CN113486196B - Intelligent physical knowledge point identification method and device based on teaching thinking - Google Patents
Intelligent physical knowledge point identification method and device based on teaching thinking Download PDFInfo
- Publication number
- CN113486196B CN113486196B CN202111046337.2A CN202111046337A CN113486196B CN 113486196 B CN113486196 B CN 113486196B CN 202111046337 A CN202111046337 A CN 202111046337A CN 113486196 B CN113486196 B CN 113486196B
- Authority
- CN
- China
- Prior art keywords
- physical
- knowledge
- examination
- point
- map
- 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
Images
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
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- 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
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Animal Behavior & Ethology (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention provides a physical knowledge point intelligent identification method and a physical knowledge point intelligent identification device based on teaching thinking, which relate to the technical field of education and comprise the following steps: constructing a knowledge element map based on keywords and element knowledge points of the physical discipline, carding an examination point knowledge map associated with the knowledge points and the examination points based on an examination point logic system of the physical discipline, and refining a map logic relationship according to the knowledge element map and the examination point knowledge map; carrying out structuralization processing on the physical questions, respectively extracting physical elements of each part of content, and carrying out semantic combination on the physical elements through a pre-trained language model; and constructing an examination point identification algorithm model, combining the structural analysis and the physical semanteme of the physical question, identifying an examination point interval with strong question correlation, and marking the physical examination points in the examination point interval. The invention can solve the technical problems of low knowledge point marking efficiency and low marking accuracy of the automatic examination point marking method in the prior art.
Description
Technical Field
The invention relates to the technical field of education, in particular to a method and a device for intelligently identifying physical knowledge points based on teaching thinking.
Background
In order to make students have a better grasp of knowledge points, teachers usually make manual annotations on the knowledge points on the teaching materials. However, manual labeling suffers from the following disadvantages: the labor cost is excessively high, the labeling efficiency is low, and the method is difficult to be suitable for the knowledge point labeling of a large batch of question banks; the human standard is too random to be easily limited by personal subjective factors and knowledge levels. Aiming at the defects of manual labeling, some enterprises are exploring automatic labeling of knowledge points so as to solve the problems existing in the conventional manual labeling form.
The existing automatic labeling generally comprises a similarity contrast labeling algorithm, machine learning and deep learning model labeling and a feature model. The similarity comparison labeling algorithm has the following defects: the general questions do not have enough marked questions as the standard of similarity comparison; the similarity of the question stems cannot accurately reflect the investigation key points and knowledge point directions of the questions. Machine learning + deep learning model labeling has the following disadvantages: the model depends on a large amount of labeled topic data, the core characteristics of the topics cannot be accurately learned by the current model, and no effective model is available for commercial use. The feature model has the following disadvantages: the discipline knowledge feature is strong in specificity, and no universal discipline feature model can be used in the market.
Therefore, the automatic examination point labeling method in the prior art generally has the technical problems of low knowledge point labeling efficiency and low labeling accuracy.
Disclosure of Invention
Based on the above, the invention aims to provide a method and a device for intelligently identifying physical knowledge points based on teaching thinking, and aims to solve the technical problems of low knowledge point marking efficiency and low marking accuracy commonly existing in an examination point automatic marking method in the prior art.
The invention provides a physical knowledge point intelligent identification method based on teaching thinking, which comprises the following steps:
constructing a knowledge element map based on keywords and element knowledge points of the physical subject, carding an examination point knowledge map associated with the knowledge points and the examination points based on an examination point logic system of the physical subject, and refining a map logic relationship according to the knowledge element map and the examination point knowledge map;
carrying out structuralization processing on the physical questions, respectively extracting physical elements of each part of content, and carrying out semantic combination on the physical elements through a pre-trained language model;
and constructing an examination point identification algorithm model, combining the structural analysis and the physical semanteme of the physical question, identifying an examination point interval with strong question correlation, and marking the physical examination points in the examination point interval.
According to one aspect of the foregoing technical solution, the step of performing structuring processing on the physical topic and extracting the physical elements of each part of the content respectively includes:
decomposing a physical topic into a physical scene condition, a topic examination content, an option text content and a topic content of an analysis content;
and respectively extracting physical key words, physical knowledge points and physical elements of physical quantity under examination of each part of topic content.
According to one aspect of the above technical solution, after the steps of extracting physical keywords, physical knowledge points, and examining physical elements of physical quantities of each part of the topic content, the method further comprises:
semantically combining the physical elements through a pre-trained language model to form a physical element combination with physical significance;
and carrying out model training and classification on the physical element combination, identifying the physical scene behind the physical element combination, the application of physical laws and subject key information of the physical quantity under key examination.
According to one aspect of the above technical solution, the step of identifying the examination point interval with strong question correlation by combining the structural analysis and the physical semantic meaning of the physical question specifically includes:
combining the structural analysis result of the physical question with the physical semantic meaning, and identifying a test point interval with strong question correlation;
combining the identified test points in the test point interval with the physical elements, and carrying out algorithm logic deduction on a feedback learning mechanism of the test point identification algorithm model by combining the atlas logic relationship.
According to one aspect of the above technical solution, after the step of deducing the algorithm logic of the feedback learning mechanism of the test point identification algorithm model, the method comprises:
comparing and verifying a deduction result of the algorithm logic with a real result to generate feedback information;
and feeding the feedback information back to the test point identification algorithm model, and performing reverse learning optimization on the logical relationship between the test point identification algorithm model and the atlas.
According to an aspect of the foregoing technical solution, the method further includes:
and carrying out iterative optimization on the test point identification algorithm model and the atlas logical relationship for a plurality of times according to the reverse learning result of the test point identification algorithm model and the atlas logical relationship.
The second aspect of the invention is to provide a physical knowledge point intelligent recognition device based on teaching thinking, which comprises:
the logic construction module is used for constructing a knowledge element map based on keywords and element knowledge points of the physical discipline, combing an examination point knowledge map associated with the examination point based on an examination point logic system of the physical discipline, and refining a map logic relationship according to the knowledge element map and the examination point knowledge map;
the question processing module is used for carrying out structural processing on the physical questions, respectively extracting physical elements of each part of content, and carrying out semantic combination on the physical elements through a pre-trained language model;
and the marking learning module is used for constructing an examination point identification algorithm model, combining the structural analysis and the physical semanteme of the physical examination questions, identifying examination point intervals with strong question correlation and marking the physical examination points in the examination point intervals.
According to an aspect of the foregoing technical solution, the title processing module is further configured to:
decomposing a physical topic into a physical scene condition, a topic examination content, an option text content and a topic content of an analysis content;
and respectively extracting physical key words, physical knowledge points and physical elements of physical quantity under examination of each part of topic content.
According to an aspect of the foregoing technical solution, the label learning module is further configured to:
combining the structural analysis result of the physical question with the physical semantic meaning, and identifying a test point interval with strong question correlation;
combining the identified test points in the test point interval with the physical elements, and carrying out algorithm logic deduction on a feedback learning mechanism of the test point identification algorithm model by combining the atlas logic relationship.
Compared with the prior art, the intelligent identification method and device for physical knowledge points based on teaching thinking, disclosed by the invention, have the advantages that the logical relation between the knowledge element map and the examination point knowledge map is extracted according to the extraction map of the knowledge element map and the examination point knowledge map, the physical elements of each part are extracted after the physical subjects are subjected to structural processing, the structural analysis and the physical semanteme of the physical subjects are combined through an examination point identification algorithm model, the examination point interval with strong subject correlation is identified, and the physical examination points of the examination point interval are labeled. The method can basically cover most middle-school subject matters, has strong interpretability of feature combination, has controllable precision of the examination point marking, is far beyond the current general recognition model, achieves the aim of replacing manual marking, and is far beyond the manual marking in the aspects of efficiency and standardization.
Drawings
FIG. 1 is a flow chart of a method for intelligently identifying points of physical knowledge based on teaching thinking according to a first embodiment of the present invention;
FIG. 2 is a flow chart of the second embodiment of the present invention for the intelligent identification of physical knowledge points based on teaching thinking, the structuralization of physical topics, the extraction of physical elements, and the semantic combination of physical elements;
FIG. 3 is a flowchart illustrating identification of an examination point interval by an algorithm model and labeling of physical examination points in the examination point interval in the intelligent identification method of physical knowledge points based on teaching thinking according to the second embodiment of the present invention;
FIG. 4 is a block diagram of a physical knowledge point intelligent recognition device based on teaching thinking according to a third embodiment of the present invention;
the following detailed description will further illustrate the invention in conjunction with the above-described figures.
Detailed Description
To facilitate an understanding of the invention, the invention will now be described more fully with reference to the accompanying drawings. Several embodiments of the invention are presented in the drawings. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1, a first embodiment of the present invention provides a method for intelligently identifying physical knowledge points based on teaching thinking, which includes steps S10-S30:
step S10, constructing a knowledge element map based on keywords and element knowledge points of the physical discipline, combing out an examination point knowledge map associated with the knowledge points and the examination points based on an examination point logic system of the physical discipline, and refining the logical relationship of the map according to the knowledge element map and the examination point knowledge map;
as is easy to understand, each subject has the subject characteristics, so the subject questions usually have stronger subject question characteristics; for example, the Chinese subject has more Chinese characters and grammar, and is abstract as a whole, the English subject is composed of words and grammar, and the physical subject has physical formulas and practical application scenarios.
In this embodiment, the physical formula is equivalent to a keyword and a meta knowledge point of the physical discipline as the actual application scenario, and the physical element map is constructed based on the keyword and the meta knowledge point of the physical discipline, so as to obtain the physical elements of the physical discipline.
The test point knowledge graph associated with the test point is combed out based on a test point logic system of the physical subject, and more knowledge points exist in the physical subject, such as the Newton's third law and the like. And (3) combing an examination point logic system according to the education outline, the examination rules of the past year and the teacher experience, and when the Newton third law is the key examination direction of the physical examination, considering that the Newton third law is associated with an examination point, and constructing an examination point knowledge graph with other examination points.
Step S20, carrying out structuralization processing on the physical questions, respectively extracting the physical elements of each part of content, and carrying out semantic combination on the physical elements through a pre-trained language model;
for example, the physical choice question may be divided into a question stem part, a choice part, and an answer parsing part, and question contents such as an actual examination scene of the physical choice question, so as to extract physical elements of each part of the question contents.
By way of example and not limitation, keywords of the stem part, such as "strength of solution" are physical elements of the stem part, keywords of the option part, such as "nimi", are physical elements of the option part, and keywords of answer resolution, such as "according to XX law, according to XX formula", are physical elements of the answer resolution part.
And step S30, constructing an examination point identification algorithm model, combining the structural analysis and the physical semantic meaning of the physical examination questions, identifying examination point intervals with strong question correlation, and labeling the physical examination points of the examination point intervals.
By adopting the intelligent identification method for physical knowledge points based on teaching thinking, which is shown in the embodiment, the knowledge element map and the examination point knowledge map are constructed, the logical relationship of the map is refined according to the knowledge element map and the examination point knowledge map, each part of physical elements are extracted after the physical questions are structurally processed, the structural analysis and the physical semanteme of the physical questions are combined through an examination point identification algorithm model, the examination point interval with strong question correlation is identified, and the physical examination points in the examination point interval are labeled. The intelligent identification method of physical knowledge points based on teaching thinking can basically cover most of the subjects of the middle school subjects, and the interpretability of feature combinations is strong, so that the accuracy of test point marking is controllable and far exceeds that of the current universal identification model, the aim of replacing manual marking is achieved, and the efficiency and the standardization are far beyond those of manual marking.
Referring to fig. 2 and fig. 3, a second embodiment of the present invention provides an intelligent physical knowledge point identification method based on teaching thinking, and the difference between the intelligent physical knowledge point identification method based on teaching thinking in this embodiment and the intelligent physical knowledge point identification method based on teaching thinking in the first embodiment is:
in this embodiment, step S20 specifically includes steps S201 to S204:
step S201, decomposing a physical topic into a physical scene condition, a topic examination content, an option text content and a topic content of an analysis content;
step S202, extracting physical key words, physical knowledge points and physical elements of physical quantity under examination of each part of topic content respectively;
for example, the physical choice question may be divided into a question stem part, a choice part, and an answer parsing part, and question contents such as an actual examination scene of the physical choice question, so as to extract physical elements of each part of the question contents.
By way of example and not limitation, keywords of the stem part, such as "strength of solution" are physical elements of the stem part, keywords of the option part, such as "nimi", are physical elements of the option part, and keywords of answer resolution, such as "according to XX law, according to XX formula", are physical elements of the answer resolution part.
Step S203, semantically combining the physical elements through a pre-trained language model to form a physical element combination with physical significance;
and step S204, performing model training and classification on the physical element combination, identifying a physical scene behind the physical element combination, applying a physical law, and mainly examining subject key information of physical quantities.
In this embodiment, step S30 specifically includes steps S301 to S305:
step S301, combining the structural analysis result of the physical question with the physical semantic meaning, and identifying the examination point interval with strong question correlation;
step S302, combining the identified test points in the test point interval with physical elements, and performing algorithm logic deduction on a feedback learning mechanism of the test point identification algorithm model by combining a map logic relation;
step S303, comparing and verifying a deduction result of the algorithm logic with a real result to generate feedback information;
and step S304, feeding back the feedback information to the test point identification algorithm model, and performing reverse learning optimization on the logical relationship between the test point identification algorithm model and the atlas.
And S305, carrying out iterative optimization on the test point identification algorithm model and the map logical relationship for a plurality of times according to the reverse learning result of the test point identification algorithm model and the map logical relationship.
In the embodiment, the test point identification algorithm model and the atlas logical relationship are subjected to iterative optimization for a plurality of times, so that the accuracy and the efficiency of the model are continuously improved, and the aim of replacing manual labeling is finally fulfilled.
By adopting the intelligent identification method for physical knowledge points based on teaching thinking, which is shown in the embodiment, the knowledge element map and the examination point knowledge map are constructed, the logical relationship of the map is refined according to the knowledge element map and the examination point knowledge map, each part of physical elements are extracted after the physical questions are structurally processed, the structural analysis and the physical semanteme of the physical questions are combined through an examination point identification algorithm model, the examination point interval with strong question correlation is identified, and the physical examination points in the examination point interval are labeled. The intelligent identification method for physical knowledge points based on teaching thinking disclosed by the embodiment can basically cover most subjects of middle school subjects, and the interpretability of feature combinations is strong, so that the accuracy of test point marking is controllable and far exceeds that of the current universal identification model, the goal of replacing manual marking is achieved, and the efficiency and standardization are far beyond those of manual marking. In the later practical process, the test point algorithm model can be continuously optimized according to the feedback of the labeling result, so that the accuracy of the test point labeling is further improved.
Referring to fig. 4, a third embodiment of the present invention provides an intelligent recognition device for physical knowledge points based on teaching thinking, which includes:
the logic construction module 10 is used for constructing a knowledge element map based on keywords and element knowledge points of the physical discipline, combing an examination point knowledge map associated with the examination point based on an examination point logic system of the physical discipline, and refining a map logic relationship according to the knowledge element map and the examination point knowledge map;
as is easy to understand, each subject has the subject characteristics, so the subject questions usually have stronger subject question characteristics; for example, the Chinese subject has more Chinese characters and grammar, and is abstract as a whole, the English subject is composed of words and grammar, and the physical subject has physical formulas and practical application scenarios.
In this embodiment, the physical formula is equivalent to a keyword and a meta knowledge point of the physical discipline as the actual application scenario, and the physical element map is constructed based on the keyword and the meta knowledge point of the physical discipline, so as to obtain the physical elements of the physical discipline.
The test point knowledge graph associated with the test point is combed out based on a test point logic system of the physical subject, and more knowledge points exist in the physical subject, such as the Newton's third law and the like. And (3) combing an examination point logic system according to the education outline, the examination rules of the past year and the teacher experience, and when the Newton third law is the key examination direction of the physical examination, considering that the Newton third law is associated with an examination point, and constructing an examination point knowledge graph with other examination points.
The question processing module 20 is configured to perform structured processing on physical questions, extract physical elements of each part of content, and perform semantic combination on the physical elements through a pre-trained language model;
for example, the physical choice question may be divided into a question stem part, a choice part, and an answer parsing part, and question contents such as an actual examination scene of the physical choice question, so as to extract physical elements of each part of the question contents.
By way of example and not limitation, keywords of the stem part, such as "strength of solution" are physical elements of the stem part, keywords of the option part, such as "nimi", are physical elements of the option part, and keywords of answer resolution, such as "according to XX law, according to XX formula", are physical elements of the answer resolution part.
And the labeling learning module 30 is configured to construct an examination point identification algorithm model, combine the structural analysis and the physical semantic meaning of the physical examination questions, identify an examination point interval with strong question correlation, and label the physical examination points in the examination point interval.
In this embodiment, the topic processing module 20 is specifically configured to:
decomposing a physical topic into a physical scene condition, a topic examination content, an option text content and a topic content of an analysis content;
respectively extracting physical key words, physical knowledge points and physical elements of physical quantity under examination of each part of the subject contents;
semantically combining the physical elements through a pre-trained language model to form a physical element combination with physical significance;
and performing model training and classification on the physical element combination, identifying a physical scene behind the physical element combination, applying a physical law, and mainly examining subject key information of physical quantities.
In this embodiment, the label learning module 30 is specifically configured to:
combining the structural analysis result of the physical question with the physical semantic meaning, and identifying a test point interval with strong question correlation;
combining the identified test points in the test point interval with physical elements, and performing algorithm logic deduction on a feedback learning mechanism of the test point identification algorithm model by combining a map logic relation;
comparing and verifying a deduction result of the algorithm logic with a real result to generate feedback information;
feeding back the feedback information to the test point identification algorithm model, and performing reverse learning optimization on the logical relationship between the test point identification algorithm model and the atlas;
and carrying out iterative optimization on the test point identification algorithm model and the atlas logical relationship for a plurality of times according to the reverse learning result of the test point identification algorithm model and the atlas logical relationship.
Adopt the physical knowledge point intelligent recognition device based on teaching thinking that this embodiment shows, through establishing knowledge element map and examination point knowledge map, refine the atlas logical relationship according to knowledge element map and examination point knowledge map, extract every partial physical element with physical topic structurization processing back, through examination point identification algorithm model to the structural analysis and the physical semanteme combination of physical topic, discern the examination point interval that the topic relevance is strong to mark the physical examination point of examination point interval. The intelligent physical knowledge point recognition device based on teaching thinking in the embodiment can basically cover most subjects in middle school, and the interpretability of feature combination is strong, so that the precision of examination point marking is controllable and far exceeds that of the current general recognition model, the goal of replacing manual marking is achieved, and the efficiency and standardization are far beyond those of manual marking.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (6)
1. A physical knowledge point intelligent identification method based on teaching thinking is characterized by comprising the following steps:
constructing a knowledge element map based on keywords and element knowledge points of the physical subject, carding an examination point knowledge map associated with the knowledge points and the examination points based on an examination point logic system of the physical subject, and refining a map logic relationship according to the knowledge element map and the examination point knowledge map;
carrying out structuring processing on the physical questions, respectively extracting physical elements of each part of content, and carrying out semantic combination on the physical elements through a pre-trained language model to form a physical element combination with physical significance;
performing model training and classification on the physical element combination, identifying a physical scene behind the physical element combination, applying a physical law and mainly examining subject key information of physical quantities;
constructing an examination point identification algorithm model, combining the structural analysis and the physical semanteme of the physical question, identifying an examination point interval with strong question correlation, and marking the physical examination points in the examination point interval;
the method comprises the following steps of combining the structural analysis and the physical semanteme of a physical topic, and identifying an examination point interval with strong topic correlation, and specifically comprises the following steps:
combining the structural analysis result of the physical question with the physical semantic meaning, and identifying a test point interval with strong question correlation;
combining the identified test points in the test point interval with the physical elements, and carrying out algorithm logic deduction on a feedback learning mechanism of the test point identification algorithm model by combining the atlas logic relationship.
2. The intelligent recognition method for physical knowledge points based on teaching thinking as claimed in claim 1, wherein the step of structuring the physical topic and extracting the physical elements of each part of the content respectively comprises:
decomposing a physical topic into a physical scene condition, a topic examination content, an option text content and a topic content of an analysis content;
and respectively extracting physical key words, physical knowledge points and physical elements of physical quantity under examination of each part of topic content.
3. The intelligent recognition method of physical knowledge points based on teaching thinking according to claim 1, wherein after the step of deducting the algorithm logic of the feedback learning mechanism of the test point recognition algorithm model, the method comprises:
comparing and verifying a deduction result of the algorithm logic with a real result to generate feedback information;
and feeding the feedback information back to the test point identification algorithm model, and performing reverse learning optimization on the logical relationship between the test point identification algorithm model and the atlas.
4. The intelligent physical knowledge point recognition method based on instructional thinking according to claim 3, wherein the method further comprises:
and carrying out iterative optimization on the test point identification algorithm model and the atlas logical relationship for a plurality of times according to the reverse learning result of the test point identification algorithm model and the atlas logical relationship.
5. The utility model provides a physical knowledge point intelligent recognition device based on teaching thinking, its characterized in that, the device includes:
the logic construction module is used for constructing a knowledge element map based on keywords and element knowledge points of the physical discipline, combing an examination point knowledge map associated with the examination point based on an examination point logic system of the physical discipline, and refining a map logic relationship according to the knowledge element map and the examination point knowledge map;
the question processing module is used for carrying out structural processing on physical questions, respectively extracting physical elements of each part of content, carrying out semantic combination on the physical elements through a pre-trained language model to form a physical element combination with physical significance, carrying out model training and classification on the physical element combination, and identifying physical scenes behind the physical element combination, application of physical laws and subject key information of key physical quantity;
the annotation learning module is used for constructing an examination point identification algorithm model, combining the structural analysis and the physical semanteme of the physical examination, identifying an examination point interval with strong question correlation, and annotating the physical examination points in the examination point interval;
the label learning module is specifically configured to:
combining the structural analysis result of the physical question with the physical semantic meaning, and identifying a test point interval with strong question correlation;
combining the identified test points in the test point interval with the physical elements, and carrying out algorithm logic deduction on a feedback learning mechanism of the test point identification algorithm model by combining the atlas logic relationship.
6. The intelligent recognition device of physical knowledge points based on instructional thinking according to claim 5, wherein the theme processing module is further configured to:
decomposing a physical topic into a physical scene condition, a topic examination content, an option text content and a topic content of an analysis content;
and respectively extracting physical key words, physical knowledge points and physical elements of physical quantity under examination of each part of topic content.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111046337.2A CN113486196B (en) | 2021-09-08 | 2021-09-08 | Intelligent physical knowledge point identification method and device based on teaching thinking |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111046337.2A CN113486196B (en) | 2021-09-08 | 2021-09-08 | Intelligent physical knowledge point identification method and device based on teaching thinking |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113486196A CN113486196A (en) | 2021-10-08 |
| CN113486196B true CN113486196B (en) | 2022-01-28 |
Family
ID=77947333
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111046337.2A Active CN113486196B (en) | 2021-09-08 | 2021-09-08 | Intelligent physical knowledge point identification method and device based on teaching thinking |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113486196B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115203441B (en) * | 2022-09-19 | 2022-12-20 | 江西风向标智能科技有限公司 | Method, system, storage medium and equipment for analyzing high school mathematical formula |
| CN117557425B (en) * | 2023-12-08 | 2024-04-16 | 广州市小马知学技术有限公司 | Question bank data optimization method and system based on intelligent question bank system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017028723A1 (en) * | 2015-08-19 | 2017-02-23 | 阿里巴巴集团控股有限公司 | Information processing method and device |
| CN107784088A (en) * | 2017-09-30 | 2018-03-09 | 杭州博世数据网络有限公司 | The knowledge mapping construction method of knowledge based point annexation |
| CN109977291A (en) * | 2019-03-20 | 2019-07-05 | 武汉市软迅科技有限公司 | Search method, device, equipment and storage medium based on physical knowledge map |
| CN110532462A (en) * | 2019-07-25 | 2019-12-03 | 北京三快在线科技有限公司 | A kind of recommended method, device, equipment and readable storage medium storing program for executing |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11222052B2 (en) * | 2011-02-22 | 2022-01-11 | Refinitiv Us Organization Llc | Machine learning-based relationship association and related discovery and |
| CN110134945B (en) * | 2019-04-15 | 2024-04-23 | 平安科技（深圳）有限公司 | Method, device, equipment and storage medium for identifying examination points of exercise |
| CN110941723A (en) * | 2019-11-18 | 2020-03-31 | 广东宜学通教育科技有限公司 | Method, system and storage medium for constructing knowledge graph |
-
2021
- 2021-09-08 CN CN202111046337.2A patent/CN113486196B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017028723A1 (en) * | 2015-08-19 | 2017-02-23 | 阿里巴巴集团控股有限公司 | Information processing method and device |
| CN107784088A (en) * | 2017-09-30 | 2018-03-09 | 杭州博世数据网络有限公司 | The knowledge mapping construction method of knowledge based point annexation |
| CN109977291A (en) * | 2019-03-20 | 2019-07-05 | 武汉市软迅科技有限公司 | Search method, device, equipment and storage medium based on physical knowledge map |
| CN110532462A (en) * | 2019-07-25 | 2019-12-03 | 北京三快在线科技有限公司 | A kind of recommended method, device, equipment and readable storage medium storing program for executing |
Non-Patent Citations (2)
| Title |
|---|
| Evolutionary fine-tuning of automated semantic annotation system;Cuzzola J;《Expert System with Applications An International Journal》;20151231;第42卷(第20期);第6864-6877页 * |
| 知识图谱对中学生创新能力培养的实践研究——以高一物理为例;高晋阳;《中国优秀博硕士学位论文全文数据库(硕士)社会科学Ⅱ辑》;20190415(第2019年第04期);第H130-293页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113486196A (en) | 2021-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Koppel et al. | Automatically determining an anonymous author’s native language | |
| CN113486196B (en) | Intelligent physical knowledge point identification method and device based on teaching thinking | |
| CN108121702B (en) | Method and system for evaluating and reading mathematical subjective questions | |
| CN108363743A (en) | A kind of intelligence questions generation method, device and computer readable storage medium | |
| CN108052504B (en) | Structure analysis method and system for mathematic subjective question answer result | |
| WO2023273583A1 (en) | Exam-marking method and apparatus, electronic device, and storage medium | |
| CN111326040B (en) | Intelligent test and intelligent tutoring system and method for Chinese reading understanding | |
| CN110909035A (en) | Personalized review question set generation method and device, electronic equipment and storage medium | |
| US20150026184A1 (en) | Methods and systems for content management | |
| CN112148862B (en) | Method and device for identifying problem intention, storage medium and electronic equipment | |
| Hirsh | Researching vocabulary | |
| CN111369980A (en) | Voice detection method and device, electronic equipment and storage medium | |
| Sahan | Cognitive reading comprehension strategies employed by ELT Students | |
| Imaniar | Students' writing errors and what lies beyond them | |
| Atapattu et al. | Educational question answering motivated by question-specific concept maps | |
| CN112800182A (en) | Test question generation method and device | |
| CN115438624A (en) | Identification method, system, storage medium and equipment for question setting intention of mathematical subjects | |
| Boutorwick | Vocabulary development through reading: A comparison of approaches | |
| CN115345591A (en) | Intelligent interviewing method, intelligent interviewing device and intelligent interviewing system | |
| CN112860983B (en) | Method, system, equipment and readable storage medium for pushing learning content | |
| Suresh et al. | Identifying teamwork indicators in an online collaborative problem-solving task: A text-mining approach | |
| CN112164262A (en) | Intelligent paper reading tutoring system | |
| Boateng et al. | Real-World Deployment and Evaluation of Kwame for Science, An AI Teaching Assistant for Science Education in West Africa | |
| Wen et al. | Research on Chinese Character Feature Extraction and Modeling of Children's Cognitive Law Based on LightGBM Algorithm | |
| Kankhar et al. | Word level similarity auto-evaluation for an online question answering system |
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 | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Gao Yuwei Inventor after: Tao Feipan Inventor before: Gao Yuwei |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 330000 Building 1, maiyuan Road, Nanchang Economic and Technological Development Zone, Jiangxi Province Patentee after: Jiangxi wind vane Intelligent Technology Co.,Ltd. Address before: 330000 Building 1, maiyuan Road, Nanchang Economic and Technological Development Zone, Jiangxi Province Patentee before: JIANGXI VANEDUCATION TECHNOLOGY Inc. |