A computer system including a memory, at least one processor coupled to the memory, and a search component executable by the at least one processor is provided. The search component is configured to receive information descriptive of at least one search term; execute a first query against a plurality of documents that identifies at least one first document of the plurality of documents responsive to the at least one search term; identify one or more secondary terms associated with the at least one first document based on occurrence of the one or more secondary terms within the at least one first document; and provide a search result including at least one of the one or more secondary terms and one or more identifiers of one or more documents including the one or more secondary terms. The search result may also include one or more identifiers of bookmarked documents.

Methods, systems, and techniques for using of keywords, categories, patent related publications, and other literature to profile users are provided. Some examples provide a profiling tool which enables users to self-describe using, for example, keywords, patent related publications, and articles. In other examples, the tool assigns search-based profiling information. The profiling tool using citation based patent related search techniques to suggest additional keywords and/or patent publications for augmenting the user's search-based profile information. In some examples, the IP Invention Management System (IPIMS) uses these profiles to distribute workload, for example, to route patent assets to be reviewed or be improved upon as ripe for invention. In addition, other applications may use these profiles to offer other types of matching services, such as social mapping.

A word completion method and apparatus are described. The method is applied to a search scenario and is used to complete an incomplete word entered by a user. The method is based on an improved trie. Hot words are stored in some nodes of the trie. In the word completion method, a target node that matches a character string is searched in the trie, and at least one completed word is output to a user based on a hot word stored in the target node. Word completion efficiency is improved, and a case in which a word is recommended to a user when the user enters an excessively short character string is avoided.

The disclosed subject matter relates to a system and method for providing an extended search. The system generates a list of synonym groups based on previous engagements linking queries and products. With receipt of a user query, the system accesses synonyms to the search terms and incorporates them into the query of the product catalog in order to obtain a complete set of results. The creation of the synonym groups uses various approaches including sequence tagging and graph embedding to identify synonyms in the query and the item titles.

A method and apparatus of a device that links a term in an application running on a device to a predictive search query is described. In one embodiment, the device receives a plurality of key terms from a key terms server, wherein each of the plurality of key terms is associated with the predictive search query. For each of the plurality of application terms, the device determines if there is a matching key term for this application term with at least one of the plurality of key terms. The device further receives an indication that a user has selected the matching key term. In addition, the device requests a query search to a search server using the predictive search query associated with the matching key term. Furthermore, the device receives a query search result from the query search server and presents the query search results to the user of the device.

Disclosed embodiments include computer-implemented methods and systems that can efficiently generate highly relevant recommended search terms to clinicians. A hybrid collaborative filtering model recommends search terms for a specific patient to the clinician. The model draws on information from patients' clinical encounters and the searches that were performed during the clinical encounters. To generate recommendations, the model uses search terms which are (1) frequently co-occurring with the ICD codes recorded for the patient and (2) highly relevant to the most recent search terms. One variation of the model uses only the most recent ICD codes assigned to the patient. Another variation uses all ICD codes. Comprehensive experiments of embodiments of the methods and systems have demonstrate high levels of performance.

Various embodiments are described herein that generally relate to systems and methods for generating context specific terms and performing various actions based on the context specific terms. One example embodiment includes a computer-implemented method for generating context specific terms comprising obtaining a collection of terms from at least one electronic file associated with a given context; comparing the collection of terms with a collection of expected terms to generate candidate terms that are not in the collection of expected terms; determining a relevance for each of the candidate terms; and determining whether to add a given candidate term to a collection of context specific terms for the given context if the relevance for the given candidate term is above a threshold.

Systems and processes for predictive conversion of language input are provided. In one example process, text composed by a user can be obtained. Input comprising a sequence of symbols of a first symbolic system can be received from the user. Candidate word strings corresponding to the sequence of symbols can be determined. Each candidate word string can comprise two or more words of a second symbolic system. The candidate word strings can be ranked based on a probability of occurrence of each candidate word string in the obtained text. Based on the ranking, a portion of the candidate word strings can be displayed for selection by the user.

The present teaching relates to providing a query suggestion. In one example, a request is received for query suggestions with respect to a query prefix input by a user. A plurality of query suggestions is determined based on the query prefix and a preceding query input by the user. A degree of popularity of the preceding query is determined. One or more query suggestions are selected from the plurality of query suggestions based on the degree of popularity of the preceding query. The one or more query suggestions are provided as a response to the request.

In one embodiment, a method includes receiving a user query inputted on a head-mounted device from the head-mounted device, wherein the user query corresponds to multiple dialog-intents, executing multiple tasks corresponding to the multiple dialog-intents, generating a multi-perspective response by a stitching model based on two or more of execution results of the multiple tasks, wherein the stitching model combines the two or more of the execution results based on natural language processing, and wherein the multi-perspective response comprises a natural-language response combining the two or more execution results, and sending instructions to the head-mounted device for presenting the multi-perspective response on the head-mounted device.