GENERATING A RESPONSE TO A NATURAL LANGUAGE COMMAND BASED ON A CONCATENATED GRAPH

• US 20180349353A1
• Filed: 06/05/2017
• Published: 12/06/2018
• Est. Priority Date: 06/05/2017
• Status: Active Grant

• Current Assignee: Lenovo PC International Limited (Lenovo Group Ltd.)
• Original Assignee: Lenovo Singapore Pte Limited (Lenovo Group Ltd.)
• Inventors: Qian, Ming, Kumar, Jatinder, Nicholson, John Weldon, Schwarz, David Alexander, Wang, Song
• Granted Patent: US 10,789,425 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 40/216 using statistical methods
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06T 11/206 Drawing of charts or graphs
• CPC Class Codes: G06T 11/60 Editing figures and text; Combining figures or text

Abstract

For generating a response to a natural language command based on a concatenated graph, a processor identifies one or more relevant data sets in response to a natural language command received from an input device. Each relevant data set includes one of a subject of the natural language command and a subject of another relevant data set. The processor further generates a graph for each of the one or more relevant data sets and concatenates the graphs into a concatenated graph. In addition, the processor generates a response to the natural language command based on the concatenated graph.

Claims

1. An apparatus comprising:

an input device;

a processor;

a memory that stores code executable by the processor to;

identify two or more relevant data sets in response to a natural language command received from the input device, wherein a first relevant data set comprises a first subject of the natural language command and a second relevant data set comprises a second subject of the first relevant data set;

generate a graph for each of the two or more relevant data sets;

concatenate the graphs into a concatenated graph by merging the second subject of a first graph for the first relevant data set and the second subject of a second graph for the second relevant data set; and

generate a response to the natural language command based on the concatenated graph.

2. The apparatus of claim 1, wherein the code is further executable by the processor to:

display the concatenated graph; and

receive edits to the concatenated graph.

3. The apparatus of claim 1, wherein each graph comprises two or more of the subjects and one or more relationships between the two or more subjects.

4. The apparatus of claim 3, wherein the code is further executable by the processor to:

determine one or more solution sets from the concatenated graph;

calculate a solution score for each solution set; and

select a solution set with a highest solution score for the response.

5. The apparatus of claim 4, wherein the selected solution set is selected as a function of the solution score and a solution cost.

6. The apparatus of claim 3, wherein the code is further executable by the processor to prune irrelevant subjects.

7. (canceled)

8. A method comprising:

identifying, by use of a processor, two or more relevant data sets in response to a natural language command, wherein a first relevant data set comprises a first subject of the natural language command and a second relevant data set comprises a second subject of the first relevant data set;

generating a graph for each of the two or more relevant data sets;

concatenating the graphs into a concatenated graph by merging the second subject of a first graph for the first relevant data set and the second subject of a second graph for the second relevant data set; and

generating a response to the natural language command based on the concatenated graph.

9. The method of claim 8, the method further comprising:

displaying the concatenated graph; and

receive edits to the concatenated graph.

10. The method of claim 8, wherein each graph comprises two or more of the subjects and one or more relationships between the two or more subjects.

11. The method of claim 10, the method further comprising:

determining one or more solution sets from the concatenated graph;

calculating a solution score for each solution set; and

selecting a solution set with a highest solution score for the response.

12. The method of claim 11, wherein the selected solution set is selected as a function of the solution score and a solution cost.

13. The method of claim 10, the method further comprising pruning irrelevant subjects.

14. (canceled)

15. A program product comprising a non-transitory computer readable storage medium that stores code executable by a processor to perform:

identifying two or more relevant data sets in response to a natural language command, wherein a first relevant data set comprises a first subject of the natural language command and a second relevant data set comprises a second subject of the first relevant data set;

generating a graph for each of the two or more relevant data sets;

concatenating the graphs into a concatenated graph by merging the second subject of a first graph for the first relevant data set and the second subject of a second graph for the second relevant data set; and

generating a response to the natural language command based on the concatenated graph.

16. The program product of claim 15, the processor further performing:

displaying the concatenated graph; and

receive edits to the concatenated graph.

17. The program product of claim 15, wherein each graph comprises two or more of the subjects and one or more relationships between the two or more subjects.

18. The program product of claim 17, the processor further performing:

determining one or more solution sets from the concatenated graph;

calculating a solution score for each solution set; and

selecting a solution set with a highest solution score for the response.

19. The program product of claim 18, wherein the selected solution set is selected as a function of the solution score and a solution cost.

20. The program product of claim 17, the processor further pruning irrelevant subjects.