System architecture for and method of voice processing
First Claim
1. A system architecture for efficiently distributing voice call data over a telephone network using speech recognition, the system architecture comprising:
- a) a first circuit for receiving incoming voice call data from a call, wherein the first circuit recognizes a grammar-type of the call;
b) a plurality of processing circuits configured to process the voice call data;
c) a load balancing circuit coupled each of the first circuit and the plurality of processing circuits for distributing the voice call data to a preferred processor circuit within the plurality of processors,wherein the preferred processor circuit is selected by the load balance circuit using criteria comprising the assigned grammar type and known processor efficiencies for each processor circuit for processing previously received voice call data having a same grammar type as the call.
6 Assignments
0 Petitions
Accused Products
Abstract
A system and method for efficiently distributing voice call data received from speech recognition servers over a telephone network having a shared processing resource is disclosed. Incoming calls are received from phone lines and assigned grammar types by speech recognition servers. A request for processing the voice call data is sent to a resource manager which monitors the shared processing resource and identifies a preferred processor within the shared resource. The resource manager sends an instruction to the speech recognition server to send the voice call data to a preferred processor for processing. The preferred processor is determined by known processor efficiencies for voice call data having the assigned grammar type of the incoming voice call data and a measure of processor loads. While the system is operating, the resource manger develops and updates a history of each processor. The histories include processing efficiency values for all grammar types received. The processing efficiencies are stored, tabulated and assigned usage number values for each processor. When incoming voice call data is receive, the resource manages evaluates the total sum of the usage numbers for processing requests assigned to each processor and the usage number for the grammar type of the incoming data as applied to each processor. The incoming data is distributed to the processor with the lowest sum of total of usage numbers for assigned requests and the usage number assigned to the incoming data for that processor.
-
Citations
16 Claims
-
1. A system architecture for efficiently distributing voice call data over a telephone network using speech recognition, the system architecture comprising:
-
a) a first circuit for receiving incoming voice call data from a call, wherein the first circuit recognizes a grammar-type of the call; b) a plurality of processing circuits configured to process the voice call data; c) a load balancing circuit coupled each of the first circuit and the plurality of processing circuits for distributing the voice call data to a preferred processor circuit within the plurality of processors, wherein the preferred processor circuit is selected by the load balance circuit using criteria comprising the assigned grammar type and known processor efficiencies for each processor circuit for processing previously received voice call data having a same grammar type as the call. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A system for efficiently distributing data over a telephone network using speech recognition, the system comprising:
-
a) a voice recognition unit capable of receiving call data and assigning the voice call data a grammar type; b) a processing resource coupled to the voice recognition device for processing the voice call data, the processing resource comprising a plurality of processors; c) a resource managing unit coupled to the voice recognition device and the processing resource, wherein the resource manager measures load numbers indicative of a number of processing requests issued each of the plurality of processors, wherein the resource managing unit is capable of storing processor histories for each processor within the plurality of processors and based on the processor histories and the load numbers directs the voice call data to a preferred processor within the plurality processors. - View Dependent Claims (9, 10, 11)
-
-
12. A method for distributing call data over a telephone network with a plurality of processing stations, the method comprising the steps of:
-
a) receiving voice call data from calls; b) assigning a grammar type from a set of grammar types for each call received; c) collecting processor histories for each processor within the plurality of processor, wherein the processor histories include processor efficiencies for processing each grammar type within the set of grammar types; d) measuring loads of the each processor obtain a load numbers; e) distributing calls to a processing stations within the plurality of processing stations most capable to process calls based load numbers and processing efficiencies. - View Dependent Claims (13, 14, 15)
-
-
16. An adaptive system for efficiently distributing data over a telephone network using speech recognition, the system comprising
a) means for receiving an incoming voice instructions and identifying a grammar type of the incoming voice instructions; -
b) means for issuing a processing request to have the incoming voice instructions processes; c) a set of processors c) a means to identify a processor from the set of processors which is most capable of processing the request with the grammar type; and d) a means to direct the voice instruction to the processor.
-
Specification