Granted Patent B2

US 12,608,427 · App. 18/671,825 · Granted Apr 21, 2026

Inventor: Michael Patrick Rodgers (Lake Oswego, OR)

Assignee: Oracle International Corporation

G06F16/9038G10L15/22G10L2015/0631G10L2015/223G10L2015/228

Abstract

Claims (105)

1 . A non-transitory computer readable medium comprising instructions which, when executed by one or more hardware processors, causes performance of operations comprising:

executing a virtual assistant platform on a first device, the virtual assistant platform configured to receive audio inputs on the first device and to initiate actions corresponding to the audio inputs;

receiving, by the virtual assistant platform, a first audio input comprising a first request corresponding to a first action to be initiated by the virtual assistant platform;

determining and storing, by the virtual assistant platform, contextual data associated with at least one of (a) a configuration of the first device and (b) one or more applications executing on the first device at a time when the first audio input was received;

receiving, by the virtual assistant platform, a second request for audio playback of the first audio input;

based at least on receiving the second request:

retrieving, by the virtual assistant platform executing on the first device, at least a portion of the first audio input;

retrieving, by the virtual assistant platform, the contextual data associated with at least one of (a) a configuration of the first device and (b) one or more applications executing on the first device at the time when the first audio input was received; and

presenting, by the virtual assistant platform, the contextual data together with the portion of the first audio input in a user interface of the first device or a second device,

wherein the contextual data comprises at least one of:

geo-location data corresponding to a geo-location of the first device at the time when the first audio input was received;

first application data corresponding to a first application being executed on the first device at the time when the first audio input was received;

second application data corresponding to a second application that was a last application to be executed on the first device prior to the time when the first audio input was received; and

device configuration data corresponding to a configuration of the first device at the time when the first audio input was received.

2 . The non-transitory computer readable medium of claim 1 , wherein the operations further comprise:

analyzing, by the virtual assistant platform, the first audio input to identify a particular action corresponding to the first audio input; and

determining the virtual assistant platform failed to identify any particular action, including the first action, corresponding to the first audio input,

wherein retrieving the contextual data is performed based on (a) receiving the second request, and (b) determining the virtual assistant platform failed to identify any particular action corresponding to the first audio input.

3 . The non-transitory computer readable medium of claim 1 , wherein the operations further comprise:

analyzing, by the virtual assistant platform, the first audio input to identify a particular action corresponding to the first audio input; and

determining the virtual assistant platform identified a second action, different from the first action, as corresponding to the first audio input,

wherein retrieving the contextual data is performed based on (a) receiving the second request, and (b) determining virtual assistant platform identified the second action as corresponding to the first audio input.

4 . The non-transitory computer readable medium of claim 1 , wherein the operations further comprise:

analyzing, by the virtual assistant platform, the first audio input to identify a particular action corresponding to the first audio input;

determining the virtual assistant platform identified a second action as corresponding to the first audio input; and

computing a confidence score associated with a pairing of the second action with the first audio input,

wherein retrieving the contextual data is performed based on (a) receiving the second request, and (b) determining confidence score does not meet a threshold confidence value.

5 . The non-transitory computer readable medium of claim 4 , wherein the confidence score is based at least on a confidence that the virtual assistant platform correctly classified a set of phonemes included in the first audio input.

6 . The non-transitory computer readable medium of claim 4 , wherein the operations further comprise:

generating a transcript of the first audio input,

wherein the confidence score is based at least on a confidence that the transcript correctly identifies words included in the first audio input.

7 . The non-transitory computer readable medium of claim 1 , wherein the operations further comprise:

identifying, by the virtual assistant platform, a request type corresponding to the first request,

wherein retrieving the contextual data comprises:

identifying a first type of contextual data corresponding to the first request; and

based on identifying the first type of contextual data: retrieving the contextual data of the first type.

8 . A method comprising:

executing a virtual assistant platform on a first device, the virtual assistant platform configured to receive audio inputs on the first device and to initiate actions corresponding to the audio inputs;

receiving, by the virtual assistant platform, a first audio input comprising a first request corresponding to a first action to be initiated by the virtual assistant platform;

determining and storing, by the virtual assistant platform, contextual data associated with at least one of (a) a configuration of the first device and (b) one or more applications executing on the first device at a time when the first audio input was received;

receiving, by the virtual assistant platform, a second request for audio playback of the first audio input;

based at least on receiving the second request:

retrieving, by the virtual assistant platform executing on the first device, at least a portion of the first audio input;

retrieving, by the virtual assistant platform, the contextual data associated with at least one of (a) a configuration of the first device and (b) one or more applications executing on the first device at the time when the first audio input was received; and

presenting, by the virtual assistant platform, the contextual data together with the portion of the first audio input in a user interface of the first device or a second device,

wherein the contextual data comprises at least one of:

geo-location data corresponding to a geo-location of the first device at the time when the first audio input was received;

first application data corresponding to a first application being executed on the first device at the time when the first audio input was received;

second application data corresponding to a second application that was a last application to be executed on the first device prior to the time when the first audio input was received; and

device configuration data corresponding to a configuration of the first device at the time when the first audio input was received.

9 . The method of claim 8 , further comprising:

analyzing, by the virtual assistant platform, the first audio input to identify a particular action corresponding to the first audio input; and

determining the virtual assistant platform failed to identify any particular action, including the first action, corresponding to the first audio input,

wherein retrieving the contextual data is performed based on (a) receiving the second request, and (b) determining the virtual assistant platform failed to identify any particular action corresponding to the first audio input.

10 . The method of claim 8 , further comprising:

analyzing, by the virtual assistant platform, the first audio input to identify a particular action corresponding to the first audio input; and

determining the virtual assistant platform identified a second action, different from the first action, as corresponding to the first audio input,

wherein retrieving the contextual data is performed based on (a) receiving the second request, and (b) determining virtual assistant platform identified the second action as corresponding to the first audio input.

11 . The method of claim 8 , further comprising:

analyzing, by the virtual assistant platform, the first audio input to identify a particular action corresponding to the first audio input;

determining the virtual assistant platform identified a second action as corresponding to the first audio input; and

computing a confidence score associated with a pairing of the second action with the first audio input,

wherein retrieving the contextual data is performed based on (a) receiving the second request, and (b) determining confidence score does not meet a threshold confidence value.

12 . The method of claim 11 , wherein the confidence score is based at least on a confidence that the virtual assistant platform correctly classified a set of phonemes included in the first audio input.

13 . The method of claim 11 , further comprising:

generating a transcript of the first audio input,

wherein the confidence score is based at least on a confidence that the transcript correctly identifies words included in the first audio input.

14 . The method of claim 8 , further comprising:

identifying, by the virtual assistant platform, a request type corresponding to the first request,

wherein retrieving the contextual data comprises:

identifying a first type of contextual data corresponding to the first request; and

based on identifying the first type of contextual data: retrieving the contextual data of the first type.

15 . A system comprising:

at least one device including a hardware processor;

the system being configured to perform operations comprising:

executing a virtual assistant platform on a first device, the virtual assistant platform configured to receive audio inputs on the first device and to initiate actions corresponding to the audio inputs;

receiving, by the virtual assistant platform, a first audio input comprising a first request corresponding to a first action to be initiated by the virtual assistant platform;

determining and storing, by the virtual assistant platform, contextual data associated with at least one of (a) a configuration of the first device and (b) one or more applications executing on the first device at a time when the first audio input was received;

receiving, by the virtual assistant platform, a second request for audio playback of the first audio input;

based at least on receiving the second request:

retrieving, by the virtual assistant platform executing on the first device, at least a portion of the first audio input;

retrieving, by the virtual assistant platform, the contextual data associated with at least one of (a) a configuration of the first device and (b) one or more applications executing on the first device at the time when the first audio input was received; and

presenting, by the virtual assistant platform, the contextual data together with the portion of the first audio input in a user interface of the first device or a second device,

wherein the contextual data comprises at least one of:

geo-location data corresponding to a geo-location of the first device at the time when the first audio input was received;

first application data corresponding to a first application being executed on the first device at the time when the first audio input was received;

second application data corresponding to a second application that was a last application to be executed on the first device prior to the time when the first audio input was received; and

device configuration data corresponding to a configuration of the first device at the time when the first audio input was received.

16 . The system of claim 15 , wherein the operations further comprise:

analyzing, by the virtual assistant platform, the first audio input to identify a particular action corresponding to the first audio input; and

determining the virtual assistant platform failed to identify any particular action, including the first action, corresponding to the first audio input,

wherein retrieving the contextual data is performed based on (a) receiving the second request, and (b) determining the virtual assistant platform failed to identify any particular action corresponding to the first audio input.

17 . The system of claim 15 , wherein the operations further comprise:

analyzing, by the virtual assistant platform, the first audio input to identify a particular action corresponding to the first audio input; and

determining the virtual assistant platform identified a second action, different from the first action, as corresponding to the first audio input,

wherein retrieving the contextual data is performed based on (a) receiving the second request, and (b) determining virtual assistant platform identified the second action as corresponding to the first audio input.

18 . The system of claim 15 , wherein the operations further comprise:

analyzing, by the virtual assistant platform, the first audio input to identify a particular action corresponding to the first audio input;

determining the virtual assistant platform identified a second action as corresponding to the first audio input; and

computing a confidence score associated with a pairing of the second action with the first audio input,

wherein retrieving the contextual data is performed based on (a) receiving the second request, and (b) determining confidence score does not meet a threshold confidence value.

19 . The system of claim 18 , wherein the confidence score is based at least on a confidence that the virtual assistant platform correctly classified a set of phonemes included in the first audio input.

20 . The system of claim 18 , wherein the operations further comprise:

generating a transcript of the first audio input,

wherein the confidence score is based at least on a confidence that the transcript correctly identifies words included in the first audio input.

Assignments (1)

Continuity (2)

References Cited (79)