Personalized modification of audio and visual components of a virtual agent of a user interface
Systems, methods and/or computer program products personalizing user interactions with virtual agents of applications and/or services, using audio/visual components customized to appeal to user preferences. Upon initial interaction with virtual agents, AI ranking algorithms are triggered to adopt the highest ranked persona for the virtual agent based on previous positive interactions with the user, learned preferences, the user's state inferred from facial expressions, body language, tone. Personas can emulate voice signatures of popular characters, actors, celebrities and sports figures, and access a corpus of dialogue of the available personas to learn unique speech patterns, slang, tone, grammar, speed, and vocabulary. The corpus that comprises various personas of real and/or fictional individuals can include data of the mannerisms and visual likeness of the various characters and people, allowing avatars depicting the virtual agents to be animated in the likeness of the selected persona in real-time during conversational workflows.
1 . A computer-implemented method, the computer-implemented method comprising:
receiving, by a processor, an engagement with a virtual agent of a user interface by a user;
triggering, by the processor, in response to the engagement of the virtual agent, a selection of a persona for the virtual agent, wherein selection of the persona comprises:
collecting, by the processor, real-time data of an application or service running the user interface and historical data about the user from one or more data sources and a corpus of available personas, wherein each of the available personas comprises audio components or visual components that modify a visual appearance or audio presentation of the virtual agent on the user interface;
applying, by the processor, a ranking algorithm to the available personas, wherein the ranking algorithm ranks the available personas based on features that most closely align with preferences of the user; and
selecting, by the processor, a highest ranked persona from the ranked available personas;
modifying, by the processor, settings and behaviors of the virtual agent with one of more of the audio components or visual components in accordance with the selected persona;
guiding, by the processor, the user through a workflow presented by the user interface via the modified virtual agent;
generating, by the processor, a response to an input from the user during the workflow, the response comprising a behavior or action to be executed by the modified virtual agent, wherein the selecting the behavior or action comprises:
ranking, by the processor, behaviors or actions implemented by the selected persona that are predicted, based on previous conversations with the user, to increase engagement or satisfaction of the user during the guided workflow;
determining, by the processor, that a highest ranked behavior or action from the ranked behaviors or actions is a repeat behavior or action; and
in response to determining, based on the previous conversations, that a previous response of the user to the repeat behavior or action was below a threshold level of positive reaction, selecting a next highest ranked behavior or action to execute by the modified virtual agent; and
outputting, by the processor, the response to the user via the user interface using the persona of the virtual agent to implement the selected behavior or action.
2 . The computer-implemented method of claim 1 , wherein modifying settings and behaviors of the virtual agent with audio components includes applying a voice signature to the virtual agent that mimics speech or dialog patterns of a real or fictious character or person.
3 . The computer-implemented method of claim 2 , wherein the speech or dialog patterns applied to the virtual agent modify speech output of the virtual agent selected from the group consisting of slang, tone, grammar, speed, vocabulary, use of adjectives and combinations thereof.
4 . The computer-implemented method of claim 1 , wherein the ranking algorithm weights previously used personas that have previously been used to interact with the user via the user interface lower in the ranking than unused personas.
5 . The computer-implemented method of claim 2 , wherein modifying the settings and the behaviors of the virtual agent with visual components comprises:
animating, by the processor, a visual avatar for the virtual agent, displayed by the user interface, wherein the visual avatar corresponds to the real or the fictitious character or person associated with the voice signature applied to the virtual agent.
6 . The computer-implemented method of claim 1 , further comprising:
querying, by the processor, a corpus of real-time or near real-time events occurring during a present time period;
ranking, by the processor, the real-time or near real-time events in correlation to preferences of the user;
determining, by the processor, that a highest-ranked real-time or near real-time event meets or exceeds a threshold level of correlation to the preferences of the user; and
in response to the determining, incorporating, by the processor, information describing the highest-ranked real-time or near real-time event into the behavior or action outputted by the virtual agent via the user interface.
7 . A computer system comprising:
a processor; and
a computer-readable storage media coupled to the processor, wherein the computer-readable storage media contains program instructions executing, via the processor, a computer-implemented method comprising:
receiving, by the processor, an engagement with a virtual agent of a user interface by a user;
triggering, by the processor, in response to the engagement of the virtual agent, a selection of a persona for the virtual agent, wherein selection of the persona comprises:
collecting, by the processor, real-time data of an application or service running the user interface and historical data about the user from one or more data sources and a corpus of available personas, wherein each of the available personas comprises audio components or visual components that modify a visual appearance or audio presentation of the virtual agent on the user interface;
applying, by the processor, a ranking algorithm to the available personas, wherein the ranking algorithm ranks the available personas based on features that most closely align with preferences of the user; and
selecting, by the processor, the persona from the ranking of available personas that is ranked highest by the ranking algorithm for the user;
modifying, by the processor, settings and behaviors of the virtual agent with one of more of the audio components or visual components in accordance with the selected persona;
guiding, by the processor, the user through a workflow presented by the user interface via the modified virtual agent;
generating, by the processor, a response to an input from the user during the workflow, the response comprising a behavior or action to be executed by the modified virtual agent, wherein the selecting the behavior or action comprises:
ranking, by the processor, behaviors or actions implemented by the selected persona that are predicted, based on previous conversations with the user, to increase engagement or satisfaction of the user during the guided workflow;
determining, by the processor, that a highest ranked behavior or action from the ranked behaviors or actions is a repeat behavior or action; and
in response to determining, based on the previous conversations, that a previous response of the user to the repeat behavior or action was below a threshold level of positive reaction, selecting a next highest ranked behavior or action to execute by the modified virtual agent; and
outputting, by the processor, the response to the user via the user interface using the modified virtual agent to implement the selected behavior or action.
8 . The computer system of claim 7 , wherein modifying settings and behaviors of the virtual agent with audio components includes applying a voice signature to the virtual agent that mimics speech or dialog patterns of a real or fictious character or person.
9 . The computer system of claim 8 , wherein the speech or dialog patterns applied to the virtual agent modify speech output of the virtual agent selected from the group consisting of slang, tone, grammar, speed, vocabulary, use of adjectives and combinations thereof.
10 . The computer system of claim 7 , wherein the ranking algorithm weights previously used personas that have previously been used to interact with the user via the user interface lower in the ranking than unused personas.
11 . The computer system of claim 8 , wherein modifying the settings and the behaviors of the virtual agent with visual components comprises:
animating, by the processor, a visual avatar for the virtual agent, displayed by the user interface, wherein the visual avatar corresponds to the real or the fictitious character or person associated with the voice signature applied to the virtual agent.
12 . The computer system of claim 8 , further comprising:
querying, by the processor, a corpus of real-time or near real-time events occurring during a present time period;
ranking, by the processor, the real-time or near real-time events in correlation to preferences of the user;
determining, by the processor, that a highest-ranked real-time or near real-time event meets or exceeds a threshold level of correlation to the preferences of the user; and
in response to the determining, incorporating, by the processor, information describing the highest-ranked real-time or near real-time event into the behavior or action outputted by the virtual agent via the user interface.
13 . A computer program product comprising:
one or more computer readable storage media having computer-readable program instructions stored on the one or more computer readable storage media, said program instructions executes a computer-implemented method comprising:
receiving, by a processor, an engagement with a virtual agent of a user interface by a user;
triggering, by the processor, in response to the engagement of the virtual agent, a selection of a persona for the virtual agent, wherein selection of the persona comprises:
collecting, by the processor, real-time data of an application or service running the user interface and historical data about the user from one or more data sources and a corpus of available personas, wherein each of the available personas comprises audio components or visual components that modify a visual appearance or audio presentation of the virtual agent on the user interface;
applying, by the processor, a ranking algorithm to the available personas, wherein the ranking algorithm ranks the available personas based on features that most closely align with preferences of the user; and
selecting, by the processor, a highest ranked persona from the ranked available personas;
modifying, by the processor, settings and behaviors of the virtual agent with one of more of the audio components or visual components in accordance with the selected persona;
guiding, by the processor, the user through a workflow presented by the user interface via the modified virtual agent;
generating, by the processor, a response to an input from the user during the workflow, the response comprising a behavior or action to be executed by the modified virtual agent, wherein the selecting the behavior or action comprises:
ranking, by the processor, behaviors or actions implemented by the selected persona that are predicted, based on previous conversations with the user, to increase engagement or satisfaction of the user during the guided workflow;
determining, by the processor, that a highest ranked behavior or action from the ranked behaviors or actions is a repeat behavior or action; and
in response to determining, based on the previous conversations, that a previous response of the user to the repeat behavior or action was below a threshold level of positive reaction, selecting a next highest ranked behavior or action to execute by the modified virtual agent; and
outputting, by the processor, the response to the user via the user interface using the modified virtual agent to implement the selected behavior or action.
14 . The computer program product of claim 13 , wherein modifying settings and behaviors of the virtual agent with audio components includes applying a voice signature to the virtual agent that mimics speech or dialog patterns of a real or fictious character or person.
15 . The computer program product of claim 14 , wherein the speech or dialog patterns applied to the virtual agent modify speech output of the virtual agent selected from the group consisting of slang, tone, grammar, speed, vocabulary, use of adjectives and combinations thereof.
16 . The computer program product of claim 14 , wherein modifying the settings and the behaviors of the virtual agent with visual components comprises:
animating, by the processor, a visual avatar for the virtual agent, displayed by the user interface, wherein the visual avatar corresponds to the real or the fictitious character or person associated with the voice signature applied to the virtual agent.
17 . The computer program product of claim 13 further comprising:
querying, by the processor, a corpus of real-time or near real-time events occurring during a present time period;
ranking, by the processor, the real-time or near real-time events in correlation to preferences of the user;
determining, by the processor, that a highest-ranked real-time or near real-time event meets or exceeds a threshold level of correlation to the preferences of the user; and
in response to the determining, incorporating, by the processor, information describing the highest-ranked real-time or near real-time event into the behavior or action outputted by the virtual agent via the user interface.