Abstract: Systems and methods for generating personalized input suggestions for query interfaces are described. The query interfaces can include chat interfaces (such as chatbot interfaces) and web browsers, for example. In some cases, the system generates personalized input suggestions for a particular user by identifying a set of files that are predicted to be relevant to the user and providing information about each of the files in a prompt to an artificial intelligence (AI) model. The AI model generates a response based on the prompt, and the system surfaces the response in a query interface as an input suggestion. In some cases, the system generates personalized input suggestions (e.g., using an AI model) for a particular user based on the user's search history and classifies each of the generated input suggestions with a label. The system selects input suggestions for surfacing in a query interface based on the label.

Abstract: Systems and methods for generating personalized input suggestions for query interfaces are described. The query interfaces can include chat interfaces (such as chatbot interfaces) and web browsers, for example. In some cases, the system generates personalized input suggestions for a particular user by identifying a set of files that are predicted to be relevant to the user and providing information about each of the files in a prompt to an artificial intelligence (AI) model. The AI model generates a response based on the prompt, and the system surfaces the response in a query interface as an input suggestion. In some cases, the system generates personalized input suggestions (e.g., using an AI model) for a particular user based on the user's search history and classifies each of the generated input suggestions with a label. The system selects input suggestions for surfacing in a query interface based on the label.

Abstract: Non-limiting examples of the present disclosure describe processing by a contextual image analysis service that generates and surfaces contextually relevant data objects based on entities identified from image content. In one example, image content is analyzed and entity annotations are generated for the image content. The entity annotations may be converted to queries. Raw search results may be identified based on the converted queries. The raw search results may be filtered based on one or more specific content types. A contextual representation is generated based on the filtered raw search results, where the contextual representation comprises the image content and one or more contextually relevant data objects for at least one entity associated with the image content. The exemplary contextual representation of the image content and the one or more contextually relevant data objects may be surfaced through a user interface of an application/service.

Abstract: The technology described herein provides an efficient mechanism for quickly analyzing huge amounts of media content to find media content (hereafter “content” or “media content”) that is relevant to a user. The technology analyzes features of a curator to classify curators by interest and/or find curators with similar content recommendations. The curator data can be used to make curator recommendations to users based on the user's interests. The technology described herein collects curator data from multiple content sites and analyzes the data to identify curators that recommend similar content on different content sites.

Abstract: Non-limiting examples of the present disclosure describe processing by a contextual image analysis service that generates and surfaces contextually relevant data objects based on entities identified from image content. In one example, image content is analyzed and entity annotations are generated for the image content. The entity annotations may be converted to queries. Raw search results may be identified based on the converted queries. The raw search results may be filtered based on one or more specific content types. A contextual representation is generated based on the filtered raw search results, where the contextual representation comprises the image content and one or more contextually relevant data objects for at least one entity associated with the image content. The exemplary contextual representation of the image content and the one or more contextually relevant data objects may be surfaced through a user interface of an application/service.

Abstract: Examples of the present disclosure describe systems and methods for dynamic representation of suggested queries. In an example, a suggested search query may be generated to provide a user with an alternative query that may be used by the user to adjust, refine, or vary a search. The suggested search query may be displayed to the user in the form of suggested content, wherein the suggested content may comprise a compilation or a collage of search results associated with the suggested search query. A suggested search query may be generated based on one or more datasets, wherein a dataset may provide different variations for a given search query. Accordingly, search queries from different datasets may be incorporated into search results, thereby providing diverse and dynamic search suggestions to the user.

Abstract: Data regarding a base digital image and a request to generate one or more customized digital stickers for the base digital image can be received. In response to the received request, a customized digital sticker can be generated for the base digital image using results of analysis of the data regarding the base digital image, with the customized sticker including multiple visual features. The generating can include generating a customized digital sticker using a set of sticker generation rules, with the layout of multiple visual features of the digital sticker being dictated by the sticker generation rules, and with the generating of the sticker including combining the multiple visual features in the digital sticker. The digital sticker can be overlaid on the base digital image to produce a composite digital image.

Abstract: The technology described herein provides an efficient mechanism for quickly analyzing huge amounts of media content to find media content (hereafter “content” or “media content”) that is relevant to a user. The technology analyzes features of a curator to classify curators by interest and/or find curators with similar content recommendations. The curator data can be used to make curator recommendations to users based on the user's interests. The technology described herein collects curator data from multiple content sites and analyzes the data to identify curators that recommend similar content on different content sites.