CN114020894B - Intelligent evaluation system capable of realizing multi-wheel interaction - Google Patents
Intelligent evaluation system capable of realizing multi-wheel interaction Download PDFInfo
- Publication number
- CN114020894B CN114020894B CN202111311891.9A CN202111311891A CN114020894B CN 114020894 B CN114020894 B CN 114020894B CN 202111311891 A CN202111311891 A CN 202111311891A CN 114020894 B CN114020894 B CN 114020894B
- Authority
- CN
- China
- Prior art keywords
- dialogue
- answer
- evaluation
- user
- round
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 45
- 230000003993 interaction Effects 0.000 title claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000012854 evaluation process Methods 0.000 claims abstract description 6
- 239000013598 vector Substances 0.000 claims description 14
- 238000000034 method Methods 0.000 claims description 11
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 7
- 230000001960 triggered effect Effects 0.000 claims description 4
- 238000013145 classification model Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000007474 system interaction Effects 0.000 claims description 2
- 238000012360 testing method Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3346—Query execution using probabilistic model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Educational Technology (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Probability & Statistics with Applications (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Electrically Operated Instructional Devices (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses an intelligent evaluation system capable of realizing multi-round interaction, which is characterized by comprising an answer intelligent processing sub-module, a multi-round dialogue sub-module, a dialogue management sub-module and a knowledge base management sub-module which are interconnected with an intelligent terminal. The system can be used for on-site evaluation in teaching, and can quickly and automatically acquire the mastering degree of a learner on knowledge points; meanwhile, for a learner, even if the teacher is not at the side, through the multi-round interaction link in the evaluation process, the user can deepen knowledge points, the teacher can clearly know the mastering condition of the classmates on course contents, so that the interactivity is improved, and the learning efficiency and the teaching efficiency are improved.
Description
Technical Field
The invention relates to the technical field of intelligent mobile terminal application development, in particular to an intelligent evaluation system capable of realizing multi-round interaction.
Background
Along with the development of informatization experiment teaching of universities, the digital learning trend is increasingly obvious, and learning is performed at any time and any place through a mobile phone client, so that the digital learning trend also becomes the hot tide for teaching and learning of the universities at present. As students in universities have a plurality of numbers, the students in each course have a plurality of numbers, and the students cannot be considered due to the difficulty of the education of the students. The auxiliary teaching tool frequently used in the current universities has a certain limitation, students can evaluate the mastering condition of course contents by using the modes of selecting questions and filling blank questions in the class, and if the mode of selecting the questions is adopted, the condition that the students do not master the contents and answer the questions by guessing the mask can exist; the method of filling the blank questions cannot accurately judge whether the students grasp the content because similar answers cannot be well identified and evaluated.
Moreover, the existing teaching auxiliary platform lacks interaction with students, and cannot play a better role in helping the students understand course contents. Therefore, a teaching aid is needed that can generate evaluation questions including blank filling questions and simple answering questions according to course contents before or during a course, can evaluate answers input by a user in real time, and can perform multiple times and rounds of conversations for interaction.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an intelligent evaluation system capable of realizing multi-wheel interaction. The system can be used for on-site evaluation in teaching, and can quickly and automatically acquire the mastering degree of a learner on knowledge points; meanwhile, for a learner, even if the teacher is not at the side, through the multi-round interaction link in the evaluation process, the user can deepen knowledge points, the teacher can clearly know the mastering condition of the classmates on course contents, so that the interactivity is improved, and the learning efficiency and the teaching efficiency are improved.
The technical scheme for realizing the aim of the invention is as follows:
an intelligent evaluation system capable of realizing multi-wheel interaction comprises an intelligent terminal interconnected with
Answer intelligent processing submodule: the answer intelligent processing sub-module is used for preprocessing an answer input by a user to finish the functions of Chinese word segmentation, word vector, text error correction and keyword extraction, and changing the answer input by the user into a language which can be understood by a system, wherein the answer replied by the Chinese word segmentation is divided into word lists mainly aiming at simple answer questions for subsequent modules to use, the word vector mainly converts words into a vector space, the similar relation between the semantics of the words and the words is expressed in a vector form, and the text error correction is used for correcting error conditions such as wrongly written words which possibly exist in the input of the user;
a multi-round dialog sub-module: the multi-round dialogue submodule comprises three units of dialogue triggering, language understanding and question asking strategy question generation, the multi-round dialogue submodule controls dialogue content, and a user submits answers to trigger dialogue, wherein the language understanding is to acquire user intention by adopting a CNN-based text classification model, then interact with the dialogue management submodule, and meanwhile determine a question asking strategy according to a preprocessing result, generate questions through natural language and knowledge base content, wait for the user to answer, wherein the question asking determination strategy refers to obtaining questions related to the contents answered by the user after adding an offset according to a text processing result, and enlarge a question scope, so that an evaluation result can reflect the grasping degree of the user on course content;
a dialog management sub-module: the dialogue management submodule comprises a dialogue state mark, a dialogue round judgment and score evaluation part, wherein after a user inputs an answer, the answer is submitted, the text is preprocessed through the answer intelligent processing module, the obtained preprocessing result is used as an input text of a plurality of rounds of dialogue, the rounds of dialogue is triggered, the user intention is detected through the language understanding unit, so that a questioning strategy is determined, the dialogue management submodule manages the dialogue length, the dialogue state mark is carried out in the dialogue process, if the user does not answer temporarily, the dialogue mark repeatedly questions in a limited time, the completeness of evaluation is ensured, the end mark of the rounds of interaction is given according to the dialogue round judgment, a dialogue round threshold is set, an end dialogue signal is given once the dialogue round reaches the threshold, so that a plurality of rounds of dialogue is exited, the evaluation result is given, the dialogue round judgment is used for controlling the dialogue length, wherein the score evaluation part adopts the corresponding score and proportion to set for the answer of the question matched with the key word in the dialogue, and the score obtained by proportion accumulation for the answer given by the user and the system interaction process;
knowledge base management sub-module: the knowledge base management submodule is used for respectively storing question model question-answer models, course knowledge points and scores generated in the evaluation process, manages the questions and the knowledge points by using a database, and finally obtains an evaluation result by the evaluation score management through interaction with the multi-round dialogue submodule so as to realize the content evaluation of keys in the evaluation, wherein the evaluation score management is that the knowledge base management submodule is connected with the answer intelligent processing submodule, obtains key words in a dialogue through the answer intelligent processing submodule, matches with answers of the questions, sets corresponding scores according to the matching degree, and calculates final scores according to proportion of answers given by a user in the interaction process of the evaluation system.
After the answer of the blank filling and simple answering is completed, the intelligent terminal initially identifies the answer filled by the answer through an artificial intelligence method, information is popped up at the intelligent terminal according to the result obtained through the initial identification, further questions are asked for the answer, multiple times and multiple rounds of interactions can be carried out according to the situation, and the score of the answer is given through comprehensive analysis of the information of the multiple times and multiple rounds of answers of the answer.
The technical scheme can be used for on-site evaluation in teaching, and the intelligent terminal is used for completing the evaluation, so that the mastering degree of a learner on knowledge points can be quickly and automatically obtained; meanwhile, for a learner, even if the teacher is not at hand, the learner can deepen knowledge points through a plurality of dialogue links in the evaluation process, and the teacher can also know the mastering condition of the students on course contents through the evaluation result. The interactivity is increased, and the learning efficiency and the classroom efficiency are improved.
Drawings
FIG. 1 is a schematic diagram of an embodiment;
FIG. 2 is a flow chart of the working method in the embodiment.
Detailed Description
The present invention will now be further illustrated, but not limited, by the following figures and examples.
Examples:
referring to fig. 1 and 2, an intelligent evaluation system capable of realizing multi-round interaction comprises an intelligent terminal interconnected with
Answer intelligent processing submodule: the answer intelligent processing sub-module is used for preprocessing an answer input by a user to complete the functions of Chinese word segmentation, word vector, text error correction and keyword extraction, the answer input by the user is changed into a language which can be understood by a system, wherein the answer replied by the Chinese word segmentation is mainly divided into word lists aiming at simple answer questions for subsequent modules to use, the word vector is mainly used for converting words into a vector space, the similar relation between the semantics of the words and the words is expressed in a vector form, the text error correction is used for correcting error conditions such as misplaced words which possibly exist in the input of the user, the answer intelligent processing sub-module in the embodiment firstly adopts a word segmentation mode based on character string matching to realize word segmentation of the input problem of the user, and then word2vec algorithm is used for training word vectors according to context characteristics and storing the word vectors in a model form for subsequent operation to be called. And fitting the text by adopting an end-to-end depth model based on word segmentation for the text error correction part, and detecting whether a specific error type exists in the sentence after fitting the input problem based on the RNN sequence model. And finally outputting the matching keywords based on the problem corpus.
A multi-round dialog sub-module: the multi-round dialogue submodule comprises three units of dialogue triggering, language understanding and question asking strategy question generation, the multi-round dialogue submodule controls dialogue content, a user submits answers and then triggers dialogue, wherein the language understanding is to acquire user intention by adopting a CNN-based text classification model, then interact with the dialogue management submodule, and meanwhile determine a question asking strategy according to a preprocessing result, generate questions through natural language and knowledge base content, wait for the user to answer, wherein the question asking determination strategy refers to obtaining questions related to the contents answered by the user after adding an offset according to a text processing result, and enlarge a question range, so that an evaluation result can reflect the grasping degree of the user on course content; in the multi-round dialogue sub-module in the example, after the user submits an answer by utilizing the monitoring of the button, the dialogue is triggered, and the natural language generation model generates a problem according to the matching of the keywords and the content in the knowledge base, wherein the natural language generation model adopts a coding-decoding model.
A dialog management sub-module: the dialogue management sub-module comprises a dialogue state mark and dialogue round judgment, wherein after a user inputs an answer, the answer is submitted, the text is preprocessed through the answer intelligent processing module, the obtained preprocessing result is used as an input text of a plurality of rounds of dialogue, the rounds of dialogue is triggered, the user intention is detected through the language understanding unit, a question-asking strategy is determined, the dialogue management sub-module manages the dialogue length, the dialogue state mark is carried out in the dialogue process, if the user does not answer temporarily, the question is repeated in a limited time, the test integrity is ensured, the end mark of the rounds of interaction is given according to the dialogue round judgment, a dialogue round threshold is set, an end dialogue signal is given once the dialogue round reaches the threshold, so that a plurality of rounds of dialogue is exited, the test result is given, the dialogue round judgment is used for controlling the dialogue length, wherein the score evaluation part adopts the score and the proportion obtained by the answer which is matched with a keyword in the dialogue, the dialogue management sub-module in the example adopts the design of a user intention chart, a dialogue state record table, a dialogue round record table and a test score record are accumulated in the system test mode. Continuously storing the current dialogue state in the dialogue process, recording dialogue rounds, and exiting multiple rounds of dialogue when the dialogue rounds reach a set threshold;
knowledge base management sub-module: the knowledge base management submodule is used for respectively storing the question model, the question-answer model, the course knowledge points and scores generated in the evaluation process, manages the database for the questions and the knowledge points, interacts with the multi-round dialogue submodule, finally obtains an evaluation result through the evaluation score management, and achieves the key content evaluation in the evaluation, wherein the evaluation score management is that the knowledge base management submodule is connected with the answer intelligent processing submodule, obtains key words in the dialogue through the answer intelligent processing submodule, matches with answers of the questions, sets corresponding scores according to the matching degree, and calculates final scores according to proportion of answers given by a user in the interaction process of the evaluation system. The knowledge base management sub-module in the embodiment is realized by adopting a database management system, and the database is created to store the evaluation questions and the knowledge points, so that the data in the database can be obtained when the question model and the question-answer model are trained. And meanwhile, database operations such as adding, searching, modifying and deleting can be used for realizing operations such as adding or modifying the question type, acquiring the evaluation score and the like.
Claims (1)
1. An intelligent evaluation system capable of realizing multi-round interaction is characterized by comprising an intelligent terminal connected with the intelligent terminal
Answer intelligent processing submodule: the answer intelligent processing sub-module is used for preprocessing an answer input by a user to finish the functions of Chinese word segmentation, word vector, text error correction and keyword extraction, and changing the answer input by the user into a language which can be understood by a system, wherein the answer replied by the Chinese word segmentation is divided into word lists mainly aiming at simple answer questions for subsequent modules to use, the word vector mainly converts words into a vector space, the similar relation between the semantics of the words and the words is expressed in a vector form, and the text error correction is used for correcting error conditions such as wrongly written words which possibly exist in the input of the user;
a multi-round dialog sub-module: the multi-round dialogue submodule comprises three units of dialogue triggering, language understanding and question asking strategy question generation, the multi-round dialogue submodule controls dialogue content, a user submits answers and triggers dialogue, wherein the language understanding unit acquires user intention by adopting a CNN-based text classification model and then interacts with the dialogue management submodule, and meanwhile, a question asking strategy is determined according to a preprocessing result, questions are generated through natural language and knowledge base content, and a user waits for answering, wherein the question asking determination strategy refers to obtaining questions related to the contents answered by the user after adding an offset according to a text processing result, the problem range is enlarged, and the evaluation result can reflect the grasping degree of the user on course content;
a dialog management sub-module: the dialogue management submodule comprises a dialogue state mark, a dialogue round judgment and score evaluation part, wherein after a user inputs an answer, the answer is submitted, the pretreatment is carried out through the answer intelligent processing module, the obtained pretreatment result is used as an input text of a plurality of rounds of dialogue, the rounds of dialogue is triggered, the user intention is detected through a language understanding unit, the dialogue management submodule manages the dialogue length, the dialogue state mark is carried out in the dialogue process, if the user does not answer temporarily, the dialogue mark repeatedly asks in a limited time, an end mark of the rounds of interaction is given according to the dialogue round judgment, a dialogue round threshold is set, an end dialogue signal is given once the dialogue round reaches the threshold, so that a plurality of rounds of dialogue is exited, wherein the score evaluation part adopts the corresponding score and proportion to be set for the answer of the question matched with the keyword in the dialogue, and the score obtained by accumulating the answer given by the user and the system interaction process in proportion is obtained;
knowledge base management sub-module: the knowledge base management submodule comprises a question management submodule, a knowledge point management submodule and an evaluation score management submodule, wherein the knowledge base management submodule is used for storing question model question-answer models, course knowledge points and scores generated in the evaluation process, the knowledge base management submodule is used for managing a database for the questions and the knowledge points, and finally obtaining an evaluation result through the evaluation score management through interaction with a plurality of rounds of dialogue submodules, and the evaluation score management is used for realizing key content evaluation in evaluation, wherein the evaluation score management is that the knowledge base management submodule is connected with an answer intelligent processing submodule, obtains key words in dialogue through the answer intelligent processing submodule, matches with answers of the questions, sets corresponding scores according to matching degrees and calculates final scores according to proportions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111311891.9A CN114020894B (en) | 2021-11-08 | 2021-11-08 | Intelligent evaluation system capable of realizing multi-wheel interaction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111311891.9A CN114020894B (en) | 2021-11-08 | 2021-11-08 | Intelligent evaluation system capable of realizing multi-wheel interaction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114020894A CN114020894A (en) | 2022-02-08 |
| CN114020894B true CN114020894B (en) | 2024-03-26 |
Family
ID=80062201
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111311891.9A Active CN114020894B (en) | 2021-11-08 | 2021-11-08 | Intelligent evaluation system capable of realizing multi-wheel interaction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114020894B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110148318A (en) * | 2019-03-07 | 2019-08-20 | 上海晨鸟信息科技有限公司 | A kind of number assiatant system, information interacting method and information processing method |
| CN110489756A (en) * | 2019-08-23 | 2019-11-22 | 上海乂学教育科技有限公司 | Conversational human-computer interaction spoken language evaluation system |
| CN112749263A (en) * | 2020-11-12 | 2021-05-04 | 国衡智慧城市科技研究院(北京)有限公司 | Multi-round answer generation system based on single question |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110125734A1 (en) * | 2009-11-23 | 2011-05-26 | International Business Machines Corporation | Questions and answers generation |
| CN108897848A (en) * | 2018-06-28 | 2018-11-27 | 北京百度网讯科技有限公司 | Robot interactive approach, device and equipment |
-
2021
- 2021-11-08 CN CN202111311891.9A patent/CN114020894B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110148318A (en) * | 2019-03-07 | 2019-08-20 | 上海晨鸟信息科技有限公司 | A kind of number assiatant system, information interacting method and information processing method |
| CN110489756A (en) * | 2019-08-23 | 2019-11-22 | 上海乂学教育科技有限公司 | Conversational human-computer interaction spoken language evaluation system |
| CN112749263A (en) * | 2020-11-12 | 2021-05-04 | 国衡智慧城市科技研究院(北京)有限公司 | Multi-round answer generation system based on single question |
Non-Patent Citations (2)
| Title |
|---|
| 基于网络在线学习与智能测评系统的混合式教学模式;李博洋;韩淑洁;张晓荣;;航海教育研究;20160315(第01期);全文 * |
| 智能回复系统研究综述;岳世峰;林政;王伟平;孟丹;;信息安全学报;20200115(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114020894A (en) | 2022-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Weston | Dialog-based language learning | |
| CN109389870B (en) | Data self-adaptive adjusting method and device applied to electronic teaching | |
| CN109670168B (en) | Short answer automatic scoring method, system and storage medium based on feature learning | |
| CN112016767A (en) | Dynamic planning method and device for learning route | |
| CN110175228A (en) | Based on basic module and the loop embedding of machine learning dialogue training method and system | |
| US11989524B2 (en) | Knowledge-grounded dialogue system and method for language learning | |
| Graesser et al. | Computerized Learning Environments That Incorporate Research in Discourse Psychology, Cognitive Science, and Computational Linguistics. | |
| CN108831229B (en) | Chinese automatic grading method | |
| WO2021159816A1 (en) | Idiom blank-filling question answer selection method and apparatus, and computer device | |
| CN116597461B (en) | Topic knowledge point association method and system based on artificial intelligence | |
| CN115640368A (en) | Method and system for intelligently diagnosing recommended question bank | |
| CN114885216A (en) | Exercise pushing method and system, electronic equipment and storage medium | |
| CN114020894B (en) | Intelligent evaluation system capable of realizing multi-wheel interaction | |
| CN109191968A (en) | Language education robot and more educational robot langue leaning systems | |
| CN112560429A (en) | Intelligent training detection method and system based on deep learning | |
| Amarnani et al. | A Complete Chatbot based Architecture for answering user's Course-related queries in MOOC platforms | |
| CN110826341A (en) | Semantic similarity calculation method based on seq2seq model | |
| CN112133147A (en) | Online automatic teaching and interaction system based on teaching plan and preset question bank | |
| CN114266340A (en) | Knowledge query network model introducing self-attention mechanism | |
| CN113221577A (en) | Education text knowledge induction method, system, equipment and readable storage medium | |
| Weerasinghe et al. | Enhancing learning through self-explanation | |
| CN113688226A (en) | Exercise practice method, system and storage medium based on big data | |
| CN112115275A (en) | Knowledge graph construction method and system for math tutoring question-answering system | |
| CN112560431A (en) | Method, apparatus, device, storage medium, and computer program product for generating test question tutoring information | |
| Graesser | Questioning Mechanisms during Tutoring, Conversation, and Human-Computer Interaction. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |