本發明的目的在於提供一種支付通道推薦方法及其系統，既可以有效的達到支付通道的容量目標，同時又讓用戶有著良好的支付體驗。
為了解決上述問題，本發明公開了一種支付通道推薦方法，包括：
獲取各通道支付容量在上一時間視窗的實際占比；
根據該實際占比和預先設置的各通道支付容量在當前時間視窗的期望占比，對各通道支付容量在上一時間視窗的推薦比進行調整，得到各通道支付容量在當前時間視窗的推薦比；
根據該當前時間視窗的推薦比和特定用戶的支付偏好參數，得到對該特定用戶的支付通道推薦結果；其中該支付偏好參數是反映一個用戶對其能夠使用的各支付通道的偏好程度的參數。
在一個較佳例中，該對上一時間視窗的推薦比進行調整，進一步包括：
將該各通道支付容量在當前時間視窗的期望占比分別除以該各通道支付容量在上一時間視窗的實際占比，再分別乘以該各通道支付容量在上一時間視窗的推薦比，得到該各通道支付容量在當前時間視窗的推薦比。
在一個較佳例中，該根據該當前時間視窗的推薦比和特定用戶的支付偏好參數，得到對該特定用戶的支付通道推薦結果，進一步包括：
對於每一個該通道，分別將該通道在當前時間視窗的推薦比乘以該特定用戶對該通道的支付偏好參數，得到該特定用戶對該通道的推薦值；
將推薦值最大的通道作為對該特定用戶的支付通道推薦結果。
在一個較佳例中，該支付偏好參數是根據用戶最近一段時間內的支付行為和/或用戶的設定得到的。
在一個較佳例中，該根據該當前時間視窗的推薦比和特定用戶的支付偏好參數，得到對該特定用戶的支付通道推薦結果的步驟，是在該特定用戶提交訂單的時候觸發的。
在一個較佳例中，在該得到對該特定用戶的支付通道推薦結果之後，還包括：向該特定用戶使用的終端發送該支付通道推薦結果。
在一個較佳例中，該時間視窗的長度在10秒至15秒的範圍。
本發明還公開了一種支付通道推薦系統，包括：
實際占比獲取模組，用於獲取各通道支付容量在上一時間視窗的實際占比；
推薦比調整模組，用於根據該實際占比和預先設置的各通道支付容量在當前時間視窗的期望占比，對各通道支付容量在上一時間視窗的推薦比進行調整，得到各通道支付容量在當前時間視窗的推薦比；
推薦模組，用於根據該當前時間視窗的推薦比和特定用戶的支付偏好參數，得到對該特定用戶的支付通道推薦結果；其中該支付偏好參數是反映一個用戶對其能夠使用的各支付通道的偏好程度的參數。
在一個較佳例中，該推薦比調整模組透過以下方式調整推薦比：將該各通道支付容量在當前時間視窗的期望占比分別除以該各通道支付容量在上一時間視窗的實際占比，再分別乘以該各通道支付容量在上一時間視窗的推薦比，得到該各通道支付容量在當前時間視窗的推薦比。
在一個較佳例中，該推薦模組進一步包括：
推薦值計算子模組，用於對於每一個該通道，分別將該通道在當前時間視窗的推薦比乘以該特定用戶對該通道的支付偏好參數，得到該特定用戶對該通道的推薦值；
比較子模組，用於將推薦值最大的通道作為對該特定用戶的支付通道推薦結果。
在一個較佳例中，該支付偏好參數是根據用戶最近一段時間內的支付行為和/或用戶的設定得到的。
在一個較佳例中，該推薦模組在該特定用戶提交訂單的時候被觸發以計算對該特定用戶的支付通道推薦結果。
在一個較佳例中，還包括發送模組，用於向該特定用戶使用的終端發送該支付通道推薦結果。
在一個較佳例中，該時間視窗的長度在10秒至15秒的範圍。
本發明還公開了一種支付通道推薦系統，包括：
記憶體，用於儲存電腦可執行指令；以及，
處理器，用於在執行該電腦可執行指令時實現如前文描述的方法中的步驟。
本發明還公開了一種電腦可讀儲存媒體，該電腦可讀儲存媒體中儲存有電腦可執行指令，該電腦可執行指令被處理器執行時實現如前文描述的方法中的步驟。
本發明實施態樣既可以快速而有效地達到支付通道的容量目標，同時又讓用戶有著良好的支付體驗，在用戶體驗和資源配置上做到即時的動態調整，而且不需要與場景相關的較多先驗知識。
本發明的說明書中記載了大量的技術特徵，分佈在各個技術方案中，如果要羅列出本發明所有可能的技術特徵的組合（即技術方案）的話，會使得說明書過於冗長。為了避免這個問題，本發明上述發明內容中公開的各個技術特徵、在下文各個實施態樣和例子中公開的各技術特徵、以及圖式中公開的各個技術特徵，都可以自由地互相組合，從而構成各種新的技術方案（這些技術方案均因視為在本說明書中已經記載），除非這種技術特徵的組合在技術上是不可行的。例如，在一個例子中公開了特徵A+B+C，在另一個例子中公開了特徵A+B+D+E，而特徵C和D是起到相同作用的等同技術手段，技術上只要擇一使用即可，不可能同時採用，特徵E技術上可以與特徵C相組合，則，A+B+C+D的方案因技術不可行而應當不被視為已經記載，而A+B+C+E的方案應當視為已經被記載。The purpose of the present invention is to provide a payment channel recommendation method and a system thereof, which can effectively achieve the capacity target of the payment channel and at the same time allow users to have a good payment experience.
In order to solve the above problems, the present invention discloses a payment channel recommendation method, including:
Obtain the actual percentage of each channel's payment capacity in the previous time window;
According to the actual proportion and the preset expected proportion of each channel's payment capacity in the current time window, adjust the recommended ratio of each channel's payment capacity in the previous time window to obtain the recommended ratio of each channel's payment capacity in the current time window ；
According to the recommendation ratio of the current time window and the payment preference parameter of the specific user, the payment channel recommendation result of the specific user is obtained; wherein the payment preference parameter is a parameter reflecting a user's preference for each payment channel that can be used.
In a preferred example, the adjustment of the recommendation ratio of the previous time window further includes:
Divide the expected proportion of each channel's payment capacity in the current time window by the actual proportion of each channel's payment capacity in the previous time window, and then multiply it by the recommended ratio of each channel's payment capacity in the previous time window, Obtain the recommended ratio of each channel's payment capacity in the current time window.
In a preferred example, obtaining the payment channel recommendation result of the specific user based on the recommendation ratio of the current time window and the payment preference parameter of the specific user further includes:
For each channel, the recommendation ratio of the channel in the current time window is multiplied by the payment preference parameter of the specific user for the channel to obtain the recommended value of the specific user for the channel;
The channel with the largest recommended value is used as the payment channel recommendation result for the specific user.
In a preferred example, the payment preference parameter is obtained according to the user's payment behavior in the most recent period of time and/or the user's setting.
In a preferred example, the step of obtaining the payment channel recommendation result of the specific user based on the recommendation ratio of the current time window and the payment preference parameter of the specific user is triggered when the specific user submits an order.
In a preferred example, after obtaining the payment channel recommendation result for the specific user, the method further includes: sending the payment channel recommendation result to the terminal used by the specific user.
In a preferred embodiment, the length of the time window is in the range of 10 seconds to 15 seconds.
The invention also discloses a payment channel recommendation system, which includes:
The actual percentage acquisition module is used to acquire the actual percentage of each channel's payment capacity in the previous time window;
The recommendation ratio adjustment module is used to adjust the recommendation ratio of the payment capacity of each channel in the previous time window according to the actual ratio and the preset expected ratio of the payment capacity of each channel in the current time window to obtain the payment of each channel Recommended ratio of capacity in the current time window;
The recommendation module is used to obtain the payment channel recommendation result of the specific user according to the recommendation ratio of the current time window and the payment preference parameter of the specific user; wherein the payment preference parameter reflects the payment channels that a user can use for it The parameter of the degree of preference.
In a preferred example, the recommendation ratio adjustment module adjusts the recommendation ratio in the following way: the expected proportion of the payment capacity of each channel in the current time window is divided by the actual payment capacity of each channel in the previous time window. The ratio is then multiplied by the recommended ratio of the payment capacity of each channel in the previous time window to obtain the recommended ratio of the payment capacity of each channel in the current time window.
In a preferred embodiment, the recommendation module further includes:
The recommended value calculation sub-module is used to, for each channel, multiply the channel's recommendation ratio in the current time window by the specific user's payment preference parameter for the channel to obtain the specific user's recommended value for the channel;
The comparison sub-module is used to use the channel with the largest recommended value as the payment channel recommendation result for the specific user.
In a preferred example, the payment preference parameter is obtained according to the user's payment behavior in the most recent period of time and/or the user's setting.
In a preferred embodiment, the recommendation module is triggered when the specific user submits an order to calculate the payment channel recommendation result for the specific user.
In a preferred embodiment, it further includes a sending module for sending the payment channel recommendation result to the terminal used by the specific user.
In a preferred embodiment, the length of the time window is in the range of 10 seconds to 15 seconds.
The invention also discloses a payment channel recommendation system, which includes:
Memory, used to store computer executable instructions; and,
The processor is used to implement the steps in the method described above when executing the computer executable instructions.
The present invention also discloses a computer-readable storage medium in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the steps in the method described above are implemented.
The implementation aspect of the present invention can not only quickly and effectively achieve the capacity target of the payment channel, but also allows users to have a good payment experience, real-time dynamic adjustment of user experience and resource configuration, and does not require comparison with scenes. More prior knowledge.
A large number of technical features are recorded in the specification of the present invention, which are distributed in various technical solutions. If all possible combinations of technical features (ie technical solutions) of the present invention are to be listed, the specification will be too long. In order to avoid this problem, the various technical features disclosed in the above content of the present invention, the various technical features disclosed in the various embodiments and examples below, and the various technical features disclosed in the drawings can be freely combined with each other, thereby Form various new technical solutions (these technical solutions are deemed to have been recorded in this specification), unless this combination of technical features is technically infeasible. For example, in one example, the feature A+B+C is disclosed, and in another example, the feature A+B+D+E is disclosed, and the features C and D are equivalent technical means that play the same role. Technically, just choose It can be used once and cannot be used at the same time. Feature E can be combined with feature C technically, then the A+B+C+D solution should not be regarded as recorded because it is technically infeasible, and A+B+ The C+E plan should be deemed to have been documented.
在以下的敘述中，為了使讀者更好地理解本發明而提出了許多技術細節。但是，本領域的普通技術人員可以理解，即使沒有這些技術細節和基於以下各實施態樣的種種變化和修改，也可以實現本發明所要求保護的技術方案。
部分概念的說明：
時間視窗：指預設長度的一段時間。例如，可以將1分鐘按10秒鐘的長度依次劃分為6個時間視窗。
支付通道：即支付的通道，例如不同銀行發行的銀行卡就是不同的支付通道，不同的第三方支付方式也屬於不同的支付通道。在本發明的各實施例中，支付通道也可以簡稱為通道。
各通道支付容量在一個時間視窗的占比：在一個時間視窗中，每一種支付通道被使用的次數占總支付次數的比例。
各通道支付容量在上一時間視窗的實際占比：在上一個時間視窗中，每一種支付通道實際被使用的次數占總支付次數的比例。
各通道支付容量在當前時間視窗的期望占比：在當前時間視窗中，每一種支付通道希望被使用的次數占總支付次數的比例。
支付偏好參數：反映用戶可用的支付通道及其使用偏好，例如一個用戶總共有A、B、C三種支付通道，則可以用[A,B,C]=[0.1,0.6,0.3]來表示該用戶對這三種支付通道的使用偏好程度，數值越大代表該用戶越偏好使用對應的支付通道。
本發明的發明人發現，個性化支付通道推薦的挑戰在於，系統不知道下一時刻到來的請求的用戶擁有的支付工具是什麼，並且每個用戶之間支付習慣大不相同，僅僅考慮容量目標將嚴重影響用戶支付體驗。所以本發明實施態樣將用戶個性化支付習慣、當時的用戶支付因素和通道狀況綜合起來做個性化推薦。
為使本發明的目的、技術方案和優點更加清楚，下面將結合圖式對本發明的實施態樣作進一步地詳細描述。
本發明的第一實施態樣涉及一種支付通道推薦方法，其流程如圖1所示，該方法包括以下步驟：
在步驟101中，獲取各通道支付容量在上一時間視窗的實際占比。在一個實施例中，時間視窗的長度可以在10秒至15秒的範圍內。在其他的實施例中，在不同的場景中，可以根據實際情況對時間視窗的長度進行設定，不限於10至15秒的範圍。
此後進入步驟102，根據所獲取的實際占比和預先設置的各通道支付容量在當前時間視窗的期望占比，對各通道支付容量在上一時間視窗的推薦比進行調整，得到各通道支付容量在當前時間視窗的推薦比。
可選地，本步驟進一步包括：將各通道支付容量在當前時間視窗的期望占比分別除以各通道支付容量在上一時間視窗的實際占比，再分別乘以各通道支付容量在上一時間視窗的推薦比，得到各通道支付容量在當前時間視窗的推薦比。
在一個實施例中，假定當前時間視窗為第n個時間視窗，n為正整數，則各通道支付容量在上一時間視窗的實際占比可以以向量Vn-1
表示，各通道支付容量在當前時間視窗的期望占比可以用向量Un
表示, 各通道支付容量在上一時間視窗和當前時間視窗的推薦比分別為Xn-1
和Xn
，這些向量的長度均為支付通道的數量k，該向量中第i個元素代表第i種通道，k為正整數，0＜i≤k。其中U和X的長度都是k。那麼，Xn
=Xn-1
·Un
/Vn-1
,該公式表示對於將Xn-1
和Un
中每一個對應位置的元素相乘後，分別除以Vn-1
中每一個對應位置的元素，得到Xn
。
此後進入步驟103，根據當前時間視窗的推薦比和特定用戶的支付偏好參數，得到對特定用戶的支付通道推薦結果。可選地，本步驟進一步包括：對於每一個通道，分別將該通道在當前時間視窗的推薦比乘以特定用戶對該通道的支付偏好參數，得到特定用戶對該通道的推薦值；將推薦值最大的通道作為對特定用戶的支付通道推薦結果。
支付偏好參數是反映一個用戶對其能夠使用的各支付通道的偏好程度的參數。可選地，支付偏好參數是根據用戶最近一段時間內的支付行為和/或用戶的設定得到的。支付行為包括支付記錄，支付成功，支付失敗，上一次支付成功距離現在的時間等等。例如，可以根據在最近的一個月內用戶使用各種支付通道的次數確定支付偏好次數。又如，用戶設定的各種可用支付通道的支付順序也可以作為影響支付偏好參數的一個因素，支付順序在前的支付通道在支付偏好參數中相應具有更大權重。
在每一個時間視窗上述步驟101、102和103都會執行，不斷地反覆運算計算各通道支付容量在當前時間視窗的期望占比，並為當前時間視窗中需要支付的各個用戶給出個性化的支付通道推薦結果，其中需要支付的各個用戶就可以看作是上述特定用戶。
在一個實施例中，步驟101和102是在每個時間視窗開始的時候執行的，以得到各通道支付容量在當前時間視窗的推薦比。步驟103是在用戶提交訂單的時候觸發的，提交訂單的那個用戶就可以被作為特定用戶，透過步驟103計算得到該用戶支付通道推薦結果。步驟101、102和103都是在雲端（或服務端，伺服器等）進行的，雲端會將支付通道推薦結果發送到該用戶使用的終端（例如智慧手機或筆記型電腦等），該用戶提交訂單後會進入支付介面，支付介面中就可以顯示與支付通道推薦結果相關的資訊（例如顯示推薦的支付通道，或顯示相關的提示資訊等）。
透過上述技術方案，可以兼顧支付通道容量能力和用戶的支付習慣。
為了能夠更好地理解本發明的技術方案，下面結合一個具體的例子來進行說明，該例子中羅列的細節主要是為了便於理解，不作為對本發明保護範圍的限制。
假定每個時間視窗的長度是10秒，總共有A、B、C三個支付通道。在當前的時間視窗（假定為第n個時間視窗）內，雲端收到三個用戶的請求，即用戶1、用戶2、和用戶3。
上一個時間視窗各個支付通道的推薦因數Xn-1
= [0.4,0.4,0.2]，當前時間視窗各個支付通道的期望占比是Un
= [0.5,0.4,0.1]，上一時間視窗各個通道支付容量的實際占比為Vn-1
=[0.4,0.4,0.2]。那麼當前時間視窗各個支付通道的推薦因數Xn-1
=[0.4*0.5/0.4,0.4*0.4/0.4,0.2*0.1/0.2] =[0.5,0.4,0.1]
假定這三個用戶分別擁有的支付通道以及對應的支付偏好參數分別是[A,B,C]=[0.1,0.6,0.3]，[C]=[1]，[A,B]=[0.8,0.2]，那麼這三個用戶的支付通道推薦為：
用戶1: max(0.5∗0.1,0.4∗0.6,0.3∗0.1) 推薦B
用戶2: max(0,0,0.1*1) 推薦C
用戶3: max(0.5∗0.8,0.4∗0.1) 推薦A
其中，max是取最大值的函數。
本發明的第二實施態樣涉及一種支付通道推薦系統，其結構如圖2所示，該支付通道推薦系統包括：
實際占比獲取模組201，用於獲取各通道支付容量在上一時間視窗的實際占比。可選地，時間視窗的長度在10秒至15秒的範圍內。可選地，在不同的場景中，可以根據實際情況對時間視窗的長度進行設定，不限於10至15秒的範圍。
推薦比調整模組202，用於根據實際占比和預先設置的各通道支付容量在當前時間視窗的期望占比，對各通道支付容量在上一時間視窗的推薦比進行調整，得到各通道支付容量在當前時間視窗的推薦比。
可選地，推薦比調整模組透過以下方式調整推薦比：將各通道支付容量在當前時間視窗的期望占比分別除以各通道支付容量在上一時間視窗的實際占比，再分別乘以各通道支付容量在上一時間視窗的推薦比，得到各通道支付容量在當前時間視窗的推薦比。
推薦模組203，用於根據當前時間視窗的推薦比和特定用戶的支付偏好參數，得到對特定用戶的支付通道推薦結果。其中支付偏好參數是反映一個用戶對其能夠使用的各支付通道的偏好程度的參數。可選地，支付偏好參數是根據用戶最近一段時間內的支付行為和/或用戶的設定得到的。
可選地，推薦模組進一步包括：推薦值計算子模組，用於對於每一個通道，分別將該通道在當前時間視窗的推薦比乘以特定用戶對該通道的支付偏好參數，得到特定用戶對該通道的推薦值。比較子模組，用於將推薦值最大的通道作為對特定用戶的支付通道推薦結果。
可選地，推薦模組在特定用戶提交訂單的時候被觸發以計算對特定用戶的支付通道推薦結果。該系統還可以包括發送模組，用於向特定用戶使用的終端發送支付通道推薦結果。
第一實施態樣是與本實施態樣相對應的方法實施態樣，第一實施態樣中的技術細節可以應用於本實施態樣，本實施態樣中的技術細節也可以應用於第一實施態樣。
需要說明的是，本領域技術人員應當理解，上述支付通道推薦系統的實施態樣中所示的各模組的實現功能可參照前述支付通道推薦方法的相關描述而理解。上述支付通道推薦系統的實施態樣中所示的各模組的功能可透過運行於處理器上的程式（可執行指令）而實現，也可透過具體的邏輯電路而實現。本發明實施例上述支付通道推薦系統如果以軟體功能模組的形式實現並作為獨立的產品銷售或使用時，也可以儲存在一個電腦可讀取儲存媒體中。基於這樣的理解，本發明實施例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，該電腦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電腦設備（可以是個人電腦、伺服器、或者網路設備等）執行本發明各個實施例所述方法的全部或部分。而前述的儲存媒體包括：USB隨身碟、抽取式硬碟、唯讀記憶體（ROM，Read Only Memory）、磁碟或者光碟等各種可以儲存程式碼的媒體。這樣，本發明實施例不限制於任何特定的硬體和軟體結合。
相應地，本發明實施態樣還提供一種電腦可讀儲存媒體，其中儲存有電腦可執行指令，該電腦可執行指令被處理器執行時實現本發明的各方法實施態樣。電腦可讀儲存媒體包括永久性和非永久性、抽取式和非抽取式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)、快閃記憶體或其他內部記憶體技術、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，電腦可讀儲存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。
此外，本發明實施態樣還提供一種支付通道推薦系統，其中包括用於儲存電腦可執行指令的儲存器，以及，處理器；該處理器用於在執行該記憶體中的電腦可執行指令時實現上述各方法實施態樣中的步驟。其中，該處理器可以是中央處理單元(Central Processing Unit，簡稱“CPU”)，還可以是其他通用處理器、數位訊號處理器(Digital Signal Processor，簡稱“DSP”)、專用積體電路(Application Specific Integrated Circuit，簡稱“ASIC”)等。前述的儲存器可以是唯讀記憶體(read-only memory，簡稱“ROM”)、隨機存取記憶體(random access memory，簡稱“RAM”)、快閃記憶體（Flash）、硬碟或者固態硬碟等。本發明各實施態樣所公開的方法的步驟可以直接體現為硬體處理器執行完成，或者用處理器中的硬體及軟體模組組合執行完成。
需要說明的是，在本專利的申請文件中，諸如第一和第二等之類的關係術語僅僅用來將一個實體或者操作與另一個實體或操作區分開來，而不一定要求或者暗示這些實體或操作之間存在任何這種實際的關係或者順序。而且，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、物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、物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、物品或者設備中還存在另外的相同要素。本專利的申請文件中，如果提到根據某要素執行某行為，則是指至少根據該要素執行該行為的意思，其中包括了兩種情況：僅根據該要素執行該行為、和根據該要素和其它要素執行該行為。多個、多次、多種等表達包括2個、2次、2種以及2個以上、2次以上、2種以上。
在本發明提及的所有文獻都被認為是整體性地包括在本發明的公開內容中，以便在必要時可以作為修改的依據。此外應理解，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。
上述對本說明書特定實施例進行了描述。其它實施例在申請專利範圍的範圍內。在一些情況下，在申請專利範圍中記載的動作或步驟可以按照不同於實施例中的順序來執行並且仍然可以實現期望的結果。另外，在圖式中描繪的過程不一定要求示出的特定順序或者連續順序才能實現期望的結果。在某些實施態樣中，多工處理和並行處理也是可以的或者可能是有利的。In the following description, many technical details are proposed for the reader to better understand the present invention. However, those of ordinary skill in the art can understand that even without these technical details and various changes and modifications based on the following embodiments, the technical solution claimed by the present invention can be realized. Explanation of some concepts: Time window: refers to a period of time of preset length. For example, 1 minute can be divided into 6 time windows in order of 10 seconds. Payment channel: the payment channel. For example, bank cards issued by different banks are different payment channels, and different third-party payment methods also belong to different payment channels. In each embodiment of the present invention, the payment channel may also be referred to as a channel for short. Percentage of payment capacity of each channel in a time window: In a time window, the ratio of the number of times each payment channel is used to the total number of payments. The actual proportion of the payment capacity of each channel in the last time window: In the last time window, the percentage of the number of times that each payment channel was actually used to the total number of payments. The expected proportion of payment capacity of each channel in the current time window: in the current time window, the proportion of the number of times each payment channel is expected to be used to the total number of payments. Payment preference parameters: reflect the payment channels available to users and their preferences. For example, if a user has a total of three payment channels A, B, and C, you can use [A,B,C]=[0.1,0.6,0.3] to represent this The user's preference for these three payment channels. The larger the value, the more the user prefers to use the corresponding payment channel. The inventor of the present invention found that the challenge of personalized payment channel recommendation is that the system does not know what payment tool the user has for the next request, and the payment habits of each user are very different, only considering the capacity target Will seriously affect user payment experience. Therefore, the implementation aspect of the present invention integrates the user's personalized payment habits, the user's current payment factors and channel conditions to make personalized recommendations. In order to make the objectives, technical solutions, and advantages of the present invention clearer, the implementation aspects of the present invention will be described in further detail below in conjunction with the drawings. The first aspect of the present invention relates to a method for recommending payment channels. The process is shown in FIG. 1. The method includes the following steps: In step 101, the actual proportion of the payment capacity of each channel in the previous time window is obtained. In one embodiment, the length of the time window may be in the range of 10 seconds to 15 seconds. In other embodiments, in different scenarios, the length of the time window can be set according to actual conditions, and is not limited to the range of 10 to 15 seconds. After that, proceed to step 102. According to the obtained actual proportion and the preset expected proportion of the payment capacity of each channel in the current time window, the recommended proportion of the payment capacity of each channel in the previous time window is adjusted to obtain the payment capacity of each channel The recommendation ratio in the current time window. Optionally, this step further includes: dividing the expected proportion of each channel's payment capacity in the current time window by the actual proportion of each channel's payment capacity in the previous time window, and then multiplying it by the respective channel's payment capacity in the previous time window. The recommendation ratio of the time window is to obtain the recommendation ratio of the payment capacity of each channel in the current time window. In one embodiment, assuming that the current time window is the nth time window and n is a positive integer, the actual proportion of the payment capacity of each channel in the previous time window can be represented by the vector V n-1 , and the payment capacity of each channel is The expected proportion of the current time window can be represented by a vector U n . The recommended ratios of the payment capacity of each channel in the previous time window and the current time window are X n-1 and X n respectively . The lengths of these vectors are the number of payment channels k, the i-th element in the vector represents the i-th channel, k is a positive integer, 0<i≤k. The length of U and X are both k. Then, X n =X n-1 ·U n /V n-1 , this formula means that after multiplying the elements at each corresponding position in X n-1 and U n , divide by each of V n-1 For an element at a corresponding position, X n is obtained. After that, step 103 is entered to obtain the payment channel recommendation result for the specific user according to the recommendation ratio of the current time window and the payment preference parameter of the specific user. Optionally, this step further includes: for each channel, the recommendation ratio of the channel in the current time window is multiplied by the payment preference parameter of the specific user for the channel to obtain the recommended value of the specific user for the channel; The largest channel is used as the payment channel recommendation result for a specific user. The payment preference parameter is a parameter that reflects a user's preference for each payment channel that can be used. Optionally, the payment preference parameter is obtained according to the user's payment behavior in a recent period of time and/or the user's setting. Payment behavior includes payment records, payment success, payment failure, the time between the last successful payment and the present, etc. For example, the number of payment preferences can be determined based on the number of times the user has used various payment channels in the most recent month. For another example, the payment order of various available payment channels set by the user can also be used as a factor that affects the payment preference parameter, and the payment channel with the first payment order has a corresponding greater weight in the payment preference parameter. The above steps 101, 102, and 103 will be executed in each time window, and iteratively calculate the expected proportion of the payment capacity of each channel in the current time window, and provide personalized payment for each user who needs to pay in the current time window In the channel recommendation result, each user who needs to pay can be regarded as the above-mentioned specific user. In one embodiment, steps 101 and 102 are executed at the beginning of each time window to obtain the recommended ratio of the payment capacity of each channel in the current time window. Step 103 is triggered when the user submits the order. The user who submitted the order can be regarded as a specific user, and the result of the user's payment channel recommendation is calculated through step 103. Steps 101, 102, and 103 are all performed in the cloud (or server, server, etc.). The cloud will send the payment channel recommendation result to the terminal used by the user (such as a smart phone or laptop, etc.), and the user submits After the order is placed, the payment interface will be entered, and the payment interface can display information related to the payment channel recommendation result (for example, display the recommended payment channel, or display related prompt information, etc.). Through the above technical solutions, it is possible to balance the capacity of the payment channel and the payment habits of users. In order to better understand the technical solution of the present invention, a specific example is used for description below. The details listed in the example are mainly for ease of understanding and are not intended to limit the protection scope of the present invention. Assuming that the length of each time window is 10 seconds, there are a total of three payment channels A, B, and C. In the current time window (assumed to be the nth time window), the cloud receives requests from three users, namely user 1, user 2, and user 3. The recommended factor of each payment channel in the previous time window X n-1 = [0.4,0.4,0.2], the expected proportion of each payment channel in the current time window is U n = [0.5,0.4,0.1], each of the previous time windows The actual proportion of channel payment capacity is V n-1 =[0.4,0.4,0.2]. Then the recommended factor of each payment channel in the current time window X n-1 =[0.4*0.5/0.4,0.4*0.4/0.4,0.2*0.1/0.2] =[0.5,0.4,0.1] Assuming that these three users have The payment channel and the corresponding payment preference parameters are [A,B,C]=[0.1,0.6,0.3], [C]=[1], [A,B]=[0.8,0.2], then these three The recommended payment channel for users is: User 1: max(0.5∗0.1,0.4∗0.6,0.3∗0.1) Recommended B user 2: max(0,0,0.1*1) Recommended C user 3: max(0.5∗0.8, 0.4∗0.1) Recommendation A Among them, max is a function that takes the maximum value. The second embodiment of the present invention relates to a payment channel recommendation system. Its structure is shown in Figure 2. The payment channel recommendation system includes: an actual percentage acquisition module 201 for acquiring the payment capacity of each channel in the previous time window The actual percentage. Optionally, the length of the time window is in the range of 10 seconds to 15 seconds. Optionally, in different scenarios, the length of the time window can be set according to actual conditions, and is not limited to the range of 10 to 15 seconds. The recommendation ratio adjustment module 202 is used to adjust the recommendation ratio of the payment capacity of each channel in the previous time window according to the actual percentage and the preset expected percentage of the payment capacity of each channel in the current time window to obtain the payment of each channel The recommended ratio of the capacity in the current time window. Optionally, the recommendation ratio adjustment module adjusts the recommendation ratio in the following way: divide the expected proportion of each channel's payment capacity in the current time window by the actual proportion of each channel's payment capacity in the previous time window, and then multiply it by The recommended ratio of the payment capacity of each channel in the previous time window is obtained, and the recommended ratio of the payment capacity of each channel in the current time window is obtained. The recommendation module 203 is configured to obtain a payment channel recommendation result for a specific user according to the recommendation ratio of the current time window and the payment preference parameter of the specific user. The payment preference parameter is a parameter that reflects a user's preference for each payment channel that can be used. Optionally, the payment preference parameter is obtained according to the user's payment behavior in a recent period of time and/or the user's setting. Optionally, the recommendation module further includes: a recommendation value calculation sub-module, which is used for each channel to multiply the recommendation ratio of the channel in the current time window by the payment preference parameter of the specific user for the channel to obtain the specific user The recommended value for this channel. The comparison sub-module is used to use the channel with the largest recommendation value as the payment channel recommendation result for a specific user. Optionally, the recommendation module is triggered when a specific user submits an order to calculate the payment channel recommendation result for the specific user. The system may also include a sending module for sending payment channel recommendation results to a terminal used by a specific user. The first implementation aspect is a method implementation aspect corresponding to this implementation aspect. The technical details in the first implementation aspect can be applied to this implementation aspect, and the technical details in this implementation aspect can also be applied to the first implementation aspect. Implementation status. It should be noted that those skilled in the art should understand that the implementation functions of each module shown in the implementation mode of the payment channel recommendation system can be understood with reference to the relevant description of the payment channel recommendation method described above. The functions of each module shown in the implementation mode of the payment channel recommendation system can be implemented through programs (executable instructions) running on the processor, or through specific logic circuits. If the payment channel recommendation system in the embodiment of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention can be embodied in the form of a software product in essence or a part that contributes to the prior art. The computer software product is stored in a storage medium and includes a number of commands to enable A computer device (which may be a personal computer, a server, or a network device, etc.) executes all or part of the methods described in the various embodiments of the present invention. The aforementioned storage media include: USB flash drives, removable hard drives, read-only memory (ROM, Read Only Memory), magnetic disks or optical disks and other media that can store program codes. In this way, the embodiments of the present invention are not limited to any specific combination of hardware and software. Correspondingly, the implementation aspects of the present invention also provide a computer-readable storage medium in which computer-executable instructions are stored, and when the computer-executable instructions are executed by the processor, the implementation aspects of the methods of the present invention are implemented. Computer-readable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be realized by any method or technology. Information can be computer-readable instructions, data structures, program modules, 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 programmable read-only memory (EEPROM), flash memory or other internal memory technology, read-only CD-ROM (CD-ROM), digital multi Functional compact discs (DVD) or other optical storage, magnetic cassettes, magnetic tape storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by computing devices. According to the definition in this article, computer-readable storage media does not include transitory media, such as modulated data signals and carrier waves. In addition, the embodiment of the present invention also provides a payment channel recommendation system, which includes a memory for storing computer-executable instructions, and a processor; the processor is used to execute the computer-executable instructions in the memory. The steps in the implementation aspects of the above methods. Among them, the processor can be a central processing unit (Central Processing Unit, "CPU"), other general-purpose processors, digital signal processors (Digital Signal Processor, "DSP"), and dedicated integrated circuits (Application Specific Integrated Circuit, referred to as "ASIC"), etc. The aforementioned storage can be read-only memory ("ROM"), random access memory (random access memory, "RAM"), flash memory (Flash), hard disk or solid state Hard disk, etc. The steps of the method disclosed in each embodiment of the present invention can be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor. It should be noted that in the application documents of this patent, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply these There is any such actual relationship or sequence between entities or operations. Moreover, the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes those that are not explicitly listed Other elements of, or also include elements inherent to this process, method, article or equipment. If there are no more restrictions, the element defined by the phrase "including one" does not exclude the existence of other same elements in the process, method, article, or equipment that includes the element. In the application documents of this patent, if it is mentioned that an act is performed according to a certain element, it means that the act is performed at least according to that element, and it includes two situations: performing the act only according to the element, and according to the element and Other elements perform the behavior. Multiple, multiple, multiple, etc. expressions include two, two, two, and two or more, two or more, and two or more expressions. All documents mentioned in the present invention are considered to be included in the disclosure of the present invention as a whole, so that they can be used as a basis for modification when necessary. In addition, it should be understood that the above descriptions are only preferred embodiments of this specification, and are not intended to limit the protection scope of this specification. Any modification, equivalent replacement, improvement, etc. 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 foregoing describes specific embodiments of this specification. Other embodiments are within the scope of the patent application. In some cases, the actions or steps described in the scope of the patent application may be performed in a different order from the embodiment and still achieve desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown in order to achieve the desired result. In some implementation aspects, multiplexing and parallel processing are also possible or may be advantageous.
