US 2026/0093558 A1Published application

System and method for fulfilling service request using computing nodes

AssigneeAssmbl.Ai Limited

InventorHumayun Munir Sheikh

Life of this patent

Estimating the term…

Loading patent…

Abstract

Disclosed is system for fulfilling service request using computing nodes. The system comprises a decentralized computing network, comprising computing nodes operating as autonomous agents, configured to implement software framework comprising: client-agent device configured to: receive service request and generate objective therefor, and send objective to agent-device configured to send queries to a machine learning model agent and/or obtain tasks, and list of autonomous agents associated with objective; and processing arrangement configured to: generate directed acyclic graph (DAG) having nodes representing first task and edges representing dependency of first task on second task(s) amongst tasks, and initialize Bloom filter of each node to track completion status of second task(s). Autonomous agent is configured to: identify second task(s), check completion status of second task(s), using Bloom filter of first task, upon completion of second task(s), execute first task, and update Bloom filter.

Claims10

Dependent claims

A system (100) for fulfilling a service request (114) using computing nodes, the system comprising a decentralized computing network (104) configured to implement a software framework (102), wherein the decentralized computing network comprises a plurality of computing nodes (106A-B) configured to operate as autonomous agents (AAs) (108A-B), which are configured to execute a plurality of modular and extensible software modules (110A-B), wherein the autonomous agents are communicably coupled with each other, wherein the software framework comprises:

a client-agent device (client-AA) (112) comprising a software application configured to:
receive the service request and generate an objective (116) associated with the service request, wherein the objective is in a form of one or more vectors recorded in a vector database, and
send the objective to an agent-device (AA) (118), wherein the agent-device comprises a context-builder software module (120) configured to upon receiving the objective, send one or more queries to a machine learning model agent (ML-Model AA) and/or to access the vector database to obtain a plurality of tasks (122) associated with the objective, and obtain a list of a plurality of autonomous agents (124) that are associated with the objective;
a processing arrangement (126) configured to:
generate a directed acyclic graph (DAG) (128), wherein each node in the DAG represents a first task amongst the plurality of tasks and each edge in the DAG represents a dependency of the first task on a second task amongst the plurality of tasks, and
initialize a Bloom filter (130) associated with each node of the DAG to track a completion status of each of at least one second task on which the first task is dependent;
wherein each autonomous agent amongst the plurality of autonomous agents is configured to:
identify the at least one second task on which the first task associated to said autonomous agent is dependent, based on the DAG,
check the completion status of each of the identified at least one second task, using the Bloom filter associated with the given task,
upon successful completion of each of the identified at least one second task, execute the first task, and
update the Bloom filter associated with the first task.

8 more elements

A method for fulfilling a service request (114) using computing nodes, the method comprising:

implementing a software framework (102), via a decentralized computing network (104), wherein the decentralized computing network comprises a plurality of computing nodes (106A-B) configured to operate as autonomous agents (AAs) (108A-B), which are configured to execute a plurality of modular and extensible software modules (110A-B), wherein the autonomous agents are communicably coupled with each other;
receiving, at a client-agent device (client-AA) (112) comprising a software application, the service request and generating an objective (116) associated with the service request, wherein the objective is in a form of one or more vectors recorded in a vector database;
sending the objective from the client-AA to an agent-device (AA) (118), wherein the agent-device comprises a context-builder software module (120) configured to upon receiving the objective, send one or more queries to a machine learning model agent (ML-Model AA) and/or to access the vector database to obtain a plurality of tasks (122) associated with the objective, and obtain a list of a plurality of autonomous agents (124) that are associated with the objective;
generating a directed acyclic graph (DAG) (128), wherein each node in the DAG represents a first task amongst the plurality of tasks and each edge in the DAG represents a dependency of the first task on a second task amongst the plurality of tasks, using a processing arrangement (126);
initializing a Bloom filter (130) associated with each node of the DAG to track a completion status of each of at least one second task on which the first task is dependent, using the processing arrangement;
identifying the at least one second task on which the first task associated to said autonomous agent is dependent, based on the DAG;
checking the completion status of each of the identified at least one second task, using the Bloom filter associated with the first task;
upon successful completion of each of the identified at least one second task, executing the first task;
and
updating the Bloom filter associated with the first task.

7 more elements

Dependencies are inferred from the claim text.

Facts

Application: 18/903,066Filed 1 Oct 2024
Published: 2 Apr 2026
Term ends: Not estimatedThe source records don’t support an estimate.

Classification8 codes

G06F 9/5038
The resource being a machine, e.g. CPUs, Servers, Terminals: considering the execution order of a plurality of tasks, e.g. taking priority or time…
G06F 9/52
Multiprogramming arrangements: program synchronisation; Mutual exclusion, e.g. by means of semaphores
G06F 9/4881
By program, e.g. task dispatcher, supervisor, operating system: scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
G06F 9/5027
To service a request: the resource being a machine, e.g. CPUs, Servers, Terminals

Family

No related US applications are recorded in the indexed filing history.

Timeline

Citations

Open elsewhere

Building an agent or pulling many patents? Use the API or MCP server instead of scraping pages. Get an API key