System and method for natural language processing

• US 9,104,780 B2
• Filed: 03/15/2013
• Issued: 08/11/2015
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Kamazooie Development Corporation
• Original Assignee: Kamazooie Development Corporation
• Inventors: Ritchie, Brian Douglas, Ritchie, Jared Brian, Ritchie, William Lark
• Primary Examiner(s): To, Baoquoc N
• Application Number:
  US13/833,584
• Publication Number:
  US 20140280210A1
• Time in Patent Office: 879 Days
• Field of Search: 707/797
• US Class Current: 1/1
• CPC Class Codes: G06F 16/9024 Graphs; Linked lists G06F16/9027 takes precedence
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

According to embodiments described in the specification, systems and methods are provided for natural language processing. A method in a server includes receiving, at the network interface device, an input for response from an electronic device, parsing the input to identify one or more entity data values and one or more relationship data values, populating a graph data structure with the identified entity data values, and the relationship data values, wherein the populating includes applying evaluation criteria-rating pair values, traversing the graph data structure to identify one or more problems indicated by the evaluation criteria-rating pair values, in response to the traversing, determining one or more changes to the graph data structure to satisfy one or more identified problems, if the determination is affirmative, populating a solution graph data structure that satisfies one or more identified problems, and transmitting, to the electronic device, a response to the input.

Claims

1. A method in a server having a processor, a memory, and a network interface device comprising:

storing, in the memory, a graph data structure comprising a plurality of nodes, each node associated with an entity data value, and a plurality of links, wherein each link connects two nodes and is associated with a relationship data value and one or more evaluation criteria-rating pair values;

receiving, at the network interface device, an input for response from an electronic device;

parsing the input to identify one or more entity data values and one or more relationship data values;

populating the graph data structure with the identified entity data values, and the relationship data values, wherein the populating includes applying evaluation criteria-rating pair values;

traversing the graph data structure to identify one or more problems indicated by the evaluation criteria-rating pair values;

in response to the traversing, determining one or more changes to the graph data structure to satisfy one or more of the identified problems;

when the determination is affirmative, populating a solution graph data structure that satisfies one or more of the identified problems; and

transmitting, to the electronic device, a response to the input.

2. The method of claim 1 wherein the response comprises a natural language representation of the solution graph data structure.

3. The method of claim 1 wherein the input for response is selected from one of:

a text input, a speech-to-text input, and an audio-video input.

4. The method of claim 3 wherein the response is calculated and formatted according to a motivation data value.

5. The method of claim 4 wherein the motivation data value is selected from one of:

a conversational data value, an educational/research data value, and a consultative/counseling data value.

6. The method of claim 5 wherein the response is selected from one of:

a text response, a text-to-speech response, and an audio-video response.

7. The method of claim 6 wherein the evaluation criteria-rating pair values are generated by accessing a metadata database comprising pre-determined individual personal values.

8. The method of claim 1 wherein the problems are identified when, after traversing, a calculation including a rating pair value of the evaluation criteria-rating pair values is a negative value.

9. The method of claim 1 wherein the evaluation criteria-rating pair values are generated by accessing a metadata database comprising pre-determined individual personal values.

10. The method of claim 1 wherein the electronic device is selected from one of:

a desktop computer, a smart phone, a laptop computer, and a tablet computer.

11. A system comprising:

a server having a processor and connected to a network interface device and a memory, wherein the processor is configured to;

store, in the memory, a graph data structure comprising a plurality of nodes, each node associated with an entity data value, and a plurality of links, wherein each link connects two nodes and is associated with a relationship data value and one or more evaluation criteria-rating pair values;

receive, at the network interface device, an input for response from an electronic device;

parse the input to identify one or more entity data values and one or more relationship data values;

populate the graph data structure with the identified entity data values, and the relationship data values, wherein the populating includes applying evaluation criteria-rating pair values;

traverse the graph data structure to identify one or more problems indicated by the evaluation criteria-rating pair values;

in response to the traversing, determine at least one change to the graph data structure to satisfy one of the identified problems; and

when the determination is affirmative, populate a solution graph data structure that satisfies the one of the identified problems.

12. The system of claim 11 wherein the electronic device is selected from one of:

a desktop computer, a smart phone, a laptop computer, and a tablet computer and wherein the processor is configured to transmit, to the electronic device, a response to the input.

13. The system of claim 11 wherein the electronic device is a crawling engine and wherein the processor is configured to transmit, to a solution database for further evaluation, a response to the input.