為使本發明實施例的目的、技術方案和優點更加清楚，下面將結合本發明實施例中的圖式，對本發明實施例中的技術方案進行清楚、完整地描述，顯然，所描述的實施例是本發明一部分實施例，而不是全部的實施例。基於本發明中的實施例，本領域普通技術人員在沒有作出創造性勞動前提下所獲得的所有其他實施例，都屬於本發明保護的範圍。
在本發明實施例中使用的術語是僅僅出於描述特定實施例的目的，而非旨在限制本發明。在本發明實施例和所附申請專利範圍中所使用的單數形式的“一種”、“所述”和“該”也旨在包括多數形式，除非上下文清楚地表示其他含義，“多種”一般包含至少兩種，但是不排除包含至少一種的情況。
應當理解，本文中使用的術語“及/或”僅僅是一種描述關聯對象的關聯關係，表示可以存在三種關係，例如，A及/或B，可以表示：單獨存在A，同時存在A和B，單獨存在B這三種情況。另外，本文中字符“/”，一般表示前後關聯對象是一種“或”的關係。
取決於語境，如在此所使用的詞語“如果”、“若”可以被解釋成為“在……時”或“當……時”或“響應於確定”或“響應於檢測”。類似地，取決於語境，片語“如果確定”或“如果檢測(陳述的條件或事件)”可以被解釋成為“當確定時”或“響應於確定”或“當檢測(陳述的條件或事件)時”或“響應於檢測(陳述的條件或事件)”。
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商品或者系統不僅包括那些要素，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商品或者系統所固有的要素。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商品或者系統中還存在另外的相同要素。
另外，下述各方法實施例中的步驟時序僅為一種舉例，而非嚴格限定。
圖1為本發明實施例提供的一種商品清點方法的流程圖，本實施例提供的該商品清點方法可以由一商品清點裝置來執行，該商品清點裝置可以實現為軟體，或者實現為軟體和硬體的組合。可選地，該商品清點裝置可以設置在使用者終端設備中的一購物客戶端中，或者也可以設置在購物伺服器中。如圖1所示，該方法包括如下步驟：
101、響應於使用者對訂單觸發的商品清點操作，獲取使用者清點訂單中商品的語音。
102、識別清點訂單中商品的語音，以確定訂單中的已收貨商品。
以使用者使用購物客戶端進行購物的場景為例，使用者下單完成之後，在某時間會收到所購商品，此時，為核對已收貨商品是否是自己所下單的商品以及所下單的商品是否已經都送達，需要進行商品清點。
此時，可選地，使用者可以透過如下操作觸發商品清點操作：打開購物客戶端，選擇相應訂單進入訂單詳情頁，如圖2所示，該訂單詳情頁中可以設置有觸發商品清點操作的控制項，使用者點擊該控制項即觸發了商品清點操作。
在一可選實施例中，當檢測到使用者針對某個訂單觸發了商品清點操作後，觸發語音採集功能生效，以接收使用者清點該訂單中的商品的語音。該實施例中，針對任一已收貨商品，使用者可以說出已收貨商品描述資訊，即輸出包含有已收貨商品描述資訊的語音。其中，已收貨商品描述資訊中比如可以包括商品名稱、尺碼、顏色、數量、款號等商品特徵。在採集到該語音後，對該語音進行語音識別處理，以識別出其中包含的已收貨商品描述資訊，可選地，如圖3所示，可以在界面中顯示出語音識別結果，以便可以讓使用者看出識別結果是否與其輸出的已收貨商品描述資訊一致。進而，可以在訂單對應的商品資訊中查找是否存在與該已收貨商品描述資訊相匹配的商品資訊，以確定使用者當前收到的商品是訂單中的哪個商品，其中，該商品資訊可以體現為訂單詳情頁中的一個個商品記錄項。當從中找到與已收貨商品描述資訊匹配的商品資訊時，可選地，如圖4所示，可以在突出顯示匹配到的商品資訊，同時還可以為該匹配到的商品資訊打上已收貨狀態標記，還可以播放預設提示音，以提示使用者已經匹配到相應的商品資訊。根據上述過程，使用者逐次輸出每個已收貨商品對應的語音，基於上述語音識別、商品資訊匹配處理，最終可以得到訂單中有多少個商品已經被使用者收到，多少商品還未送達等資訊。可選地，可以在圖4所示界面中設置清點完成控制項，當使用者點擊該控制項時即觸發清點結束操作，此時，如圖5所示，可以顯示清點結果頁面，該清點結果頁面中可以包括已收貨商品總數、未收貨商品總數、已收貨商品詳情和未收貨商品詳情中的至少一種清點結果提示資訊。觸發清點結束操作還可以是一定時間內未接收到商品清點語音視為觸發了清點結束操作。
可以理解的是，每當在訂單包含的商品資訊中匹配到一個到貨商品描述資訊後，已收貨商品總數、未收貨商品總數會進行更新。已收貨商品詳情和未收貨商品詳情可以是差異性的顯示訂單中的已收貨商品對應的商品資訊和未收貨商品的商品資訊，比如將未收貨的商品資訊集中靠前突出顯示，已收貨的商品資訊靠後集中顯示，不限於此。
綜上，基於本發明實施例提供的語音交互方式的商品清點方案，在對訂單中的商品進行清點的過程中，使用者與購物客戶端進行語音交互，逐次輸出用於進行商品清點的語音，以便透過識別該語音來確定使用者收到的已收貨商品對應於訂單中的哪個商品，從而最終完成已收貨商品的清點。該方案中，無需使用者側配置額外的硬體設備，僅透過語音交互的方式即可簡單方便地實現商品的清點。
圖6為本發明實施例提供的另一種商品清點方法的流程圖，如圖6所示，還方法可以包括如下步驟：
601、響應於使用者對訂單觸發的商品清點操作，顯示清點模式選擇頁面。
602、根據使用者在清點模式選擇頁面中的選擇操作，確定採用的清點模式。
本發明實施例的基於語音交互進行商品清點的方案，可以提供兩種可選的清點模式：對應於使用者語音輸入已收貨商品的第一清點模式和對應於設備側語音播報訂單中商品的第二清點模式。簡單來說，第一清點模式即為使用者語音輸出已收貨商品的描述資訊，在客戶端側進行語音識別以及在訂單包含的商品資訊中查找與已收貨商品匹配的商品資訊的模式；第二清點模式即為客戶端側播報訂單包含的商品資訊，使用者在已收貨商品中查找是否存在與播報的商品資訊對應的已收貨商品，並基於查找結果進行語音反饋的模式。
在一可選實施例中，使用者可以根據自身需求自主選擇採用哪種清點模式進行商品清點。此時，當使用者比如在圖2所示訂單詳情頁中透過點擊清點控制項而觸發商品清點操作後，可以在界面中顯示清點模式選擇頁面，該頁面中包括第一清點模式和第二清點模式選擇項，使用者從中選擇所需的清點模式即可。
值得說明的是，當使用者選擇了某種清點模式進行商品清點後，在清點過程中，使用者還可以切換選擇另一種清點模式進行商品清點，也就是說，在一次商品清點過程中，使用者可以根據實際需要在兩種清點模式間切換。
可以理解的是，上述兩種清點模式也形成了互補，避免在一種清點模式無法很好的完成商品清點處理時，可以採用另一種清點模式來完成商品清點處理。比如，當採用第一清點模式時，如果因為使用者的口音等問題，導致語音識別準確性不佳時，第二清點模式可以彌補該不足。
在另一可選實施例中，相比於使用者手動選擇清點模式的方式，還可以實現自動選擇清點模式。此時，可以根據訂單中包含的商品數量確定採用的清點模式是哪種。比如：若商品數量大於或等於預設閾值，則確定採用第一清點模式；若商品數量小於預設閾值，則確定採用第二清點模式。因為，在訂單中的商品數量較多時，一般地，已收貨商品數量也較多，此時採用第一清點模式可以避免使用者在眾多已收貨商品中查找客戶端播報的商品而導致的不便；相反地，當在訂單中的商品數量較少時，一般地，已收貨商品數量也較少，此時採用第二清點模式可以避免使用者需要說出冗長的已收貨商品資訊。
一方面，若確定採用上述第一清點模式，則執行步驟603-604：
603、若確定採用第一清點模式，則獲取使用者播報已收貨商品的第一語音。
604、識別第一語音中包含的第一已收貨商品描述資訊，在訂單包含的商品資訊中匹配第一已收貨商品描述資訊，以根據匹配結果確定所述訂單中的已收貨商品。
如前述實施例中所介紹的，針對任一已收貨商品，使用者可以說出包含已收貨商品描述資訊(稱為第一已收貨商品描述資訊)的語音。其中，第一已收貨商品描述資訊中比如可以包括商品名稱、尺碼、顏色、數量、款號等商品特徵。在採集到該語音後，對該語音進行語音識別處理，以識別出其中包含的第一已收貨商品描述資訊。進而，可以在訂單包含的商品資訊中匹配該第一已收貨商品描述資訊，以確定該訂單中是否包含與該第一已收貨商品描述資訊相匹配的商品資訊，從而根據匹配結果訂單中的已收貨商品。
在匹配第一已收貨商品描述資訊與訂單包含的商品資訊的過程中，可能會出現匹配到一個與該第一已收貨商品描述資訊對應的商品資訊，匹配到多個與該第一已收貨商品描述資訊對應的商品資訊，沒有匹配到與該第一已收貨商品描述資訊對應的商品資訊幾種情況，下面分別針對步驟604執行過程中可能遇到的各種匹配結果下的處理邏輯進行說明。
第一種情況：若在訂單包含的商品資訊中僅匹配到一個與第一已收貨商品描述資訊對應的目標商品資訊，則確定目標商品資訊所對應的商品為所述已收貨商品。此時，可選地，可以對該目標商品資訊進行已收貨狀態標記，以便後續在針對另一已收貨商品進行清點的過程中，可以不必再匹配具有已收貨狀態標識的商品資訊，降低了匹配次數。另外，為了提高使用者體驗，在匹配到該目標商品資訊時，還可以播放預設提示音，以提示使用者已經匹配到相應的商品資訊，比如播放“匹配成功”。
第二種情況：若在訂單包含的商品資訊中匹配到與第一已收貨商品描述資訊對應的多個商品資訊，則確定多個商品資訊的差異商品特徵；根據差異商品特徵輸出第一提示語音；接收使用者對第一提示語音的應答語音；根據應答語音從多個商品資訊中確定已收貨商品對應的目標商品資訊，亦即根據應答語音從多個商品資訊對應的商品中確定出已收貨商品。
如前所說，對於任一已收貨商品，為了保證匹配結果的準確性，使用者描述該已收貨商品時，理想情況下，應該說出完備的該已收貨商品的描述資訊，即用於唯一標識該已收貨商品的各種商品特徵，比如商品名稱、尺碼、顏色、數量、款號等。當使用者說出的第一已收貨商品描述資訊過於模糊時，可能導致無法成功匹配到對應的商品資訊，或者匹配到多個商品資訊的情況。
針對匹配到多個商品資訊的情況，說明第一已收貨商品描述資訊中包含的商品特徵比較少，而訂單中多個商品資訊中都包含第一已收貨商品描述資訊中包含的商品特徵，此時，在一可選方式中，可以對比這多個商品資訊，找出彼此之間的差異商品特徵。該差異商品特徵能夠區分開該多個商品資訊。舉例來說，假設第一已收貨商品描述資訊中包含的商品特徵為BBB品牌連衣裙，如果訂單中包含兩個商品都對應於該BBB品牌連衣裙，而這兩個商品的差異商品特徵可以為尺碼不同或者顏色不同等。值得說明的是，如果存在多個足以區分該多個商品資訊的差異商品特徵時，可以隨機從中選擇一個，或者可以按照不同商品特徵的優先級從中選擇優先級最高的差異商品特徵。進而，根據確定出的差異商品特徵輸出第一提示語音時，可以輸出包含該差異商品特徵的第一提示語音，比如“是某某尺碼的商品嗎”，也可以輸出包含該差異商品特徵和第一已收貨商品描述資訊包含的商品特徵的第一提示語音，比如“是BBB品牌的某某尺碼的連衣裙嗎”。使用者回答該第一提示語音而輸出應答語音，比如該應答語音為“是”或“不是”，從而，可以根據該應答語音確定多個商品資訊對應的商品中哪個是當前的已收貨商品。
可以理解的是，可以逐個針對上述多個商品資訊輸出對應的第一提示語音，假設匹配到兩個商品資訊，對應的商品分別為商品1、商品2，先輸出商品1對應的第一提示語音，如果此時使用者的應答語音為“是”，則說明該商品1即為已到貨商品，此時不必再輸出商品2對應的第一提示語音。可選地，此時，商品1對應的商品資訊作為與已到貨商品對應的目標商品資訊，可以對該目標商品資訊進行已收貨狀態標記。
當匹配到多個商品資訊時，在另一可選方式下，也可以逐個輸出多個商品資訊各自對應的詢問語音，該詢問語音中包含對應的商品資訊的詳細的商品特徵即可以用於唯一標識一個商品的商品特徵，比如包含商品名稱、尺碼、顏色、數量、款號等，進而，使用者回答該詢問語音而輸出應答語音，根據應答語音從該多個商品資訊中確定與已收貨商品對應的目標商品資訊。
第三種情況：若在訂單包含的商品資訊中未匹配到與第一已收貨商品描述資訊對應的商品資訊，則輸出第二提示語音，第二提示語音用於指示使用者重新輸出播報該已收貨商品的語音；識別使用者重新輸出的播報該已收貨商品的第二語音中包含的第二已收貨商品描述資訊；在訂單包含的商品資訊中匹配第二已收貨商品描述資訊，以根據匹配結果確定訂單中的已收貨商品。
實際應用中，可能由於使用者距離較遠、聲音過小、方言等原因導致無法識別出第一語音中包含的第一已收貨商品描述資訊，從而無法匹配到與第一已收貨商品描述資訊對應的商品資訊。此時，可以向使用者輸出第二提示語音，以讓使用者重新輸出用於清點當前的已收貨商品的語音，比如為“訂單中沒有該商品，請重新說出該商品”。基於該第二提示語音使用者可以意識到自己之前輸出第一語音的時候可能因為距離較遠、聲音過小、方言等原因導致客戶端無法準確識別第一語音，此時，可以促使使用者以更加便於進行語音識別的方式重新說出包含第二已收貨商品描述資訊的第二語音，使得客戶端可以針對該第二語音重新進行語音識別、商品資訊匹配的過程，該匹配過程中如果出現第一種情況或第二種情況，則可以參見前述兩種情況的處理邏輯進行處理即可。
值得說明的是，如果使用者重新輸出第二語音後還是無法匹配到對應的商品資訊，或者重新輸出了一定次數還是無法匹配到對應的商品資訊，則客戶端可以提醒用於該已到貨商品無法匹配成功，使用者可以轉而對其他已到貨商品進行清點，待完成其他已到貨商品的清點之後，使用者可以手動查詢訂單，確定是否是商家發錯貨或者其他異常情況。
另一方面，若確定採用設備側語音播報訂單中商品的第二清點模式，則執行步驟605-607：
605、若確定採用第二清點模式，則輸出用於播報訂單中包含的商品資訊的第三語音。
606、獲取使用者響應第三語音而輸出的第四語音。
607、識別第四語音中包含的收貨指示資訊，以根據收貨指示資訊確定是否收到與第三語音中包含的商品資訊對應的商品。
實際應用中，可以按照訂單中商品資訊的排列順序依次播報每個商品資訊。
當向使用者播報出某個商品資訊後，使用者從已收貨商品中查找對應的商品，如果查找到，則可以回覆語音“有”，反之，如果沒有查找到，則可以回覆語音“沒有”。該有、沒有，即為上述收貨指示資訊，從而，基於對使用者的第四語音中該收貨指示資訊的識別，可以確定當前播報的商品資訊對應的商品是否已經被使用者接收，如果已經被接收，則可以對該商品資訊進行已收貨狀態標記，之後繼續播報下一個商品資訊。
綜上，基於本發明實施例提供的兩種語音交互方式可以實現對訂單中商品的可靠、簡便地清點處理。
另外，上述各方法實施例可以是在客戶端側完成的，實際上，也可以基於客戶端與伺服端交互來完成，此時，上述的語音識別過程、在訂單包含的商品資訊中進行匹配的過程可以在伺服端實現。
以下將詳細描述本發明的一個或多個實施例的商品清點裝置。本領域技術人員可以理解，這些商品清點裝置均可使用市售的硬體組件透過本方案所教導的步驟進行配置來構成。
圖7為本發明實施例提供的一種商品清點裝置的結構示意圖，如圖7所示，該裝置包括：語音獲取模組11、語音處理模組12。
語音獲取模組11，用於響應於使用者對訂單觸發的商品清點操作，獲取所述使用者清點所述訂單中商品的語音。
語音處理模組12，用於識別所述語音，以確定所述訂單中的已收貨商品。
可選地，該裝置還包括：模式確定模組13。
模式確定模組13，用於根據所述訂單包含的商品數量確定採用的清點模式；或者，根據所述使用者在清點模式選擇頁面中的選擇操作，確定採用的清點模式；
其中，所述清點模式包括對應於使用者語音輸入已收貨商品的第一清點模式和對應於設備側語音播報訂單中商品的第二清點模式。
其中，在根據所述訂單包含的商品數量確定採用的清點模式的可選實施例中，所述模式確定模組13具體用於：
若所述商品數量大於或等於預設閾值，則確定採用所述第一清點模式；
若所述商品數量小於預設閾值，則確定採用所述第二清點模式。
在一可選實施例中，所述語音獲取模組11用於：若確定採用第一清點模式，則獲取所述使用者播報已收貨商品的第一語音，所述第一清點模式對應於使用者語音輸入已收貨商品的模式。
所述語音處理模組12用於：識別所述第一語音中包含的第一已收貨商品描述資訊；在所述訂單包含的商品資訊中匹配所述第一已收貨商品描述資訊，以根據匹配結果確定所述訂單中的已收貨商品。
其中，可選地，所述語音處理模組12具體可以用於：若在所述訂單包含的商品資訊中僅匹配到一個與所述第一已收貨商品描述資訊對應的目標商品資訊，則確定所述目標商品資訊所對應的商品為所述已收貨商品。
其中，可選地，所述語音處理模組12具體可以用於：若在所述訂單包含的商品資訊中匹配到與所述第一已收貨商品描述資訊對應的多個商品資訊，則確定所述多個商品資訊的差異商品特徵；根據所述差異商品特徵輸出第一提示語音。所述語音獲取模組11還可以用於：接收所述使用者對所述第一提示語音的應答語音。所述語音處理模組12用於：根據所述應答語音從所述多個商品資訊中確定所述已收貨商品對應的目標商品資訊。
所述語音處理模組12具體可以用於：對所述目標商品資訊進行已收貨狀態標記。
其中，可選地，所述語音處理模組12還可以用於：若在所述訂單包含的商品資訊中未匹配到與所述第一已收貨商品描述資訊對應的商品資訊，則輸出第二提示語音，所述第二提示語音用於指示所述使用者重新輸出播報所述已收貨商品的語音；識別所述使用者重新輸出的播報所述已收貨商品的第二語音中包含的第二已收貨商品描述資訊；在所述訂單包含的商品資訊中匹配所述第二已收貨商品描述資訊，以根據匹配結果確定所述訂單中的已收貨商品。
在另一可選實施例中，所述語音處理模組12還用於：若確定採用第二清點模式，則輸出用於播報所述訂單中包含的商品資訊的第三語音，所述第二清點模式對應於設備側語音播報訂單中商品的模式。所述語音獲取模組11用於：獲取所述使用者響應所述第三語音而輸出的第四語音。所述語音處理模組12還用於：識別所述第四語音中包含的收貨指示資訊，以根據所述收貨指示資訊確定是否收到所述商品資訊對應的商品。
可選地，所述裝置還包括：顯示模組14，用於響應於所述使用者觸發的清點結束操作，顯示清點結果頁面，所述清點結果頁面中包括已收貨商品總數、未收貨商品總數、已收貨商品詳情和未收貨商品詳情中的至少一種清點結果提示資訊。
圖7所示裝置可以執行圖1和圖6所示實施例的方法，本實施例未詳細描述的部分，可參考對圖1和圖6所示實施例的相關說明。該技術方案的執行過程和技術效果參見圖1和圖6所示實施例中的描述，在此不再贅述。
以上描述了商品清點裝置的內部功能和結構，在一個可能的設計中，圖8所示商品清點裝置的結構可實現為一電子設備，該電子設備可以為使用者終端設備，如圖8所示，該電子設備可以包括：處理器21和儲存器22。其中，所述儲存器22用於儲存支持電子設備執行上述圖1和圖6所示實施例中提供的商品清點方法的程式，所述處理器21被配置為用於執行所述儲存器22中儲存的程式。
所述程式包括一條或多條電腦指令，其中，所述一條或多條電腦指令被所述處理器21執行時能夠實現如下步驟：
響應於使用者對訂單觸發的商品清點操作，獲取所述使用者清點所述訂單中商品的語音；
識別所述語音，以確定所述訂單中的已收貨商品。
可選地，該處理器21還可以用於執行前述各方法實施例中的全部或部分步驟。
其中，所述電子設備的結構中還可以包括通訊介面23，用於電子設備與其他設備或通訊網路通訊。
另外，本發明實施例提供了一種電腦儲存媒介，用於儲存電子設備所用的電腦軟體指令，其包含用於執行上述圖1和圖6所示方法實施例中商品清點方法所涉及的程式。
以上所描述的裝置實施例僅僅是示意性的，其中所述作為分離部件說明的單元可以是或者也可以不是實體上分開的，作為單元顯示的部件可以是或者也可以不是實體單元，即可以位於一個地方，或者也可以分佈到多個網路單元上。可以根據實際的需要選擇其中的部分或者全部模組來實現本實施例方案的目的。本領域普通技術人員在不付出創造性的勞動的情況下，即可以理解並實施。
透過以上的實施方式的描述，本領域的技術人員可以清楚地瞭解到各實施方式可借助加必需的通用硬體平臺的方式來實現，當然也可以透過硬體和軟體結合的方式來實現。基於這樣的理解，上述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電腦產品的形式體現出來，本發明可採用在一個或多個其中包含有電腦可用程式代碼的電腦可用儲存媒介(包括但不限於磁碟儲存器、CD-ROM、光學儲存器等)上實施的電腦程式產品的形式。
本發明是參照根據本發明實施例的方法、設備(系統)、和電腦程式產品的流程圖及/或方塊圖來描述的。應理解可由電腦程式指令實現流程圖及/或方塊圖中的每一流程及/或方塊、以及流程圖及/或方塊圖中的流程及/或方塊的結合。可提供這些電腦程式指令到通用電腦、專用電腦、嵌入式處理機或其他可程式化資料處理設備的處理器以產生一個機器，使得透過電腦或其他可程式化資料處理設備的處理器執行的指令產生用於實現在流程圖一個流程或多個流程及/或方塊圖一個方塊或多個方塊中指定的功能的裝置。
這些電腦程式指令也可儲存在能引導電腦或其他可程式化資料處理設備以特定方式工作的電腦可讀儲存器中，使得儲存在該電腦可讀儲存器中的指令產生包括指令裝置的製造品，該指令裝置實現在流程圖一個流程或多個流程及/或方塊圖一個方塊或多個方塊中指定的功能。
這些電腦程式指令也可裝載到電腦或其他可程式化資料處理設備上，使得在電腦或其他可程式化設備上執行一系列操作步驟以產生電腦實現的處理，從而在電腦或其他可程式化設備上執行的指令提供用於實現在流程圖一個流程或多個流程及/或方塊圖一個方塊或多個方塊中指定的功能的步驟。
在一個典型的配置中，計算設備包括一個或多個處理器(CPU)、輸入/輸出介面、網路介面和記憶體。
記憶體可能包括電腦可讀媒介中的非永久性儲存器，隨機存取記憶體(RAM)及/或非易失性記憶體等形式，如唯讀記憶體(ROM)或快閃記憶體(flash RAM)。記憶體是電腦可讀媒介的示例。
電腦可讀媒介包括永久性和非永久性、可移除和非可移除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。電腦的儲存媒介的例子包括，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)、電可抹除可程式化唯讀記憶體(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、卡式磁帶，磁帶磁磁碟儲存或其他磁性儲存設備或任何其他非傳輸媒介，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，電腦可讀媒介不包括暫存電腦可讀媒體(transitory media)，如調變的資料信號和載波。
最後應說明的是：以上實施例僅用以說明本發明的技術方案，而非對其限制；儘管參照前述實施例對本發明進行了詳細的說明，本領域的普通技術人員應當理解：其依然可以對前述各實施例所記載的技術方案進行修改，或者對其中部分技術特徵進行等同替換；而這些修改或者替換，並不使相應技術方案的本質脫離本發明各實施例技術方案的精神和範圍。To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be described clearly and completely in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of the embodiments of the present invention, but not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present invention.
The terminology used in the embodiments of the present invention is for the purpose of describing specific embodiments only, and is not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the scope of the attached patent application are also intended to include most forms, unless the context clearly indicates other meanings, "multiple" generally includes At least two, but does not exclude the case that contains at least one.
It should be understood that the term "and/or" used herein is merely an association relationship describing an associated object, indicating that there may be three relationships, for example, A and/or B, which may indicate: A exists alone, and A and B exist simultaneously. There are three cases of B alone. In addition, the character "/" in this article generally indicates that the related objects are a "or" relationship.
Depending on the context, the words "if" and "if" as used herein can be interpreted as "at..." or "when..." or "in response to determination" or "in response to detection". Similarly, depending on the context, the phrase "if determined" or "if detected (condition or event stated)" can be interpreted as "when determined" or "in response to determination" or "when detected (condition stated or Event)" or "in response to detection (statement or event stated)".
It should also be noted that the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusions, so that a commodity or system that includes a series of elements includes not only those elements, but also those not explicitly listed Or other elements that are inherent to this commodity or system. Without more restrictions, the element defined by the sentence "include one..." does not exclude that there are other identical elements in the commodity or system that includes the element.
In addition, the sequence of steps in the following method embodiments is only an example, not strictly limited.
FIG. 1 is a flowchart of a commodity inventory method provided by an embodiment of the present invention. The commodity inventory method provided by this embodiment may be executed by a commodity inventory device, and the commodity inventory device may be implemented as software, or as software and hardware. Body combination. Optionally, the commodity counting device may be installed in a shopping client in the user terminal device, or may be installed in a shopping server. As shown in Figure 1, the method includes the following steps:
101. In response to the user's inventory operation triggered by the order, obtain the voice of the user's inventory of the order.
102. Identify the voice of the goods in the inventory order to determine the goods received in the order.
Take the scenario where a user uses a shopping client to make a purchase. For example, after the user places an order, the user will receive the purchased product at a certain time. At this time, in order to check whether the received product is the product and the order Whether the goods ordered have been delivered, it is necessary to carry out inventory check.
At this time, optionally, the user can trigger the inventory operation through the following operations: open the shopping client, select the corresponding order to enter the order details page, as shown in Figure 2, the order details page can be set to trigger the commodity inventory operation Control item, the user clicks the control item to trigger the inventory operation.
In an alternative embodiment, when it is detected that the user triggers a product inventory operation for an order, the trigger voice collection function takes effect to receive the user's voice for inventorying the products in the order. In this embodiment, for any received goods, the user can speak the description information of the received goods, that is, output the voice containing the description information of the received goods. Among them, the description information of the received goods may include, for example, the product name, size, color, quantity, section number and other product characteristics. After collecting the voice, perform voice recognition processing on the voice to recognize the description information of the received goods contained in the voice. Optionally, as shown in FIG. 3, the voice recognition result can be displayed in the interface so that Let the user see whether the recognition result is consistent with the output description information of the received goods. Furthermore, you can find whether there is product information that matches the received product description information in the product information corresponding to the order to determine which product in the order the user currently receives is the product information, which can be reflected Record items for each item in the order details page. When finding the product information that matches the received product description information, optionally, as shown in FIG. 4, the matched product information can be highlighted, and the received product information can also be marked as received The status mark can also play a preset prompt tone to remind the user that the corresponding product information has been matched. According to the above process, the user sequentially outputs the voice corresponding to each received product. Based on the above voice recognition and product information matching processing, you can finally get how many products in the order have been received by the user, how many products have not been delivered, etc. News. Optionally, the inventory completion control item can be set in the interface shown in FIG. 4, and when the user clicks the control item, the inventory end operation is triggered. At this time, as shown in FIG. 5, the inventory result page can be displayed. The inventory result The page may include at least one kind of inventory result prompting information among the total number of goods received, the total number of goods not received, the details of goods received, and the details of goods not received. The triggering of the inventory end operation may also be regarded as that the inventory end operation is triggered if the voice of the product inventory is not received within a certain period of time.
It is understandable that whenever a description of the arrival commodity is matched in the commodity information included in the order, the total number of goods received and the total number of goods not received will be updated. The received product details and the unreceived product details can be different. The product information corresponding to the received goods in the order and the product information of the unreceived goods are displayed. For example, the unreceived product information is focused on the front and highlighted , The information of the received goods is displayed centrally afterwards, not limited to this.
In summary, based on the product inventory solution in the voice interaction mode provided by the embodiments of the present invention, during the inventory process of the products in the order, the user interacts with the shopping client to output voices for product inventory one by one, In order to recognize the voice to determine which product in the order corresponding to the received product received by the user, the inventory of the received product is finally completed. In this solution, there is no need to configure additional hardware devices on the user side, and the inventory can be simply and conveniently realized through voice interaction.
FIG. 6 is a flowchart of another method for counting goods according to an embodiment of the present invention. As shown in FIG. 6, the method may include the following steps:
601. In response to the user's inventory operation triggered by the order, display an inventory mode selection page.
602. Determine the adopted inventory mode according to the user's selection operation on the inventory mode selection page.
The solution for inventorying goods based on voice interaction according to an embodiment of the present invention may provide two optional inventory modes: a first inventory mode corresponding to the user's voice input of the received goods and a product inventory corresponding to the products in the voice announcement order on the device side The second inventory mode. To put it simply, the first inventory mode is a mode for the user to output the description information of the received goods by voice, and perform voice recognition on the client side and find the product information that matches the received goods in the product information included in the order; The second inventory mode is a mode in which the client side broadcasts the commodity information included in the order. The user finds whether there is a received commodity corresponding to the broadcasted commodity information in the received commodity, and performs voice feedback based on the search result.
In an alternative embodiment, the user can independently choose which inventory mode to use for inventory counting according to his own needs. At this time, when the user triggers the inventory operation by clicking the inventory control item on the order details page shown in FIG. 2, for example, the inventory mode selection page can be displayed on the interface, which includes the first inventory mode and the second inventory Mode selection item, the user can select the required inventory mode from it.
It is worth noting that after the user selects a certain inventory mode for inventory, during the inventory process, the user can also switch to another inventory mode for inventory, that is to say, in a commodity inventory process, use You can switch between the two inventory modes according to actual needs.
It is understandable that the above two inventory modes also complement each other, to avoid that when one inventory mode cannot complete the commodity inventory process well, another inventory mode can be adopted to complete the commodity inventory process. For example, when the first inventory mode is used, if the accuracy of speech recognition is poor due to problems such as the user's accent, the second inventory mode can make up for this deficiency.
In another optional embodiment, compared with the way in which the user manually selects the inventory mode, the inventory mode can also be automatically selected. At this time, you can determine which inventory mode to use based on the number of goods included in the order. For example: if the number of commodities is greater than or equal to the preset threshold, the first inventory mode is determined; if the number of commodities is less than the preset threshold, the second inventory mode is determined. Because, when the number of products in the order is large, generally, the number of received goods is also large, at this time, the first inventory mode can be used to prevent users from finding the products broadcast by the client among many received goods. Inconvenience; on the contrary, when the number of goods in the order is small, generally, the number of goods received is also small, in this case, the second inventory mode can avoid the need for users to speak long received goods information .
On the one hand, if it is determined that the above-mentioned first inventory mode is adopted, steps 603-604 are executed:
603. If it is determined that the first inventory mode is adopted, obtain the first voice of the user broadcasting the received goods.
604. Identify the first received product description information included in the first voice, and match the first received product description information in the product information included in the order to determine the received product in the order according to the matching result.
As described in the foregoing embodiment, for any received commodity, the user can speak a voice containing description information of the received commodity (referred to as first received commodity description information). Among them, the description information of the first received commodity may include, for example, the commodity name, size, color, quantity, model number and other commodity characteristics. After the voice is collected, a voice recognition process is performed on the voice to recognize the first received commodity description information contained therein. Furthermore, the first received product description information can be matched in the product information included in the order to determine whether the order contains product information matching the first received product description information, so that the order can be based on the matching result. Received goods for.
In the process of matching the first received product description information with the product information contained in the order, there may be a matching product information corresponding to the first received product description information, and multiple matching to the first received product information There are several cases where the product information corresponding to the received product description information does not match the product information corresponding to the first received product description information. The processing logics under the various matching results that may be encountered during the execution of step 604 are described below Be explained.
The first case: If only one target product information corresponding to the first received product description information is matched in the product information included in the order, then the product corresponding to the target product information is determined to be the received product. At this time, optionally, the target product information can be marked with the received status, so that in the subsequent inventory process for another received product, it is no longer necessary to match the product information with the received status indicator. Reduced the number of matches. In addition, in order to improve the user experience, when the target product information is matched, a preset prompt sound can also be played to remind the user that the corresponding product information has been matched, such as playing "matching success".
The second case: If multiple product information corresponding to the first received product description information is matched in the product information included in the order, the difference product characteristics of the multiple product information are determined; the first prompt is output according to the difference product characteristics Voice; receive the user's response voice to the first prompt voice; determine the target product information corresponding to the received product from the multiple product information according to the response voice, that is, determine the product corresponding to the multiple product information according to the response voice Goods received.
As mentioned before, for any received product, in order to ensure the accuracy of the matching result, when the user describes the received product, ideally, he should say complete description information of the received product, that is, It is used to uniquely identify various product characteristics of the received product, such as product name, size, color, quantity, and model number. When the description information of the first received product spoken by the user is too vague, it may result in a situation where the corresponding product information cannot be successfully matched, or multiple product information is matched.
In the case of matching multiple product information, it means that the first received product description information contains fewer product characteristics, and the multiple product information in the order contains the first received product description information. At this time, in an optional way, you can compare the multiple product information to find out the differences between the product characteristics. The difference product characteristics can distinguish the plurality of product information. For example, assuming that the product feature included in the description of the first received product is a BBB brand dress, if the order contains two products that correspond to the BBB brand dress, the difference between the two products can be the size of the product feature Different or different colors. It is worth noting that if there are multiple different product features sufficient to distinguish the multiple product information, one can be randomly selected from them, or the highest priority differential product features can be selected according to the priority of different product features. Furthermore, when the first prompt voice is output according to the determined difference product feature, the first prompt voice including the difference product feature may be output, such as "Is the product of a certain size", or the output containing the difference product feature and the first A first prompt voice of the product features included in the received product description information, such as "Is it a dress of the certain size of the BBB brand?" The user answers the first prompt voice and outputs a response voice, for example, the response voice is "yes" or "no", so that it can be determined which of the products corresponding to the multiple product information is the current received product according to the response voice .
It is understandable that the corresponding first prompt voice can be output one by one for the above multiple product information, assuming that two product information are matched, the corresponding products are product 1, product 2, and the first prompt voice corresponding to product 1 is output first If the user's answer voice is "Yes" at this time, it means that the product 1 is an already-arrived product, and there is no need to output the first prompt voice corresponding to the product 2 at this time. Optionally, at this time, the product information corresponding to the product 1 is used as the target product information corresponding to the delivered product, and the target product information may be marked as received.
When multiple product information is matched, in another optional way, the query voice corresponding to each product information can also be output one by one, and the query voice contains detailed product characteristics of the corresponding product information can be used for unique Identify the product features of a product, such as product name, size, color, quantity, model number, etc. In addition, the user answers the query voice and outputs a response voice, which is determined and received from the multiple product information according to the response voice The target product information corresponding to the product.
The third case: If the product information corresponding to the first received product description information is not matched in the product information included in the order, the second prompt voice is output, and the second prompt voice is used to instruct the user to re-output the broadcast The voice of the received product; identify the second received product description information contained in the second voice re-output by the user that broadcasts the received product; match the second received product description in the product information included in the order Information to determine the goods received in the order based on the matching result.
In practical applications, the first received product description information included in the first voice may not be recognized due to the user's long distance, low voice, dialect, etc., so that it cannot be matched with the first received product description information Corresponding product information. At this time, a second prompt voice can be output to the user to allow the user to re-output the voice used to count the current received goods, for example, "the product is not in the order, please say the product again." Based on the second prompt voice, the user can realize that when the first voice was output before, the client may not be able to accurately recognize the first voice because of the distance, the sound is too small, or the dialect. At this time, the user may be prompted to It is convenient for voice recognition to re-speak the second voice containing the description information of the second received goods, so that the client can re-process the voice recognition and product information matching for the second voice. For one case or the second case, you can refer to the processing logic of the previous two cases for processing.
It is worth noting that if the user cannot match the corresponding product information after re-outputting the second voice, or if the product information cannot be matched after re-outputting a certain number of times, the client can be reminded to use the product If the match cannot be matched successfully, the user can turn to check the other goods that have arrived. After the inventory of the other goods has been completed, the user can manually check the order to determine whether the merchant sent the wrong goods or other abnormal conditions.
On the other hand, if it is determined to use the second inventory mode of the device-side voice announcement of the goods in the order, then steps 605-607 are executed:
605. If it is determined that the second inventory mode is adopted, output a third voice for broadcasting the commodity information included in the order.
606. Acquire a fourth voice output by the user in response to the third voice.
607. Identify the receipt instruction information included in the fourth voice, to determine whether a commodity corresponding to the commodity information included in the third voice is received according to the receipt instruction information.
In actual application, you can broadcast each product information in order according to the order of the product information in the order.
After broadcasting a certain product information to the user, the user finds the corresponding product from the received goods. If it finds it, it can reply the voice "Yes", otherwise, if it does not find it, it can reply the voice "No" ". The presence and absence are the above-mentioned receipt instruction information. Therefore, based on the recognition of the receipt instruction information in the user's fourth voice, it can be determined whether the commodity corresponding to the currently announced commodity information has been received by the user, if If it has been received, you can mark the product information as received, and then continue to broadcast the next product information.
In summary, based on the two voice interaction methods provided by the embodiments of the present invention, reliable and simple inventory processing of the goods in the order can be achieved.
In addition, the above method embodiments can be completed on the client side, in fact, it can also be completed based on the interaction between the client and the server. At this time, the above voice recognition process is matched in the product information included in the order The process can be implemented on the servo side.
The commodity counting device of one or more embodiments of the present invention will be described in detail below. Those skilled in the art can understand that these commodity inventory devices can be configured by using commercially available hardware components through the steps taught in this solution.
7 is a schematic structural diagram of a product inventory device provided by an embodiment of the present invention. As shown in FIG. 7, the device includes: a voice acquisition module 11 and a voice processing module 12.
The voice acquisition module 11 is configured to acquire the voice of the user's inventory of the products in the order in response to the user's inventory operation triggered by the order.
The voice processing module 12 is used to recognize the voice to determine the received goods in the order.
Optionally, the device further includes: a mode determination module 13.
The mode determination module 13 is used to determine the inventory mode to be used according to the number of commodities included in the order; or to determine the inventory mode to be used according to the user's selection operation on the inventory mode selection page;
Wherein, the inventory mode includes a first inventory mode corresponding to the user's voice input of the received goods and a second inventory mode corresponding to the device-side voice broadcast of the goods in the order.
Wherein, in an optional embodiment of determining the inventory mode to be adopted according to the number of commodities included in the order, the mode determination module 13 is specifically used to:
If the number of commodities is greater than or equal to a preset threshold, it is determined to use the first inventory mode;
If the number of commodities is less than a preset threshold, it is determined to use the second inventory mode.
In an alternative embodiment, the voice acquisition module 11 is configured to: if it is determined that the first inventory mode is adopted, acquire the first voice of the user broadcasting the received goods, the first inventory mode corresponding to User voice input mode of received goods.
The voice processing module 12 is used to: identify the first received commodity description information included in the first voice; match the first received commodity description information in the commodity information included in the order, to According to the matching result, the received goods in the order are determined.
Wherein, optionally, the voice processing module 12 may be specifically used to: if only one target product information corresponding to the first received product description information is matched in the product information included in the order, then It is determined that the commodity corresponding to the target commodity information is the received commodity.
Wherein, optionally, the voice processing module 12 may be specifically used to determine if multiple commodity information corresponding to the first received commodity description information is matched in the commodity information included in the order Different product features of the plurality of product information; output a first prompt voice according to the different product features. The voice acquisition module 11 may also be used to receive the user's response voice to the first prompt voice. The voice processing module 12 is configured to determine target commodity information corresponding to the received commodity from the plurality of commodity information according to the response voice.
The voice processing module 12 may be specifically used for: marking the received product status of the target product information.
Wherein, optionally, the voice processing module 12 may also be used to output the product information if the product information corresponding to the first received product description information is not matched in the product information included in the order Two prompt voices, the second prompt voice is used to instruct the user to re-output the voice that broadcasts the received goods; the second voice that recognizes the re-output of the user that broadcasts the received goods includes Description information of the second received commodity; matching the description information of the second received commodity in the commodity information included in the order to determine the received commodity in the order according to the matching result.
In another optional embodiment, the voice processing module 12 is further configured to: if it is determined that the second inventory mode is adopted, output a third voice for broadcasting the commodity information included in the order, the second The inventory mode corresponds to the mode of voice announcement of goods in the order on the device side. The voice acquisition module 11 is configured to acquire a fourth voice output by the user in response to the third voice. The voice processing module 12 is further configured to: identify receipt instruction information included in the fourth voice, to determine whether to receive a commodity corresponding to the commodity information according to the receipt instruction information.
Optionally, the device further includes: a display module 14 configured to display an inventory result page in response to an inventory end operation triggered by the user, where the inventory result page includes the total number of goods received and unreceived goods At least one of the total number of products, the received product details and the unreceived product details inventory result prompt information.
The device shown in FIG. 7 can execute the method of the embodiments shown in FIGS. 1 and 6. For the parts that are not described in detail in this embodiment, reference may be made to the relevant description of the embodiments shown in FIGS. 1 and 6. For the execution process and technical effect of the technical solution, refer to the description in the embodiments shown in FIG. 1 and FIG. 6, and details are not described herein again.
The internal functions and structure of the product inventory device are described above. In a possible design, the structure of the product inventory device shown in FIG. 8 may be implemented as an electronic device, and the electronic device may be a user terminal device, as shown in FIG. 8 The electronic device may include a processor 21 and a storage 22. Wherein, the storage 22 is used to store a program that supports an electronic device to perform the commodity inventory method provided in the embodiments shown in FIGS. 1 and 6 above, and the processor 21 is configured to execute the storage 22 Saved programs.
The program includes one or more computer instructions. When the one or more computer instructions are executed by the processor 21, the following steps can be implemented:
In response to the user's inventory operation triggered by the user's order, acquiring the voice of the user's inventory of the product in the order;
Recognize the voice to determine the received goods in the order.
Optionally, the processor 21 may also be used to execute all or part of the steps in the foregoing method embodiments.
Among them, the structure of the electronic device may further include a communication interface 23 for communication between the electronic device and other devices or a communication network.
In addition, an embodiment of the present invention provides a computer storage medium for storing computer software instructions used by an electronic device, which includes a program for executing the commodity inventory method in the method embodiments shown in FIGS. 1 and 6 described above.
The device embodiments described above are only schematics, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located One place, or can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement without paying creative labor.
Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by adding a necessary general hardware platform, and of course, can also be implemented by a combination of hardware and software. Based on this understanding, the above technical solutions can be embodied in the form of computer products in essence or part of the contribution to the existing technology. The present invention can use one or more computer-usable storage media containing computer-usable program codes (Including but not limited to disk storage, CD-ROM, optical storage, etc.) The form of computer program products implemented.
The present invention is described with reference to flowcharts and/or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and/or block in the flowchart and/or block diagram and a combination of the flow and/or block in the flowchart and/or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing equipment to produce a machine that allows instructions to be executed by the processor of the computer or other programmable data processing equipment Generate means for implementing the functions specified in one block or multiple blocks of one flow or multiple flows of a flowchart and/or one block of a block diagram.
These computer program instructions can also be stored in a computer readable memory that can guide the computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device The instruction device implements the functions specified in one block or multiple blocks in one flow or multiple processes in the flowchart and/or one block in the block diagram.
These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operating steps can be performed on the computer or other programmable device to generate computer-implemented processing, and thus on the computer or other programmable device The instructions executed on the provide steps for implementing the functions specified in one block or multiple blocks of the flowchart one flow or multiple flows and/or block diagrams.
In a typical configuration, the computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
Memory may include non-permanent storage in computer-readable media, random access memory (RAM) and/or non-volatile memory, such as read only memory (ROM) or flash memory ( flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including permanent and non-permanent, removable and non-removable media, can store information by any method or technology. The 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 disks (DVD) or other optical storage, cassette tapes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media can 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.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, persons of ordinary skill in the art should understand that they can still The technical solutions described in the foregoing embodiments are modified, or some of the technical features are equivalently replaced; and these modifications or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.
