A document repository may be searched for documents that are similar to a source document. Multiple queries may be generated based on a type of the source document, and the results may be combined in a unified response. User behavior may then be monitored, and implicit and explicit feedback may be gathered to evaluate the performance of the search. The gathered feedback may indicate how relevant each of the result documents are in comparison to the original source document. This feedback may then be used to adjust search parameters for the source document type, such that the performance of subsequent searches may be improved. A model may also be trained to classify implicit feedback using explicit feedback received from users.

Embodiments of the present disclosure provide a method and apparatus for processing consultation information. A specific implementation of the method includes: pushing, in response to receiving consultation information of a first user, a questionnaire corresponding to the consultation information to the first user; acquiring a questionnaire result corresponding to the questionnaire and submitted by the first user; inputting the questionnaire result into a preset consultation model, to obtain a first consultation result; pushing the questionnaire result and the first consultation result to a second user; and in response to receiving a second consultation result provided by the second user based on the questionnaire result and the first consultation result, pushing the second consultation result to the first user.

Methods, apparatuses, and systems for grouping topics for users from different communication platforms are described herein. For example, a computing device may receive, from a user and via a communication platform, a request for sending content associated with the communication platform to the computing device. The computing device may determine, based on the received request, one or more keywords from the content. In addition, the computing device may determine a topic based on the one or more keywords. In addition, the computing device may determine a similarity between the determined topic and one or more stored topics. The one or more stored topics may be associated with one or more additional users. Further, based on a determination that the similarity satisfies a threshold, the computing device may send, to the user, a message identifying the one or more additional users.

Systems for processing queries may first determine correspondence between the parameters of the query and a set of existing data entries, a set of previous queries that have been received, or both the existing data entries and the previous queries. If the query parameters do not correspond to the data entries or pervious queries, correspondence is determined between the query parameters and group data that associates at least a subset the query parameters with a particular group that may generate a response to the query. The same group or the generated response may be used when similar queries are received. If the group transmits the query to a different group or if negative user feedback is received, the group data may be modified to indicate the different group or to remove the association with the initial group that received the query.

A device, system and method for providing descriptions to communication devices using machine learning generated templates is provided. A device replaces given word types in provided text files with corresponding tags to generate corresponding intermediate templates, the provided text files associated with a given topic. The device generates, for the given topic, one or more textual templates that include at least a portion of the corresponding tags, the textual templates in natural language sentences, the generating of the textual templates at least partially based on the corresponding intermediate templates. The device populate the corresponding tags in a textual template, of the textual templates, with corresponding words of a given data file associated with the given topic, to generate a respective description of a given item associated with the given topic, the given data file being specific to the given item. The device provides the respective description to a communication device

With the proliferation of data and documents available on the internet and other information sources, analysis of adverse events poses a serious technical challenge on account of associated data volume and variety. This disclosure relates generally to identification and profiling of adverse events. By receiving a set of articles from a plurality of data sources and utilizing a series of Natural Language Processors, NLP techniques are employed to identify implicit and explicit adverse events. Entity statistics and sentiment extraction and analysis is performed. An ontology based adverse event identification framework is proposed for identification and profiling of implicit adverse event. An attention based bi-directional long short term memory network for adverse event identification and classification is proposed.

This invention relates to a computer-implemented method of (and a system for) searching clustered data (106), the clustered data (106) representing a multi-dimensional feature space and the method comprising the steps of: obtaining data representing a query feature vector (202) comprising a predetermined number of numerical feature values, projecting the query feature vector (202) into the clustered data (106) and obtaining a number of potential matches (203) determined to be within a pre-determined dimensional range of the query feature vector (202), determining data representing one or more score values for each of the potential matches (203), updating or re-calibrating the query feature vector (202), resulting in a modified query feature vector, in response to the determined one or more score values, projecting the modified query feature vector into the clustered data (106) and obtaining a number of potential matches (203) in response thereto, and repeating the steps of determining data representing one or more score values, updating or re-calibrating the query feature vector (202), and projecting the modified query feature vector into the clustered data (106) and obtaining a number of potential matches (203) in response thereto, until the obtained number of potential matches (203) are satisfactory according to one or more predetermined criteria and then providing the satisfactory potential matches (203) as a search result (206).

A method and system are provided for combining models. The method includes forming, by a computer having a processor and a memory, model pairs from a model ensemble that includes a plurality of models. The method further includes comparing the model pairs based on sets of output results produced by the model pairs to provide comparison results. The method also includes constructing, by the computer, a combination model from at least one of the model pairs based on the comparison results. The comparing step is performed using user-generated set-based feedback.

A transcription of a query for content discovery is generated, and a context of the query is identified, as well as a first plurality of candidate entities to which the query refers. A search is performed based on the context of the query and the first plurality of candidate entities, and results are generated for output. A transcription of a second voice query is then generated, and it is determined whether the second transcription includes a trigger term indicating a corrective query. If so, the context of the first query is retrieved. A second term of the second query similar to a term of the first query is identified, and a second plurality of candidate entities to which the second term refers is determined. A second search is performed based on the second plurality of candidates and the context, and new search results are generated for output.

A transcription of a query for content discovery is generated, and a context of the query is identified, as well as a first plurality of candidate entities to which the query refers. A search is performed based on the context of the query and the first plurality of candidate entities, and results are generated for output. A transcription of a second voice query is then generated, and it is determined whether the second transcription includes a trigger term indicating a corrective query. If so, the context of the first query is retrieved. A second term of the second query similar to a term of the first query is identified, and a second plurality of candidate entities to which the second term refers is determined. A second search is performed based on the second plurality of candidates and the context, and new search results are generated for output.