US-20260127257-A1 - CONTEXTUAL METHOD FOR ENABLING PASSIVE LISTENING ENGAGEMENT

US20260127257A1US 20260127257 A1US20260127257 A1US 20260127257A1US-20260127257-A1

Abstract

Methods and systems for managing operation of data processing systems are disclosed. To manage operation of the data processing systems, access controls may be selected and enforced based on inferred users of the data processing systems. The users may be inferred based on sensing of the environments around the data processing systems. During the inferencing process, the types of the environments may be taken into account to improve a likelihood of identifying users that are present in the environments and/or conditions in the environment that impact security of the data processing systems.

Inventors

Rachid M. Alameh
Jarrett Simerson
Marc Randall Hammons

Assignees

DELL PRODUCTS L.P.

Dates

Publication Date: 20260507
Application Date: 20241107

Claims (20)

1 . A method for managing operation of a data processing system, the method comprising: obtaining audio from a first environment around the data processing system using an audio sensor of the data processing system; classifying the audio to obtain a context for the first environment; obtaining, from a repository, at least one audio sample of a user of the data processing system while the user is present in a second environment, the at least one audio sample being classified in the context; comparing the audio to the at least one audio sample to identify a likelihood of a first voice from the audio being a voice of the user; selecting, based on the likelihood, an access control to be applied to the data processing system; and providing computer implemented services using the data processing system based on the access control.
2 . The method of claim 1 , further comprising: obtaining location data for the data processing system, wherein the access control is also selected based on the location data, and the access control limits access to different types of data hosted by the data processing system.
3 . The method of claim 2 , wherein selecting the access control comprises: when the likelihood falls into a first likelihood range: concluding that no access is to be granted; when the likelihood falls into a second likelihood range: concluding that full access is to be granted; and when the likelihood falls into a third range: comparing the location data to a known location list; in a first instance of the comparing where the location data indicates that the data processing system is not located at any location of the known location list: concluding that no access is to be granted, and in a second instance of the comparing where the location data indicates that the data processing system is located at one location of the known location list: concluding that limited access is to be granted.
4 . The method of claim 1 , further comprising: prior to obtaining the audio obtaining an audio clip of the user while the user is present in a third environment; obtaining video data of the user while the audio clip is obtained; confirming the audio clip based on activity of lips of the user in the video data to obtain a new audio sample; classifying the new audio sample to obtain a second context for the third environment; and adding the new audio sample to the repository using the second context to group the new audio sample with other audio samples that also have the second context.
5 . The method of claim 4 , further comprising: using the new audio sample and the other audio samples to obtain a representative audio sample for the second context.
6 . The method of claim 5 , wherein the representative audio sample is an average of the new audio sample and the other audio samples.
7 . The method of claim 1 , further comprising: after selecting the access control: monitoring the first environment for occurrences of prescribed events; and re-evaluating the access control based on the occurrences.
8 . The method of claim 7 , wherein the prescribed events comprises: changes in a cardinality of a number of speakers present in the first environment.
9 . The method of claim 7 , wherein monitoring the first environment comprises: obtaining passive audio samples of the first environment; in an instance of the obtaining of the passive audio samples where a change in a cardinality of a number of speakers present in the first environment based on the passive audio samples is identified: obtaining presence data for the user; in a first instance of the obtaining where the presence data indicates that the user is continuously present with respect to the data processing system: concluding that no prescribed event has occurred; and in a second instance of the obtaining where the presence data indicates that the user is not continuously present with respect to the data processing system: concluding that an occurrence of the occurrences of the prescribed event has occurred.
10 . The method of claim 7 , further comprising: setting a rate of the monitoring based on presence of the user with respect to the data processing system and/or a location of the data processing system with respect to locations of a known location list.
11 . A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause operations for managing operation of a data processing system to be performed, the operations comprising: obtaining audio from a first environment around the data processing system using an audio sensor of the data processing system; classifying the audio to obtain a context for the first environment; obtaining, from a repository, at least one audio sample of a user of the data processing system while the user is present in a second environment, the at least one audio sample being classified in the context; comparing the audio to the at least one audio sample to identify a likelihood of a first voice from the audio being a voice of the user; selecting, based on the likelihood, an access control to be applied to the data processing system; and providing computer implemented services using the data processing system based on the access control.
12 . The non-transitory machine-readable medium of claim 11 , wherein the operations further comprise: obtaining location data for the data processing system, wherein the access control is also selected based on the location data.
13 . The non-transitory machine-readable medium of claim 12 , wherein selecting the access control comprises: when the likelihood falls into a first likelihood range: concluding that no access is to be granted; when the likelihood falls into a second likelihood range: concluding that full access is to be granted; and when the likelihood falls into a third range: comparing the location data to a known location list; in a first instance of the comparing where the location data indicates that the data processing system is not located at any location of the known location list: concluding that no access is to be granted, and in a second instance of the comparing where the location data indicates that the data processing system is located at one location of the known location list: concluding that limited access is to be granted.
14 . The non-transitory machine-readable medium of claim 11 , wherein the operations further comprise: prior to obtaining the audio obtaining an audio clip of the user while the user is present in a third environment; obtaining video data of the user while the audio clip is obtained; filtering the audio clip based on activity of lips of the user in the video data to obtain a new audio sample; classifying the new audio sample to obtain a second context for the third environment; and adding the new audio sample to the repository using the second context to group the new audio sample with other audio samples that also have the second context.
15 . The non-transitory machine-readable medium of claim 14 , wherein the operations further comprise: using the new audio sample and the other audio samples to obtain a representative audio sample for the second context.
16 . A data processing system, comprising: a processor; and a memory coupled to the processor to store instructions, which when executed by the processor, cause operations for managing operation of the data processing system, the operations comprising: obtaining audio from a first environment around the data processing system using an audio sensor of the data processing system; classifying the audio to obtain a context for the first environment; obtaining, from a repository, at least one audio sample of a user of the data processing system while the user is present in a second environment, the at least one audio sample being classified in the context; comparing the audio to the at least one audio sample to identify a likelihood of a first voice from the audio being a voice of the user; selecting, based on the likelihood, an access control to be applied to the data processing system; and providing computer implemented services using the data processing system based on the access control.
17 . The data processing system of claim 16 , wherein the operations further comprise: obtaining location data for the data processing system, wherein the access control is also selected based on the location data.
18 . The data processing system of claim 17 , wherein selecting the access control comprises: when the likelihood falls into a first likelihood range: concluding that no access is to be granted; when the likelihood falls into a second likelihood range: concluding that full access is to be granted; and when the likelihood falls into a third range: comparing the location data to a known location list; in a first instance of the comparing where the location data indicates that the data processing system is not located at any location of the known location list: concluding that no access is to be granted, and in a second instance of the comparing where the location data indicates that the data processing system is located at one location of the known location list: concluding that limited access is to be granted.
19 . The data processing system of claim 16 , wherein the operations further comprise: prior to obtaining the audio obtaining an audio clip of the user while the user is present in a third environment; obtaining video data of the user while the audio clip is obtained; filtering the audio clip based on activity of lips of the user in the video data to obtain a new audio sample; classifying the new audio sample to obtain a second context for the third environment; and adding the new audio sample to the repository using the second context to group the new audio sample with other audio samples that also have the second context.
20 . The data processing system of claim 19 , wherein the operations further comprise: using the new audio sample and the other audio samples to obtain a representative audio sample for the second context.

Description

FIELD Embodiments disclosed herein relate generally to system management. More particularly, embodiments disclosed herein relate to systems and methods to manage use of systems. BACKGROUND Computing devices may provide computer-implemented services. The computer-implemented services may be used by users of the computing devices and/or devices operably connected to the computing devices. The computer-implemented services may be performed with hardware components such as processors, memory modules, storage devices, and communication devices. The operation of these components and the components of other devices may impact the performance of the computer-implemented services. BRIEF DESCRIPTION OF THE DRAWINGS Embodiments disclosed herein are illustrated by way of example and not limitation in the figures of the accompanying drawings in which like references indicate similar elements. FIG. 1 shows a block diagram illustrating a system in accordance with an embodiment. FIGS. 2A-2D show diagrams illustrating data flows in accordance with an embodiment. FIG. 3 shows a flow diagram illustrating a method of providing computer implemented services in accordance with an embodiment. FIG. 4 shows a block diagram illustrating a data processing system in accordance with an embodiment. DETAILED DESCRIPTION Various embodiments will be described with reference to details discussed below, and the accompanying drawings will illustrate the various embodiments. The following description and drawings are illustrative and are not to be construed as limiting. Numerous specific details are described to provide a thorough understanding of various embodiments. However, in certain instances, well-known or conventional details are not described in order to provide a concise discussion of embodiments disclosed herein. Reference in the specification to “one embodiment” or “an embodiment” means that a particular feature, structure, or characteristic described in conjunction with the embodiment can be included in at least one embodiment. The appearances of the phrases “in one embodiment” and “an embodiment” in various places in the specification do not necessarily all refer to the same embodiment. References to an “operable connection” or “operably connected” means that a particular device is able to communicate with one or more other devices. The devices themselves may be directly connected to one another or may be indirectly connected to one another through any number of intermediary devices, such as in a network topology. In general, embodiments disclosed herein relate to methods and systems for managing operation of data processing systems. To manage the operation of the data processing systems, access controls may be enforced over time. The access controls may limit use of the data processing systems to reduce the likelihood of malicious user using the data processing systems. To decide how to enforce access controls, the data processing systems may analyze local environments to infer whether authorized or unauthorized users are likely using the data processing systems. The local environments may be analyzed by identifying (i) voices present in the environments, and (ii) types (e.g., contexts) of the environments. The contexts may be used to select basis of comparison for the voices to identify whether the voices likely correspond to authorized users. By using environments as contexts, a data processing systems in accordance with an embodiment may be more likely to accurately ascertain whether authorized users are using the data processing systems. Thus, embodiments disclosed herein may address, among others, the technical problem of use identification in complex environments. By using a type of the environment as a context, basis for comparison may be selected in a manner that is likely to result in more accurate identifications of users. Thus, the security and usability of data processing systems may be improved through more accurate user identification. In an embodiment, a method for managing operation of a data processing system is provided. The method may include obtaining audio from a first environment around the data processing system using an audio sensor of the data processing system; classifying the audio to obtain a context for the first environment; obtaining, from a repository, at least one audio sample of a user of the data processing system while the user is present in a second environment, the at least one audio sample being classified in the context; comparing the audio to the at least one audio sample to identify a likelihood of a first voice from the audio being a voice of the user; selecting, based on the likelihood, an access control to be applied to the data processing system; and providing computer implemented services using the data processing system based on the access control. The method may also include obtaining location data for the data processing system. The access control may also be selected based on the