Distributed parser of natural language input
First Claim
1. Computing apparatus, for use with natural language input messages, comprising a network of agents, a subset of at least two of which each have a respective set of at least one interpretation policy, none of said sets of interpretation policies being identical with any other in said subset of agents, each given one of said agents in said subset of agents asserting a claim to a given one of said messages in response to detection by said given agent that a given interpretation policy of the given agent applies to said given message.
1 Assignment
0 Petitions
Accused Products
Abstract
Method and agent network architecture for processing a subject message, where each agent has a view of its own domain of responsibility. An initiator agent which receives a user-input request and does not itself have a relevant interpretation policy, queries its downchain agents whether the queried agent considers such message to be in its domain of responsibility. Each queried agent recursively determines whether it has an interpretation policy of its own that applies to the request, and if not, further queries its own further downchain neighboring agents. The further agents eventually respond to such further queries, thereby allowing the first-queried agents to respond to the initiator agent. The recursive invocation of this procedure ultimately determines one or more paths through the network from the initiator agent to one more more leaf agents. The request is then transmitted down the path(s), with each agent along the way taking any local action thereon and passing the message on to the next agent in the path. In the event of a contradiction, the network is often able to resolve many of such contradictions according to predetermined algorithms. If it cannot resolve a contradiction automatically, it learns new interpretation policies necessary to interpret the subject message properly. Such learning preferably includes interaction with the user (but only to the extent necessary), and preferably localizes the learning close to the correct leaf agent in the network.
36 Citations
27 Claims
- 1. Computing apparatus, for use with natural language input messages, comprising a network of agents, a subset of at least two of which each have a respective set of at least one interpretation policy, none of said sets of interpretation policies being identical with any other in said subset of agents, each given one of said agents in said subset of agents asserting a claim to a given one of said messages in response to detection by said given agent that a given interpretation policy of the given agent applies to said given message.
-
17. User-responsive apparatus comprising:
-
a user input module having an input system for receiving natural language user input and further having an output port for outputting user messages in response to the user input received by said user input module;
a network of computational agents including a plurality of agents each responsible for recognizing respective natural language characteristics in said user messages, at least two of said agents being responsible for recognizing respective distinct natural language characteristics in said user messages, said network having a network output port and providing network output signals on said network output port in response to at least some user messages; and
a device which performs predefined functions in response to predefined ones of said network output signals. - View Dependent Claims (18, 19, 20, 21, 22, 23, 24, 25, 26, 27)
-
Specification
-
- Resources
-
Current AssigneeiAnywhere Solutions Incorporated (SAP SE)
-
Original AssigneeDejima, Inc. (SAP SE)
-
InventorsHodjat, Babak, Savoie, Christopher J., Amamiya, Makoto
-
Primary Examiner(s)Coulter, Kenneth R.
-
Application NumberUS10/004,042Publication NumberTime in Patent Office973 DaysField of Search709/201, 709/202, 706/10, 706/11US Class Current709/202CPC Class CodesG06N 5/043 Distributed expert systems;...
