WO2006093593A1 - Appareil et methode pour generer un resume de contenu personnalise - Google Patents

Appareil et methode pour generer un resume de contenu personnalise Download PDF

Info

Publication number
WO2006093593A1
WO2006093593A1 PCT/US2006/002515 US2006002515W WO2006093593A1 WO 2006093593 A1 WO2006093593 A1 WO 2006093593A1 US 2006002515 W US2006002515 W US 2006002515W WO 2006093593 A1 WO2006093593 A1 WO 2006093593A1
Authority
WO
WIPO (PCT)
Prior art keywords
content
events
event
training
response
Prior art date
Application number
PCT/US2006/002515
Other languages
English (en)
Inventor
Paola Hobson
Michael Brady
Catherine Mary Dolbean
Original Assignee
Motorola, Inc.
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Motorola, Inc. filed Critical Motorola, Inc.
Publication of WO2006093593A1 publication Critical patent/WO2006093593A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/40—Information retrieval; Database structures therefor; File system structures therefor of multimedia data, e.g. slideshows comprising image and additional audio data
    • G06F16/43—Querying
    • G06F16/435—Filtering based on additional data, e.g. user or group profiles
    • G06F16/437—Administration of user profiles, e.g. generation, initialisation, adaptation, distribution

Definitions

  • the approach is particularly suitable for personalisation of the content summaries by biasing of the training data.
  • the rating means is arranged to determine ratings by applying a Markov chain to event subsets of the event groups. This may e.g. allow a low complexity implementation while achieving accurate performance.
  • a content item is provided from a content item source 101.
  • the content item source 101 may be an internal or external content source.
  • the content item is an audiovisual sequence.
  • the content of the audiovisual sequence comprises a number of events which are identified in event information.
  • the event information may be provided integrally with the content item or may be provided separately.
  • the event information may be provided as embedded metadata in the audio visual sequence or may be provided as a separate file comprising event data.
  • the rating processor 103 determines the rating for each event group in response to the frequency indication for the event group and may specifically determine an increasing rating for an increasing frequency value.
  • the frequency (or probability) value may be used directly as a rating.
  • the training data selection processor 107 may select the content items of the first group from e.g. an external set of content items and the training data storage 105 may only store data for the first group.
  • the training data storage 105 may alternatively or additionally comprise data for other content items and the training data selection processor 107 may select the first group as the subset of these content items which are to be used by the rating processor 103.
  • the training data storage 105 may comprise a large set of content items and the training data selection processor 107 may select a subset of these to be used by the rating processor 103 when rating the summaries.
  • i is an index of the user profile properties
  • N is the number of properties in the user profile
  • wj is a weighting for each property.
  • a Markov chain is constructed beginning with the first event in the test sequence E 1 , with subsequent events E 2 ... E t , to calculate the joint probability of a number of events E t ... E 2 , E 1 :
  • the rating processor 103 evaluates the frequency at which the training content items of the first group comprise the same event class sequences as the current event group and the frequency at which these event sequences are reflected in the training content summaries.
  • a frequency (or probability) indication for the event group may be determined as the ratio between these.
  • the frequency or probability value may directly be used as a rating value.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

L'invention concerne un appareil (100) pour générer un résumé de contenu personnalisé pour un article de contenu comprenant une pluralité d'événements. L'appareil comprend un processeur d'évaluation (103) qui détermine une évaluation des événements de l'article de contenu, en réaction à des associations entre des événements et des résumés de contenu, pour un premier groupe d'articles de contenu d'entraînement. Les articles de contenu d'entraînement appartenant au premier groupe sont sélectionnés par un processeur de sélection de données d'entraînement (107), en réaction à un profil de préférences d'utilisateur (109). En particulier, les articles de contenu correspondant aux préférences de l'utilisateur sont sélectionnés pour le premier groupe. Un processeur de sélection (111) sélectionne des événements à inclure dans le résumé de contenu, en réaction à l'évaluation des événements, et un générateur de résumé (113) génère le résumé personnalisé, en incluant des articles de résumé associés aux événements sélectionnés. L'invention permet ainsi une personnalisation améliorée en orientant les données d'entraînement par rapport aux préférences d'utilisateur.
PCT/US2006/002515 2005-02-21 2006-01-19 Appareil et methode pour generer un resume de contenu personnalise WO2006093593A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
GB0503503.5 2005-02-21
GB0503503A GB2423383A (en) 2005-02-21 2005-02-21 Method for generating a personalised content summary

Publications (1)

Publication Number Publication Date
WO2006093593A1 true WO2006093593A1 (fr) 2006-09-08

Family

ID=34401020

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US2006/002515 WO2006093593A1 (fr) 2005-02-21 2006-01-19 Appareil et methode pour generer un resume de contenu personnalise

Country Status (2)

Country Link
GB (1) GB2423383A (fr)
WO (1) WO2006093593A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140081991A1 (en) * 2006-12-15 2014-03-20 Jeffrey Aaron Automatic Rating Optimization

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2009001278A1 (fr) * 2007-06-28 2008-12-31 Koninklijke Philips Electronics N.V. Système et procédé pour générer un résumé à partir d'une pluralité d'éléments multimédia

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010013009A1 (en) * 1997-05-20 2001-08-09 Daniel R. Greening System and method for computer-based marketing
US20020055936A1 (en) * 2000-08-21 2002-05-09 Kent Ridge Digital Labs Knowledge discovery system
US20040172267A1 (en) * 2002-08-19 2004-09-02 Jayendu Patel Statistical personalized recommendation system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010013009A1 (en) * 1997-05-20 2001-08-09 Daniel R. Greening System and method for computer-based marketing
US20020055936A1 (en) * 2000-08-21 2002-05-09 Kent Ridge Digital Labs Knowledge discovery system
US20040172267A1 (en) * 2002-08-19 2004-09-02 Jayendu Patel Statistical personalized recommendation system

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140081991A1 (en) * 2006-12-15 2014-03-20 Jeffrey Aaron Automatic Rating Optimization
US9456250B2 (en) * 2006-12-15 2016-09-27 At&T Intellectual Property I, L.P. Automatic rating optimization
US10028000B2 (en) 2006-12-15 2018-07-17 At&T Intellectual Property I, L.P. Automatic rating optimization

Also Published As

Publication number Publication date
GB0503503D0 (en) 2005-03-30
GB2423383A (en) 2006-08-23

Similar Documents

Publication Publication Date Title
CN109033229B (zh) 问答处理方法和装置
US11197036B2 (en) Multimedia stream analysis and retrieval
Wu et al. Personalized next-song recommendation in online karaokes
US9087297B1 (en) Accurate video concept recognition via classifier combination
CN110737783B (zh) 一种推荐多媒体内容的方法、装置及计算设备
CN106709040B (zh) 一种应用搜索方法和服务器
CN112533051B (zh) 弹幕信息显示方法、装置、计算机设备和存储介质
Wei et al. Multimodal fusion for video search reranking
US9165255B1 (en) Automatic sequencing of video playlists based on mood classification of each video and video cluster transitions
WO2017070656A1 (fr) Système de récupération de contenu vidéo
Yang et al. Multi-modality web video categorization
CN101122909A (zh) 文本信息检索装置以及文本信息检索方法
US20150213361A1 (en) Predicting interesting things and concepts in content
US20130325864A1 (en) Systems and methods for building a universal multimedia learner
JP2011175362A (ja) 情報処理装置、重要度算出方法及びプログラム
Vall et al. Order, context and popularity bias in next-song recommendations
Santos Explicit web search result diversification
Ping et al. Video highlights detection and summarization with lag-calibration based on concept-emotion mapping of crowd-sourced time-sync comments
Messina et al. A generalised cross-modal clustering method applied to multimedia news semantic indexing and retrieval
Rudinac et al. Leveraging visual concepts and query performance prediction for semantic-theme-based video retrieval
WO2006093593A1 (fr) Appareil et methode pour generer un resume de contenu personnalise
Browne et al. Dublin City University video track experiments for TREC 2003
KR101563625B1 (ko) 온톨로지 기반 메타 데이터 간 연관성을 이용한 영상 콘텐츠 추천 시스템 및 방법
Doğan et al. A flexible and scalable audio information retrieval system for mixed‐type audio signals
Zhang et al. Personalized retrieval of sports video based on multi-modal analysis and user preference acquisition

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application
NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 06748172

Country of ref document: EP

Kind code of ref document: A1