Interoperable Composite Data Units for use in Distributed Computing Execution Environments
Disclosed implementations provide executable models, such as artificial intelligence models that can be owned, traded, and used in various execution environments. By coupling a model with a strictly defined interface definition, the model can be executed in various execution environments that support the interface. Coupling the model with a non-fungible cryptographic token allows the model and other components to be owned and traded as a unit. The tradeable composite units have utility across multiple supported execution environments, such as video game environments, chat bot environments and financial trading environments. Additionally, the interface allows for the creation of pipelines and systems from multiple complementary composite units.
1 . Non-transitory computer readable media for providing an Agent for an execution environment, the media including software modules recorded thereon, the modules comprising:
a content-addressed model module including an Artificial Intelligence (AI) agent model that, when executed within an execution environment, performs tasks within the execution environment, wherein the AI agent model is capable of learning based on activity within the execution environment;
an interface definition module specifying an interface that is used by the execution environment to communicate with the AI agent model; and
an identifier module specifying an identifier which identifies the AI agent within the execution environment.
2 . The non-transitory computer readable media of claim 1 , wherein the identifier is a unique address assigned to the AI Agent model.
3 . The non-transitory computer readable medium of claim 2 , where the address is an address on a decentralized ledger.
4 . The non-transitory computer readable media of claim 1 , wherein the interface specifies a finite set of inputs and outputs for the computation model.
5 . The non-transitory computer readable media of claim 1 , further comprising a data structure that contains a set of values that define characteristics of the AI agent to thereby have an effect on behavior of the AI agent within the execution environment.
6 . The non-transitory computer readable media of claim 5 , wherein values in the set of values is mapped to an input of the AI agent model.
7 . The non-transitory computer readable media of claim 5 , wherein the values are changed as a result of activity of the AI agent within the execution environment.
8 . The non-transitory computer readable media of claim 1 , wherein the tasks within the execution environment include performing tasks of a character and wherein the execution environment is at least one of a game environment or a metaverse environment.
9 . A method for creating an Agent for an execution environment, the method comprising:
providing a content-addressed model module including an Artificial Intelligence (AI) agent model that, when executed within an execution environment, performs tasks within the execution environment, wherein the AI agent model is capable of learning based on activity within the execution environment;
providing an interface definition module specifying an interface that is used by the execution environment to communicate with the AI agent model; and
providing an identifier module specifying an identifier which identifies the AI agent within the execution environment.
10 . The method of claim 9 , wherein the identifier is a unique address assigned to the AI Agent model.
11 . The of claim 10 , where the address is an address on a decentralized ledger.
12 . The method of claim 9 , wherein the interface specifies a finite set of inputs and outputs for the computation model.
13 . The method of claim 9 , further comprising a data structure that contains a set of values that define characteristics of the AI agent to thereby have an effect on behavior of the AI agent within the execution environment.
14 . The method of claim 13 , wherein values in the set of values is mapped to an input of the AI agent model.
15 . The method of claim 13 , wherein the values are changed as a result of activity of the AI agent within the execution environment.
16 . The method of claim 9 , wherein the tasks within the execution environment include performing tasks of a character and wherein the execution environment is at least one of a game environment or a metaverse environment.