KR101887196B1 - 빅데이터 딥러닝 기반의 t커머스 방송편성정보 제공방법 - Google Patents
빅데이터 딥러닝 기반의 t커머스 방송편성정보 제공방법 Download PDFInfo
- Publication number
- KR101887196B1 KR101887196B1 KR1020170018034A KR20170018034A KR101887196B1 KR 101887196 B1 KR101887196 B1 KR 101887196B1 KR 1020170018034 A KR1020170018034 A KR 1020170018034A KR 20170018034 A KR20170018034 A KR 20170018034A KR 101887196 B1 KR101887196 B1 KR 101887196B1
- Authority
- KR
- South Korea
- Prior art keywords
- sales
- product
- time
- information
- programming
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/254—Management at additional data server, e.g. shopping server, rights management server
- H04N21/2542—Management at additional data server, e.g. shopping server, rights management server for selling goods, e.g. TV shopping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4662—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms
- H04N21/4666—Learning process for intelligent management, e.g. learning user preferences for recommending movies characterized by learning algorithms using neural networks, e.g. processing the feedback provided by the user
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Economics (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Description
도 2는 본 발명의 일실시예에 따른 빅데이터 딥러닝 기반의 T커머스 방송편성정보 제공방법을 설명하는 개념도이다.
도 3은 본 발명의 일실시예에 따른 심층신경망 매출예측기를 설명하는 도면이다.
도 4는 본 발명의 일실시예에 따른 상품별 매출 예상 결과를 이분 그래프로 표현하여 최적 방송편성을 얻는 방법을 설명하는 도면이다.
도 5는 본 발명의 일실시예에 따른 최대 가중치 매칭 알고리즘(헝가리안 알고리즘)을 설명하는 도면이다.
도 6과 도 7는 본 발명의 일실시예에 따른 매출 증가 추세를 반영한 상품별 매출 예상 결과를 도시한 그래프이다
Categories | Input Information | Coding | Feature dim. |
Product | Goods code | 1-of-C | 396 |
Timeslot | Day of week (0~6) and hour (0~23) | 1-of-C | 168 |
Week of year (1~52) | 1-of-C | 52 | |
External factors |
Holiday | 0(non-holiday) or 1(holiday) | 1 |
Weather (temperature, rainfall,wind speed,snowfall,cloud,effective temperature) |
value (min-max minimized) |
6 |
Predictors | Training data | |
14months | 3months | |
DNN predictor | 0.13 | 0.12 |
Statistical predictor | 0.19 | 0.18 |
DNN +Stat | 0.13 | 0.12 |
Claims (3)
- 빅데이터 딥러닝 기반의 T커머스 방송편성정보 제공방법에 있어서,
(a) 인공지능 매출 예측 모듈이 상품정보, 판매시간 정보, 외부요인 정보를 기초로 각 상품의 시간별 예상 매출을 학습하고 상품별 및 편성시간별 예상매출을 출력하는 단계; 및
(b) 매출 최적화 방송 편성 모듈이 상기 인공지능 매출 예측 모듈로부터 수신한 상품 및 편성시간별 예상매출에 기초하여 상품과 편성시간별 예상 매출을 가중치로 배정하고, 최대 가중치 알고리즘에 따라 최대 가중치를 매칭하여 방송편성정보를 생성하는 단계;를 포함하고,
상기 인공지능 매출 예측 모듈은 심층신경망 예측기와 통계적 예측기로 구성되되, 상기 심층신경망 예측기는 판매기록이 있는 상품-시간대 조합에 대해 예측하고 날씨, 휴일 변수를 반영하고, 상기 통계적 예측기는 평활화 또는 SVD 기법을 통해 데이터에 희박성을 완화하고,
상기 심층신경망 예측기와 상기 통계적 예측기가 출력한 예상 매출은 아래 식과 같이 가중평균에 의해 결합되는 빅데이터 딥러닝 기반의 T커머스 방송편성정보 제공방법.
, 은 심층신경망 예측기가 출력한 상품 x를 시간 y에 편성했을 때 예상되는 매출, 은 통계적 예측기가 출력한 상품 x를 시간 y에 편성했을 때 예상되는 매출,는 심층신경망의 가중치 - 제1항에 있어서,
상기 (a) 단계는,
상품정보, 판매시간 정보, 외부요인 정보를 기반으로 과거 매출 기록으로부터 예상 매출을 학습하는 단계를 포함하는 빅데이터 딥러닝 기반의 T커머스 방송편성정보 제공방법. - 제1항에 있어서,
상기 (b) 단계는,
판매상품, 판매시간 및 예상 매출을 이분그래프로 표현한 후 이분그래프 매칭을 이용해 최적 방송 편성을 제공하고,
동일 상품이 연속된 시간대에 배치되는 것을 예방하는 단계를 더 포함하고,
상기 최적 방송 편성은,
각 상품 x과 편성시간 y간 연결에지(x,y)에는 그 상품 x를 시간대 y에 편성했을 때의 예상 매출을 가중치로 배정하고, 이분그래프에서 X,Y간 에지 가중치의 합을 최대화하는 매칭은 최적 예상 매출을 최대화하는 방송편성을 의미하고, 이러한 그래프 G에서 각 시간대 y를 각 판매 상품 x와 연결하면서, 선택된 min(|X|, |Y|)개 에지들의 연결가중치w(x, y)의 총합을 최대화하기 위해 아래 식에 따라 매칭을 찾는 빅데이터 딥러닝 기반의 T커머스 방송편성정보 제공방법.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020160174542 | 2016-12-20 | ||
KR20160174542 | 2016-12-20 |
Publications (2)
Publication Number | Publication Date |
---|---|
KR20180071906A KR20180071906A (ko) | 2018-06-28 |
KR101887196B1 true KR101887196B1 (ko) | 2018-09-06 |
Family
ID=62780558
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
KR1020170018034A Active KR101887196B1 (ko) | 2016-12-20 | 2017-02-09 | 빅데이터 딥러닝 기반의 t커머스 방송편성정보 제공방법 |
Country Status (1)
Country | Link |
---|---|
KR (1) | KR101887196B1 (ko) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110599234A (zh) * | 2019-08-13 | 2019-12-20 | 广东工业大学 | 一种产品销售预测方法 |
KR102385407B1 (ko) * | 2020-11-17 | 2022-04-11 | 에스케이스토아 주식회사 | 방송 연출 정보 생성 방법 및 그 장치 |
KR102522676B1 (ko) * | 2020-11-17 | 2023-04-17 | 에스케이스토아 주식회사 | 데이터 분석 서버, 송출 예정된 커머스 컨텐츠에 대한 예상 판매 정도를 산출하는 방법 및 컴퓨터 프로그램 |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101467707B1 (ko) * | 2013-12-23 | 2014-12-02 | 포항공과대학교 산학협력단 | 지식 베이스의 개체 매칭 방법 및 이를 위한 장치 |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
AU2010203781B9 (en) * | 2009-01-07 | 2013-12-05 | 3M Innovative Properties Company | System and method for concurrently conducting cause-and-effect experiments on content effectiveness and adjusting content distribution to optimize business objectives |
-
2017
- 2017-02-09 KR KR1020170018034A patent/KR101887196B1/ko active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101467707B1 (ko) * | 2013-12-23 | 2014-12-02 | 포항공과대학교 산학협력단 | 지식 베이스의 개체 매칭 방법 및 이를 위한 장치 |
Also Published As
Publication number | Publication date |
---|---|
KR20180071906A (ko) | 2018-06-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112183818A (zh) | 一种推荐概率预测方法、装置、电子设备及存储介质 | |
WO2017106977A1 (en) | End-to-end deep collaborative filtering | |
EP2071473A9 (en) | Method for solving minimax and linear programming problems | |
KR101887196B1 (ko) | 빅데이터 딥러닝 기반의 t커머스 방송편성정보 제공방법 | |
US10496651B2 (en) | User recommendation generation | |
CN109417644A (zh) | 跨屏广告投放的收益优化 | |
Lakshmanan et al. | Sales demand forecasting using LSTM network | |
CN116739665A (zh) | 信息投放方法、装置、电子设备及存储介质 | |
Müller-Navarra et al. | Sales forecasting with partial recurrent neural networks: Empirical insights and benchmarking results | |
CN117436955A (zh) | 一种基于用户行为的商品推荐系统及方法 | |
Bandeira et al. | Comparison of selection and combination strategies for demand forecasting methods | |
Ahmadov et al. | Deep learning-based approach for forecasting intermittent online sales | |
Wang et al. | Prediction of loan rate for mortgage data: Deep learning versus robust regression | |
KR102642595B1 (ko) | 광고물 주문 수요 예측 시스템 및 그의 동작 방법 | |
CN114880575B (zh) | 用户行为预测方法、装置、设备、介质及产品 | |
Shahjalal et al. | A user rating based collaborative filtering approach to predict movie preferences | |
Suzuki et al. | TV advertisement scheduling by learning expert intentions | |
Mendel | Type-1 Fuzzy Systems: Design Methods and Applications | |
CN116932657A (zh) | 数据处理方法、装置、设备、存储介质及计算机程序产品 | |
Godoy et al. | Demand Forecasting of Fast-Moving Consumer Goods by Deep Learning-Based Time Series Analysis | |
Khanarsa et al. | Self-identification deep learning ARIMA | |
Singh et al. | Optimal production policy for multi-product with inventory-level-dependent demand in segmented market | |
TW202221548A (zh) | 階層式時間序列預測方法 | |
Wan et al. | Forecasting E-commerce Key Performance Indicators | |
Jones | Short-term traffic forecasting for a smart satellite communications system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A201 | Request for examination | ||
PA0109 | Patent application |
Patent event code: PA01091R01D Comment text: Patent Application Patent event date: 20170209 |
|
PA0201 | Request for examination | ||
E902 | Notification of reason for refusal | ||
PE0902 | Notice of grounds for rejection |
Comment text: Notification of reason for refusal Patent event date: 20180104 Patent event code: PE09021S01D |
|
PG1501 | Laying open of application | ||
E701 | Decision to grant or registration of patent right | ||
PE0701 | Decision of registration |
Patent event code: PE07011S01D Comment text: Decision to Grant Registration Patent event date: 20180724 |
|
PR0701 | Registration of establishment |
Comment text: Registration of Establishment Patent event date: 20180803 Patent event code: PR07011E01D |
|
PR1002 | Payment of registration fee |
Payment date: 20180806 End annual number: 3 Start annual number: 1 |
|
PG1601 | Publication of registration | ||
PR1001 | Payment of annual fee |
Payment date: 20210723 Start annual number: 4 End annual number: 4 |
|
PR1001 | Payment of annual fee |
Payment date: 20220707 Start annual number: 5 End annual number: 5 |
|
PR1001 | Payment of annual fee |
Payment date: 20230720 Start annual number: 6 End annual number: 6 |
|
PR1001 | Payment of annual fee |
Payment date: 20240716 Start annual number: 7 End annual number: 7 |