Web [1] [2] [3] [4] [5] SupportVectorMachine SVM [6] [7] Google [11] Web

Similar documents
DEIM Forum 2009 E

SERPWatcher SERPWatcher SERP Watcher SERP Watcher,

1., 1 COOKPAD 2, Web.,,,,,,.,, [1]., 5.,, [2].,,.,.,, 5, [3].,,,.,, [4], 33,.,,.,,.. 2.,, 3.., 4., 5., ,. 1.,,., 2.,. 1,,

TF-IDF TDF-IDF TDF-IDF Extracting Impression of Sightseeing Spots from Blogs for Supporting Selection of Spots to Visit in Travel Sat

DEIM Forum 2010 A Web Abstract Classification Method for Revie

1 Web [2] Web [3] [4] [5], [6] [7] [8] S.W. [9] 3. MeetingShelf Web MeetingShelf MeetingShelf (1) (2) (3) (4) (5) Web MeetingShelf

IT,, i

2reN-A14.dvi

, IT.,.,..,.. i

Web Web Web Web Web, i

FA

IPSJ SIG Technical Report Vol.2016-CE-137 No /12/ e β /α α β β / α A judgment method of difficulty of task for a learner using simple

untitled

Web Web [4] Web Web [5] Web 2 Web 3 4 Web Web 2.1 Web Web Web Web Web 2.2 Web Web Web *1 Web * 2*3 Web 3. [6] [7] [8] 4. Web 4.1 Web Web *1 Ama

07_伊藤由香_様.indd

Japanese Journal of Family Sociology, 29(1): (2017)

,,,,., C Java,,.,,.,., ,,.,, i

〈論文〉英語学習辞書における二重母音と三重母音の発音表記の異同

知能と情報, Vol.30, No.5, pp


[2] , [3] 2. 2 [4] 2. 3 BABOK BABOK(Business Analysis Body of Knowledge) BABOK IIBA(International Institute of Business Analysis) BABOK 7

DEIM Forum 2010 A3-3 Web Web Web Web Web. Web Abstract Web-page R


untitled

16_.....E...._.I.v2006


THE INSTITUTE OF ELECTRONICS, INFORMATION AND COMMUNICATION ENGINEERS TECHNICAL REPORT OF IEICE.

untitled

IPSJ SIG Technical Report 3,a),b),,c) Web Web Web Patrash Patrash Patrash Design and Implementation of 3D interface for Patrash: Personalized Autonomo

23 The Study of support narrowing down goods on electronic commerce sites


24 Region-Based Image Retrieval using Fuzzy Clustering

日本看護管理学会誌15-2

soturon.dvi


九州大学学術情報リポジトリ Kyushu University Institutional Repository 看護師の勤務体制による睡眠実態についての調査 岩下, 智香九州大学医学部保健学科看護学専攻 出版情報 : 九州大学医学部保健学

DOUSHISYA-sports_R12339(高解像度).pdf

TEM


Web Basic Web SAS-2 Web SAS-2 i

1 1 tf-idf tf-idf i

Microsoft Word - ??? ????????? ????? 2013.docx

(II) tikeya[at]shoin.ac.jp ayakutsuki[at]shoin.ac.jp Study of katakana for English Speakers Learning Japanese (II) IKEYA Tomoko KUTSUKI Aya Faculty of

1 Fig. 1 Extraction of motion,.,,, 4,,, 3., 1, 2. 2.,. CHLAC,. 2.1,. (256 ).,., CHLAC. CHLAC, HLAC. 2.3 (HLAC ) r,.,. HLAC. N. 2 HLAC Fig. 2

評論・社会科学 84号(よこ)(P)/3.金子

IPSJ SIG Technical Report Vol.2011-EC-19 No /3/ ,.,., Peg-Scope Viewer,,.,,,,. Utilization of Watching Logs for Support of Multi-

{.w._.p7_.....\.. (Page 6)


1 4 4 [3] SNS 5 SNS , ,000 [2] c 2013 Information Processing Society of Japan

FA FA FA FA FA 5 FA FA 9

tikeya[at]shoin.ac.jp The Function of Quotation Form -tte as Sentence-final Particle Tomoko IKEYA Kobe Shoin Women s University Institute of Linguisti

1 Web Web 1,,,, Web, Web : - i -


2


クレジットカードの利用に関する一考察―JGSS-2005の分析から―

第62巻 第1号 平成24年4月/石こうを用いた木材ペレット

大学における原価計算教育の現状と課題

28 Theoretical and Applied Linguistics at Kobe Shoin 2014 No. 17 objects, (3) to choose KATAKANA word, if they are unsure of selecting, (4) to develop

’ÓŠ¹/‰´„û

対朝鮮人絹織物移出と繊維専門商社の生産過程への進出

卒業論文2.dvi


2 ( ) i

J No J. J

,,.,.,,.,.,.,.,,.,..,,,, i

DEIM Forum 2009 B4-6, Str

udc-2.dvi

1: A/B/C/D Fig. 1 Modeling Based on Difference in Agitation Method artisoc[7] A D 2017 Information Processing

58 10

PC PDA SMTP/POP3 1 POP3 SMTP MUA MUA MUA i

01ⅢⅣⅤⅥⅦⅧⅨⅩ一二三四五六七八九零壱弐02ⅢⅣⅤⅥⅦⅧⅨⅩ一二三四五六七八九零壱弐03ⅢⅣⅤⅥⅦⅧⅨⅩ一二三四五六七八九零壱弐04ⅢⅣⅤⅥⅦⅧⅨⅩ一二三四五六七八九零壱弐05ⅢⅣⅤⅥⅦⅧⅨⅩ一二三四五六七八九零壱弐06ⅢⅣⅤⅥⅦⅧⅨⅩ一二三四五六

The Journal of the Japan Academy of Nursing Administration and Policies Vol 7, No 2, pp 19 _ 30, 2004 Survey on Counseling Services Performed by Nursi

DEIM Forum 2010 D Development of a La

06_仲野恵美.indd

Microsoft Word - toyoshima-deim2011.doc


Journal of Geography 116 (6) Configuration of Rapid Digital Mapping System Using Tablet PC and its Application to Obtaining Ground Truth

When creating an interactive case scenario of a problem that may occur in the educational field, it becomes especially difficult to assume a clear obj

29 jjencode JavaScript

IPSJ SIG Technical Report Vol.2011-MUS-91 No /7/ , 3 1 Design and Implementation on a System for Learning Songs by Presenting Musical St

先端社会研究 ★5★号/4.山崎


WikiWeb Wiki Web Wiki 2. Wiki 1 STAR WARS [3] Wiki Wiki Wiki 2 3 Wiki 5W1H Wiki Web 2.2 5W1H 5W1H 5W1H 5W1H 5W1H 5W1H 5W1H 2.3 Wiki 2015 Informa

IPSJ SIG Technical Report Vol.2012-CG-148 No /8/29 3DCG 1,a) On rigid body animation taking into account the 3D computer graphics came

IPSJ SIG Technical Report Vol.2014-IOT-27 No.14 Vol.2014-SPT-11 No /10/10 1,a) 2 zabbix Consideration of a system to support understanding of f

52-2.indb

Vol. 5, 29 39, 2016 Good/Virtue actions for competitive sports athlete Actions and Choices that receive praise Yo Sato Abstract: This paper focuses on

SPSS



Perspective-Taking Perspective-Taking.... Vol. No.

22 Google Trends Estimation of Stock Dealing Timing using Google Trends

Q [4] 2. [3] [5] ϵ- Q Q CO CO [4] Q Q [1] i = X ln n i + C (1) n i i n n i i i n i = n X i i C exploration exploitation [4] Q Q Q ϵ 1 ϵ 3. [3] [5] [4]

Bull. of Nippon Sport Sci. Univ. 47 (1) Devising musical expression in teaching methods for elementary music An attempt at shared teaching

DEIM Forum 2009 C8-4 QA NTT QA QA QA 2 QA Abstract Questions Recomme

Web Stamps 96 KJ Stamps Web Vol 8, No 1, 2004

9(2007).ren

07_太田美帆.indd

21 A contents organization method for information sharing systems

Transcription:

DEIM Forum 2009 E5-6 112-8610 2-1-1 112-8610 2-1-1 E-mail: {asami y,koba}@koba.is.ocha.ac.jp Web AJINOMOTO Easy Cooking Recipe Recommendation Considering User s Conditions Asami YAJIMA and Ichiro KOBAYASHI Dept. of Information Science, Faculty of Sciences, Ochanomizu University 2-1-1 Ohtsuka, Bunkyo-ku, Tokyo 112-8610 Japan Graduate School of Humanities and Sciences, Advanced Sciences, Ochanomizu University 2-1-1 Ohtsuka, Bunkyo-ku, Tokyo 112-8610 Japan E-mail: {asami y,koba}@koba.is.ocha.ac.jp Abstract It is natural to think that couples who work at a company or a person who lives by her/himself want to cook food for themselves as quickly and easily as possible when they are busy. However, to keep having the same food they can easily cook fed them up, therefore, it should be preferable for them to be recommended a variety of food that they can cook easily. Currently, there are so many Web sites for cooking recipes, and there are also recipes regarded as easy to cook on the sites. However, those recipes are not estimated as easy by taking user s conditions into account. The meaning of the word, easy, would be differently interpreted by each user s conditions. Therefore, in this study, we aim to propose a method to recommend easy cooking recipes by considering user s conditions and then develop a recommendation system with the proposed method. Concretely, we collect approximately 10,000 recipes from AJINOMOTO Web recipe site; analyze the kinds of seasonings, ingredients, and cooking methods; and then make a ranking data set which expresses the difficulty for cooking. We develop a system that recommends easy cooking recipes based on the recommendation knowledge made by considering user s conditions. Key words Recipe Recommendation Personalization Browsing Log information Retrieval 1.

Web 3. 3. 1 1 2. [1] [2] [3] [4] [5] SupportVectorMachine SVM [6] [7] 1 3. 2 3. 2. 1 Google [11] 2 3. 2. 2 Web

MySQL AJINOMOTO 2 [8] AJI- NOMOTO [9] 1 1 / AJINOMOTO AJINOMOTO 400 000 10 000 AJINOMOTO AJINOMOTO AJINOMOTO 3. 2. 3 AJINOMOTO 3. 2. 4 3. 2. 1 3. 2. 1 3 T P T youmiryoup oint T P T P T T T youmiryout imes T T T P l x T P T P x = 1 T T x a = 1 l (1) max(t T a (1) T P [0 1] SP SyokuzaiP oint SP SP T P ST SyokuzaiT imes SP m y SP SP y = 1 ST y b = 1 m (2) max(st b V P V erbp oint ChaSen [10] V P

V P 2 V P 1 V P 0 (3) 0 V P z = 1 (3) 2 (1) (2) (3) T P SP V P RP RP RecipeP oint RP T P T T P T youmiryout otalp oint SP ST P SyokuzaiT otalp oint V P V T P V erbt otalp oint t s v RP (3. 2. 4) t s v k RP RP k = T T P k max(t T P a + ST P k max(st P b + a = 1 l ; b = 1 m ; c = 1 n) V T P k max(v T P c (4) RP 3 0 10 2 2 10 1 0.136919 2 0.153786 3 0.180568 4 0.192196 5 0.197519 6 0.202532 7 0.209853 8 0.213084 9 0.213605 10 0.219243 4. 4. 1 AJINOMOTO AJINOMOTO AJINOMOTO AJINOMOTO AJINOMOTO 1 AJINOMOTO AJINOMOTO AJINOMOTO 4. 2 A B 4. 3 3 4. 3. 1 2 ( 3 ) 3 A B C D 2 3. 2. 5 0 UT P UserT otalp oint 0 3

4. 3. 2 [ ( )] [ ] 4 [2 ] 4 4 4 [ ] [ ] 4. 4 AJINOMOTO AJINOMOTO web AJINOMOTO Step.1 6 ( ) Step.3 Step.6 4 4. 3. 3 ( 5 ) 6 Step.2 5 7 Step.3 Step.1 4. 3 3 Step.2

以上が本システムにおける推薦の例である 以下は システ ムをユーザにとってより使いやすいものにするために行う操作 である Step.4 ユーザによるレシピ閲覧 ユーザは出力された候補の中からレシピ A を選択すると AJINOMOTO サイトへジャンプし ユーザはそのレシピ A の Web ページを閲覧することができる 図 10 参照 図7 ユーザによる初期クエリの入力 から得たクエリを追加する また レシピの順番は RP の か んたん 順とし U T P 1 買い足す調味料が少ないことを意 味する のレシピのみを出力する 3. 2. 5 参照 さらに デ フォルトでは調理時間は 60 分以下 主食材にユーザが頻繁に 図 10 使用する食材上位 30 品目のどれかが含まれるレシピを出力す 画像を選択 閲覧 る 図 8 9 参照 この際 推薦のために使用した知識に基づ このとき システムはレシピ A についての閲覧履歴を得る く推薦理由も出力する 同じように レシピ B を選択するとユーザはレシピ B のペー ジを閲覧でき システムはその閲覧履歴を得る ここで取得し た閲覧履歴は Step.6 で使用される Step.5 ユーザによるレシピ選択 調理 評価 ユーザがレシピ A を調理することに決め 調理したと仮定す る レシピ A が AJINOMOTO レシピの場合 ユーザはレシ ピ A について 簡単 普通 難しい の 3 段階の評価を行う 図 11 参照 図 8 出力イメージ 図 11 評 価 画 面 また システムはレシピ A を AJINOMOTO レシピ集合 から ユーザレシピ集合 へと移動させ ユーザの調理レパー トリを増やす 一方 レシピ A がユーザレシピの場合 ユーザ は評価をする必要はなく またシステム側の作業も発生しない Step.6 ユーザによる食歴追加 ユーザはレシピ A について食歴をつける 図 12 参照 ここでシステムは Step.1 で取得した検索時の状況の情報と Step.4 で取得した閲覧履歴から ユーザがどのような状況のと きにどのような特徴のレシピを選択する といった 4. 3. 2 で述 べた知識を生成する ここで生成された知識は 次回以降の検 図9 推薦理由 索において Step.3 の検索条件を追加するときに活用される

12 5. AJINOMOTO MySQL Ruby on Rails Web [1] vol.20 No.3 pp.337-346 2008. [2] http://orchid.ics.nara-wu.ac.jp/ppt/2001/takada ppt.pdf [3] vol.48 No.9 pp.957-965 2007. [4] Context-Aware vol.48 No.SIG11 TOD34 pp.162-176 2007. [5] vol.49 No.1 pp.130-140 2008. [6] Letters vol.6 No.4 pp.29-32 2008. [7] 2006. [8] http://cookpad.com/ [9] http://www.ajinomoto.co.jp/recipe/ [10] http://chasen.naist.jp/hiki/chasen/ [11] Google http://www.google.com/intl/ja/googlecalendar/tour.html 6.