International Business Machines Corporation

Aya Soffer

David Carmel

Michael Herscovici

Ronny Lempel

Andrei Zary Broder

Jason Yeong Zien

Yariv Aridor

Einat Amitay

Yoelle Maarek-Smadja

Yoelle Smadja Maarek

Amit Fisher

Gabi Zodik

David Angelo Ferrucci

Eitan D Farchi

Wlodek Wlodzimierz Zadrozny

Ron Hoory

Doron Cohen

Yosi Mass

Tal Drory

Sima Nadler

Ronald Fagin

Aharon Satt

Arthur Charles Ciccolo

Adam Darlow

Yael Petruschka

David C Smith

Uri Weiss

Rani Nelken

Niblack Wayne

A method comprising: receiving an interactive voice response (IVR) tree configured to implement one or more tasks, each associated with one or more IVR node paths comprising a plurality of IVR nodes arranged in a hierarchical relationship; analyzing the IVR tree to identify one or more intent IVR nodes, each associated with one of the tasks; with respect to each of the intent IVR nodes, identifying a plurality of corresponding entity IVR nodes included within the IVR node path associated with the intent IVR node; assembling one or more task-specific chatbot skills, each comprising (i) one of the intent IVR nodes, and (ii) at least some of the plurality of corresponding entity IVR nodes, wherein each of the task-specific chatbot skills is configured to perform one of the tasks by conducting a dialog with a user; and generating a chatbot comprising at least one of the task-specific chatbot skills.

Automated chatbot generation from an interactive voice response tree

Device, system, and method of electronic communication to facilitate collaboration and meeting. For example, a method of inducing social interaction among users of an electronic communication network includes: receiving a first behavioral profile representing one or more schedule items of a first user; receiving a second behavioral profile representing one or more schedule items of a second user; identifying a time-slot in which the first and second users are available according to the first and second behavioral profiles, respectively, and identifying a common activity-of-interest reflected in the first and second behavioral profiles; and sending to the first and second users invitations to engage in said activity-of-interest in said time-slot.

Device, system, and method of electronic communication to facilitate collaboration and meeting

Disclosed is a system architecture, components and a searching technique for an Unstructured Information Management System (UIMS). The UIMS may be provided as middleware for the effective management and interchange of unstructured information over a wide array of information sources. The architecture generally includes a search engine, data storage, analysis engines containing pipelined document annotators and various adapters. The searching technique makes use of a two-level searching technique. A search query includes a search operator containing of a plurality of search sub-expressions each having an associated weight value. The search engine returns a document or documents having a weight value sum that exceeds a threshold weight value sum. The search operator is implemented as a Boolean predicate that functions as a Weighted AND (WAND).

System, method and computer program product for performing unstructured information management and automatic text analysis, including a search operator functioning as a Weighted AND (WAND)

Device, system, and method of project planning and management. For example, a method of project planning and management includes: publishing a representation of a project specification comprising one or more discrete objects; publishing a collaborative comment to one or more of the discrete objects; and receiving a supplier proposal to fulfill one or more of the discrete objects.

Device, system, and method of project planning and management

A method for searching a corpus of documents, such as the World Wide Web, includes defining a knowledge domain and identifying a set of reference documents in the corpus pertinent to the domain. Upon inputting a query, the corpus is searched using the set of reference documents to find one or more of the documents in the corpus that contain information in the domain relevant to the query. The set of reference documents is updated with the found documents that are most relevant to the domain. The updated set is used in searching the corpus for information in the domain relevant to subsequent queries.

Information search using knowledge agents

A method for gathering and recording temporal information for a linked entity, the method including identifying a link related activity within a linked source entity, and recording a time stamp in association with the link related activity.

Temporal link analysis of linked entities

A dynamic index may list physical items in the changing vicinity of a user or a generator of the index. The vicinity may be within the same space as the user or the generator, such as a store, a library, a shelf, an aisle, within a given radius, a street, a city, a campus, a building, an area and a park. The index may store information about the physical items near the user or generator, such as content found on tags associated with the physical items. The content might be a description of the physical items and their locations. The present invention also includes a system and method to generate such a dynamic index.

Personal index of items in physical proximity to a user

System, method and computer program product for performing unstructured information management and automatic text analysis, including a search operator functioning as a weighted and (WAND)

A method for searching a document collection includes providing an index of terms indicating the documents in which the terms appear. A first statistical distribution of each of at least some of the terms in the index and a second statistical distribution of each of at least some of the categories are estimated a over the documents in the collection. A query including one or more of the terms and a category restriction referring to at least one of the categories is accepted. A modified term distribution is produced by operating on the first statistical distribution of at least one of the terms in the query using the second statistical distribution, responsively to the category restriction. The query is applied to the index to return a response, in which occurrences of the at least one of the terms are scored responsively to the modified term distribution.

Term-statistics modification for category-based search

An apparatus and method is provided for pruning an index of a corpus of text documents by creating an inverted index of terms appearing in the documents, wherein the index includes postings of the terms in the documents, ranking the postings in the index, and pruning from the index the postings below a given level in the ranking.

Lossy index compression

A method for extracting information from a corpus of data includes specifying a topic and a query term associated with the topic, and defining adjunct terms which may occur in the corpus in a context of the query term, the adjunct terms comprising one or more off-topic terms. Occurrences of the query term are found in the corpus, the occurrences including at least one occurrence of the query term together with at least one of the off-topic terms in the context of the query term. The at least one occurrence of the query term is classified as non-relevant to the topic responsively to the occurrence of the at least one of the off-topic terms in the context of the query term.

Disambiguation of term occurrences

Disclosed is a system architecture, components and a searching technique for an Unstructured Information Management System (UIMS). The UIMS may be provided as middleware for the effective management and interchange of unstructured information over a wide array of information sources. The architecture generally includes a search engine, data storage, analysis engines containing pipelined document annotators and various adapters. The searching technique makes use of a two-level searching technique. Also disclosed is system, method and computer program product to process document data. The method includes inputting a document and operating at least one text analysis engine that comprises a plurality of coupled annotators for tokenizing document data for identifying and annotating a particular type of semantic content. Operating the at least one text analysis engine generates a plurality of views of a document, where each of the plurality of views are derived from a different tokenization of the document. The method further includes storing the plurality of views in a common data structure associated with the document.

System, method and computer program product for performing unstructured information management and automatic text analysis, and providing multiple document views derived from different document tokenizations

Growing community of inventors

Haifa, Israel

Aya Soffer