白丝美女被狂躁免费视频网站,500av导航大全精品,yw.193.cnc爆乳尤物未满,97se亚洲综合色区,аⅴ天堂中文在线网官网

Passive authentication through voice data analysis

專利號
US10867612B1
公開日期
2020-12-15
申請人
United Services Automobile Association (USAA)(US TX San Antonio)
發(fā)明人
Jeffrey Neal Pollack; Michael E'shawn Weaver; Andrew L. Anaruk
IPC分類
G10L17/22; G06F21/32; H04L9/32; G10L17/02; H04L29/06; G10L15/26; G06K9/00; G10L15/02
技術(shù)領(lǐng)域
speech,user,or,data,may,pa,device,cui,in,be
地域: TX TX San Antonio

摘要

Techniques are described for passive authentication based at least partly on collected voice data of a user. During a speech interaction between a user and a personal assistant (PA) device, the user's speech may be analyzed to authenticate the user. The authentication of the user may be a passive authentication, in which the user is not explicitly asked to provide authenticating credentials. Instead, the speech data of the user is collected during the user's interactions with the PA device, and the collected speech data is compared to a previously developed model of the user's speech. The user is successfully authenticated based on determining that there is sufficient correspondence between the collected speech data and the model of the user's speech. After the user is authenticated passively during the conversation, they may be able to access sensitive data or services that may not be otherwise inaccessible without authentication.

說明書

In some implementations, the analysis device(s) 120 may provide various service(s) to user(s) 102. The service(s) may include financial service(s) associated with banking, investment management, lending, home financing, and so forth. In some instances, the service(s) may include insurance service(s) for health insurance, vehicle insurance, life insurance, homeowner's insurance, and so forth. Implementations also support other types of service(s). The user 102 may be provided with information associated with the various services. In some instances, the sensitive information can include information related to these services. For example, sensitive information may include account balances and/or transaction history related to financial accounts, insurance claims status related to an insurance policy, and so forth. Sensitive information may also include requests for operations to be performed, where such operations may involve some risk of fraud, theft, or other harm if they were performed for unauthorized individuals. For example, a user's request for sensitive information may be the user 102 requesting a funds transfer from one financial account to another. If the user 102 makes such a request through the PA device 104, the transfer may be performed if the user 102 has been authenticated.

FIG. 3 depicts a flow diagram of an example process for authenticating a user 102, according to implementations of the present disclosure. Operations of the process may be performed by one or more of the CUI 108, the analysis module(s) 122, the authentication engine 124, the transcription engine 126, the model(s) 128, and/or other module(s) of the PA device 104, the analysis device(s) 120, and/or other device(s).

權(quán)利要求

1
微信群二維碼
意見反饋