Abstract: A method and system for recommending articles including: receiving a customer request from the customer during the session; generating case data for a case, by an article recommender app; configuring a training set based on the subject and description data of the customer request; identifying, by an artificial intelligence (AI) app, a first pool of articles from a knowledge database; identifying by at least one query, a second pool of articles from a case article database to into a merged pool of articles; assigning, by the AI app, an implicit label to one of the first pool and the second pool of the articles; applying a model derived by the AI app based on customer behavior and a set of features related to the case to classify each article of the merged pool of articles based at least in part on the predicted relevance of the article.

Abstract: Methods, systems, and devices for processing and answering a natural language query at a database server are described. An end user may submit a question in natural language over a communication platform. An answer engine running on the database server may receive the question, and may process the content of the question using natural language processing (NLP) techniques. The answer engine may construct a search query based on the NLP, and may retrieve a set of documents from a database using the search query. The answer engine may rank the documents, prune the number of documents, modify the documents for the given communication platform, or perform any combination of these functions. In some cases, an intermediate user may review the documents, and may select one or more documents for publication. The answer engine may send the selected documents to the end user as answers in response to the question.

Abstract: A method is provided for providing a final result set to a user. In some embodiments, the method includes receiving from the user an input question directed to an organization belonging to a particular category. The method includes applying a plurality of rules to the input question, at least one rule being assigned a weight dependent on the particular category to which the organization belongs. The method further includes extracting, based on applying the plurality of rules, multiple collections of keywords and generating a plurality of search queries. Each search query includes a different collection of keywords. The method also includes submitting the plurality of search queries to a database and in response, receiving multiple result sets from the database. The method further includes in response to the input question, providing a final result including a subset of documents included in the multiple result sets to the user.

Abstract: Disclosed embodiments are related to feature hashing techniques. A processing device of a database system may identify a set of machine learning features; generate a first hash map of said set of machine learning features and a second different hash map of said set of machine learning features. The processing device may generate a memory compact model for an online machine learning system using the first and second hash maps, and store the memory compact model in the memory device.

Abstract: A method and system for recommending articles including: receiving a customer request from the customer during the session; generating case data for a case, by an article recommender app; configuring a training set based on the subject and description data of the customer request; identifying, by an artificial intelligence (AI) app, a first pool of articles from a knowledge database; identifying by at least one query, a second pool of articles from a case article database to into a merged pool of articles; assigning, by the AI app, an implicit label to one of the first pool and the second pool of the articles; applying a model derived by the AI app based on customer behavior and a set of features related to the case to classify each article of the merged pool of articles based at least in part on the predicted relevance of the article.

Abstract: A method is provided for providing a final result set to a user. In some embodiments, the method includes receiving from the user an input question directed to an organization belonging to a particular category. The method includes applying a plurality of rules to the input question, at least one rule being assigned a weight dependent on the particular category to which the organization belongs. The method further includes extracting, based on applying the plurality of rules, multiple collections of keywords and generating a plurality of search queries. Each search query includes a different collection of keywords. The method also includes submitting the plurality of search queries to a database and in response, receiving multiple result sets from the database. The method further includes in response to the input question, providing a final result including a subset of documents included in the multiple result sets to the user.

Abstract: Methods, systems, and devices for processing and answering a natural language query at a database server are described. An end user may submit a question in natural language over a communication platform. An answer engine running on the database server may receive the question, and may process the content of the question using natural language processing (NLP) techniques. The answer engine may construct a search query based on the NLP, and may retrieve a set of documents from a database using the search query. The answer engine may rank the documents, prune the number of documents, modify the documents for the given communication platform, or perform any combination of these functions. In some cases, an intermediate user may review the documents, and may select one or more documents for publication. The answer engine may send the selected documents to the end user as answers in response to the question.

Abstract: In an example, a processing device of a database system may identify a set of machine learning features; generate a first hash map of said set of machine learning features and a second different hash map of said set of machine learning features. The processing device may generate a memory compact model for an online machine learning system using the first and second hash maps, and store the memory compact model in the memory device.

Abstract: Techniques for forming, designing, generating or building up recognizers using recursive qualifications are described, where the recognizers can be used in any devices or systems with recognition capabilities, such as robotic vision systems, motion detections, artificial intelligence and driverless vehicles. Through respective and recursive observations on a set of actual data, recognizers are generated to reduce the inconsistencies among the observations to produce better recognition accuracies.