Slide 1

Slide 1 text

Patents that Support Yahoo! JAPAN Shopping’s Ranking Ayane Konno / Yahoo! JAPAN Ryu Inagaki / Yahoo! JAPAN

Slide 2

Slide 2 text

No content

Slide 3

Slide 3 text

No content

Slide 4

Slide 4 text

Agenda - Introduction - Background - Patents - Results

Slide 5

Slide 5 text

Agenda - Introduction - Background - Patents - Results

Slide 6

Slide 6 text

- Online shopping service - Wide variety of stores & items - “PayPay” can be used What is Yahoo! Shopping?

Slide 7

Slide 7 text

- Ranking is determined based on order, review, and stuff like that. - Provide information to aid the user's buying experience What is “Ranking”?

Slide 8

Slide 8 text

Number of patents applications in the commerce field by Z Holdings Source:https://www.z-holdings.co.jp/sustainability/stakeholder/18/

Slide 9

Slide 9 text

Agenda - Introduction - Background - Patents - Results

Slide 10

Slide 10 text

- Anyway, only the lowest priced ones come out on top. Problem that the ranking faced - Whenever I look at them, I always see the same products. Not a ranking I'd want to see over and over again!

Slide 11

Slide 11 text

Changed the feature used for ranking Logic Coefficient Feature Approaches to Problem Solving Change the logic used to generate rankings Tuning coefficients Perfect Ranking

Slide 12

Slide 12 text

The result was a failure vs Likes good deal items & Follows trends Likes high quality and long-selling items User A User B

Slide 13

Slide 13 text

There is no such what the perfect ranking.

Slide 14

Slide 14 text

Change of Policy

Slide 15

Slide 15 text

Policy Conversion-rate supremacy Change the decision making process to look at multiple indicators. before after Creating the "Perfect Ranking Logic" Search for "Optimal UI/UX with Ranking"

Slide 16

Slide 16 text

Policy Conversion-rate supremacy Change the decision making process to look at multiple indicators. Creating the "Perfect Ranking Logic" Search for "Optimal UI/UX with Ranking" before after

Slide 17

Slide 17 text

Policy Conversion-rate supremacy Change the decision making process to look at multiple indicators. Creating the "Perfect Ranking Logic" Search for "Optimal UI/UX with Ranking" before after

Slide 18

Slide 18 text

Ranking has undergone a transformation.

Slide 19

Slide 19 text

Agenda - Introduction - Background - Patents - Results

Slide 20

Slide 20 text

We will now present 6 patents. Boost Section Proactive Aggregation Format Fusion

Slide 21

Slide 21 text

『 Fusion 』 〜 How to send customers to the ranking ? 〜

Slide 22

Slide 22 text

検索クエリに対応する検索結果を配置した第1タブと、前記検索クエリに対応する取引対象のランキングを配置し た第2タブとを含むコンテンツを提供する提供部を備えることを特徴とする情報処理装置。 Main Claim

Slide 23

Slide 23 text

1. When you perform a search on an e-commerce site or auction site The patent essentials 2. Provide search results and rankings with tab

Slide 24

Slide 24 text

The ranking were once isolated Search Item Cart Ranking Main Purchasing Site Flow Category Ranking Brand Ranking Top Ranking Yahoo! Shopping TOP Page Other Flow

Slide 25

Slide 25 text

Sample Image

Slide 26

Slide 26 text

A new search experience with the ranking

Slide 27

Slide 27 text

『 Section 』 〜 How to organize the information 〜

Slide 28

Slide 28 text

取引対象に対応する複数の切り口のうち、検索クエリとの関連が所定の条件を満たす切り口である関連切り 口を決定する決定部と、前記決定部により決定された前記関連切り口と前記検索クエリとに基づく前記取引 対象のランキングを示すコンテンツを提供する提供部と、を備えることを特徴とする情報処理装置。 Main Claim

Slide 29

Slide 29 text

1. Read the intent of the search terms retrieved by the user The patent essentials 3. Provide a flexible combination of constructed section 2. Construct various section depending on the intent

Slide 30

Slide 30 text

Some users are not clear about what they want Gift for my friend Washing machine

Slide 31

Slide 31 text

Organize so that you have a clear idea of what you want Ambiguous categories Ranking classified by category Ranking classified by price range Ranking classified by brand Ambiguous brands Ambiguous price range

Slide 32

Slide 32 text

When searching for “ふるさと納税” * Category Section (e.g. Steak, Meats, Sweets, Fruits …) Price range Section * hometown tax payment (e.g. ~10000yen, 10001~15000yen … )

Slide 33

Slide 33 text

When searching for “Lenovo pc” Top Ranking of Category × Brand

Slide 34

Slide 34 text

Spec Section (e.g. OS Type, CPU Type … )

Slide 35

Slide 35 text

“Want it!" can be found

Slide 36

Slide 36 text

『 Format 』 〜 The best way to show it〜

Slide 37

Slide 37 text

検索クエリを受け付ける受付部と、前記受付部によって受け付けられた前記検索クエリの意図を推定する推 定部と、前記推定部によって推定された前記検索クエリの意図に基づいて、ランキング情報の表示形式を決 定する決定部と、前記決定部によって決定された表示形式のランキング情報を提供する提供部と、を備える ことを特徴とする情報処理装置。 Main Claim

Slide 38

Slide 38 text

1. Intent is inferred according to the search query The patent essentials 3. The details of the "format" are free 2. Display a different form of ranking depending on the judged intent

Slide 39

Slide 39 text

What information will help you decide what to buy?

Slide 40

Slide 40 text

Item Name Image Price Point Review Spec Store Name Review Excellent Store Badge Gift wrap option Delivery Postage Delivery date Shipment date Arrange a scheduled Wide variety of information What Konno focus on What Inagaki focus on

Slide 41

Slide 41 text

Search Keyword that cannot imagine specific items

Slide 42

Slide 42 text

Display format branching by search keyword Search keyword or Interpret the intent of search keyword Ranking System List Grid

Slide 43

Slide 43 text

- Pros. Show diverse information - Cons. Not good at showing a large amount of items at the same time LIST Format

Slide 44

Slide 44 text

- Pros. Display at the same time that a large number of items - Cons. Not good at showing diverse information GRID Format

Slide 45

Slide 45 text

Get just the information you need

Slide 46

Slide 46 text

『 Aggregation 』 〜 Aiming for Variety of Ranking 〜

Slide 47

Slide 47 text

検索クエリに対応する複数の取引対象のうち、同一の製品とする取引対象群を決定する決定部と、 前記決定部により決定された前記取引対象群を一の製品としたランキングを生成する生成部と、前 記生成部により生成された前記ランキングを配置したタブを含む複数のタブを含むコンテンツを提 供する提供部と、を備えることを特徴とする情報処理装置。 Main Claim

Slide 48

Slide 48 text

1. When generating rankings The patent essentials 3. Ranking those two indistinguishably. 2. Mixing "products" that are grouped together and "products" that are not grouped together of the same commodity

Slide 49

Slide 49 text

We provide mall-type e-commerce Store A Store B Store C Yahoo! Shopping MJTUTIPQ MJTUTIPQ MJTUTIPQ

Slide 50

Slide 50 text

No content

Slide 51

Slide 51 text

This is not a useful ranking for users who know the item or already have it. Ranking Issue © Nintendo / HAL Laboratory, Inc. / Pokémon / Creatures Inc./ GAME FREAK inc. Source: https://shopping.yahoo.co.jp/searchranking/?p=nintendo+switch+%E3%82%BD%E3%83%95%E3%83%88&rcid=50522

Slide 52

Slide 52 text

This is not a useful ranking for users who know it or already have it. Ranking Issue © Nintendo / HAL Laboratory, Inc. / Pokémon / Creatures Inc./ GAME FREAK inc. Source: https://shopping.yahoo.co.jp/searchranking/?p=nintendo+switch+%E3%82%BD%E3%83%95%E3%83%88&rcid=50522

Slide 53

Slide 53 text

Solution - The approach of aggregating the same products - Scoring as a single "product", taking into account the ranking of products, etc. © Microsoft / Mojang / Nintendo / HAL Laboratory, Inc. / ARMOR PROJECT / BIRD STUDIO/ SQUARE ENIX / Pokémon / Creatures Inc./ GAME FREAK inc. / BANDAI NAMCO Entertainment Inc. Source: https://shopping.yahoo.co.jp/searchranking/?p=nintendo+switch+%E3%82%BD%E3%83%95%E3%83%88&rcid=50522

Slide 54

Slide 54 text

Toward Harmony of Two Rankings

Slide 55

Slide 55 text

『 Proactive 』 〜To increase the number of ranking fans〜

Slide 56

Slide 56 text

検索クエリを入力した利用者の利用者情報に基づいて、前記検索クエリに対応する取引対象から、ランキン グとして表示する取引対象である対象取引対象を決定する決定部と、前記決定部により決定された前記対象 取引対象の前記ランキングを示すコンテンツを提供する提供部と、を備え、前記提供部は、前記利用者の属 性に類似する類似利用者に提供した他のランキングに対応する前記ランキングを示す前記コンテンツを提供 することを特徴とする情報処理装置。 Main Claim

Slide 57

Slide 57 text

1. When a user executes a search process based on a query The patent essentials 3. Generate and provide rankings appropriate to user information 2. Based on user information and query information entered by the user

Slide 58

Slide 58 text

Ranking × Personalize User Info Search Query × Optimal ranking for users × Ranking

Slide 59

Slide 59 text

Get ahead of the ranking you want #1 Provide a ranking of the best deodorizers for cars deodorant They likes driving ×

Slide 60

Slide 60 text

Get ahead of the ranking you want #2 Provide a ranking of "foods that go well with balsamic vinegar" ふるさと納税 They bought balsamic vinegar × * hometown tax payment

Slide 61

Slide 61 text

Always want to see it again and again

Slide 62

Slide 62 text

『 Boost 』 〜Toward a "FUTURE" ranking〜

Slide 63

Slide 63 text

取引対象のうち、ランキングにおけるブーストを行うブースト処理の対象とする取引対象であるブースト対 象を決定する決定部と、前記決定部により決定された前記ブースト対象について前記ブースト処理が行われ た結果を反映した前記ランキングを生成する生成部と、を備え、前記決定部は、前記取引対象に関する取引 対象情報に基づいて、前記ブースト処理のタイミングを決定することを特徴とする情報処理装置。 Main Claim

Slide 64

Slide 64 text

For Ranking based on some trigger determine when to boost rankings. The patent essentials

Slide 65

Slide 65 text

Dynamically change the scoring depending on the trigger. Number of sales and sales history Transition in number of products sold PV numbers and review information SNS BUZZ Indicators 1 2 3 4 And more... Trigger Example

Slide 66

Slide 66 text

What happens when boosting is applied to ranking Reliability Renewability Reproducibility UP DOWN DOWN

Slide 67

Slide 67 text

What happens when boosting is applied to ranking Reliability Renewability Reproducibility UP DOWN DOWN

Slide 68

Slide 68 text

Use of boosted rankings "Things that will sell in the future" "SNS Buzz" "What's hot right now" Ranking of... e.g. Super Realtime Ranking And more...

Slide 69

Slide 69 text

Toward "Future Ranking"

Slide 70

Slide 70 text

Agenda - Introduction - Background - Patents - Results

Slide 71

Slide 71 text

'21/10 '21/11 '21/12 '22/01 '22/02 '22/03 '22/04 '22/05 '22/06 '22/07 '22/08 '22/09 New Ranking Conventional Ranking Conventional Ranking vs New Ranking (CVR)

Slide 72

Slide 72 text

'22/04 '22/04 '22/05 '22/05 '22/06 '22/06 '22/07 '22/07 '22/08 '22/08 '22/08 '22/09 '22/09 '22/10 SP PC Trends in external inflows

Slide 73

Slide 73 text

Boost Section Proactive Aggregation Format Fusion and more...

Slide 74

Slide 74 text

Thank You