TWI726981B - Screening method and equipment for information delivery users - Google Patents
Screening method and equipment for information delivery users Download PDFInfo
- Publication number
- TWI726981B TWI726981B TW106102468A TW106102468A TWI726981B TW I726981 B TWI726981 B TW I726981B TW 106102468 A TW106102468 A TW 106102468A TW 106102468 A TW106102468 A TW 106102468A TW I726981 B TWI726981 B TW I726981B
- Authority
- TW
- Taiwan
- Prior art keywords
- user
- information
- behavior data
- delivery
- preset
- Prior art date
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
本發明公開了一種資訊投放用戶的篩選方法,所述方法包括:伺服器獲取用戶的行為資料;所述伺服器判斷所述用戶的行為資料是否滿足預設的行為標準;如果滿足,所述伺服器根據預設的行為資料得分確定所述用戶的綜合得分;所述伺服器根據所述用戶綜合得分和其他用戶的綜合得分確定資訊向各個用戶的投放順序;所述伺服器根據資訊的投放種類和預設的投放策略按照所述投放順序向所述用戶投放所述資訊。本發明可對潛在用戶實現精確定位,從而實現資訊投放的命中率。 The present invention discloses a method for screening information delivery users. The method includes: a server obtains user behavior data; the server determines whether the user behavior data meets a preset behavior standard; if so, the server The server determines the comprehensive score of the user according to the preset behavioral data score; the server determines the order in which information is delivered to each user based on the comprehensive score of the user and the comprehensive scores of other users; the server determines the delivery order of the information to each user according to the type of delivery of the information And the preset delivery strategy delivers the information to the user according to the delivery sequence. The invention can realize precise positioning of potential users, thereby realizing the hit rate of information delivery.
Description
本發明涉及電子商務領域,特別是涉及一種資訊投放用戶的篩選方法和設備。 The present invention relates to the field of e-commerce, in particular to a method and equipment for screening users of information delivery.
近年來隨著電子商務的快速發展,越來越多的商家選擇在網上開店。為了吸引買家,提高銷量,很多賣家都會通過發放優惠券的方式來刺激買家在自己的店鋪購買商品。賣家發放優惠券一般採用兩種方法,一是對已經在本店鋪購買過商品的老客戶主動發放。由於賣家已經掌握了老客戶的網購帳號及手機號碼,因而可以直接將優惠券發放到老客戶的帳戶中並短信通知;二是直接將優惠券放在網上店鋪顯眼位置,由進入店鋪的買家主動領取,當買家需要購買店鋪商品時直接抵扣使用。 With the rapid development of e-commerce in recent years, more and more businesses choose to open stores online. In order to attract buyers and increase sales, many sellers will issue coupons to stimulate buyers to buy goods in their stores. Sellers generally use two methods to issue coupons. One is to proactively issue them to old customers who have already purchased goods in this store. Since the seller has mastered the online shopping account and mobile phone number of the old customer, he can directly issue the coupon to the old customer’s account and notify by text message; the second is to directly place the coupon in a prominent position of the online store, and then buy the coupon from the store. The home takes the initiative to receive it, and it is directly deducted when the buyer needs to purchase the goods in the store.
這兩種由賣家自身發起的優惠券發放方法均有明顯缺陷。對於第一種方法,很多店鋪的商品往往購買了一次之後短時間內不會再購買第二次,例如大件商品,或者電子類產品,因而對老客戶發放之後優惠券的使用率極低;而第二種方法沒有對進入店鋪的用戶進行細分,所有買家均 可以領取,領取後的利用率亦很低。 Both of these two methods of issuing coupons initiated by the seller themselves have obvious flaws. For the first method, many stores often buy goods once and will not buy them again within a short period of time, such as large-sized goods or electronic products, so the use rate of coupons after the issuance of old customers is extremely low; The second method does not segment the users who enter the store. All buyers are It can be received, and the utilization rate after receiving it is also very low.
針對上述問題現有技術提出了一種解決方案,所述方案中包括,參數配置模組、接收模組和商品頁文件產生模組。 The prior art proposes a solution to the above-mentioned problems. The solution includes a parameter configuration module, a receiving module, and a product page file generation module.
參數配置用於根據配置的活動範圍控制參數和活動資訊展示控制參數產生用於向特定商戶展示優惠券活動的活動頁文件。其中,所述活動範圍控制參數用於配置參與優惠券活動的商品類目,所述活動資訊展示控制參數用於配置參與優惠券活動的商戶。可以以資料庫表的形式儲存各個商戶所對應的活動資訊展示控制參數。通過配置該活動資訊展示控制參數,可以將商戶設置為可參與優惠券活動和不可參與優惠券活動,對於不可參與優惠券活動的商戶,不產生所述活動頁文件。 The parameter configuration is used to generate an activity page file for displaying coupon activities to specific merchants according to the configured activity range control parameters and activity information display control parameters. Wherein, the activity range control parameter is used to configure the product category participating in the coupon activity, and the activity information display control parameter is used to configure the merchant participating in the coupon activity. The activity information display control parameters corresponding to each merchant can be stored in the form of a database table. By configuring the event information display control parameters, merchants can be set to be able to participate in coupon activities and not to participate in coupon activities, and for merchants that cannot participate in coupon activities, the activity page file is not generated.
接收模組用於接收所述特定商戶中的商戶提交的活動請求。 The receiving module is used for receiving activity requests submitted by merchants in the specific merchants.
商品頁文件產生模組用於為提交活動請求的商戶中滿足審核規則的商品產生商品頁文件,所述商品頁文件包括參加優惠券活動的商品資訊及優惠券活動資訊。為白名單中的商戶產生所述商品頁文件,所述白名單為預先設定的滿足所述審核規則的商戶名單。 The product page file generation module is used to generate a product page file for the products that meet the review rules in the merchant that submits the activity request, and the product page file includes the product information for participating in the coupon activity and the coupon activity information. The product page file is generated for the merchants in the whitelist, and the whitelist is a preset list of merchants that meet the review rules.
在實現現有技術的過程,申請人發現現有技術至少存在以下問題:現有技術中未對消費者的日常行為資料進行分析,不能精確劃分出對店鋪優惠券感興趣的用戶,且是手動設置 參數,不僅不夠智慧,並且工作量較大,同時,以白名單的方式確定滿足規定的用戶會使用戶發生變化時操作不夠靈活。 In the process of implementing the prior art, the applicant found that the prior art has at least the following problems: the prior art does not analyze the daily behavior data of consumers, cannot accurately classify users who are interested in store coupons, and is manually set The parameters are not only not smart enough, but also a lot of work. At the same time, determining the users who meet the requirements by means of a whitelist will make the operation not flexible enough when the user changes.
本發明的目的在於提供一種資訊投放用戶的篩選方法和設備,通過分析用戶的行為資料來確定出需要投放資訊的潛在用戶,不僅可以實現潛在用戶的精准定位,還提高了資訊投放的命中率。 The purpose of the present invention is to provide a method and equipment for screening information delivery users, which can determine potential users who need to deliver information by analyzing user behavior data, which can not only achieve accurate positioning of potential users, but also improve the hit rate of information delivery.
本發明的技術方案如下:一種資訊投放用戶的篩選方法,所述方法包括:伺服器獲取用戶的行為資料;所述伺服器判斷所述用戶的行為資料是否滿足預設的行為標準;如果滿足,所述伺服器根據預設的行為資料得分確定所述用戶的綜合得分;所述伺服器根據所述用戶綜合得分和其他用戶的綜合得分確定資訊向各個用戶的投放順序;所述伺服器根據資訊的投放種類和預設的投放策略按照所述投放順序向所述用戶投放所述資訊。 The technical solution of the present invention is as follows: a method for screening information delivery users, the method includes: a server obtains user behavior data; the server determines whether the user behavior data meets a preset behavior standard; if it meets, The server determines the user's comprehensive score according to preset behavior data scores; the server determines the order in which information is delivered to each user based on the user's comprehensive score and the comprehensive scores of other users; the server determines the order in which information is delivered to each user based on the information The delivery type and the preset delivery strategy of delivering the information to the user according to the delivery sequence.
所述行為資料包括以下的一種或多種的任意組合:對目標對象的瀏覽次數、對目標對象的收藏情況、對目標對象的檢索情況、行業偏好和歷史購買資訊。 The behavior data includes any combination of one or more of the following: the number of times to browse the target object, the collection status of the target object, the retrieval status of the target object, industry preference and historical purchase information.
所述伺服器判斷所述用戶行為資料是否滿足預設的行 為標準,具體為:當所述行為資料為對目標對象的瀏覽次數時,所述伺服器判斷第一預設時間內所述用戶瀏覽所述目標對象的次數是否超過瀏覽閾值;當所述行為資料為對目標對象的收藏情況時,所述伺服器判斷第二預設時間內所述用戶是否收藏過所述目標對象;當所述行為資料為對目標對象的檢索次數時,所述伺服器判斷第三預設時間內所述用戶檢索所述目標對象的次數是否超過檢索閾值;當所述行為資料為行業偏好時,所述伺服器統計第四預設時間內所述用戶的行業偏好,判斷所述用戶的行業偏好是否與所述目標對象的所屬行業相匹配;當所述行為資料為購物資訊時,所述伺服器統計第五預設時間內所述用戶的購物資訊,判斷所述用戶的購物資訊是否與所述目標對象有關聯。 The server determines whether the user behavior data meets the preset behavior Is a standard, specifically: when the behavior data is the number of times the target object is browsed, the server determines whether the number of times the user browses the target object within the first preset time exceeds the browsing threshold; when the behavior When the data is the collection of the target object, the server determines whether the user has collected the target object within the second preset time; when the behavior data is the number of times the target object is retrieved, the server Determining whether the number of times the user retrieves the target object within the third preset time exceeds a retrieval threshold; when the behavior data is an industry preference, the server counts the user's industry preference within the fourth preset time; Determine whether the user’s industry preference matches the industry of the target object; when the behavior data is shopping information, the server counts the user’s shopping information within the fifth preset time, and determines the Whether the user's shopping information is related to the target object.
所述伺服器根據預設的行為資料得分確定所述用戶的綜合得分,具體為:所述伺服器確定所述用戶的行為資料的種類;所述伺服器根據預設的行為資料得分為所述用戶的行為資料的種類進行打分;所述伺服器根據所述用戶的行為資料的種類的打分確定所述用戶的綜合得分。 The server determines the user's comprehensive score according to a preset behavior data score, specifically: the server determines the type of the user's behavior data; the server determines the user's behavior data according to the preset behavior data score as the The user's behavior data type is scored; the server determines the user's comprehensive score according to the scoring of the user's behavior data type.
所述伺服器根據所述資訊的投放種類和預設的投放策 略按照所述投放順序向所述用戶投放所述資訊,具體為:所述伺服器根據所述用戶的行為資料和所述用戶的行業筆單價通過所述預設的投放策略確定所述資訊的投放種類;所述伺服器根據所述資訊的投放種類按照所述投放順序向所述用戶投放所述資訊。 The server is based on the delivery type of the information and the preset delivery policy The delivery of the information to the user slightly in accordance with the delivery sequence is specifically: the server determines the delivery strategy of the information according to the user’s behavior data and the user’s industry unit price through the preset delivery strategy Delivery type; the server delivers the information to the user in the order of delivery according to the delivery type of the information.
一種伺服器,所述伺服器包括:獲取模組,用於獲取用戶的行為資料;判斷模組,用於判斷所述用戶的行為資料是否滿足預設的行為標準;第一確定模組,如果所述用戶的行為資料滿足預設的行為標準,用於根據預設的行為資料得分確定所述用戶的綜合得分;第二確定模組,用於根據所述用戶綜合得分和其他用戶的綜合得分確定資訊向各個用戶的投放順序;投放模組,用於根據資訊的投放種類和預設的投放策略按照所述投放順序向所述用戶投放所述資訊。 A server comprising: an acquisition module for acquiring user behavior data; a judging module for determining whether the user’s behavior data meets a preset behavior standard; and a first determining module, if The user's behavior data meets preset behavior standards, and is used to determine the user's comprehensive score based on the preset behavior data score; the second determination module is used to determine the user's comprehensive score based on the user's comprehensive score and other users' comprehensive scores Determine the delivery order of the information to each user; the delivery module is used to deliver the information to the user according to the delivery order according to the delivery type of the information and the preset delivery strategy.
所述行為資料包括以下的一種或多種的任意組合:對目標對象的瀏覽次數、對目標對象的收藏情況、對目標對象的檢索情況、行業偏好和歷史購買資訊。 The behavior data includes any combination of one or more of the following: the number of times to browse the target object, the collection status of the target object, the retrieval status of the target object, industry preference and historical purchase information.
所述判斷模組,具體用於:當所述行為資料為對目標對象的瀏覽次數時,判斷第一預設時間內所述用戶瀏覽所述目標對象的次數是否超過瀏覽閾值; 當所述行為資料為對目標對象的收藏情況時,判斷第二預設時間內所述用戶是否收藏過所述目標對象;當所述行為資料為對目標對象的檢索次數時,判斷第三預設時間內所述用戶檢索所述目標對象的次數是否超過檢索閾值;當所述行為資料為行業偏好時,統計第四預設時間內所述用戶的行業偏好,判斷所述用戶的行業偏好是否與所述目標對象的所屬行業相匹配;當所述行為資料為購物資訊時,統計第五預設時間內所述用戶的購物資訊,判斷所述用戶的購物資訊是否與所述目標對象有關聯。 The judging module is specifically configured to: when the behavior data is the number of times to browse the target object, determine whether the number of times the user browses the target object within the first preset time exceeds a browsing threshold; When the behavior data is the collection of the target object, it is determined whether the user has collected the target object within the second preset time; when the behavior data is the number of times the target object is retrieved, the third prediction is determined Set whether the number of times the user retrieves the target object within a time exceeds the retrieval threshold; when the behavior data is an industry preference, count the user’s industry preference within the fourth preset time to determine whether the user’s industry preference Match with the industry of the target object; when the behavior data is shopping information, collect the shopping information of the user within the fifth preset time, and determine whether the shopping information of the user is related to the target object .
所述第一確定模組,具體用於:確定所述用戶的行為資料的種類;根據預設的行為資料得分為所述用戶的行為資料的種類進行打分;根據所述用戶的行為資料的種類的打分確定所述用戶的綜合得分。 The first determination module is specifically configured to: determine the type of the user's behavior data; score the type of the user's behavior data according to a preset behavior data score; and according to the type of the user's behavior data The scoring determines the overall score of the user.
所述投放模組,具體用於:根據所述用戶的行為資料和所述用戶的行業筆單價通過所述預設的投放策略確定所述資訊的投放種類;根據所述資訊的投放種類按照所述投放順序向所述用戶投放所述資訊。 The placement module is specifically configured to: determine the type of placement of the information according to the user’s behavior data and the user’s industry unit price through the preset placement strategy; and according to the type of placement of the information according to the type of placement. The delivery order delivers the information to the user.
本發明通過分析用戶的行為資料來判斷所述用戶的行為資料是否滿足預設的行為標準,如果滿足,再根據確定 的所述用戶的綜合得分確認資訊向所述用戶的投放順序,然後根據資訊的投放種類和預設的投放策略按照所述投放順序投放所述資訊,本發明可以確定出需要所述投放資訊的潛在用戶,通過對潛在用戶進行排序並投放資訊不僅可以實現潛在用戶的精准定位,還提高了資訊投放的命中率,同時還保證了對所述投放資訊興趣較大的用戶可以優先獲得,而且本發明還是直接基於大數據對用戶進行分析,減輕了操作人員的工作負擔,並且在用戶的行為發生變化時可以靈活的針對用戶的變化做出相應的判斷。 The present invention judges whether the user’s behavior data meets the preset behavior standard by analyzing the user’s behavior data. The user’s comprehensive score confirms the order in which the information is delivered to the user, and then the information is delivered according to the delivery order according to the type of information delivery and the preset delivery strategy. The present invention can determine the delivery order of the delivery information. Potential users, by sorting the potential users and delivering information, not only can the accurate positioning of potential users be achieved, but also the hit rate of information delivery can be improved. At the same time, it also ensures that users who are more interested in the delivery information can get priority. The invention still analyzes users directly based on big data, which reduces the workload of operators, and can flexibly make corresponding judgments in response to user changes when user behavior changes.
21:獲取模組 21: Get the module
22:判斷模組 22: Judgment module
23:第一確定模組 23: The first confirmation module
24:第二確定模組 24: The second confirmation module
25:投放模組 25: Putting the module
為了更清楚地說明本發明或現有技術中的技術方案,下面將對本發明或現有技術描述中所需要使用的附圖作簡單的介紹,顯而易見地,下面描述中的附圖僅僅是本發明的一些實施例,對於本領域普通技術人員來講,在不付出創造性勞動的前提下,還可以根據這些附圖獲得其他的附圖。 In order to more clearly explain the technical solutions of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the present invention or the prior art. Obviously, the drawings in the following description are only some of the present invention. Embodiments, for those of ordinary skill in the art, without creative work, other drawings can be obtained based on these drawings.
圖1為本發明實施例中的一種資訊投放用戶的篩選方法流程圖;圖2為本發明實施例中的一種伺服器的結構示意圖。 FIG. 1 is a flowchart of a method for screening information delivery users in an embodiment of the present invention; FIG. 2 is a schematic structural diagram of a server in an embodiment of the present invention.
下面將結合本發明中的附圖,對本發明中的技術方案進行清楚、完整的描述,顯然,所描述的實施例是本發明 的一部分實施例,而不是全部的實施例。基於本發明中的實施例,本領域普通技術人員獲得的其他實施例,都屬於本發明保護的範圍。 In the following, the technical solutions of the present invention will be described clearly and completely in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are the present invention. Part of the embodiments, but not all of the embodiments. Based on the embodiments of the present invention, other embodiments obtained by those of ordinary skill in the art all fall within the protection scope of the present invention.
如背景技術所述現有技術未對消費者的日常行為資料進行分析,不能精確劃分出對店鋪優惠券感興趣的用戶且是手動設置參數,不僅不夠智慧,並且工作量較大,同時,以白名單的方式確定滿足規定的用戶會使用戶發生變化時操作不夠靈活。 As described in the background art, the prior art does not analyze consumers’ daily behavior data, cannot accurately classify users who are interested in store coupons, and manually set parameters, which is not only not smart enough, but also requires a lot of work. The way to determine the users who meet the requirements in the way of the list will make the operation not flexible enough when the users change.
基於此,本發明實施例提出了一種資訊投放用戶的篩選方法,通過分析用戶的行為資料來判斷所述用戶是滿足所述資訊的投放標準,在所述用戶滿足所述資訊的投放標準後確定所述用戶對所述資訊的需求程度,並以此確定所述資訊向所述用戶的投放順序,再根據資訊的投放種類和預設的投放策略確定出所述用戶對應的投放資訊按照所述投放順序投放所述資訊,實現了投放資訊對應用戶的精確定位和投放資訊的精確投放,提高了資訊投放的命中率,還保證了對所述投放資訊興趣較大的用戶可以優先獲得。 Based on this, an embodiment of the present invention proposes a method for screening information delivery users, which determines whether the user meets the information delivery standard by analyzing the user's behavior data, and determines after the user meets the information delivery standard The user’s demand for the information is used to determine the order in which the information is delivered to the user, and then according to the type of information delivery and a preset delivery strategy, it is determined that the delivery information corresponding to the user is in accordance with the The delivery of the information in the order of delivery realizes the precise positioning of the delivery information corresponding to the user and the precise delivery of the delivery information, improves the hit rate of the information delivery, and also ensures that users who are more interested in the delivery information can get priority.
如圖1所述,為本發明實施例提出的一種資訊投放用戶的篩選方法的流程示意圖,所述方法包括以下步驟: As shown in Fig. 1, it is a schematic flow chart of a method for screening information delivery users according to an embodiment of the present invention. The method includes the following steps:
步驟101,伺服器獲取用戶的行為資料。 Step 101: The server obtains user behavior data.
其中,所述行為資料包括以下的一種或多種的任意組合:對目標對象的瀏覽次數、對目標對象的收藏情況、對目標對象的檢索情況、行業偏好和歷史購買資訊。 Wherein, the behavior data includes any combination of one or more of the following: the number of times to browse the target object, the collection status of the target object, the retrieval status of the target object, industry preferences, and historical purchase information.
需要說明的是,這裡的目標對象,可以指的是一家店鋪,也可以是一家店鋪中所在出售的業務對象,而業務對象本身,可以是實體商品,也可以是服務,例如:洗車、養護、按摩、清潔、廚師上門、家政、家教、娛樂、吃喝、旅行、酒店、租車等,凡是可以屬於用戶需求範圍的內容都可以作為本發明實施例中的分析對象,用以找出潛在的目標用戶,這樣的變化並不會影響本發明的保護範圍,在本發明的後續說明中,目標對象的含義同樣存在上述的限定,後文中不再重複說明。 It should be noted that the target object here can refer to a store, or a business object sold in a store, and the business object itself can be a physical product or a service, such as: car washing, maintenance, Massage, cleaning, chef visits, housekeeping, tutoring, entertainment, eating and drinking, travel, hotels, car rental, etc., any content that can fall into the scope of user needs can be used as the analysis object in the embodiment of the present invention to find potential target users Such a change will not affect the protection scope of the present invention. In the subsequent description of the present invention, the meaning of the target object also has the above limitation, and the description will not be repeated in the following.
所述伺服器可以為電商平臺的伺服器,用戶在日常網購時會在電商平臺上留下操作痕跡,這些操作痕跡即為用戶的行為資料,可以根據所述操作痕跡分析出用戶潛在的業務對象需求或喜歡哪家店鋪中在售的業務對象。 The server may be a server of an e-commerce platform, and users will leave operation traces on the e-commerce platform during daily online shopping. These operation traces are the user's behavior data, and the user's potential can be analyzed based on the operation traces. The business object needs or likes the business object sold in the store.
例如:以業務對象為實體商品的情況為例,如果一個用戶多次瀏覽某店鋪中在售的商品,則表明用戶對該店鋪的商品比較喜歡,但是由於某些原因(如:價格或沒有優惠等)而沒有購買,通過用戶的瀏覽該店鋪的商品的次數這一資訊可以確定出用戶對哪家店鋪的商品感興趣,並且還可以進一步分析出是對該家店鋪的何種商品感興趣。 For example: Taking the business object as physical goods as an example, if a user browses the goods sold in a certain store many times, it means that the user prefers the goods of the store, but due to some reasons (such as: price or no discount And so on) without purchasing, the information of the number of times the user browses the products of the store can determine which store's products the user is interested in, and can further analyze which products are of the store's interest.
同樣的,如果用戶收藏了某店鋪的商品、或者檢索某個商品的次數達到了一定數量,或者用戶的行業偏好(如某用戶經常購買一些電子產品表明該用戶對電子產品有偏好),以及用戶的購物資訊與某些商品存在明顯關聯,則同樣可以表明用戶對這些商品感興趣。 Similarly, if a user collects a store’s goods, or retrieves a certain product for a certain number of times, or the user’s industry preference (for example, a user often purchases some electronic products indicates that the user has a preference for electronic products), and the user There is a clear correlation between the shopping information of and certain products, which can also indicate that users are interested in these products.
通過獲取用戶的行為資料可以分析出用戶喜歡哪些商品,進而判斷出所述用戶是否對某店鋪出售的商品相對應,從而得出所述用戶是否為所述店鋪的潛在用戶。 By acquiring the user's behavior data, it is possible to analyze which products the user likes, and then to determine whether the user corresponds to the products sold in a certain store, so as to determine whether the user is a potential user of the store.
當然,如果業務對象為具體的服務內容,例如家政服務,酒店業務等等,也存在上述的情況,可以得出用戶是否為提供這些服務的店鋪的潛在用戶。 Of course, if the business object is a specific service content, such as housekeeping service, hotel business, etc., the above situation also exists, and it can be determined whether the user is a potential user of the store that provides these services.
當然,用戶的行為資料還可以包括用戶在日常消費過程中在伺服器(例如前述的電商平臺)上留下的其他操作痕跡,凡是能夠表明用戶潛在的業務需求的行為資訊均屬於本發明的保護範圍。 Of course, the user's behavior data can also include other operation traces left by the user on the server (such as the aforementioned e-commerce platform) during the daily consumption process. Any behavior information that can indicate the user's potential business needs belongs to the present invention. protected range.
步驟102,所述伺服器判斷所述用戶的行為資料是否滿足預設的行為標準。 Step 102: The server determines whether the user's behavior data meets a preset behavior standard.
如果滿足,則執行步驟103,如果不滿足,則結束。 If it is satisfied, go to step 103, and if it is not satisfied, go to the end.
所述伺服器判斷所述用戶行為資料是否滿足預設的行為標準,具體為:當所述行為資料為對目標對象的瀏覽次數時,所述伺服器判斷第一預設時間內所述用戶瀏覽所述目標對象的次數是否超過瀏覽閾值;當所述行為資料為對目標對象的收藏情況時,所述伺服器判斷第二預設時間內所述用戶是否收藏過所述目標對象;當所述行為資料為對目標對象的檢索次數時,所述伺服器判斷第三預設時間內所述用戶檢索所述目標對象的次數是否超過檢索閾值; 當所述行為資料為行業偏好時,所述伺服器統計第四預設時間內所述用戶的行業偏好,判斷所述用戶的行業偏好是否與所述目標對象的所屬行業相匹配;當所述行為資料為購物資訊時,所述伺服器統計第五預設時間內所述用戶的購物資訊,判斷所述用戶的購物資訊是否與所述目標對象有關聯。 The server determines whether the user behavior data meets a preset behavior standard, specifically: when the behavior data is the number of times the target object is viewed, the server determines whether the user browses within the first preset time Whether the number of times of the target object exceeds the browsing threshold; when the behavior data is the bookmarking of the target object, the server determines whether the user has bookmarked the target object within the second preset time; When the behavior data is the number of retrievals of the target object, the server determines whether the number of retrievals of the target object by the user within the third preset time exceeds a retrieval threshold; When the behavior data is an industry preference, the server counts the user's industry preference within the fourth preset time, and determines whether the user's industry preference matches the industry preference of the target object; When the behavior data is shopping information, the server counts the user's shopping information within the fifth preset time, and determines whether the user's shopping information is related to the target object.
具體的,針對不同的具體應用場景,同樣以業務對象為實體商品的情況為例,對以上各情況進行說明如下: Specifically, for different specific application scenarios, taking the case where the business object is a physical commodity as an example, the above situations are explained as follows:
情況一、行為資料為對目標對象的瀏覽次數。 Case 1. The behavioral data is the number of times the target object is viewed.
在此種情況下,目標用戶的確定依據為:當某用戶瀏覽某一店鋪的商品超過一定次數時,表明所述用戶對該店鋪的商品有比較強烈的購買需求,但是可能由於價格或沒有折扣等原因而沒有購買,因此,可以確定所述用戶為該商品的潛在購買用戶,或者所述用戶為所述店鋪的潛在購買用戶。 In this case, the basis for determining the target user is: when a user browses a certain store’s merchandise more than a certain number of times, it indicates that the user has a strong purchase demand for the store’s merchandise, but it may be due to price or no discount. If there is no purchase due to other reasons, it can be determined that the user is a potential purchase user of the commodity, or the user is a potential purchase user of the store.
基於上述的依據,在一個店鋪或該店鋪所銷售的商品有促銷活動要投放資訊時,可以獲取第一預設時間內各用戶對該店鋪或該店鋪內商品的瀏覽次數,並判斷瀏覽次數是否超過預先設定的瀏覽閾值。如果超過,則相應的用戶滿足該店鋪預設的行為標準,表明該用戶對該店鋪或該店鋪在售的商品購買需求比較強烈,因此,可以將該用戶作為該店鋪在投放資訊時需要投放的用戶之一。相反,如果沒有超過,則相應的用戶不滿足該店鋪預設的行為標準,表明該用戶對該店鋪或該店鋪在售的商品購買需求不太強 烈,在該店鋪投放資訊時不需要投放給該用戶。其中,所述第一預設時間和瀏覽閾值可以根據實際需要進行確定。 Based on the above-mentioned basis, when a store or the goods sold in the store have promotional activities to put information, it is possible to obtain the number of views of the store or the products in the store by each user within the first preset time, and determine whether the number of views is Exceeds the preset browsing threshold. If it exceeds, the corresponding user meets the behavior standards preset by the store, indicating that the user has a strong demand for the store or the products sold in the store. Therefore, the user can be regarded as the information that the store needs to place when posting information. One of the users. On the contrary, if it does not exceed, the corresponding user does not meet the behavior standards preset by the shop, indicating that the user has a low demand for the shop or the goods sold in the shop Strong, you don’t need to deliver to the user when posting information in the store. Wherein, the first preset time and the browsing threshold may be determined according to actual needs.
情況二、行為資料為對目標對象的收藏情況。 Case 2: The behavioral data is the collection of the target object.
在此種情況下,目標用戶的確定依據為:當某用戶收藏過某店鋪的商品時,表明所述用戶對該店鋪的這件商品有購買欲望或比較喜歡所述商品,但是可能由於價格或沒有折扣等原因而沒有購買,或者,當某用戶收藏過某店鋪時,表明所述用戶對該店鋪的商品有購買欲望或比較喜歡這個店鋪,但是可能由於價格或沒有折扣等原因而沒有購買,因此,可以確定所述用戶為該店鋪的這件商品的潛在購買用戶,或所述用戶為所述店鋪的潛在的購買用戶。 In this case, the basis for determining the target user is: when a user has bookmarked a product in a certain store, it indicates that the user has a desire to purchase the product in the store or prefers the product, but it may be due to price or No purchase due to discounts or other reasons, or, when a user has bookmarked a store, it indicates that the user has a desire to purchase the goods in the store or prefers the store, but may not purchase due to price or no discount. Therefore, it can be determined that the user is a potential purchase user of the commodity in the shop, or the user is a potential purchase user of the shop.
基於上述的依據,在一個店鋪或該店鋪所銷售的商品有促銷活動要投放資訊時,判斷第二預設時間範圍內各用戶是否收藏過該店鋪或者該店鋪的商品。如果收藏過,則相應的用戶滿足該店鋪預設的行為標準,表明該用戶對該店鋪或該店鋪在售的商品購買需求比較強烈,因此,可以將該用戶作為該店鋪在投放資訊時需要投放的用戶之一。相反,如果沒有收藏過,則相應的用戶不滿足該店鋪預設的行為標準,表明該用戶對該店鋪或該店鋪在售的商品購買需求不太強烈,在該店鋪投放資訊時不需要投放給該用戶。其中,所述第二設時間可以根據實際需要進行確定。 Based on the above-mentioned basis, when a store or a product sold in the store has information to be placed in a promotional event, it is determined whether each user has bookmarked the store or the products of the store within the second preset time range. If it has been bookmarked, the corresponding user meets the preset behavior standards of the store, indicating that the user has a strong demand for the store or the products sold in the store. Therefore, the user can be regarded as the store that needs to be posted when posting information One of the users. On the contrary, if there is no collection, the corresponding user does not meet the preset behavior standards of the store, indicating that the user does not have a strong demand for the store or the goods sold in the store, and does not need to be posted to the store when posting information in the store The user. Wherein, the second setting time can be determined according to actual needs.
情況三、行為資料為對目標對象的檢索次數。 Case 3. The behavioral data is the number of times the target object is retrieved.
在此種情況下,目標用戶的確定依據為:當某用戶對某一店鋪的商品檢索次數超過一定次數時,表明所述用戶 對該店鋪的商品有比較強烈的購買需求,但是可能由於價格或沒有折扣等原因而沒有購買,因此,可以確定所述用戶為該商品的潛在購買用戶,或者所述用戶為所述店鋪的潛在購買用戶。 In this case, the basis for determining the target user is: when the number of times a user searches for a product in a certain store exceeds a certain number of times, it indicates that the user There is a strong purchase demand for the goods in the store, but may not be purchased due to price or no discount. Therefore, it can be determined that the user is a potential purchaser of the product, or the user is a potential purchaser of the store. Purchase users.
基於上述的依據,在一個店鋪或該店鋪所銷售的商品有促銷活動要投放資訊時,可以獲取第三預設時間內各用戶對該店鋪或該店鋪內商品的檢索次數,並判斷檢索次數是否超過預先設定的檢索閾值。如果超過,則相應的用戶滿足該店鋪預設的行為標準,表明該用戶對該店鋪或該店鋪在售的商品購買需求比較強烈,因此,可以將該用戶作為該店鋪在投放資訊時需要投放的用戶之一。相反,如果沒有超過,則相應的用戶不滿足該店鋪預設的行為標準,表明該用戶對該店鋪或該店鋪在售的商品購買需求不太強烈,在該店鋪投放資訊時不需要投放給該用戶。其中,所述第三預設時間和檢索閾值可以根據實際需要進行確定。 Based on the above-mentioned basis, when a store or the goods sold in the store have promotional activities to put information, it is possible to obtain the number of times each user has searched the store or the goods in the store within the third preset time, and determine whether the number of searches is Exceeds the preset retrieval threshold. If it exceeds, the corresponding user meets the behavior standards preset by the store, indicating that the user has a strong demand for the store or the products sold in the store. Therefore, the user can be regarded as the information that the store needs to place when posting information. One of the users. On the contrary, if it does not exceed, the corresponding user does not meet the preset behavior standards of the store, indicating that the user does not have a strong demand for the store or the products sold in the store, and does not need to be delivered to the store when posting information in the store. user. Wherein, the third preset time and the retrieval threshold can be determined according to actual needs.
情況四、行為資料為行業偏好。 Situation 4. The behavioral data are industry preferences.
某些用戶有行業偏好,例如:某用戶的行業偏好是電子產品,那麼,該用戶平時肯定會關注或購買很多電子產品,或者某些用戶在一段時間內對某些產品具有明顯的偏好,例如:某用戶在進行家裝時,所述用戶會對家裝產品具有明顯的行業偏好。如果某用戶的行業偏好於一些店鋪的商品相對應時,那麼,該用戶就成為了這些店鋪的潛在買家。 Some users have industry preferences. For example, if a user’s industry preference is electronic products, then the user will usually pay attention to or buy a lot of electronic products, or some users have obvious preferences for certain products over a period of time, such as : When a user is doing home improvement, the user has an obvious industry preference for home improvement products. If a user’s industry prefers to correspond to the products in some stores, then the user becomes a potential buyer of these stores.
由於用戶的行業偏好可能是固定的,也可能是一段時 間內具有某行業偏好,因此,需要統計第四預設時間範圍內用戶的行業偏好,根據統計到的行業偏好判斷是否與某店鋪的商品相吻合。如果吻合,則滿足該店鋪預設的行為標準,表明該用戶對該店鋪或該店鋪在售的商品購買需求比較強烈,因此,可以將該用戶作為該店鋪在投放資訊時需要投放的用戶之一。相反,如果不吻合,則相應的用戶不滿足該店鋪預設的行為標準,表明該用戶對該店鋪或該店鋪在售的商品購買需求不太強烈,在該店鋪投放資訊時不需要投放給該用戶。其中,所述第四設時間可以根據實際需要進行確定。 Since the user’s industry preference may be fixed, it may also be for a period of time There is a certain industry preference in the time, therefore, it is necessary to count the user's industry preference in the fourth preset time range, and judge whether it is consistent with the goods of a certain store according to the statistics of the industry preference. If they match, the behavior standards preset by the store are met, indicating that the user has a strong demand for the store or the products sold in the store. Therefore, the user can be regarded as one of the users that the store needs to publish when posting information. . On the contrary, if they do not match, the corresponding user does not meet the behavior standards preset by the store, indicating that the user does not have a strong demand for the store or the goods sold in the store, and does not need to be posted to the store when posting information in the store. user. Wherein, the fourth setting time can be determined according to actual needs.
情況五、行為資料為購物資訊。 Situation 5. The behavior data is shopping information.
用戶的購物資訊能夠反映出該用戶需要哪方面的商品,例如:某用戶購買過筆記本電腦,那麼該用戶對筆記本電腦和與筆記本電腦有關的電腦配件可能比較需要,如果某店鋪的商品與筆記本電腦或筆記本電腦有關的電腦配件有關,那麼該用戶就是該店鋪的潛在買家。 The user’s shopping information can reflect what kind of products the user needs. For example, if a user has bought a laptop, then the user may need laptops and laptop-related computer accessories. If a store’s products and laptops Or laptop-related computer accessories, then the user is a potential buyer of the shop.
基於以上的依據,可以統計第五預設時間內各用戶的購物資訊,根據各用戶的購物資訊判斷是否與某店鋪的商品有關聯。如果有關聯,則相應的用戶滿足該店鋪預設的行為標準,表明該用戶對該店鋪或該店鋪在售的商品購買需求比較強烈,因此,可以將該用戶作為該店鋪在投放資訊時需要投放的用戶之一。相反,如果沒有關聯,則相應的用戶不滿足該店鋪預設的行為標準,表明該用戶對該店鋪或該店鋪在售的商品購買需求不太強烈,在該店鋪投放 資訊時不需要投放給該用戶。其中,所述第五預設時間可以根據實際需要進行確定。 Based on the above basis, the shopping information of each user can be counted within the fifth preset time, and it can be judged whether it is related to a product in a certain store according to the shopping information of each user. If there is an association, the corresponding user meets the preset behavior standards of the store, indicating that the user has a strong demand for the store or the products sold in the store. Therefore, the user can be regarded as the store that needs to be posted when posting information One of the users. On the contrary, if there is no association, the corresponding user does not meet the behavior standards preset by the store, indicating that the user does not have a strong demand for the store or the goods sold in the store, and puts it in the store The information does not need to be delivered to the user. Wherein, the fifth preset time can be determined according to actual needs.
需要進行說明的是,上述的示例都是以業務對象為實體商品的情況為例進行說明的,如果業務對象具體為服務,相應的處理流程也與上述的方案相類似,可以以此類推,在此不再重複說明。 It should be noted that the above examples are all based on the case where the business object is a physical commodity. If the business object is specifically a service, the corresponding processing flow is similar to the above-mentioned solution, which can be deduced by analogy. This will not be repeated.
步驟103,所述伺服器根據預設的行為資料得分確定所述用戶的綜合得分。 Step 103: The server determines the comprehensive score of the user according to a preset behavior data score.
所述伺服器根據預設的行為資料得分確定所述用戶的綜合得分,具體為:所述伺服器確定所述用戶的行為資料的種類;所述伺服器根據預設的行為資料得分為所述用戶的行為資料的種類進行打分;所述伺服器根據所述用戶的行為資料的種類的打分確定所述用戶的綜合得分。 The server determines the user's comprehensive score according to a preset behavior data score, specifically: the server determines the type of the user's behavior data; the server determines the user's behavior data according to the preset behavior data score as the The user's behavior data type is scored; the server determines the user's comprehensive score according to the scoring of the user's behavior data type.
具體的,預先為行為資料設定得分,例如:瀏覽一個目標對象的得分為W1,收藏過該目標對象的得分為W2,檢索過該目標對象的得分為W3,行業偏好與該目標對象相吻合的得分為W4,購物資訊與該目標對象相關聯的得分為W5。 Specifically, set a score for the behavior data in advance, for example, the score for browsing a target object is W1, the score for bookmarking the target object is W2, the score for searching the target object is W3, and the industry preference is consistent with the target object. The score is W4, and the score associated with the shopping information and the target object is W5.
用戶可能有多種的行為資料都滿足所述店鋪預設的行為標準,例如:用戶在第一預設時間內瀏覽一個店鋪的商品的次數超過閾值,並且,該用戶在第二預設時間內也收藏過該店鋪的商品,那麼,該用戶的綜合得分為 W1+W2,進一步的,如果預設的行為資料類型中還包括購物資訊,並且該用戶的行業偏好也與該店鋪的商品相吻合,那麼,該用戶的綜合得分為W1+W2+W4。 The user may have a variety of behavioral data that meet the behavior standards preset by the store. For example, the number of times that the user browses a shop’s merchandise in the first preset time exceeds a threshold, and the user also has a second preset time. The store’s goods have been collected, then the user’s comprehensive score is W1+W2. Further, if the preset behavior data type also includes shopping information, and the user's industry preference is also consistent with the products of the store, then the user's comprehensive score is W1+W2+W4.
步驟104,所述伺服器根據所述用戶綜合得分和其他用戶的綜合得分確定資訊向各個用戶的投放順序。 Step 104: The server determines the order in which information is delivered to each user according to the user's comprehensive score and the comprehensive score of other users.
具體的,所述用戶的綜合得分能夠反映出所述用戶與所述店鋪投放資訊興趣的大小,得分越高表示所述用戶對所述店鋪投放資訊的興趣越大,那麼所述用戶使用所述投放資訊的機率也越大,因此需要優先向綜合得分高的用戶投放資訊,以避免設定的投放資訊數目的原因使綜合得分高的用戶無法獲得投放資訊。 Specifically, the user’s comprehensive score can reflect the size of the user’s and the store’s interest in posting information. The higher the score, the greater the user’s interest in the store’s posting of information, and the user will use the The higher the probability of posting information, it is necessary to give priority to users with high comprehensive scores, so as to avoid the set number of posting information that prevents users with high comprehensive scores from obtaining advertising information.
步驟105,所述伺服器根據資訊的投放種類和預設的投放策略按照所述投放順序向所述用戶投放所述資訊。 Step 105: The server delivers the information to the user in the order of delivery according to the type of delivery of the information and the preset delivery strategy.
所述伺服器根據所述資訊的投放種類和預設的投放策略按照所述投放順序向所述用戶投放所述資訊,具體為:所述伺服器根據所述用戶的行為資料和所述用戶的行業筆單價通過所述預設的投放策略確定所述資訊的投放種類;所述伺服器根據所述資訊的投放種類按照所述投放順序向所述用戶投放所述資訊。 The server delivers the information to the user according to the delivery order according to the delivery type of the information and the preset delivery strategy, specifically: the server delivers the information to the user according to the user’s behavior data and the user’s The unit price of the industry pen determines the delivery type of the information according to the preset delivery strategy; the server delivers the information to the user according to the delivery order according to the delivery type of the information.
用戶的行業筆單價為所述用戶在某行業購買商品,平均每筆訂單的價格,用於考查所述用戶在所述行業的購買能力。 The industry unit price of the user is the average price of each order purchased by the user in a certain industry, which is used to examine the user's purchasing ability in the industry.
當所述用戶的行為資料滿足所述店鋪設定的行為標準 時,那麼所述用戶為所述店鋪的潛在用戶,再根據所述店鋪的商品確定所述店鋪所屬的行業,然後確定所述用戶在所述行業的行業筆單價,以確定所述用戶的購買能力。 When the user's behavior data meets the behavior standards set by the store When the user is a potential user of the shop, the industry to which the shop belongs is determined based on the products of the shop, and then the industry unit price of the user in the industry is determined to determine the user’s purchase ability.
所述伺服器將所述用戶的購買能力和所述用戶行為資料對應的價格進行對比,根據預設的投放策略確定資訊投放種類,具體以資訊為優惠券為例,要投放的優惠券有滿300元減30和滿200元減20兩種。 The server compares the purchasing power of the user with the price corresponding to the user behavior data, and determines the type of information delivery according to a preset delivery strategy. Specifically, taking the information as a coupon as an example, the number of coupons to be delivered is full 300 yuan minus 30 and full 200 yuan minus 20 two kinds.
當所述用戶的行為資料為收藏過所述店鋪的商品時,如果收藏的所述店鋪的商品的價格為200元,所述用戶的行業筆單價為300時,且如果預設的投放策略為刺激性投放策略,確定要投放的資訊的種類為滿300元減30的優惠券,這樣可以刺激用戶購買所述店鋪中更多的商品,如果預設的投放策略為穩健型投放策略,確定要投放的資訊的種類為滿200元減20的優惠券,這樣可以使用戶直接進行消費,使用戶使用所述優惠券的機率增加。當收藏的所述店鋪的商品的價格為200元,所述用戶的行業筆單價為100時,向用戶投放滿200減20的優惠券。其中,在投放時按照確定的用戶投放順序進行投放。 When the user’s behavior data is a product of the store, if the price of the product of the store is 200 yuan, the unit price of the user’s industry pen is 300, and if the preset delivery strategy is Stimulative delivery strategy. Determine the type of information to be delivered as a coupon of 300 yuan minus 30, which can stimulate users to purchase more goods in the store. If the preset delivery strategy is a robust delivery strategy, make sure to The type of information posted is a discount coupon of RMB 20 minus 20, so that the user can directly make purchases and increase the user's probability of using the coupon. When the price of the stored commodity in the store is 200 yuan, and the unit price of the user's industry pen is 100, a coupon of 200 minus 20 is offered to the user. Among them, the delivery is carried out in accordance with the determined user delivery order during delivery.
本發明通過分析用戶的行為資料來判斷所述用戶的行為資料是否滿足預設的行為標準,如果滿足,再根據確定的所述用戶的綜合得分確認資訊向所述用戶的投放順序,然後根據資訊的投放種類和預設的投放策略按照所述投放順序投放所述資訊,本發明可以確定出需要所述投放資訊的潛在用戶,通過對潛在用戶進行排序並投放資訊不僅可 以實現潛在用戶的精准定位,還提高了資訊投放的命中率,同時還保證了對所述投放資訊興趣較大的用戶可以優先獲得,而且本發明還是直接基於大資料對用戶進行分析,減輕了操作人員的工作負擔,並且在用戶的行為發生變化時可以靈活的針對用戶的變化做出相應的判斷。 The present invention judges whether the user’s behavior data meets the preset behavior standard by analyzing the user’s behavior data. If it does, it then confirms the order in which the information is delivered to the user according to the determined comprehensive score of the user, and then according to the information The delivery type and the preset delivery strategy will deliver the information according to the delivery order. The present invention can determine the potential users who need the delivery information. By sorting the potential users and delivering the information, it is not only In order to achieve precise positioning of potential users, it also improves the hit rate of information delivery, and at the same time, it also ensures that users who are more interested in the delivery information can obtain priority. Moreover, the present invention directly analyzes users based on big data, which reduces The workload of the operator, and when the user's behavior changes, it can flexibly make corresponding judgments for the user's changes.
為了進一步闡述本發明的技術思想,現結合具體的應用場景,對本發明的技術方案進行說明,具體如下: 以業務對象為實體商品的情況為例,伺服器獲取用戶的行為資料,具體包括:瀏覽店鋪的一件商品的次數、是否收藏該商品、檢索該商品的次數、行業偏好和購物資訊,根據所述行為資料判斷所述用戶是否為所述店鋪的潛在購買用戶。 In order to further illustrate the technical idea of the present invention, the technical scheme of the present invention will now be described in combination with specific application scenarios, which are specifically as follows: Taking the business object as a physical product as an example, the server obtains user behavior data, including: the number of times a product in the store is browsed, whether the product is collected, the number of times the product is retrieved, industry preferences, and shopping information, according to all The behavior data determines whether the user is a potential purchase user of the store.
對於用戶在短時間內頻繁瀏覽一個店鋪中的某個商品的情況,如果在伺服器中設定的行為標準為10天(相當於前述第一預設時間)內瀏覽一家店鋪中的某個商品超過5次(相當於前述瀏覽閾值),則所述伺服器判斷該用戶在10天內瀏覽該店鋪的這件商品的次數是否超過5次,如果超過,則將該用戶列為該店鋪或該店鋪的這件商品的潛在購買者。 For users who frequently browse a certain product in a shop in a short period of time, if the behavior standard set in the server is 10 days (equivalent to the aforementioned first preset time), the browsing of a certain product in a shop exceeds 5 times (equivalent to the aforementioned browsing threshold), the server determines whether the user has browsed the product in the shop more than 5 times in 10 days, and if it exceeds, the user is listed as the shop or the shop Of potential buyers of this item.
對於用戶收藏店鋪商品的情況,如果在所述伺服器中設定的行為標準為最近5天(相當於前述第二預設時間)內收藏過某個店鋪的商品,則所述伺服器判斷該用戶是否在5天內收藏過該店鋪的商品,如果收藏過,則將該用戶列為該店鋪或該店鋪的這件商品的潛在購買者。 In the case of a user’s collection of goods in a shop, if the behavior standard set in the server is that the goods of a certain shop have been collected in the last 5 days (equivalent to the aforementioned second preset time), the server will determine that the user Whether the store’s merchandise has been bookmarked within 5 days, if so, the user will be listed as a potential purchaser of the store or the merchandise in the store.
對於用戶在短時間內頻繁檢索一個店鋪中的某個商品的情況,如果在伺服器中設定的行為標準為10天(相當於前述第三預設時間)內檢索一家店鋪中的某個商品超過5次(相當於前述檢索閾值),則所述伺服器判斷該用戶在10天內檢索該店鋪的這件商品的次數是否超過5次,如果超過,則將該用戶列為該店鋪或該店鋪的這件商品的潛在購買者。 For users who frequently search for a certain product in a shop in a short period of time, if the behavior standard set in the server is 10 days (equivalent to the aforementioned third preset time), the search for a certain product in a shop exceeds 5 times (equivalent to the aforementioned retrieval threshold), the server determines whether the user has retrieved the item in the shop more than 5 times within 10 days, and if so, the user is listed as the shop or the shop Of potential buyers of this item.
在另一種應用場景下,伺服器可以根據各用戶1個月內(相當於前述的第四預設時間)的日常購買行為確定出所述用戶的行業偏好,基於這樣的行業偏好結果,伺服器判斷該用戶的行業偏好與某個店鋪的商品是否相同,例如:如果確定用戶的行業偏好為購買圖書,而當前店鋪的商品為圖書的話,那麼,該用戶的行業偏好與這個店鋪的商品相吻合,則將該用戶列為該店鋪或該店鋪的潛在購買者。 In another application scenario, the server can determine the user’s industry preference based on the daily purchase behavior of each user within 1 month (equivalent to the aforementioned fourth preset time). Based on the result of such industry preference, the server Determine whether the user’s industry preference is the same as the goods of a certain store, for example: if it is determined that the user’s industry preference is to buy books and the current store’s goods are books, then the user’s industry preference is consistent with the goods of this shop , The user is listed as a potential purchaser of the store or the store.
在另一種應用場景下,所述伺服器可以統計1個月內各用戶的購物資訊,如果一個用戶在1個月(相當於前述的第五預設時間)內購買過筆記本電腦,那麼,伺服器通過關聯分析算法,如:Apriori算法(一種挖掘關聯規則的頻繁項集算法),確定出某個店鋪的商品與該用戶的購物資訊是否存在關聯,如果存在關聯,則將該用戶列為該店鋪或該店鋪的潛在購買者。 In another application scenario, the server can count the shopping information of each user within one month. If a user has purchased a laptop within one month (equivalent to the aforementioned fifth preset time), then the server Through the association analysis algorithm, such as: Apriori algorithm (a frequent itemset algorithm for mining association rules), determine whether a store’s goods are associated with the user’s shopping information. If there is an association, the user will be listed as the user. The shop or potential purchasers of the shop.
需要進行說明的是,上述的示例都是以業務對象為實體商品的情況為例進行說明的,如果業務對象具體為店鋪 本身或者服務,相應的處理流程也與上述的方案相類似,可以以此類推,在此不再重複說明。 It should be noted that the above examples are all based on the case where the business object is a physical product. If the business object is specifically a store The corresponding processing flow for itself or service is also similar to the above-mentioned solution, and can be deduced by analogy, and will not be repeated here.
在具體的處理過程中,伺服器統計所述用戶滿足預設的行為標準的行為資料,當一個用戶的行為資料中有2項滿足預設的行為標準時,則伺服器為這2項行為資料進行打分,並確定出該用戶的綜合得分,例如:所述用戶的行為資料中瀏覽所述店鋪的次數和收藏所述店鋪的商品都滿足預設的行為標準,那麼所述伺服器根據預設的行為資料得分為瀏覽所述店鋪的次數和收藏所述店鋪的商品這兩項行為資料進行評分,並得出所述用戶的綜合得分。 In the specific processing process, the server counts the behavior data of the user that meets the preset behavior standard. When two items of a user's behavior data meet the preset behavior standard, the server performs the calculation for these two behavior data. Score, and determine the user’s comprehensive score, for example: the user’s behavior data for the number of times the shop has been browsed and the goods in the shop meet the preset behavior criteria, then the server will follow the preset The behavioral data score is scored for the two behavioral data of the number of times of browsing the store and the products of the store, and the comprehensive score of the user is obtained.
所述伺服器將多個用戶的綜合得分進行排序,並按照所述排序投放所述店鋪準備的優惠券。 The server sorts the comprehensive scores of multiple users, and places the coupons prepared by the store according to the sort.
在投放優惠券之前,所述伺服器還要確定投放的優惠券的種類,具體的,所述伺服器確定所述店鋪的商品所述的行業,然後確定出所述用戶在所述行業的行業筆單價,如果所述用戶瀏覽所述店鋪的次數滿足設定的行為標準時,且所述用戶瀏覽所述店鋪的商品都在200元左右,所述店鋪所售商品屬電子產品,然後確定出所述用戶在電子產品上的行業筆單價,如果所述用戶在電子產品上的行業筆單價為300元時,所述伺服器根據預先設定的投放策略確定優惠券的投放種類,根據所述用戶的投放順序投放對應的優惠券,例如:要投放的優惠券有滿300元減30和滿200元減20兩種,如果預設的投放策略為穩健型投放策略,確定要投放的資訊的種類為滿200元減20的優 惠券,如果預設的投放策略為刺激性投放策略,確定要投放的資訊的種類為滿300元減30的優惠券。 Before placing the coupon, the server must determine the type of the coupon to be placed. Specifically, the server determines the industry of the product in the store, and then determines the industry of the user in the industry The unit price, if the number of times the user browses the store meets the set behavior standard, and the goods the user browses to the store are all around 200 yuan, the goods sold in the store are electronic products, and then the The user’s industry unit price on the electronic product. If the user’s industry unit price on the electronic product is 300 yuan, the server determines the type of coupon placement according to the preset placement strategy, and according to the user’s placement Place the corresponding coupons in order, for example: There are two types of coupons to be placed: 300 yuan minus 30 and 200 yuan minus 20. If the preset placement strategy is a robust placement strategy, make sure that the type of information to be placed is full 200 yuan minus 20 excellent Coupon, if the preset delivery strategy is a stimulative delivery strategy, determine the type of information to be delivered as a coupon of 300 yuan minus 30.
當所述用戶的行業筆單價小於所述用戶瀏覽所述店鋪的商品的價格時,所述伺服器選擇滿200元減20的優惠券進行投放。其中,在投放時根據所述用戶的投放順序進行投放。 When the industry unit price of the user is less than the price of the commodity browsed by the user in the shop, the server selects a coupon of 200 yuan minus 20 for placement. Wherein, the placing is performed according to the placing order of the user when placing.
本發明通過分析用戶的行為資料來判斷所述用戶的行為資料是否滿足預設的行為標準,如果滿足,再根據確定的所述用戶的綜合得分確認資訊向所述用戶的投放順序,然後根據資訊的投放種類和預設的投放策略按照所述投放順序投放所述資訊,本發明可以確定出需要所述投放資訊的潛在用戶,通過對潛在用戶進行排序並投放資訊不僅可以實現潛在用戶的精准定位,還提高了資訊投放的命中率,同時還保證了對所述投放資訊興趣較大的用戶可以優先獲得,而且本發明還是直接基於大數據對用戶進行分析,減輕了操作人員的工作負擔,並且在用戶的行為發生變化時可以靈活的針對用戶的變化做出相應的判斷。 The present invention judges whether the user’s behavior data meets the preset behavior standard by analyzing the user’s behavior data. If it does, it then confirms the order in which the information is delivered to the user according to the determined comprehensive score of the user, and then according to the information The delivery type and the preset delivery strategy deliver the information according to the delivery order. The present invention can determine the potential users who need the delivery information. By sorting the potential users and placing the information, the accurate positioning of the potential users can not only be achieved , It also improves the hit rate of information delivery, and at the same time, it ensures that users who are more interested in the delivery information can obtain priority. Moreover, the present invention directly analyzes users based on big data, reducing the workload of operators, and When the user's behavior changes, it can flexibly make corresponding judgments for the user's changes.
基於與上述方法同樣的申請構思,本發明還提出了一種伺服器,如圖2所述,所述伺服器包括:獲取模組21,用於獲取用戶的行為資料;判斷模組22,用於判斷所述用戶的行為資料是否滿足預設的行為標準;第一確定模組23,如果所述用戶的行為資料滿足預設的行為標準,用於根據預設的行為資料得分確定所述用
戶的綜合得分;第二確定模組24,根據所述用戶綜合得分和其他用戶的綜合得分確定資訊向各個用戶的投放順序;投放模組25,用於根據資訊的投放種類和預設的投放策略按照所述投放順序向所述用戶投放所述資訊。
Based on the same application concept as the above method, the present invention also proposes a server, as shown in FIG. 2, the server includes: an
所述行為資料包括以下的一種或多種的任意組合:對目標對象的瀏覽次數、對目標對象的收藏情況、對目標對象的檢索情況、行業偏好和歷史購買資訊。 The behavior data includes any combination of one or more of the following: the number of times to browse the target object, the collection status of the target object, the retrieval status of the target object, industry preference and historical purchase information.
所述判斷模組,具體用於:當所述行為資料為對目標對象的瀏覽次數時,判斷第一預設時間內所述用戶瀏覽所述目標對象的次數是否超過瀏覽閾值;當所述行為資料為對目標對象的收藏情況時,判斷第二預設時間內所述用戶是否收藏過所述目標對象;當所述行為資料為對目標對象的檢索次數時,判斷第三預設時間內所述用戶檢索所述目標對象的次數是否超過檢索閾值;當所述行為資料為行業偏好時,統計第四預設時間內所述用戶的行業偏好,判斷所述用戶的行業偏好是否與所述目標對象的所屬行業相匹配;當所述行為資料為購物資訊時,統計第五預設時間內所述用戶的購物資訊,判斷所述用戶的購物資訊是否與所述目標對象有關聯。 The judgment module is specifically configured to: when the behavior data is the number of times the target object is viewed, determine whether the number of times the user browses the target object within the first preset time exceeds a browsing threshold; when the behavior When the data is the collection of the target object, it is determined whether the user has collected the target object within the second preset time; when the behavior data is the number of times the target object is retrieved, it is determined whether the target object is retrieved within the third preset time. Whether the number of times that the user retrieves the target object exceeds the retrieval threshold; when the behavior data is an industry preference, the user’s industry preference is counted within the fourth preset time to determine whether the user’s industry preference is consistent with the target The industry of the object matches; when the behavior data is shopping information, the shopping information of the user within the fifth preset time is counted, and it is determined whether the shopping information of the user is related to the target object.
所述第一確定模組,具體用於: 確定所述用戶的行為資料的種類;根據預設的行為資料得分為所述用戶的行為資料的種類進行打分;根據所述用戶的行為資料的種類的打分確定所述用戶的綜合得分。 The first determining module is specifically used for: Determine the type of the user's behavior data; score the type of the user's behavior data according to a preset behavior data score; determine the user's comprehensive score based on the score of the type of the user's behavior data.
所述投放模組,具體用於:根據所述用戶的行為資料和所述用戶的行業筆單價通過所述預設的投放策略確定所述資訊的投放種類;根據所述資訊的投放種類按照所述投放順序向所述用戶投放所述資訊。 The placement module is specifically configured to: determine the type of placement of the information according to the user’s behavior data and the user’s industry unit price through the preset placement strategy; and according to the type of placement of the information according to the type of placement. The delivery order delivers the information to the user.
本發明通過分析用戶的行為資料來判斷所述用戶的行為資料是否滿足預設的行為標準,如果滿足,再根據確定的所述用戶的綜合得分確認資訊向所述用戶的投放順序,然後根據資訊的投放種類和預設的投放策略按照所述投放順序投放所述資訊,本發明可以確定出需要所述投放資訊的潛在用戶,通過對潛在用戶進行排序並投放資訊不僅可以實現潛在用戶的精准定位,還提高了資訊投放的命中率,同時還保證了對所述投放資訊興趣較大的用戶可以優先獲得,而且本發明還是直接基於大數據對用戶進行分析,減輕了操作人員的工作負擔,並且在用戶的行為發生變化時可以靈活的針對用戶的變化做出相應的判斷。 The present invention judges whether the user’s behavior data meets the preset behavior standard by analyzing the user’s behavior data. If it does, it then confirms the order in which the information is delivered to the user according to the determined comprehensive score of the user, and then according to the information The delivery type and the preset delivery strategy deliver the information according to the delivery order. The present invention can determine the potential users who need the delivery information. By sorting the potential users and placing the information, the accurate positioning of the potential users can not only be achieved , It also improves the hit rate of information delivery, and at the same time ensures that users who are more interested in the delivery information can obtain priority. Moreover, the present invention directly analyzes users based on big data, reducing the workload of operators, and When the user's behavior changes, it can flexibly make corresponding judgments for the user's changes.
通過以上的實施方式的描述,本領域的技術人員可以清楚地瞭解到本發明可借助軟體加必需的通用硬體平臺的方式來實現,當然也可以通過硬體,但很多情況下前者是 更佳的實施方式。基於這樣的理解,本發明的技術方案本質上或者說對現有技術做出貢獻的部分可以以軟體產品的形式體現出來,該計算機軟體產品儲存在一個儲存媒體中,包括若干指令用以使得一台終端設備(可以是手機,個人計算機,伺服器,或者網路設備等)執行本發明各個實施例所述的方法。 Through the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus the necessary universal hardware platform, of course, it can also be implemented by hardware, but in many cases the former is Better implementation. Based on this understanding, the technical solution of the present invention essentially or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions to make a computer A terminal device (which can be a mobile phone, a personal computer, a server, or a network device, etc.) executes the methods described in the various embodiments of the present invention.
以上所述僅是本發明的較佳實施方式,應當指出,對於本技術領域的普通技術人員來說,在不脫離本發明原理的前提下,還可以做出若干改進和潤飾,這些改進和潤飾也應視本發明的保護範圍。 The above are only the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and modifications can be made. These improvements and modifications The protection scope of the present invention should also be considered.
本領域技術人員可以理解實施例中的裝置中的模組可以按照實施例描述進行分佈於實施例的裝置中,也可以進行相應變化位於不同於本實施例的一個或多個裝置中。上述實施例的模組可以集成於一體,也可以分離部署;可以合併為一個模組,也可以進一步拆分成多個子模組。上述本發明實施例序號僅僅為了描述,不代表實施例的優劣。 Those skilled in the art can understand that the modules in the device in the embodiment can be distributed in the device in the embodiment according to the description of the embodiment, or can be changed to be located in one or more devices different from this embodiment. The modules in the above-mentioned embodiments can be integrated or deployed separately; they can be combined into one module, or they can be further split into multiple sub-modules. The sequence numbers of the foregoing embodiments of the present invention are only for description, and do not represent the superiority or inferiority of the embodiments.
以上公開的僅為本發明的幾個具體實施例,但是,本發明並非局限於此,任何本領域的技術人員能思之的變化都應落入本發明的保護範圍。 The above-disclosed are only a few specific embodiments of the present invention, but the present invention is not limited thereto, and any changes that can be thought of by those skilled in the art should fall into the protection scope of the present invention.
Claims (10)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW106102468A TWI726981B (en) | 2017-01-23 | 2017-01-23 | Screening method and equipment for information delivery users |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
TW106102468A TWI726981B (en) | 2017-01-23 | 2017-01-23 | Screening method and equipment for information delivery users |
Publications (2)
Publication Number | Publication Date |
---|---|
TW201828194A TW201828194A (en) | 2018-08-01 |
TWI726981B true TWI726981B (en) | 2021-05-11 |
Family
ID=63960520
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW106102468A TWI726981B (en) | 2017-01-23 | 2017-01-23 | Screening method and equipment for information delivery users |
Country Status (1)
Country | Link |
---|---|
TW (1) | TWI726981B (en) |
Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080162574A1 (en) * | 2006-11-22 | 2008-07-03 | Sheldon Gilbert | Analytical E-Commerce Processing System And Methods |
CN102346894A (en) * | 2010-08-03 | 2012-02-08 | 阿里巴巴集团控股有限公司 | Output method, system and server of recommendation information |
US20130151258A1 (en) * | 2008-08-18 | 2013-06-13 | Microsoft Corporation | Context Based Online Advertising |
TW201327233A (en) * | 2011-12-16 | 2013-07-01 | Alibaba Group Holding Ltd | Personalized information pushing method and device |
US20130268317A1 (en) * | 2010-12-07 | 2013-10-10 | Digital Foodie Oy | Arrangement for facilitating shopping and related method |
CN103714067A (en) * | 2012-09-29 | 2014-04-09 | 腾讯科技(深圳)有限公司 | Method and device for pushing information |
CN103729780A (en) * | 2013-12-23 | 2014-04-16 | 北京掌阔技术有限公司 | Advertisement optimized delivery method and system |
CN103995839A (en) * | 2014-04-30 | 2014-08-20 | 兴天通讯技术(天津)有限公司 | Commodity recommendation optimizing method and system based on collaborative filtering |
CN104331819A (en) * | 2014-11-05 | 2015-02-04 | 中国建设银行股份有限公司 | Method and device for processing information |
CN104539740A (en) * | 2015-01-26 | 2015-04-22 | 北京奇艺世纪科技有限公司 | Information push method and device |
US20150242866A1 (en) * | 2012-09-27 | 2015-08-27 | Nec Corporation | Determination device, determination method, and computer-readable recording medium |
CN104901817A (en) * | 2014-03-07 | 2015-09-09 | 腾讯科技(北京)有限公司 | Method and device for pushing target information |
TW201638850A (en) * | 2015-03-31 | 2016-11-01 | Rakuten Inc | Information processing device, information processing method, and information processing program |
TW201719532A (en) * | 2015-11-17 | 2017-06-01 | Alibaba Group Services Ltd | Recommendation method and device |
-
2017
- 2017-01-23 TW TW106102468A patent/TWI726981B/en active
Patent Citations (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080162574A1 (en) * | 2006-11-22 | 2008-07-03 | Sheldon Gilbert | Analytical E-Commerce Processing System And Methods |
US20130151258A1 (en) * | 2008-08-18 | 2013-06-13 | Microsoft Corporation | Context Based Online Advertising |
CN102346894A (en) * | 2010-08-03 | 2012-02-08 | 阿里巴巴集团控股有限公司 | Output method, system and server of recommendation information |
US20130268317A1 (en) * | 2010-12-07 | 2013-10-10 | Digital Foodie Oy | Arrangement for facilitating shopping and related method |
TW201327233A (en) * | 2011-12-16 | 2013-07-01 | Alibaba Group Holding Ltd | Personalized information pushing method and device |
US20150242866A1 (en) * | 2012-09-27 | 2015-08-27 | Nec Corporation | Determination device, determination method, and computer-readable recording medium |
CN103714067A (en) * | 2012-09-29 | 2014-04-09 | 腾讯科技(深圳)有限公司 | Method and device for pushing information |
CN103729780A (en) * | 2013-12-23 | 2014-04-16 | 北京掌阔技术有限公司 | Advertisement optimized delivery method and system |
CN104901817A (en) * | 2014-03-07 | 2015-09-09 | 腾讯科技(北京)有限公司 | Method and device for pushing target information |
CN103995839A (en) * | 2014-04-30 | 2014-08-20 | 兴天通讯技术(天津)有限公司 | Commodity recommendation optimizing method and system based on collaborative filtering |
CN104331819A (en) * | 2014-11-05 | 2015-02-04 | 中国建设银行股份有限公司 | Method and device for processing information |
CN104539740A (en) * | 2015-01-26 | 2015-04-22 | 北京奇艺世纪科技有限公司 | Information push method and device |
TW201638850A (en) * | 2015-03-31 | 2016-11-01 | Rakuten Inc | Information processing device, information processing method, and information processing program |
TW201719532A (en) * | 2015-11-17 | 2017-06-01 | Alibaba Group Services Ltd | Recommendation method and device |
Also Published As
Publication number | Publication date |
---|---|
TW201828194A (en) | 2018-08-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2017092602A1 (en) | Method for screening information delivery user and server | |
US10354312B2 (en) | Electronic marketplace recommendations | |
US8266014B1 (en) | Method and medium for creating a ranked list of products | |
JP4969550B2 (en) | Website management method and online system | |
WO2017028687A1 (en) | Unused commodity object information processing method and device | |
US20130030950A1 (en) | Providing social product recommendations | |
US8364559B1 (en) | Method, medium, and system of recommending a substitute item | |
JP5957164B1 (en) | Information processing apparatus, information processing method, and information processing program | |
WO2017158798A1 (en) | Information processing device, information distribution system, information processing method, and information processing program | |
JP6679451B2 (en) | Selection device, selection method, and selection program | |
US8423420B1 (en) | Method and media for duplicate detection in an electronic marketplace | |
JP5824602B1 (en) | Information processing apparatus, information processing method, and information processing program | |
CN113205382B (en) | Method, apparatus, device, storage medium and program product for determining object | |
JP7145823B2 (en) | Provision device, provision method and provision program | |
JP7140588B2 (en) | Decision device, decision method and decision program | |
JP6397092B1 (en) | Distribution apparatus, distribution method, and distribution program | |
JP2020107269A (en) | Information processing device, information processing method, and information processing program | |
JP6543576B2 (en) | System and method for providing customized search results based on a user's shopping history, a retailer's identity and items promoted by the retailer | |
US20130185146A1 (en) | Method and server of providing advertisement | |
KR101960524B1 (en) | Smart market service system and Method thereof | |
TW201801006A (en) | Personalized online marketing recommendation method capable of predicting the trend of preference according to factors such as browsing date, browsing time, and website visited, to thereby provide marketing materials | |
WO2016157426A1 (en) | Information processing device, information processing method, and information processing program | |
JP6276443B1 (en) | Information providing apparatus, information providing method, and information providing program | |
TWI726981B (en) | Screening method and equipment for information delivery users | |
JP7042787B2 (en) | Judgment device, judgment method, and judgment program |