A completely unsupervised solution for generating and maintaining a list of lexically similar terms for an e-commerce system is provided. Given a particular electronic collection of items in an e-commerce system, each term in a first item listing is initially paired with each term in a second item listing to form a set of token pairs. The token pairs represent possible candidates for being synonyms. For a respective token pair, an attempt is made to match the shortest token of the token pair to the longest token of the token pair, character by character. If a match is successful, the terms in the token pair are automatically labeled as synonyms for the particular electronic collection of items. Some implementations automatically filter out false positives and/or token pairs that are unrelated and not likely synonyms. The solution can be performed at the granularity of a product, category, vertical, or entire catalog.

Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and perform: for each respective record in a plurality of records, assigning the respective record: (1) to a first database cluster on a first database server; or (2) to a second database cluster on a second database server; receiving a search request from a requester; executing the search request in the first database cluster to retrieve a first set of results; when the first set of results is greater than a threshold number of results, presenting the first set of results to the requester; and when the first set of results is less than the minimum number of results: executing the search request in the second database cluster to create a second set of results; and presenting the second set of results to the requester, wherein: the threshold number of results is configured such that a probability that the first set of results is greater than the minimum number of results is at least fifty percent. Other embodiments are disclosed herein.

A system and method for concept-based search and categorization that uses a lexical database to take a search term and from this to build a set of concepts and related terms and then searches stemmed or lemmatized text from a call transcription, email or chat message to perform categorization based on these concepts.

One or more techniques and/or systems for sending push notifications of content items to client devices are provided herein. For example, an input received from a user can be expanded to obtain an expanded user interest. Content items from a content source can be filtered based upon the expanded user interest to obtain a set of filtered content items. A push notification can be constructed to comprise one or more of the filtered content items from the set of filtered content items. The push notification can be sent to a client device of the user for display as a device alert notification. In an example, the filtered content items, within the push notification, may be ranked based upon a ranking metric.

The present disclosure relates to systems, devices, and methods for suggesting geographic results to a user. The systems, devices, and methods may include receiving a prefix for a geographic query and ranking received candidate results for the prefix of the geographic query. The systems, devices, and methods may provide a query expansion based on a highest ranked candidate result. The systems, devices, and methods may determine a likelihood of the user selecting the query expansion, and if the likelihood exceeds a threshold, provide the query expansion.

A retrieval device 10 includes an input unit 11 configured to receive a search query from a user, a retrieval unit 12 configured to calculate a degree of fitness between the search query and each of a plurality of pieces of retrieval target data, a query expansion unit 13 configured to generate an expanded search query, and a policy determination unit 14 configured to determine which of a first process and a second process is to be executed on the basis of the degree of fitness for each piece of the retrieval data calculated by the retrieval unit 12. The first process is presenting the retrieval target data having a high degree of fitness to the user. The second process is proposing to the user that the retrieval unit is caused to calculate the degree of fitness for each piece of the retrieval target data using the expanded search query.

Provided is a method including obtaining a corpus and an associated set of domain indicators. The method includes learning a set of vectors in an embedding space based on n-grams of the corpus. The method includes updating ontology graphs comprising a set of vertices and edges associating the set of vertices with each other. The method also includes determining a vector cluster using hierarchical clustering based on distances of the set of vectors with respect to each other in the embedding space and determining a hierarchy of the ontology graphs based on a set of domain indicators of a respective set of vertices corresponding to vectors of the vector cluster. The method also includes updating an index based on the ontology graphs.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for optimized graph traversal are disclosed. In one aspect, a method includes the actions of receiving a given phrase that is input through a user interface by a digital component provider. The actions further include determining an entity that is being referred to by the given phrase. The actions further include identifying properties of the entity. The actions further include selecting a subset of the properties that were identified for the entity. The actions further include identifying additional phrases. The actions further include updating the user interface to present at least some of the additional phrases with programmatic controls that assign one or more of the additional phrase as distribution criteria for digital components of the digital component provider in response to activation of the programmatic controls.

An architecture for semantic search over encrypted data that improves upon existing encrypted data search techniques by providing a solution that is space-efficient on both the cloud and client sides, considers the semantic meaning of the user's query, and returns a list of documents accurately ranked by their similarity to the query. Different search schemes are presented based on S3C architecture (namely, FKSS, SKSS, and KSWF) that are fine-tuned for different types of datasets. The system requires only a single plaintext query to be entered and is easily portable to thin-clients, making it simple and quick for users to use. The system is also shown to be secure and resistant to attacks.

A system for conducting a search of dual databases for conducting a dual search, where at least two databases are searched simultaneously by entering a single search term comprising a processor and a memory to store a set of instructions wherein the processor accesses the instructions to receive a search term by a program, dissect the search term into its component parts using a dictionary algorithm, form a first search term having a first format of the first search term, form a second search term with a second format of the second search term, use the first search term to search a first database and saving a first result, use the second search term to search a second database and saving a second result and combine the first and second results in a single display page.