Method and device for generating online question paths from existing question banks using a knowledge graph
The disclosure provides an information processing method and device. In one embodiment, an information processing method comprises receiving a request for generating questions inputted by a user, the request for generating questions includes a to-be-learned knowledge point; acquiring, from a knowledge graph for questions, a node path including a target node indicating the to-be-learned knowledge point, the nodes in the knowledge graph for questions indicating question-answering steps of existing questions, knowledge points tested in the question-answering steps, and questioning styles corresponding to the question-answering steps; and generating questions required by the user according to question-answering steps, knowledge points tested in the question-answering steps, and questioning styles corresponding to the question-answering steps indicated by nodes on the node path. The present disclosure enables generation of new questions and facilitates the expansion of a question bank.
1. A method comprising:
generating, by a server device, a knowledge graph representing question-answering steps extracted from a set of existing questions in a question bank;
receiving, at the server device, a request for generating questions from a client device;
calculating, at the server device, a path within the knowledge graph of questions, the path including a target node representing a knowledge point and a set of nodes representing question-answering steps, knowledge points, and questioning styles;
generating, by the server device, a series of questions based on the set of nodes, the series of questions comprising new questions not stored in the question bank;
storing, by the server device, the series of questions in the question bank; and
transmitting, by the server device, the series of questions to the client device in response to the request for generating questions.
2. The method of claim 1 , the receiving a request for generating questions from a client device comprising receiving, by the server device, a to-be-learned knowledge point from the client device and using the to-be-learned knowledge point as the target node.
3. The method of claim 1 , the calculating a path within a knowledge graph of questions further comprising:
selecting, by the server device, a starting node and an ending node in the knowledge graph; and
calculating, by the server device, a path passing through the target node from the starting node to the ending node.
4. The method of claim 1 , further comprising calculating, by the server device, a set of candidate paths in the knowledge graph, the set of candidate paths including the calculated path.
5. The method of claim 4 , further comprising selecting, by the server device, the path from the set of candidate paths by randomly selecting the path.
6. The method of claim 4 , further comprising selecting, by the server device, the path from the set of candidate paths by ranking the candidate paths and selecting the path if the path is the highest: ranking path.
7. The method of claim 4 , the calculating a set of candidate paths in the knowledge graph comprising calculating, by the server device, a set of candidate paths, each candidate path including a plurality of nodes, each node in the pluralities of nodes having the same questioning style.
8. The method of claim 1 , the calculating a path within a knowledge graph of questions comprising calculating, by the server device, a path length for the path based on a difficulty of a knowledge point included within the request for generating questions.
9. A method comprising
retrieving, by a server device, a set of questions from a question bank, each question in the set of questions including at least one question-answering step;
parsing, by the server device, the question-answering steps associated with the set of questions to generate a set of nodes, each node including knowledge points and a questioning style;
marking, by the server device, connection relationships between each node in the set of nodes;
generating, by the server device, a series of questions based on the connection relationships, the series of questions comprising new questions not stored in the question bank; and
storing, by the server device, the series of questions in the question bank.
10. The method of claim 9 , the marking connection relationships between each node in the set of nodes comprising establishing, by the server device, connection relationships between question-answering steps of different questions in the set of questions.
11. The method of claim 9 , further comprising assigning, by the server device, an input, process, output, questioning style, difficulty level, and knowledge point attribute extracted from the question-answering step to a given node in the set of nodes.
12. The method of claim 9 , further comprising merging, by the server device, a plurality of nodes in the set of nodes to form a combined node, the plurality of nodes representing a similar question-answering step.
13. The method of claim 12 , the merging further comprising merging, by the server device, the plurality of nodes using a fuzzy rule, the fuzzy rule identifying question-answering steps having shared knowledge points.
14. The method of claim 12 , the combined node including multiple questioning style attributes and multiple difficulty levels.
15. A device comprising:
a processor; and
a non-transitory computer-readable storage medium for tangibly storing thereon program logic for execution by the processor, the stored program logic comprising:
logic, executed by the processor, for generating a knowledge graph representing question-answering steps extracted from a set of existing questions in a question bank;
logic, executed by the processor, for receiving a request for generating questions from a client device;
logic, executed by the processor, for calculating a path within the knowledge graph of questions, the path including a target node representing a knowledge point and a set of nodes representing question-answering steps, knowledge points, and questioning styles; and
logic, executed by the processor, for generating a series of questions based on the set of nodes, the series of questions comprising new questions not stored in the question bank;
logic, executed by the processor, for storing the series of questions in the question bank; and
logic, executed by the processor, for transmitting the series of questions to the client device in response to the request for generating questions.
16. The device of claim 15 , further comprising logic, executed by the processor, for calculating a set of candidate paths in the knowledge graph, the set of candidate paths including the calculated path.
17. The device of claim 16 , the logic for calculating a set of candidate paths in the knowledge graph comprising logic, executed by the processor, for calculating a set of candidate paths, each candidate path including a plurality of nodes, each node in the pluralities of nodes having the same questioning style.
18. The device of claim 15 , the logic for calculating a path within a knowledge graph of questions comprising logic, executed by the processor, for calculating a path length for the path based on a difficulty of a knowledge point included within the request for generating questions.
19. The device of claim 15 , the logic further comprising
logic, executed by the processor, for retrieving a set of questions from a question bank, each question in the set of questions including at least one question-answering step;
logic, executed by the processor, for parsing the question-answering steps associated with the set of questions to generate a set of nodes, each node including knowledge points and a questioning style; and
logic, executed by the processor, for marking connection relationships between each node in the set of nodes.
20. The device of claim 19 , the logic further comprising logic, executed by the processor, for merging a plurality of nodes in the set of nodes to form a combined node, the plurality of nodes representing a similar question-answering step.