TW201933226A - Method and apparatus for determining false resource transfer, method and apparatus for determining false trading, and electronic device - Google Patents
Method and apparatus for determining false resource transfer, method and apparatus for determining false trading, and electronic device Download PDFInfo
- Publication number
- TW201933226A TW201933226A TW107144476A TW107144476A TW201933226A TW 201933226 A TW201933226 A TW 201933226A TW 107144476 A TW107144476 A TW 107144476A TW 107144476 A TW107144476 A TW 107144476A TW 201933226 A TW201933226 A TW 201933226A
- Authority
- TW
- Taiwan
- Prior art keywords
- data
- transaction
- false
- resource transfer
- historical
- Prior art date
Links
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
- G06Q30/018—Certifying business or products
-
- 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
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- 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]
- G06Q30/0623—Item investigation
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
Description
本申請案涉及電腦技術領域，尤其涉及一種判定虛假資源轉移及虛假交易的方法、裝置及電子設備。The present application relates to the field of computer technology, and in particular, to a method, a device, and an electronic device for determining a false resource transfer and a false transaction.
目前，隨著網際網路技術的快速發展，諸如京東、淘寶等電商平臺逐漸成為人們日常生活中不可缺少的一部分。當買家想要購買某件商品時，可以通過這些電商平臺瀏覽想要購買的商品，並選擇某件商品完成交易。大多數買家在選擇某件商品時，往往會通過對多個類似的商品進行比較，通常依據其他買家對商品、賣家商戶的評價、以及賣家商戶的信用積分等資訊來判斷某個商品是否值得購買。
然而，電商平臺上的賣家為了獲得對其商戶或者某個商品較好的評價，往往會通過不正當方式(比如刷單等虛假交易的方式)獲得商品銷量、商戶評分、信用積分等不當利益，使得買家在購買商品時做出錯誤的判斷，進而妨害買家的權益。
因此，如何準確有效地識別虛假交易越來越成為電商平臺亟需解決的重要問題之一。At present, with the rapid development of Internet technologies, e-commerce platforms such as JD.com and Taobao have gradually become an indispensable part of people's daily lives. When buyers want to purchase a certain product, they can browse the desired product through these e-commerce platforms and select a certain product to complete the transaction. When most buyers choose a certain product, they often compare multiple similar products, usually based on other buyers' evaluations of the products, sellers' merchants, and sellers' credit scores to determine whether a product is worth buying.
However, in order to obtain a better evaluation of their merchants or a certain product, sellers on the e-commerce platform often obtain improper benefits such as product sales, merchant ratings, credit points, etc. through improper methods (such as false transactions such as slipping orders). , So that buyers make wrong judgments when buying goods, which in turn hinders the rights of buyers.
Therefore, how to accurately and effectively identify fake transactions has become one of the important issues that e-commerce platforms need to solve urgently.
本申請案實施例提供了一種判定虛假資源轉移及虛假交易的方法、裝置及電子設備，以解決現有技術中判定虛假交易的方法不夠優化的問題。
為解決上述技術問題，本申請案實施例是這樣實現的：
第一方面，提出了一種判定虛假資源轉移的方法，包括：
獲取資源轉入方在待驗證資源轉移前第一預定時間段內的歷史資源轉移資料、和所述資源轉入方在所述待驗證資源轉移前第二預定時間段內的行為資料；
基於所述歷史資源轉移資料、所述行為資料和虛假資源轉移模型，判定所述待驗證資源轉移是否為虛假資源轉移；
其中，所述虛假資源轉移模型基於歷史資源轉移訓練資料和對應的行為訓練資料訓練得到。
第二方面，提出了一種判定虛假交易的方法，包括：
獲取交易支付方在待驗證交易前第一預定時間段內的歷史交易資料、和所述交易支付方在所述待驗證交易前第二預定時間段內的行為資料；
基於所述歷史資源轉移資料、所述行為資料和虛假交易模型，判定所述待驗證交易是否為虛假交易；
其中，所述虛假交易模型基於歷史交易訓練資料和對應的行為訓練資料訓練得到。
第三方面，提出了一種判定虛假資源轉移的裝置，包括：
獲取單元，獲取資源轉入方在待驗證資源轉移前第一預定時間段內的歷史資源轉移資料、和所述資源轉入方在所述待驗證資源轉移前第二預定時間段內的行為資料；
判定單元，基於所述歷史資源轉移資料、所述行為資料和虛假資源轉移模型，判定所述待驗證資源轉移是否為虛假資源轉移；
其中，所述虛假資源轉移模型基於歷史資源轉移訓練資料和對應的行為訓練資料訓練得到。
第四方面，提出了一種判定虛假交易的裝置，包括：
獲取單元，獲取交易支付方在待驗證交易前第一預定時間段內的歷史交易資料、和所述交易支付方在所述待驗證交易前第二預定時間段內的行為資料；
判定單元，基於所述歷史資源轉移資料、所述行為資料和虛假交易模型，判定所述待驗證交易是否為虛假交易；
其中，所述虛假交易模型基於歷史交易訓練資料和對應的行為訓練資料訓練得到。
第五方面，提出了一種電子設備，該電子設備包括：
處理器；以及
被安排成儲存電腦可執行指令的記憶體，所述可執行指令在被執行時使所述處理器執行以下操作：
被安排成儲存電腦可執行指令的記憶體，所述可執行指令在被執行時使所述處理器執行以下操作：
獲取資源轉入方在待驗證資源轉移前第一預定時間段內的歷史資源轉移資料、和所述資源轉入方在所述待驗證資源轉移前第二預定時間段內的行為資料；
基於所述歷史資源轉移資料、所述行為資料和虛假資源轉移模型，判定所述待驗證資源轉移是否為虛假資源轉移；
其中，所述虛假資源轉移模型基於歷史資源轉移訓練資料和對應的行為訓練資料訓練得到。
第六方面，提出了一種電腦可讀儲存媒體，所述電腦可讀儲存媒體儲存一個或多個程式，所述一個或多個程式當被包括多個應用程式的電子設備執行時，使得所述電子設備執行以下操作：
被安排成儲存電腦可執行指令的記憶體，所述可執行指令在被執行時使所述處理器執行以下操作：
獲取資源轉入方在待驗證資源轉移前第一預定時間段內的歷史資源轉移資料、和所述資源轉入方在所述待驗證資源轉移前第二預定時間段內的行為資料；
基於所述歷史資源轉移資料、所述行為資料和虛假資源轉移模型，判定所述待驗證資源轉移是否為虛假資源轉移；
其中，所述虛假資源轉移模型基於歷史資源轉移訓練資料和對應的行為訓練資料訓練得到。
第七方面，提出了一種電子設備，該電子設備包括：
處理器；以及
被安排成儲存電腦可執行指令的記憶體，所述可執行指令在被執行時使所述處理器執行以下操作：
獲取資源轉入方在待驗證資源轉移前第一預定時間段內的歷史資源轉移資料、和所述資源轉入方在所述待驗證資源轉移前第二預定時間段內的行為資料；
基於所述歷史資源轉移資料、所述行為資料和虛假資源轉移模型，判定所述待驗證資源轉移是否為虛假資源轉移；
其中，所述虛假交易模型基於歷史交易訓練資料和對應的行為訓練資料訓練得到。
第八方面，提出了一種電腦可讀儲存媒體，所述電腦可讀儲存媒體儲存一個或多個程式，所述一個或多個程式當被包括多個應用程式的電子設備執行時，使得所述電子設備執行以下操作：
獲取資源轉入方在待驗證資源轉移前第一預定時間段內的歷史資源轉移資料、和所述資源轉入方在所述待驗證資源轉移前第二預定時間段內的行為資料；
基於所述歷史資源轉移資料、所述行為資料和虛假資源轉移模型，判定所述待驗證資源轉移是否為虛假資源轉移；
其中，所述虛假交易模型基於歷史交易訓練資料和對應的行為訓練資料訓練得到。
本申請案實施例採用上述技術方案至少可以達到下述技術效果：
通過獲取資源轉入方在待驗證資源轉移前第一預定時間段內的歷史資源轉移資料、和資源轉入方在待驗證資源轉移前第二預定時間段內的行為資料，基於獲取的歷史資源轉移資料、行為資料和虛假資源轉移模型，判定待驗證資源轉移是否為虛假資源轉移，不僅考慮了資源轉入方的歷史資源轉移資料，還將其在資源轉移前的行為資料作為判別識別虛假資源轉移的依據，提高了判別虛假資源轉移的準確性，達到優化識別虛假資源轉移的目的。
通過獲取交易支付方在待驗證交易前第一預定時間段內的歷史交易資料、和交易支付方在待驗證交易前第二預定時間段內的行為資料，基於獲取的歷史交易資料、行為資料和虛假交易模型，判定待驗證交易是否為虛假交易，不僅考慮了交易支付方也就是買家的歷史交易資料，還將其在交易前的行為資料作為判別識別虛假交易的依據，提高了判別虛假交易的準確性，達到優化識別虛假交易的目的。The embodiments of the present application provide a method, a device, and an electronic device for determining a false resource transfer and a false transaction, so as to solve the problem that the method for determining a false transaction in the prior art is insufficiently optimized.
To solve the above technical problems, the embodiments of the present application are implemented as follows:
In the first aspect, a method for determining the transfer of false resources is proposed, including:
Acquiring historical resource transfer data of a resource transferee within a first predetermined time period before the resource to be verified is transferred, and behavioral data of the resource transfer party within a second predetermined time period before the resource to be verified is transferred;
Determining whether the resource transfer to be verified is a false resource transfer based on the historical resource transfer data, the behavior data, and a false resource transfer model;
The false resource transfer model is obtained based on training data of historical resource transfer training and corresponding behavior training data.
In the second aspect, a method for determining false transactions is proposed, including:
Obtaining historical transaction data of a transaction payer within a first predetermined time period before a transaction to be verified, and behavioral data of the transaction payer within a second predetermined time period before the transaction to be verified;
Determining whether the transaction to be verified is a false transaction based on the historical resource transfer data, the behavior data, and a false transaction model;
Wherein, the false trading model is obtained by training based on historical trading training data and corresponding behavior training data.
In a third aspect, a device for determining the transfer of false resources is proposed, including:
An acquiring unit, which acquires historical resource transfer data of a resource transferee within a first predetermined time period before the resource to be verified is transferred, and behavior data of the resource transferee within a second predetermined time period before the resource to be verified is transferred ;
A determining unit, based on the historical resource transfer data, the behavior data, and a false resource transfer model, determining whether the resource transfer to be verified is a false resource transfer;
The false resource transfer model is obtained based on training data of historical resource transfer training and corresponding behavior training data.
In a fourth aspect, a device for determining false transactions is proposed, including:
An acquiring unit, which acquires historical transaction data of a transaction payer within a first predetermined time period before a transaction to be verified, and behavior data of the transaction payer within a second predetermined time period before the transaction to be verified;
A determining unit, based on the historical resource transfer data, the behavior data, and a false transaction model, determining whether the transaction to be verified is a false transaction;
Wherein, the false trading model is obtained by training based on historical trading training data and corresponding behavior training data.
In a fifth aspect, an electronic device is provided. The electronic device includes:
A processor; and a memory arranged to store computer-executable instructions that, when executed, cause the processor to perform the following operations:
Memory arranged to store computer-executable instructions that, when executed, cause the processor to perform the following operations:
Acquiring historical resource transfer data of a resource transferee within a first predetermined time period before the resource to be verified is transferred, and behavioral data of the resource transfer party within a second predetermined time period before the resource to be verified is transferred;
Determining whether the resource transfer to be verified is a false resource transfer based on the historical resource transfer data, the behavior data, and a false resource transfer model;
The false resource transfer model is obtained based on training data of historical resource transfer training and corresponding behavior training data.
According to a sixth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores one or more programs. When the one or more programs are executed by an electronic device including a plurality of application programs, The electronic device does the following:
Memory arranged to store computer-executable instructions that, when executed, cause the processor to perform the following operations:
Acquiring historical resource transfer data of a resource transferee within a first predetermined time period before the resource to be verified is transferred, and behavioral data of the resource transfer party within a second predetermined time period before the resource to be verified is transferred;
Determining whether the resource transfer to be verified is a false resource transfer based on the historical resource transfer data, the behavior data, and a false resource transfer model;
The false resource transfer model is obtained based on training data of historical resource transfer training and corresponding behavior training data.
According to a seventh aspect, an electronic device is provided. The electronic device includes:
A processor; and a memory arranged to store computer-executable instructions that, when executed, cause the processor to perform the following operations:
Acquiring historical resource transfer data of a resource transferee within a first predetermined time period before the resource to be verified is transferred, and behavioral data of the resource transfer party within a second predetermined time period before the resource to be verified is transferred;
Determining whether the resource transfer to be verified is a false resource transfer based on the historical resource transfer data, the behavior data, and a false resource transfer model;
Wherein, the false trading model is obtained by training based on historical trading training data and corresponding behavior training data.
According to an eighth aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores one or more programs. When the one or more programs are executed by an electronic device including a plurality of application programs, The electronic device does the following:
Acquiring historical resource transfer data of a resource transferee within a first predetermined time period before the resource to be verified is transferred, and behavioral data of the resource transfer party within a second predetermined time period before the resource to be verified is transferred;
Determining whether the resource transfer to be verified is a false resource transfer based on the historical resource transfer data, the behavior data, and a false resource transfer model;
Wherein, the false trading model is obtained by training based on historical trading training data and corresponding behavior training data.
The embodiments of the present application can achieve at least the following technical effects by adopting the foregoing technical solutions:
Based on the acquired historical resources, the historical resource transfer data of the resource transferee within the first predetermined period of time before the transfer of the resource to be verified and the behavior data of the resource transferee within the second predetermined period of time before the resource to be verified are transferred. Transfer data, behavior data, and false resource transfer models to determine whether the resource transfer to be verified is a false resource transfer. Not only the historical resource transfer data of the resource transferor is considered, but also its behavior data before the resource transfer is used to identify the false resource. The basis of the transfer improves the accuracy of judging the transfer of false resources and achieves the purpose of optimizing and identifying the transfer of false resources.
By obtaining historical transaction data of the transaction payer in the first predetermined time period before the transaction to be verified, and behavior data of the transaction payer in the second predetermined time period before the transaction to be verified, based on the acquired historical transaction data, behavior data, and The false transaction model determines whether the transaction to be verified is a false transaction, not only taking into account the historical transaction data of the transaction payer, that is, the buyer, but also using its behavioral data before the transaction as the basis for identifying and identifying false transactions, which improves the identification of false transactions. Accuracy to achieve the purpose of optimizing and identifying false transactions.
為使本申請案的目的、技術方案和優點更加清楚，下面將結合本申請案具體實施例及相應的附圖對本申請案技術方案進行清楚、完整地描述。顯然，所描述的實施例僅是本申請案一部分實施例，而不是全部的實施例。基於本申請案中的實施例，本領域普通技術人員在沒有做出進步性勞動前提下所獲得的所有其他實施例，都屬於本申請案保護的範圍。
以下結合附圖，詳細說明本申請案各實施例提供的技術方案。
為解決現有技術中判定虛假交易的方法不夠優化的問題，本說明書實施例提供一種判定虛假資源轉移的方法。本說明書實施例提供的判定虛假資源轉移的方法的執行主體可以但不限於伺服器、個人電腦等能夠被配置為執行本發明實施例提供的該方法終端中的至少一種。
為便於描述，下文以該方法的執行主體為能夠執行該方法的伺服器為例，對該方法的實施方式進行介紹。可以理解，該方法的執行主體為伺服器只是一種示例性的說明，並不應理解為對該方法的限定。
具體地，本說明書一個或多個實施例提供的一種判定虛假資源轉移的方法的實現流程示意圖如圖1所示，包括：
步驟110，獲取資源轉入方在待驗證資源轉移前第一預定時間段內的歷史資源轉移資料、和資源轉入方在待驗證資源轉移前第二預定時間段內的行為資料；
其中，歷史資源轉移資料至少包括下述一種：歷史資源轉移次數，歷史資源轉移額度，歷史資源轉移涉及的資源接收方的數量。在實際應用中，該資源轉移比如可以是交易，則歷史資源轉移資料具體可以包括：歷史交易次數，歷史交易額度，歷史交易涉及的交易接收方也就是賣家或者是商戶的數量，單筆交易最大值，單筆交易最小值，單筆交易平均值，日交易最大值，日交易最小值、日交易平均值等等，都可以作為交易支付方也就是買家在此次交易之前的歷史交易資料。
其中，行為資料至少包括下述一種：資源轉入方瀏覽的資源接收方的資訊、瀏覽時長、瀏覽的資源資訊，資源接收方的資訊至少包括資源接收方的信用值、資源類別、資源價值分佈、健康程度。在實際應用中，該行為資料具體可以包括：買家在完成此次交易之前所瀏覽過的賣家或者商戶的資訊，以及在各個賣家或者商戶瀏覽時停留的時長，在各個商戶中瀏覽過的商品資訊(比如商品的名稱、價格等資訊)，其中賣家或者商戶的資訊包括賣家或者商戶的信用值、商戶中的商品類別、商品的價格分佈、以及商戶近期(比如近一個月內)被投訴的次數，等等。
此外，第一預定時間段可以是資源轉入方在此次資源轉移之前的某一時間段，比如在此次資源轉移之前的三個月、一個月或者一個星期內的一段時間，第二預定時間段可以是資源轉入方在此次資源轉移之前的幾天或者一天或者幾個小時的一段時間，該第一預定時間段和第二預定時間段可以根據實際需求來設定，本說明書一個或多個實施例對此不作具體限定。
應理解，在實際應用中，非虛假資源轉移中，大部分買家準備在電商平臺購買某一類商品時，往往會瀏覽與該類商品相關的賣家或者商戶，其在瀏覽這些商品並決定是否要購買時，往往會查看該類商品的價格、對該商品的介紹、其他買家對該商品的評價、以及銷售該類商品的賣家或商戶的信用值，等等資訊。而虛假資源轉移中，資源轉入方往往是為了一些不當利益為資源接收方也就是一些賣家或者商戶刷單並給好評，來提高這些賣家或者商戶的信用值，其在完成某一虛假資源轉移時，往往不會提前瀏覽與該類商品相關的賣家或者商戶，或者為了隱藏虛假交易的目的，而故意瀏覽一些與該商品相關的賣家或商戶。
儘管虛假資源轉移也有這些類似的行為資料，但究其動機與非虛假資源轉移在本質上並不相同，這便可以體現在資源轉入方在資源轉移之前的一系列行為資料中，比如虛假資源轉移和非虛假資源轉移中的資源轉入方在瀏覽各個賣家或商戶中的商品時的瀏覽時長、查看的賣家或商品的資訊內容上就會有較大的差異。本說明書一個或多個實施例基於這一點，不僅考慮了資源轉入方在待驗證資源轉移前的第一預定時間段內的歷史資源轉移資料，還深究了資源轉入方在待驗證資源轉移前第二預定時間段內的行為資料，從而提高了識別虛假資源轉移的準確性，進一步維護了其他資源轉入方也就是買家的權益。
步驟120，基於歷史資源轉移資料、行為資料和虛假資源轉移模型，判定待驗證資源轉移是否為虛假資源轉移；其中，虛假資源轉移模型基於歷史資源轉移訓練資料和對應的行為訓練資料訓練得到。
具體來說，基於歷史資源轉移資料、行為資料和虛假資源轉移模型，判定待驗證資源轉移是否為虛假資源轉移，則可以首先根據歷史資源轉移資料，確定歷史資源轉移特徵資料，並根據行為資料，確定行為特徵資料，最後，便可以根據歷史資源轉移特徵資料、行為特徵資料和虛假資源轉移模型，判定待驗證資源轉移是否為虛假資源轉移。
如圖2所示，為本說明書一個或多個實施例所提供的基於歷史資源轉移資料、行為資料和虛假資源轉移模型，判定待驗證資源轉移是否為虛假資源轉移過程示意圖。其中，歷史資源轉移資料包括圖2所示的買家資訊等資料，該買家資訊可以包括買家在此次資源轉移之前的第一預定時間段內的資源轉移次數、資源轉移額度等資訊，由於該歷史資源轉移資料是資源轉入方也就是買家在此次資源轉移之前的歷史資源轉移資料，不會再隨該資源轉入方的行為的變化而變化，因此可以也可以將該歷史資源轉移資料稱為靜態資料；行為資料包括圖2所示的商戶資訊、買賣家交易歷史和瀏覽日誌等資料，由於該行為資料會隨買家行為的變化而變化，因此也可以將該行為資料稱為動態資料。
在獲取了上述靜態資料和動態資料之後，便可以根據該靜態資料確定歷史資源轉移特徵資料，根據該動態資料，確定行為特徵資料。由於動態資料中可能會包括不能直接用向量表徵的資料比如商戶地址等資料，因此在根據動態資料，確定行為特徵資料時，還需要將動態資料中不能直接用向量表徵的資料進行序列資料編碼，也就是下文所述的向量化預處理。在分別確定了靜態資料和動態資料的特徵資料之後，便可以基於這兩個特徵資料和虛假資源轉移模型，將這兩個特徵資料進行拼接，通過二分類器演算法，確定此次的資源轉移是否為虛假資源轉移。
應理解，由於上述行為資料中可能會包括資源接收方也就是賣家或者商戶的ID等不能用向量直接表徵的資料，為了便於對行為資料的處理，因此，根據行為資料，確定行為特徵資料，則可以首先對行為資料中不能用向量直接表徵的資料進行向量化預處理，以將行為資料中的非向量資料轉換為向量資料；而由於行為資料中包括多個特徵維度的資料，為了統一這些特徵維度的資料的量綱，因此還要將經過向量化預處理後的行為資料進行歸一化處理，以得到行為特徵資料。其中，對行為資料進行向量化預處理的方式可以採用將字串轉換成向量形式的工具比如word2vector演算法、embedding演算法等。
如圖3所示，為本說明書一個或多個實施例提供的對行為資料進行處理的過程示意圖，在圖3中，可以將行為資料中不能直接用向量表徵的資料通過向量化預處理轉換為向量形式，如圖3中的“點擊瀏覽ID”資料即資源轉入方在資源轉移前瀏覽過的某一個商戶的ID，由於該資料為“00N5789Y218”即字串形式，不能直接用向量來表徵，為了便於對該行為資料的處理，可以通過word2vector演算法將該字串轉換為向量的形式，再將獲取的“本次瀏覽商戶資訊”和“瀏覽詳情資訊”通過向量的形式表徵，並將這些表徵為向量形式的行為資料拼接為一個多維向量，再通過歸一化處理統一量綱。
在基於歷史資源轉移資料、行為資料和虛假資源轉移模型，判定待驗證資源轉移是否為虛假資源轉移之前，可以通過有監督的二分類訓練方式和無監督的二分類訓練方式兩種方式來訓練得到虛假資源轉移模型：
(1)有監督的二分類訓練方式
首先，對歷史資源轉移訓練資料進行歸一化處理得到對應的歷史資源轉移特徵資料；再對行為訓練資料中不能用向量直接表徵的資料進行向量化預處理；然後，將經過向量化預處理後的行為訓練資料進行歸一化處理，得到對應的行為特徵資料；最後，將歷史資源轉移特徵資料、行為特徵資料及對應的資源轉移類型作為輸入，訓練得到虛假資源轉移模型，其中，資源轉移類型包括非虛假資源轉移和非虛假資源轉移。
在這種方式中，由於資源轉移類型包括非虛假資源轉移和非虛假資源轉移，因此，歷史資源轉移訓練資料和對應的行為訓練資料包括：多個非虛假資源轉移的資源轉入方的歷史資源轉移資料和對應的行為資料、以及多個虛假資源轉移的資源轉入方的歷史資源轉移資料和對應的行為資料；則虛假資源轉移模型基於歷史資源轉移訓練資料和對應的行為訓練資料訓練得到的過程，則可以包括：
步驟i，可以對多個非虛假資源轉移的資源轉入方的歷史資源轉移資料進行歸一化處理得到對應的多個非虛假資源轉移的歷史資源轉移特徵資料，對多個虛假資源轉移的資源轉入方的歷史資源轉移資料進行歸一化處理得到對應的多個虛假資源轉移的歷史資源轉移特徵資料，其中，多個非虛假資源轉移的資源轉入方的歷史資源轉移資料為資源轉入方在相應的非虛假資源轉移前的第一預定時間段內的歷史資源轉移資料，多個虛假資源轉移的資源轉入方的歷史資源轉移資料為資源轉入方在相應的虛假資源轉移前的第一預定時間段內的歷史資源轉移資料；
步驟ii，對多個非虛假資源轉移中對應的行為資料中不能用向量直接表徵的資料進行向量化預處理；對多個虛假資源轉移中對應的行為資料中不能用向量直接表徵的資料進行向量化預處理，其中，多個非虛假資源轉移中對應的行為資料為資源轉入方在相應的非虛假資源轉移前的第二預定時間段內的行為資料，多個虛假資源轉移中對應的行為資料為資源轉入方在相應的虛假資源轉移前的第二預定時間段內的行為資料；
步驟iii，將經過向量化預處理後的所述多個非虛假資源轉移中對應的行為資料進行歸一化處理，以得到多個非虛假資源轉移中對應的行為特徵資料；將經過向量化預處理後的多個虛假資源轉移中對應的行為資料進行歸一化處理，以得到多個虛假資源轉移中對應的行為特徵資料；
步驟iv，基於多個非虛假資源轉移的歷史資源轉移特徵資料和對應的行為特徵資料，以及多個虛假資源轉移的歷史資源轉移特徵資料和對應的行為特徵資料，訓練得到虛假資源轉移模型。在實際應用中，虛假資源轉移模組可以基於多個非虛假資源轉移的歷史資源轉移特徵資料和對應的行為特徵資料，以及多個虛假資源轉移的歷史資源轉移特徵資料和對應的行為特徵資料通過二分類器訓練得到，具體訓練方式可參考現有技術中相關模型訓練方法，不再贅述。
(2)無監督的二分類訓練方式
首先對歷史資源轉移訓練資料進行歸一化處理得到對應的歷史資源轉移特徵資料；然後，對行為訓練資料中不能用向量直接表徵的資料進行向量化預處理，並將經過向量化預處理後的行為訓練資料進行歸一化處理，得到對應的行為特徵資料；最後將歷史資源轉移特徵資料、行為特徵資料作為輸入，按二分類進行聚類訓練得到所述虛假資源轉移模型，具體訓練方式可參考現有技術中相關模型訓練方法，不再贅述。
通過獲取資源轉入方在待驗證資源轉移前第一預定時間段內的歷史資源轉移資料、和資源轉入方在待驗證資源轉移前第二預定時間段內的行為資料，基於獲取的歷史資源轉移資料、行為資料和虛假資源轉移模型，判定待驗證資源轉移是否為虛假資源轉移，不僅考慮了資源轉入方的歷史資源轉移資料，還將其在資源轉移前的行為資料作為判別識別虛假資源轉移的依據，提高了判別虛假資源轉移的準確性，達到優化識別虛假資源轉移的目的。
圖4是本說明書的一個實施例提供的判定虛假交易的方法的實施流程示意圖，包括：
步驟210，獲取交易支付方在待驗證交易前第一預定時間段內的歷史交易資料、和交易支付方在待驗證交易前第二預定時間段內的行為資料；
其中，歷史交易資料至少包括下述一種：歷史交易次數，歷史交易額度，歷史交易涉及的交易接收方的數量；行為資料至少包括下述一種：交易支付方瀏覽的交易接收方的資訊、瀏覽時長、瀏覽的商品資訊，交易接收方的資訊至少包括交易接收方的信用值、商品類別、商品價格分佈、健康程度。
步驟220，基於歷史資源轉移資料、行為資料和虛假交易模型，判定待驗證交易是否為虛假交易；虛假交易模型基於歷史交易訓練資料和對應的行為訓練資料訓練得到。
具體來說，基於歷史交易資料、行為資料和虛假交易模型，判定待驗證交易是否為虛假交易，則可以首先根據歷史交易資料，確定歷史交易特徵資料；然後，根據行為資料，確定行為特徵資料；最後，基於歷史交易特徵資料、行為特徵資料和虛假交易模型，判定待驗證交易是否為虛假交易。
可選的，根據行為資料，確定行為特徵資料，具體則可以首先，對行為資料中不能用向量直接表徵的資料進行向量化預處理；然後，將經過向量化預處理後的行為資料進行歸一化處理，以得到行為特徵資料。
在基於歷史交易資料、行為資料和虛假交易模型，判定待驗證交易是否為虛假交易之前，可以通過有監督的二分類訓練方式和無監督的二分類訓練方式兩種方式來訓練得到虛假交易模型：
(1)有監督的二分類訓練方式
首先，對歷史交易訓練資料進行歸一化處理得到對應的歷史交易特徵資料；再對行為訓練資料中不能用向量直接表徵的資料進行向量化預處理；然後，將經過向量化預處理後的行為訓練資料進行歸一化處理，得到對應的行為特徵資料；最後，將歷史交易特徵資料、行為特徵資料及對應的交易類型作為輸入，訓練得到虛假交易模型，其中，交易類型包括非虛假交易和非虛假交易。
(2)無監督的二分類訓練方式
首先對歷史交易訓練資料進行歸一化處理得到對應的歷史交易特徵資料；然後，對行為訓練資料中不能用向量直接表徵的資料進行向量化預處理，並將經過向量化預處理後的行為訓練資料進行歸一化處理，得到對應的行為特徵資料；最後將歷史交易特徵資料、行為特徵資料作為輸入，按二分類進行聚類訓練得到所述虛假交易模型。
圖4所示實施例相關步驟的具體實現可參考圖1~圖3所示實施例中對應的步驟的具體實現，本說明書一個或多個實施例在此不再贅述。
通過獲取交易支付方在待驗證交易前第一預定時間段內的歷史交易資料、和交易支付方在待驗證交易前第二預定時間段內的行為資料，基於獲取的歷史交易資料、行為資料和虛假交易模型，判定待驗證交易是否為虛假交易，不僅考慮了交易支付方也就是買家的歷史交易資料，還將其在交易前的行為資料作為判別識別虛假交易的依據，提高了判別虛假交易的準確性，達到優化識別虛假交易的目的。
圖5是本說明書的一個實施例提供的電子設備的結構示意圖。請參考圖5，在硬體層面，該電子設備包括處理器，可選地還包括內部匯流排、網路介面、記憶體。其中，記憶體可能包含記憶體，例如高速隨機存取記憶體(Random-Access Memory，RAM)，也可能還包括非易失性記憶體(non-volatile memory)，例如至少1個磁碟記憶體等。當然，該電子設備還可能包括其他服務所需要的硬體。
處理器、網路介面和記憶體可以通過內部匯流排相互連接，該內部匯流排可以是ISA(Industry Standard Architecture，工業標準架構)匯流排、PCI(Peripheral Component Interconnect，周邊組件互連標準)匯流排或EISA(Extended Industry Standard Architecture，延伸工業標準架構)匯流排等。所述匯流排可以分為位址匯流排、資料匯流排、控制匯流排等。為便於表示，圖5中僅用一個雙向箭頭表示，但並不表示僅有一根匯流排或一種類型的匯流排。
記憶體，用於存放程式。具體地，程式可以包括程式碼，所述程式碼包括電腦操作指令。記憶體可以包括記憶體和非易失性記憶體，並向處理器提供指令和資料。
處理器從非易失性記憶體中讀取對應的電腦程式到記憶體中然後運行，在邏輯層面上形成判定虛假資源轉移的裝置。處理器，執行記憶體所存放的程式，並具體用於執行以下操作：
獲取資源轉入方在待驗證資源轉移前第一預定時間段內的歷史資源轉移資料、和所述資源轉入方在所述待驗證資源轉移前第二預定時間段內的行為資料；
基於所述歷史資源轉移資料、所述行為資料和虛假資源轉移模型，判定所述待驗證資源轉移是否為虛假資源轉移；
其中，所述虛假資源轉移模型基於歷史資源轉移訓練資料和對應的行為訓練資料訓練得到。
上述如本說明書圖1所示實施例揭示的判定虛假資源轉移的方法可以應用於處理器中，或者由處理器實現。處理器可能是一種積體電路晶片，具有信號的處理能力。在實現過程中，上述方法的各步驟可以通過處理器中的硬體的集成邏輯電路或者軟體形式的指令完成。上述的處理器可以是通用處理器，包括中央處理器(Central Processing Unit，CPU)、網路處理器(Network Processor，NP)等；還可以是數位訊號處理器(Digital Signal Processor，DSP)、專用積體電路(Application Specific Integrated Circuit，ASIC)、現場可程式設計閘陣列(Field-Programmable Gate Array，FPGA)或者其他可程式設計邏輯裝置、分立閘或者電晶體邏輯裝置、分立硬體組件。可以實現或者執行本說明書一個或多個實施例中的公開的各方法、步驟及邏輯方塊圖。通用處理器可以是微處理器或者該處理器也可以是任何常規的處理器等。結合本說明書一個或多個實施例所公開的方法的步驟可以直接體現為硬體解碼處理器執行完成，或者用解碼處理器中的硬體及軟體模組組合執行完成。軟體模組可以位於隨機記憶體，快閃記憶體、唯讀記憶體，可程式設計唯讀記憶體或者電可讀寫可程式設計記憶體、暫存器等本領域成熟的儲存媒體中。該儲存媒體位於記憶體，處理器讀取記憶體中的資訊，結合其硬體完成上述方法的步驟。
該電子設備還可執行圖1的判定虛假資源轉移的方法，本說明書在此不再贅述。
當然，除了軟體實現方式之外，本說明書的電子設備並不排除其他實現方式，比如邏輯裝置抑或軟硬體結合的方式等等，也就是說以下處理流程的執行主體並不限定於各個邏輯單元，也可以是硬體或邏輯裝置。
圖6是本說明書的一個實施例電子設備的結構示意圖。請參考圖6，在硬體層面，該電子設備包括處理器，可選地還包括內部匯流排、網路介面、記憶體。其中，記憶體可能包含記憶體，例如高速隨機存取記憶體(Random-Access Memory，RAM)，也可能還包括非易失性記憶體(non-volatile memory)，例如至少1個磁碟記憶體等。當然，該電子設備還可能包括其他服務所需要的硬體。
處理器、網路介面和記憶體可以通過內部匯流排相互連接，該內部匯流排可以是ISA(Industry Standard Architecture，工業標準架構)匯流排、PCI(Peripheral Component Interconnect，周邊組件互連標準)匯流排或EISA(Extended Industry Standard Architecture，延伸工業標準架構)匯流排等。所述匯流排可以分為位址匯流排、資料匯流排、控制匯流排等。為便於表示，圖6中僅用一個雙向箭頭表示，但並不表示僅有一根匯流排或一種類型的匯流排。
記憶體，用於存放程式。具體地，程式可以包括程式碼，所述程式碼包括電腦操作指令。記憶體可以包括記憶體和非易失性記憶體，並向處理器提供指令和資料。
處理器從非易失性記憶體中讀取對應的電腦程式到記憶體中然後運行，在邏輯層面上形成判定虛假交易的裝置。處理器，執行記憶體所存放的程式，並具體用於執行以下操作：
獲取交易支付方在待驗證交易前第一預定時間段內的歷史交易資料、和所述交易支付方在所述待驗證交易前第二預定時間段內的行為資料；
基於所述歷史資源轉移資料、所述行為資料和虛假交易模型，判定所述待驗證交易是否為虛假交易；
其中，所述虛假交易模型基於歷史交易訓練資料和對應的行為訓練資料訓練得到。
上述如本說明書圖4所示實施例揭示的判定虛假交易的方法可以應用於處理器中，或者由處理器實現。處理器可能是一種積體電路晶片，具有信號的處理能力。在實現過程中，上述方法的各步驟可以通過處理器中的硬體的集成邏輯電路或者軟體形式的指令完成。上述的處理器可以是通用處理器，包括中央處理器(Central Processing Unit，CPU)、網路處理器(Network Processor，NP)等；還可以是數位訊號處理器(Digital Signal Processor，DSP)、專用積體電路(Application Specific Integrated Circuit，ASIC)、現場可程式設計閘陣列(Field-Programmable Gate Array，FPGA)或者其他可程式設計邏輯裝置、分立閘或者電晶體邏輯裝置、分立硬體組件。可以實現或者執行本說明書一個或多個實施例中的公開的各方法、步驟及邏輯方塊圖。通用處理器可以是微處理器或者該處理器也可以是任何常規的處理器等。結合本說明書一個或多個實施例所公開的方法的步驟可以直接體現為硬體解碼處理器執行完成，或者用解碼處理器中的硬體及軟體模組組合執行完成。軟體模組可以位於隨機記憶體，快閃記憶體、唯讀記憶體，可程式設計唯讀記憶體或者電可讀寫可程式設計記憶體、暫存器等本領域成熟的儲存媒體中。該儲存媒體位於記憶體，處理器讀取記憶體中的資訊，結合其硬體完成上述方法的步驟。
該電子設備還可執行圖4的判定虛假交易的方法，本說明書在此不再贅述。
當然，除了軟體實現方式之外，本說明書的電子設備並不排除其他實現方式，比如邏輯裝置抑或軟硬體結合的方式等等，也就是說以下處理流程的執行主體並不限定於各個邏輯單元，也可以是硬體或邏輯裝置。
圖7是本說明書提供的判定虛假資源轉移的裝置700的結構示意圖。請參考圖7，在一種軟體實施方式中，判定虛假資源轉移的裝置700可包括獲取單元701、判定單元702，其中：
獲取單元701，獲取資源轉入方在待驗證資源轉移前第一預定時間段內的歷史資源轉移資料、和所述資源轉入方在所述待驗證資源轉移前第二預定時間段內的行為資料；
判定單元702，基於所述歷史資源轉移資料、所述行為資料和虛假資源轉移模型，判定所述待驗證資源轉移是否為虛假資源轉移；
其中，所述虛假資源轉移模型基於歷史資源轉移訓練資料和對應的行為訓練資料訓練得到。
在一種實施方式中，所述判定單元702，
根據所述歷史資源轉移資料，確定歷史資源轉移特徵資料；
根據所述行為資料，確定行為特徵資料；
基於所述歷史資源轉移特徵資料、所述行為特徵資料和所述虛假資源轉移模型，判定所述待驗證資源轉移是否為虛假資源轉移。
在一種實施方式中，所述判定單元702，
對所述行為資料中不能用向量直接表徵的資料進行向量化預處理；
將經過所述向量化預處理後的行為資料進行歸一化處理，以得到所述行為特徵資料。
在一種實施方式中，在所述判定單元702基於所述歷史資源轉移資料、所述行為資料和虛假資源轉移模型，判定所述待驗證資源轉移是否為虛假資源轉移之前，所述裝置還包括：
第一處理單元703，對所述歷史資源轉移訓練資料進行歸一化處理得到對應的歷史資源轉移特徵資料；
第二處理單元704，對所述行為訓練資料中不能用向量直接表徵的資料進行向量化預處理；
第三處理單元705，將經過所述向量化預處理後的行為訓練資料進行歸一化處理，得到對應的行為特徵資料；
第一訓練單元706，將所述歷史資源轉移特徵資料、所述行為特徵資料及對應的資源轉移類型作為輸入，訓練得到所述虛假資源轉移模型，其中，所述資源轉移類型包括虛假資源轉移和非虛假資源轉移。
在一種實施方式中，在所述判定單元702基於所述歷史資源轉移資料、所述行為資料和虛假資源轉移模型，判定所述待驗證資源轉移是否為虛假資源轉移之前，所述裝置還包括：
第四處理單元707，對所述歷史資源轉移訓練資料進行歸一化處理得到對應的歷史資源轉移特徵資料；
第五處理單元708，對所述行為訓練資料中不能用向量直接表徵的資料進行向量化預處理，並將經過所述向量化預處理後的行為訓練資料進行歸一化處理，得到對應的行為特徵資料；
第二訓練單元709，將所述歷史資源轉移特徵資料、所述行為特徵資料作為輸入，按二分類進行聚類訓練得到所述虛假資源轉移模型。
在一種實施方式中，所述歷史資源轉移資料至少包括下述一種：
歷史資源轉移次數，歷史資源轉移額度，歷史資源轉移涉及的資源接收方的數量。
在一種實施方式中，所述行為資料至少包括下述一種：
所述資源轉入方瀏覽的資源接收方的資訊、瀏覽時長、瀏覽的資源資訊，所述資源接收方的資訊至少包括所述資源接收方的信用值、資源類別、資源價值分佈、健康程度。
判定虛假資源轉移的裝置700能夠實現圖1~圖3的方法實施例的方法，具體可參考圖1所示實施例的判定虛假資源轉移的方法，不再贅述。
圖8是本說明書提供的判定虛假交易的裝置800的結構示意圖。請參考圖8，在一種軟體實施方式中，判定虛假交易的裝置800可包括獲取單元801、判定單元802，其中：
獲取單元，獲取交易支付方在待驗證交易前第一預定時間段內的歷史交易資料、和所述交易支付方在所述待驗證交易前第二預定時間段內的行為資料；
判定單元，基於所述歷史資源轉移資料、所述行為資料和虛假交易模型，判定所述待驗證交易是否為虛假交易；
其中，所述虛假交易模型基於歷史交易訓練資料和對應的行為訓練資料訓練得到。
在一種實施方式中，所述判定單元802，
基於所述歷史交易資料、所述行為資料和虛假交易模型，判定所述待驗證交易是否為虛假交易，包括：
根據所述歷史交易資料，確定歷史交易特徵資料；
根據所述行為資料，確定行為特徵資料；
基於所述歷史交易特徵資料、所述行為特徵資料和所述虛假交易模型，判定所述待驗證交易是否為虛假交易。
在一種實施方式中，所述判定單元802，
對所述行為資料中不能用向量直接表徵的資料進行向量化預處理；
將經過所述向量化預處理後的行為資料進行歸一化處理，以得到所述行為特徵資料。
在一種實施方式中，在所述判定單元802基於所述歷史交易資料、所述行為資料和虛假交易模型，判定所述待驗證交易是否為虛假交易之前，所述裝置還包括：
第一處理單元803，對所述歷史交易訓練資料進行歸一化處理得到對應的歷史交易特徵資料；
第二處理單元804，對所述行為訓練資料中不能用向量直接表徵的資料進行向量化預處理；
第三處理單元805，將經過所述向量化預處理後的行為訓練資料進行歸一化處理，得到對應的行為特徵資料；
第一訓練單元806，將所述歷史交易特徵資料、所述行為特徵資料及對應的交易類型作為輸入，訓練得到所述虛假交易模型，其中，所述交易類型包括虛假交易和非虛假交易。
在一種實施方式中，在所述判定單元802基於所述歷史交易資料、所述行為資料和虛假交易模型，判定所述待驗證交易是否為虛假交易之前，所述裝置還包括：
第四處理單元807，對所述歷史交易訓練資料進行歸一化處理得到對應的歷史交易特徵資料；
第五處理單元808，對所述行為訓練資料中不能用向量直接表徵的資料進行向量化預處理，並將經過所述向量化預處理後的行為訓練資料進行歸一化處理，得到對應的行為特徵資料；
第二訓練單元809，將所述歷史交易特徵資料、所述行為特徵資料作為輸入，按二分類進行聚類訓練得到所述虛假交易模型。
在一種實施方式中，所述歷史交易資料至少包括下述一種：
歷史交易次數，歷史交易額度，歷史交易涉及的交易接收方的數量。
在一種實施方式中，所述行為資料至少包括下述一種：
所述交易支付方瀏覽的交易接收方的資訊、瀏覽時長、瀏覽的資源資訊，所述交易接收方的資訊至少包括所述交易接收方的信用值、商品類別、商品價值分佈、健康程度。
判定虛假交易的裝置800能夠實現圖4的方法實施例的方法，具體可參考圖4所示實施例的判定虛假交易的方法，不再贅述。
總之，以上所述僅為本說明書的較佳實施例而已，並非用於限定本說明書的保護範圍。凡在本說明書一個或多個實施例的精神和原則之內，所作的任何修改、等同替換、改進等，均應包含在本說明書一個或多個實施例的保護範圍之內。
上述實施例闡明的系統、裝置、模組或單元，具體可以由電腦晶片或實體實現，或者由具有某種功能的產品來實現。一種典型的實現設備為電腦。具體的，電腦例如可以為個人電腦、膝上型電腦、蜂巢式電話、相機電話、智慧型電話、個人數位助理、媒體播放機、導航設備、電子郵件設備、遊戲控制台、平板電腦、可穿戴設備或者這些設備中的任何設備的組合。
電腦可讀媒體包括永久性和非永久性、可移動和非可移動媒體可以由任何方法或技術來實現資訊儲存。資訊可以是電腦可讀指令、資料結構、程式的模組或其他資料。電腦的儲存媒體的例子包括，但不限於相變記憶體(PRAM)、靜態隨機存取記憶體(SRAM)、動態隨機存取記憶體(DRAM)、其他類型的隨機存取記憶體(RAM)、唯讀記憶體(ROM)、電可擦除可程式設計唯讀記憶體(EEPROM)、快閃記憶體或其他記憶體技術、唯讀光碟唯讀記憶體(CD-ROM)、數位多功能光碟(DVD)或其他光學儲存、磁盒式磁帶，磁帶磁磁片儲存或其他磁性存放裝置或任何其他非傳輸媒體，可用於儲存可以被計算設備存取的資訊。按照本文中的界定，電腦可讀媒體不包括暫存電腦可讀媒體(transitory media)，如調變的資料信號和載波。
還需要說明的是，術語“包括”、“包含”或者其任何其他變體意在涵蓋非排他性的包含，從而使得包括一系列要素的過程、方法、商品或者設備不僅包括那些要素，而且還包括沒有明確列出的其他要素，或者是還包括為這種過程、方法、商品或者設備所固有的要素。在沒有更多限制的情況下，由語句“包括一個……”限定的要素，並不排除在包括所述要素的過程、方法、商品或者設備中還存在另外的相同要素。
本說明書中的各個實施例均採用遞進的方式描述，各個實施例之間相同相似的部分互相參見即可，每個實施例重點說明的都是與其他實施例的不同之處。尤其，對於系統實施例而言，由於其基本相似於方法實施例，所以描述的比較簡單，相關之處參見方法實施例的部分說明即可。In order to make the purpose, technical solution, and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described in combination with specific embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in this application, all other embodiments obtained by a person of ordinary skill in the art without making progressive labor fall within the protection scope of this application.
The technical solutions provided by the embodiments of the present application will be described in detail below with reference to the accompanying drawings.
In order to solve the problem that the method for determining false transactions in the prior art is insufficiently optimized, the embodiment of the present specification provides a method for determining the transfer of false resources. The execution subject of the method for determining the transfer of false resources provided in the embodiments of the present specification may be, but is not limited to, a server, a personal computer, and the like that can be configured to execute at least one of the method terminals provided by the embodiments of the present invention.
For the convenience of description, the following describes the implementation of the method by taking the execution subject of the method as a server capable of executing the method as an example. It can be understood that the execution subject of the method as a server is only an exemplary description, and should not be understood as a limitation on the method.
Specifically, a schematic flowchart of a method for determining a false resource transfer provided by one or more embodiments of this specification is shown in FIG. 1 and includes:
Step 110: Obtain historical resource transfer data in the first predetermined period of time before the transfer of the resource to be verified, and behavior data of the resource transferer in the second predetermined period of time before the transfer of the resource to be verified;
The historical resource transfer data includes at least one of the following: the number of historical resource transfers, the historical resource transfer quota, and the number of resource receivers involved in the historical resource transfer. In practical applications, the resource transfer can be, for example, a transaction. The historical resource transfer data can include: historical transaction times, historical transaction quotas, and the number of transaction receivers involved in historical transactions, that is, sellers or merchants. The largest single transaction is Value, the minimum value of a single transaction, the average value of a single transaction, the maximum value of a daily transaction, the minimum value of a daily transaction, the average value of a daily transaction, etc., can be used as transaction payers, that is, buyers ’historical transaction data before the transaction .
Among them, the behavioral data includes at least one of the following: the information of the resource receiver viewed by the transferee, the duration of the browse, and the information of the resource viewed. The information of the resource receiver includes at least the credit value, resource category, and resource value of the resource receiver. Distribution, health. In actual application, the behavior data may specifically include: information of sellers or merchants that the buyer viewed before completing the transaction, and the length of stay of each seller or merchant when browsing, and the information Product information (such as product name, price, etc.), where the seller or merchant's information includes the credit value of the seller or merchant, the product category in the merchant, the price distribution of the product, and the merchant's recent complaint (such as in the past month). The number of times, and so on.
In addition, the first predetermined time period may be a period of time before the resource transferee is before the resource transfer, such as a period of three months, one month, or one week before the resource transfer, and the second reservation The time period may be a period of days or days or hours before the transfer of resources to the resource. The first predetermined time period and the second predetermined time period may be set according to actual needs. Multiple embodiments do not specifically limit this.
It should be understood that in practical applications, in the transfer of non-fake resources, most buyers tend to browse the sellers or merchants related to such products when they are buying certain types of products on the e-commerce platform, and they are browsing these products and deciding whether to When you want to buy, you often check the price of the product, the introduction of the product, the evaluation of the product by other buyers, and the credit value of the seller or merchant selling the product. In the transfer of false resources, the transferee of the resource often orders and gives favorable comments to the receiver of the resource, that is, some sellers or merchants, to improve the credit value of these sellers or merchants. , Often do not browse in advance sellers or merchants related to this type of goods, or for the purpose of hiding false transactions, intentionally browse some sellers or merchants related to this product.
Although there are similar behavioral data in the transfer of false resources, the motivation is not the same as the transfer of non-false resources. This can be reflected in a series of behavioral data of the transferee before the resource transfer, such as false resources. The resource transferee in the transfer and non-false resource transfer will have a large difference in the browsing time when viewing the products in various sellers or merchants, and the content of the information of the seller or the product being viewed. Based on this, one or more embodiments of this specification not only consider the historical resource transfer data of the resource transferor in the first predetermined time period before the resource transfer to be verified, but also delve into the resource transfer party's transfer of the resource to be verified. The behavior data within the second predetermined time period improves the accuracy of identifying false resource transfers and further protects the rights of other transferees, namely buyers.
Step 120: Determine whether the resource transfer to be verified is a false resource transfer based on historical resource transfer data, behavior data, and a false resource transfer model. The false resource transfer model is obtained based on historical resource transfer training data and corresponding behavior training data.
Specifically, based on historical resource transfer data, behavior data, and false resource transfer models, to determine whether the resource transfer to be verified is a false resource transfer, you can first determine historical resource transfer characteristic data based on historical resource transfer data, and based on behavior data, After determining the behavior characteristic data, finally, according to the historical resource transfer characteristic data, the behavior characteristic data, and the false resource transfer model, it can be determined whether the resource to be verified is a false resource transfer.
As shown in FIG. 2, a schematic diagram of a process for determining whether a resource transfer to be verified is a false resource transfer based on historical resource transfer data, behavior data, and a false resource transfer model provided by one or more embodiments of the present specification. The historical resource transfer data includes buyer information and other data shown in FIG. 2. The buyer information may include information such as the number of resource transfers and resource transfer quotas of the buyer in the first predetermined time period before the resource transfer. Since the historical resource transfer data is the historical resource transfer information of the resource transferor, that is, the buyer before the resource transfer, it will not change with the behavior of the resource transferor, so the history can also be changed. Resource transfer data is called static data; behavioral data includes information such as merchant information, buyer and seller transaction history, and browsing logs shown in Figure 2. Since this behavioral data will change with changes in buyer behavior, you can also use this behavioral data Called dynamic data.
After the above static data and dynamic data are obtained, historical resource transfer characteristic data can be determined based on the static data, and behavior characteristic data can be determined based on the dynamic data. Because dynamic data may include data that cannot be directly characterized by vectors, such as business address and other information, when determining behavioral characteristics data based on dynamic data, you also need to encode sequence data that cannot be directly characterized by vectors. This is the vectorized preprocessing described below. After the feature data of the static data and the dynamic data are determined separately, the two feature data can be stitched based on the two feature data and the false resource transfer model, and the resource transfer is determined by the two classifier algorithm. Whether it is a false resource transfer.
It should be understood that, because the above behavioral data may include data that cannot be directly characterized by vectors, such as the ID of the resource receiver, that is, the seller or the merchant, in order to facilitate the processing of the behavioral data, therefore, based on the behavioral data, determine the behavioral characteristic data, You can first perform vectorization preprocessing on data that cannot be directly characterized by vectors in behavior data to convert non-vector data in behavior data to vector data; and because behavior data includes data with multiple feature dimensions, in order to unify these features The dimension of the dimensional data, so the behavior data after vectorization preprocessing should be normalized to obtain behavior characteristic data. Among them, a method for performing vectorization preprocessing on behavior data may use a tool that converts a string into a vector form, such as a word2vector algorithm, an embedding algorithm, and the like.
As shown in FIG. 3, a schematic diagram of a process for processing behavior data provided by one or more embodiments of the present specification. In FIG. 3, data that cannot be directly characterized by vectors in the behavior data can be converted into vectorized preprocessing into Vector format, as shown in the "click to browse ID" data in Figure 3, that is, the ID of a certain business that the resource transferee viewed before the resource transfer. Because the data is in the form of "00N5789Y218", it cannot be directly represented by vectors. In order to facilitate the processing of this behavioral data, the word2vector algorithm can be used to convert the string into a vector form, and then the "browser information" and "browse details information" obtained in this form are represented by vectors, and These behavioral data, which is characterized as a vector, are spliced into a multi-dimensional vector, which is then processed to a unified dimension through normalization.
Before judging whether the resource transfer to be verified is a false resource transfer based on historical resource transfer data, behavioral data, and false resource transfer models, it can be trained through two methods: supervised binary classification training method and unsupervised binary classification training method. False resource transfer model:
(1) Supervised binary classification training method First, normalize historical resource transfer training data to obtain corresponding historical resource transfer feature data; then perform vectorization preprocessing on data that cannot be directly characterized by vectors in behavior training data ; Then, normalize the behavior training data after vectorization preprocessing to obtain the corresponding behavior feature data; finally, take the historical resource transfer feature data, behavior feature data, and the corresponding resource transfer type as inputs, and get False resource transfer model, where the types of resource transfer include non-false resource transfer and non-false resource transfer.
In this way, since the types of resource transfer include non-fake resource transfers and non-fake resource transfers, historical resource transfer training materials and corresponding behavioral training materials include: multiple non-fake resource transfer resource transferees ’historical resources Transfer data and corresponding behavior data, and historical resource transfer data and corresponding behavior data of multiple transferees of false resource transfers; the false resource transfer model is based on historical resource transfer training data and corresponding behavior training data. The process can include:
Step i: Normalize the historical resource transfer data of the multiple transferees of the non-false resource transfer to obtain the corresponding historical resource transfer characteristics of the multiple non-false resource transfers, and transfer the resources of the multiple false resources. The historical resource transfer data of the transferee is normalized to obtain the corresponding historical resource transfer feature data of multiple false resource transfers. Among them, the historical resource transfer data of the multiple transferees that are not false resource transfers is the resource transfer. Historical resource transfer data for the first predetermined time period before the corresponding non-fake resource transfer, and the historical resource transfer data for the multiple resource transferees for the false resource transfer is the resource transfer party ’s data before the corresponding false resource transfer. Historical resource transfer data within the first predetermined time period;
Step ii, perform vectorization preprocessing on data that cannot be directly represented by vectors in the corresponding behavior data in multiple non-fake resource transfers; perform vectorization on data that cannot be directly represented by the vector in the corresponding behavior data in multiple false resource transfers Preprocessing, in which the corresponding behavior data in the multiple non-fake resource transfers is the behavior data of the resource transferor in the second predetermined time period before the corresponding non-fake resource transfer, and the corresponding behavior in the multiple false resource transfers The data is the behavior data of the transferee in the second predetermined time period before the transfer of the corresponding false resources;
Step iii: Normalize the behavior data corresponding to the multiple non-fake resource transfers after vectorization preprocessing to obtain corresponding behavior characteristic data in the multiple non-fake resource transfers; Normalize the corresponding behavioral data in the processed multiple false resource transfers to obtain the corresponding behavioral characteristic data in the multiple false resource transfers;
In step iv, a false resource transfer model is trained based on historical resource transfer characteristic data and corresponding behavior characteristic data of multiple non-false resource transfers, and historical resource transfer characteristic data and corresponding behavior characteristic data of multiple false resource transfers. In practical applications, the false resource transfer module can pass historical resource transfer feature data and corresponding behavior feature data of multiple non-false resource transfers, as well as historical resource transfer feature data and corresponding behavior feature data of multiple false resource transfers. The two classifiers are obtained through training. For specific training methods, reference may be made to related model training methods in the prior art, and details are not described again.
(2) Unsupervised binary classification training method First, normalize the historical resource transfer training data to obtain the corresponding historical resource transfer feature data; then, perform vectorization preprocessing on the data in the behavior training data that cannot be directly characterized by vectors. , And normalize the behavior training data after vectorized preprocessing to obtain the corresponding behavior feature data; finally, take the historical resource transfer feature data and behavior feature data as input, and perform cluster training according to the two classifications to obtain the For a false resource transfer model, the specific training method can refer to the related model training method in the prior art, and will not be described again.
Based on the acquired historical resources, the historical resource transfer data of the resource transferee within the first predetermined period of time before the transfer of the resource to be verified and the behavior data of the resource transferee within the second predetermined period of time before the resource to be verified are transferred. Transfer data, behavior data, and false resource transfer models to determine whether the resource transfer to be verified is a false resource transfer. Not only the historical resource transfer data of the resource transferor is considered, but also its behavior data before the resource transfer is used to identify the false resource. The basis of the transfer improves the accuracy of judging the transfer of false resources and achieves the purpose of optimizing and identifying the transfer of false resources.
FIG. 4 is a schematic diagram of an implementation process of a method for determining a false transaction according to an embodiment of the present specification, including:
Step 210: Obtain historical transaction data of the transaction payer in the first predetermined time period before the transaction to be verified, and behavior data of the transaction payer in the second predetermined time period before the transaction to be verified;
Among them, historical transaction data includes at least one of the following: historical transaction times, historical transaction quotas, and the number of transaction receivers involved in historical transactions; behavioral data includes at least one of the following: information of transaction receivers viewed by transaction payers, Long, browsed product information, and the information of the transaction receiver includes at least the credit value of the transaction receiver, the product category, the price distribution of the product, and the health level.
Step 220: Determine whether the transaction to be verified is a false transaction based on historical resource transfer data, behavior data, and a false transaction model; the false transaction model is trained based on historical transaction training data and corresponding behavior training data.
Specifically, based on historical transaction data, behavior data, and false transaction models, to determine whether the transaction to be verified is a false transaction, you can first determine historical transaction characteristic data based on historical transaction data; then, determine behavior characteristic data based on behavior data; Finally, based on historical transaction characteristic data, behavior characteristic data, and false transaction models, determine whether the transaction to be verified is a false transaction.
Optionally, the behavior characteristic data is determined according to the behavior data. Specifically, first, vectorized preprocessing is performed on the data in the behavior data that cannot be directly represented by vectors; then, the behavior data after the vectorized preprocessing is normalized. Processing to obtain behavioral characteristics.
Before judging whether the transaction to be verified is a false transaction based on historical transaction data, behavioral data, and false transaction models, the false transaction model can be trained through two methods: supervised binary classification training method and unsupervised binary classification training method:
(1) Supervised binary classification training method First, normalize historical transaction training data to obtain corresponding historical transaction feature data; then perform vectorized preprocessing on behavior training data that cannot be directly characterized by vectors; then , Normalize the behavior training data after vectorized preprocessing to obtain corresponding behavior characteristic data; finally, use historical transaction characteristic data, behavior characteristic data and corresponding transaction types as inputs to train to obtain false transaction models, Among them, transaction types include non-false transactions and non-false transactions.
(2) The unsupervised binary classification training method first normalizes the historical transaction training data to obtain the corresponding historical transaction feature data; then, performs vectorization preprocessing on the behavior training data that cannot be directly characterized by vectors, and The normalized processing of the behavior training data after vector preprocessing is performed to obtain corresponding behavior characteristic data. Finally, historical transaction characteristic data and behavior characteristic data are used as input, and cluster training is performed according to two classifications to obtain the false transaction model. .
For specific implementation of the steps in the embodiment shown in FIG. 4, reference may be made to the specific implementation of the corresponding steps in the embodiments shown in FIG. 1 to FIG. 3, and one or more embodiments of this specification will not be repeated here.
By obtaining historical transaction data of the transaction payer in the first predetermined time period before the transaction to be verified, and behavior data of the transaction payer in the second predetermined time period before the transaction to be verified, The false transaction model determines whether the transaction to be verified is a false transaction, not only taking into account the historical transaction data of the transaction payer, that is, the buyer, but also using its behavioral data before the transaction as the basis for identifying and identifying false transactions, which improves the identification of false transactions. Accuracy to achieve the purpose of optimizing and identifying false transactions.
FIG. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present specification. Please refer to FIG. 5. At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. Wait. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory can be connected to each other through an internal bus. The internal bus can be an ISA (Industry Standard Architecture, Industry Standard Architecture) bus, and a PCI (Peripheral Component Interconnect) bus. Or EISA (Extended Industry Standard Architecture, extended industry standard architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only a two-way arrow is used in FIG. 5, but it does not mean that there is only one bus or one type of bus.
Memory for programs. Specifically, the program may include code, and the code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.
The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to form a device for judging the transfer of false resources on a logical level. The processor executes programs stored in the memory and is specifically used to perform the following operations:
Acquiring historical resource transfer data of a resource transferee within a first predetermined time period before the resource to be verified is transferred, and behavioral data of the resource transfer party within a second predetermined time period before the resource to be verified is transferred;
Determining whether the resource transfer to be verified is a false resource transfer based on the historical resource transfer data, the behavior data, and a false resource transfer model;
The false resource transfer model is obtained based on training data of historical resource transfer training and corresponding behavior training data.
The foregoing method for determining a false resource transfer disclosed in the embodiment shown in FIG. 1 of this specification may be applied to a processor, or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method may be completed by an integrated logic circuit of hardware in a processor or an instruction in a form of software. The above processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc .; it may also be a Digital Signal Processor (DSP), a dedicated Integrated Circuit (Application Specific Integrated Circuit, ASIC), Field Programmable Gate Array (FPGA), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. Various methods, steps, and logic block diagrams disclosed in one or more embodiments of this specification may be implemented or executed. A general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in combination with one or more embodiments of the present specification can be directly embodied as being executed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium such as a random memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically readable and writable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
The electronic device may also execute the method for determining a false resource transfer in FIG. 1, which is not described in this specification.
Of course, in addition to the software implementation, the electronic device in this specification does not exclude other implementations, such as logical devices or a combination of hardware and software. In other words, the execution body of the following processing flow is not limited to each logical unit. , It can also be a hardware or logical device.
FIG. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present specification. Please refer to FIG. 6. At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. Wait. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory can be connected to each other through an internal bus. The internal bus can be an ISA (Industry Standard Architecture, Industry Standard Architecture) bus, and a PCI (Peripheral Component Interconnect) bus. Or EISA (Extended Industry Standard Architecture, extended industry standard architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, only a two-way arrow is used in FIG. 6, but it does not mean that there is only one bus or one type of bus.
Memory for programs. Specifically, the program may include code, and the code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.
The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to form a device for judging false transactions on a logical level. The processor executes programs stored in the memory and is specifically used to perform the following operations:
Obtaining historical transaction data of a transaction payer within a first predetermined time period before a transaction to be verified, and behavioral data of the transaction payer within a second predetermined time period before the transaction to be verified;
Determining whether the transaction to be verified is a false transaction based on the historical resource transfer data, the behavior data, and a false transaction model;
Wherein, the false trading model is obtained by training based on historical trading training data and corresponding behavior training data.
The method for determining a false transaction disclosed in the embodiment shown in FIG. 4 of the present specification may be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method may be completed by an integrated logic circuit of hardware in a processor or an instruction in a form of software. The above processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc .; it may also be a Digital Signal Processor (DSP), a dedicated Integrated Circuit (Application Specific Integrated Circuit, ASIC), Field Programmable Gate Array (FPGA), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. Various methods, steps, and logic block diagrams disclosed in one or more embodiments of this specification may be implemented or executed. A general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in combination with one or more embodiments of the present specification can be directly embodied as being executed by a hardware decoding processor, or executed and completed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium such as a random memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically readable and writable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
The electronic device may also execute the method for determining a false transaction in FIG. 4, which is not described in this specification.
Of course, in addition to the software implementation, the electronic device in this specification does not exclude other implementations, such as logical devices or a combination of hardware and software. In other words, the execution body of the following processing flow is not limited to each logical unit. , It can also be a hardware or logical device.
FIG. 7 is a schematic structural diagram of an apparatus 700 for determining a false resource transfer provided in this specification. Referring to FIG. 7, in a software implementation, the apparatus 700 for determining a false resource transfer may include an obtaining unit 701 and a determining unit 702, where:
The obtaining unit 701 obtains historical resource transfer data of a resource transferee within a first predetermined time period before the resource to be verified is transferred, and the behavior of the resource transferee within a second predetermined time period before the resource to be verified is transferred data;
A determining unit 702, based on the historical resource transfer data, the behavior data, and a false resource transfer model, determining whether the resource transfer to be verified is a false resource transfer;
The false resource transfer model is obtained based on training data of historical resource transfer training and corresponding behavior training data.
In an implementation manner, the determining unit 702,
Determining historical resource transfer characteristic data according to the historical resource transfer data;
Determining behavior characteristic data according to said behavior data;
Based on the historical resource transfer characteristic data, the behavior characteristic data, and the false resource transfer model, it is determined whether the resource to be verified is a false resource transfer.
In an implementation manner, the determining unit 702,
Vectorize preprocessing of the behavior data that cannot be directly characterized by vectors;
Normalize the behavior data after the vectorization preprocessing to obtain the behavior characteristic data.
In one embodiment, before the determining unit 702 determines whether the resource to be verified is a false resource transfer based on the historical resource transfer data, the behavior data, and a false resource transfer model, the device further includes:
A first processing unit 703, performing normalization processing on the historical resource transfer training data to obtain corresponding historical resource transfer feature data;
A second processing unit 704, performing vectorized preprocessing on the behavior training data that cannot be directly characterized by a vector;
The third processing unit 705 performs normalization processing on the behavior training data after the vectorization preprocessing to obtain corresponding behavior characteristic data;
The first training unit 706 receives the historical resource transfer characteristic data, the behavior characteristic data, and the corresponding resource transfer type as inputs to obtain the false resource transfer model, where the resource transfer type includes false resource transfer Non-fake resource transfers.
In one embodiment, before the determining unit 702 determines whether the resource to be verified is a false resource transfer based on the historical resource transfer data, the behavior data, and a false resource transfer model, the device further includes:
A fourth processing unit 707, performing normalization processing on the historical resource transfer training data to obtain corresponding historical resource transfer feature data;
A fifth processing unit 708 performs vectorization preprocessing on the behavior training data that cannot be directly characterized by vectors, and normalizes the behavior training data after the vectorization preprocessing to obtain corresponding behaviors. Characteristic information
The second training unit 709 takes the historical resource transfer feature data and the behavior feature data as inputs, and performs cluster training according to two classifications to obtain the false resource transfer model.
In one embodiment, the historical resource transfer data includes at least one of the following:
The number of historical resource transfers, the historical resource transfer quota, and the number of resource receivers involved in the historical resource transfer.
In one embodiment, the behavior data includes at least one of the following:
The information of the resource transferee browsed by the resource transferee, the browsing duration, and the resource information browsed. The information of the resource receiver includes at least the credit value, resource category, resource value distribution, and health of the resource receiver. .
The apparatus 700 for judging false resource transfer can implement the method embodiment of the method in FIG. 1 to FIG. 3. For details, refer to the method for judging false resource transfer in the embodiment shown in FIG. 1, and details are not described again.
FIG. 8 is a schematic structural diagram of a device 800 for determining a false transaction provided in this specification. Please refer to FIG. 8. In a software implementation, the device 800 for determining a false transaction may include an obtaining unit 801 and a determining unit 802, where:
An acquiring unit, which acquires historical transaction data of a transaction payer within a first predetermined time period before a transaction to be verified, and behavior data of the transaction payer within a second predetermined time period before the transaction to be verified;
A determining unit, based on the historical resource transfer data, the behavior data, and a false transaction model, determining whether the transaction to be verified is a false transaction;
Wherein, the false trading model is obtained by training based on historical trading training data and corresponding behavior training data.
In an implementation manner, the determining unit 802,
Determining whether the transaction to be verified is a false transaction based on the historical transaction data, the behavior data, and a false transaction model includes:
Determining historical transaction characteristic data according to said historical transaction data;
Determining behavior characteristic data according to said behavior data;
Based on the historical transaction characteristic data, the behavior characteristic data, and the false transaction model, it is determined whether the transaction to be verified is a false transaction.
In an implementation manner, the determining unit 802,
Vectorize preprocessing of the behavior data that cannot be directly characterized by vectors;
Normalize the behavior data after the vectorization preprocessing to obtain the behavior characteristic data.
In one embodiment, before the determining unit 802 determines whether the transaction to be verified is a false transaction based on the historical transaction data, the behavior data, and a false transaction model, the device further includes:
A first processing unit 803, performing normalization processing on the historical transaction training data to obtain corresponding historical transaction characteristic data;
A second processing unit 804, performing vectorization preprocessing on data in the behavior training data that cannot be directly characterized by vectors;
A third processing unit 805, performing normalization processing on the behavior training data after the vectorization preprocessing to obtain corresponding behavior characteristic data;
The first training unit 806 receives the historical transaction characteristic data, the behavior characteristic data, and corresponding transaction types as inputs, and obtains the false transaction model. The transaction types include false transactions and non-false transactions.
In one embodiment, before the determining unit 802 determines whether the transaction to be verified is a false transaction based on the historical transaction data, the behavior data, and a false transaction model, the device further includes:
A fourth processing unit 807, performing normalization processing on the historical transaction training data to obtain corresponding historical transaction characteristic data;
The fifth processing unit 808 performs vectorization preprocessing on the behavior training data that cannot be directly characterized by vectors, and normalizes the behavior training data after the vectorization preprocessing to obtain corresponding behaviors. Characteristic information
The second training unit 809 takes the historical transaction characteristic data and the behavior characteristic data as inputs, and performs cluster training according to two classifications to obtain the false transaction model.
In one embodiment, the historical transaction data includes at least one of the following:
The number of historical transactions, the historical transaction quota, and the number of transaction receivers involved in historical transactions.
In one embodiment, the behavior data includes at least one of the following:
The information of the transaction receiver viewed by the transaction payer, the browsing duration, and the resource information browsed. The information of the transaction receiver includes at least the credit value of the transaction receiver, the product category, the value distribution of the product, and the health degree.
The device 800 for determining a false transaction can implement the method of the method embodiment in FIG. 4. For details, refer to the method for determining a false transaction in the embodiment shown in FIG. 4, and details are not described herein again.
In short, the above descriptions are merely preferred embodiments of the present specification, and are not intended to limit the protection scope of the present specification. Any modification, equivalent replacement, or improvement made within the spirit and principle of one or more embodiments of this specification shall be included in the protection scope of one or more embodiments of this specification.
The system, device, module, or unit described in the foregoing embodiments may be specifically implemented by a computer chip or entity, or by a product having a certain function. A typical implementation is a computer. Specifically, the computer may be, for example, a personal computer, a laptop, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable Device or any combination of these devices.
Computer-readable media includes permanent and non-permanent, removable and non-removable media. Information can be stored by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), and other types of random access memory (RAM) , Read-only memory (ROM), electrically erasable and programmable read-only memory (EEPROM), flash memory or other memory technologies, read-only disc read-only memory (CD-ROM), digital multifunction Optical discs (DVDs) or other optical storage, magnetic tape cartridges, magnetic tape storage or other magnetic storage devices or any other non-transmitting media may be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.
It should also be noted that the terms "including,""including," or any other variation thereof are intended to encompass non-exclusive inclusion, so that a process, method, product, or device that includes a range of elements includes not only those elements, but also Other elements not explicitly listed, or those that are inherent to such a process, method, product, or device. Without more restrictions, the elements defined by the sentence "including a ..." do not exclude the existence of other identical elements in the process, method, product or equipment including the elements.
Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For the relevant part, refer to the description of the method embodiment.
700‧‧‧判定虛假資源轉移的裝置700‧‧‧ Device for determining false resource transfer
701‧‧‧獲取單元 701‧‧‧ Acquisition Unit
702‧‧‧判定單元 702‧‧‧Judgment unit
800‧‧‧判定虛假交易的裝置 800‧‧‧ Device for determining false transactions
801‧‧‧獲取單元 801‧‧‧ Acquisition Unit
802‧‧‧判定單元 802‧‧‧Judgment unit
此處所說明的附圖用來提供對本申請案的進一步理解，構成本申請案的一部分，本申請案的示意性實施例及其說明用於解釋本申請案，並不構成對本申請案的不當限定。在附圖中：The drawings described here are used to provide a further understanding of the present application and constitute a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the application and do not constitute an improper limitation on the application. . In the drawings:
圖1為本說明書一個實施例提供的一種判定虛假資源轉移的方法的實現流程示意圖； FIG. 1 is a schematic flowchart of a method for determining a false resource transfer provided by an embodiment of the present specification; FIG.
圖2為本說明書一個實施例提供的一種判定虛假交易的方法的實現流程示意圖； FIG. 2 is a schematic flowchart of a method for determining a false transaction provided by an embodiment of the present specification; FIG.
圖3為本說明書一個實施例提供的一種判定虛假交易的方法的資料處理過程示意圖； 3 is a schematic diagram of a data processing process of a method for determining a false transaction provided by an embodiment of the present specification;
圖4為本說明書一個實施例提供的一種判定虛假交易的方法中對行為資料進行向量化預處理的過程示意圖； FIG. 4 is a schematic diagram of a process of vectorized preprocessing of behavior data in a method for determining a false transaction provided by an embodiment of the present specification; FIG.
圖5為本說明書一個實施例提供的一種電子設備的結構示意圖； 5 is a schematic structural diagram of an electronic device according to an embodiment of the present specification;
圖6為本說明書一個實施例提供的另一種電子設備的結構示意圖； 6 is a schematic structural diagram of another electronic device according to an embodiment of the present disclosure;
圖7為本說明書一個實施例提供的一種判定虛假資源轉移的裝置的結構示意圖； 7 is a schematic structural diagram of a device for determining a false resource transfer according to an embodiment of the present specification;
圖8為本說明書一個實施例提供的一種判定虛假交易的裝置的結構示意圖。 FIG. 8 is a schematic structural diagram of a device for determining a false transaction according to an embodiment of the present specification.
Claims (20)
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810063623.1A CN108492112B (en) | 2018-01-23 | 2018-01-23 | Method and device for judging false resource transfer and false transaction and electronic equipment |
| ??201810063623.1 | 2018-01-23 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| TW201933226A true TW201933226A (en) | 2019-08-16 |
Family
ID=63343713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| TW107144476A TW201933226A (en) | 2018-01-23 | 2018-12-11 | Method and apparatus for determining false resource transfer, method and apparatus for determining false trading, and electronic device |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN108492112B (en) |
| TW (1) | TW201933226A (en) |
| WO (1) | WO2019144808A1 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108492112B (en) * | 2018-01-23 | 2020-06-23 | 阿里巴巴集团控股有限公司 | Method and device for judging false resource transfer and false transaction and electronic equipment |
| CN109242499A (en) * | 2018-09-19 | 2019-01-18 | 中国银行股份有限公司 | A kind of processing method of transaction risk prediction, apparatus and system |
| CN110198310B (en) * | 2019-05-20 | 2021-09-14 | 腾讯科技（深圳）有限公司 | Network behavior anti-cheating method and device and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103310353B (en) * | 2013-07-05 | 2016-11-02 | 重庆大学 | The data filtering of a kind of attack resistance optimizes system and method |
| CN107169499B (en) * | 2016-03-07 | 2021-01-05 | 创新先进技术有限公司 | Risk identification method and device |
| CN107346463B (en) * | 2016-05-04 | 2020-08-28 | 阿里巴巴集团控股有限公司 | Method and device for training risk control model and determining model input data |
| CN107368936A (en) * | 2016-05-12 | 2017-11-21 | 阿里巴巴集团控股有限公司 | Air control model training method and device |
| CN107563757B (en) * | 2016-07-01 | 2020-09-22 | 阿里巴巴集团控股有限公司 | Data risk identification method and device |
| CN108492112B (en) * | 2018-01-23 | 2020-06-23 | 阿里巴巴集团控股有限公司 | Method and device for judging false resource transfer and false transaction and electronic equipment |
-
2018
- 2018-01-23 CN CN201810063623.1A patent/CN108492112B/en active Active
- 2018-12-11 TW TW107144476A patent/TW201933226A/en unknown
-
2019
- 2019-01-10 WO PCT/CN2019/071113 patent/WO2019144808A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| CN108492112B (en) | 2020-06-23 |
| CN108492112A (en) | 2018-09-04 |
| WO2019144808A1 (en) | 2019-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019223379A1 (en) | Product recommendation method and device | |
| JP5889300B2 (en) | Method and system for reliability assessment of online trading users | |
| CN110874491B (en) | Privacy data processing method and device based on machine learning and electronic equipment | |
| CN108921566B (en) | False transaction identification method and device based on graph structure model | |
| WO2018001195A1 (en) | Method and device for controlling data risk | |
| US11379845B2 (en) | Method and device for identifying a risk merchant | |
| CN108550046B (en) | Resource and marketing recommendation method and device and electronic equipment | |
| TW201933226A (en) | Method and apparatus for determining false resource transfer, method and apparatus for determining false trading, and electronic device | |
| CN108885762B (en) | Method and system for allocating price discovery mechanism in data market | |
| CN111768258A (en) | Method, device, electronic equipment and medium for identifying abnormal order | |
| WO2020177477A1 (en) | Credit service recommendation method, apparatus, and device | |
| Zhao et al. | Anatomy of a web-scale resale market: a data mining approach | |
| TWI725527B (en) | Insurance transaction processing method and device | |
| CN111582872A (en) | Abnormal account detection model training method, abnormal account detection device and abnormal account detection equipment | |
| CN110008986B (en) | Batch risk case identification method and device and electronic equipment | |
| CN111275071A (en) | Prediction model training method, prediction device and electronic equipment | |
| KR102164279B1 (en) | E-commerce apparatus using tool for matching product | |
| KR102354982B1 (en) | Method and apparatus for providing clothing platform service based on big data | |
| WO2019100867A1 (en) | Processing method based on resources appreciation objects and resources objects, and apparatus | |
| US20220300991A1 (en) | System and method for customizing a digital platform for a target user | |
| KR102670452B1 (en) | Method, device and system for visualize product sales status based on timeline | |
| KR102619471B1 (en) | Method and apparatus for evaluating product information | |
| US20240037620A1 (en) | Systems and Methods for Verifying Transaction Authenticity Using Securitized Token-Based System | |
| CN107609879B (en) | Method, device and system for identifying stolen logistics information | |
| TWI644272B (en) | Shopping guiding system for digital bank based on big data and method thereof |