System and method for adaptive text recommendation

摘要

Network system provides a real-time adaptive recommendation set of documents with a high statistical measure of relevancy to the requestor device. The recommendation set is optimized based on analyzing text of documents of the interest set, categorizing these documents into clusters, extracting keywords representing the themes or concepts of documents in the clusters, and filtering a population of eligible documents accessible to the system utilizing site and or Internet-wide search engines. The system is either automatically or manually invoked and it develops and presents the recommendation set in real-time. The recommendation set may be presented as a greeting, notification, alert, HTML fragment, fax, voicemail, or automatic classification or routing of customer e-mail, personal e-mail, job postings, and offers for sale or exchange.

主权项

1. A method for adaptive information recommendation, the method comprising:
storing user-specific information in memory, the user-specific information concerning interactions with a plurality of documents; and executing instructions stored in memory, wherein execution of the instructions by a processor:
assembles an interest set of documents corresponding to the user-specific information concerning interactions with the plurality of documents, wherein the interactions include a previous view of a document by the user,groups the documents in the interest set into a plurality of clusters based on a level of similarity between words in the documents,determines a keyword for a cluster of the one or more clusters, the keyword identified based on a plurality of terms identified via natural language understanding and representing the theme of the documents in the cluster, wherein the keyword is not one of the terms identified via natural language understanding,determines a set of eligible documents within the cluster, each identified document including either the keyword representing the theme of the documents or a portion of the terms identified via natural language understanding,constructs from the eligible documents a recommended set of documents for the cluster based on a relevance score of each document in the cluster, wherein the relevance score is based on:
the frequency that the keyword or the portion of the terms identified via natural language understanding appears in each document in the set of eligible documents, anda user-defined limit on document age, andprovides the recommended set of documents.