Speech-based selection of augmented reality content for detected objects

1. A method, comprising:

causing, by a messaging application running on a device, a camera of the device to capture an image;

receiving by the messaging application, speech input to select augmented reality content for display with the image;

determining at least one keyword included in the speech input;

determining that the at least one keyword indicates an object depicted in the image and an action to perform with respect to the object;

determining first attributes of the object;

assigning weights to each of the first attributes of the object;

ranking plural augmented reality content items based on the assigned weights and on second attributes of the action;

selecting, based on the ranking, a highest-ranked augmented reality content item from among the plural augmented reality content items;

activating the highest-ranked augmented reality content item with respect to the image; and

displaying, in ranked order based on the ranking, an interface with user-selectable elements for activating remaining ones of the plural augmented reality content items.

2. The method of claim 1 , further comprising:

performing a scan of the image to identify multiple objects in the image; and

detecting, based on performing the scan, the object from among the multiple objects.

3. The method of claim 1 , wherein determining the at least one keyword comprises:

sending, to a speech recognition service, a request to perform speech recognition based on the speech input; and

receiving, from the speech recognition service and based on sending the request, the at least one keyword.

4. The method of claim 3 , wherein a first part of the speech input includes a trigger word, and

wherein the at least one keyword is based on a second part of the speech input that does not include the trigger word.

5. The method of claim 1 ,

wherein the interface is a carousel interface with a respective user-selectable icon for each of the plural augmented reality content items, and

wherein the carousel interface differentiates display of the icon for the augmented reality content item, relative to remaining icons, within the carousel interface.

6. The method of claim 1 , where the at least one keyword comprises a first keyword indicating the object and a second keyword indicating the action to perform with respect to the object.

7. The method of claim 1 , wherein the object is a math problem and the action corresponds to solving the math problem,

wherein the selecting comprises selecting, from among the plural augmented reality content items, the augmented reality content item that corresponds to displaying a solution to the math problem, and

wherein the displaying comprises displaying the solution to the math problem with the image.

8. The method of claim 7 , further comprising:

displaying a link which is user-selectable to navigate to a third-party application that provides additional information with respect to solving the math problem.

9. A device, comprising:

a processor; and

a memory storing instructions that, when executed by the processor, cause the processor to:

cause, by a messaging application running on a device, a camera of the device to capture an image;

receive by the messaging application, speech input to select augmented reality content for display with the image;

determine at least one keyword included in the speech input;

determine that the at least one keyword indicates an object depicted in the image and an action to perform with respect to the object;

determine first attributes of the object;

assign weights to each of the first attributes of the object;

rank plural augmented reality content items based on the assigned weights and on second attributes of the action;

select, based on the ranking, a highest-ranked augmented reality content item from among the plural augmented reality content items;

activate the highest-ranked augmented reality content item with respect to the image; and

display, in ranked order based on the ranking, an interface with user-selectable elements for activating remaining ones of the plural augmented reality content items.

10. The device of claim 9 , wherein the instructions further cause the processor to:

perform a scan of the image to identify multiple objects in the image; and

detect, based on performing the scan, the object from among the multiple objects.

11. The device of claim 9 , wherein determining the at least one keyword comprises:

sending, to a speech recognition service, a request to perform speech recognition based on the speech input; and

receiving, from the speech recognition service and based on sending the request, the at least one keyword.

12. The device of claim 11 , wherein a first part of the speech input includes a trigger word, and

wherein the at least one keyword is based on a second part of the speech input that does not include the trigger word.

13. The device of claim 9 , wherein

the interface is a carousel interface with a respective user-selectable icon for each of the plural augmented reality content items, and

wherein the carousel interface differentiates display of the icon for the augmented reality content item, relative to remaining icons, within the carousel interface.

14. A non-transitory computer-readable storage medium, the computer-readable storage medium including instructions that when executed by a computer, cause the computer to:

cause, by a messaging application running on a device, a camera of the device to capture an image;

receive by the messaging application, speech input to select augmented reality content for display with the image;

determine at least one keyword included in the speech input;

determine that the at least one keyword indicates an object depicted in the image and an action to perform with respect to the object;

determine first attributes of the object;

assign weights to each of the first attributes of the object;

rank plural augmented reality content items based on the assigned weights and on second attributes of the action;

select, based on the ranking, a highest-ranked augmented reality content item from among the plural augmented reality content items;

activate the highest-ranked augmented reality content item with respect to the image; and

display, in ranked order based on the ranking, an interface with user-selectable elements for activating remaining ones of the plural augmented reality content items.