Reinstantiating digital humans with stored session context in response to navigation to a different destination
Techniques are provided for reinstantiating digital humans with stored session context in response to navigation to a different destination. One method comprises obtaining information characterizing a user interacting with a digital human instantiated in a first destination (e.g., a webpage or a virtual environment); and, in response to a navigation from the first destination to a different destination: automatically storing session context information in a persistent session context storage based on the obtained information; and reinstantiating the digital human in the different destination with the stored session context information. A query, based on a user input, may be provided to an information retrieval system that generates query results; and a prompt for a language model may be determined based on the query results, wherein the language model generates a response comprising a first content portion comprising a first content type and a second content portion comprising a second content type.
1 . A method, comprising:
obtaining information characterizing at least one user interacting with a processor- based digital human, instantiated in at least a portion of one or more of a first destination, during a first session;
performing the following steps, in response to a navigation from the first destination to a different destination:
automatically storing session context information, of the first session, in a persistent session context storage based at least in part on the obtained information, wherein the stored session context information comprises information characterizing at least a portion of at least one prior interaction, with the at least one user, during at least one prior session; and
reinstantiating the processor-based digital human, as part of the first session, in at least a portion of the different destination with the stored session context information, wherein, following the navigation from the first destination to the different destination, the processor-based digital human responds to the at least one user using at least a portion of the stored session context information for the first session and the at least one prior session;
wherein the method is performed by at least one processing device comprising a processor coupled to a memory.
2 . The method of claim 1 , wherein the navigation from the first destination to the different destination is initiated by one or more of the at least one user and the processor-based digital human.
3 . The method of claim 1 , wherein the first destination comprises one or more of a first webpage and a first virtual environment.
4 . The method of claim 1 , wherein the processor-based digital human is instantiated in one or more of a banner portion embedded in a first webpage and a loadable portion of the first webpage that loads another webpage over at least a portion of the first webpage.
5 . The method of claim 1 , wherein the session context information is stored in the persistent session context storage with a session identifier, of the first session, used to reinstantiate the processor-based digital human in the at least the portion of the different destination with the stored session context information.
6 . The method of claim 1 , further comprising providing a query, based at least in part on an at least one input from the at least one user, to an information retrieval system that generates one or more query results; and determining a prompt for a language model based at least in part on at least one of the one or more query results, wherein the language model generates a user response, wherein the user response comprises at least a first content portion comprising a first content type and a second content portion comprising a different, second content type.
7 . The method of claim 6 , wherein the first content type comprises one or more of an audible content type and a visual content type and wherein the second content type comprises a destination address for accessing at least a portion of the second content portion.
8 . The method of claim 6 , wherein the language model separately identifies the first content type and the second content type in the prompt.
9 . The method of claim 1 , wherein the session context information for the first session and the at least one prior session is stored in one or more persistent session context slots, of at least one conversation system, prior to the reinstantiating, with a corresponding session identifier.
10 . An apparatus comprising:
at least one processing device comprising a processor coupled to a memory;
the at least one processing device being configured to implement the following steps:
obtaining information characterizing at least one user interacting with a processor-based digital human, instantiated in at least a portion of one or more of a first destination, during a first session;
performing the following steps, in response to a navigation from the first destination to a different destination:
automatically storing session context information, of the first session, in a persistent session context storage based at least in part on the obtained information, wherein the stored session context information comprises information characterizing at least a portion of at least one prior interaction, with the at least one user, during at least one prior session; and
reinstantiating the processor-based digital human, as part of the first session, in at least a portion of the different destination with the stored session context information, wherein, following the navigation from the first destination to the different destination, the processor-based digital human responds to the at least one user using at least a portion of the stored session context information for the first session and the at least one prior session.
11 . The apparatus of claim 10 , wherein the processor-based digital human is instantiated in one or more of a banner portion embedded in a first webpage and a loadable portion of the first webpage that loads another webpage over at least a portion of the first webpage.
12 . The apparatus of claim 10 , wherein the session context information is stored in the persistent session context storage with a session identifier, of the first session, used to reinstantiate the processor-based digital human in the at least the portion of the different destination with the stored session context information.
13 . The apparatus of claim 10 , further comprising providing a query, based at least in part on an at least one input from the at least one user, to an information retrieval system that generates one or more query results; and determining a prompt for a language model based at least in part on at least one of the one or more query results, wherein the language model generates a user response, wherein the user response comprises at least a first content portion comprising a first content type and a second content portion comprising a different, second content type.
14 . The apparatus of claim 13 , wherein the first content type comprises one or more of an audible content type and a visual content type and wherein the second content type comprises a destination address for accessing at least a portion of the second content portion, and wherein the language model separately identifies the first content type and the second content type in the prompt.
15 . The apparatus of claim 10 , wherein the session context information for the first session and the at least one prior session is stored in one or more persistent session context slots, of at least one conversation system, prior to the reinstantiating, with a corresponding session identifier.
16 . A non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device to perform the following steps:
obtaining information characterizing at least one user interacting with a processor- based digital human, instantiated in at least a portion of one or more of a first destination, during a first session;
performing the following steps, in response to a navigation from the first destination to a different destination:
automatically storing session context information, of the first session, in a persistent session context storage based at least in part on the obtained information, wherein the stored session context information comprises information characterizing at least a portion of at least one prior interaction, with the at least one user, during at least one prior session; and
reinstantiating the processor-based digital human, as part of the first session, in at least a portion of the different destination with the stored session context information, wherein, following the navigation from the first destination to the different destination, the processor-based digital human responds to the at least one user using at least a portion of the stored session context information for the first session and the at least one prior session.
17 . The non-transitory processor-readable storage medium of claim 16 , wherein the session context information is stored in the persistent session context storage with a session identifier, of the first session, used to reinstantiate the processor-based digital human in the at least the portion of the different destination with the stored session context information.
18 . The non-transitory processor-readable storage medium of claim 16 , further comprising providing a query, based at least in part on an at least one input from the at least one user, to an information retrieval system that generates one or more query results; and determining a prompt for a language model based at least in part on at least one of the one or more query results, wherein the language model generates a user response, wherein the user response comprises at least a first content portion comprising a first content type and a second content portion comprising a different, second content type.
19 . The non-transitory processor-readable storage medium of claim 18 , wherein the first content type comprises one or more of an audible content type and a visual content type and wherein the second content type comprises a destination address for accessing at least a portion of the second content portion, and wherein the language model separately identifies the first content type and the second content type in the prompt.
20 . The non-transitory processor-readable storage medium of claim 16 , wherein the session context information for the first session and the at least one prior session is stored in one or more persistent session context slots, of at least one conversation system, prior to the reinstantiating, with a corresponding session identifier.