# US 2006/0153345 A1 · System and method for speech-enabled call routing

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2006/0153345 A1
- Document ID: US20060153345A1
- Status: Published application
- Kind: A1
- Application number: 11/032,495
- Filed: 2005-01-10
- Published: 2006-07-13
- Earliest claimed: 2005-01-10
- Assignees: SBC Knowledge Ventures, L.P.
- Inventors: Robert Bushey; Benjamin Knott; Sarah Korth
- Web page: https://patentgrep.com/patent/US20060153345A1

## CPC

- H04M 3/4936: {Speech interaction details (speech recognition per se G10L15/00)}
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G10L 19/0204: {using subband decomposition}
- H04M 3/523: with call distribution or queueing
- G10L 19/265: {Pre-filtering, e.g. high frequency emphasis prior to encoding}
- H04M 2201/60: Medium conversion
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A method of processing a call is disclosed. The method can transform speech input from a caller of a call into text and convert the text into an object and an action. The method determines a call destination based on the object and the action. The method can route the call to a destination when a caller is not in compliance with at least one business rule. The method can further route the call to the call destination when the caller is in compliance.

## Claims

### Claim 1

A method of processing a call comprising:
transforming speech input from a caller of a call into text;
converting the text into an object and an action;
determining a first call destination based on the objects and the action;
routing the call to a second call destination when the caller is not in compliance with at least one business rule.

### Claim 2 (depends on 1)

The method of claim 1, further comprising converting the text into a specific action and transmitting the specific action.

### Claim 3 (depends on 1)

The method of claim 1, further comprising converting the text into a specific object and transmitting the specific object.

### Claim 4 (depends on 2)

The method of claim 2, further comprising transmitting the specific object with the routed call.

### Claim 5 (depends on 1)

The method of claim 1, further comprising assigning a confidence value to the action and the object.

### Claim 6 (depends on 1)

The method of claim 1, further comprising assigning a confidence level to the action based on a probability that the action represents an intent of the caller, and assigning a confidence value to the object based on a probability that the object represents an intent of the caller.

### Claim 7 (depends on 1)

The method of claim 1, wherein the action is one of a verb and an adverb-verb combination.

### Claim 8 (depends on 1)

The method of claim 1, further comprising placing a caller in compliance with at least one business rule subsequent to routing the call to the second call destination and after the caller fulfills an obligation.

### Claim 9 (depends on 8)

The method of claim 8, further comprising routing the call based on the action and the object to the first call destination after placing the caller in compliance.

### Claim 10 (depends on 1)

The method of claim 1, further comprising routing a call based on a current destination.

### Claim 11 (depends on 1)

The method of claim 1, further comprising routing a call based on at least one of a current destination, a future destination, and a prior destination.

### Claim 12 (depends on 1)

The method of claim 1, further comprising assigning a current routing destination variable to a destination.

### Claim 13 (depends on 1)

The method of claim 1, further comprising setting a current routing destination to the call routing destination after the call is routed.

### Claim 14 (depends on 1)

The method of claim 1, further comprising setting a prior routing destination to the current routing destination.

### Claim 15 (depends on 1)

The method of claim 1, wherein the current routing destination is set to the call routing destination as determined by a selected action-object pair.

### Claim 16

A system comprising:
a call routing system having a processor, the call routing system configured to convert speech input from a caller into an object and an action;
an action-object routing module configured to determine a first destination for the call based on the object and the action;
wherein the call routing system routes the call to a second destination when the caller is not in compliance with at least one business rule.

### Claim 17 (depends on 16)

The system of claim 16, wherein the first destination is based on at least one of a selected action and a selected object.

### Claim 18 (depends on 16)

The system of claim 16, wherein the call routing system routes the call based on at least one of a current routing destination, a future routing destination and a prior routing destination.

### Claim 19 (depends on 16)

The system of claim 16, wherein the call routing system sets a future destination to the first routing destination.

### Claim 20 (depends on 16)

The system of claim 16, wherein the call routing system sets a current routing destination to the second destination.

### Claim 21 (depends on 16)

The system of claim 16, wherein the call routing system sets a prior routing destination to the current destination after the call is routed to the second destination.

### Claim 22 (depends on 16)

The system of claim 16, wherein the processor uses phonemes to convert the speech input into a textual format.

### Claim 23 (depends on 16)

The system of claim 16, wherein the processor assigns a confidence level to the textual format.

### Claim 24 (depends on 16)

The system of claim 16, further comprising a synonym table accessible to the processor.

### Claim 25

A system comprising:
an acoustic model configured to accept speech input and to produce text at its output;
a semantic model responsive to the acoustic model to produce an action and an object in responsive to the text;
a call routing module responsive to the semantic model to provide a routing destination based on the action and the object; and
wherein the routing destination is determined based on at least one of a current routing destination, a future routing destination and a prior routing destination.

### Claim 26 (depends on 25)

The system of claim 25, wherein the routing destination is determined based on a selected action and a selected object.

### Claim 27 (depends on 25)

The system of claim 25, wherein the call routing module sets a future routing destination based on a selected action and a selected object.

### Claim 28 (depends on 25)

The system of claim 25, wherein the routing module sets a current routing destination to a routing destination after it is determined that the caller violates a business rule.

### Claim 29 (depends on 25)

The system of claim 25, wherein the call routing module sets a prior routing destination to the current routing destination after the call is routed to the routing destination.
