The disclosed computer-implemented method for protecting search privacy may include (i) receiving, via a search interface, a search query comprising at least one search term, (ii) determining a sensitivity level of the search query based on the at least one search term, (iii) directing the search query to a search engine that has a level of privacy correlated with the sensitivity level of the search query, and (iv) returning, via the search interface, at least one result of directing the search query to the search engine that has the level of privacy correlated with the sensitivity level of the search query. Various other methods, systems, and computer-readable media are also disclosed.

Systems and methods providing drill-down access to timeline events to a user by a user interface are disclosed herein. In some embodiments, a timeline is presented to a user by the user interface. The timeline may comprise a plurality of event cards comprising event data associated with a customer. The user may select an input associated with the event card. Upon selection of the input, a second plurality of event cards indicative of an event category and associate with the customer may be displayed.

Techniques are disclosed to provide a graph based recommendation system. A recommendation engine definition that includes for each of a plurality of pipeline phases a corresponding phase definition and data indicating a location of the phase in a pipeline defined by the recommendation engine definition is stored in a memory of other storage device. The recommendation engine definition is used to generate programmatically one or more procedures to provide a recommendation engine that implements the pipeline. An API usable by a client to obtain a recommendation from the recommendation engine is generated programmatically and exposed.

A device can obtain location information that includes a set of location name values associated with a set of locations. The device can identify, using a natural language processing model, a set of proper noun values associated with the set of location name values. The device can generate a set of search criteria variant terms for the set of proper noun values. The set of search criteria variant terms can each include one or more characters associated with an alias of a particular proper noun value. The device can receive, from a user device, partial search criteria relating to an alias of a destination location. The device can process the partial search criteria using the set of search criteria variant terms to identify a set of candidate search terms. The device can provide the set of candidate search terms to the user device.

Techniques are disclosed to provide guided natural language interactions with a connected data system, such as a graph database. In various embodiments, natural language input associated with a graph database query associated with a graph data set is received. The natural language input is processed to generate a set of candidate strings. At least a subset of the candidate strings is mapped to an entity in the graph data set. The entity and data comprising the graph data are used set to determine a candidate graph pattern associated with the graph database query. The candidate graph pattern is used to guide a user associated with the natural language input to refine the graph database query.

A method for ranking relevance of documents includes using a set of queries, searching a corpus of documents for a set of candidate documents with information relevant to the set of queries. The method further includes ranking the set of candidate documents by a deep learning processing system according to relevance to respective ones of the set of queries. The method additionally includes responsive to user input, revising the ranked set of candidate documents to produce a revised ranked set of candidate documents. The method further includes using the revised ranked set of candidate documents to retrain the deep learning processing system. The method still further includes performing a categorization of the set of candidate documents by the retrained deep learning processing system.

In one implementation, a computer-implemented method includes receiving, at a computer system, a request for outdoor adventures that satisfy one or more criteria; accessing a centralized data repository of outdoor adventures that are provided by a plurality of different guides; identifying, by the computer system, one or more outdoor adventures based on a comparison of the one or more criteria to data associated with the outdoor adventures; generating code that includes information for the one or more outdoor adventures, the code being generated for execution or interpretation on the client computing device; and transmitting the code to the client computing device, wherein the client computing device is programmed to automatically execute or interpret the code upon receipt so as to present a graphical user interface presenting the one or more outdoor adventures and a selectable feature to reserve at least a portion of the one or more adventures.

An online concierge system generates an item graph connecting item nodes with attribute nodes of the items. Example attributes include a brand, a category, a department, or any other suitable information about the item. When the online concierge system receives a search query to identify one or more items from a customer, the online concierge system parses the search query into combinations of terms and identifies item nodes and attribute nodes related to the search query. The online concierge system identifies item nodes and attribute nodes that are likely to result in a conversion. Information about the identified nodes is presented to the customer. The customer may select an item node to purchase the item, or an attribute node to execute a new search query based on terms associated with the attribute node.

The disclosed computer-implemented method for producing message search recommendations may include (i) providing a search bar for searching a corpus of network messages such that the search bar is configured to enable a user to search the network messages by specifying both a specialized keyword that designates a separate common field for searching the network messages and a value that corresponds to the separate common field, (ii) detecting, as the user types the specialized keyword that the user is inputting the specialized keyword, and (iii) presenting, in response to detecting that the user is inputting the specialized keyword, a recommended different specialized keyword that has been used in conjunction with the detected specialized keyword in search queries rather than simply recommending a value that corresponds to the detected specialized keyword. Various other methods, systems, and computer-readable media are also disclosed.

Systems and methods are disclosed for assigning a global parameter to one or more queries present in a single graphical user interface (GUI) displayed in a client browser. The client browser causes the display of a first user interface field in a first area of the GUI, where the first user interface field can be used to enter or edit a first query. The client browser further causes the display of a second user interface field in a second area of the GUI, where the second user interface field can be used to enter or edit a second query. The client browser also receives a selection of a global parameter, applies the global parameter to the first and second queries, receives a modification to the global parameter for the second query, and causes execution of the first query using the global parameter and of the second query using the modification.