本說明書一個或多個實施例的目的是提供一種問題推送方法及裝置，用以完善問題推送機制，以使推送的問題更具針對性。 為解決上述技術問題，本說明書一個或多個實施例是這樣實現的： 一方面，本說明書一個或多個實施例提供一種問題推送方法，包括： 判定目標使用者的驗證問題的特徵屬性；其中，所述特徵屬性包括：驗證問題的答題正確率、安全程度、隱私程度中的至少一項； 根據所述驗證問題的特徵屬性，判定所述驗證問題的推送分值； 根據每個所述驗證問題的推送分值，判定向所述目標使用者推送的目標驗證問題。 可選地，所述根據所述驗證問題的特徵屬性，判定所述驗證問題的推送分值，包括： 判定所述驗證問題的特徵屬性的權值，以及，判定所述驗證問題的特徵屬性的屬性值； 將所述驗證問題的特徵屬性的權值以及屬性值的加權值判定為所述驗證問題的推送分值。 可選地，所述判定所述驗證問題的特徵屬性的權值，包括： 根據所述目標使用者所對應的驗證服務的場景和/或業務類型，判定所述驗證問題的特徵屬性的權值。 可選地，所述特徵屬性包括所述驗證問題的答題正確率； 相應的，判定所述驗證問題的特徵屬性的屬性值，包括： 獲取所述目標使用者在當前驗證服務所對應的業務中的歷史行為資料，所述歷史行為資料包括對所述業務的歷史使用行為資訊、針對所述驗證問題的歷史答題行為資訊、所述驗證問題的答題通過率得分中的至少一項； 構建指定二分類模型； 將所述歷史行為資料作為所述指定二分類模型的樣本資料進行訓練，得到所述驗證問題的答題正確率。 可選地，所述歷史答題行為資訊包括答題結果，所述答題結果包括正確結果或錯誤結果； 所述方法還包括： 獲取所述目標使用者在當前驗證服務中針對所述目標驗證問題的答題結果； 根據針對所述目標驗證問題的答題結果，更新所述目標驗證問題的答題正確率。 可選地，所述特徵屬性包括所述安全程度； 相應的，判定所述驗證問題的特徵屬性的屬性值，包括： 根據所述驗證問題中包含的關鍵字，判定所述驗證問題所攜帶的資訊量； 根據所述資訊量判定所述驗證問題的安全程度，其中，所述資訊量與所述安全程度成正比。 可選地，所述特徵屬性包括所述隱私程度； 相應的，判定所述驗證問題的特徵屬性的屬性值，包括： 判定所述驗證問題和所述目標使用者的個人資訊之間的相關度； 根據所述相關度判定所述驗證問題的隱私程度，其中，所述相關度與所述隱私程度成正比。 可選地，根據每個所述驗證問題的推送分值，判定向所述目標使用者推送的目標驗證問題，包括： 將所述推送分值最高的驗證問題判定為向所述目標使用者推送的目標驗證問題；或， 將達到預設臨限值的推送分值所對應的驗證問題判定為向所述目標使用者推送的目標驗證問題。 另一方面，本說明書一個或多個實施例提供一種問題推送裝置，包括： 第一判定模組，判定目標使用者的驗證問題的特徵屬性；其中，所述特徵屬性包括：驗證問題的答題正確率、安全程度、隱私程度中的至少一項； 第二判定模組，根據所述驗證問題的特徵屬性，判定所述驗證問題的推送分值； 第三判定模組，根據每個所述驗證問題的推送分值，判定向所述目標使用者推送的目標驗證問題。 可選地，所述第二判定模組包括： 第一判定單元，判定所述驗證問題的特徵屬性的權值，以及，判定所述驗證問題的特徵屬性的屬性值； 第二判定單元，將所述驗證問題的特徵屬性的權值以及屬性值的加權值判定為所述驗證問題的推送分值。 可選地，所述第一判定單元，根據所述目標使用者所對應的驗證服務的場景和/或業務類型，判定所述驗證問題的特徵屬性的權值。 可選地，所述特徵屬性包括所述驗證問題的答題正確率； 所述第一判定單元，獲取所述目標使用者在當前驗證服務所對應的業務中的歷史行為資料，所述歷史行為資料包括對所述業務的歷史使用行為資訊、針對所述驗證問題的歷史答題行為資訊、所述驗證問題的答題通過率得分中的至少一項；構建指定二分類模型；將所述歷史行為資料作為所述指定二分類模型的樣本資料進行訓練，得到所述驗證問題的答題正確率。 可選地，所述歷史答題行為資訊包括答題結果，所述答題結果包括正確結果或錯誤結果； 所述裝置還包括： 獲取模組，獲取所述目標使用者在當前驗證服務中針對所述目標驗證問題的答題結果； 更新模組，根據針對所述目標驗證問題的答題結果，更新所述目標驗證問題的答題正確率。 可選地，所述特徵屬性包括所述安全程度； 所述第一判定單元，根據所述驗證問題中包含的關鍵字，判定所述驗證問題所攜帶的資訊量；根據所述資訊量判定所述驗證問題的安全程度，其中，所述資訊量與所述安全程度成正比。 可選地，所述特徵屬性包括所述隱私程度； 所述第一判定單元，判定所述驗證問題和所述目標使用者的個人資訊之間的相關度；根據所述相關度判定所述驗證問題的隱私程度，其中，所述相關度與所述隱私程度成正比。 可選地，所述第三判定模組包括： 第三判定單元，將所述推送分值最高的驗證問題判定為向所述目標使用者推送的目標驗證問題；或， 第四判定單元，將達到預設臨限值的推送分值所對應的驗證問題判定為向所述目標使用者推送的目標驗證問題。 再一方面，本說明書一個或多個實施例提供一種問題推送設備，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： 判定目標使用者的驗證問題的特徵屬性；其中，所述特徵屬性包括：驗證問題的答題正確率、安全程度、隱私程度中的至少一項； 根據所述驗證問題的特徵屬性，判定所述驗證問題的推送分值； 根據每個所述驗證問題的推送分值，判定向所述目標使用者推送的目標驗證問題。 再一方面，本說明書一個或多個實施例提供一種儲存介質，用於儲存電腦可執行指令，所述可執行指令在被執行時實現以下流程： 判定目標使用者的驗證問題的特徵屬性；其中，所述特徵屬性包括：驗證問題的答題正確率、安全程度、隱私程度中的至少一項； 根據所述驗證問題的特徵屬性，判定所述驗證問題的推送分值； 根據每個所述驗證問題的推送分值，判定向所述目標使用者推送的目標驗證問題。 採用本說明書一個或多個實施例的技術方案，能夠判定目標使用者的驗證問題的特徵屬性（包括驗證問題的答題正確率、安全程度、隱私程度中的至少一項），根據特徵屬性判定驗證問題的推送分值，進而根據每個驗證問題的推送分值判定向目標使用者推送的目標驗證問題。因此，該技術方案在向使用者推送驗證問題時，能夠兼顧目標使用者的驗證問題的答題正確率、安全程度和/或隱私程度，從而在採用問答形式進行身份驗證時能夠更加有針對性地、靈活地向使用者推送驗證問題，完善了驗證問題的推送機制，且提升使用者的答題通過率以及驗證服務的安全性和隱私性，進而提升使用者對驗證服務的體驗度。The purpose of one or more embodiments of this specification is to provide a problem pushing method and device to improve the problem pushing mechanism, so that the pushed problems are more targeted. In order to solve the above technical problems, one or more embodiments of this specification are implemented as follows: On the one hand, one or more embodiments of this specification provide a problem push method, including: determining the characteristic attributes of the verification problem of the target user; wherein , The characteristic attribute includes: at least one of the correct answer rate of the verification question, the degree of security, and the degree of privacy; according to the characteristic attribute of the verification question, determine the push score of the verification question; The push score of the question determines the target verification question pushed to the target user. Optionally, said determining the push score of the verification question according to the characteristic attribute of the verification question includes: determining the weight of the characteristic attribute of the verification question, and determining the characteristic attribute of the verification question Attribute value; Determine the weight value of the characteristic attribute of the verification question and the weighted value of the attribute value as the push score of the verification question. Optionally, the determining the weight of the characteristic attribute of the verification question includes: determining the weight of the characteristic attribute of the verification question according to the scenario and/or business type of the verification service corresponding to the target user . Optionally, the characteristic attribute includes the correct answer rate of the verification question; correspondingly, determining the attribute value of the characteristic attribute of the verification question includes: obtaining the target user in the business corresponding to the current verification service The historical behavior data includes at least one of the historical use behavior information of the business, the historical answer behavior information for the verification question, and the answer pass rate score of the verification question; construction designated two Classification model; train the historical behavior data as the sample data of the specified two-classification model to obtain the correct answer rate of the verification question. Optionally, the historical answering behavior information includes answering results, and the answering results include correct results or incorrect results; The method further includes: obtaining the answers of the target user to the target verification question in the current verification service Results; According to the answer results for the target verification question, update the correct answer rate of the target verification question. Optionally, the characteristic attribute includes the degree of security; correspondingly, determining the attribute value of the characteristic attribute of the verification question includes: determining what the verification question carries according to the keywords contained in the verification question The amount of information; Determine the degree of security of the verification problem based on the amount of information, wherein the amount of information is proportional to the degree of security. Optionally, the characteristic attribute includes the degree of privacy; correspondingly, determining the attribute value of the characteristic attribute of the verification question includes: determining the correlation between the verification question and the personal information of the target user Determine the degree of privacy of the verification question according to the degree of correlation, wherein the degree of correlation is directly proportional to the degree of privacy. Optionally, determining the target verification question pushed to the target user according to the push score of each verification question includes: determining the verification question with the highest push score to be pushed to the target user Or, judges the verification problem corresponding to the push score that reaches the preset threshold value as the target verification problem pushed to the target user. On the other hand, one or more embodiments of the present specification provide a question push device, including: a first judgment module, which judges the characteristic attribute of the verification question of the target user; wherein the characteristic attribute includes: the answer to the verification question is correct The second judgment module determines the push score of the verification question according to the characteristic attribute of the verification question; The third judgment module, according to each verification The push score of the question determines the target verification question pushed to the target user. Optionally, the second judgment module includes: a first judgment unit that judges the weight of the characteristic attribute of the verification question, and judges the attribute value of the characteristic attribute of the verification question; a second judgment unit, The weighted value of the characteristic attribute of the verification question and the weighted value of the attribute value are determined as the push score of the verification question. Optionally, the first determining unit determines the weight of the characteristic attribute of the verification question according to the scenario and/or business type of the verification service corresponding to the target user. Optionally, the characteristic attribute includes the correct answer rate of the verification question; the first determining unit obtains historical behavior data of the target user in the business corresponding to the current verification service, the historical behavior data Including at least one of the historical use behavior information of the business, the historical answering behavior information for the verification question, and the pass rate score of the verification question; constructing a designated two-class model; using the historical behavior data as The sample data of the designated two-classification model is trained to obtain the correct answer rate of the verification question. Optionally, the historical answering behavior information includes answering results, the answering results including correct results or incorrect results; The device further includes: acquisition module to obtain the target user in the current verification service for the target The answer result of the verification question; update module, according to the answer result for the target verification question, update the correct answer rate of the target verification question. Optionally, the characteristic attribute includes the degree of security; the first determining unit determines the amount of information carried by the verification question according to the keywords contained in the verification question; The security level of the verification problem, wherein the amount of information is proportional to the security level. Optionally, the characteristic attribute includes the degree of privacy; the first determination unit determines the correlation between the verification question and the personal information of the target user; determines the verification according to the correlation The degree of privacy of the question, wherein the degree of correlation is directly proportional to the degree of privacy. Optionally, the third judgment module includes: a third judgment unit, which judges the verification question with the highest push score as the target verification question pushed to the target user; or, fourth judgment unit, The verification question corresponding to the push score that reaches the preset threshold is determined as the target verification question pushed to the target user. In another aspect, one or more embodiments of the present specification provide a problem push device, including: a processor; and a memory arranged to store computer-executable instructions, which when executed, cause the processor to determine the characteristic attribute of the verification question of the target user; wherein the characteristic attribute includes: at least one of the correct answer rate of the verification question, the degree of security, and the degree of privacy; judge the characteristic according to the characteristic attribute of the verification question Push score of the verification question; Determine the target verification question pushed to the target user according to the push score of each verification question. In another aspect, one or more embodiments of this specification provide a storage medium for storing computer-executable instructions that, when executed, realize the following process: determine the characteristic attributes of the verification problem of the target user; wherein , The characteristic attribute includes: at least one of the correct answer rate of the verification question, the degree of security, and the degree of privacy; according to the characteristic attribute of the verification question, determine the push score of the verification question; according to each verification The push score of the question determines the target verification question pushed to the target user. Using the technical solutions of one or more embodiments of this specification, it is possible to determine the characteristic attributes of the verification questions of the target user (including at least one of the correct answer rate of the verification questions, the degree of security, and the degree of privacy), and determine the verification according to the characteristic attributes The push score of the question, and then determine the target verification question pushed to the target user based on the push score of each verification question. Therefore, this technical solution can take into account the correct answer rate, security level and/or privacy level of the target user’s verification question when pushing the verification question to the user, so that it can be more targeted when using the question and answer form for identity verification. , Flexible push verification questions to users, improve the push mechanism of verification questions, and improve the user's answer pass rate and the security and privacy of the verification service, thereby enhancing the user's experience of the verification service.
本說明書一個或多個實施例提供一種問題推送方法及裝置，用以完善問題推送機制，以使推送的問題更具針對性。 為了使本技術領域的人員更好地理解本說明書一個或多個實施例中的技術方案，下面將結合本說明書一個或多個實施例中的附圖，對本說明書一個或多個實施例中的技術方案進行清楚、完整地描述，顯然，所描述的實施例僅僅是本說明書一部分實施例，而不是全部的實施例。基於本說明書一個或多個實施例，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，都應當屬於本說明書一個或多個實施例保護的範圍。 圖1是根據本說明書一實施例的一種問題推送方法的示意性流程圖，如圖1所示，該方法包括： 步驟S102，判定目標使用者的驗證問題的特徵屬性。 其中，特徵屬性包括驗證問題的答題正確率、安全程度、隱私程度中的至少一項。 步驟S104，根據驗證問題的特徵屬性，判定驗證問題的推送分值。 步驟S106，根據每個驗證問題的推送分值，判定向目標使用者推送的目標驗證問題。 採用本說明書一個或多個實施例的技術方案，能夠判定目標使用者的驗證問題的特徵屬性（包括驗證問題的答題正確率、安全程度、隱私程度中的至少一項），根據特徵屬性判定驗證問題的推送分值，進而根據每個驗證問題的推送分值判定向目標使用者推送的目標驗證問題。因此，該技術方案在向使用者推送驗證問題時，能夠兼顧目標使用者的驗證問題的答題正確率、安全程度和/或隱私程度，從而在採用問答形式進行身份驗證時能夠更加有針對性地、靈活地向使用者推送驗證問題，完善了驗證問題的推送機制，且提升使用者的答題通過率以及驗證服務的安全性和隱私性，進而提升使用者對驗證服務的體驗度。 在一個實施例中，根據驗證問題的特徵屬性判定驗證問題的推送分值時，首先判定驗證問題的特徵屬性的權值，以及，判定驗證問題的特徵屬性的屬性值；進而將驗證問題的特徵屬性的權值以及屬性值的加權值判定為驗證問題的推送分值。 本實施例中，驗證問題的特徵屬性的權值可根據目標使用者所對應的驗證服務的場景和/或業務類型來判定。其中，驗證服務的場景如使用帳號進行登錄、修改資訊等；驗證服務的業務類型如購物類、遊戲類、金融類等。根據驗證服務的場景和/或業務類型的不同，可針對驗證問題的特徵屬性設置不同的權值。例如，當驗證服務的場景為修改資訊時，可對特徵屬性中安全程度和隱私程度均設置較高的權值；當驗證服務的業務類型屬於金融類時，可對特徵屬性中安全程度設置較高的權值；當驗證服務的業務類型屬於購物類時，可對特徵屬性中對驗證問題的答題正確率設置較高的權值；等等。 通常情況下，同一使用者可對應多個不同的驗證問題。因此，對於目標使用者的多個驗證問題，各驗證問題的特徵屬性的權值可設置為相同，也可設置為不同。 本實施例中，屬性值的表徵方式可採用分值、概率等形式。例如，使用者對各問題的答題正確率對應的屬性值可以是答題正確率本身，各問題的安全程度對應的屬性值可以是安全分值，各問題的隱私程度對應的屬性值可以是隱私分值。同一驗證問題的各特徵屬性分別對應的權值的和為1。 以下詳細介紹如何判定驗證問題的特徵屬性的屬性值。 當特徵屬性包括驗證問題的答題正確率時，可按照如下方式判定驗證問題的答題正確率（即答題正確率的屬性值）： 首先，獲取目標使用者在當前驗證服務所對應的業務中的歷史行為資料，該歷史行為資料包括對該業務的歷史使用行為資訊、針對驗證問題的歷史答題行為資訊、驗證問題的答題通過率得分中的至少一項。 其中，歷史答題行為資訊包括答題結果，答題結果包括正確結果或錯誤結果。 表1示例性地示出了某個驗證問題的答題通過率得分情況。由表1可看出該驗證問題的答題通過率與答題通過率得分之間的對應關係，例如，若該驗證問題的答題通過率為50%，則其對應的答題通過率得分為50分；若該驗證問題的答題通過率為60%，則其對應的答題通過率得分為70分；若該驗證問題的答題通過率為90%，則其對應的答題通過率得分為98分；等等。 表1
各驗證問題的答題通過率得分情況可以相同，也可以不相同。在一個實施例中，為各驗證問題預設答題通過率得分時，可綜合考慮各驗證問題的難易程度、安全程度、隱私程度等因素，根據各驗證問題的難易程度、安全程度或隱私程度等因素的不同，可為各驗證問題設定不同的答題通過率得分。例如，若驗證問題的難度較高，則可為該驗證問題設置較高的答題通過率得分。 其次，構建指定二分類模型。 再次，將歷史行為資料作為指定二分類模型的樣本資料進行訓練，得到驗證問題的答題正確率。 其中，指定二分類模型可以是xgboost二分類模型，利用xgboost二分類模型對樣本資料進行訓練的過程為現有技術，因此不再贅述。當然，指定二分類模型還可以是其他類型的二分類模型，本實施例對此不做限定。 當特徵屬性包括驗證問題的安全程度時，可按照如下方式判定驗證問題的安全程度（即安全程度的屬性值）：首先，根據驗證問題中包含的關鍵字，判定驗證問題所攜帶的資訊量；其次，根據資訊量判定驗證問題的安全程度，其中，資訊量與安全程度成正比。 具體的，驗證問題中包含的關鍵字越多，其所攜帶的資訊量越大，那麼該驗證問題的安全程度也就越高。例如，對於驗證問題1——「您近期購買過的最貴的商品是什麼？」，其中包含的關鍵字包括「最貴的」、「是什麼」；對於驗證問題2——「您近期購買過的商品是什麼？」，其中包含的關鍵字僅包括 「是什麼」；顯然，驗證問題1所攜帶的資訊量大於驗證問題2所攜帶的資訊量，驗證問題1的安全程度高於驗證問題2的安全程度。 當特徵屬性包含驗證問題的隱私程度時，可按照如下方式判定驗證問題的隱私程度（即隱私程度的屬性值）：首先，判定驗證問題和目標使用者的個人資訊之間的相關度；其次，根據相關度判定驗證問題的隱私程度，其中，相關度與隱私程度成正比。 具體的，驗證問題和目標使用者的個人資訊之間的相關度越高，該驗證問題的隱私程度就越高；反之，驗證問題和目標使用者的個人資訊之間的相關度月底，則該驗證問題的隱私程度就越低。其中，目標使用者的個人資訊可包括姓名、暱稱、帳號資訊、綁定的銀行卡號、手機號碼等。例如，對於驗證問題3——「哪個是您當前帳號所綁定的銀行卡號？」，以及驗證問題4——「哪個是您使用的wifi？」，由於驗證問題3與目標使用者的個人資訊（即銀行卡號）相關度很高，而驗證問題4不涉及目標使用者的個人資訊，因此驗證問題3的隱私程度高於驗證問題4的隱私程度。 舉例而言，在淘寶中進行驗證服務。目標使用者每次登錄淘寶帳戶時，伺服器會採用問題核身方式驗證使用者身份，即，向目標使用者展示一個或兩個與淘寶相關的驗證問題供使用者答題。那麼，可利用多次驗證過程以及目標使用者使用淘寶的使用行為資訊來判定目標使用者對各問題的答題通過率。 首先獲取目標使用者在淘寶中的歷史行為資料。其中，該歷史行為資料包括使用者對淘寶的歷史使用行為資訊、對各驗證問題的歷史答題行為資訊以及各驗證問題的答題通過率得分。目標使用者對淘寶的歷史使用行為資訊以及對各驗證問題的歷史答題行為資訊可預先進行記錄並統計，針對各驗證問題的答題通過率得分可預先儲存於伺服器端。例如，目標使用者對淘寶的歷史使用行為資訊如：該使用者在最近一個月內購買過商品A、商品B以及商品C，該使用者最近半年內登錄淘寶帳戶時使用的wifi為「12345678」；目標使用者對各驗證問題的歷史答題行為資訊如：針對問題a有3次正確結果和2次錯誤結果，針對問題b有10次正確結果；各驗證問題的答題通過率得分如表1所示。為簡便說明，本實施例中各驗證問題的答題通過率得分情況可相同。 獲取到目標使用者在淘寶中的歷史行為資料之後，構建xgboost二分類模型。 構建xgboost二分類模型之後，將歷史行為資料作為xgboost二分類模型的樣本資料進行訓練，得到驗證問題的答題正確率。例如，目標使用者對問題a的答題正確率為70%，對問題b的答題正確率為98%，對問題c的答題正確率為80%，等等。 沿用上述舉例來判定驗證問題的特徵屬性的屬性值和權值。其中，特徵屬性的屬性值採用和分值和/或概率形式表徵，具體可包括驗證使用者對驗證問題的答題正確率、驗證問題的安全分值以及隱私分值。為簡便說明，本實施例中僅列舉三個驗證問題，如問題a、問題b以及問題c，實際應用中問題庫中的驗證問題數量通常遠大於三。 表2-表4示例性地分別示出了問題a、問題b以及問題c的各特徵屬性分別對應的屬性值和權值。其中，各問題的各特徵屬性分別對應的權值的和為1。 表2
表3
表4
基於表2-表4示出的問題a、問題b以及問題c的各特徵屬性分別對應的屬性值和權值，將各問題的各特徵屬性分別對應的屬性值和權值進行加權求和，即可計算出各問題的推送分值。 具體的，問題a的推送分值Ta=80%*40%+80*40%+50*20%=42.32；問題b的推送分值Tb=98%*50%+60*30%+50*20%=28.49；問題c的推送分值Tc=70%*30%+40*10%+80*60%=52.21。 計算出問題a、問題b以及問題c的推送分值之後，根據各驗證問題的推送分值即可對各驗證問題進行排序。本實施例中，按照各驗證問題的推送分值由高到低的順序對各驗證問題進行排序，由於問題c的推送分值最高，問題a的推送分值次高，問題b的推送分值最低，因此排序結果為問題c＞問題a＞問題b。 在一個實施例中，向用目標使用者推送目標驗證問題時，可將推送分值最高的驗證問題判定為向目標使用者推送的目標驗證問題；或，將達到預設臨限值的推送分值所對應的驗證問題判定為向目標使用者推送的目標驗證問題。 沿用上述舉例，得到排序結果之後，即可根據排序結果向淘寶推送目標驗證問題。假設目標驗證問題為推送分值最高的驗證問題，那麼可將問題c作為目標驗證問題推送至目標使用者。 由以上實施例可知，驗證問題的答題正確率與目標使用者在當前驗證服務所對應的業務中的歷史行為資料相關，驗證問題的安全程度與其所攜帶的資訊量相關，該資訊量與目標使用者在該業務中的歷史行為資訊有關，驗證問題的隱私程度與目標使用者的個人資訊相關。由於不同使用者對應有各自不同的歷史行為資料以及不同的個人資訊，因此，針對不同的目標使用者，驗證問題的特徵屬性均有所不同，這使得為不同的目標使用者推送驗證問題時，相同驗證問題對應的推送分值也有所不同。 在一個實施例中，將目標驗證問題推送至目標使用者之後，目標使用者對目標驗證問題進行答題。通過獲取目標使用者在當前驗證服務中針對目標驗證問題的答題結果，可根據該答題結果更新目標驗證問題的答題正確率，進而根據更新後的答題正確率更新目標驗證問題的推送分值。例如，目標驗證問題為問題c。假設目標使用者對目標驗證問題——問題c的答題結果為正確結果，則根據該答題結果對問題c的答題正確率進行更新，此時，目標使用者對問題c的答題正確率被更新後有所提高。 本實施例中，能夠基於目標使用者對目標驗證問題的答題結果對目標驗證問題的答題正確率進行更新，進而更新目標驗證問題的推送分值，使得驗證問題的推送分值能夠隨著目標使用者對驗證問題的答題結果及時得以更新，從而使推送至目標使用者的目標驗證問題更加符合目標使用者的答題需求，即降低目標使用者答題的錯誤率。 綜上，已經對本主題的特定實施例進行了描述。其它實施例在所附申請專利書的範圍內。在一些情況下，在申請專利書中記載的動作可以按照不同的順序來執行並且仍然可以實現期望的結果。另外，在附圖中描繪的過程不一定要求示出的特定順序或者連續順序，以實現期望的結果。在某些實施方式中，多工處理和並行處理可以是有利的。 以上為本說明書一個或多個實施例提供的問題推送方法，基於同樣的思路，本說明書一個或多個實施例還提供一種問題推送裝置。 圖2是根據本說明書一實施例的一種問題推送裝置的示意性方塊圖。如圖2所示，該裝置包括： 第一判定模組210，判定目標使用者的驗證問題的特徵屬性；其中，特徵屬性包括：驗證問題的答題正確率、安全程度、隱私程度中的至少一項； 第二判定模組220，根據驗證問題的特徵屬性，判定驗證問題的推送分值； 第三判定模組230，根據每個驗證問題的推送分值，判定向目標使用者推送的目標驗證問題。 可選地，第二判定模組220包括： 第一判定單元，判定驗證問題的特徵屬性的權值，以及，判定驗證問題的特徵屬性的屬性值； 第二判定單元，將驗證問題的特徵屬性的權值以及屬性值的加權值判定為驗證問題的推送分值。 可選地，第一判定單元，根據目標使用者所對應的驗證服務的場景和/或業務類型，判定驗證問題的特徵屬性的權值。 可選地，特徵屬性包括驗證問題的答題正確率； 第一判定單元，獲取目標使用者在當前驗證服務所對應的業務中的歷史行為資料，歷史行為資料包括對業務的歷史使用行為資訊、針對驗證問題的歷史答題行為資訊、驗證問題的答題通過率得分中的至少一項；構建指定二分類模型；將歷史行為資料作為指定二分類模型的樣本資料進行訓練，得到驗證問題的答題正確率。 可選地，歷史答題行為資訊包括答題結果，答題結果包括正確結果或錯誤結果； 上述裝置還包括： 獲取模組，獲取目標使用者在當前驗證服務中針對目標驗證問題的答題結果； 更新模組，根據針對目標驗證問題的答題結果，更新目標驗證問題的答題正確率。 可選地，特徵屬性包括安全程度； 第一判定單元，根據驗證問題中包含的關鍵字，判定驗證問題所攜帶的資訊量；根據資訊量判定驗證問題的安全程度，其中，資訊量與安全程度成正比。 可選地，特徵屬性包括隱私程度； 第一判定單元，判定驗證問題和目標使用者的個人資訊之間的相關度；根據相關度判定驗證問題的隱私程度，其中，相關度與隱私程度成正比。 可選地，第三判定模組230包括： 第三判定單元，將推送分值最高的驗證問題判定為向目標使用者推送的目標驗證問題；或， 第四判定單元，將達到預設臨限值的推送分值所對應的驗證問題判定為向目標使用者推送的目標驗證問題。 採用本說明書一個或多個實施例的裝置，能夠判定目標使用者的驗證問題的特徵屬性（包括驗證問題的答題正確率、安全程度、隱私程度中的至少一項），根據特徵屬性判定驗證問題的推送分值，進而根據每個驗證問題的推送分值判定向目標使用者推送的目標驗證問題。因此，該技術方案在向使用者推送驗證問題時，能夠兼顧目標使用者的驗證問題的答題正確率、安全程度和/或隱私程度，從而在採用問答形式進行身份驗證時能夠更加有針對性地、靈活地向使用者推送驗證問題，完善了驗證問題的推送機制，且提升使用者的答題通過率以及驗證服務的安全性和隱私性，進而提升使用者對驗證服務的體驗度。 本領域的技術人員應可理解，圖2中的問題推送裝置能夠用來實現前文所述的問題推送方法，其中的細節描述應與前文方法部分描述類似，為避免繁瑣，此處不另贅述。 基於同樣的思路，本說明書一個或多個實施例還提供一種問題推送設備，如圖3所示。問題推送設備可因配置或性能不同而產生比較大的差異，可以包括一個或一個以上的處理器301和記憶體302，記憶體302中可以儲存有一個或一個以上儲存應用程式或資料。其中，記憶體302可以是短暫儲存或持久儲存。儲存在記憶體302的應用程式可以包括一個或一個以上模組（圖示未示出），每個模組可以包括對問題推送設備中的一系列電腦可執行指令。更進一步地，處理器301可以設置為與記憶體302通訊，在問題推送設備上執行記憶體302中的一系列電腦可執行指令。問題推送設備還可以包括一個或一個以上電源303，一個或一個以上有線或無線網路介面304，一個或一個以上輸入輸出介面305，一個或一個以上鍵盤306。 具體在本實施例中，問題推送設備包括有記憶體，以及一個或一個以上的程式，其中一個或者一個以上程式儲存於記憶體中，且一個或者一個以上程式可以包括一個或一個以上模組，且每個模組可以包括對問題推送設備中的一系列電腦可執行指令，且經配置以由一個或者一個以上處理器執行該一個或者一個以上套裝程式含用於進行以下電腦可執行指令： 判定目標使用者的驗證問題的特徵屬性；其中，所述特徵屬性包括：驗證問題的答題正確率、安全程度、隱私程度中的至少一項； 根據所述驗證問題的特徵屬性，判定所述驗證問題的推送分值； 根據每個所述驗證問題的推送分值，判定向所述目標使用者推送的目標驗證問題。 可選地，判定所述驗證問題的特徵屬性的權值，以及，判定所述驗證問題的特徵屬性的屬性值； 將所述驗證問題的特徵屬性的權值以及屬性值的加權值判定為所述驗證問題的推送分值。 可選地，電腦可執行指令在被執行時，還可以使所述處理器： 根據所述目標使用者所對應的驗證服務的場景和/或業務類型，判定所述驗證問題的特徵屬性的權值。 可選地，所述特徵屬性包括所述驗證問題的答題正確率；電腦可執行指令在被執行時，還可以使所述處理器： 獲取所述目標使用者在當前驗證服務所對應的業務中的歷史行為資料，所述歷史行為資料包括對所述業務的歷史使用行為資訊、針對所述驗證問題的歷史答題行為資訊、所述驗證問題的答題通過率得分中的至少一項； 構建指定二分類模型； 將所述歷史行為資料作為所述指定二分類模型的樣本資料進行訓練，得到所述驗證問題的答題正確率。 可選地，所述歷史答題行為資訊包括答題結果，所述答題結果包括正確結果或錯誤結果；電腦可執行指令在被執行時，還可以使所述處理器： 獲取所述目標使用者在當前驗證服務中針對所述目標驗證問題的答題結果； 根據針對所述目標驗證問題的答題結果，更新所述目標驗證問題的答題正確率。 可選地，所述特徵屬性包括所述安全程度；電腦可執行指令在被執行時，還可以使所述處理器： 根據所述驗證問題中包含的關鍵字，判定所述驗證問題所攜帶的資訊量； 根據所述資訊量判定所述驗證問題的安全程度，其中，所述資訊量與所述安全程度成正比。 可選地，所述特徵屬性包括所述隱私程度；電腦可執行指令在被執行時，還可以使所述處理器： 判定所述驗證問題和所述目標使用者的個人資訊之間的相關度； 根據所述相關度判定所述驗證問題的隱私程度，其中，所述相關度與所述隱私程度成正比。 可選地，電腦可執行指令在被執行時，還可以使所述處理器： 將所述推送分值最高的驗證問題判定為向所述目標使用者推送的目標驗證問題；或， 將達到預設臨限值的推送分值所對應的驗證問題判定為向所述目標使用者推送的目標驗證問題。 本說明書一個或多個實施例還提出了一種電腦可讀儲存介質，該電腦可讀儲存介質儲存一個或多個程式，該一個或多個程式包括指令，該指令當被包括多個應用程式的電子設備執行時，能夠使該電子設備執行上述問題推送方法，並具體用於執行： 判定目標使用者的驗證問題的特徵屬性；其中，所述特徵屬性包括：驗證問題的答題正確率、安全程度、隱私程度中的至少一項； 根據所述驗證問題的特徵屬性，判定所述驗證問題的推送分值； 根據每個所述驗證問題的推送分值，判定向所述目標使用者推送的目標驗證問題。 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、蜂窩電話、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。 為了描述的方便，描述以上裝置時以功能分為各種單元分別描述。當然，在實施本說明書一個或多個實施例時可以把各單元的功能在同一個或多個軟體和/或硬體中實現。 本領域內的技術人員應明白，本說明書一個或多個實施例可提供為方法、系統、或電腦程式產品。因此，本說明書一個或多個實施例可採用完全硬體實施例、完全軟體實施例、或結合軟體和硬體方面的實施例的形式。而且，本說明書一個或多個實施例可採用在一個或多個其中包含有電腦可用程式碼的電腦可用儲存介質（包括但不限於磁碟記憶體、CD-ROM、光學記憶體等）上實施的電腦程式產品的形式。 本說明書一個或多個實施例是參照根據本申請實施例的方法、設備（系統）、和電腦程式產品的流程圖和／或方塊圖來描述的。應理解可由電腦程式指令實現流程圖和／或方塊圖中的每一流程和／或方塊、以及流程圖和／或方塊圖中的流程和／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設計資料處理設備的處理器以產生一個機器，使得通過電腦或其他可程式設計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和／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設計資料處理設備以特定方式工作的電腦可讀記憶體中，使得儲存在該電腦可讀記憶體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和／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設計資料處理設備上，使得在電腦或其他可程式設計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設計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和／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介質中的非永久性記憶體，隨機存取記憶體（RAM）和/或非揮發性記憶體等形式，如唯讀記憶體（ROM）或快閃記憶體（flash RAM）。記憶體是電腦可讀介質的示例。 電腦可讀介質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。電腦的儲存介質的例子包括，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介質，可用於儲存可以被計算設備訪問的資訊。按照本文中的界定，電腦可讀介質不包括暫存電腦可讀媒體（transitory media），如調製的資料信號和載波。 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。 本說明書一個或多個實施例可以在由電腦執行的電腦可執行指令的一般上下文中描述，例如程式模組。一般地，程式模組包括執行特定任務或實現特定抽象資料類型的常式、程式、物件、元件、資料結構等等。也可以在分散式運算環境中實踐本申請，在這些分散式運算環境中，由通過通訊網路而被連接的遠端處理設備來執行任務。在分散式運算環境中，程式模組可以位於包括存放裝置在內的本地和遠端電腦儲存介質中。 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。 以上所述僅為本說明書一個或多個實施例而已，並不用於限制本說明書。對於本領域技術人員來說，本說明書一個或多個實施例可以有各種更改和變化。凡在本說明書一個或多個實施例的精神和原理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申請專利範圍之內。One or more embodiments of this specification provide a method and device for pushing a question to improve the mechanism for pushing a question, so that the pushed question is more targeted. In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will combine the drawings in one or more embodiments of this specification to compare The technical solution is described clearly and completely. Obviously, the described embodiments are only a part of the embodiments in this specification, rather than all the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of one or more embodiments of this specification. Fig. 1 is a schematic flowchart of a question push method according to an embodiment of the present specification. As shown in Fig. 1, the method includes: Step S102, determining the characteristic attribute of the verification question of the target user. Among them, the characteristic attribute includes at least one of the correct answer rate of the verification question, the degree of security, and the degree of privacy. Step S104: Determine the push score of the verification question according to the characteristic attribute of the verification question. Step S106: Determine the target verification question pushed to the target user according to the push score of each verification question. Using the technical solutions of one or more embodiments of this specification, it is possible to determine the characteristic attributes of the verification questions of the target user (including at least one of the correct answer rate of the verification questions, the degree of security, and the degree of privacy), and determine the verification according to the characteristic attributes The push score of the question, and then determine the target verification question pushed to the target user based on the push score of each verification question. Therefore, this technical solution can take into account the correct answer rate, security level and/or privacy level of the target user’s verification question when pushing the verification question to the user, so that it can be more targeted when using the question and answer form for identity verification. , Flexible push verification questions to users, improve the push mechanism of verification questions, and improve the user's answer pass rate and the security and privacy of the verification service, thereby enhancing the user's experience of the verification service. In one embodiment, when determining the push score of the verification question based on the characteristic attribute of the verification question, first determine the weight of the characteristic attribute of the verification question, and determine the attribute value of the characteristic attribute of the verification question; The weight of the attribute and the weighted value of the attribute value are determined as the push score of the verification question. In this embodiment, the weight of the characteristic attribute of the verification question can be determined according to the scenario and/or business type of the verification service corresponding to the target user. Among them, the scenarios of the verification service are such as using an account to log in, modifying information, etc.; the business types of the verification service are such as shopping, games, and finance. According to different scenarios and/or business types of verification services, different weights can be set for the characteristic attributes of verification problems. For example, when the scenario of the verification service is to modify information, a higher weight value can be set for both the security level and the privacy degree in the feature attribute; when the business type of the verification service belongs to the financial category, a higher security level can be set for the feature attribute. A high weight; when the business type of the verification service belongs to the shopping category, a higher weight can be set for the correct answer rate of the verification question in the characteristic attribute; and so on. Usually, the same user can correspond to multiple different verification questions. Therefore, for multiple verification questions of the target user, the weight of the characteristic attribute of each verification question can be set to be the same or different. In this embodiment, the characterization method of the attribute value may adopt the form of score, probability, etc. For example, the attribute value corresponding to the correct rate of the user's answer to each question can be the correct answer rate itself, the attribute value corresponding to the security level of each question can be the security score, and the attribute value corresponding to the privacy level of each question can be the privacy score. value. The sum of the weights corresponding to each feature attribute of the same verification problem is 1. The following details how to determine the attribute value of the characteristic attribute of the verification problem. When the characteristic attribute includes the correct answer rate of the verification question, the correct answer rate of the verification question (that is, the attribute value of the correct answer rate) can be determined as follows: First, obtain the history of the target user in the business corresponding to the current verification service Behavioral data, the historical behavioral data includes at least one of historical use behavior information of the business, historical answer behavior information for verification questions, and a pass rate score of verification questions. Among them, historical answering behavior information includes answering results, and answering results include correct or incorrect results. Table 1 exemplarily shows the pass rate score of a certain verification question. Table 1 shows the correspondence between the pass rate of the verification question and the pass rate score. For example, if the pass rate of the verification question is 50%, the corresponding pass rate score is 50 points; If the pass rate of the verification question is 60%, the corresponding pass rate score is 70 points; if the pass rate of the verification question is 90%, the corresponding pass rate score is 98 points; etc. . Table 1 The pass rate of each verification question can be the same or different. In one embodiment, when pre-setting the pass rate score for each verification question, the difficulty, security, privacy and other factors of each verification question can be comprehensively considered, according to the difficulty, security, or privacy of each verification question. Different factors can set different pass rate scores for each verification question. For example, if the difficulty of the verification question is higher, a higher pass rate score can be set for the verification question. Second, build a designated two-class model. Third, the historical behavior data is used as the sample data of the designated two-class model for training, and the correct answer rate of the verification question is obtained. Wherein, the designated two-classification model may be an xgboost two-classification model, and the process of using the xgboost two-classification model to train sample data is an existing technology, so it will not be repeated. Of course, the designated two-category model may also be other types of two-category models, which is not limited in this embodiment. When the characteristic attribute includes the security degree of the verification question, the security degree of the verification question (that is, the attribute value of the security degree) can be determined as follows: First, determine the amount of information carried by the verification question according to the keywords contained in the verification question; Second, determine the security level of the verification problem based on the amount of information, where the amount of information is directly proportional to the security level. Specifically, the more keywords contained in the verification question, the greater the amount of information it carries, and the higher the degree of security of the verification question. For example, for verification question 1-"What is the most expensive item you have recently purchased?", the keywords included include "most expensive" and "what is"; for verification question 2-"You recently purchased What’s the product you’ve used?", the keywords included only include "what"; obviously, the amount of information carried by verification question 1 is greater than the amount of information carried by verification question 2, and verification question 1 is more secure than verification question 2. The degree of safety. When the characteristic attribute includes the degree of privacy of the verification question, the degree of privacy of the verification question (that is, the attribute value of the degree of privacy) can be determined as follows: First, determine the correlation between the verification question and the personal information of the target user; second, The degree of privacy of the verification question is determined according to the degree of correlation, where the degree of correlation is directly proportional to the degree of privacy. Specifically, the higher the correlation between the verification question and the target user’s personal information, the higher the degree of privacy of the verification question; conversely, the higher the correlation between the verification question and the target user’s personal information at the end of the month, the The lower the degree of privacy of the verification question. Among them, the personal information of the target user may include name, nickname, account information, bound bank card number, mobile phone number, etc. For example, for verification question 3-"Which is the bank card number bound to your current account?", and verification question 4-"Which is your wifi?", due to verification question 3 and the target user's personal information (Ie, the bank card number) is highly relevant, and verification question 4 does not involve the personal information of the target user, so verification question 3 has a higher degree of privacy than verification question 4. For example, perform verification services in Taobao. Each time a target user logs in to a Taobao account, the server will verify the user's identity by question verification, that is, show the target user one or two Taobao-related verification questions for the user to answer. Then, the multiple verification process and the usage behavior information of the target user using Taobao can be used to determine the pass rate of the target user's answer to each question. First obtain the historical behavior data of the target user in Taobao. Among them, the historical behavior data includes the user's historical use behavior information on Taobao, historical answer behavior information on each verification question, and the answer pass rate score of each verification question. The target user's historical usage behavior information on Taobao and the historical answer behavior information of each verification question can be recorded and counted in advance, and the pass rate score for each verification question can be pre-stored on the server side. For example, the target user’s historical usage behavior information on Taobao, such as: the user has purchased product A, product B, and product C in the last month, and the wifi used by the user when logging in to the Taobao account in the last six months is "12345678"; the historical response behavior information of the target user for each verification question, such as: 3 correct results and 2 incorrect results for question a, and 10 correct results for question b; the pass rate score of each verification question is shown in the table 1 shown. For the sake of simplicity, the pass rate scores of each verification question in this embodiment can be the same. After obtaining the historical behavior data of the target user in Taobao, construct the xgboost two-classification model. After constructing the xgboost two-classification model, the historical behavior data is used as the sample data of the xgboost two-classification model for training, and the correct answer rate of the verification question is obtained. For example, the target user's answer to question a is 70%, the answer to question b is 98%, the answer to question c is 80%, and so on. The above examples are used to determine the attribute value and weight of the characteristic attribute of the verification problem. Among them, the attribute value of the characteristic attribute is represented in the form of sum score and/or probability, which may specifically include the correct answer rate of the verification user to the verification question, the security score of the verification question, and the privacy score. For the sake of simplicity, only three verification questions are listed in this embodiment, such as question a, question b, and question c. In practical applications, the number of verification questions in the question library is usually much greater than three. Tables 2 to 4 exemplarily show the attribute values and weights corresponding to each feature attribute of question a, question b, and question c. Among them, the sum of the weights corresponding to each feature attribute of each question is 1. Table 2 table 3 Table 4 Based on the attribute value and weight corresponding to each feature attribute of question a, question b, and question c shown in Table 2 to Table 4, the attribute value and weight corresponding to each feature attribute of each question are weighted and summed, Then the push score of each question can be calculated. Specifically, the push score of question a Ta=80%*40%+80*40%+50*20%=42.32; the push score of question b Tb=98%*50%+60*30%+50* 20%=28.49; the push score of question c Tc=70%*30%+40*10%+80*60%=52.21. After calculating the push scores of question a, question b, and question c, each verification question can be sorted according to the push score of each verification question. In this embodiment, the verification questions are sorted according to the push score of each verification question from high to low. Since the push score of question c is the highest, the push score of question a is the second highest, and the push score of question b is the second highest. The lowest, so the ranking result is question c> question a> question b. In one embodiment, when the target verification question is pushed to the target user, the verification question with the highest push score may be determined as the target verification question pushed to the target user; or, the push score that reaches the preset threshold The verification question corresponding to the value is determined as the target verification question pushed to the target user. Following the above example, after obtaining the sorting result, the target verification problem can be pushed to Taobao according to the sorting result. Assuming that the target verification question is the verification question with the highest push score, then question c can be pushed to the target user as the target verification question. It can be seen from the above embodiments that the correct answer rate of the verification question is related to the historical behavior data of the target user in the business corresponding to the current verification service. The security level of the verification question is related to the amount of information it carries, and the amount of information is related to the target usage Is related to the historical behavior information of the user in the business, and the degree of privacy of the verification question is related to the personal information of the target user. Since different users correspond to different historical behavior data and different personal information, the characteristic attributes of verification questions are different for different target users. This makes it possible to push verification questions for different target users. The push score corresponding to the same verification question is also different. In one embodiment, after the target verification question is pushed to the target user, the target user answers the target verification question. By obtaining the answer results of the target user for the target verification question in the current verification service, the correct answer rate of the target verification question can be updated according to the answer result, and then the push score of the target verification question can be updated according to the updated answer correct rate. For example, the target verification problem is problem c. Assuming that the target user has a correct answer to the target verification question-question c, the correct answer rate of question c is updated according to the answer result. At this time, the correct answer rate of the target user to question c is updated has seen an increase. In this embodiment, the correct answer rate of the target verification question can be updated based on the answer result of the target user to the target verification question, and then the push score of the target verification question is updated, so that the push score of the verification question can be used with the target The answering results of the verification questions are updated in a timely manner, so that the target verification questions pushed to the target users are more in line with the answering needs of the target users, that is, the error rate of the target users' answers is reduced. In summary, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the attached patent application. In some cases, the actions described in the patent application can be executed in a different order and still achieve desired results. In addition, the processes depicted in the figures do not necessarily require the specific order or sequential order shown in order to achieve the desired result. In certain embodiments, multiplexing and parallel processing may be advantageous. The above is the question pushing method provided by one or more embodiments of this specification. Based on the same idea, one or more embodiments of this specification also provide a question pushing device. Fig. 2 is a schematic block diagram of a question pushing device according to an embodiment of the present specification. As shown in FIG. 2, the device includes: a first determination module 210 that determines the characteristic attributes of the verification question of the target user; wherein the characteristic attributes include: at least one of the correct answer rate of the verification question, the degree of security, and the degree of privacy Item; The second determination module 220 determines the push score of the verification question according to the characteristic attribute of the verification problem; the third determination module 230 determines the target verification to be pushed to the target user according to the push score of each verification question problem. Optionally, the second judging module 220 includes: a first judging unit that judges the weight of the feature attribute of the verification question, and judging the property value of the feature attribute of the verification question; the second judging unit will verify the feature attribute of the question The weight of and the weighted value of the attribute value are determined as the push score of the verification question. Optionally, the first determining unit determines the weight of the characteristic attribute of the verification problem according to the scenario and/or business type of the verification service corresponding to the target user. Optionally, the characteristic attribute includes the correct answer rate of the verification question; the first judging unit obtains historical behavior data of the target user in the business corresponding to the current verification service, and the historical behavior data includes historical use behavior information of the business, At least one of the historical answer behavior information of the verification question and the pass rate score of the verification question; construct a designated two-classification model; train the historical behavior data as the sample data of the designated two-classification model to obtain the correct answer rate of the verification question. Optionally, the historical answering behavior information includes answering results, and the answering results include correct or incorrect results; the above-mentioned device further includes: an acquisition module, which acquires the answer results of the target user for the target verification question in the current verification service; update the module , According to the answer results for the target verification question, update the correct answer rate of the target verification question. Optionally, the characteristic attribute includes a degree of security; the first determining unit determines the amount of information carried by the verification question based on the keywords contained in the verification question; determines the degree of security of the verification question based on the amount of information, where the amount of information and the degree of security Proportionally. Optionally, the characteristic attribute includes the degree of privacy; the first determining unit determines the degree of correlation between the verification question and the personal information of the target user; the degree of privacy of the verification problem is determined according to the degree of correlation, wherein the degree of correlation is proportional to the degree of privacy . Optionally, the third judging module 230 includes: a third judging unit that judges the verification question with the highest push score as the target verification question pushed to the target user; or, the fourth judging unit will reach a preset threshold The verification question corresponding to the push score of the value is determined as the target verification question pushed to the target user. Using the device of one or more embodiments of this specification, it is possible to determine the characteristic attributes of the verification question of the target user (including at least one of the correct answer rate of the verification question, the degree of security, and the degree of privacy), and determine the verification question according to the characteristic attribute According to the push score of each verification question, determine the target verification question pushed to the target user. Therefore, this technical solution can take into account the correct answer rate, security level and/or privacy level of the target user’s verification question when pushing the verification question to the user, so that it can be more targeted when using the question and answer form for identity verification. , Flexible push verification questions to users, improve the push mechanism of verification questions, and improve the user's answer pass rate and the security and privacy of the verification service, thereby enhancing the user's experience of the verification service. Those skilled in the art should understand that the problem pushing device in FIG. 2 can be used to implement the problem pushing method described above, and the detailed description should be similar to the previous method part description. To avoid cumbersomeness, it will not be repeated here. Based on the same idea, one or more embodiments of this specification also provide a problem pushing device, as shown in FIG. 3. The problem push device may have relatively large differences due to different configurations or performances, and may include one or more processors 301 and a memory 302, and the memory 302 may store one or more storage applications or data. Among them, the memory 302 may be short-term storage or permanent storage. The application program stored in the memory 302 may include one or more modules (not shown in the figure), and each module may include a series of computer-executable instructions for the problem push device. Furthermore, the processor 301 may be configured to communicate with the memory 302 and execute a series of computer executable instructions in the memory 302 on the problem push device. The question push device may also include one or more power sources 303, one or more wired or wireless network interfaces 304, one or more input and output interfaces 305, and one or more keyboards 306. Specifically, in this embodiment, the problem push device includes memory and one or more programs. One or more programs are stored in the memory, and one or more programs may include one or more modules. And each module can include a series of computer-executable instructions in the problem push device, and is configured to be executed by one or more processors to execute the one or more package programs including the following computer-executable instructions: determination The characteristic attribute of the verification question of the target user; wherein the characteristic attribute includes: at least one of the correct answer rate of the verification question, the degree of security, and the degree of privacy; and the verification question is determined according to the characteristic attribute of the verification question According to the push score of each verification question, determine the target verification question pushed to the target user. Optionally, determine the weight of the characteristic attribute of the verification question, and determine the attribute value of the characteristic attribute of the verification question; determine the weight of the characteristic attribute of the verification question and the weighted value of the attribute value as all Describe the push score of the verification question. Optionally, when the computer-executable instructions are executed, the processor can also: determine the right of the characteristic attribute of the verification question according to the scenario and/or business type of the verification service corresponding to the target user value. Optionally, the characteristic attribute includes the correct answer rate of the verification question; when the computer-executable instructions are executed, the processor may also: obtain the target user in the business corresponding to the current verification service The historical behavior data includes at least one of the historical use behavior information of the business, the historical answer behavior information for the verification question, and the answer pass rate score of the verification question; Classification model; training the historical behavior data as the sample data of the specified two-classification model to obtain the correct answer rate of the verification question. Optionally, the historical answering behavior information includes answering results, and the answering results include correct or incorrect results; when the computer-executable instructions are executed, the processor may also enable the processor: The answer result for the target verification question in the verification service; and update the correct answer rate of the target verification question according to the answer result for the target verification question. Optionally, the characteristic attribute includes the degree of security; when the computer-executable instruction is executed, the processor may also be caused to: determine the content of the verification question according to the keywords contained in the verification question Information volume: Determine the security level of the verification problem based on the information volume, wherein the information volume is proportional to the security level. Optionally, the characteristic attribute includes the degree of privacy; when the computer-executable instructions are executed, the processor can also be used to: determine the degree of correlation between the verification question and the personal information of the target user ; Determine the degree of privacy of the verification question according to the degree of correlation, wherein the degree of correlation is directly proportional to the degree of privacy. Optionally, when the computer-executable instructions are executed, the processor can also: determine the verification problem with the highest push score as the target verification problem pushed to the target user; or The verification question corresponding to the push score with the threshold value is determined as the target verification question pushed to the target user. One or more embodiments of this specification also propose a computer-readable storage medium that stores one or more programs, and the one or more programs include instructions. When the instructions include multiple application programs, When the electronic device is executed, the electronic device can execute the above question push method, and is specifically used to execute: Determine the characteristic attribute of the verification question of the target user; wherein, the characteristic attribute includes: the correct answer rate of the verification question and the degree of safety At least one of the degree of privacy; determine the push score of the verification question according to the characteristic attribute of the verification question; determine the push target to the target user according to the push score of each verification question Verify the problem. The systems, devices, modules, or units explained in the above embodiments may be implemented by computer chips or entities, or implemented by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cell 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, and a wearable device. Or any combination of these devices. For the convenience of description, when describing the above device, the functions are divided into various units and described separately. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and/or hardware. Those skilled in the art should understand that one or more embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, one or more embodiments of this specification may adopt the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware. Moreover, one or more embodiments of this specification can be implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program codes. In the form of a computer program product. One or more embodiments of this specification are described with reference to flowcharts and/or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this application. It should be understood that each process and/or block in the flowchart and/or block diagram, and the combination of processes and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, dedicated computers, embedded processors, or other programmable data processing equipment to generate a machine that can be executed by the processor of the computer or other programmable data processing equipment Produce means for realizing the functions specified in one or more processes in the flowchart and/or one block or more in the block diagram. These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing equipment to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including the instruction device , The instruction device realizes the functions specified in one process or multiple processes in the flowchart and/or one block or multiple blocks in the block diagram. These computer program instructions can also be loaded on a computer or other programmable data processing equipment, so that a series of operation steps are executed on the computer or other programmable equipment to produce computer-implemented processing, so that the computer or other programmable equipment The instructions executed above provide steps for implementing functions specified in a flow or multiple flows in the flowchart and/or a block or multiple blocks in the block diagram. In a typical configuration, the computing device includes one or more processors (CPU), input/output interfaces, network interfaces, and memory. Memory may include non-permanent memory, random access memory (RAM) and/or non-volatile memory in computer-readable media, such as read-only memory (ROM) or flash memory (flash). RAM). Memory is an example of computer-readable media. Computer-readable 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 memory technology, read-only CD-ROM (CD-ROM), digital multi-function Optical 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 media does not include transitory media, such as modulated data signals and carrier waves. It should also be noted that the terms "include", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, product or equipment including a series of elements not only includes those elements, but also includes Other elements that are not explicitly listed, or also include elements inherent to such processes, methods, commodities, or equipment. If there are no more restrictions, the element defined by the sentence "includes a..." does not exclude the existence of other identical elements in the process, method, product, or equipment that includes the element. One or more embodiments of this specification may be described in the general context of computer-executable instructions executed by a computer, such as a program module. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The application can also be implemented in a distributed computing environment. In these distributed computing environments, remote processing devices connected through a communication network perform tasks. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices. The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and 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, and the relevant parts can be referred to the part of the description of the method embodiment. The above description is only one or more embodiments of this specification, and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification can have various modifications and changes. 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 scope of patent application of one or more embodiments of this specification.
