Techniques are described including displaying an interface associated with a computing device, the interface being configured to present a form including a text entry box, receiving data from an activity information pipeline associated with a self-reporting service, the activity information pipeline having a source of activity information associated with a tool configured to geotag the activity information and another source of associated with a mobile sensor configured to capture other activity information geotagged by the tool, the other activity information being processed by the self-reporting service to deprioritize a suggestion over another suggestion, displaying, in response to selection of the text entry box, a suggestion indicative of a journey and identified as prioritized and presented proximate to the center of the interface of the display device, and dynamically adjusting the suggestion while prioritizing display of the suggestion over a generic suggestion.

An electronic device is described which has a user interface which receives an input comprising a sequence of target indicators of data items. The data entry system has a search component which searches for candidate expanded sequences of indicators comprising the target indicators. The search component searches amongst indicators generated by a trained conditional language model, the conditional language model having been trained using pairs, each individual pair comprising a sequence of indicators and a corresponding expanded sequence of indicators.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for ranking query completions based on activity session data. One of the methods includes receiving a query prefix from a user. A reference parameter for the user is obtained. One or more likely queries that are likely to co-occur with the reference parameter in user activity sessions are identified, wherein each likely query has an associated prediction score. A ranking of the one or more likely queries is provided in response to receiving the query prefix.

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.

A device may receive a request to identify items that satisfy parameters of the request. The device may identify a plurality of items that satisfy the parameters. The device may generate a plurality of explanation sets. An explanation set of the plurality of explanation sets may relate to an item of the plurality of items. The explanation set may include at least one of: a positive explanation indicating that the item is positively associated with a first characteristic that relates to a first preference of a user, or a negative explanation indicating that the item is negatively associated with a second characteristic that relates to a second preference of the user. The device may select an item from the plurality of items based on the plurality of explanation sets. The device may provide information that includes an explanation set of the item selected.

A method executed by a computing device includes determining a set of identigens for each query word of a query to produce sets of identigens. The method further includes interpreting the sets of identigens to produce different first and second query entigen groups. The method further includes generating an interim response based on the first and second query entigen groups. The method further includes determining a set of identigens for each updated query word of an updated query to produce updated sets of identigens. The method further includes selecting one of the first or second query entigen group based on the updated sets of identigens to produce a selected query entigen group. The method further includes generating a response entigen group utilizing the selected query entigen group and generating a response to the query utilizing the response entigen group.

Implementations described herein relate to generating, locally at a client device, corresponding subset(s) of zero-prefix suggestions, for a user of the client device, and for suggestion state(s) associated with the client device, and subsequently causing the client device to utilize the corresponding subset(s) of zero-prefix suggestions. The suggestion state(s) and a superset of candidate zero-prefix suggestions can be processed, using machine learning model(s), to generate a corresponding score for each of the candidate zero-prefix suggestions and with respect to the suggestion state(s). Further, zero-prefix suggestions can be selected for inclusion in the corresponding subset(s) of zero-prefix suggestions, and for the suggestion state(s), based on the corresponding scores. Accordingly, when a given suggestion state is subsequently detected at the client device, a given corresponding subset of zero-prefix suggestions that is stored in association with the given suggestion state can be obtained and provided for presentation to the user.

Aspects of the technology described herein leverage usage data of content items to facilitate returning search results relevant to a user's intent. A search engine enables a user to select from one of three filter options: a first filter option for the user's own content items, a second filter option for content items previously accessed by the user, and a third filter option for content items new to the user. In response to selection of one of the filter options, the search engine identifies and returns search results based at least in part on correspondence between usage data for content items and the selected filter option. In some aspects, the search engine may automatically select one of the filter options based on search context and provide the selected filter option as a filter suggestion.

A method and system are described that provide responses to natural language queries regarding the performance of a business. The method and system provide for crowd-sourced data to determine natural language query suggestions to transmit to a user, based upon previously submitted questions of the user and/or similar merchants to the user. Natural language query suggestions may be provided as utterances to a keyboard of a merchant user. The merchant user may select one or more suggestions provided. The use of natural language queries and responses allows a merchant without a business intelligence background to obtain business insights easily and accurately assess his performance (e.g., against similar merchants, etc.) without personally identifiable or confidential information of other merchants being compromised.

A method includes receiving, by a processing device, a command search query for searching a command search history, identifying, by the processing device, a command from the command search history in view of the command search query, determining, by the processing device, that the command comprises a replaceable parameter, identifying, by the processing device, a content source corresponding to the replaceable parameter, and generating, by the processing device, an updated command by replacing the replaceable parameter with a data item from the content source.