threshold; and

transmitting the composite content item to the client device over the network.

2. The method of claim 1 , wherein the user context was received along with the search query from the client device.

3. The method of claim 2 , wherein the user context includes a date and time when the search query was received.

4. The method of claim 3 , further comprising:

determining based on the user context that the date when the search query was received matches a predetermined day; and

selecting the image having a color feature matching the predetermined day.

5. The method of claim 1 , wherein ranking the plurality of images based on a user context comprises:

for each of the plurality of images, extracting one or more image features from the image;

determining whether the extracted image features are suitable for presentation based on the user context; and

removing the image from consideration if the extracted image features contradicts user contextual information provided by the user context.

6. The method of claim 5 , further comprising performing an image recognition on the image to determine image content represented by the image, wherein an image having image content related to the circumstances represented by the user context is ranked higher.

7. The method of claim 5 , wherein the image features include one or more of an edge feature, a color feature, or a blob feature.

8. A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations of searching and selecting images, the operations comprising:

receiving a content item that was searched and identified based on a first set of one or more keywords determined based on a search query received from a client device over a network;

searching in an image store to identify a plurality of images based on the first set of keywords and a second set of one or more keywords associated with the content item;

ranking the plurality of images based on a user context obtained at a time when the search query was received, including determining that a user of the client device is at a predetermined type of location based on a geographic location that was determined based on the user context; and, in response to the predetermined type of location, increasing a ranking of an image with a lower or less edge feature;

generating a composite content item by incorporating an image selected from the ranked images with the content item, wherein the selected image is ranked above a predetermined threshold; and

transmitting the composite content item to the client device over the network.

9. The machine-readable medium of claim 8 , wherein the user context was received along with the search query from the client device.

10. The machine-readable medium of claim 9 , wherein the user context includes a date and time when the search query was received.

11. The machine-readable medium of claim 10 , wherein the operations further comprise:

determining based on the user context that the date when the search query was received matches a predetermined day; and

selecting the image having a color feature matching the predetermined day.

12. The machine-readable medium of claim 8 , wherein ranking the plurality of images based on a user context comprises:

for each of the plurality of images, extracting one or more image features from the image;

determining whether the extracted image features are suitable for presentation based on the user context; and

removing the image from consideration if the extracted image features contradicts user contextual information provided by the user context.

13. The machine-readable medium of claim 12 , wherein the operations further comprise performing an image recognition on the image to determine image content represented by the image, wherein an image having image content related to the circumstances represented by the user context is ranked higher.

14. The machine-readable medium of claim 12 , wherein the image features include one or more of an edge feature, a color feature, or a blob feature.

15. A data processing system, comprising:

a processor; and

a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations of searching and selecting images, the operations including

receiving a content item that was searched and identified based on a first set of one or more keywords determined based on a search query received from a client device over a network,

searching in an image store to identify a plurality of images based on the first set of keywords and a second set of one or more keywords associated with the content item,

ranking the plurality of images based on a user context obtained at a time when the search query was received, including determining that a user of the client device is at a predetermined type of location based on a geographic location that was determined based on the user context; and, in response to the predetermined type of location, increasing a ranking of an image with a lower or less edge feature,

generating a composite content item by incorporating an image selected from the ranked images with the content item, wherein the selected image is ranked above a predetermined threshold, and

transmitting the composite content item to the client device over the network.

16. The system of claim 15 , wherein the user context was received along with the search query from the client device.

17. The system of claim 16 , wherein the user context includes a date and time when the search query was received.

18. The system of claim 17 , wherein the operations further comprise:

determining based on the user context that the date when the search query was received matches a predetermined day; and

selecting the image having a color feature matching the predetermined day.

19. The system of claim 15 , wherein ranking the plurality of images based on a user context comprises:

for each of the plurality of images, extracting one or more image features from the image;

determining whether the extracted image features are suitable for presentation based on the user context; and

removing the image from consideration if the extracted image features contradicts user contextual information provided by the user context.

20. The system of claim 19 , wherein the operations further comprise performing an image recognition on the image to determine image content represented by the image, wherein an image having image content related to the circumstances represented by the user context is ranked higher.

21. The system of claim 19 , wherein the image features include one or more of an edge feature, a color feature, or a blob feature.