| CPC G06F 21/32 (2013.01) [G06F 21/6245 (2013.01); G10L 17/02 (2013.01); G10L 17/14 (2013.01); G10L 17/24 (2013.01); G06F 3/0481 (2013.01)] | 24 Claims |
|
1. A computer-implemented method when executed on data processing hardware causes the data processing hardware to perform operations comprising:
receiving, at a profile service executing on the data processing hardware, from an assistant service executing on a user device of a user, a request requesting the profile service to release personal information associated with the user to the assistant service, wherein the assistant service sends the request to the profile service in response to the assistant service:
receiving initial audio data characterizing a query spoken by the user that requests the assistant service to perform an action on behalf of the user; and
processing the initial audio data to identify the personal information associated with the user as personal information explicitly stored by the user on a centralized data store managed by the profile service that the assistant service requires in order to perform the action on the behalf of the user;
determining that the user device is not suitable for receiving out-of-band notifications directly from the profile service without the assistant service for gaining user consent for releasing the requested personal information to the assistant service; and
based on determining that the user device is not suitable for receiving the out-of-band notifications directly from the profile service, performing, through the assistant service, a verification process to verify that the user consents to releasing the requested personal information to the assistant service by:
extracting, from the requested personal information explicitly stored by the user on the centralized data store that the assistant service requires in order to perform the action on the behalf of the user, one or more personal information fragments, the extracted one or more personal information fragments comprising a unique token prescribed to the user by the profile service;
generating a security statement answered by the extracted one or more personal information fragments that comprise the unique token;
generating a verification message that prompts the user to provide a spoken input that answers the security statement;
instructing the assistant service to output the verification message from the user device;
receiving audio data characterizing a spoken utterance captured by the user device of the user;
processing the audio data to determine whether a transcription of the spoken utterance recites each of the one or more extracted personal information fragments; and
when the transcription of the spoken utterance recites each of the one or more extracted personal information fragments, releasing, to the assistant service, the requested personal information stored on the centralized data store managed by the profile service, the requested personal information enabling the assistant service to perform the action on behalf of the user.
|
|
13. A system comprising:
data processing hardware; and
memory hardware in communication with the data processing hardware, the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising,
receiving, at a profile service executing on the data processing hardware, from an assistant service executing on a user device of a user, a request requesting the profile service to release personal information associated with the user to the assistant service, wherein the assistant service sends the request to the profile service in response to the assistant service:
receiving initial audio data characterizing a query spoken by the user that requests the assistant service to perform an action on behalf of the user; and
processing the initial audio data to identify the personal information associated with the user as personal information explicitly stored by the user on a centralized data store managed by the profile service that the assistant service requires in order to perform the action on the behalf of the user;
determining that the user device is not suitable for receiving out-of-band notifications directly from the profile service without the assistant service for gaining user consent for releasing the requested personal information to the assistant service; and
based on determining that the user device is not suitable for receiving the out-of-band notifications directly from the profile service, performing, through the assistant service, a verification process to verify that the user consents to releasing the requested personal information to the assistant service by:
extracting, from the requested personal information explicitly stored by the user on the centralized data store that the assistant service requires in order to perform the action on the behalf of the user, one or more personal information fragments, the extracted one or more personal information fragments comprising a unique token prescribed to the user by the profile service;
generating a security statement answered by the extracted one or more personal information fragments that comprise the unique token;
generating a verification message that prompts the user to provide a spoken input that answers the security statement;
instructing the assistant service to output the verification message from the user device;
receiving audio data characterizing a spoken utterance captured by the user device of the user;
processing the audio data to determine whether a transcription of the spoken utterance recites each of the one or more extracted personal information fragments; and
when the transcription of the spoken utterance recites each of the one or more extracted personal information fragments, releasing, to the assistant service, the requested personal information stored on the centralized data store managed by the profile service, the requested personal information enabling the assistant service to perform the action on behalf of the user.
|