CN112966121A - Artificial intelligence autonomous learning education robot for overcoming food preference - Google Patents
Artificial intelligence autonomous learning education robot for overcoming food preference Download PDFInfo
- Publication number
- CN112966121A CN112966121A CN202110228045.4A CN202110228045A CN112966121A CN 112966121 A CN112966121 A CN 112966121A CN 202110228045 A CN202110228045 A CN 202110228045A CN 112966121 A CN112966121 A CN 112966121A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- learning
- data
- knowledge point
- food preference
- 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.)
- Granted
Links
- 235000020803 food preference Nutrition 0.000 title claims abstract description 148
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 claims abstract description 67
- 238000012360 testing method Methods 0.000 claims description 87
- 238000012549 training Methods 0.000 claims description 24
- 238000004364 calculation method Methods 0.000 claims description 19
- 238000013528 artificial neural network Methods 0.000 claims description 12
- 238000013136 deep learning model Methods 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 12
- 238000012552 review Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 6
- 230000000638 stimulation Effects 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 8
- 238000013135 deep learning Methods 0.000 description 3
- 206010019233 Headaches Diseases 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000001447 compensatory effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 231100000869 headache Toxicity 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
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
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B19/00—Teaching not covered by other main groups of this subclass
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Tourism & Hospitality (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Strategic Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medical Informatics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Evolutionary Biology (AREA)
- Human Resources & Organizations (AREA)
- Entrepreneurship & Innovation (AREA)
- Animal Behavior & Ethology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
Overcome artificial intelligence autonomous learning educational robot of "food preference", include: establishing a course knowledge graph; establishing a learning knowledge graph; calculating the monophagia and monophagia degree; overcomes the treatment steps of food preference and food preference. According to the method, the curriculum knowledge map is constructed to analyze other knowledge points which are overlooked when part of knowledge points are over-concerned in the learning process of the student, whether the learning of the student is drilled into a locally related similar knowledge point set can be known according to the similarity between the learned knowledge points and the unlearned knowledge points of the student, the learning food preference problem is particularly prominent under the influence of artificial intelligence recommendation, whether the student has food preference can be clearly determined by calculating the food preference degree of the student, the knowledge points recommended by the treatment of food preference can help the student to make up for the repeated reviewing and attention of the overlooked and unfocused knowledge points, and therefore the learning food preference problem of artificial intelligence auxiliary stimulation can be effectively overcome.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an artificial intelligence autonomous learning education robot for overcoming food preference.
Background
Under the prior art, early research finds that when artificial intelligence is used for education, students can be helped to find learning contents which the students want to find more quickly and automatically, or students are helped to find learning contents which the students do not master yet.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art: under the prior art, because the artificial intelligence can help the student to find the content that the student wants to find more quickly, that is to say, the artificial intelligence is good for the student, the good for the student often limits to the local of course knowledge system, and the data that the artificial intelligence helps the student to find at this moment also only limits to local knowledge, can shield all other data irrelevant with the knowledge that the student wants to find moreover for the student loses the chance of independent selection. Under the condition of no artificial intelligence auxiliary education, students can see all the data when searching for learning data and then select the knowledge wanted by themselves from all the data, and although the students have the wanted knowledge, the students can also know other knowledge and even possibly have interest in other knowledge when searching for the data, thereby being capable of partially overcoming the food preference and the food choosing in an intangible way. If the local knowledge desired by the student is compared to the student's preferred diet, then artificial intelligence can encourage and expedite the student's "food preference," resulting in less comprehensive learning of the course knowledge by the student in education with the assistance of artificial intelligence than in education without the assistance of artificial intelligence. Meanwhile, in the prior art, the artificial intelligence finds out the learning content which is not mastered by the student according to the examination and recommends the knowledge to the student pertinently, so that the student can master the knowledge related to the examination paper better with the help of the artificial intelligence, the knowledge irrelevant to the examination paper can be automatically screened by the artificial intelligence, and the student cannot see the knowledge, so that the student loses the opportunity of independent selection. Under the condition of no artificial intelligence assistance, when a student reviews after making a wrong question, the student looks over the data, browses all knowledge in the process of looking over the data, and possibly reviews the contents which are not related to the examination paper but not mastered together. If the local knowledge involved in the test paper is compared with the food preferred by the test paper, the artificial intelligence can promote and accelerate the 'food preference' of the test paper, and the defect of the education to be tested is amplified, so that the students can not master the course knowledge more comprehensively in the education with the artificial intelligence assistance than in the education without the artificial intelligence assistance.
Accordingly, the prior art is yet to be improved and developed.
Disclosure of Invention
Based on this, it is necessary to provide an artificial intelligence autonomous learning education robot for overcoming the defects or shortcomings of the prior art, so as to prevent the problem of aggravated learning of "food preference" of students under the influence of artificial intelligence recommendation and the like, and enable the students to comprehensively and autonomously grasp course knowledge relatively comprehensively.
In a first aspect, an embodiment of the present invention provides an artificial intelligence method, where the method includes:
course knowledge graph establishing: establishing a curriculum knowledge graph;
a learning knowledge graph establishing step: copying a knowledge graph of the course as a learning knowledge graph; acquiring on-line learning data of a student or/and off-line learning data of the student through a camera, inputting the data into a data knowledge point prediction model, and calculating to obtain output as a knowledge point for autonomous learning of the student; judging whether each node in the learning knowledge graph belongs to a knowledge point which has been learned by a student, if so, adding 'the knowledge point which has been learned by the student' in the attribute of the node, and otherwise, adding 'the knowledge point which has not been learned by the student';
calculating the food preference degree: calculating the mean value of the similarity correlation degrees between every two nodes of which the attributes are 'knowledge points which have been learned by students' in each level of learning knowledge map to obtain the mean value of the similarity correlation degrees of the learned knowledge in each level, and calculating the mean value of the mean values of the similarity correlation degrees of the learned knowledge in all levels to be used as a first mean value; calculating the mean value of the similarity correlation degrees between every two nodes in each level of the learning knowledge graph to obtain the mean value of the knowledge similarity correlation degrees of each level, and calculating the mean value of the knowledge similarity correlation degrees of all levels to be used as a second mean value; dividing the first average value by the second average value to obtain the food preference degree of the learning knowledge graph;
the treatment steps of overcoming food preference are as follows: acquiring at least one preset level and the number of nodes of which the attribute of each level comprises knowledge points which are not learned by students, or acquiring at least one preset level and the number of nodes of which the attribute comprises knowledge points which are not learned by students, or acquiring conditions related to learning of a knowledge map as preset conditions; selecting a node set from the learning knowledge graph according to preset conditions to obtain each node set meeting the preset conditions, and copying the learning knowledge graph into a temporary learning knowledge graph; changing 'knowledge points which are not learned by students' and are included in the attributes of the nodes belonging to each node set in the temporary learning knowledge graph into 'knowledge points which have been learned by students', and calculating the food preference degree of the temporary learning knowledge graph; and selecting a knowledge point set corresponding to a node in each node set corresponding to the temporary learning knowledge graph with the minimum food preference degree as a knowledge point set capable of overcoming the food preference and recommending the knowledge point set to relevant teachers and students.
Preferably, the method further comprises:
the method comprises the following steps of establishing a knowledge point similarity correlation degree prediction model: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a knowledge point similarity correlation degree prediction model; taking two knowledge points with a common father node in each of the training and testing samples and the similarity correlation degree of the two knowledge points as the input and the expected output of a knowledge point similarity correlation degree prediction model, and training and testing the knowledge point similarity correlation degree prediction model;
the method for using the knowledge point similarity correlation degree prediction model comprises the following steps: and taking two knowledge points to be predicted with a common father node as the input of a knowledge point similarity correlation degree prediction model for calculation, and taking the obtained output as the similarity correlation degree of the two knowledge points.
Preferably, the method further comprises:
pre-warning steps of food preference: when the food preference degree of a learning knowledge graph of a certain student exceeds an early warning threshold value, sending early warning of food preference to a teacher of the student and the student; when the average value of the food preference degrees of the learning knowledge maps of each student in a certain classroom exceeds an early warning threshold value, sending early warning of food preference to teachers in the classroom; when the average value of the food preference degrees of the learning knowledge graph of each student in a certain course exceeds an early warning threshold value, sending early warning of food preference to a teacher in the course;
reminding after food preference early warning: reminding relevant teachers to tutor according to the knowledge points recommended by the treatment step of overcoming the food preference and food preference, and reminding students to review according to the knowledge points recommended by the treatment step of overcoming the food preference and food preference;
recommending after the food preference early warning: searching by using a knowledge point recommended in the treatment step of overcoming the food preference as a keyword from a search engine to obtain learning materials and recommend the learning materials to relevant teachers and students; and searching knowledge points recommended by the treatment step of overcoming the food preference and food preference according to the knowledge point labels of the data from the data big data to obtain data corresponding to the knowledge points recommended by the treatment step of overcoming the food preference and food preference, and recommending the data to relevant teachers and students.
Preferably, the method further comprises:
the method comprises the following steps of: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a data knowledge point prediction model; taking each learning material and a knowledge point corresponding to each learning material in the training and testing sample as the input and expected output of the material knowledge point prediction model, and training and testing the material knowledge point prediction model;
the method for using the data knowledge point prediction model comprises the following steps: calculating the learning material to be predicted as the input of the material knowledge point prediction model, and taking the obtained output as the knowledge point corresponding to the learning material;
data big data labeling step: inputting each data in the big data of the data into a data knowledge point prediction model for calculation, and using the obtained output as a knowledge point label of each data;
the test question knowledge point prediction model construction step: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a test question knowledge point prediction model; taking each test question in the training and testing sample and a knowledge point corresponding to each test question material as the input and expected output of a test question knowledge point prediction model, and training and testing the test question knowledge point prediction model;
the test question prediction model application steps are as follows: and taking the test question to be predicted as the input of the test question knowledge point prediction model for calculation, and taking the obtained output as the knowledge point corresponding to the test question.
Preferably, the method further comprises:
and in normal times, overcoming food preference recommending steps: acquiring the latest learning data of a student, inputting the output obtained by calculation of a data knowledge point prediction model as the latest learning knowledge point, inquiring at least 2 knowledge points from a learning knowledge map, wherein the knowledge points have the maximum similarity with the latest learning knowledge point, the Nth-highest similarity, the smallest similarity and the parent node of the corresponding node of the latest learning knowledge point, retrieving the data corresponding to all the inquired knowledge points by a search engine or data big data and recommending the data to the student, and if the retrieval fails, retrieving the data corresponding to all the inquired knowledge points by the search engine or the data big data and recommending the data to the student.
Preferably, the method further comprises:
and (3) testing, overcoming food preference and recommending: the method comprises the steps of obtaining a test question of a student which has an error recently, inputting output obtained by calculation of a test question knowledge point prediction model as a knowledge point of the error recently, inquiring at least 2 knowledge points from a learning knowledge map corresponding to a knowledge point with the maximum similarity to the knowledge point of the error recently, a knowledge point with the Nth maximum similarity, a knowledge point with the minimum similarity and a parent node of the knowledge point corresponding to the error recently, retrieving data corresponding to the inquired knowledge points through a search engine or data big data and recommending the data to the student, and if the acquisition fails, respectively retrieving the data corresponding to the inquired knowledge points through the search engine or the data big data and recommending the data to the student.
In a second aspect, an embodiment of the present invention provides an artificial intelligence system, where the system includes:
the course knowledge graph establishing module: establishing a curriculum knowledge graph;
a learning knowledge graph establishing module: copying a knowledge graph of the course as a learning knowledge graph; acquiring on-line learning data of a student or/and off-line learning data of the student through a camera, inputting the data into a data knowledge point prediction model, and calculating to obtain output as a knowledge point for autonomous learning of the student; judging whether each node in the learning knowledge graph belongs to a knowledge point which has been learned by a student, if so, adding 'the knowledge point which has been learned by the student' in the attribute of the node, and otherwise, adding 'the knowledge point which has not been learned by the student';
the food preference degree calculating module is used for: calculating the mean value of the similarity correlation degrees between every two nodes of which the attributes are 'knowledge points which have been learned by students' in each level of learning knowledge map to obtain the mean value of the similarity correlation degrees of the learned knowledge in each level, and calculating the mean value of the mean values of the similarity correlation degrees of the learned knowledge in all levels to be used as a first mean value; calculating the mean value of the similarity correlation degrees between every two nodes in each level of the learning knowledge graph to obtain the mean value of the knowledge similarity correlation degrees of each level, and calculating the mean value of the knowledge similarity correlation degrees of all levels to be used as a second mean value; dividing the first average value by the second average value to obtain the food preference degree of the learning knowledge graph;
overcome "food preference" treatment module: acquiring at least one preset level and the number of nodes of which the attribute of each level comprises knowledge points which are not learned by students, or acquiring at least one preset level and the number of nodes of which the attribute comprises knowledge points which are not learned by students, or acquiring conditions related to learning of a knowledge map as preset conditions; selecting a node set from the learning knowledge graph according to preset conditions to obtain each node set meeting the preset conditions, and copying the learning knowledge graph into a temporary learning knowledge graph; changing 'knowledge points which are not learned by students' and are included in the attributes of the nodes belonging to each node set in the temporary learning knowledge graph into 'knowledge points which have been learned by students', and calculating the food preference degree of the temporary learning knowledge graph; and selecting a knowledge point set corresponding to a node in each node set corresponding to the temporary learning knowledge graph with the minimum food preference degree as a knowledge point set capable of overcoming the food preference and recommending the knowledge point set to relevant teachers and students.
Preferably, the system further comprises:
the knowledge point similarity correlation degree prediction model construction module comprises: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a knowledge point similarity correlation degree prediction model; taking two knowledge points with a common father node in each of the training and testing samples and the similarity correlation degree of the two knowledge points as the input and the expected output of a knowledge point similarity correlation degree prediction model, and training and testing the knowledge point similarity correlation degree prediction model;
the knowledge point similarity correlation degree prediction model application module comprises: and taking two knowledge points to be predicted with a common father node as the input of a knowledge point similarity correlation degree prediction model for calculation, and taking the obtained output as the similarity correlation degree of the two knowledge points.
Preferably, the system further comprises:
the pre-warning module for food preference: when the food preference degree of a learning knowledge graph of a certain student exceeds an early warning threshold value, sending early warning of food preference to a teacher of the student and the student; when the average value of the food preference degrees of the learning knowledge maps of each student in a certain classroom exceeds an early warning threshold value, sending early warning of food preference to teachers in the classroom; when the average value of the food preference degrees of the learning knowledge graph of each student in a certain course exceeds an early warning threshold value, sending early warning of food preference to a teacher in the course;
the reminding module after the food preference early warning: reminding relevant teachers to tutor according to the knowledge points recommended by the treatment module for overcoming the food preference and food preference, and reminding students to review according to the knowledge points recommended by the treatment module for overcoming the food preference and food preference;
the recommendation module after the food preference early warning: searching by using a knowledge point which is recommended by a treatment module for overcoming food preference as a keyword from a search engine to obtain learning materials and recommend the learning materials to relevant teachers and students; and searching knowledge points recommended by the treatment module for overcoming the food preference and food preference according to the knowledge point labels of the data from the data big data to obtain data corresponding to the knowledge points recommended by the treatment module for overcoming the food preference and food preference, and recommending the data to relevant teachers and students.
Preferably, the system further comprises:
the data knowledge point prediction model construction module comprises: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a data knowledge point prediction model; taking each learning material and a knowledge point corresponding to each learning material in the training and testing sample as the input and expected output of the material knowledge point prediction model, and training and testing the material knowledge point prediction model;
the data knowledge point prediction model application module comprises: calculating the learning material to be predicted as the input of the material knowledge point prediction model, and taking the obtained output as the knowledge point corresponding to the learning material;
data big data labeling module: inputting each data in the big data of the data into a data knowledge point prediction model for calculation, and using the obtained output as a knowledge point label of each data;
the test question knowledge point prediction model construction module comprises: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a test question knowledge point prediction model; taking each test question in the training and testing sample and a knowledge point corresponding to each test question material as the input and expected output of a test question knowledge point prediction model, and training and testing the test question knowledge point prediction model;
the test question prediction model application module comprises: and taking the test question to be predicted as the input of the test question knowledge point prediction model for calculation, and taking the obtained output as the knowledge point corresponding to the test question.
Preferably, the system further comprises:
overcome food preference recommending module at ordinary times: acquiring the latest learning data of a student, inputting the output obtained by calculation of a data knowledge point prediction model as the latest learning knowledge point, inquiring at least 2 knowledge points from a learning knowledge map, wherein the knowledge points have the maximum similarity with the latest learning knowledge point, the Nth-highest similarity, the smallest similarity and the parent node of the corresponding node of the latest learning knowledge point, retrieving the data corresponding to all the inquired knowledge points by a search engine or data big data and recommending the data to the student, and if the retrieval fails, retrieving the data corresponding to all the inquired knowledge points by the search engine or the data big data and recommending the data to the student.
Preferably, the system further comprises:
the test overcoming food preference recommending module comprises: the method comprises the steps of obtaining a test question of a student which has an error recently, inputting output obtained by calculation of a test question knowledge point prediction model as a knowledge point of the error recently, inquiring at least 2 knowledge points from a learning knowledge map corresponding to a knowledge point with the maximum similarity to the knowledge point of the error recently, a knowledge point with the Nth maximum similarity, a knowledge point with the minimum similarity and a parent node of the knowledge point corresponding to the error recently, retrieving data corresponding to the inquired knowledge points through a search engine or data big data and recommending the data to the student, and if the acquisition fails, respectively retrieving the data corresponding to the inquired knowledge points through the search engine or the data big data and recommending the data to the student.
In a third aspect, an embodiment of the present invention provides an artificial intelligence apparatus, where the apparatus includes the modules of the system in any one of the embodiments of the second aspect.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method according to any one of the embodiments of the first aspect.
In a fifth aspect, an embodiment of the present invention provides a robot, including a memory, a processor, and an artificial intelligence robot program stored in the memory and executable on the processor, where the processor executes the program to implement the steps of the method according to any one of the embodiments of the first aspect.
The artificial intelligence autonomous learning education robot that overcomes "food preference" that this embodiment provided includes: establishing a course knowledge graph; establishing a learning knowledge graph; calculating the monophagia and monophagia degree; overcomes the treatment steps of food preference and food preference. According to the method, the system and the robot, the curriculum knowledge map is constructed to analyze other knowledge points which are overlooked due to over-focus of part of knowledge points in the learning process of the student, whether the student has drilled into a locally related similar knowledge point set or not can be known according to the similarity between the learned knowledge points and the non-learned knowledge points of the student, the learning food preference problem is particularly prominent under the influence of artificial intelligence recommendation, whether the student has food preference or not can be clear through calculation of the food preference degree, the knowledge points recommended by the food preference treatment can be overcome to help the student to perform compensatory review and attention on the overlooked and unfocused knowledge points, and therefore the learning food preference problem of artificial intelligence auxiliary stimulation can be effectively overcome.
Drawings
FIG. 1 is a flow diagram of an artificial intelligence method provided by one embodiment of the invention;
FIG. 2 is a flow diagram of an artificial intelligence method comprising according to an embodiment of the invention;
FIG. 3 is a flow chart of an artificial intelligence method comprising according to an embodiment of the invention;
FIG. 4 is a flow chart of an artificial intelligence method according to an embodiment of the present invention.
Detailed Description
The technical solutions in the examples of the present invention are described in detail below with reference to the embodiments of the present invention.
Basic embodiment of the invention
One embodiment of the present invention provides an artificial intelligence method, as shown in fig. 1, the method including: establishing a course knowledge graph; establishing a learning knowledge graph; calculating the monophagia and monophagia degree; overcomes the treatment steps of food preference and food preference. The technical effects are as follows: according to the method, the curriculum knowledge graph is constructed to analyze other knowledge points which are overlooked when the student excessively pays attention to partial knowledge points in the learning process, whether the student has drilled into a locally related similar knowledge point set or not can be known according to the similarity between the learned knowledge points and the non-learned knowledge points of the student based on big data, the learning food preference problem is particularly prominent under the influence of artificial intelligence recommendation, whether the student has food preference or not can be clear by calculating the food preference degree based on the knowledge graph, the knowledge points recommended by the treatment of food preference can help the student to carry out compensatory review and attention on the overlooked and non-attended knowledge points by overcoming the food preference degree based on the big data, and therefore the learning food preference problem of artificial intelligence auxiliary stimulation can be effectively overcome.
In a preferred embodiment, as shown in fig. 2, the method further comprises: constructing a knowledge point similarity correlation degree prediction model; and using a knowledge point similarity correlation degree prediction model. The technical effects are as follows: the method can learn whether the learning of students is trapped in local knowledge aggregation with high similarity correlation degree through knowledge point similarity correlation degree prediction based on artificial intelligence algorithms such as deep learning.
In a preferred embodiment, as shown in fig. 3, the method further comprises: pre-warning about food preference; reminding after the food preference early warning; and recommending after the food preference early warning. The technical effects are as follows: the method can help teachers and students to overcome local knowledge sets which are misled by artificial intelligence through the food preference early warning and reminding, and can move to the local knowledge sets as soon as possible through limited knowledge points, so that the symptoms of food preference are eliminated.
In a preferred embodiment, as shown in fig. 4, the method further comprises: constructing a data knowledge point prediction model; using a data knowledge point prediction model; labeling big data of the data; building a test question knowledge point prediction model; and (3) using the test question prediction model. The technical effects are as follows: the method is based on an artificial intelligent algorithm such as deep learning, and the like, and the relationship is established among the data, the test questions and the knowledge points, so that the data learned by students and the test questions in the test can be corresponding to the knowledge points in the knowledge map, and a basis and a condition are provided for the prediction and elimination of the food preference.
In a preferred embodiment, the method further comprises: and overcoming the food preference recommending step in normal times. The technical effects are as follows: the method is based on the knowledge map, and by overcoming food preference recommendation at ordinary times, the method helps students to overcome food preference possibly caused by self or artificial intelligence recommendation in the process of learning at ordinary times, so that the effect of preventing diseases is achieved.
In a preferred embodiment, the method further comprises: and (5) testing and overcoming the preference and food recommendation steps. The technical effects are as follows: the method overcomes the food preference recommendation through the test based on the knowledge map, helps students to overcome the food preference possibly caused by self or artificial intelligence recommendation when reviewing after the test and examination are finished, and thus the effect of preventing diseases is achieved.
The multidimensional content recommendation which is liked by the students and can avoid food preference is screened out based on big data, knowledge maps and deep learning, so that the advantage that the learning efficiency is improved by artificial intelligence is kept, the learning independent selection right is returned to the students, and the method has extremely important significance for overcoming the loss of learning independent right caused by artificial intelligence.
PREFERRED EMBODIMENTS OF THE PRESENT INVENTION
Course knowledge graph establishing: and establishing a course knowledge graph. The knowledge of the course is divided into i-level knowledge points (i takes values from 1 to N continuously, and N is a natural number greater than or equal to 1); the knowledge of each course has at least one level of knowledge points; the first-level knowledge points are the knowledge points with the highest level and also the coarsest knowledge points; the N-level knowledge points are the knowledge points of the lowest level and are also the finest knowledge points; the i + 1-level knowledge points are more specific and finer than the i-level knowledge points, and the i + 1-level knowledge points are concreteness and fineness of the i-level knowledge points; taking the i-level knowledge points as nodes of the curriculum knowledge graph; establishing an edge between an i-level knowledge point and an i + 1-level knowledge point, and taking a parent-child relationship between the i-level knowledge point and the i + 1-level knowledge point as the attribute of the edge, wherein the i-level knowledge point in the parent-child relationship is a parent and the i + 1-level knowledge point in the parent-child relationship is a child; one i-level knowledge point corresponds to one or more i + 1-level knowledge points; if the number of the i-level knowledge points is more than 1, establishing an edge between every two i-level knowledge points; taking the similarity correlation degree of every two i-level knowledge points with a common father node as the attribute of an edge between every two i-level knowledge points; and dividing the similarity correlation between two father nodes of every two i-level knowledge points without a common father node by the number of children of each father node to obtain the similarity correlation between every two i-level knowledge points as the attribute of the edge between every two i-level knowledge points. For example, a similarity of 50% indicates a half similarity or correlation.
The method comprises the following steps of establishing a knowledge point similarity correlation degree prediction model: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a knowledge point similarity correlation degree prediction model; taking two knowledge points with a common father node in each of the training and testing samples and the similarity correlation degree of the two knowledge points as the input and the expected output of a knowledge point similarity correlation degree prediction model, and training and testing the knowledge point similarity correlation degree prediction model;
the method for using the knowledge point similarity correlation degree prediction model comprises the following steps: calculating two knowledge points to be predicted with a common father node as the input of a knowledge point similarity correlation degree prediction model, and taking the obtained output as the similarity correlation degree of the two knowledge points;
a learning knowledge graph establishing step: copying a knowledge graph of the course as a learning knowledge graph; acquiring on-line learning data of a student or/and off-line learning data of the student through a camera, inputting the data into a data knowledge point prediction model, and calculating to obtain output as a knowledge point for autonomous learning of the student; judging whether each node in the learning knowledge graph belongs to a knowledge point which has been learned by a student, if so, adding ' the knowledge point which has been learned by the student ' in the attribute of the node ' (the attribute of learning times can be further added to the node containing ' the knowledge point which has been learned by the student '), and if not, adding ' the knowledge point which has not been learned by the student ';
calculating the food preference degree: calculating the average value of the similarity correlation degrees between every two nodes with the attribute of the knowledge point which is learned by the student in each level of the learning knowledge graph, obtaining the weighted average value of the similarity correlation degrees of the learned knowledge in each level (if the attribute of the learning times is existed, the weighted average value of the similarity correlation degrees between every two nodes with the attribute of the knowledge point which is learned by the student in each level of the learning knowledge graph and the product of the learning times of the two nodes is calculated (for example, the node A, B, C, the learning times of A is 2, the learning times of B is 5, the learning times of C is 3, the similarity correlation degree of AB is 0.5, the similarity correlation degree of AC is 0.6, the similarity correlation degree of CB is 0.8, the similarity correlation degree of CB is (2 x 5 x 0.5+2 x 3 x 0.6+3 x 5 x 0.8)/(2 x 5+2 x 3+3 x 3) and the average value of the learned knowledge correlation degrees of all levels is calculated), as a first average; calculating the mean value of the similarity correlation degrees between every two nodes in each level of the learning knowledge graph to obtain the mean value of the knowledge similarity correlation degrees of each level, and calculating the mean value of the knowledge similarity correlation degrees of all levels to be used as a second mean value; dividing the first average value by the second average value to obtain the food preference degree of the learning knowledge graph;
the treatment steps of overcoming food preference are as follows: obtaining at least one preset level (such as a first level and a fourth level) and the number of nodes (such as a first level 2 nodes and a fourth level 3 nodes) of which the attribute comprises the knowledge points which are not learned by students, or obtaining at least one preset level (such as a first level and a fourth level) and the number of nodes (such as 5 nodes, namely the number of the first level nodes and the number of the fourth level nodes are 5) of which the attribute comprises the knowledge points which are not learned by students, or obtaining the number of nodes (such as 5 nodes) of which the attribute comprises the knowledge points which are not learned by students, as a preset condition, selecting a node set from a learning knowledge map according to the preset condition to obtain each node set meeting the preset condition, copying the learning knowledge map into a temporary learning knowledge map, and obtaining the 'knowledge points which are not learned' and are included by the attribute of the nodes in each node set in the temporary learning knowledge map Changing the learning knowledge map into knowledge points which have already been learned by students, and calculating the food preference degree of the temporary learning knowledge map; and selecting a knowledge point set corresponding to a node in each node set corresponding to the temporary learning knowledge graph with the minimum food preference degree as a knowledge point set capable of overcoming the food preference and recommending the knowledge point set to relevant teachers and students.
Pre-warning steps of food preference: when the food preference degree of a learning knowledge graph of a certain student exceeds an early warning threshold value, sending early warning of food preference to a teacher of the student and the student; when the average value of the food preference degrees of the learning knowledge maps of each student in a certain classroom exceeds an early warning threshold value, sending early warning of food preference to teachers in the classroom; when the average value of the food preference degrees of the learning knowledge graph of each student in a certain course exceeds an early warning threshold value, sending early warning of food preference to a teacher in the course;
reminding after food preference early warning: reminding relevant teachers to tutor according to the knowledge points recommended by the treatment step of overcoming the food preference and food preference, and reminding students to review according to the knowledge points recommended by the treatment step of overcoming the food preference and food preference;
recommending after the food preference early warning: searching by using a knowledge point recommended by the treatment step of overcoming 'food preference and food preference' as a keyword from a search engine (such as Google and Baidu), and obtaining learning materials and recommending the learning materials to relevant teachers and students; searching knowledge points recommended by the treatment step of overcoming the food preference and food preference according to the knowledge point labels of the data from the data big data to obtain data corresponding to the knowledge points recommended by the treatment step of overcoming the food preference and food preference, and recommending the data to relevant teachers and students;
data big data labeling step: inputting each data in the big data into a data knowledge point prediction model for calculation, and using the obtained output as a knowledge point label of each data.
The method comprises the following steps of: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a data knowledge point prediction model; taking each learning material and a knowledge point corresponding to each learning material in the training and testing sample as the input and expected output of the material knowledge point prediction model, and training and testing the material knowledge point prediction model;
the method for using the data knowledge point prediction model comprises the following steps: calculating the learning material to be predicted as the input of the material knowledge point prediction model, and taking the obtained output as the knowledge point corresponding to the learning material;
the test question knowledge point prediction model construction step: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a test question knowledge point prediction model; taking each test question in the training and testing sample and a knowledge point corresponding to each test question material as the input and expected output of a test question knowledge point prediction model, and training and testing the test question knowledge point prediction model;
the test question prediction model application steps are as follows: taking the test questions to be predicted as the input of a test question knowledge point prediction model for calculation, and taking the obtained output as the knowledge points corresponding to the test questions;
and in normal times, overcoming food preference recommending steps: acquiring the latest learning data of a student, inputting the output calculated by a data knowledge point prediction model as the latest learning knowledge point, inquiring a knowledge point with the maximum similarity to the latest learning knowledge point, a knowledge point with the Nth maximum similarity (N defaults to 2, N is set as a natural number which is greater than or equal to 2), a knowledge point with the minimum similarity and a knowledge point corresponding to a parent node of a corresponding node of the latest learning knowledge point from a learning knowledge map (any two knowledge points can also be inquired), respectively retrieving the data corresponding to all the knowledge points by a search engine or data big data and recommending the data to the student, if the acquisition fails, respectively retrieving the knowledge point with the maximum similarity to the latest learning knowledge point by the search engine or data big data and recommending the data corresponding to the Nth maximum similarity to the student, and retrieving the data corresponding to the knowledge point with the minimum similarity and recommending the data to the student, retrieving the data corresponding to the knowledge point corresponding to the parent node of the knowledge point corresponding to the most recently learned knowledge point and recommending the data to the student, and if the retrieval fails, retrieving the data corresponding to each knowledge point and recommending the data to the student through a search engine or data big data respectively (or recommending according to any two knowledge points, the steps are the same). During recommendation, on one hand, the most imaginable students are recommended, on the other hand, the half imaginable students are recommended, such as the second similar knowledge points, on the other hand, the half imaginable students are recommended, on the other hand, the knowledge points corresponding to the father nodes are also recommended, so that the students are very relevant and interested, and the students can grasp the students from a macroscopic view and a global view without feeling well and blindly for the students to select independently mainly according to the similarity. 3 are recommended, so that the time cost for the students to search for the data in the sea is reduced, and the possibility of independent selection of the students is ensured.
And (3) testing, overcoming food preference and recommending: acquiring a test question of a student making an error, inputting output obtained by calculation of a test question knowledge point prediction model as a knowledge point making an error last time, inquiring a knowledge point with the maximum similarity to the knowledge point making an error last time, a knowledge point with the Nth highest similarity (N is defaulted to be 2, N is set to be a natural number which is greater than or equal to 2), a knowledge point with the minimum similarity and a knowledge point corresponding to a parent node of a corresponding node of the knowledge point making an error last time from a learning knowledge map (any two knowledge points can be inquired), respectively retrieving data corresponding to all the knowledge points by a search engine or data big data and recommending the students, if the acquisition fails, respectively retrieving the knowledge point with the maximum similarity to the knowledge point making an error last time and the data corresponding to the Nth highest similarity by the search engine or data big data and recommending the students, and retrieving the data corresponding to the knowledge point with the minimum similarity and recommending the data to students, retrieving the data corresponding to the knowledge point corresponding to the parent node of the node corresponding to the knowledge point which has made an error last time and recommending the data to students, and if the retrieval fails, retrieving the data corresponding to each knowledge point and recommending the data to students through a search engine or data big data (or recommending according to any two knowledge points, the steps are the same). When recommending, on one hand, the student is recommended to be the most needed to see, on the other hand, the student is recommended to be the least needed to see, on the other hand, the student is recommended to be the half needed to see and the half needed to see, for example, the second similar knowledge point, on the other hand, the knowledge point corresponding to the parent node is recommended, on the one hand, the relation is good, the student is interested, and the student can be held macroscopically and globally without headache and headache, and the student can independently select the student mainly according to the similarity. 3 are recommended, so that the time cost for the students to search for the data in the sea is reduced, and the possibility of independent selection of the students is ensured.
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 those skilled in the art, various changes and modifications can be made without departing from the spirit of the present invention, and these changes and modifications are within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. An artificial intelligence method, the method comprising:
course knowledge graph establishing: establishing a curriculum knowledge graph;
a learning knowledge graph establishing step: copying a knowledge graph of the course as a learning knowledge graph; acquiring on-line learning data of a student or/and off-line learning data of the student through a camera, inputting the data into a data knowledge point prediction model, and calculating to obtain output as a knowledge point for autonomous learning of the student; judging whether each node in the learning knowledge graph belongs to a knowledge point which has been learned by a student, if so, adding 'the knowledge point which has been learned by the student' in the attribute of the node, and otherwise, adding 'the knowledge point which has not been learned by the student';
calculating the food preference degree: calculating the mean value of the similarity correlation degrees between every two nodes of which the attributes are 'knowledge points which have been learned by students' in each level of learning knowledge map to obtain the mean value of the similarity correlation degrees of the learned knowledge in each level, and calculating the mean value of the mean values of the similarity correlation degrees of the learned knowledge in all levels to be used as a first mean value; calculating the mean value of the similarity correlation degrees between every two nodes in each level of the learning knowledge graph to obtain the mean value of the knowledge similarity correlation degrees of each level, and calculating the mean value of the knowledge similarity correlation degrees of all levels to be used as a second mean value; dividing the first average value by the second average value to obtain the food preference degree of the learning knowledge graph;
the treatment steps of overcoming food preference are as follows: acquiring at least one preset level and the number of nodes of which the attribute of each level comprises knowledge points which are not learned by students, or acquiring at least one preset level and the number of nodes of which the attribute comprises knowledge points which are not learned by students, or acquiring conditions related to learning of a knowledge map as preset conditions; selecting a node set from the learning knowledge graph according to preset conditions to obtain each node set meeting the preset conditions, and copying the learning knowledge graph into a temporary learning knowledge graph; changing 'knowledge points which are not learned by students' and are included in the attributes of the nodes belonging to each node set in the temporary learning knowledge graph into 'knowledge points which have been learned by students', and calculating the food preference degree of the temporary learning knowledge graph; and selecting a knowledge point set corresponding to a node in each node set corresponding to the temporary learning knowledge graph with the minimum food preference degree as a knowledge point set capable of overcoming the food preference and recommending the knowledge point set to relevant teachers and students.
2. The artificial intelligence method of claim 1, wherein the method further comprises:
the method comprises the following steps of establishing a knowledge point similarity correlation degree prediction model: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a knowledge point similarity correlation degree prediction model; taking two knowledge points with a common father node in each of the training and testing samples and the similarity correlation degree of the two knowledge points as the input and the expected output of a knowledge point similarity correlation degree prediction model, and training and testing the knowledge point similarity correlation degree prediction model;
the method for using the knowledge point similarity correlation degree prediction model comprises the following steps: and taking two knowledge points to be predicted with a common father node as the input of a knowledge point similarity correlation degree prediction model for calculation, and taking the obtained output as the similarity correlation degree of the two knowledge points.
3. The artificial intelligence method of claim 1, wherein the method further comprises:
pre-warning steps of food preference: when the food preference degree of a learning knowledge graph of a certain student exceeds an early warning threshold value, sending early warning of food preference to a teacher of the student and the student; when the average value of the food preference degrees of the learning knowledge maps of each student in a certain classroom exceeds an early warning threshold value, sending early warning of food preference to teachers in the classroom; when the average value of the food preference degrees of the learning knowledge graph of each student in a certain course exceeds an early warning threshold value, sending early warning of food preference to a teacher in the course;
reminding after food preference early warning: reminding relevant teachers to tutor according to the knowledge points recommended by the treatment step of overcoming the food preference and food preference, and reminding students to review according to the knowledge points recommended by the treatment step of overcoming the food preference and food preference;
recommending after the food preference early warning: searching by using a knowledge point recommended in the treatment step of overcoming the food preference as a keyword from a search engine to obtain learning materials and recommend the learning materials to relevant teachers and students; and searching knowledge points recommended by the treatment step of overcoming the food preference and food preference according to the knowledge point labels of the data from the data big data to obtain data corresponding to the knowledge points recommended by the treatment step of overcoming the food preference and food preference, and recommending the data to relevant teachers and students.
4. The artificial intelligence method of claim 1, wherein the method further comprises:
the method comprises the following steps of: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a data knowledge point prediction model; taking each learning material and a knowledge point corresponding to each learning material in the training and testing sample as the input and expected output of the material knowledge point prediction model, and training and testing the material knowledge point prediction model;
the method for using the data knowledge point prediction model comprises the following steps: calculating the learning material to be predicted as the input of the material knowledge point prediction model, and taking the obtained output as the knowledge point corresponding to the learning material;
data big data labeling step: inputting each data in the big data of the data into a data knowledge point prediction model for calculation, and using the obtained output as a knowledge point label of each data;
the test question knowledge point prediction model construction step: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a test question knowledge point prediction model; taking each test question in the training and testing sample and a knowledge point corresponding to each test question material as the input and expected output of a test question knowledge point prediction model, and training and testing the test question knowledge point prediction model;
the test question prediction model application steps are as follows: and taking the test question to be predicted as the input of the test question knowledge point prediction model for calculation, and taking the obtained output as the knowledge point corresponding to the test question.
5. The artificial intelligence method of claim 4, wherein the method further comprises:
and in normal times, overcoming food preference recommending steps: acquiring the latest learning data of a student, inputting the output obtained by calculation of a data knowledge point prediction model as the latest learning knowledge point, inquiring at least 2 knowledge points from a learning knowledge map, wherein the knowledge points have the maximum similarity with the latest learning knowledge point, the Nth-highest similarity, the smallest similarity and the parent node of the corresponding node of the latest learning knowledge point, retrieving the data corresponding to all the inquired knowledge points by a search engine or data big data and recommending the data to the student, and if the retrieval fails, retrieving the data corresponding to all the inquired knowledge points by the search engine or the data big data and recommending the data to the student.
6. The artificial intelligence method of claim 4, wherein the method further comprises:
and (3) testing, overcoming food preference and recommending: the method comprises the steps of obtaining a test question of a student which has an error recently, inputting output obtained by calculation of a test question knowledge point prediction model as a knowledge point of the error recently, inquiring at least 2 knowledge points from a learning knowledge map corresponding to a knowledge point with the maximum similarity to the knowledge point of the error recently, a knowledge point with the Nth maximum similarity, a knowledge point with the minimum similarity and a parent node of the knowledge point corresponding to the error recently, retrieving data corresponding to the inquired knowledge points through a search engine or data big data and recommending the data to the student, and if the acquisition fails, respectively retrieving the data corresponding to the inquired knowledge points through the search engine or the data big data and recommending the data to the student.
7. An artificial intelligence system, characterized in that the system is adapted to implement the steps of the method of any of claims 1-6.
8. An artificial intelligence device, wherein the device is configured to implement the steps of the method of any of claims 1-6.
9. A robot comprising a memory, a processor and an artificial intelligence robot program stored on the memory and executable on the processor, wherein the steps of the method of any one of claims 1 to 6 are carried out when the program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110228045.4A CN112966121B (en) | 2021-03-02 | 2021-03-02 | Artificial intelligence autonomous learning education robot for overcoming food preference |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110228045.4A CN112966121B (en) | 2021-03-02 | 2021-03-02 | Artificial intelligence autonomous learning education robot for overcoming food preference |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112966121A true CN112966121A (en) | 2021-06-15 |
| CN112966121B CN112966121B (en) | 2023-01-03 |
Family
ID=76276267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110228045.4A Active CN112966121B (en) | 2021-03-02 | 2021-03-02 | Artificial intelligence autonomous learning education robot for overcoming food preference |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112966121B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009053303A (en) * | 2007-08-24 | 2009-03-12 | Nippon Telegr & Teleph Corp <Ntt> | Discussion knowledge graph constructing method, device, and program, and recording medium with program recorded thereon |
| US20140379323A1 (en) * | 2013-06-20 | 2014-12-25 | Microsoft Corporation | Active learning using different knowledge sources |
| US20170124464A1 (en) * | 2015-10-28 | 2017-05-04 | Fractal Industries, Inc. | Rapid predictive analysis of very large data sets using the distributed computational graph |
| CN109903617A (en) * | 2017-12-11 | 2019-06-18 | 北京三好互动教育科技有限公司 | Individualized exercise method and system |
| CN111753098A (en) * | 2020-06-23 | 2020-10-09 | 陕西师范大学 | Teaching method and system based on cross-media dynamic knowledge graph |
| CN111831831A (en) * | 2020-07-17 | 2020-10-27 | 广东金融学院 | Knowledge graph-based personalized learning platform and construction method thereof |
| CN111858951A (en) * | 2019-04-30 | 2020-10-30 | 广东小天才科技有限公司 | Learning recommendation method and device based on knowledge graph and terminal equipment |
-
2021
- 2021-03-02 CN CN202110228045.4A patent/CN112966121B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009053303A (en) * | 2007-08-24 | 2009-03-12 | Nippon Telegr & Teleph Corp <Ntt> | Discussion knowledge graph constructing method, device, and program, and recording medium with program recorded thereon |
| US20140379323A1 (en) * | 2013-06-20 | 2014-12-25 | Microsoft Corporation | Active learning using different knowledge sources |
| US20170124464A1 (en) * | 2015-10-28 | 2017-05-04 | Fractal Industries, Inc. | Rapid predictive analysis of very large data sets using the distributed computational graph |
| CN109903617A (en) * | 2017-12-11 | 2019-06-18 | 北京三好互动教育科技有限公司 | Individualized exercise method and system |
| CN111858951A (en) * | 2019-04-30 | 2020-10-30 | 广东小天才科技有限公司 | Learning recommendation method and device based on knowledge graph and terminal equipment |
| CN111753098A (en) * | 2020-06-23 | 2020-10-09 | 陕西师范大学 | Teaching method and system based on cross-media dynamic knowledge graph |
| CN111831831A (en) * | 2020-07-17 | 2020-10-27 | 广东金融学院 | Knowledge graph-based personalized learning platform and construction method thereof |
Non-Patent Citations (1)
| Title |
|---|
| 王冬青等: "基于知识图谱的个性化习题推荐系统设计研究", 《中国教育信息化》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112966121B (en) | 2023-01-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Epskamp et al. | A tutorial on regularized partial correlation networks. | |
| ElGamal | An educational data mining model for predicting student performance in programming course | |
| CN104573062B (en) | Intelligence learning method based on description logic and reasoning by cases | |
| CN113127731A (en) | Knowledge graph-based personalized test question recommendation method | |
| Yudelson et al. | Investigating automated student modeling in a Java MOOC | |
| CN111914550B (en) | Knowledge graph updating method and system oriented to limited field | |
| Guttman et al. | On the definition and varieties of attitude and wellbeing | |
| Liu et al. | Going beyond better data prediction to create explanatory models of educational data | |
| Nelyub et al. | Machine learning to identify key success indicators | |
| CN112991847A (en) | Artificial intelligence drive-based omnibearing multifunctional intelligent programming teaching system | |
| Pujianto et al. | Students Academic Performance Prediction with k-Nearest Neighbor and C4. 5 on SMOTE-balanced data | |
| Song et al. | Pluggable reputation systems for peer review: A web-service approach | |
| CN112966121B (en) | Artificial intelligence autonomous learning education robot for overcoming food preference | |
| Lonij et al. | Open-world visual recognition using knowledge graphs | |
| Siew | Investigating cognitive network models of learners’ knowledge representations | |
| Shehata et al. | Enhancing video-based learning using knowledge tracing: Personalizing students’ learning experience with ORBITS | |
| CN115858725B (en) | Text noise screening method and system based on unsupervised graph neural network | |
| CN114328633B (en) | Wrong question knowledge point reinforcement training test question recommendation method based on concept lattice | |
| CN112785001B (en) | Artificial intelligence educational back-province robot for overcoming discrimination and prejudice | |
| CN112926901B (en) | Structured capacity model construction method for learning analysis and evaluation | |
| CN114492156A (en) | Student score prediction method, system, computer and medium based on big data | |
| Redfield et al. | The future of intelligent tutoring systems | |
| Nuñez et al. | Semi-supervised regression based on tree SOMs for predicting students performance | |
| Mayer et al. | Using subgroup discovery and latent growth curve modeling to identify unusual developmental trajectories | |
| WO2016105182A1 (en) | Method for automatic diagrammatic question generation and answer assessment |
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 |