WO2019141039A1 - 账户信息的分组方法、装置及支付方法、装置 - Google Patents

账户信息的分组方法、装置及支付方法、装置 Download PDF

Info

Publication number
WO2019141039A1
WO2019141039A1 PCT/CN2018/122341 CN2018122341W WO2019141039A1 WO 2019141039 A1 WO2019141039 A1 WO 2019141039A1 CN 2018122341 W CN2018122341 W CN 2018122341W WO 2019141039 A1 WO2019141039 A1 WO 2019141039A1
Authority
WO
WIPO (PCT)
Prior art keywords
account
information
account information
payment
server
Prior art date
Application number
PCT/CN2018/122341
Other languages
English (en)
French (fr)
Inventor
王群
Original Assignee
北京君林科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京君林科技股份有限公司 filed Critical 北京君林科技股份有限公司
Publication of WO2019141039A1 publication Critical patent/WO2019141039A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L9/00—Cryptographic mechanisms or cryptographic arrangements for secret or secure communications; Network security protocols
    • H04L9/40—Network security protocols
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401—Transaction verification
    • G06Q20/4014—Identity check for transactions
    • G06Q20/40145—Biometric identity checks

Definitions

  • the embodiments of the present invention relate to the field of biometrics, and in particular, to a method and a device for grouping payment accounts, and a payment method and device.
  • Mobile payment allows mobile users to make payment for goods or services they consume using a mobile terminal, such as a mobile phone.
  • Mobile payment usually includes two ways. One is that the consumer can use the mobile terminal to scan the QR code provided by the merchant to complete the payment. The other is that the merchant's collection terminal determines the consumer's electronic payment account (hereinafter referred to as "payment account" by scanning the two-dimensional code on the consumer mobile terminal, and then from the payment account balance or the bound bank card. The lieutenant transfers the corresponding fee to the merchant account to complete the payment.
  • payment account the consumer's electronic payment account
  • mobile payment is more convenient and faster than traditional payment methods, it requires consumers to carry mobile terminals at any time to complete payment. The mobile payment method is still not convenient enough.
  • Biometrics is a technique for identifying personal identities using the inherent physiological characteristics of the human body (such as fingerprints, facial features, irises, etc.) and behavioral characteristics (such as handwriting, sound, gait, etc.). If the merchant's collection terminal is able to determine the consumer's payment account through biometric identification, the consumer can complete the payment even if the mobile terminal is not carried.
  • the biometric payment method can only be applied to the consumer's mobile terminal for 1:1 identification, and the biometrics acquired at the time of payment and the only creature saved by the mobile terminal. The feature is matched, the match is successfully completed, otherwise the payment fails. Because the number of users who currently have payment accounts is quite large, even hundreds of millions of people, and the current biometric identification technology in the 1:n identification process, the number of n is limited, generally about 100,000, when it is 1 million It has been very difficult. If you increase the number of servers by increasing the number of n, but the cost is large, it will also increase the operation response time. Therefore, it is very difficult to use biometric technology to match specific account information from such a large account information base.
  • the embodiment of the invention provides a method for grouping account information and a payment method, so as to solve the problem that the current payment function is more difficult to use the biometric technology.
  • an embodiment of the present invention provides a payment method, including:
  • a target account set corresponding to the voice password according to at least one sound feature of the voice password, the target account set being one of an account set included in the account information database, each of the accounts
  • the set includes at least one account information
  • the sound feature includes a gender feature, an age stage feature, a dialect feature, or text information.
  • the step of determining a target account set corresponding to the voice password in the account information base according to the at least one sound feature of the voice password comprises:
  • the first account set is a target account set if the first account set corresponding to the first voice feature of the voice password does not include a sub-account set;
  • the second account set corresponding to the second voice feature of the voice password does not include the sub-account set, determining that the second account set is the target account set.
  • the step of searching for account information matching the at least one biometric information in the target account set includes:
  • an embodiment of the present invention further provides a method for grouping account information, including:
  • Each of the account information is divided into at least two account sets based on at least one sound characteristic of each of the voice passwords.
  • the step of dividing each of the account information into at least two account sets according to at least one sound feature of each of the voice passwords further includes:
  • the account information in the first account set is divided into at least two secondary account sets according to a second sound feature of the voice password corresponding to the account information in the first account set.
  • the method further includes:
  • the second account set is stored in the first server, and the deposit condition is that the sum of the number of account information in the current server and the number of account information in the second account set is less than a second threshold, the second set of accounts being one of the at least two account sets;
  • the first server does not meet the deposit condition, it is determined whether the second server meets the deposit condition
  • the second account set is stored in the second server.
  • the method further includes:
  • the third server is one of the servers.
  • an embodiment of the present invention further provides a payment apparatus, including:
  • a first obtaining unit configured to acquire a voice password of the user
  • a determining unit configured to determine, in the account information base, a target account set corresponding to the voice password according to at least one sound feature of the voice password, where the target account set is one of an account set included in the account information database
  • Each of the set of accounts includes at least one account information
  • a second acquiring unit configured to acquire at least one biometric information of the user
  • a search unit configured to search, in the target account set, account information that matches the at least one biometric information, where the account information includes at least one preset biometric information and an account.
  • the embodiment of the present invention further provides a grouping device for account information, including:
  • An obtaining unit configured to acquire at least two account information and a voice password corresponding to each of the account information
  • a grouping unit configured to divide each of the account information into at least two account sets according to at least one sound feature of each of the voice passwords.
  • the account information that needs to be biometrically identified is stored in groups according to the voice features of the voice password.
  • the user's voice password can be obtained to determine the target account set to which the user's account information belongs, thereby enabling The target account set quickly finds the account information matching the biometric feature of the user, reduces the operation process of the biometric matching, and improves the operation speed, and the payment method does not require the user to carry the mobile terminal, and the payment is more convenient.
  • FIG. 1 is a flowchart of a method for grouping account information according to an embodiment of the present invention
  • FIG. 2 is a flowchart of a payment method according to an embodiment of the present invention.
  • FIG. 3 is a structural block diagram of a grouping apparatus for account information according to an embodiment of the present invention.
  • FIG. 4 is a structural block diagram of a payment apparatus according to an embodiment of the present invention.
  • Embodiments of the present invention can be applied to a scenario in which consumer payment is performed using biometrics.
  • the inventive concept of the present invention is to store the account information that needs to be biometrically identified according to the voice characteristics of the voice password.
  • the user's voice password can be obtained to determine the target account set to which the user's account information belongs.
  • the account information matching the biometrics of the user can be quickly found from the target account set, the operation process of the biometric matching is reduced, the operation speed is improved, and the payment method does not require the user to carry the mobile terminal, and the payment is more convenient.
  • the account information of each user may include an account identification, an account password, and at least one preset biometric information.
  • the preset biometric information includes a voiceprint feature, a fingerprint feature, an iris feature, a facial feature, and the like.
  • the voice password in the present invention may be a voice password of any voice content, such as "Hello”, “Agree to Pay”, “Open Sesame”, and the like.
  • the gender of the user who outputs the voice password the age stage of the user, the dialect used by the user, or the text corresponding to the voice password, etc., can be determined, so that the voice characteristics of the voice password can include Gender characteristics, age stage characteristics, dialect characteristics or textual information.
  • FIG. 1 is a method for grouping account information according to an embodiment of the present invention.
  • the method may specifically include the following steps.
  • Step 101 Acquire at least two account information and a voice password corresponding to each of the account information.
  • the user When registering the payment account, the user can input any voice password, and the voice information corresponding to each account information can also be saved in the account information database.
  • Step 102 Divide each of the account information into at least two account sets according to at least one sound feature of each of the voice passwords.
  • each of the account information may be divided into a plurality of account sets according to a sound feature. For example, all the account information of the voice password is "same open" to the same account set.
  • each of the account information may be further divided into a plurality of account sets according to at least two sound characteristics. For example, when grouping according to gender characteristics and dialect characteristics, the dialect feature may be a Sichuan dialect, and the gender may be All account information with characteristics of males is divided into the same account set.
  • Each account set may mark a corresponding sound feature identifier (hereinafter referred to as "identity") according to its corresponding sound feature.
  • identity a corresponding sound feature identifier
  • the account set is divided according to gender characteristics, and the identifier of the account set may be male or female, for example, each account.
  • the set is divided according to the dialect feature and the gender feature, and the identifier of the account set can be set to, for example, the identifier of "A dialect, gender male".
  • the embodiment of the present invention may further divide the account information into a multi-level account set, and the specific process may be: dividing each of the account information into at least according to the first sound feature of each of the voice passwords. Two first-level account sets; determining whether there is a first account set whose number of account information is greater than a first threshold, the first account set being one of the first-level account sets; if present, according to the first account set
  • the second voice feature of the voice password corresponding to the account information divides the account information in the first account set into at least two secondary account sets.
  • account information can be divided into more levels of account sets.
  • each of the account information is divided into at least two first-level account sets, and then the first-level account set is further divided into two-level account sets according to the text information of the voice password.
  • the voice information may be divided according to a plurality of voice features.
  • the embodiment of the present invention does not specifically limit the types of voice features according to the account information grouping of the same level.
  • the group information can be saved, and the group information can include the identifier of each account set and the belonging relationship between the respective account sets.
  • the group information can be used to quickly determine the target account set corresponding to the target voice password.
  • the grouping information may also include a saved address of the account set without the sub-account set to enable quick finding of the target account set.
  • the identifiers of the respective account sets in the grouping information may be sorted according to a preset rule, for example, according to the pinyin initials of the identifiers, to quickly find the target account set by using the dichotomy.
  • each account set of the same level can also be sorted according to its identifier, or the dichotomy method can be used to quickly find the target account set.
  • Step 103 Save the at least two account sets to at least one server.
  • Each account set may be saved in one or more servers.
  • the process of saving each account set to multiple servers may include: if the first server meets the deposit condition, then The second account set is stored in the first server, and the deposit condition is that the sum of the number of account information in the current server and the number of account information in the second account set is less than a second threshold, and the second account set is One of the at least two account sets; if the first server does not meet the deposit condition, determining whether the second server meets the deposit condition; if the second server meets the deposit condition, then the second The account set is stored in the second server.
  • the second account set may be an account set without a sub-account set, or may be a higher-level account set.
  • the embodiment of the present invention does not limit the level at which the second account set is located.
  • the number of payment processes processed by each server in each unit time in multiple payment periods can also be monitored in real time, and the number of payment processes processed by each server is the sum of the number of payment times corresponding to all account information in each server. Then, according to the number of payment processes processed by each server in each unit time, a payment peak period corresponding to each server that stores the account information in the payment period is determined, and the payment peak period may include one or more consecutive unit times, and each server corresponds to The peak period of the payment may be the same or different, and the embodiment is not specifically limited herein.
  • any one of the third servers may be transferred to a payment peak at the third server
  • the third server is one of the servers. If the number of payment processed by the fourth server during the peak payment period of the third server plus the number of payment of the account set to be transferred during the peak payment period of the third server is greater than a preset number of times, the The transferred account set is transferred to a server that does not have saved account information.
  • the payment cycle can be one day, one week, one month, one quarter, or one year.
  • the unit time can be n hours or n days, where n can be a natural number or an unnatural number. Dynamically planning the storage location of the account set according to the number of payment processes processed by each server during the peak payment period can effectively ensure that each server maintains a smooth running speed at all times.
  • the number of payment processes processed by each server in each unit time in multiple payment periods can also be monitored in real time, and the number of payment processes processed by each server is the sum of the number of payment times corresponding to all account information in each server. Then, according to the number of payment processes processed by each server in each unit time, the peak period of payment corresponding to each server that holds the account information in the payment period is determined; the number of spare payments of each server in the peak period of the payment period is counted, and the number of spare payments is the peak period.
  • each server corresponds to a spare payment number in a certain peak period, if the fifth server is in the fifth server.
  • the number of payment processes in the peak period of the payment is greater than the preset number of times, and any account set of the fifth server is retrieved, and the number of payment times corresponding to the account set during the peak payment period is counted as the number of sub-payments, according to the sub-payment
  • the number of times determines that the number of vacant payouts is greater than the sixth server from the number of payouts, and transfers the set of accounts to the sixth server.
  • the account information that needs to be biometrically identified is stored in groups according to the voice features of the voice password.
  • the user's voice password can be obtained to determine the target account set to which the user's account information belongs, thereby enabling The target account set quickly finds the account information matching the biometric feature of the user, reduces the operation process of the biometric matching, and improves the operation speed, and the payment method does not require the user to carry the mobile terminal, and the payment is more convenient.
  • FIG. 2 is a method for payment according to an embodiment of the present invention.
  • the method may specifically include the following steps.
  • Step 201 Acquire a voice password of the user.
  • the user may first input a voice password to the payment system for determining the account set to which the user's account information belongs. If there is an account set divided by the text information of the voice password in the account set, the user needs to input the voice password with the same content as the preset voice password, so that the account set of the user's account information can be accurately determined, otherwise Limit the content of the voice password entered by the user.
  • Step 202 Determine, according to at least one sound feature of the voice password, a target account set corresponding to the voice password in an account information database, where the target account set is one of an account set included in the account information database, and each The set of accounts includes at least one account information.
  • Each account set in the account information base may be a set of accounts of the same level or a set of accounts of different levels.
  • the target account set corresponding to the voice password may be determined according to the identifier of each account set. If each account set is divided according to a sound feature, the identification of each account set can be marked with a sound feature, such as an A dialect. If each account set is divided into two sound characteristics, the identification of each account set is marked by two sound features, for example, the identifier can be set to "A dialect, gender male".
  • the voice feature of the voice password may be determined first, and then the target account set is determined according to the voice feature and the identity of each account set.
  • the process of determining the target account set may include: determining a first sound feature of the voice password, and each first level account set in the account information base is according to the first Decoding a sound feature; determining whether the first account set corresponding to the first sound feature of the voice password includes a sub-account set, the first account set being one of the first-level account sets; if the voice password is Determining, in the first account set corresponding to the first sound feature, that the first account set is a target account set; if the first account set corresponding to the first sound feature of the voice password includes a sub-account set, Determining a second sound feature of the voice password, the second account set in the account information database is divided according to the second sound feature; determining a second account set corresponding to the second sound feature of the voice password Whether a sub-account set is included, the second account set is one of a set of sub-accounts included in the first account set; if the second voice
  • all the voice features required to determine the target account set may also be obtained first, and then the target account set is determined according to each sound feature.
  • each level of the account set may also be divided according to at least two voice features.
  • the at least two types corresponding to the level account set may be determined first.
  • a sound feature, and determining, according to the at least two sound characteristics, the account set corresponding to the voice password in the level account set may be determined first.
  • the dichotomy may be used for searching.
  • the specific search process may include: determining an account set in the middle of the account information database, and each account in the account information database Sorting according to at least one sound feature corresponding to each of the set of accounts; comparing at least one sound feature corresponding to the set of accounts in the intermediate position according to the at least one sound feature of the voice password, A lookup is made forward or backward from the set of accounts in the middle position to determine a target account set corresponding to the voice password.
  • the sorting priority of each sound feature can be set to complete the sorting.
  • the sound characteristics corresponding to each account set may be determined according to the identifiers of the respective account sets, so each account set in the account information base may be sorted according to the identified pinyin initials.
  • searching from the account set ranked in the middle position it may be determined according to a preset sorting rule whether the target account set is located before or after the account set of the intermediate position, so that only the identities of half of the account sets can be traversed at most Going to the target account set can save search time and reduce the search process.
  • the dichotomy method may also be used for searching.
  • the specific process refer to the dichotomy method described in the previous paragraph. The process of searching is not repeated here.
  • Step 203 Acquire at least one biometric information of the user.
  • the preset biometric information is saved in each account information.
  • the preset biometric information is a voiceprint feature and a facial feature
  • the user voice and the facial image need to be acquired, thereby acquiring the voiceprint feature and the facial feature of the user.
  • the preset biometric information is a voiceprint feature and a facial feature
  • Step 204 Search for account information that matches the at least one biometric information in the target account set, where the account information includes at least one preset biometric information and an account.
  • the target account set may include a plurality of account information.
  • the account information in the target account set may be traversed, and the acquired biometric information is traversed to Each preset biometric information in the account information is matched separately, and only the biometric information is matched successfully, and the search ends.
  • the top account information may be arranged from the target account set to start searching for account information that matches the at least one biometric information, and each account information in the target account set The ranking is performed in descending order of the payment frequency corresponding to each of the account information.
  • the payment frequency corresponding to each account information may be the payment frequency within the payment period.
  • Each time a payment period can be re-arranged according to the payment frequency corresponding to each account information in the previous payment period, to ensure the correct ordering of the newly added account information or to adapt to the payment frequency caused by the change of the user's consumption habits. change.
  • the account information that needs to be biometrically identified is stored in groups according to the voice features of the voice password.
  • the user's voice password can be obtained to determine the target account set to which the user's account information belongs, thereby enabling The target account set quickly finds the account information matching the biometric feature of the user, reduces the operation process of the biometric matching, and improves the operation speed, and the payment method does not require the user to carry the mobile terminal, and the payment is more convenient.
  • FIG. 3 is a structural block diagram of a grouping apparatus for account information according to an embodiment of the present invention.
  • the device may specifically include an obtaining unit 301, a grouping unit 302, and a saving unit 303.
  • the obtaining unit 301 is configured to acquire at least two account information and a voice password corresponding to each of the account information.
  • the grouping unit 302 is configured to divide each of the account information into at least two account sets according to at least one sound feature of each of the voice passwords.
  • the saving unit 303 is configured to save the at least two account sets to at least one server.
  • the grouping unit 302 is specifically configured to:
  • the account information in the first account set is divided into at least two secondary account sets according to a second sound feature of the voice password corresponding to the account information in the first account set.
  • the saving unit 303 is specifically configured to:
  • the second account set is stored in the first server, and the deposit condition is that the sum of the number of account information in the current server and the number of account information in the second account set is less than a second threshold, the second set of accounts being one of the at least two account sets;
  • the first server does not meet the deposit condition, it is determined whether the second server meets the deposit condition
  • the second account set is stored in the second server.
  • the saving unit 303 may further include a determining subunit and a transferring subunit.
  • the determining subunit is configured to determine a payment peak period corresponding to each server that stores the account information in the payment period.
  • a transfer subunit configured to transfer any one of the third servers to the first time when the number of payment processes processed by the third server in the payment peak period of the third server is greater than a preset number of times Among the servers having the lowest number of payment processed during the peak payment period of the three servers, the third server is one of the servers.
  • FIG. 4 is a structural block diagram of a payment apparatus according to an embodiment of the present invention.
  • the apparatus may include a first obtaining unit 401, a determining unit 402, a second obtaining unit 403, and a searching unit 404.
  • the first obtaining unit 401 is configured to acquire a voice password of the user.
  • the determining unit 402 is configured to determine, in the account information base, a target account set corresponding to the voice password according to the at least one sound feature of the voice password, where the target account set is an account set included in the account information database One, each of the set of accounts includes at least one account information.
  • the second obtaining unit 403 is configured to acquire at least one biometric information of the user.
  • the searching unit 404 is configured to search, in the target account set, account information that matches the at least one biometric information, where the account information includes at least one preset biometric information and an account.
  • the determining unit 402 is specifically configured to:
  • the first account set corresponding to the first voice feature of the voice password does not include a sub-account set, determining that the first account set is a target account set;
  • the second account set corresponding to the second voice feature of the voice password does not include the sub-account set, determining that the second account set is the target account set.
  • the searching unit 404 is specifically configured to start to search for account information that matches the at least one biometric information from the top account information in the target account set, and the account information in the target account set is in accordance with The payment frequency corresponding to each of the account information is sorted from high to low.
  • the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, ie may be located A place, or it 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 the embodiment. Those of ordinary skill in the art can understand and implement without deliberate labor.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Computer Security & Cryptography (AREA)
  • Accounting & Taxation (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

一种账户信息的分组方法、装置以及一种支付方法、装置，该支付方法包括：获取用户的语音口令(201)；根据所述语音口令的至少一种声音特征在账户信息库中确定所述语音口令对应的目标账户集，所述目标账户集为所述账户信息库所包括的账户集中的一个，各个所述账户集包括至少一个账户信息(202)；获取所述用户的至少一种生物特征信息(203)；在所述目标账户集中查找与所述至少一种生物特征信息均匹配的账户信息，所述账户信息中包括至少一种预设生物特征信息以及账号(204)。本方法将账户信息根据语音口令的声音特征进行分组保存，当进行支付时，可以根据用户的语音口令确定该用户的账户信息所属的目标账号集并在目标账号集中快速查找到目标账户信息。

Description

账户信息的分组方法、装置及支付方法、装置 技术领域
本发明实施例涉及生物识别技术领域，尤其涉及一种支付账户的分组方法、装置及一种支付方法、装置。
背景技术
移动支付允许移动用户使用移动终端(例如手机)对所消费的商品或服务进行账务支付。移动支付通常包括两种方式，一种是消费者可以利用移动终端扫描商家提供的二维码完成费用支付。另一种是商家的收款终端通过扫描消费者移动终端上的二维码，确定消费者的电子支付账户(以下简称“支付账户”)，再从该支付账户的余额或绑定的银行卡中将相应的费用转到商家账户中，从而完成支付。移动支付虽然较传统的支付方式更加方便、快捷，但是都需要消费者随时携带移动终端才能完成支付，移动支付方式仍然不够方便。
生物识别为利用人体固有的生理特性(如指纹、面相、虹膜等)和行为特征(如笔迹、声音、步态等)来进行个人身份的鉴定的技术。如果商家的收款终端能够通过生物识别确定出消费者的支付账户，那么消费者即使没有携带移动终端也能够完成支付。
但是由于生物识别技术的匹配算法较复杂，所以目前生物识别支付方式一般只能应用在消费者的移动终端上，进行1：1的识别，即将支付时获取的生物特征与移动终端保存的唯一生物特征进行匹配，匹配成功完成支付，否则支付失败。由于目前拥有支付账户的用户的数量相当庞大，甚至有几亿人，而目前的生物识别技术在1：n的识别过程中，n的数量有限，一般为10万左右，当为100万时实现起来已经非常困难。如果通过增加服务器的数量，以提高n的数量，但是成本较大，同时也会增加运算响应时间。所以从如此庞大的账户信息库中利用生物识别技术匹配出特定的账户信息，实现起来非常困难。
发明内容
本发明实施例提供了一种账户信息的分组方法以及支付方法，以解决目前使用生物识别技术实现支付功能比较困难的问题。
第一方面，本发明实施例提供了一种支付方法，包括：
获取用户的语音口令；
根据所述语音口令的至少一种声音特征在账户信息库中确定所述语音口令对应的目标账户集，所述目标账户集为所述账户信息库所包括的账户集中的一个，各个所述账户集包括至少一个账户信息；
获取所述用户的至少一种生物特征信息；
在所述目标账户集中查找与所述至少一种生物特征信息均匹配的账户信息，所述账户信息中包括至少一种预设生物特征信息以及账号。
进一步地，所述声音特征包括性别特征、年龄阶段特征、方言特征或文字信息。
进一步地，根据所述语音口令的至少一种声音特征在账户信息库中确定所述语音口令对应的目标账户集的步骤，包括：
确定所述语音口令的第一声音特征，所述账户信息库中的各个一级账户集根据所述第一声音特征划分而成；
确定所述语音口令的第一声音特征对应的第一账户集中是否包括子账户集，所述第一账户集为所述一级账户集中的一个；
如果所述语音口令的第一声音特征对应的第一账户集中不包括子账户集，则确定所述第一账户集为目标账户集；
如果所述语音口令的第一声音特征对应的第一账户集中包括子账户集，则确定所述语音口令的第二声音特征，所述账户信息库中的二级账户集根据所述第二声音特征划分而成；
确定所述语音口令的第二声音特征对应的第二账户集中是否包括子账户集，所述第二账户集为所述第一账户集所包括的子账户集的一个；
如果所述语音口令的第二声音特征对应的第二账户集中不包括子账户集，则确定所述第二账户集为目标账户集。
进一步地，在所述目标账户集中查找与所述至少一种生物特征信息均匹配的账户信息的步骤，包括：
从所述目标账户集中排列最靠前的账户信息开始查找与所述至少一种生物特征信息均匹配的账户信息，所述目标账户集中的各个账户信息按照各个所述账户信息对应的支付频率从高到低的顺序进行排序。
第二方面，本发明实施例还提供了一种账户信息的分组方法，包括：
获取至少两个账户信息以及各个所述账户信息对应的语音口令；
根据各个所述语音口令的至少一种声音特征将各个所述账户信息分为至少两个账户集。
进一步地，根据各个所述语音口令的至少一种声音特征将各个所述账户信息分为至少两个账户集的步骤还包括：
根据各个所述语音口令的第一声音特征将各个所述账户信息分为至少两个一级账户集；
判断是否存在账户信息数量大于第一阈值的第一账户集，所述第一账户集为所述一级账户集中的一个；
如果存在，根据所述第一账户集中的账户信息对应的语音口令的第二声音特征将所述第一账户集中的账户信息分为至少两个二级账户集。
进一步地，该方法还包括：
如果第一服务器符合存入条件，则将第二账户集存入所述第一服务器，所述存入条件为当前服务器中的账户信息数量与所述第二账户集中的账户信息数量之和小于第二阈值，所述第二账户集为所述至少两个账户集中的一个；
如果第一服务器不符合存入条件，则判断所述第二服务器是否符合存入条件；
如果所述第二服务器符合存入条件，则将所述第二账户集存入所述第二服务器。
进一步地，该方法还包括：
将所述至少两个账户集保存至至少一个服务器中；
确定支付周期内各个保存有账户信息的服务器对应的支付高峰期时段；
如果第三服务器在所述第三服务器的支付高峰期时段内处理的支付次数大于预 设次数，则将所述第三服务器中的任一账户集转移至在所述第三服务器的支付高峰期内处理的支付次数最低的服务器中，所述第三服务器为所述服务器中的一个。
第三方面，本发明实施例还提供了一种支付装置，包括：
第一获取单元，用于获取用户的语音口令；
确定单元，用于根据所述语音口令的至少一种声音特征在账户信息库中确定所述语音口令对应的目标账户集，所述目标账户集为所述账户信息库所包括的账户集中的一个，各个所述账户集包括至少一个账户信息；
第二获取单元，用于获取所述用户的至少一种生物特征信息；
查找单元，用于在所述目标账户集中查找与所述至少一种生物特征信息均匹配的账户信息，所述账户信息中包括至少一种预设生物特征信息以及账号。
第四方面，本发明实施例还提供了一种账户信息的分组装置，包括：
获取单元，用于获取至少两个账户信息以及各个所述账户信息对应的语音口令；
分组单元，用于根据各个所述语音口令的至少一种声音特征将各个所述账户信息分为至少两个账户集。
本发明实施例将需要进行生物识别的账户信息根据语音口令的声音特征进行分组保存，当进行支付时，可以通过获取用户的语音口令，确定该用户的账户信息所属的目标账号集，从而能够从目标账号集中快速查找到与该用户的生物特征匹配的账户信息，减少了生物特征匹配的运算过程，提高了运算速度，并且该支付方式无需用户携带移动终端，支付更加方便。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
为了更清楚地说明本申请的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，显而易见地，对于本领域普通技术人员而言，在不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本发明实施例提供的一种账户信息的分组方法的流程图；
图2为本发明实施例提供的一种支付方法的流程图；
图3为本发明实施例提供的一种账户信息的分组装置的结构框图；
图4为本发明实施例提供的一种支付装置的结构框图。
具体实施方式
为使本发明的上述目的、特征和优点能够更加明显易懂，下面结合附图和具体实施方式对本发明作进一步详细的说明。
本发明实施例可以应用在利用生物识别技术进行消费支付的场景中。本发明的发明构思为将需要进行生物识别的账户信息根据语音口令的声音特征进行分组保存，当进行支付时，可以通过获取用户的语音口令，确定该用户的账户信息所属的目标账号集，从而能够从目标账号集中快速查找到与该用户的生物特征匹配的账户信息，减少了生物特征匹配的运算过程，提高了运算速度，并且该支付方式无需用户携带移动终端，支付更加方便。
各个用户的账户信息可以包括账户标识、账户密码、以及至少一种预设生物特征信息。预设生物特征信息包括声纹特征、指纹特征、虹膜特征、面部特征等。在支付过程中进行生物识别时，可以同时进行两种以上生物特征的识别，只有全部生物特征均匹配成功才能够正常支付，从而提高支付的安全性。
本发明中的语音口令可以为任意语音内容的语音口令，例如“你好”、“同意支付”、“芝麻开门”等等。通过对语音口令的分析，可以确定输出该语音口令的用户的性别、该用户所处的年龄阶段、该用户所用的方言或者该语音口令对应的文字等等，所以，语音口令的声音特征可以包括性别特征、年龄阶段特征、方言特征或文字信息。
参见图1，为本发明实施例提供的一种账户信息的分组方法，该方法具体可以包括以下步骤。
步骤101，获取至少两个账户信息以及各个所述账户信息对应的语音口令。
用户在注册支付账户时，可以输入任意的语音口令，账户信息库中也可以保存各个账户信息对应的语音口令。
步骤102，根据各个所述语音口令的至少一种声音特征将各个所述账户信息分为至少两个账户集。
在对账户信息进行分组时，可以根据一种声音特征将各个所述账户信息分为多个账户集，例如，将语音口令的文字信息为“芝麻开门”的所有账户信息分到同一账户 集中。在对账户信息进行分组时，还可以根据至少两种声音特征将各个所述账户信息分为多个账户集，例如根据性别特征以及方言特征进行分组时，可以将方言特征为四川方言，并且性别特征为男的所有账户信息分到同一账户集中。
各个账户集可以根据其对应的声音特征标记相应的声音特征标识(以下简称“标识”)，例如账户集根据性别特征进行划分，则该账户集的标识可以为男或女，再例如，各个账户集根据方言特征以及性别特征进行划分，账户集的标识可以设置为例如“A方言、性别男”的标识。
为适应较庞大的账户信息数量，本发明实施例还可以将账户信息分为多级账户集，具体过程可以为：根据各个所述语音口令的第一声音特征将各个所述账户信息分为至少两个一级账户集；判断是否存在账户信息数量大于第一阈值的第一账户集，所述第一账户集为所述一级账户集中的一个；如果存在，根据所述第一账户集中的账户信息对应的语音口令的第二声音特征将所述第一账户集中的账户信息分为至少两个二级账户集。同理可以将账户信息分为更多级的账户集。
例如根据语音口令的方言特征将各个所述账户信息分为至少两个一级账户集，再根据语音口令的文字信息将一级账户集进一步分为二级账户集。需要说明的是，对同一级的账户信息进行分组时，也可以根据多种声音特征进行划分，本发明实施例不对同一级的账户信息分组时所依据的声音特征的种类进行具体限制。
将所有的账户信息进行分组后，可以保存分组信息，该分组信息可以包括各个账户集的标识以及各个账户集之间的所属关系。在支付过程中，可以利用该分组信息快速确定出目标语音口令对应的目标账户集。该分组信息还可以包括无子账户集的账户集的保存地址，以使快速找到目标账户集。在该分组信息中各个账户集的标识可以按照预设规则进行排序，例如按照标识的拼音首字母进行排序，以利用二分法快速查找到目标账户集。在账户信息库中，同一级的各个账户集也可以按照其标识进行排序，也可以利用二分法快速查找到目标账户集。
步骤103，将所述至少两个账户集保存至至少一个服务器中。
各个账户集可以保存在一个或多个服务器中，当各个账户集保存在多个服务器中时，将各个账户集保存至多个服务器中的过程可以包括：如果第一服务器符合存入条件，则将第二账户集存入所述第一服务器，所述存入条件为当前服务器中的账户信息数量与所述第二账户集中的账户信息数量之和小于第二阈值，所述第二账户集为所述至少两个账户集中的一个；如果第一服务器不符合存入条件，则判断所述第二服务器 是否符合存入条件；如果所述第二服务器符合存入条件，则将所述第二账户集存入所述第二服务器。通过该保存过程，可以将每个服务器中的账户信息的数量控制在一定范围内，在保证各个服务器具有较顺畅的运行速度的同时，还能够减少占用的服务器的数量。需要说明的是，该第二账户集可以是无子账户集的账户集，也可以是更高一级的账户集，本发明实施例不对第二账户集所处的级别进行限制。
在具体实施中，还可以实时监测多个支付周期内各单位时间内各个服务器处理的支付次数，每个服务器处理的支付次数为每个服务器中全部账户信息对应的支付次数之和。然后根据各单位时间内各个服务器处理的支付次数确定支付周期内各个保存有账户信息的服务器对应的支付高峰期时段，所述支付高峰期时段可以包括一个或多个连续的单位时间，各个服务器对应的支付高峰期时段可以相同也可以不同，本实施例在此不做具体限定。如果第三服务器在所述第三服务器的支付高峰期时段内处理的支付次数大于预设次数，则可以将所述第三服务器中的任一账户集转移至在所述第三服务器的支付高峰期内处理的支付次数最低的第四服务器中或者转移至没有保存账户信息的服务器中，所述第三服务器为所述服务器中的一个。如果在所述第三服务器的支付高峰期内第四服务器处理的支付次数加上待转移的账户集在所述第三服务器的支付高峰期内的支付次数后大于预设次数，则可以将待转移的账户集转移至没有保存账户信息的服务器中。该支付周期可以为一天、一周、一个月、一个季度或一年。单位时间可以为n个小时或n天，其中n可以为自然数或非自然数。根据各个服务器在支付高峰期时段内处理的支付次数对账户集的保存位置进行动态规划，能够有效保证各个服务器时刻保持较顺畅的运行速度。
在具体实施中，还可以实时监测多个支付周期内各单位时间内各个服务器处理的支付次数，每个服务器处理的支付次数为每个服务器中全部账户信息对应的支付次数之和。然后根据各单位时间内各个服务器处理的支付次数确定支付周期内各个保存有账户信息的服务器对应的支付高峰期时段；统计支付高峰期时段各服务器的空余支付次数，所述空余支付次数为高峰期时段内各服务器的预设次数与每个服务器中全部账户信息对应的支付次数的差值；在某一个高峰期时段内每个服务器对应一个空余支付次数，如果第五服务器在所述第五服务器的支付高峰期时段内处理的支付次数大于预设次数，调取所述第五服务器的任一账户集，统计所述账户集在支付高峰期时段对应的支付次数即子支付次数，根据子支付次数确定空余支付次数大于自支付次数的第六服务器，将所述账户集转移至第六服务器。
本发明实施例将需要进行生物识别的账户信息根据语音口令的声音特征进行分 组保存，当进行支付时，可以通过获取用户的语音口令，确定该用户的账户信息所属的目标账号集，从而能够从目标账号集中快速查找到与该用户的生物特征匹配的账户信息，减少了生物特征匹配的运算过程，提高了运算速度，并且该支付方式无需用户携带移动终端，支付更加方便。
参见图2，为本发明实施例提供的一种支付方法，该方法具体可以包括以下步骤。
步骤201，获取用户的语音口令。
用户在进行支付时，可以先向支付系统输入语音口令，用于确定该用户的账户信息所属的账户集。如果账户集中存在按照语音口令的文字信息进行划分的账户集，则用户需要输入内容与预设语音口令的内容相同的语音口令，以使能够准确确定该用户的账户信息所在的账户集，否则不限制该用户输入的语音口令的内容。
步骤202，根据所述语音口令的至少一种声音特征在账户信息库中确定所述语音口令对应的目标账户集，所述目标账户集为所述账户信息库所包括的账户集中的一个，各个所述账户集包括至少一个账户信息。
账户信息库中的各个账户集可以为同一级的账户集，也可以为不同级的账户集。当各个账户集为同一级的账户集时，可以根据各个账户集的标识确定该语音口令对应的目标账户集。如果各个账户集按照一种声音特征划分而成，则各个账户集的标识可以利用一种声音特征进行标记，例如A方言。如果各个账户集按照两种声音特征划分而成，则各个账户集的标识利用两种声音特征进行标记，例如标识可以设置为“A方言、性别男”。在确定目标账户集时，可以先确定该语音口令的声音特征，再根据该声音特征以及各个账户集的标识确定目标账户集。
当账户信息库中包括不同级的账户集时，确定目标账户集的过程可以包括：确定所述语音口令的第一声音特征，所述账户信息库中的各个一级账户集根据所述第一声音特征划分而成；确定所述语音口令的第一声音特征对应的第一账户集中是否包括子账户集，所述第一账户集为所述一级账户集中的一个；如果所述语音口令的第一声音特征对应的第一账户集中不包括子账户集，则确定所述第一账户集为目标账户集；如果所述语音口令的第一声音特征对应的第一账户集中包括子账户集，则确定所述语音口令的第二声音特征，所述账户信息库中的二级账户集根据所述第二声音特征划分而成；确定所述语音口令的第二声音特征对应的第二账户集中是否包括子账户集，所述第二账户集为所述第一账户集所包括的子账户集的一个；如果所述语音口令的第二声音特征对应的第二账户集中不包括子账户集，则确定所述第二账户集为目标账户集。
在具体实施中，也可以先获取确定目标账户集所需的全部声音特征，再分别根据各个声音特征确定该目标账户集。需要说明的是，每一级账户集也可以根据至少两个声音特征进行划分，那么在每一级账户集中确定该语音口令对应的账户集时，可以先确定该级账户集对应的至少两种声音特征，再根据该至少两种声音特征在该级账户集中确定该语音口令对应的账户集。该过程可以参考上一段所述的确定目标账户集的过程，在此不再赘述。
为快速查找到所述语音口令对应的目标账户集，可以利用二分法进行查找，具体查找过程可以包括：确定所述账户信息库中排在中间位置的账户集，所述账户信息库中各个账户集按照各个所述账户集对应的至少一种声音特征进行排序；根据所述语音口令的所述至少一种声音特征与所述排在中间位置的账户集对应的至少一种声音特征的对比，从所述排在中间位置的账户集开始向前或向后进行查找，以确定所述语音口令对应的目标账户集。当账户信息库中的账户集按照至少两种声音特征进行排序时，可以设置每种声音特征的排序优先级，从而完成排序。各个账户集对应的声音特征可以根据各个账户集的标识进行确定，所以账户信息库中的各个账户集可以按照标识的拼音首字母进行排序。在从排在中间位置的账户集开始进行查找时，可以根据预设的排序规则，确定目标账户集位于该中间位置的账户集之前还是之后，从而最多只需遍历半数账户集的标识即可查找到目标账户集，能够节约查找时间以及减少查找运算过程。
当账户信息库中包括不同级的账户集时，在每一级账户集中确定该语音口令对应的账户集时，也可以利用二分法进行查找，具体过程可以参考上一段所述的利用二分法进行查找的过程，在此不再赘述。
步骤203，获取所述用户的至少一种生物特征信息。
每个账户信息中保存有预设生物特征信息，例如，当预设生物特征信息为声纹特征和面部特征时，则需要获取用户声音以及面部图像，从而获取到用户的声纹特征和面部特征，以用于与预设生物特征信息进行匹配。
步骤204，在所述目标账户集中查找与所述至少一种生物特征信息均匹配的账户信息，所述账户信息中包括至少一种预设生物特征信息以及账号。
该目标账户集可以包括多个账户信息，在查找与所述至少一种生物特征信息均匹配的账户信息时，可以遍历目标账户集中的各个账户信息，将获取到的各个生物特征信息与遍历到的账户信息中的各个预设生物特征信息分别进行匹配，只有各个生物特 征信息均匹配成功，查找才结束。
为减少整个账户集的匹配运算次数，可以从所述目标账户集中排列最靠前的账户信息开始查找与所述至少一种生物特征信息均匹配的账户信息，所述目标账户集中的各个账户信息按照各个所述账户信息对应的支付频率从高到低的顺序进行排序。
在具体实施中，各个账户信息对应的支付频率可以是支付周期内的支付频率。每经过一个支付周期可以根据上一个支付周期内各个账户信息对应的支付频率对各个账户信息进行重新排列，用以保证新增加账户信息的正确排序或适应用户消费习惯的改变而导致的支付频率的改变。
本发明实施例将需要进行生物识别的账户信息根据语音口令的声音特征进行分组保存，当进行支付时，可以通过获取用户的语音口令，确定该用户的账户信息所属的目标账号集，从而能够从目标账号集中快速查找到与该用户的生物特征匹配的账户信息，减少了生物特征匹配的运算过程，提高了运算速度，并且该支付方式无需用户携带移动终端，支付更加方便。
参见图3，为本发明实施例提供的一种账户信息的分组装置的结构框图，该装置具体可以包括获取单元301，分组单元302，保存单元303。
获取单元301，用于获取至少两个账户信息以及各个所述账户信息对应的语音口令。
分组单元302，用于根据各个所述语音口令的至少一种声音特征将各个所述账户信息分为至少两个账户集。
保存单元303，用于将所述至少两个账户集保存至至少一个服务器中。
优选地，分组单元302，具体可以用于：
根据各个所述语音口令的第一声音特征将各个所述账户信息分为至少两个一级账户集；
判断是否存在账户信息数量大于第一阈值的第一账户集，所述第一账户集为所述一级账户集中的一个；
如果存在，根据所述第一账户集中的账户信息对应的语音口令的第二声音特征将所述第一账户集中的账户信息分为至少两个二级账户集。
优选地，保存单元303具体可以用于：
如果第一服务器符合存入条件，则将第二账户集存入所述第一服务器，所述存入条件为当前服务器中的账户信息数量与所述第二账户集中的账户信息数量之和小于第二阈值，所述第二账户集为所述至少两个账户集中的一个；
如果第一服务器不符合存入条件，则判断所述第二服务器是否符合存入条件；
如果所述第二服务器符合存入条件，则将所述第二账户集存入所述第二服务器。
优选地，保存单元303还可以包括确定子单元以及转移子单元。
其中，确定子单元，用于确定支付周期内各个保存有账户信息的服务器对应的支付高峰期时段。
转移子单元，用于当第三服务器在所述第三服务器的支付高峰期时段内处理的支付次数大于预设次数时，将所述第三服务器中的任一账户集转移至在所述第三服务器的支付高峰期内处理的支付次数最低的服务器中，所述第三服务器为所述服务器中的一个。
参见图4，为本发明实施例提供的一种支付装置的结构框图，该装置可以包括第一获取单元401，确定单元402，第二获取单元403，查找单元404。
其中，第一获取单元401，用于获取用户的语音口令。
确定单元402，用于根据所述语音口令的至少一种声音特征在账户信息库中确定所述语音口令对应的目标账户集，所述目标账户集为所述账户信息库所包括的账户集中的一个，各个所述账户集包括至少一个账户信息。
第二获取单元403，用于获取所述用户的至少一种生物特征信息。
查找单元404，用于在所述目标账户集中查找与所述至少一种生物特征信息均匹配的账户信息，所述账户信息中包括至少一种预设生物特征信息以及账号。
优选地，确定单元402具体可以用于：
确定所述语音口令的第一声音特征，所述账户信息库中的各个一级账户集根据所述第一声音特征划分而成；
确定所述语音口令的第一声音特征对应的第一账户集中是否包括子账户集，所述第一账户集为所述一级账户集中的一个；
如果所述语音口令的第一声音特征对应的第一账户集中不包括子账户集，则确定 所述第一账户集为目标账户集；
如果所述语音口令的第一声音特征对应的第一账户集中包括子账户集，则确定所述语音口令的第二声音特征，所述账户信息库中的二级账户集根据所述第二声音特征划分而成；
确定所述语音口令的第二声音特征对应的第二账户集中是否包括子账户集，所述第二账户集为所述第一账户集所包括的子账户集的一个；
如果所述语音口令的第二声音特征对应的第二账户集中不包括子账户集，则确定所述第二账户集为目标账户集。
优选地，查找单元404具体可以用于从所述目标账户集中排列最靠前的账户信息开始查找与所述至少一种生物特征信息均匹配的账户信息，所述目标账户集中的各个账户信息按照各个所述账户信息对应的支付频率从高到低的顺序进行排序。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。本领域普通技术人员在不付出创造性的劳动的情况下，即可以理解并实施。
通过以上的实施方式的描述，本领域的技术人员可以清楚地了解到各实施方式可借助软件加必需的通用硬件平台的方式来实现，当然也可以通过硬件。基于这样的理解，上述技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在计算机可读存储介质中，如ROM/RAM、磁碟、光盘等，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行各个实施例或者实施例的某些部分所述的方法。
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。

Claims (12)

  1. 一种支付方法，其特征在于，包括：
    获取用户的语音口令；
    根据所述语音口令的至少一种声音特征在账户信息库中确定所述语音口令对应的目标账户集，所述目标账户集为所述账户信息库所包括的账户集中的一个，各个所述账户集包括至少一个账户信息；
    获取所述用户的至少一种生物特征信息；
    在所述目标账户集中查找与所述至少一种生物特征信息均匹配的账户信息，所述账户信息中包括至少一种预设生物特征信息以及账号。
  2. 如权利要求1所述的方法，其特征在于，所述声音特征包括性别特征、年龄阶段特征、方言特征或文字信息。
  3. 如权利要求1所述的方法，其特征在于，根据所述语音口令的至少一种声音特征在账户信息库中确定所述语音口令对应的目标账户集的步骤，包括：
    确定所述语音口令的第一声音特征，所述账户信息库中的各个一级账户集根据所述第一声音特征划分而成；
    确定所述语音口令的第一声音特征对应的第一账户集中是否包括子账户集，所述第一账户集为所述一级账户集中的一个；
    如果所述语音口令的第一声音特征对应的第一账户集中不包括子账户集，则确定所述第一账户集为目标账户集；
    如果所述语音口令的第一声音特征对应的第一账户集中包括子账户集，则确定所述语音口令的第二声音特征，所述账户信息库中的二级账户集根据所述第二声音特征划分而成；
    确定所述语音口令的第二声音特征对应的第二账户集中是否包括子账户集，所述第二账户集为所述第一账户集所包括的子账户集的一个；
    如果所述语音口令的第二声音特征对应的第二账户集中不包括子账户集，则确定所述第二账户集为目标账户集。
  4. 如权利要求1所述的方法，其特征在于，在所述目标账户集中查找与所述至少一种生物特征信息均匹配的账户信息的步骤，包括：
    从所述目标账户集中排列最靠前的账户信息开始查找与所述至少一种生物 特征信息均匹配的账户信息，所述目标账户集中的各个账户信息按照各个所述账户信息对应的支付频率从高到低的顺序进行排序。
  5. 一种账户信息的分组方法，其特征在于，包括：
    获取至少两个账户信息以及各个所述账户信息对应的语音口令；
    根据各个所述语音口令的至少一种声音特征将各个所述账户信息分为至少两个账户集。
  6. 如权利要求5所述的方法，其特征在于，根据各个所述语音口令的至少一种声音特征将各个所述账户信息分为至少两个账户集的步骤还包括：
    根据各个所述语音口令的第一声音特征将各个所述账户信息分为至少两个一级账户集；
    判断是否存在账户信息数量大于第一阈值的第一账户集，所述第一账户集为所述一级账户集中的一个；
    如果存在，根据所述第一账户集中的账户信息对应的语音口令的第二声音特征将所述第一账户集中的账户信息分为至少两个二级账户集。
  7. 如权利要求5所述的方法，其特征在于，所述方法还包括：
    如果第一服务器符合存入条件，则将第二账户集存入所述第一服务器，所述存入条件为当前服务器中的账户信息数量与所述第二账户集中的账户信息数量之和小于第二阈值，所述第二账户集为所述至少两个账户集中的一个；
    如果第一服务器不符合存入条件，则判断所述第二服务器是否符合存入条件；
    如果所述第二服务器符合存入条件，则将所述第二账户集存入所述第二服务器。
  8. 如权利要求5所述的方法，其特征在于，所述方法还包括：
    将所述至少两个账户集保存至至少一个服务器中；
    确定支付周期内各个保存有账户信息的服务器对应的支付高峰期时段；
    如果第三服务器在所述第三服务器的支付高峰期时段内处理的支付次数大于预设次数，则将所述第三服务器中的任一账户集转移至在所述第三服务器的支付高峰期内处理的支付次数最低的服务器中，所述第三服务器为所述服务器中的一个。
  9. 如权利要求5所述的方法，其特征在于，所述方法还包括：
    将所述至少两个账户集保存至至少一个服务器中；
    确定支付周期内各个保存有账户信息的服务器对应的支付高峰期时段；
    统计支付高峰期时段各服务器的空余支付次数；
    如果第五服务器在所述第五服务器的支付高峰期时段内处理的支付次数大于预设次数，调取所述第五服务器中任一账户集，统计所述账户集在支付高峰期时段对应的子支付次数；
    根据子支付次数确定空余支付次数大于自支付次数的第六服务器，将所述账户集转移至第六服务器。
  10. 如权利要求5所述的方法，其特征在于，所述账户集根据其对应的声音特征标记声音特征标识。
  11. 一种支付装置，其特征在于，包括：
    第一获取单元，用于获取用户的语音口令；
    确定单元，用于根据所述语音口令的至少一种声音特征在账户信息库中确定所述语音口令对应的目标账户集，所述目标账户集为所述账户信息库所包括的账户集中的一个，各个所述账户集包括至少一个账户信息；
    第二获取单元，用于获取所述用户的至少一种生物特征信息；
    查找单元，用于在所述目标账户集中查找与所述至少一种生物特征信息均匹配的账户信息，所述账户信息中包括至少一种预设生物特征信息以及账号。
  12. 一种账户信息的分组装置，其特征在于，包括：
    获取单元，用于获取至少两个账户信息以及各个所述账户信息对应的语音口令；
    分组单元，用于根据各个所述语音口令的至少一种声音特征将各个所述账户信息分为至少两个账户集。
PCT/CN2018/122341 2018-01-17 2018-12-20 账户信息的分组方法、装置及支付方法、装置 WO2019141039A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810043115.7 2018-01-17
CN201810043115.7A CN110046898B (zh) 2018-01-17 2018-01-17 账户信息的分组方法、装置及支付方法、装置

Publications (1)

Publication Number Publication Date
WO2019141039A1 true WO2019141039A1 (zh) 2019-07-25

Family

ID=67273525

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/122341 WO2019141039A1 (zh) 2018-01-17 2018-12-20 账户信息的分组方法、装置及支付方法、装置

Country Status (2)

Country Link
CN (1) CN110046898B (zh)
WO (1) WO2019141039A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111312257A (zh) * 2019-12-16 2020-06-19 五八有限公司 一种多账号的识别方法、装置、电子设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102377741A (zh) * 2010-08-17 2012-03-14 朱建政 一种在互联网支付中采用说话者语音身份验证和账号密码保护相结合的网络安全验证方法
CN103729764A (zh) * 2013-11-25 2014-04-16 青岛丽雯互联信息有限公司 基于生物特征的数据传递方法与系统
US20150213659A1 (en) * 2012-07-30 2015-07-30 Eka A/S System and device for authenticating a user
CN107194698A (zh) * 2017-05-18 2017-09-22 周美琳 一种智能支付方法和系统

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20060033167A (ko) * 2004-10-14 2006-04-19 엘지전자 주식회사 브이오아이피 호 처리 시스템의 그룹 계정 사용 방법
MY186367A (en) * 2013-10-09 2021-07-16 Raig Tech M Sdn Bhd A system and method for processing of orders related to financial transaction using a computer readable graphical code
CN104392353A (zh) * 2014-10-08 2015-03-04 无锡指网生物识别科技有限公司 语音识别终端的支付方法及系统
CN106202071A (zh) * 2015-04-29 2016-12-07 腾讯科技（深圳）有限公司 账户信息获取的方法、终端、服务器和系统
CN104835040A (zh) * 2015-05-26 2015-08-12 浙江维尔科技股份有限公司 一种支付方法及系统
CN105677787B (zh) * 2015-12-29 2017-10-13 广州神马移动信息科技有限公司 信息搜索装置及信息搜索方法
CN107204910A (zh) * 2016-03-20 2017-09-26 徐超 社交软件中利用声音口令查找好友的方法
CN107369020A (zh) * 2017-04-21 2017-11-21 阿里巴巴集团控股有限公司 一种支付方法、装置及系统
CN107507612B (zh) * 2017-06-30 2020-08-28 百度在线网络技术（北京）有限公司 一种声纹识别方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102377741A (zh) * 2010-08-17 2012-03-14 朱建政 一种在互联网支付中采用说话者语音身份验证和账号密码保护相结合的网络安全验证方法
US20150213659A1 (en) * 2012-07-30 2015-07-30 Eka A/S System and device for authenticating a user
CN103729764A (zh) * 2013-11-25 2014-04-16 青岛丽雯互联信息有限公司 基于生物特征的数据传递方法与系统
CN107194698A (zh) * 2017-05-18 2017-09-22 周美琳 一种智能支付方法和系统

Also Published As

Publication number Publication date
CN110046898A (zh) 2019-07-23
CN110046898B (zh) 2022-01-25

Similar Documents

Publication Publication Date Title
CN105787025B (zh) 网络平台公共账号分类方法及装置
US11048956B2 (en) Intelligent gallery management for biometrics
CN109376766B (zh) 一种画像预测分类方法、装置及设备
US11593847B2 (en) Unsupervised embeddings disentanglement using a GAN for merchant recommendations
CN110298245B (zh) 兴趣收集方法、装置、计算机设备及存储介质
CN109064217B (zh) 基于用户等级的核身策略确定方法、装置及电子设备
CN115862088A (zh) 一种身份识别方法及装置
CN107491965A (zh) 一种生物特征库的建立方法和装置
CN110502694A (zh) 基于大数据分析的律师推荐方法及相关设备
Singh et al. A survey on hidden markov model for credit card fraud detection
CN110046648A (zh) 基于至少一个业务分类模型进行业务分类的方法及装置
WO2018233393A1 (zh) 投保校验的方法、装置、计算机设备及存储介质
CN117114514B (zh) 一种基于大数据的人才信息分析管理方法、系统及装置
CN108416684A (zh) 一种账号主体的可信程度评估方法、装置及服务器
CN111369080B (zh) 一种智能客服解决率预测方法和系统以及多业务预测模型
WO2019141039A1 (zh) 账户信息的分组方法、装置及支付方法、装置
CN113656699A (zh) 用户特征向量确定方法、相关设备及介质
CN113657473A (zh) 一种基于迁移学习的Web服务分类方法
AU2018306317A1 (en) System and method for detecting and responding to transaction patterns
CN109948718B (zh) 一种基于多算法融合的系统及方法
CN111368131A (zh) 用户关系识别方法、装置、电子设备及存储介质
CN109978302A (zh) 一种信用评分方法及设备
CN109308565B (zh) 人群绩效等级识别方法、装置、存储介质及计算机设备
Peng et al. Identification of incorrect karyotypes using deep learning
CN111652626B (zh) 一种业务实现的方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18901638

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18901638

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 18901638

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 20/01/2021)

122 Ep: pct application non-entry in european phase

Ref document number: 18901638

Country of ref document: EP

Kind code of ref document: A1