Provided in the present disclosure are a computer-implemented searching method and a server. The computer-implemented searching method includes: receiving, at one or more computing devices, a current searching term sent by a client; obtaining, at the one or more computing devices, a picture-expressible term contained in the current searching term; obtaining, at the one or more computing devices, a picture result according to the picture-expressible term; and sending, at the one or more computing devices, the picture result to the client. The present method improves the effect of the information expression of the search results.

A system for performing semantic search receives an electronic text corpus and separates the text corpus into a plurality of sentences. The system parses and converts each sentence into a sentence tree. The system receives a search query and matches the search query with one or more of the sentence trees.

The embodiments herein relate to intellectual property management and, more particularly, to a tool for searching and evaluating relative commercial potential of an invention. A user may select any of the services such as search, draft, innovation evaluation, commercial potential evaluation and so on. A search tool automatically generates a key string based on user inputs, searches in associated databases, organizes search results and delivers to the user. The keywords are improved or modified automatically by the search tool so as to improve subsequent search results. The keywords are improved by considering parameters such as field of search, search history of the user and so on. Further, new keywords are added to a dictionary so as to improve search strings each time. Drafting tools may be used to draft patent applications in specific format. Further, a research commercialization evaluator is used to analyze commercial potential of an invention.

A device may receive input indicating one or more search parameters associated with a search. The device may perform a comparison of the input and a dictionary file to identify the one or more search parameters associated with the search. The dictionary file may be associated with a domain specific language. The device may determine a combination or quantity of search parameters associated with the search based on a result of the comparison. The device may select a search template to be used to perform the search based on the combination or quantity of search parameters. The search template may be populated with information identifying the one or more search parameters. The device may perform the search using the search template populated with the information identifying the one or more search parameters. The device may perform an action based on a result of performing the search.

Provided are architectures, system, methods, and computer program products that provide a user with the ability to define an association of data and/or information from known reference sets perceived by the user as relevant to a subject matter domain, thereby imparting and formalizing some of the user's knowledge about the domain. An associative relevancy knowledge profiler may also allow a user to create a profile by modifying or restricting the known reference sets and windowing the results from the association as a user might refine any other analysis algorithms. An associative relevancy knowledge profiler may also be used to define a user profile used by the user and others. A user profile may be usable in various manners depending upon, for example, rights management permissions and restrictions for a user.

In one general embodiment, a computer-implemented method includes identifying an input search term, determining an additional term associated with the input search term, where the additional term targets a predetermined entity, altering the input search term utilizing the determined additional term, and performing a search, utilizing the altered input search term

Systems and methods are described to address shortcomings in a conventional conversation system via a novel technique utilizing artificial neural networks to train the conversation system whether or not to continue context. In some aspects, an interactive media guidance application determines a type of conversation continuity in a natural language conversation comprising first and second queries. The interactive media guidance application determines a first token in the first query and a second token in the second query. The interactive media guidance application identifies entity data for the first and second tokens. The interactive media guidance application retrieves, from a knowledge graph, graph connections between the entity data for the first and second tokens. The interactive media guidance application applies this data as inputs to an artificial neural network. The interactive media guidance application determines an output that indicates the type of conversation continuity between the first and second queries.

Disclosed herein are techniques related to automated generation of regular expressions. In some embodiments, a regular expression generator may receive input data comprising one or more character sequences. The regular expression generator may convert character sequences into a sets of regular expression codes and/or span data structures. The regular expression generator may identify a longest common subsequence shared by the sets of regular expression codes and/or spans, and may generate a regular expression based upon the longest common subsequence.

A structured dictionary in a database is populated from unstructured text stored in a data repository. Dictionary text is retrieved from the data repository and a dictionary term and an associated dictionary definition are identified from the dictionary text. A database category is determined for the dictionary term from the associated dictionary definition. An indication of the dictionary term is stored in the structured dictionary in association with the database category.

Systems and methods are described to suggest new content to a writer. An intelligent tool is initiated to obtain content of a document that is being written by an author. The intelligent tool then determines a topic of the content of the document, and identifies one or more predictive topics related to the determined topic. The one or more predictive topics are different from the topic. The intelligent tool then performs a content search based on the topic and the one or more predictive topics, and provides results from the content search to the author.