An information search system, including: a database (12); a query sentence acceptance unit (26) that accepts a query sentence; an inputted search keyword extractor (44) that extracts an inputted search keyword from the query sentence; a shared keyword dictionary (30) in which relevant keywords are registered in association with each other; a local keyword dictionary (102) in which district keywords used in particular districts are registered; a candidate search keyword reader (32) that reads out a keyword that is relevant to the inputted search keyword; and a retrieval executor (40) that executes retrieval processing from the database using the inputted search keyword, wherein, in a case in which the inputted search keyword is not registered in the local keyword dictionary, the candidate search keyword reader refers to the shared keyword dictionary, so as to read out a keyword that is relevant to the inputted search keyword.

An extraction unit (15b) extracts words included in information related to work. A calculation unit (15c) calculates a degree of infrequency of appearance with respect to each of the extracted words. A classification unit (15d) classifies the information related to the work issue by issue, by using the calculated degrees of infrequency of appearance of the words.

An extraction unit (15b) extracts words included in information related to work. A calculation unit (15c) calculates a degree of infrequency of appearance with respect to each of the extracted words. A classification unit (15d) classifies the information related to the work issue by issue, by using the calculated degrees of infrequency of appearance of the words.

A communication system is configured to broadcast utterance voice data received from one of mobile communication terminals to other mobile communication terminals, to control text delivery such that a result of utterance voice recognition from voice recognition processing on the received utterance voice data is displayed on the mobile communication terminals in synchronization, and to use the result of utterance voice recognition to perform communication evaluation. The communication evaluation includes a first evaluation including evaluating a dialogue between users based on a group dialogue index to produce group communication evaluation information, a second evaluation including evaluating utterances constituting the dialogue between the users based on a personal utterance index to produce personal utterance evaluation information, and a third evaluation including using the group communication evaluation information and the personal utterance evaluation information to produce entire communication group evaluation information.

A method, system, and medium for automated analysis of business intelligence each: receive natural language input from a user; evaluate, via a natural language understanding processor that includes a parser and an interpreter, the natural language input to determine an intent of the user; determine the intent of the user and generate a query based on a context manager; send an identification of the failure to a failure analysis system for human intervened analysis and refinement of a natural language model used by the natural language understand processor; assess, via a context manager processor, to determine a user interest in one or more portions of results of the query, a scrolling of the user through the results of the query; and refine, based on the user interest in the one or more portions of the results of the query, an output of the results of the query.

A method, system, and medium for automated analysis of business intelligence each: receive natural language input from a user; evaluate, via a natural language understanding processor that includes a parser and an interpreter, the natural language input to determine an intent of the user; determine the intent of the user and generate a query based on a context manager; send an identification of the failure to a failure analysis system for human intervened analysis and refinement of a natural language model used by the natural language understand processor; assess, via a context manager processor, to determine a user interest in one or more portions of results of the query, a scrolling of the user through the results of the query; and refine, based on the user interest in the one or more portions of the results of the query, an output of the results of the query.

A system and method for training a text report identification machine learning model and an image identification machine learning model, including: initially training a text report machine learning model, using a labeled set of text reports including text pre-processing the text report and extracting features from the pre-processed text report, wherein the extracted features are input into the text report machine learning model; initially training an image machine learning model, using a labeled set of images; applying the initially trained text report machine learning model to a first set of unlabeled text reports with associated images to label the associated images; selecting a first portion of labeled associated images; re-training the image machine learning model using the selected first portion of labeled associated images; applying the initially trained image machine learning model to a first set of unlabeled images with associated text reports to label the associated text reports; selecting a first portion of labeled associated text reports; and re-training the text report machine learning model using the selected first portion of labeled associated text reports.

A system and method for training a text report identification machine learning model and an image identification machine learning model, including: initially training a text report machine learning model, using a labeled set of text reports including text pre-processing the text report and extracting features from the pre-processed text report, wherein the extracted features are input into the text report machine learning model; initially training an image machine learning model, using a labeled set of images; applying the initially trained text report machine learning model to a first set of unlabeled text reports with associated images to label the associated images; selecting a first portion of labeled associated images; re-training the image machine learning model using the selected first portion of labeled associated images; applying the initially trained image machine learning model to a first set of unlabeled images with associated text reports to label the associated text reports; selecting a first portion of labeled associated text reports; and re-training the text report machine learning model using the selected first portion of labeled associated text reports.

Systems, methods, devices, instructions, and other examples are described for natural language processing. One example includes accessing natural language processing general encoder data, where the encoder data is generated from a general-domain dataset that is not domain specific. A domain specific dataset is accessed and filtered encoder data using a subset of the encoder data is generated. The filtered encoder data is trained using the domain specific dataset to generate distilled encoder data, and tuning values for the distilled encoder data are generated to configure task outputs associated with the domain specific dataset.

Systems, methods, devices, instructions, and other examples are described for natural language processing. One example includes accessing natural language processing general encoder data, where the encoder data is generated from a general-domain dataset that is not domain specific. A domain specific dataset is accessed and filtered encoder data using a subset of the encoder data is generated. The filtered encoder data is trained using the domain specific dataset to generate distilled encoder data, and tuning values for the distilled encoder data are generated to configure task outputs associated with the domain specific dataset.