TWM634368U - Electronic device for processing commodity recommendation lists - Google Patents
Electronic device for processing commodity recommendation lists Download PDFInfo
- Publication number
- TWM634368U TWM634368U TW111204495U TW111204495U TWM634368U TW M634368 U TWM634368 U TW M634368U TW 111204495 U TW111204495 U TW 111204495U TW 111204495 U TW111204495 U TW 111204495U TW M634368 U TWM634368 U TW M634368U
- Authority
- TW
- Taiwan
- Prior art keywords
- attributes
- user
- group
- product
- commodity
- Prior art date
Links
- 238000012545 processing Methods 0.000 title claims abstract description 59
- 238000004891 communication Methods 0.000 claims abstract description 57
- 230000004044 response Effects 0.000 claims abstract description 9
- 230000000694 effects Effects 0.000 claims description 8
- 230000008451 emotion Effects 0.000 claims description 5
- 238000013461 design Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 claims description 3
- 230000013011 mating Effects 0.000 abstract 1
- 239000000047 product Substances 0.000 description 153
- 238000000034 method Methods 0.000 description 41
- 238000004364 calculation method Methods 0.000 description 21
- 238000010586 diagram Methods 0.000 description 8
- 102100033040 Carbonic anhydrase 12 Human genes 0.000 description 7
- 102100032566 Carbonic anhydrase-related protein 10 Human genes 0.000 description 7
- 102100033029 Carbonic anhydrase-related protein 11 Human genes 0.000 description 7
- 101000867855 Homo sapiens Carbonic anhydrase 12 Proteins 0.000 description 7
- 101000867836 Homo sapiens Carbonic anhydrase-related protein 10 Proteins 0.000 description 7
- 101000867841 Homo sapiens Carbonic anhydrase-related protein 11 Proteins 0.000 description 7
- 101001075218 Homo sapiens Gastrokine-1 Proteins 0.000 description 7
- 230000006870 function Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 241000405147 Hermes Species 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 239000006227 byproduct Substances 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000001151 other effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000033458 reproduction Effects 0.000 description 1
- 210000002268 wool Anatomy 0.000 description 1
Images
Classifications
-
- 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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Description
本揭露關於用於推薦商品之電子裝置。更明確地說,本揭露關於基於用戶與商品之匹配程度而推薦商品的電子裝置。 The present disclosure relates to an electronic device for recommending products. More specifically, the present disclosure relates to an electronic device that recommends items based on how well a user matches the item.
因網路購物、拍賣平台蓬勃興起帶來龐大的網路購物商機。如何針對消費者需求或喜好而推薦能吸引消費者注意的相關商品,可以有效地增進消費者購買商品的可能性,進而促成交易。 The vigorous rise of online shopping and auction platforms has brought huge online shopping business opportunities. How to recommend relevant commodities that can attract consumers' attention according to consumers' needs or preferences can effectively increase the possibility of consumers purchasing commodities, thereby facilitating transactions.
商品的推薦方法可能是藉由統計銷售量或點閱率的方式找出人氣熱門商品,並將人氣熱門商品推薦給每一位消費者。或者可以將特價或最低價商品推薦給消費者,並藉此吸引消費者購買。這些作法有可能導致相對降低其他較冷門商品的曝光率與被購買之機會,並造成熱門商品恆熱賣,而冷門商品則無人知曉的消費現象。 The product recommendation method may be to find popular and popular products by counting sales volume or click-through rate, and recommend popular and popular products to every consumer. Or you can recommend specials or lowest-priced products to consumers, and use this to attract consumers to buy. These practices may lead to a relative reduction in the exposure rate and chances of being purchased for other less popular products, and result in a consumption phenomenon where popular products are always hot, while unpopular products are unknown.
在一些其他的推薦方法中,利用資料探勘的方式,並根據使用者的消費習性、滿意度或評分回饋機制,而給予個人化的商品推薦。然而,此種推薦方法需要依靠有大量的使用者消費紀錄。 In some other recommendation methods, data mining is used to give personalized product recommendations based on the user's consumption habits, satisfaction or score feedback mechanism. However, this recommendation method needs to rely on a large number of user consumption records.
然而,大部分的商品推薦方法並未考慮商品屬性的關聯性。例如商品的外觀設計風格或規格的相近或關聯,均可能是消費者在購 買行為發生前的重要考量因素之一。 However, most item recommendation methods do not consider the relevance of item attributes. For example, the similarity or association of the appearance design style or specifications of the products may be a reason for consumers to purchase goods. One of the important considerations before buying behavior.
本揭露提供一種新穎的商品推薦方法及其相關電子裝置。本揭露提供一種以商品屬性與用戶屬性為導向(user oriented)之商品推薦方法及其相關電子裝置。 The disclosure provides a novel commodity recommendation method and related electronic device. The present disclosure provides a product recommendation method and a related electronic device oriented by product attributes and user attributes.
在某些實施例中,本揭露包含一種用於處理一商品推薦清單的電子裝置。該電子裝置包括:一通信模組、一記憶模組以及一處理模組。該通信模組經組態以與一用戶之一用戶裝置以及一資料庫通信耦合。該通信模組經組態以:接收該用戶之一目前狀態;接收該用戶之至少一個先前訂單;接收該用戶之至少一個瀏覽紀錄;及回應於一商品之一匹配分數大於或等於一用戶屬性分數之一第一預定比例,傳送一第一信號,該第一信號指示將該商品加入至該用戶之一商品推薦清單中。該記憶模組經組態以儲存多個指令及資訊。該處理模組經組態以耦合至該通信模組及該記憶模組並基於儲存於該記憶模組之指令及資訊執行以下操作:基於該用戶之該目前狀態判定一第一組用戶屬性;基於該用戶之該至少一個先前訂單判定一第二組用戶屬性;基於該用戶之該至少一個瀏覽紀錄判定一第三組用戶屬性;基於該第一組用戶屬性、該第二組用戶屬性以及該第三組用戶屬性判定該用戶屬性分數;及基於該第一組用戶屬性、該第二組用戶屬性、該第三組用戶屬性以及該商品之一第一組商品屬性判定該商品之該匹配分數。 In some embodiments, the present disclosure includes an electronic device for processing a product recommendation list. The electronic device includes: a communication module, a memory module and a processing module. The communication module is configured to be communicatively coupled with a user device of a user and a database. The communication module is configured to: receive a current status of the user; receive at least one previous order of the user; receive at least one browsing history of the user; and respond to a product with a match score greater than or equal to a user attribute A first predetermined proportion of the score transmits a first signal indicating to add the product to a product recommendation list of the user. The memory module is configured to store a plurality of instructions and information. The processing module is configured to be coupled to the communication module and the memory module and to perform the following operations based on instructions and information stored in the memory module: determine a first set of user attributes based on the current state of the user; Determine a second set of user attributes based on the at least one previous order of the user; determine a third set of user attributes based on the at least one browsing record of the user; determine a third set of user attributes based on the first set of user attributes, the second set of user attributes and the Determining the user attribute score for a third set of user attributes; and determining the matching score for the item based on the first set of user attributes, the second set of user attributes, the third set of user attributes, and a first set of item attributes of the item .
在某些實施例中,本揭露包含一種用於推薦商品之方法。該方法包括:接收一用戶之一目前狀態;基於該用戶之該目前狀態判定一第一組用戶屬性;接收該用戶之至少一個先前訂單;基於該用戶之該至少一 個先前訂單判定一第二組用戶屬性;接收該用戶之至少一個瀏覽紀錄;基於該用戶之該至少一個瀏覽紀錄判定一第三組用戶屬性;基於該第一組用戶屬性、該第二組用戶屬性以及該第三組用戶屬性判定一用戶屬性分數;基於該第一組用戶屬性、該第二組用戶屬性、該第三組用戶屬性以及一商品之一第一組商品屬性判定該商品之一匹配分數;以及回應於該商品之該匹配分數大於或等於該用戶屬性分數之一第一預定比例,將該商品加入至該用戶之一推薦清單中。 In some embodiments, the present disclosure includes a method for recommending products. The method includes: receiving a current status of a user; determining a first set of user attributes based on the current status of the user; receiving at least one previous order of the user; based on the at least one Determine a second set of user attributes for a previous order; receive at least one browsing record of the user; determine a third set of user attributes based on the at least one browsing record of the user; based on the first set of user attributes, the second set of user Determine a user attribute score based on the attribute and the third group of user attributes; determine one of the commodities based on the first group of user attributes, the second group of user attributes, the third group of user attributes and the first group of commodity attributes of a commodity a matching score; and in response to the matching score of the commodity being greater than or equal to a first predetermined ratio of the user attribute score, adding the commodity to a recommendation list of the user.
100:系統 100: system
110:伺服器 110: server
111:輸入輸出模組 111: Input and output module
112:記憶模組 112: memory module
113:處理模組 113: Processing module
114:通信模組 114: Communication module
120:資料庫 120: database
121:輸入輸出模組 121: Input and output module
122:記憶模組 122: memory module
123:處理模組 123: Processing module
124:通信模組 124: Communication module
130:用戶裝置 130: user device
131:輸入輸出模組 131: Input and output module
132:記憶模組 132: memory module
133:處理模組 133: Processing module
134:通信模組 134:Communication module
200:程序 200: program
201:操作 201: Operation
202:操作 202: Operation
203:操作 203: Operation
204:操作 204: Operation
205:操作 205: Operation
206:操作 206: Operation
207:操作 207: Operation
208:操作 208: Operation
209:操作 209: Operation
CA1:第一組商品屬性 CA1: The first group of commodity attributes
MS1:第一匹配分數 MS1: First Match Score
MS2:第二匹配分數 MS2: Second Match Score
MS3:第三匹配分數 MS3: Third Match Score
UA1:第一組用戶屬性 UA1: The first set of user attributes
UA2:第二組用戶屬性 UA2: The second set of user attributes
UA3:第三組用戶屬性 UA3: The third group of user attributes
UA4:第四組用戶屬性 UA4: The fourth group of user attributes
UA5:第五組用戶屬性 UA5: The fifth set of user attributes
UA6:第六組用戶屬性 UA6: The sixth group of user attributes
UA7:第七組用戶屬性 UA7: The seventh group of user attributes
UA8:第八組用戶屬性 UA8: The eighth group of user attributes
UA9:第九組用戶屬性 UA9: The ninth group of user attributes
UA10:第十組用戶屬性 UA10: The tenth group of user attributes
UA11:第十一組用戶屬性 UA11: The eleventh group of user attributes
US1:第一用戶屬性分數 US1: First User Attribute Score
US2:第二用戶屬性分數 US2: Second User Attribute Score
US3:第三用戶屬性分數 US3: Third User Attribute Score
圖1繪示根據本揭露之一些實施例的系統及裝置。 FIG. 1 illustrates systems and devices according to some embodiments of the present disclosure.
圖2繪示根據本揭露之一些實施例之方法的流程圖。 FIG. 2 illustrates a flowchart of a method according to some embodiments of the present disclosure.
圖3A及圖3B繪示根據本揭露之一些實施例中用戶屬性分數與匹配分數之計算方法的示意圖。 3A and 3B are schematic diagrams illustrating calculation methods of user attribute scores and matching scores according to some embodiments of the present disclosure.
圖4A至圖4C繪示根據本揭露之一些實施例中用戶屬性分數與匹配分數之計算方法的示意圖。 4A to 4C are schematic diagrams illustrating calculation methods of user attribute scores and matching scores according to some embodiments of the present disclosure.
圖5繪示根據本揭露之一些實施例中用戶屬性分數與匹配分數之計算方法的示意圖。 FIG. 5 is a schematic diagram illustrating a method for calculating user attribute scores and matching scores according to some embodiments of the present disclosure.
圖6A及圖6B繪示根據本揭露之一些實施例中用戶屬性分數與匹配分數之計算方法的示意圖。 6A and 6B are schematic diagrams illustrating calculation methods of user attribute scores and matching scores according to some embodiments of the present disclosure.
為更好地理解本揭露之前述態樣以及其額外態樣及實施例,應結合以上圖式參考下文實施方式。在各個圖式中,相似參考符號指示相似元件。應注意,各種特徵可能未按比例繪製。實際上,出於清晰描述之目的,可任意增大或減小各種特徵之大小。 For a better understanding of the aforementioned aspects of the present disclosure, as well as additional aspects and embodiments thereof, reference should be made to the following description in conjunction with the above figures. In the various drawings, like reference symbols indicate like elements. It should be noted that various features may not be drawn to scale. In fact, the dimensions of the various features may be arbitrarily increased or reduced for clarity of description.
描述本揭露之方法、系統及其他態樣。將參考本揭露之某些實施例,其實例在隨附圖式中加以說明。雖然本揭露將結合實施例進行描述,但將理解,並不意欲將本揭露僅限於此等特定實施例。相反地,本揭露意欲涵蓋本揭露之精神及範圍內的替代方案、修改及等效物。因此,應在說明性意義上而非限定性意義上看待說明書及圖式。 Methods, systems and other aspects of the disclosure are described. Reference will be made to certain embodiments of the present disclosure, examples of which are illustrated in the accompanying drawings. While the disclosure will be described in conjunction with the embodiments, it will be understood that they are not intended to limit the disclosure to these particular embodiments. On the contrary, the present disclosure is intended to cover alternatives, modifications and equivalents within the spirit and scope of the present disclosure. Accordingly, the specification and drawings should be regarded in an illustrative sense rather than a restrictive sense.
此外,在以下描述中,闡述眾多具體細節以提供對本揭露之透徹理解。然而,一般熟習此項技術者將可無需此等特定細節而實踐本揭露。在其他情況下,為避免混淆本揭露之態樣,並未詳細描述一般熟習此項技術者已熟知的方法、程序、操作、組件及網路。 Furthermore, in the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, one of ordinary skill in the art will be able to practice the present disclosure without these specific details. In other instances, methods, procedures, operations, components and networks that are well known by those of ordinary skill in the art have not been described in detail so as not to obscure the aspects of the present disclosure.
圖1繪示根據本揭露之一些實施例的系統100以及用戶裝置130。系統100可包含伺服器110、資料庫120。在一些實施例中,伺服器110可設置於提供線上購物的公司、提供商品管理的公司或是其他提供相關服務的公司。資料庫120可設置於提供線上購物的公司、提供商品管理的公司或是其他提供相關服務的公司。資料庫120可用於儲存用戶資料以及商品資料。
FIG. 1 illustrates a
伺服器110可包含輸入輸出模組111、記憶模組112、處理模組113以及通信模組114。處理模組113可經組態以耦合至記憶模組112。處理模組113及記憶模組112可經組態以耦合至通信模組114,且處理模組113可基於儲存於記憶模組112之指令及資訊使通信模組114執行若干操作。處理模組113及記憶模組112可經組態以耦合至輸入輸出模組111,且處理模組113可基於儲存於記憶模組112之指令及資訊使輸入輸出模組111執行若干操作。資料庫120可包含輸入輸出模組121、記憶模組122、處理模組123以及通信模組124。處理模組123可經組態以耦合至記憶模組122。處理模組123及記憶模組122可經組態以耦合至通信模組124,且處理模組123可基於儲存於記憶模組122之指令及資訊使通信模組124執行若干操作。處理模組123及記憶模組122可經組態以耦合至輸入輸出模組121,且處理模組123可基於儲存於記憶模組122之指令及資訊使輸入輸出模組121執行若干操作。用戶裝置130可包含輸入輸出模組131、記憶模組132、處理模組133以及通信模組134。處理模組133可經組態以耦合至記憶模組132。處理模組133及記憶模組132可經組態以耦合至通信模組134,且處理模組133可基於儲存於記憶模組132之指令及資訊使通信模
組134執行若干操作。處理模組133及記憶模組132可經組態以耦合至輸入輸出模組131,且處理模組133可基於儲存於記憶模組132之指令及資訊使輸入輸出模組131執行若干操作。
The
伺服器110可為工作站或電腦。資料庫120可為工作站或電腦。在一些實施例中,資料庫120可整合於伺服器110中。用戶裝置130可為電腦、個人數位助理、智慧型手機或平板電腦。
The
伺服器110及資料庫120可經由伺服器110之通信模組114及資料庫120之通信模組124相互通信耦接。伺服器110及資料庫120可藉由有線方法相互通信耦接,例如藉由乙太網路線、同軸電纜、Universal Serial Bus(USB)或其他具有通訊功能之線路而相互通信耦接。伺服器110及資料庫120可藉由無線方法相互通信耦接,例如藉由藍牙、IEEE 802.11、LTE、5G或其他無線通訊協定而相互通信耦接。
The
在某些實施例中,伺服器110及資料庫120可設置於不同地理位置。伺服器110可經由伺服器110之通信模組114而與網際網路相互通信耦接。伺服器110可藉由有線方法(例如藉由乙太網路線、同軸電纜或其他具有通訊功能之線路),或藉由無線方法(例如藉由藍牙、IEEE 802.11、LTE、5G或其他無線通訊協定),而通信耦接至網際網路。資料庫120可經由資料庫120之通信模組124而與網際網路相互通信耦接。資料庫120亦可藉由有線方法(例如藉由乙太網路線、同軸電纜或其他具有通訊功能之線路),或藉由無線方法(例如藉由藍牙、IEEE 802.11、LTE、5G或其他無線通訊協定),而通信耦接至網際網路。伺服器110及資料庫120可藉由網際網路而相互通訊耦接。
In some embodiments, the
經由用戶裝置130之通信模組134,系統100可與用戶裝置130可藉由無線方法相互通訊耦接,例如藉由藍牙、IEEE 802.11、LTE、5G或其他無線通訊協定而相互通信耦接。在一些實施例中,經由用戶裝置130之通信模組134,系統100可與用戶裝置130可藉由有線方法相互通訊耦接,例如藉由乙太網路線、同軸電纜、USB或其他具有通訊功能之線路而相互通信耦接。系統100可藉由伺服器110之通信模組114而與用戶裝置130通信耦接。在一些實施例中,系統100可藉由一額外之通信模組而與用戶裝置130通信耦接。
Through the
在某些實施例中,系統100可藉由有線方法(例如藉由乙太網路線、同軸電纜或其他具有通訊功能之線路),或藉由無線方法(例如藉由藍牙、IEEE 802.11、LTE、5G或其他無線通訊協定),而通信耦接至網際網路140。用戶裝置130可經由用戶裝置130之通信模組134而與網際網路相互通信耦接。用戶裝置130亦可藉由有線方法(例如藉由乙太網路線、同軸電纜或其他具有通訊功能之線路),或藉由無線方法(例如藉由藍牙、IEEE 802.11、LTE、5G或其他無線通訊協定),而通信耦接至網際網路。系統100及用戶裝置130可藉由網際網路而相互通訊耦接。
In some embodiments, the
伺服器110之輸入輸出模組111、記憶模組112、處理模組113以及通信模組114可經組態以執行下文以及圖2至圖6B所描述之操作。資料庫120之輸入輸出模組121、記憶模組122、處理模組123以及通信模組124可經組態以執行下文以及圖2至圖6B所描述之操作。在一些實施例中,系統100可藉由額外之輸出模組、記憶模組、處理模組以及通信模組以執行下文以及圖2至圖6B所描述之操作。
The I/
圖2繪示根據本揭露之一些實施例之程序200的流程圖。程序200之各操作可由如圖1所示之系統100所執行。程序200之各操作可由如圖1所示之系統100中之伺服器110所執行。程序200之各操作可由如圖1所示之系統100中之伺服器110與資料庫120協同運作。程序200之各操作可由如圖1所示之系統100與用戶裝置130協同運作。
FIG. 2 shows a flowchart of a
程序200可包含操作201。操作201包含接收用戶之目前狀態。用戶可藉由用戶裝置130而輸入用戶的目前狀態。用戶可以將用戶之目前活動、目前情緒、目前地點或其他目前之狀態輸入至用戶裝置130中。用戶之目前狀態可以經由相應通信模組而自用戶裝置130或資料庫
120接收。用戶之目前地點可藉由用戶裝置130之位置而判定。用戶之目前活動可基於用戶裝置130之位置以及附近之活動而判定。用戶之目前活動或目前情緒可基於用戶裝置130之位置以及最近之社群軟體發文紀錄而判定。伺服器110之通信模組114可經組態以執行操作201。在一些實施例中,可回應於用戶裝置130開啟相關聯之程式(例如購物平台程式,或可瀏覽購物平台之程式)後,而執行操作201。
程序200可包含操作202。操作202包含基於用戶之目前狀態判定第一組用戶屬性。基於用戶之目前活動、目前情緒、目前地點或其他目前之狀態,經由相應處理模組而判定第一組用戶屬性。例如,用戶之目前地點為「Apple商品專賣店」,則可判定第一組用戶屬性包含Apple之相關屬性,例如「品牌為Apple」之屬性或「適用於Apple」之屬性。例如,用戶之目前活動為「慶祝生日」,則可判定第一組用戶屬性包含生日之相關屬性,例如「生日蛋糕」之屬性或「生日禮物」之屬性。例如,用戶之目前情緒為「壓力」,則可判定第一組用戶屬性包含紓壓之相關屬性,例如「紓壓」之屬性。
程序200可包含操作203。操作203包含接收用戶之至少一個先前訂單。可經由相應通信模組而自資料庫120處接收用戶之一或多個先前訂單。操作203可進一步包含檢視先前訂單中之商品,以及商品之相關商品屬性。
程序200可包含操作204。操作204包含基於用戶之至少一個先前訂單判定第二組用戶屬性。自資料庫120處接收用戶之一或多個先前訂單中可包含一或多個已購買之商品。基於用戶之先前訂單中已購買之商品,可經由相應處理模組而判定第二組用戶屬性。舉例而言,若用戶之
先前訂單中已購買之商品包含Sony之手機,則第二組用戶屬性可能包含「品牌為Sony」之屬性或「適用於Sony」之屬性。若用戶之先前訂單中已購買之商品包含無印良品的商品,則第二組用戶屬性可能包含「簡約風格」之屬性。
程序200可包含操作205。操作205包含接收用戶之至少一個瀏覽紀錄。可根據伺服器端之暫存紀錄而接收用戶之一或多個瀏覽紀錄。可經由相應通信模組而自資料庫120處接收用戶之一或多個瀏覽紀錄。操作206可進一步包含檢視瀏覽紀錄中之商品,以及商品之相關商品屬性。
程序200可包含操作206。操作206包含基於用戶之至少一個瀏覽紀錄判定第三組用戶屬性。一或多個瀏覽紀錄中可包含一或多個已點擊或已瀏覽之商品。基於用戶之瀏覽紀錄中已點擊或已瀏覽之商品,可經由相應處理模組而判定第三組用戶屬性。舉例而言,若用戶之瀏覽紀錄中已點擊或已瀏覽包含法蘭絨襯衫,則第三組用戶屬性可能包含「法蘭絨」之屬性或「休閒襯衫」之屬性。若用戶之先前訂單中已購買之商品包含針織背心,則第二組用戶屬性可能包含「學院風格」之屬性或「毛料」之屬性。
根據本揭露,可以基於商品之視覺特徵、商品之觸覺特徵、商品之設計特徵、商品之品牌特徵、商品之文字特徵或商品之類別而判定商品之商品屬性。舉例而言,基於商品之視覺特徵可判定商品屬性包含「莫蘭迪色系」或「粉色系」。基於商品之設計特徵可判定商品屬性包含「簡約風格」、「哥德風」或「工業風」。基於商品之品牌特徵可判定商品屬性包含「HERMES」、「LV」或「PRADA」。基於商品之文字特徵可 判定商品屬性包含「我要加薪」、「早日退休」或「ITW」。基於商品之類別可判定商品屬性包含「精品」、「晚宴包」或「項鍊」。 According to the present disclosure, the product attributes of the product can be determined based on the visual features of the product, the tactile features of the product, the design features of the product, the brand features of the product, the character features of the product or the category of the product. For example, based on the visual characteristics of the product, it can be determined that the product attributes include "Morandi color" or "Pink color". Based on the design features of the product, it can be determined that the product attributes include "simple style", "gothic style" or "industrial style". Based on the brand characteristics of the product, it can be determined that the product attribute contains "HERMES", "LV" or "PRADA". Based on the text features of the product, it can be determined that the product attributes include "I want a salary increase", "early retirement" or "I TW". Based on the category of the product, it can be determined that the product attribute includes "boutique", "evening bag" or "necklace".
程序200可包含操作207。操作207包含基於第一組用戶屬性、第二組用戶屬性以及第三組用戶屬性判定用戶屬性分數。操作207可基於第一組用戶屬性、第二組用戶屬性以及第三組用戶屬性,並經由相應處理模組而判定用戶屬性分數。
程序200可包含操作208。操作208包含基於第一組用戶屬性、第二組用戶屬性、第三組用戶屬性以及商品之第一組商品屬性判定商品之匹配分數。操作207可第一組用戶屬性、第二組用戶屬性、第三組用戶屬性以及商品之第一組商品屬性,並經由相應處理模組而判定商品之匹配分數。操作208可進一步包含經由相應通信模組而自資料庫120接收商品資料及/或相應商品屬性。基於第一組用戶屬性、第二組用戶屬性、第三組用戶屬性以及商品之第一組商品屬性之間的匹配程度而判定此商品對於用戶之匹配分數。
程序200可包含操作209。操作209包含回應於商品之匹配分數大於或等於用戶屬性分數之預定比例,將商品加入至用戶之推薦清單中。在某些實施例中,回應於商品之匹配分數大於或等於用戶屬性分數之預定比例,可經由相應通信模組傳送一信號以指示將商品加入至用戶之推薦清單中。
若將操作209之預定比例設定為100%,商品之匹配分數必需等於用戶之屬性分數,方可將商品加入至用戶之推薦清單中。換言之,若將操作209之預定比例設定為100%,商品之商品屬性必需等於第一組用戶屬性、第二組用戶屬性、第三組用戶屬性之一特定組合,方可將商品加
入至用戶之推薦清單中。若將操作209之預定比例設定為100%,被推薦商品之範圍較受限制。根據本揭露之某些實施例,若將操作209之預定比例設定為60%至90%之間,被推薦之商品之範圍較不受限制。因為被推薦之商品之範圍較不受限制,可有效降低用戶因大量瀏覽類似商品所產生之疲勞感,並可提高被推薦之商品被購買之機率。根據本揭露之特定實施例,若將操作209之預定比例設定為80%,可以有效提高被推薦之商品被購買之機率。
If the predetermined ratio in
圖3A及圖3B繪示根據本揭露之一些實施例中用戶屬性分數與匹配分數之計算的示意圖。圖3A及圖3B所揭示之計算方法可由系統100所執行。圖3A及圖3B所揭示之計算方法可由伺服器110之處理模組113或由資料庫120之處理模組123所執行。
3A and 3B are schematic diagrams illustrating the calculation of user attribute scores and matching scores according to some embodiments of the present disclosure. The calculation method disclosed in FIG. 3A and FIG. 3B can be implemented by the
本揭露所述之一組用戶屬性可為一個集合,此集合之元素為屬性。例如第一組用戶屬性可為集合UA1={手機,品牌為Sony,適用於Sony,Xperia,Android}。本揭露所述之一組商品屬性可為一個集合,此集合之元素為屬性。例如第一組商品屬性可為集合CA1={手機,品牌為Apple,適用於Apple,iPhone,iOS}。 A set of user attributes described in this disclosure may be a collection, and the elements of this collection are attributes. For example, the first group of user attributes may be the set UA1={mobile phone, the brand is Sony, applicable to Sony, Xperia, Android}. A set of product attributes described in this disclosure may be a set, and the elements of this set are attributes. For example, the first group of commodity attributes may be the set CA1={mobile phone, the brand is Apple, applicable to Apple, iPhone, iOS}.
圖3A繪示第一組用戶屬性UA1、第二組用戶屬性UA2以及第三組用戶屬性UA3。基於第一組用戶屬性UA1、第二組用戶屬性UA2以及第三組用戶屬性UA3而判定第四組用戶屬性UA4。第四組用戶屬性UA4可為第一組用戶屬性UA1、第二組用戶屬性UA2以及第三組用戶屬性UA3之聯集。基於第四組用戶屬性UA4而判定用戶之用戶屬性分數。此用戶之用戶屬性分數可為第四組用戶屬性UA4之屬性個數。 FIG. 3A shows a first group of user attributes UA1 , a second group of user attributes UA2 and a third group of user attributes UA3 . A fourth group of user attributes UA4 is determined based on the first group of user attributes UA1 , the second group of user attributes UA2 and the third group of user attributes UA3 . The fourth group of user attributes UA4 may be a union of the first group of user attributes UA1 , the second group of user attributes UA2 and the third group of user attributes UA3 . The user attribute score of the user is determined based on the fourth set of user attributes UA4. The user attribute score of the user may be the attribute number of the fourth group of user attributes UA4.
舉例而言,假設第一組用戶屬性UA1={a,b,c},第二組用 戶屬性UA2={c,d,e},第三組用戶屬性UA3={d,e,f,g},其中元素a、b、c、d、e、f、g之每一者為一屬性。基於第一組用戶屬性UA1、第二組用戶屬性UA2以及第三組用戶屬性UA3之聯集,第四組用戶屬性UA4=UA1∪UA2∪UA3={a,b,c,d,e,f,g}。相應用戶之用戶屬性分數則為n(UA4)=|UA4|=7。 For example, suppose the first group of user attributes UA1={a,b,c}, the second group with User attribute UA2={c,d,e}, the third group of user attributes UA3={d,e,f,g}, where each of the elements a, b, c, d, e, f, g is one Attributes. Based on the union of the first group of user attributes UA1, the second group of user attributes UA2 and the third group of user attributes UA3, the fourth group of user attributes UA4=UA1∪UA2∪UA3={a,b,c,d,e,f ,g}. The user attribute score of the corresponding user is n(UA4)=|UA4|=7.
圖3B繪示第四組用戶屬性UA4(如圖3B中灰色形狀)以及一商品之第一組商品屬性CA1(如圖3B中以虛線所繪製之圓)。基於第四組用戶屬性UA4以及第一組商品屬性CA1而判定該商品之第二組商品屬性CA2。該商品之第二組商品屬性CA2可為第四組用戶屬性UA4與第一組商品屬性CA1之交集。基於該商品之第二組商品屬性CA2而判定用戶與該商品之匹配程度。基於該商品之第二組商品屬性CA2而判定用戶之用戶屬性分數與該商品之匹配分數。此用戶之用戶屬性分數與該商品之匹配分數可為該商品之第二組商品屬性CA2之屬性個數。 FIG. 3B shows the fourth group of user attributes UA4 (the gray shape in FIG. 3B ) and the first group of product attributes CA1 of a product (the circle drawn with a dotted line in FIG. 3B ). The second group of commodity attributes CA2 of the commodity is determined based on the fourth group of user attributes UA4 and the first group of commodity attributes CA1. The second group of commodity attributes CA2 of the commodity may be the intersection of the fourth group of user attributes UA4 and the first group of commodity attributes CA1. The degree of matching between the user and the commodity is determined based on the second group of commodity attributes CA2 of the commodity. Based on the second set of commodity attributes CA2 of the commodity, the matching score between the user attribute score of the user and the commodity is determined. The matching score between the user attribute score of the user and the commodity may be the attribute number of the second group of commodity attributes CA2 of the commodity.
舉例而言,當第四組用戶屬性UA4={a,b,c,d,e,f,g}且第一組商品屬性CA1={c,d,e,h,i,j},其中元素c、d、e、h、i、j之每一者為一屬性。基於第四組用戶屬性UA4與第一組商品屬性CA1之交集,第二組商品屬性CA2=UA4∩CA1={c,d,e}。相應用戶之用戶屬性分數與該商品之匹配分數則為:n(CA2)=|CA2|=3。 For example, when the fourth group of user attributes UA4={a,b,c,d,e,f,g} and the first group of commodity attributes CA1={c,d,e,h,i,j}, where Each of the elements c, d, e, h, i, j is an attribute. Based on the intersection of the fourth group of user attributes UA4 and the first group of commodity attributes CA1, the second group of commodity attributes CA2=UA4∩CA1={c,d,e}. The matching score between the user attribute score of the corresponding user and the commodity is: n(CA2)=|CA2|=3.
假設操作209中所述之預定比例為80%。用戶屬性分數為7,且匹配分數為3,3小於7*80%,故相應商品將不會被加入相應用戶之商品推薦清單中。
Assume that the predetermined ratio described in
圖4A至圖4C繪示根據本揭露之一些實施例中用戶屬性分數與匹配分數之計算的示意圖。圖4A至圖4C所揭示之計算方法可由系統
100所執行。圖4A至圖4C所揭示之計算方法可由伺服器110之處理模組113或由資料庫120之處理模組123所執行。
4A to 4C are schematic diagrams illustrating the calculation of user attribute scores and matching scores according to some embodiments of the present disclosure. The calculation method disclosed in Fig. 4A to Fig. 4C can be used by the
在圖4A至圖4C之用戶屬性分數之計算方法中,基於第一組用戶屬性UA1之屬性個數、第二組用戶屬性UA2之屬性個數以及第三組用戶屬性UA3之屬性個數而判定用戶之用戶屬性分數。此用戶之用戶屬性分數可為第一組用戶屬性UA1之屬性個數、第二組用戶屬性UA2之屬性個數以及第三組用戶屬性UA3之屬性個數之總和。 In the calculation method of the user attribute score in Fig. 4A to Fig. 4C, it is determined based on the number of attributes of the first group of user attributes UA1, the number of attributes of the second group of user attributes UA2 and the number of attributes of the third group of user attributes UA3 The user attribute score of the user. The user attribute score of the user can be the sum of the attribute numbers of the first group of user attributes UA1 , the attribute numbers of the second group of user attributes UA2 and the attribute numbers of the third group of user attributes UA3 .
舉例而言,假設第一組用戶屬性UA1={a,b,c},第二組用戶屬性UA2={c,d,e},第三組用戶屬性UA3={d,e,f,g}。相應用戶之用戶屬性分數則為:n(UA1)+n(UA2)+n(UA3)=|UA1|+|UA2|+|UA3|=10。 For example, suppose the first group of user attributes UA1={a,b,c}, the second group of user attributes UA2={c,d,e}, the third group of user attributes UA3={d,e,f,g }. The user attribute score of the corresponding user is: n(UA1)+n(UA2)+n(UA3)=|UA1|+|UA2|+|UA3|=10.
在此實施例中,重複之屬性(元素)將被重複計算分數。屬性c出現於第一組用戶屬性UA1及第二組用戶屬性UA2中,則被計為2分。屬性d出現於第二組用戶屬性UA2及第三組用戶屬性UA3中,則被計為2分。屬性e出現於第二組用戶屬性UA2及第三組用戶屬性UA3中,則被計為2分。 In this embodiment, duplicate attributes (elements) will be double-counted. If attribute c appears in the first group of user attributes UA1 and the second group of user attributes UA2, it is counted as 2 points. If the attribute d appears in the second group of user attributes UA2 and the third group of user attributes UA3, it is counted as 2 points. If the attribute e appears in the second group of user attributes UA2 and the third group of user attributes UA3, it is counted as 2 points.
圖4A繪示第一組用戶屬性UA1(如圖4A中以實線所繪製之圓)與一商品之第一組商品屬性CA1(如圖4A中以虛線所繪製之橢圓)。圖4B繪示第二組用戶屬性UA2(如圖4B中以實線所繪製之圓)與該商品之第一組商品屬性CA1(如圖4B中以虛線所繪製之橢圓)。圖4C繪示第三組用戶屬性UA3(如圖4C中以實線所繪製之圓)與該商品之第一組商品屬性CA1(如圖4C中以虛線所繪製之橢圓)。 FIG. 4A shows the first group of user attributes UA1 (the circle drawn by the solid line in FIG. 4A ) and the first group of product attributes CA1 of a commodity (the ellipse drawn by the dotted line in FIG. 4A ). FIG. 4B shows the second set of user attributes UA2 (circle drawn with a solid line in FIG. 4B ) and the first set of commodity attributes CA1 of the commodity (an ellipse drawn with a dotted line in FIG. 4B ). FIG. 4C shows the third group of user attributes UA3 (circle drawn with a solid line in FIG. 4C ) and the first group of commodity attributes CA1 of the commodity (an ellipse drawn with a dotted line in FIG. 4C ).
基於第一組商品屬性CA1以及第一組用戶屬性UA1而判定該商品之第三組商品屬性CA3。該商品之第三組商品屬性CA3可為第一組 商品屬性CA1以及第一組用戶屬性UA1之交集,即CA3=CA1∩UA1。基於第一組商品屬性CA1以及第二組用戶屬性UA2而判定該商品之第四組商品屬性CA4。該商品之第四組商品屬性CA4可為第一組商品屬性CA1以及第二組用戶屬性UA2之交集,即CA4=CA1∩UA2。基於第一組商品屬性CA1以及第三組用戶屬性UA3而判定該商品之第五組商品屬性CA5。該商品之第五組商品屬性CA5可為第一組商品屬性CA1以及第三組用戶屬性UA3之交集,即CA5=CA1∩UA3。 Based on the first group of commodity attributes CA1 and the first group of user attributes UA1, the third group of commodity attributes CA3 of the commodity is determined. The third group of product attributes CA3 of the product can be the first group The intersection of the commodity attribute CA1 and the first group of user attributes UA1, that is, CA3=CA1∩UA1. The fourth group of commodity attributes CA4 of the commodity is determined based on the first group of commodity attributes CA1 and the second group of user attributes UA2. The fourth group of commodity attributes CA4 of the commodity may be the intersection of the first group of commodity attributes CA1 and the second group of user attributes UA2, that is, CA4=CA1∩UA2. Based on the first group of commodity attributes CA1 and the third group of user attributes UA3, the fifth group of commodity attributes CA5 of the commodity is determined. The fifth group of commodity attributes CA5 of the commodity may be the intersection of the first group of commodity attributes CA1 and the third group of user attributes UA3, ie CA5=CA1∩UA3.
基於第三組商品屬性CA3之屬性個數、第四組商品屬性CA4之屬性個數以及第五組商品屬性CA5之屬性個數而判定用戶與該商品之匹配程度。基於第三組商品屬性CA3之屬性個數、第四組商品屬性CA4之屬性個數以及第五組商品屬性CA5之屬性個數而判定用戶之用戶屬性分數與該商品之匹配分數。此用戶之用戶屬性分數與該商品之匹配分數可為該商品之第三組商品屬性CA3之屬性個數、第四組商品屬性CA4之屬性個數以及第五組商品屬性CA5之屬性個數之一總和。 Based on the attribute numbers of the third group of commodity attributes CA3, the attribute numbers of the fourth group of commodity attributes CA4 and the attribute numbers of the fifth group of commodity attributes CA5, the degree of matching between the user and the commodity is determined. Based on the attribute numbers of the third group of commodity attributes CA3, the attribute numbers of the fourth group of commodity attributes CA4 and the attribute numbers of the fifth group of commodity attributes CA5, determine the matching score between the user's user attribute score and the commodity. The matching score between the user attribute score of this user and the product can be the number of attributes of the third group of product attributes CA3, the number of attributes of the fourth group of product attributes CA4 and the number of attributes of the fifth group of product attributes CA5. one sum.
舉例而言,當第一組用戶屬性UA1={a,b,c},第二組用戶屬性UA2={c,d,e},第三組用戶屬性UA3={d,e,f,g},第一組商品屬性CA1={a,c,d,e,f}。基於第一組商品屬性CA1以及第一組用戶屬性UA1之交集,第三組商品屬性CA3={a,c}。基於第一組商品屬性CA1以及第二組用戶屬性UA2之交集,第四組商品屬性CA4={c,d,e}。基於第一組商品屬性CA1以及第三組用戶屬性UA3之交集,第五組商品屬性CA5={d,e,f}。相應用戶之用戶屬性分數與該商品之匹配分數則為:n(CA3)+n(CA4)+n(CA5)=|CA3|+|CA4|+|CA5|=8。 For example, when the first group of user attributes UA1={a,b,c}, the second group of user attributes UA2={c,d,e}, and the third group of user attributes UA3={d,e,f,g }, the first group of commodity attributes CA1={a,c,d,e,f}. Based on the intersection of the first group of commodity attributes CA1 and the first group of user attributes UA1, the third group of commodity attributes CA3={a,c}. Based on the intersection of the first set of commodity attributes CA1 and the second set of user attributes UA2, the fourth set of commodity attributes CA4={c,d,e}. Based on the intersection of the first group of commodity attributes CA1 and the third group of user attributes UA3, the fifth group of commodity attributes CA5={d, e, f}. The matching score between the user attribute score of the corresponding user and the product is: n(CA3)+n(CA4)+n(CA5)=|CA3|+|CA4|+|CA5|=8.
假設操作209中所述之預定比但為80%。用戶屬性分數為
10,且匹配分數為8,8等於10*80%,故相應商品將會被加入相應用戶之商品推薦清單中。
Assume that the predetermined ratio described in
在此實施例中,重複之屬性(元素)將被重複計算分數。屬性c出現於第一組用戶屬性UA1及第二組用戶屬性UA2中,則被計為2分。屬性d出現於第二組用戶屬性UA2及第三組用戶屬性UA3中,則被計為2分。屬性e出現於第二組用戶屬性UA2及第三組用戶屬性UA3中,則被計為2分。 In this embodiment, duplicate attributes (elements) will be double-counted. If attribute c appears in the first group of user attributes UA1 and the second group of user attributes UA2, it is counted as 2 points. If the attribute d appears in the second group of user attributes UA2 and the third group of user attributes UA3, it is counted as 2 points. If the attribute e appears in the second group of user attributes UA2 and the third group of user attributes UA3, it is counted as 2 points.
在圖4A至圖4C之用戶屬性分數之另一種計算方法中,基於第一組用戶屬性UA1之屬性個數、第二組用戶屬性UA2之屬性個數、第三組用戶屬性UA3之屬性個數以及相應權重值而判定用戶之用戶屬性分數。可基於第一組用戶屬性UA1之屬性個數與第一權重值W1之乘積而判定第一用戶加權分數;可基於第二組用戶屬性UA2之屬性個數與第二權重值W2之乘積而判定第二用戶加權分數;以及可基於第三組用戶屬性UA3之屬性個數與第三權重值W3之乘積而判定第三用戶加權分數。此用戶之用戶屬性分數可為第一用戶加權分數、第二用戶加權分數以及第三用戶加權分數之總和。 In another calculation method of the user attribute scores shown in Figures 4A to 4C, based on the number of attributes of the first group of user attributes UA1, the number of attributes of the second group of user attributes UA2, and the number of attributes of the third group of user attributes UA3 And the corresponding weight value to determine the user attribute score of the user. The first user weighted score can be determined based on the product of the number of attributes of the first group of user attributes UA1 and the first weight value W1; it can be determined based on the product of the number of attributes of the second group of user attributes UA2 and the second weight value W2 The second user weighted score; and the third user weighted score can be determined based on the product of the attribute number of the third group of user attributes UA3 and the third weight value W3. The user attribute score of the user may be the sum of the first user weighted score, the second user weighted score and the third user weighted score.
舉例而言,假設第一組用戶屬性UA1={a,b,c},第二組用戶屬性UA2={c,d,e},第三組用戶屬性UA3={d,e,f,g},第一權重值W1為3,第二權重值W2為2,第三權重值W3為1,相應用戶之用戶屬性分數則為:n(UA1)*3+n(UA2)*2+n(UA3)*1=|UA1|*3+|UA2|*2+|UA3|*1=19。 For example, suppose the first group of user attributes UA1={a,b,c}, the second group of user attributes UA2={c,d,e}, the third group of user attributes UA3={d,e,f,g }, the first weight value W1 is 3, the second weight value W2 is 2, the third weight value W3 is 1, and the user attribute score of the corresponding user is: n(UA1)*3+n(UA2)*2+n (UA3)*1=|UA1|*3+|UA2|*2+|UA3|*1=19.
在此實施例中,除重複之屬性(元素)將被重複計算分數之 外,出現於不同組之屬性亦有不同之權重。 In this example, attributes (elements) that are not duplicated will be counted twice In addition, attributes appearing in different groups also have different weights.
圖4A繪示第一組用戶屬性UA1(如圖4A中以實線所繪製之圓)與一商品之第一組商品屬性CA1(如圖4A中以虛線所繪製之橢圓)。圖4B繪示第二組用戶屬性UA2(如圖4B中以實線所繪製之圓)與該商品之第一組商品屬性CA1(如圖4B中以虛線所繪製之橢圓)。圖4C繪示第三組用戶屬性UA3(如圖4C中以實線所繪製之圓)與該商品之第一組商品屬性CA1(如圖4C中以虛線所繪製之橢圓)。 FIG. 4A shows the first group of user attributes UA1 (the circle drawn by the solid line in FIG. 4A ) and the first group of product attributes CA1 of a commodity (the ellipse drawn by the dotted line in FIG. 4A ). FIG. 4B shows the second set of user attributes UA2 (circle drawn with a solid line in FIG. 4B ) and the first set of commodity attributes CA1 of the commodity (an ellipse drawn with a dotted line in FIG. 4B ). FIG. 4C shows the third group of user attributes UA3 (circle drawn with a solid line in FIG. 4C ) and the first group of commodity attributes CA1 of the commodity (an ellipse drawn with a dotted line in FIG. 4C ).
基於第一組商品屬性CA1以及第一組用戶屬性UA1而判定該商品之第三組商品屬性CA3。該商品之第三組商品屬性CA3可為第一組商品屬性CA1以及第一組用戶屬性UA1之交集。基於第一組商品屬性CA1以及第二組用戶屬性UA2而判定該商品之第四組商品屬性CA4。該商品之第四組商品屬性CA4可為第一組商品屬性CA1以及第二組用戶屬性UA2之交集。基於第一組商品屬性CA1以及第三組用戶屬性UA3而判定該商品之第五組商品屬性CA5。該商品之第五組商品屬性CA5可為第一組商品屬性CA1以及第三組用戶屬性UA3之交集。 Based on the first group of commodity attributes CA1 and the first group of user attributes UA1, the third group of commodity attributes CA3 of the commodity is determined. The third group of commodity attributes CA3 of the commodity may be the intersection of the first group of commodity attributes CA1 and the first group of user attributes UA1. The fourth group of commodity attributes CA4 of the commodity is determined based on the first group of commodity attributes CA1 and the second group of user attributes UA2. The fourth group of commodity attributes CA4 of the commodity may be the intersection of the first group of commodity attributes CA1 and the second group of user attributes UA2. Based on the first group of commodity attributes CA1 and the third group of user attributes UA3, the fifth group of commodity attributes CA5 of the commodity is determined. The fifth group of commodity attributes CA5 of the commodity may be the intersection of the first group of commodity attributes CA1 and the third group of user attributes UA3.
在圖4A至圖4C之匹配分數之另一種計算方法中,基於第三組商品屬性CA3之屬性個數、第四組商品屬性CA4之屬性個數、第五組商品屬性CA5之屬性個數以及相對應之權重值而判定用戶與該商品之匹配程度。基於第三組商品屬性CA3之屬性個數、第四組商品屬性CA4之屬性個數、第五組商品屬性CA5之屬性個數以及相對應之權重值而判定用戶之用戶屬性分數與該商品之匹配分數。該商品之第三組商品屬性CA3之屬性個數與第一權重值W1之乘積而判定第一商品加權分數;第四組商品屬性CA4之屬性個數與第二權重值W2之乘積而判定第二商品加權分數;以及 第五組商品屬性CA5之屬性個數與第三權重值W3之乘積而判定第三商品加權分數。此用戶之用戶屬性分數與該商品之匹配分數可為第一商品加權分數、第二商品加權分數以及第三商品加權分數之一總和。 In another calculation method of the matching score in FIGS. 4A to 4C , based on the number of attributes of the third group of commodity attributes CA3, the number of attributes of the fourth group of commodity attributes CA4, the number of attributes of the fifth group of commodity attributes CA5 and The corresponding weight value is used to determine the degree of matching between the user and the product. Based on the number of attributes of the third group of commodity attributes CA3, the number of attributes of the fourth group of commodity attributes CA4, the number of attributes of the fifth group of commodity attributes CA5 and the corresponding weight values, determine the user's user attribute score and the value of the product. match score. The product of the product of the number of attributes of the third group of product attributes CA3 and the first weight value W1 determines the first product weighted score; the product of the product of the number of attributes of the fourth group of product attributes CA4 and the second weight value W2 determines the product of the second weight value W2 Two commodity-weighted scores; and The product of the attribute number of the fifth group of commodity attributes CA5 and the third weight value W3 is used to determine the weighted score of the third commodity. The matching score between the user attribute score of the user and the product may be the sum of the first product weighted score, the second product weighted score and the third product weighted score.
舉例而言,當第一組用戶屬性UA1={a,b,c},第二組用戶屬性UA2={c,d,e},第三組用戶屬性UA3={d,e,f,g},第一組商品屬性CA1={a,c,d,e,f}。基於第一組商品屬性CA1以及第一組用戶屬性UA1之交集,第三組商品屬性CA3={a,c}。基於第一組商品屬性CA1以及第二組用戶屬性UA2之交集,第四組商品屬性CA4={c,d,e}。基於第一組商品屬性CA1以及第三組用戶屬性UA3之交集,第五組商品屬性CA5={d,e,f}。第一權重值W1為3,第二權重值W2為2,第三權重值W3為1,相應用戶之用戶屬性分數與該商品之匹配分數則為:n(CA3)*3+n(CA4)*2+n(CA5)*1=|CA3|*3+|CA4|*2+|CA5|*1=15。 For example, when the first group of user attributes UA1={a,b,c}, the second group of user attributes UA2={c,d,e}, and the third group of user attributes UA3={d,e,f,g }, the first group of commodity attributes CA1={a,c,d,e,f}. Based on the intersection of the first group of commodity attributes CA1 and the first group of user attributes UA1, the third group of commodity attributes CA3={a,c}. Based on the intersection of the first set of commodity attributes CA1 and the second set of user attributes UA2, the fourth set of commodity attributes CA4={c,d,e}. Based on the intersection of the first group of commodity attributes CA1 and the third group of user attributes UA3, the fifth group of commodity attributes CA5={d, e, f}. The first weight value W1 is 3, the second weight value W2 is 2, and the third weight value W3 is 1. The matching score between the user attribute score of the corresponding user and the product is: n(CA3)*3+n(CA4) *2+n(CA5)*1=|CA3|*3+|CA4|*2+|CA5|*1=15.
假設操作209中所述之預定比例為80%。用戶屬性分數為19,且匹配分數為15,15小於19*80%,故相應商品將不會被加入相應用戶之商品推薦清單中。
Assume that the predetermined ratio described in
在此實施例中,重複之屬性(元素)將被重複計算分數,出現於不同組之屬性亦有不同之權重。 In this embodiment, repeated attributes (elements) will be scored repeatedly, and attributes appearing in different groups will have different weights.
圖5繪示根據本揭露之一些實施例中用戶屬性分數與匹配分數之計算的示意圖。圖5所揭示之計算方法可由系統100所執行。圖5所揭示之計算方法可由伺服器110之處理模組113或由資料庫120之處理模組123所執行。
FIG. 5 is a schematic diagram illustrating the calculation of user attribute scores and matching scores according to some embodiments of the present disclosure. The calculation method disclosed in FIG. 5 can be executed by the
在圖5之用戶屬性分數之計算方法中,基於第一組用戶屬 性UA1之屬性個數、第二組用戶屬性UA2之屬性個數以及第三組用戶屬性UA3之屬性個數而判定重複不同次數之屬性。 In the calculation method of the user attribute score in Fig. 5, based on the first group of user attribute The attribute number of the characteristic UA1, the attribute number of the second group of user attributes UA2 and the attribute number of the third group of user attributes UA3 are used to determine the attributes that repeat different times.
圖5中繪示第一組用戶屬性UA1(以實線繪制之圓)、第二組用戶屬性UA2(以實線繪制之圓)以及第三組用戶屬性UA3(以實線繪制之圓)。基於第一組用戶屬性UA1、第二組用戶屬性UA2以及第三組用戶屬性UA3之交集而判定第五組用戶屬性UA5。換言之,UA5=UA1∩UA2∩UA3。可藉由將第一組用戶屬性UA1與第二組用戶屬性UA2之交集減去第五組用戶屬性UA5而判定第六組用戶屬性UA6。換言之,UA6=(UA1∩UA2)-UA5。可藉由將第一組用戶屬性UA1與第三組用戶屬性UA3之交集減去第五組用戶屬性UA5而判定第七組用戶屬性。換言之,UA7=(UA1∩UA3)-UA5。可藉由將第二組用戶屬性UA2與第三組用戶屬性UA3之交集減去第五組用戶屬性UA5而判定第八組用戶屬性UA8。換言之,UA8=(UA2∩UA3)-UA5。可藉由將第一組用戶屬性UA1減去第五組用戶屬性UA5、第六組用戶屬性UA6以及第七組用戶屬性UA7之聯集而判定第九組用戶屬性。換言之,UA9=UA1-(UA5∪UA6∪UA7)。可藉由將第二組用戶屬性UA2減去第五組用戶屬性UA5、第六組用戶屬性UA6以及第八組用戶屬性UA8之聯集而判定第十組用戶屬性UA10。換言之,UA10=UA2-(UA5∪UA6∪UA8)。可藉由將第三組用戶屬性UA3減去第五組用戶屬性UA5、第七組用戶屬性UA7以及第八組用戶屬性UA8之聯集而判定第十一組用戶屬性UA11。換言之,UA11=UA3-(UA5∪UA7∪UA8)。 FIG. 5 shows the first group of user attributes UA1 (circle drawn in solid line), the second group of user attributes UA2 (circle drawn in solid line), and the third group of user attributes UA3 (circle drawn in solid line). The fifth group of user attributes UA5 is determined based on the intersection of the first group of user attributes UA1 , the second group of user attributes UA2 and the third group of user attributes UA3 . In other words, UA5=UA1∩UA2∩UA3. The sixth set of user attributes UA6 can be determined by subtracting the fifth set of user attributes UA5 from the intersection of the first set of user attributes UA1 and the second set of user attributes UA2. In other words, UA6=(UA1∩UA2)-UA5. The seventh set of user attributes can be determined by subtracting the fifth set of user attributes UA5 from the intersection of the first set of user attributes UA1 and the third set of user attributes UA3. In other words, UA7=(UA1∩UA3)-UA5. The eighth set of user attributes UA8 can be determined by subtracting the fifth set of user attributes UA5 from the intersection of the second set of user attributes UA2 and the third set of user attributes UA3. In other words, UA8=(UA2∩UA3)-UA5. The ninth set of user attributes can be determined by subtracting the union of the fifth set of user attributes UA5 , the sixth set of user attributes UA6 , and the seventh set of user attributes UA7 from the first set of user attributes UA1 . In other words, UA9=UA1-(UA5∪UA6∪UA7). The tenth group of user attributes UA10 can be determined by subtracting the second group of user attributes UA2 from the union of the fifth group of user attributes UA5 , the sixth group of user attributes UA6 and the eighth group of user attributes UA8 . In other words, UA10=UA2-(UA5∪UA6∪UA8). The eleventh group of user attributes UA11 can be determined by subtracting the third group of user attributes UA3 from the union of the fifth group of user attributes UA5 , the seventh group of user attributes UA7 and the eighth group of user attributes UA8 . In other words, UA11=UA3-(UA5∪UA7∪UA8).
第五組用戶屬性UA5包含在第一組用戶屬性UA1、第二組用戶屬性UA2以及第三組用戶屬性UA3皆有出現之屬性。第六組用戶屬性 UA6包含僅在第一組用戶屬性UA1以及第二組用戶屬性UA2有出現之屬性。第七組用戶屬性UA7包含僅在第一組用戶屬性UA1以及第三組用戶屬性UA3有出現之屬性。第八組用戶屬性UA8包含僅在第二組用戶屬性UA2以及第三組用戶屬性UA3有出現之屬性。第九組用戶屬性UA9包含僅在第一組用戶屬性UA1有出現之屬性。第十組用戶屬性UA10包含僅在第二組用戶屬性UA2有出現之屬性。第十一組用戶屬性UA11包含僅在第三組用戶屬性UA3有出現之屬性。 The fifth group of user attributes UA5 includes attributes that appear in the first group of user attributes UA1 , the second group of user attributes UA2 and the third group of user attributes UA3 . The sixth group of user attributes UA6 contains attributes that appear only in the first set of user attributes UA1 and the second set of user attributes UA2. The seventh group of user attributes UA7 includes attributes that appear only in the first group of user attributes UA1 and the third group of user attributes UA3. The eighth group of user attributes UA8 includes attributes that appear only in the second group of user attributes UA2 and the third group of user attributes UA3. The ninth group of user attributes UA9 contains attributes that appear only in the first group of user attributes UA1. The tenth group of user attributes UA10 contains attributes that appear only in the second group of user attributes UA2. The eleventh group of user attributes UA11 contains attributes that only appear in the third group of user attributes UA3.
可基於第五組用戶屬性UA5之屬性個數與第四權重值W4之乘積而判定第四用戶加權分數。換言之,第四用戶加權分數為n(UA5)*W4或|UA5|*W4。可基於第六組用戶屬性UA6之屬性個數與第五權重值W5之乘積而判定第五用戶加權分數。換言之,第五用戶加權分數為n(UA6)*W5或|UA6|*W5。可基於第七組用戶屬性UA7之屬性個數與第六權重值W6之乘積而判定第六用戶加權分數。換言之,第六用戶加權分數為n(UA7)*W6或|UA7|*W6。可基於第八組用戶屬性UA8之屬性個數與第七權重值之乘積而判定第七用戶加權分數。換言之,第七用戶加權分數為n(UA8)*W7或|UA8|*W7。可基於第九組用戶屬性UA9之屬性個數與第八權重值W8之乘積而判定第八用戶加權分數。換言之,第八用戶加權分數為n(UA9)*W8或|UA9|*W8。可基於第十組用戶屬性UA10之屬性個數與第九權重值W9之乘積而判定第九用戶加權分數。換言之,第九用戶加權分數為n(UA10)*W9或|UA10|*W9。可基於第十一組用戶屬性UA11之屬性個數與第十權重值W10之乘積而判定第十用戶加權分數。換言之,第十用戶加權分數為n(UA11)*W10或|UA11|*W10。 The fourth user weighted score can be determined based on the product of the attribute number of the fifth group of user attributes UA5 and the fourth weight value W4. In other words, the fourth user weighted score is n(UA5)*W4 or |UA5|*W4. The fifth user weighted score can be determined based on the product of the number of attributes in the sixth group of user attributes UA6 and the fifth weight value W5. In other words, the fifth user weighted score is n(UA6)*W5 or |UA6|*W5. The sixth user weighted score can be determined based on the product of the attribute number of the seventh group of user attributes UA7 and the sixth weight value W6. In other words, the sixth user weighted score is n(UA7)*W6 or |UA7|*W6. The seventh user weighted score can be determined based on the product of the number of attributes of the eighth group of user attributes UA8 and the seventh weight value. In other words, the seventh user weighted score is n(UA8)*W7 or |UA8|*W7. The eighth user weighted score can be determined based on the product of the number of attributes in the ninth group of user attributes UA9 and the eighth weight value W8. In other words, the eighth user weighted score is n(UA9)*W8 or |UA9|*W8. The ninth user weighted score can be determined based on the product of the number of attributes of the tenth group of user attributes UA10 and the ninth weight value W9. In other words, the ninth user weighted score is n(UA10)*W9 or |UA10|*W9. The tenth user weighted score can be determined based on the product of the number of attributes of the eleventh group of user attributes UA11 and the tenth weight value W10. In other words, the tenth user weighted score is n(UA11)*W10 or |UA11|*W10.
可基於屬性重複的次數及/或屬性出現在何組用戶屬性(例 如第一組用戶屬性、第二用戶屬性或第三組用戶屬性)而進一步調整第四權重值W4、第五權重值W5、第六權重值W6、第七權重值W7、第八權重值W8、第九權重值W9、第十權重值W10。在一些實施例中,若基於屬性重複的次數而調整權重值,則第四權重值W4可為第一值,第五權重值W5、第六權重值W6及第七權重值W7可為第二值,第八權重值W8、第九權重值W9及第十權重值W10可為第三值,其中第一值、第二值與第三值不相同。 Can be based on the number of times the attribute repeats and/or in which set of user attributes the attribute appears (e.g. Such as the first group of user attributes, the second user attributes or the third group of user attributes) to further adjust the fourth weight value W4, the fifth weight value W5, the sixth weight value W6, the seventh weight value W7, and the eighth weight value W8 , the ninth weight value W9, and the tenth weight value W10. In some embodiments, if the weight value is adjusted based on the number of attribute repetitions, the fourth weight value W4 can be the first value, and the fifth weight value W5, the sixth weight value W6 and the seventh weight value W7 can be the second value. The eighth weight value W8, the ninth weight value W9 and the tenth weight value W10 may be a third value, wherein the first value, the second value and the third value are different.
此用戶之用戶屬性分數可為前述第四用戶加權分數至第十用戶加權分數之總和。 The user attribute score of the user may be the sum of the fourth user weighted score to the tenth user weighted score mentioned above.
舉例而言,假設第一組用戶屬性UA1={a,b,c,g},第二組用戶屬性UA2={a,c,d,e},第三組用戶屬性UA3={c,d,f,g},則第五組用戶屬性UA5={c},第六組用戶屬性UA6={a},第七組用戶屬性UA7={g},第八組用戶屬性UA8={d},第九組用戶屬性UA9={b},第十組用戶屬性UA10={e},第十一組用戶屬性UA11={f}。相應用戶之用戶屬性分數則為:n(UA5)*W4+n(UA6)*W5+n(UA7)*W6+n(UA8)*W7+n(UA9)*W8+n(UA10)*W9+n(UA11)*W10=|UA5|*W4+|UA6|*W5+|UA7|*W6+|UA8|*W7+|UA9|*W8+|UA10|*W9+|UA11|*W10=W4+W5+W6+W7+W8+W9+W10。 For example, suppose the first group of user attributes UA1={a,b,c,g}, the second group of user attributes UA2={a,c,d,e}, the third group of user attributes UA3={c,d ,f,g}, then the fifth group of user attributes UA5={c}, the sixth group of user attributes UA6={a}, the seventh group of user attributes UA7={g}, the eighth group of user attributes UA8={d} , the ninth group of user attributes UA9={b}, the tenth group of user attributes UA10={e}, the eleventh group of user attributes UA11={f}. The user attribute score of the corresponding user is: n(UA5)*W4+n(UA6)*W5+n(UA7)*W6+n(UA8)*W7+n(UA9)*W8+n(UA10)*W9 +n(UA11)*W10=|UA5|*W4+|UA6|*W5+|UA7|*W6+|UA8|*W7+|UA9|*W8+|UA10|*W9+|UA11|*W10=W4+W5+W6+ W7+W8+W9+W10.
可基於一商品之第一組商品屬性CA1與第五組用戶屬性UA5之交集而判定第六組商品屬性CA6。換言之,CA6=CA1∩UA5。可基於第一組商品屬性CA1與第六組用戶屬性UA6之交集而判定第七組商品屬性CA7。換言之,CA7=CA1∩UA6。可基於第一組商品屬性CA1與第 七組用戶屬性UA7之交集而判定第八組商品屬性CA8。換言之,CA8=CA1∩UA7。可基於第一組商品屬性CA1與第八組用戶屬性UA8之交集而判定第九組商品屬性CA9。換言之,CA9=CA1∩UA8。可基於第一組商品屬性CA1與第九組用戶屬性UA9之交集而判定第十組商品屬性CA10。換言之,CA10=CA1∩UA9。可基於第一組商品屬性CA1與第十組用戶屬性UA10之交集而判定第十一組商品屬性CA11。換言之,CA11=CA1∩UA10。可基於第一組商品屬性CA1與第十一組用戶屬性UA11之交集而判定第十二組商品屬性CA12。換言之,CA12=CA1∩UA11。 The sixth group of commodity attributes CA6 can be determined based on the intersection of the first group of commodity attributes CA1 and the fifth group of user attributes UA5 of a commodity. In other words, CA6=CA1∩UA5. The seventh group of commodity attributes CA7 can be determined based on the intersection of the first group of commodity attributes CA1 and the sixth group of user attributes UA6. In other words, CA7=CA1∩UA6. Can be based on the first group of commodity attributes CA1 and the The eighth group of product attributes CA8 is determined by the intersection of the seven groups of user attributes UA7. In other words, CA8=CA1∩UA7. The ninth group of commodity attributes CA9 can be determined based on the intersection of the first group of commodity attributes CA1 and the eighth group of user attributes UA8. In other words, CA9=CA1∩UA8. The tenth group of commodity attributes CA10 can be determined based on the intersection of the first group of commodity attributes CA1 and the ninth group of user attributes UA9. In other words, CA10=CA1∩UA9. The eleventh group of commodity attributes CA11 can be determined based on the intersection of the first group of commodity attributes CA1 and the tenth group of user attributes UA10 . In other words, CA11=CA1∩UA10. The twelfth group of commodity attributes CA12 can be determined based on the intersection of the first group of commodity attributes CA1 and the eleventh group of user attributes UA11 . In other words, CA12=CA1∩UA11.
可基於第六組商品屬性CA6之屬性個數與第四權重值W4之乘積而判定第四商品加權分數。換言之,第四商品加權分數為n(CA6)*W4或|CA6|*W4。可基於第七組商品屬性CA7之屬性個數與第五權重值W5之乘積而判定第五商品加權分數。換言之,第五商品加權分數為n(CA7)*W5或|CA7|*W5。可基於第八組商品屬性CA8之屬性個數與第六權重值W6之乘積而判定第六商品加權分數。換言之,第六商品加權分數為n(CA8)*W6或|CA8|*W6。可基於第九組商品屬性CA9之屬性個數與第七權重值W7之乘積而判定第七商品加權分數。換言之,第七商品加權分數為n(CA9)*W7或|CA9|*W7。可基於第十組商品屬性CA10之屬性個數與第八權重值W8之乘積而判定第八商品加權分數。換言之,第八商品加權分數為n(CA10)*W8或|CA10|*W8。可基於第十一組商品屬性CA11之屬性個數與第九權重值W9之乘積而判定第九商品加權分數。換言之,第九商品加權分數為n(CA11)*W9或|CA11|*W9。可基於第十二組商品屬性CA12之屬性個數與第十權重值W10之乘積而判定第十商品加權分數。 換言之,第十商品加權分數為n(CA12)*W10或|CA12|*W10。 The fourth commodity weighted score can be determined based on the product of the attribute number of the sixth group of commodity attributes CA6 and the fourth weight value W4. In other words, the weighted score of the fourth commodity is n(CA6)*W4 or |CA6|*W4. The fifth commodity weighted score can be determined based on the product of the attribute number of the seventh group of commodity attributes CA7 and the fifth weight value W5. In other words, the weighted score of the fifth commodity is n(CA7)*W5 or |CA7|*W5. The sixth commodity weighted score can be determined based on the product of the number of attributes of the eighth group of commodity attributes CA8 and the sixth weight value W6. In other words, the sixth commodity weighted score is n(CA8)*W6 or |CA8|*W6. The seventh commodity weighted score can be determined based on the product of the number of attributes of the ninth group of commodity attributes CA9 and the seventh weight value W7. In other words, the seventh commodity weighted score is n(CA9)*W7 or |CA9|*W7. The eighth commodity weighted score can be determined based on the product of the number of attributes of the tenth group of commodity attributes CA10 and the eighth weight value W8. In other words, the eighth commodity weighted score is n(CA10)*W8 or |CA10|*W8. The ninth product weighted score can be determined based on the product of the number of attributes of the eleventh group of product attributes CA11 and the ninth weight value W9. In other words, the ninth commodity weighted score is n(CA11)*W9 or |CA11|*W9. The tenth commodity weighted score can be determined based on the product of the attribute number of the twelfth group of commodity attributes CA12 and the tenth weight value W10. In other words, the tenth commodity weighted score is n(CA12)*W10 or |CA12|*W10.
可基於前述第四商品加權分數至第十商品加權分數而判定用戶與該商品之匹配程度。可基於前述第四商品加權分數至第十商品加權分數而判定用戶之用戶屬性分數與該商品之匹配分數。此用戶之用戶屬性分數與該商品之匹配分數可為前述第四商品加權分數至第十商品加權分數之總和。此用戶之用戶屬性分數與該商品之匹配分數可為:n(CA6)*W4+n(CA7)*W5+n(CA8)*W6+n(CA9)*W7+n(CA10)*W8+n(CA11)*W9+n(CA12)*W10=|CA6|*W4+|CA7|*W5+|CA8|*W6+|CA9|*W7+|CA10|*W8+|CA11|*W9+|CA12|*W10。 The degree of matching between the user and the product can be determined based on the aforementioned fourth to tenth product weighted scores. The matching score between the user attribute score of the user and the product may be determined based on the fourth to tenth product weighted scores. The matching score between the user attribute score of the user and the commodity may be the sum of the aforementioned fourth to tenth commodity weighted scores. The user attribute score of this user and the matching score of this product can be: n(CA6)*W4+n(CA7)*W5+n(CA8)*W6+n(CA9)*W7+n(CA10)*W8+ n(CA11)*W9+n(CA12)*W10=|CA6|*W4+|CA7|*W5+|CA8|*W6+|CA9|*W7+|CA10|*W8+|CA11|*W9+|CA12|*W10.
圖6A及圖6B繪示根據本揭露之一些實施例中用戶屬性分數與匹配分數之計算的示意圖。圖6A及圖6B所揭示之計算方法可由系統100所執行。圖5所揭示之計算方法可由伺服器110之處理模組113或由資料庫120之處理模組123所執行。
6A and 6B are schematic diagrams illustrating the calculation of user attribute scores and matching scores according to some embodiments of the present disclosure. The calculation method disclosed in FIG. 6A and FIG. 6B can be implemented by the
在圖6A及圖6B之用戶屬性分數之計算方法中,用戶之用戶屬性分分可進一步包含第一用戶屬性分數、第二用戶屬性分數以及第三用戶屬性分數。可基於第一組用戶屬性UA1而判定第一用戶屬性分數。可基於第二組用戶屬性UA2而判定第二用戶屬性分數。可基於第三組用戶屬性UA3而判定第三用戶屬性分數。 In the calculation method of the user attribute score in FIG. 6A and FIG. 6B , the user attribute score of the user may further include a first user attribute score, a second user attribute score and a third user attribute score. The first user attribute score may be determined based on the first set of user attributes UA1. A second user attribute score may be determined based on the second set of user attributes UA2. A third user attribute score may be determined based on a third set of user attributes UA3.
舉例而言,可基於第一組用戶屬性UA1之屬性個數、第二組用戶屬性UA2之屬性個數以及第三組用戶屬性UA3之屬性個數而分別判定用戶之第一用戶屬性分數、第二用戶屬性分數以及第三用戶屬性分數。可基於第一組用戶屬性UA1之屬性個數而判定第一用戶屬性分數;可基於第二組用戶屬性UA2之屬性個數而判定第二用戶屬性分數;以及可基於第 三組用戶屬性UA3之屬性個數而判定第三用戶屬性分數。 For example, based on the number of attributes of the first group of user attributes UA1, the number of attributes of the second group of user attributes UA2, and the number of attributes of the third group of user attributes UA3, the first user attribute score, the second Two user attribute scores and a third user attribute score. The first user attribute score may be determined based on the number of attributes of the first group of user attributes UA1; the second user attribute score may be determined based on the number of attributes of the second group of user attributes UA2; and the second user attribute score may be determined based on the second group of user attributes UA2 The attribute numbers of the three groups of user attributes UA3 are used to determine the third user attribute score.
在一些實施例中,第一組用戶屬性UA1={a,b,c},第二組用戶屬性UA2={c,d,e},第三組用戶屬性UA3={d,e,f,g}。如圖6A所示之實施例,第一用戶屬性分數US1=n(UA1)=|UA1|=3;第二用戶屬性分數US2=n(UA2)=|UA2|=3;第三用戶屬性分數US3=n(UA3)=|UA3|=4。 In some embodiments, the first set of user attributes UA1={a,b,c}, the second set of user attributes UA2={c,d,e}, the third set of user attributes UA3={d,e,f, g}. In the embodiment shown in Figure 6A, the first user attribute score US1=n(UA1)=|UA1|=3; the second user attribute score US2=n(UA2)=|UA2|=3; the third user attribute score US3=n(UA3)=|UA3|=4.
在一些實施例中,可基於第一組用戶屬性UA1之屬性個數、第二組用戶屬性UA2之屬性個數、第三組用戶屬性UA3之屬性個數以及相應權重值而分別判定用戶之第一用戶屬性分數、第二用戶屬性分數以及第三用戶屬性分數。可基於第一組用戶屬性UA1之屬性個數與第一權重值W1之乘積而判定第一用戶屬性分數;可基於第二組用戶屬性UA2之屬性個數與第二權重值W2之乘積而判定第二用戶屬性分數;以及可基於第三組用戶屬性UA3之屬性個數與第三權重值W3之乘積而判定第三用戶屬性分數。 In some embodiments, the number of user attributes in the first group of user attributes UA1, the number of attributes in the second group of user attributes UA2, the number of attributes in the third group of user attributes UA3 and the corresponding weight values can be used to determine the user's second A user attribute score, a second user attribute score and a third user attribute score. The first user attribute score can be determined based on the product of the number of attributes in the first group of user attributes UA1 and the first weight value W1; it can be determined based on the product of the number of attributes in the second group of user attributes UA2 and the second weight value W2 The second user attribute score; and the third user attribute score can be determined based on the product of the attribute number of the third group of user attributes UA3 and the third weight value W3.
在一些實施例中,第一組用戶屬性UA1={a,b,c},第二組用戶屬性UA2={c,d,e},第三組用戶屬性UA3={d,e,f,g},第一權重值W1為3,第二權重值W2為2,第三權重值W3為1。如圖6B所示之實施例,第一用戶屬性分數US1=n(UA1)*3=|UA1|*3=9;第二用戶屬性分數US2=n(UA2)*2=|UA2|*2=6;第三用戶屬性分數US3=n(UA3)*1=|UA3|*1=4。 In some embodiments, the first set of user attributes UA1={a,b,c}, the second set of user attributes UA2={c,d,e}, the third set of user attributes UA3={d,e,f, g}, the first weight value W1 is 3, the second weight value W2 is 2, and the third weight value W3 is 1. In the embodiment shown in Figure 6B, the first user attribute score US1=n(UA1)*3=|UA1|*3=9; the second user attribute score US2=n(UA2)*2=|UA2|*2 =6; the third user attribute score US3=n(UA3)*1=|UA3|*1=4.
在圖6A及圖6B之匹配分數之計算方法中,匹配分數可進一步包含第一匹配分數、第二匹配分數以及第三匹配分數。可基於第一組用戶屬性UA1與一商品之第一組商品屬性CA1而判定第一匹配分數。可基於第二組用戶屬性UA2與第一組商品屬性CA1而判定第二匹配分數。可基 於第三組用戶屬性UA3與第一組商品屬性CA1而判定第三匹配分數。 In the calculation method of the matching score in FIG. 6A and FIG. 6B , the matching score may further include a first matching score, a second matching score and a third matching score. The first matching score can be determined based on the first set of user attributes UA1 and the first set of commodity attributes CA1 of a commodity. The second matching score may be determined based on the second set of user attributes UA2 and the first set of commodity attributes CA1. Keji A third matching score is determined based on the third group of user attributes UA3 and the first group of commodity attributes CA1.
舉例而言,可基於第一組商品屬性CA1以及第一組用戶屬性UA1之交集而判定該商品之第三組商品屬性CA3。換言之,CA3=CA1∩UA1。可基於第一組商品屬性CA1以及第二組用戶屬性UA2之交集而判定該商品之第四組商品屬性CA4。換言之,CA4=CA1∩UA2。可基於第一組商品屬性CA1以及第三組用戶屬性UA3之交集而判定該商品之第五組商品屬性CA5。換言之,CA5=CA1∩UA3。 For example, the third group of commodity attributes CA3 of the commodity can be determined based on the intersection of the first group of commodity attributes CA1 and the first group of user attributes UA1 . In other words, CA3=CA1∩UA1. The fourth group of commodity attributes CA4 of the commodity can be determined based on the intersection of the first group of commodity attributes CA1 and the second group of user attributes UA2. In other words, CA4=CA1∩UA2. The fifth group of commodity attributes CA5 of the commodity can be determined based on the intersection of the first group of commodity attributes CA1 and the third group of user attributes UA3. In other words, CA5=CA1∩UA3.
在一些實施例中,可基於第三組商品屬性CA3之屬性個數、第四組商品屬性CA4之屬性個數以及第五組商品屬性CA5之屬性個數而分別判定用戶之第一匹配分數、第二匹配分數以及第三匹配分數。可基於第三組商品屬性CA3之屬性個數而判定第一匹配分數;可基於第四組商品屬性CA4之屬性個數而判定第二匹配分數;以及可基於第五組商品屬性CA5之屬性個數而判定第三匹配分數。 In some embodiments, the user's first matching score, A second matching score and a third matching score. The first matching score can be determined based on the number of attributes of the third group of commodity attributes CA3; the second matching score can be determined based on the number of attributes of the fourth group of commodity attributes CA4; and the number of attributes of the fifth group of commodity attributes CA5 can be determined. count to determine a third matching score.
在一些實施例中,第一組用戶屬性UA1={a,b,c},第二組用戶屬性UA2={c,d,e},第三組用戶屬性UA3={d,e,f,g},第一組商品屬性CA1={a,c,d,e,f}。基於第一組商品屬性CA1以及第一組用戶屬性UA1之交集,第三組商品屬性CA3=CA1∩UA1={a,c}。基於第一組商品屬性CA1以及第二組用戶屬性UA2之交集,第四組商品屬性CA4=CA1∩UA2={c,d,e}。基於第一組商品屬性CA1以及第三組用戶屬性UA3之交集,第五組商品屬性CA5=CA1∩UA3={d,e,f}。如圖6A所示之實施例,第一匹配分數MS1=n(CA3)=|CA3|=2;第二匹配分數MS2=n(CA4)=|CA4|=3;第三匹配分數MS3=n(CA5)=|CA5|=3。 In some embodiments, the first set of user attributes UA1={a,b,c}, the second set of user attributes UA2={c,d,e}, the third set of user attributes UA3={d,e,f, g}, the first group of commodity attributes CA1={a, c, d, e, f}. Based on the intersection of the first group of commodity attributes CA1 and the first group of user attributes UA1, the third group of commodity attributes CA3=CA1∩UA1={a,c}. Based on the intersection of the first group of commodity attributes CA1 and the second group of user attributes UA2, the fourth group of commodity attributes CA4=CA1∩UA2={c,d,e}. Based on the intersection of the first group of commodity attributes CA1 and the third group of user attributes UA3, the fifth group of commodity attributes CA5=CA1∩UA3={d,e,f}. In the embodiment shown in Figure 6A, the first matching score MS1=n(CA3)=|CA3|=2; the second matching score MS2=n(CA4)=|CA4|=3; the third matching score MS3=n (CA5)=|CA5|=3.
在一些實施例中,可基於第三組商品屬性CA3之屬性個數、第四組商品屬性CA4之屬性個數、第五組商品屬性CA5之屬性個數以及相應權重值而分別判定用戶之第一匹配分數、第二匹配分數以及第三匹配分數。可基於第三組商品屬性CA3之屬性個數與第一權重值W1之乘積而判定第一用戶屬性分數;可基於第四組商品屬性CA4之屬性個數與第二權重值W2之乘積而判定第二用戶屬性分數;以及可基於第五組商品屬性CA5之屬性個數與第三權重值W3之乘積而判定第三用戶屬性分數。 In some embodiments, the number of attributes of the third group of commodity attributes CA3, the number of attributes of the fourth group of commodity attributes CA4, the number of attributes of the fifth group of commodity attributes CA5 and the corresponding weight values can be used to determine the user's first A match score, a second match score and a third match score. The first user attribute score can be determined based on the product of the number of attributes in the third group of commodity attributes CA3 and the first weight value W1; it can be determined based on the product of the number of attributes in the fourth group of commodity attributes CA4 and the second weight value W2 The second user attribute score; and the third user attribute score can be determined based on the product of the attribute number of the fifth group of product attributes CA5 and the third weight value W3.
在一些實施例中,第一組用戶屬性UA1={a,b,c},第二組用戶屬性UA2={c,d,e},第三組用戶屬性UA3={d,e,f,g},第一組商品屬性CA1={a,c,d,e,f},第一權重值W1為3,第二權重值W2為2,第三權重值W3為1。第三組商品屬性CA3=CA1∩UA1={a,c}。第四組商品屬性CA4=CA1∩UA2={c,d,e}。第五組商品屬性CA5=CA1∩UA3={d,e,f}。如圖6B所示之實施例,第一匹配分數可為MS1=n(CA3)*3=|CA3|*3=6;第二匹配分數可為MS2=n(CA4)*2=|CA4|*2=6;第三匹配分數可為MS3=n(CA5)*1=|CA5|*1=3。 In some embodiments, the first set of user attributes UA1={a,b,c}, the second set of user attributes UA2={c,d,e}, the third set of user attributes UA3={d,e,f, g}, the first group of commodity attributes CA1={a,c,d,e,f}, the first weight value W1 is 3, the second weight value W2 is 2, and the third weight value W3 is 1. The third group of commodity attributes CA3=CA1∩UA1={a,c}. The fourth group of commodity attributes CA4=CA1∩UA2={c,d,e}. The fifth group of commodity attributes CA5=CA1∩UA3={d,e,f}. In the embodiment shown in Figure 6B, the first matching score can be MS1=n(CA3)*3=|CA3|*3=6; the second matching score can be MS2=n(CA4)*2=|CA4| *2=6; the third matching score may be MS3=n(CA5)*1=|CA5|*1=3.
可基於第一匹配分數是否大於或等於第一用戶屬性分數之第一預定比例、第二匹配分數是否大於或等於第二用戶屬性分數之第二預定比例以及第三匹配分數是否大於或等於第三用戶屬性分數之第三預定比例等事件而判定是否將相應商品加入至相應用戶之商品推薦清單中。 may be based on whether the first matching score is greater than or equal to a first predetermined proportion of the first user attribute score, whether the second matching score is greater than or equal to a second predetermined proportion of the second user attribute score, and whether the third matching score is greater than or equal to a third Determine whether to add the corresponding product to the product recommendation list of the corresponding user based on events such as the third predetermined ratio of the user attribute score.
舉例而言,可回應於(1)第一匹配分數是否大於或等於第一用戶屬性分數之第一預定比例、(2)第二匹配分數是否大於或等於第二用戶屬性分數之第二預定比例以及(3)第三匹配分數是否大於或等於第三用戶屬性分數之第三預定比例之三事件中至少一者為真,而將相應商品加入 至相應用戶之商品推薦清單中。可回應於(1)第一匹配分數是否大於或等於第一用戶屬性分數之第一預定比例、(2)第二匹配分數是否大於或等於第二用戶屬性分數之第二預定比例以及(3)第三匹配分數是否大於或等於第三用戶屬性分數之第三預定比例之三事件中至少兩者為真,而將相應商品加入至相應用戶之商品推薦清單中。可回應於(1)第一匹配分數是否大於或等於第一用戶屬性分數之第一預定比例、(2)第二匹配分數是否大於或等於第二用戶屬性分數之第二預定比例以及(3)第三匹配分數是否大於或等於第三用戶屬性分數之第三預定比例之三事件中三者為真,而將相應商品加入至相應用戶之商品推薦清單中。 For example, it may respond to (1) whether the first matching score is greater than or equal to a first predetermined proportion of the first user attribute score, (2) whether the second matching score is greater than or equal to a second predetermined proportion of the second user attribute score And (3) whether at least one of the three events of the third predetermined proportion of the third matching score is greater than or equal to the third user attribute score is true, and the corresponding product is added to to the product recommendation list of the corresponding user. Responsive to (1) whether the first match score is greater than or equal to a first predetermined proportion of the first user attribute score, (2) whether the second match score is greater than or equal to a second predetermined proportion of the second user attribute score, and (3) At least two of the three events of whether the third matching score is greater than or equal to the third predetermined proportion of the third user attribute score are true, and the corresponding product is added to the product recommendation list of the corresponding user. Responsive to (1) whether the first match score is greater than or equal to a first predetermined proportion of the first user attribute score, (2) whether the second match score is greater than or equal to a second predetermined proportion of the second user attribute score, and (3) Whether the third matching score is greater than or equal to the third predetermined proportion of the third user attribute score is true, and the corresponding product is added to the product recommendation list of the corresponding user.
第一預定比例、第二預定比例以及第三預定比例之各者可設定為60%至90%之間,被推薦之商品之範圍較不受限制。因為被推薦之商品之範圍較不受限制,可有效降低用戶因大量瀏覽類似商品所產生之疲勞感,並可提高被推薦之商品被購買之機率。前述第一預定比例、第二預定比例以及第三預定比例可基於不同組用戶屬性之重要性而調整為不同的數值。舉例而言,若第一組用戶屬性對於推薦商品較為重要,則可將第一預定比例設定為小於第二預定比例以及第三預定。在某些實施例中,第一預定比例、第二預定比例以及第三預定比例可為相同之數值。 Each of the first predetermined ratio, the second predetermined ratio and the third predetermined ratio can be set between 60% and 90%, and the range of recommended products is relatively unlimited. Because the range of recommended products is relatively unlimited, it can effectively reduce the user's fatigue caused by browsing a large number of similar products, and can increase the probability of the recommended products being purchased. The aforementioned first predetermined ratio, second predetermined ratio and third predetermined ratio can be adjusted to different values based on the importance of different groups of user attributes. For example, if the first group of user attributes is more important for recommending commodities, the first predetermined proportion can be set to be smaller than the second predetermined proportion and the third predetermined proportion. In some embodiments, the first predetermined ratio, the second predetermined ratio and the third predetermined ratio may be the same value.
在一些實施例中,第一預定比例、第二預定比例以及第三預定比例之各者為80%,且回應於(1)第一匹配分數是否大於或等於第一用戶屬性分數之第一預定比例、(2)第二匹配分數是否大於或等於第二用戶屬性分數之第二預定比例以及(3)第三匹配分數是否大於或等於第三用戶屬性分數之第三預定比例之三事件中至少一者為真,而將相應商品加入至相應用戶之商品推薦清單中。如圖6A所示之實施例, ,故相應商品將加入至相應用戶之商品推薦清單中。如圖6B所示之實施例,,故相應商品將加入至相應用戶之商品推薦清單中。 In some embodiments, each of the first predetermined ratio, the second predetermined ratio, and the third predetermined ratio is 80%, and the first predetermined ratio is responsive to (1) whether the first matching score is greater than or equal to the first user attribute score. ratio, (2) whether the second matching score is greater than or equal to a second predetermined proportion of the second user attribute score, and (3) whether the third matching score is greater than or equal to a third predetermined proportion of the third user attribute score at least If one is true, the corresponding product is added to the product recommendation list of the corresponding user. The embodiment shown in Figure 6A, , so the corresponding product will be added to the product recommendation list of the corresponding user. The embodiment shown in Figure 6B, , so the corresponding product will be added to the product recommendation list of the corresponding user.
在一些實施例中,伺服器110之處理模組113或資料庫120之處理模組123可判定包含某一商品之商品推薦清單的個數。當包含某一商品之商品推薦清單的個數大於或等於第一臨限值,則可向伺服器110或資料庫120請求該項商品之目前庫存數目。在某些實施例中,可判定商品推薦清單包含某一商品之用戶個數。當商品推薦清單包含某一商品之用戶個數大於或等於第一臨限值,則可向伺服器110或資料庫120請求該項商品之目前庫存數目。
In some embodiments, the
根據所接收到的該商品之庫存數目,伺服器110之處理模組113或資料庫120之處理模組123可進一步判定該商品之庫存數目是否小於或等於第二臨限值。若該商品之庫存數目是否小於或等於第二臨限值,則可傳送指示增加該商品之庫存的信號。當管理人員收到指示增加該商品之庫存的信號,則可先進行補貨,以避免商品銷售一空。在某些實施例中,若補貨之程序較為繁複(例如需以代購方法進行補貨),則可設定較小之第一臨限值以及較大之第二臨限值,以避免商品銷售一空。
According to the received stock quantity of the commodity, the
雖然已參考本揭露之具體實施例描述及說明本創作,但此等描述及說明並不限制本創作。熟習此項技術者應理解,在不脫離如由隨附申請專利範圍界定的本創作之真實精神及範圍的情況下,可作出各種改變且可取代等效物。說明可不必按比例繪製。歸因於製造製程及公差,本申請中之藝術再現與實際創作中之藝術再現之間可存在區別。可存在並未特定說明的本創作之其他實施例。應將本說明書及圖式視為說明性而非限 制性的。可作出修改,以使特定情況、材料、物質之組成、方法或製程適應於本創作之目標、精神及範圍。所有此類修改意欲在此處附加之申請專利範圍之範圍內。雖然已參考按特定次序執行之特定操作描述本文中所揭示的方法,但將理解,在不脫離本創作之教示的情況下,可組合、再細分或重新定序此等操作以形成等效方法。因此,除非本文中另外特定地指示,否則操作之次序及分組並非本創作之限制。此外,在上述實施例及其類似者中詳述之效果僅為實例。因此,本申請可進一步具有其他效果。 While the invention has been described and illustrated with reference to specific embodiments of the present disclosure, such description and illustration do not limit the invention. It should be understood by those skilled in the art that various changes may be made and equivalents may be substituted without departing from the true spirit and scope of the invention as defined by the appended claims. Illustrations may not necessarily be drawn to scale. Due to manufacturing processes and tolerances, differences may exist between the art reproductions in this application and those in actual creation. There may be other embodiments of the invention not specifically described. This specification and drawings should be regarded as illustrative and not limiting Mandatory. Modifications may be made to adapt a particular situation, material, composition of matter, method or process to the aim, spirit and scope of the creation. All such modifications are intended to be within the scope of the claims appended hereto. Although the methods disclosed herein have been described with reference to particular operations performed in a particular order, it will be understood that such operations may be combined, subdivided, or reordered to form equivalent methods without departing from the teachings of the present invention. . Thus, unless specifically indicated otherwise herein, the order and grouping of operations is not a limitation of the invention. In addition, the effects detailed in the above-mentioned embodiments and the like are merely examples. Therefore, the present application can further have other effects.
另外,圖中所繪示之邏輯流程未必需要所展示之特定次序或順序次序來實現合意結果。另外,可提供其他步驟,或可自所闡述流程消除若干步驟,且可向所闡述系統添加或自所闡述系統移除其他組件。因此,其他實施例皆在所附申請專利範圍之範疇內。 In addition, the logic flows depicted in the figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In addition, other steps may be provided, or steps may be eliminated, from the described flows, and other components may be added to or removed from the described systems. Therefore, other embodiments are within the scope of the attached claims.
100:系統 100: system
110:伺服器 110: server
111:輸入輸出模組 111: Input and output module
112:記憶模組 112: memory module
113:處理模組 113: Processing module
114:通信模組 114: Communication module
120:資料庫 120: database
121:輸入輸出模組 121: Input and output module
122:記憶模組 122: memory module
123:處理模組 123: Processing module
124:通信模組 124: Communication module
130:用戶裝置 130: user device
131:輸入輸出模組 131: Input and output module
132:記憶模組 132: memory module
133:處理模組 133: Processing module
134:通信模組 134:Communication module
Claims (10)
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW111204495U TWM634368U (en) | 2022-04-29 | 2022-04-29 | Electronic device for processing commodity recommendation lists |
CN202210618323.1A CN117057863A (en) | 2022-04-29 | 2022-06-01 | Method for recommending commodity and related electronic device thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW111204495U TWM634368U (en) | 2022-04-29 | 2022-04-29 | Electronic device for processing commodity recommendation lists |
Publications (1)
Publication Number | Publication Date |
---|---|
TWM634368U true TWM634368U (en) | 2022-11-21 |
Family
ID=85784780
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW111204495U TWM634368U (en) | 2022-04-29 | 2022-04-29 | Electronic device for processing commodity recommendation lists |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN117057863A (en) |
TW (1) | TWM634368U (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI827029B (en) * | 2022-04-29 | 2023-12-21 | 台灣伽瑪移動數位股份有限公司 | Method for recommending commodities and the related electronic device |
-
2022
- 2022-04-29 TW TW111204495U patent/TWM634368U/en unknown
- 2022-06-01 CN CN202210618323.1A patent/CN117057863A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI827029B (en) * | 2022-04-29 | 2023-12-21 | 台灣伽瑪移動數位股份有限公司 | Method for recommending commodities and the related electronic device |
Also Published As
Publication number | Publication date |
---|---|
CN117057863A (en) | 2023-11-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110580649B (en) | Method and device for determining commodity potential value | |
CN109308652A (en) | Wholesale method, system, terminal device and storage medium on line | |
CN109767302B (en) | Method and device for constructing big data accurate model | |
JP6976207B2 (en) | Information processing equipment, information processing methods, and programs | |
CN110956495A (en) | Electronic mall shopping method, server and storage medium | |
JP2023044483A (en) | Information processing device, information processing method, and information processing program | |
EP4270292A1 (en) | Method for recommending commodities and the related electronic device | |
JP6906667B1 (en) | Information processing equipment, information processing methods and information processing programs | |
TWM634368U (en) | Electronic device for processing commodity recommendation lists | |
JP2018045505A (en) | Determination device, determination method, and determination program | |
JP6397092B1 (en) | Distribution apparatus, distribution method, and distribution program | |
CN105913276A (en) | Price error-proofing method based on SKU | |
JP6329293B1 (en) | Article purchase method and article purchase system | |
JP2020013447A (en) | Determination device, determination method, and determination program | |
CN112651805A (en) | Commodity recommendation method and system for online shopping mall | |
CN115170221A (en) | Commodity information aggregation method and device and electronic equipment | |
CN108320185A (en) | A kind of non-oil product of petrol station recommends method, apparatus and readable storage medium storing program for executing | |
JP7453120B2 (en) | Selection device, selection method and selection program | |
JP7087181B1 (en) | Information processing equipment, information processing methods and information processing programs | |
JP7089100B1 (en) | Information processing equipment, information processing methods and information processing programs | |
JP7342168B2 (en) | Information processing device, information processing method, and information processing program | |
CN113763103B (en) | Method and device for determining item collocation relation, electronic equipment and storage medium | |
JP7087179B1 (en) | Information processing equipment, information processing methods and information processing programs | |
JP7176075B1 (en) | Information processing device, information processing method and information processing program | |
US20230410182A1 (en) | Systems and methods handling mobile technology communications |