A query modality recommendation system provides recommendations to use a particular query modality based on one or more categories of search results for a search query. Upon receiving a search query in a first query modality at a search engine, the query modality recommendation system determines to recommend use of a second query modality based on one or more categories of the search results. For example, the first query modality may be a textual query and the second query modality may be an image query. In aspects, recommending use of the second query modality comprises comparing a first search performance of the one or more categories for the first query modality in historical search queries to a second search performance of the one or more categories for the second query modality in the historical search queries.

Search queries are received and search results are provided. Interaction tracking is used to determine with which search results users interact. The search results having received interactions can be represented as item vectors, which can include a vector representation of a portion of the search result, such as a title, description, or image. For each search query, the item vectors are aggregated, such as by averaging the item vectors. The search queries are stored in an item dataset as collected search queries respectively associated with the aggregate item vectors. When a new search query is received, a search query vector can be compared to the aggregate item description vectors to identify collected search queries that are related. The related collected search queries can be provided as search query recommendations or search results associated with the collected search queries can be provided in response to receiving the new search query.

Search queries are received and search results are provided. Interaction tracking is used to determine with which search results users interact. The search results having received interactions can be represented as item vectors, which can include a vector representation of a portion of the search result, such as a title, description, or image. For each search query, the item vectors are aggregated, such as by averaging the item vectors. The search queries are stored in an item dataset as collected search queries respectively associated with the aggregate item vectors. When a new search query is received, a search query vector can be compared to the aggregate item description vectors to identify collected search queries that are related. The related collected search queries can be provided as search query recommendations or search results associated with the collected search queries can be provided in response to receiving the new search query.

In one embodiment, a method includes receiving an initial input in a first modality from a first user from a client system associated with the first user, determining one or more intents corresponding to the initial input by an intent-understanding module, generating one or more candidate continuation-inputs based on the one or more intents, where the one or more candidate continuation-inputs are in one or more candidate modalities, respectively, and wherein the candidate modalities are different from the first modality, and sending instructions for presenting one or more suggested inputs corresponding to one or more of the candidate continuation-inputs to the client system.

Methods and systems for searching SaaS virtual applications are disclosed. One method includes receiving a set of search terms for a search of a virtual application, the search of the virtual application being executable without having the virtual application open on a computing device. The search request is provided to a source of the virtual application, the request including the set of search terms for the virtual application. At least one response is received from the source of the virtual application based on the set of search terms. A list of search results is provided to the computing device to enable selection of the virtual application from a plurality of other virtual applications accessible via the computing device, the list of search results including the received at least one response.

Methods and systems for searching SaaS virtual applications are disclosed. One method includes receiving a set of search terms for a search of a virtual application, the search of the virtual application being executable without having the virtual application open on a computing device. The search request is provided to a source of the virtual application, the request including the set of search terms for the virtual application. At least one response is received from the source of the virtual application based on the set of search terms. A list of search results is provided to the computing device to enable selection of the virtual application from a plurality of other virtual applications accessible via the computing device, the list of search results including the received at least one response.

Implemented is a remote accessibility service that utilizes a plugin for websites to provide people with an enhanced and standardized browsing experience. The remote accessibility service transmits a plugin to a website that is instantiated on a host service, in which the plugin gathers content from the website and parses and stores the content at the remote accessibility service. The gathered content is transitioned into the remote accessibility service's closed system accessibility environment. Thus, content gathered from a series of e-commerce websites, for example, are all transitioned into a standardized format to enhance the accessibility experience for users. Transitioning the content into a single standardized format makes accessibility consistent, memorable, and harmonious for users who are perusing many websites—instead of relying on the proprietary, discordant, and often times clunky accessibility implementations among each website.

Implemented is a remote accessibility service that utilizes a plugin for websites to provide people with an enhanced and standardized browsing experience. The remote accessibility service transmits a plugin to a website that is instantiated on a host service, in which the plugin gathers content from the website and parses and stores the content at the remote accessibility service. The gathered content is transitioned into the remote accessibility service's closed system accessibility environment. Thus, content gathered from a series of e-commerce websites, for example, are all transitioned into a standardized format to enhance the accessibility experience for users. Transitioning the content into a single standardized format makes accessibility consistent, memorable, and harmonious for users who are perusing many websites—instead of relying on the proprietary, discordant, and often times clunky accessibility implementations among each website.

An artificial intelligence device according to an embodiment of the present disclosure may receive voice data corresponding to viewing information and a search command from a display device, convert the received voice data into text data, obtain a first query indicating intention of the converted text data, convert the first query into a second query based on the viewing information, obtain a search result corresponding to the converted second, and transmit the obtained search result to the display device.

An artificial intelligence device according to an embodiment of the present disclosure may receive voice data corresponding to viewing information and a search command from a display device, convert the received voice data into text data, obtain a first query indicating intention of the converted text data, convert the first query into a second query based on the viewing information, obtain a search result corresponding to the converted second, and transmit the obtained search result to the display device.