公开(公告)号：EP2812812A4

公开(公告)日：2015-02-25

申请号：EP13746495

申请日：2013-02-08

Applicant: IBM

Inventor： BOYLE PETER CURRIE ,  JAVAHERY HOMA ,  ROZSA ENIKO I

IPC: G06F17/27 ,  G06F17/30

CPC classification number: G06F17/20 ,  G06F17/2785 ,  G06F17/30654 ,  G06F17/30657 ,  G06F17/30684 ,  G06F17/30734

Abstract: A method, system, and computer program product for semantic attribution of a request. Source data statements for the request are received. A selection of a domain for the received source data statements is received. The received source data statements are semantically analyzed, which includes matching elements in the received source data statements to respective one or more entries in an ontology associated with the selected domain. The ontology includes items and relationships that define the selected domain. Each element in the received source data statements is a word or a phrase. The one or more entries are assigned to the matched elements, respectively, to annotate each matched element with a respective annotation consisting of the respective one or more entries. The annotated elements are saved with the respective annotations.

公开(公告)号：CA2572116A1

公开(公告)日：2008-06-27

申请号：CA2572116

申请日：2006-12-27

Applicant: IBM CANADA

Inventor： ZHANG YU ,  BOYLE PETER CURRIE

IPC: G06F17/27 ,  A61G99/00 ,  G06F16/41 ,  G06F16/45 ,  G06F16/483 ,  G06Q50/22 ,  G16H10/60 ,  H04L12/54 ,  H04L29/02

Abstract: There is disclosed a system and method for processing multi-modal collaboration. In an embodiment communication received from multiple modes are converted into a common format. Using various conversion modules, the communication may be converted into a common electronic text format (e.g. ASCII text) that contains keywords. Once the communication is converted into a common format, the information contained in the communication may be analyzed and consolidated into related areas or topics. The consolidated information may then be searched for common references in order to augment the information context.

公开(公告)号：DE112019001493T5

公开(公告)日：2021-01-07

申请号：DE112019001493

申请日：2019-02-12

Applicant: IBM

Inventor： TRIM CRAIG ,  BOYLE PETER CURRIE ,  HADDOCK BRENDA ,  WITTNEBERT MARIA ,  ROZSA ENIKO ,  GHAZI DIMAN ,  BASU ABHISHEK ,  VERGES FARRERO XAVIER

IPC: G06F16/35 ,  G06F17/18 ,  G06F40/35 ,  G06Q50/10

Abstract: Ein durch einen Computer implementiertes Verfahren umfasst: Erzeugen einer Stichprobe einer Abfrage durch eine Datenverarbeitungseinheit, wobei die Abfrage einer vorgegebenen Kategorisierung zugeordnet wird; Verarbeiten der Stichprobe mit einem ersten Prozess zum Verarbeiten natürlicher Sprache, wobei das Verarbeiten eine Ausgabe erzeugt, die eine Kategorisierung der Stichprobe aufweist; Speichern von Daten, die angeben, ob die Kategorisierung der Ausgabe mit der vorgegebenen Kategorisierung übereinstimmt; Erstellen eines Berichtes auf Grundlage der gespeicherten Daten, der einen Prozentsatz einer Mehrzahl von Stichproben der Abfrage angibt, deren Kategorisierungen mit der vorgegebenen Charakterisierung übereinstimmen; Ausgeben des Berichtes; und Empfangen eines zweiten Prozesses zum Verarbeiten natürlicher Sprache, der Aktualisierungen des ersten Prozesses zum Verarbeiten natürlicher Sprache auf Grundlage des Berichtes aufweist, wobei die Aktualisierungen den Prozentsatz der Mehrzahl von Stichproben, die mit der vorgegebenen Kategorisierung übereinstimmen, wenn sie mit dem zweiten Prozess zum Verarbeiten natürlicher Sprache verarbeitet werden, im Vergleich dazu erhöhen, wenn die Mehrzahl von Stichproben mit dem ersten Prozess zum Verarbeiten natürlicher Sprache verarbeitet wurde.

公开(公告)号：CA2616234A1

公开(公告)日：2009-06-21

申请号：CA2616234

申请日：2007-12-21

Applicant: IBM CANADA

Inventor： ZHANG YU ,  BOYLE PETER CURRIE

IPC: H04L12/16 ,  G06F17/27

Abstract: There is disclosed a method of facilitating interaction between users of an electronic community. In an embodiment, the method comprises: reviewing a user activity log for ea ch user in the electronic community; executing a natural language parser to extract significant noun phrases from the user activity log; updating user profiles from the newly extracted noun phrases, based on their usage frequency and importance value; and storing the updated profiles in a user profile and relationship data base; and executing a similarity based clustering algorithm to cluster user profiles, thereby discovering relationships among users and storing them in a user profile and relationship database. The method may further comprise displaying for each user the one or more relationships to which the user is assigned, together with a list of users assigned to the one or more relationships. The method may also comprise storing for each user th e relationship to which the user is assigned in a user profile and relationship database.

公开(公告)号：CA2691326A1

公开(公告)日：2011-07-28

申请号：CA2691326

申请日：2010-01-28

Applicant: IBM CANADA

Inventor： BOYLE PETER CURRIE ,  ZHANG YU

IPC: G06F17/30 ,  G06F17/27

Abstract: A method of integrated automatic support and assistance includes identifying a user and retrieving models representing a computer system, receiving a query from the user, determining if the received query is a machine translatable query, restructuring machine translatable terms of the received query into semantic components based upon the retrieved models, determining a set of candidate knowledge bases both related to the semantic components, submitting the machine translatable query to each knowledge base of the set of candidate knowledge bases, receiving a set of responses from each knowledge base of the set of knowledge bases in response to the submitting, formatting the set of responses, submitting the formatted set of responses to the user, determining if a response of the submitted formatted set of responses is accepted by the user, applying updated weights within the formatted set of responses, and storing the updated weights for future queries.

公开(公告)号：CA2554951A1

公开(公告)日：2008-02-01

申请号：CA2554951

申请日：2006-08-01

Applicant: IBM CANADA

Inventor： ZHANG YU ,  BOYLE PETER CURRIE

IPC: G06F16/906 ,  G06F16/35 ,  G06F17/27

Abstract: There is disclosed a system and method for clustering data objects. In an aspect, a system for clustering data objects comprises means for calculating an importance value of at least one member in a first data object represented as a variable length vector of 0 to N members; and a clustering module for dynamically forming a plurality of clusters containing one or more data objects, the clustering module configured to associate the first data object with at least one of the plurality of clusters in dependence upo n the at least one member's similarity value in comparison to members in other data objects. Th e clustering module may be configured to cluster the first data object into a plurality o f clusters if it has at least two members and each member belongs to a different cluster.