CN112965703B - Teacher leading artificial intelligence education robot for overcoming multi-head leaders - Google Patents
Teacher leading artificial intelligence education robot for overcoming multi-head leaders Download PDFInfo
- Publication number
- CN112965703B CN112965703B CN202110228044.XA CN202110228044A CN112965703B CN 112965703 B CN112965703 B CN 112965703B CN 202110228044 A CN202110228044 A CN 202110228044A CN 112965703 B CN112965703 B CN 112965703B
- Authority
- CN
- China
- Prior art keywords
- artificial intelligence
- program
- code
- principle description
- segment
- 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
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 225
- 238000000034 method Methods 0.000 claims abstract description 79
- 238000012986 modification Methods 0.000 claims abstract description 49
- 230000004048 modification Effects 0.000 claims abstract description 49
- 230000000694 effects Effects 0.000 claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims description 25
- 238000012360 testing method Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 16
- 238000011156 evaluation Methods 0.000 claims description 14
- 238000012827 research and development Methods 0.000 claims description 14
- 235000020803 food preference Nutrition 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000013136 deep learning model Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 14
- 238000005070 sampling Methods 0.000 abstract description 6
- 238000013135 deep learning Methods 0.000 abstract description 5
- 230000002411 adverse Effects 0.000 abstract description 3
- 238000011161 development Methods 0.000 abstract description 3
- 244000309464 bull Species 0.000 abstract 1
- 230000007547 defect Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/31—Programming languages or programming paradigms
-
- 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)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Strategic Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Tourism & Hospitality (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Overcome teacher leading artificial intelligence education robot of bull leader, include: example reporting step; a principle description modification step; modifying artificial intelligence codes; and replacing the artificial intelligence codes. According to the method, the system and the robot, the dominant right is returned to the hands of the teacher again through sampling examination on the basis of deep learning and big data by sampling examination of the learning auxiliary examples of the artificial intelligence and reporting to the teacher, meanwhile, the artificial intelligence has certain degree of freedom, the effect and the effect of the artificial intelligence can be continuously exerted, and the workload of the teacher in supervising the artificial intelligence is reduced. And teachers can modify the principle description of the artificial intelligence algorithm to directly intervene and improve the learning auxiliary process of the artificial intelligence, so that the adverse current situation of the artificial intelligence education can be greatly changed, and the method has extremely important and profound significance for the healthy development of the artificial intelligence education.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a teacher leading artificial intelligence education robot for overcoming multi-head leaders.
Background
Under the prior art, the teacher can be helped to better help students to learn when artificial intelligence is used for education through earlier-stage research and discovery.
In the process of implementing the invention, the inventor finds that at least the following problems exist in the prior art: in the prior art, the algorithm adopted by artificial intelligence to help students learn is only known by designers and developers of the artificial intelligence algorithm, teachers are not aware of the algorithm, and meanwhile the designers and developers of the artificial intelligence algorithm are not communicated with the teachers, the designers and developers of the artificial intelligence algorithm are not teachers and do not understand education theories, the artificial intelligence algorithm related to the designers and developers of the artificial intelligence algorithm is designed only by the common knowledge of non-education specialties when used for education, and is not reasonable, so that the learning content recommendation which brings negative effects to the learning of students is often caused, for example, the students have problems of partial departments, limitation to local knowledge, dependence on artificial intelligence, discrimination by the artificial intelligence and the like, and after the problems occur, the teachers still have no knowledge because of the part participated by the artificial intelligence, the artificial intelligence has hundreds of leading rights, the artificial intelligence does not need to ask the teacher for consent when performing a learning content recommendation or learning evaluation, and the teacher cannot change the artificial intelligence recommendation or evaluation at all. The artificial intelligence is not tired, the students are served for 24 hours, the speed is high, the efficiency is high, and the artificial intelligence can be put to the students' position through big data, so that the leading power of a teacher is quickly weakened by the artificial intelligence and is replaced by the artificial intelligence more and more, the students prefer to learn under the assistance of the artificial intelligence, and under the condition, once the artificial intelligence is used for an algorithm of education, the students can be in bad deep and out of the way and cannot know the students, and serious teaching accidents are brought.
Accordingly, the prior art is yet to be improved and developed.
Disclosure of Invention
Based on this, it is necessary to provide a teacher leading artificial intelligence education robot for overcoming the leadership in order to prevent the students from learning the problems of "food preference", "discrimination" and the like under the influence of the algorithm of artificial intelligence for teaching, so that the teacher can lead the teaching process, and the teaching process is not weakened or even replaced by the artificial intelligence, and simultaneously, the auxiliary function of the artificial intelligence can be fully exerted.
In a first aspect, an embodiment of the present invention provides an artificial intelligence method, where the method includes:
example reporting step: acquiring a plurality of preset artificial intelligence auxiliary instances of a preset type according to a preset rule or randomly from a recent instance in a course or a classroom of a teacher, acquiring input data and output data of the artificial intelligence auxiliary instances, and calculating a principle description of a calculation process of obtaining the output data from the input data, wherein the principle description is used as report information of the artificial intelligence auxiliary instances; sending the report information to the teacher;
principle description the modification step: judging whether the teacher modifies the principle description in the received report information, if so, receiving modification information of the teacher on the principle description in the report information, sending the report information and the modification information to research and development related personnel or robots of the artificial intelligence code set, and executing an artificial intelligence code modification step; if not, executing an artificial intelligence code replacing step;
modifying artificial intelligence codes: receiving an artificial intelligence code set obtained by modifying the artificial intelligence code set by the research and development related personnel or the robot, calling the artificial intelligence code set obtained by modifying, inputting the input data to obtain updated report information, sending the updated report information to the teacher, taking the updated report information as the received report information, and re-executing the principle description modification step;
artificial intelligence code replacement: and judging whether the teacher modifies the principle description in the received report information at least once, if so, replacing the artificial intelligence code set used by the student before the first modification with the artificial intelligence code set obtained after the most recent modification online or offline.
Preferably, the method further comprises:
example definition step: the method comprises the steps of recommending primary learning content of students through artificial intelligence as a primary recommendation example, replying primary learning consultation of the students through the artificial intelligence as a primary consultation example, evaluating primary learning effect of the students through the artificial intelligence as a primary evaluation example, using the primary recommendation example or the primary consultation example or the primary evaluation example as a primary artificial intelligence auxiliary example, using the artificial intelligence recommendation, the artificial intelligence consultation, the artificial intelligence evaluation or other preset services as service types of the artificial intelligence auxiliary example, and forming big data of the artificial intelligence auxiliary example by collecting the artificial intelligence auxiliary example in real time.
Preferably, the method further comprises:
the preset rules comprise one or more preset rules among an example of preferentially selecting students with poor learning scores, an example of preferentially selecting students with the problem of learning 'food preference and food preference', an example of preferentially selecting students with dissatisfaction with artificial intelligence services (explaining that the artificial intelligence services have defects), an example of preferentially selecting students with complaints and discrimination on artificial intelligence services, an example of preferentially selecting students with too frequent artificial intelligence services (explaining that the artificial intelligence services may be depended on and can be judged by using a preset threshold value of frequency), and an example of preferentially selecting students with less artificial intelligence services (explaining that the artificial intelligence services may have defects and can be judged by using the preset threshold value of frequency).
Preferably, the method further comprises:
the method comprises the following steps of (1) describing a prediction model by a program segment principle: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a program segment principle description prediction model; taking each program code segment in the training and testing sample and the principle description corresponding to each program code segment as the input and expected output of the program segment principle description prediction model, and training and testing the program segment principle description prediction model;
description of the principle of the program segment the prediction model usage steps: calculating a program code segment to be predicted as an input of a program segment principle description prediction model, and taking an obtained output as a principle description corresponding to the program code segment;
the input and output calculation process principle description step: acquiring a program code segment set called by a calculation process for obtaining output data from input data through calculation, using the program code segment set as an artificial intelligence code set, inputting each program code segment in the artificial intelligence code set into a program segment principle description prediction model, and integrating after calculating to obtain the principle description of each program code segment to obtain the principle description of the calculation process for obtaining the output data from the input data through calculation.
Preferably, the method further comprises:
and the robot code modification step: the method comprises the steps of obtaining report information and modification information received by a robot, describing principle of each program section corresponding to the modification information, modifying the corresponding principle description of each program section according to the modification information to obtain corresponding modified principle description of each program section, inputting the modified principle description of each program section into a code prediction model, calculating to obtain program code sections corresponding to the modified principle description of each program section, and replacing corresponding program code sections in an artificial intelligence code set with the program code sections corresponding to the modified principle description of each program section to obtain an artificial intelligence code set obtained after modifying the artificial intelligence code set.
Preferably, the method further comprises:
a code 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 code prediction model; taking each program segment principle description in the training and testing sample and a program code segment corresponding to each program segment principle description as the input and expected output of a code prediction model, and training and testing the code prediction model;
the code prediction model using step: and calculating the principle description of the program segment to be predicted as the input of the code prediction model, and taking the obtained output as the program code segment corresponding to the principle description of the program segment.
In a second aspect, an embodiment of the present invention provides an artificial intelligence system, where the system includes:
an example reporting module: acquiring a plurality of preset artificial intelligence auxiliary instances of a preset type according to a preset rule or randomly from a recent instance in a course or a classroom of a teacher, acquiring input data and output data of the artificial intelligence auxiliary instances, and calculating a principle description of a calculation process of obtaining the output data from the input data, wherein the principle description is used as report information of the artificial intelligence auxiliary instances; sending the report information to the teacher;
description of the principle modification module: judging whether the teacher modifies the principle description in the received report information, if so, receiving modification information of the teacher on the principle description in the report information, sending the report information and the modification information to research and development related personnel or robots of the artificial intelligence code set, and executing an artificial intelligence code modification module; if not, executing an artificial intelligent code replacement module;
an artificial intelligence code modification module: receiving an artificial intelligence code set obtained by modifying the artificial intelligence code set by the research and development related personnel or the robot, calling the artificial intelligence code set obtained by modifying, inputting the input data to obtain updated report information, sending the updated report information to the teacher, taking the updated report information as the received report information, and executing a principle description modification module again;
artificial intelligence code replacement module: and judging whether the teacher modifies the principle description in the received report information at least once, if so, replacing the artificial intelligence code set used by the student before the first modification with the artificial intelligence code set obtained after the most recent modification online or offline.
Preferably, the system further comprises:
an instance definition module: the method comprises the steps of recommending primary learning content of students through artificial intelligence as a primary recommendation example, replying primary learning consultation of the students through the artificial intelligence as a primary consultation example, evaluating primary learning effect of the students through the artificial intelligence as a primary evaluation example, using the primary recommendation example or the primary consultation example or the primary evaluation example as a primary artificial intelligence auxiliary example, using the artificial intelligence recommendation, the artificial intelligence consultation, the artificial intelligence evaluation or other preset services as service types of the artificial intelligence auxiliary example, and forming big data of the artificial intelligence auxiliary example by collecting the artificial intelligence auxiliary example in real time.
Preferably, the system further comprises:
the preset rules comprise one or more preset rules among an example of preferentially selecting students with poor learning scores, an example of preferentially selecting students with the problem of learning 'food preference and food preference', an example of preferentially selecting students with dissatisfaction with artificial intelligence services (explaining that the artificial intelligence services have defects), an example of preferentially selecting students with complaints and discrimination on artificial intelligence services, an example of preferentially selecting students with too frequent artificial intelligence services (explaining that the artificial intelligence services may be depended on and can be judged by using a preset threshold value of frequency), and an example of preferentially selecting students with less artificial intelligence services (explaining that the artificial intelligence services may have defects and can be judged by using the preset threshold value of frequency).
Preferably, the system further comprises:
the program segment principle description prediction model construction module: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a program segment principle description prediction model; taking each program code segment in the training and testing sample and the principle description corresponding to each program code segment as the input and expected output of the program segment principle description prediction model, and training and testing the program segment principle description prediction model;
description of the principle of the program segment the prediction model usage module: calculating a program code segment to be predicted as an input of a program segment principle description prediction model, and taking an obtained output as a principle description corresponding to the program code segment;
the input and output calculation process principle description module comprises: acquiring a program code segment set called by a calculation process for obtaining output data from input data through calculation, using the program code segment set as an artificial intelligence code set, inputting each program code segment in the artificial intelligence code set into a program segment principle description prediction model, and integrating after calculating to obtain the principle description of each program code segment to obtain the principle description of the calculation process for obtaining the output data from the input data through calculation.
Preferably, the system further comprises:
the robot modifies the code module: the method comprises the steps of obtaining report information and modification information received by a robot, describing principle of each program section corresponding to the modification information, modifying the corresponding principle description of each program section according to the modification information to obtain corresponding modified principle description of each program section, inputting the modified principle description of each program section into a code prediction model, calculating to obtain program code sections corresponding to the modified principle description of each program section, and replacing corresponding program code sections in an artificial intelligence code set with the program code sections corresponding to the modified principle description of each program section to obtain an artificial intelligence code set obtained after modifying the artificial intelligence code set.
Preferably, the system further comprises:
the code prediction model construction module: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a code prediction model; taking each program segment principle description in the training and testing sample and a program code segment corresponding to each program segment principle description as the input and expected output of a code prediction model, and training and testing the code prediction model;
the code prediction model usage module: and calculating the principle description of the program segment to be predicted as the input of the code prediction model, and taking the obtained output as the program code segment corresponding to the principle description of the program segment.
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 teacher leading artificial intelligence education robot for overcoming the multi-head leadership provided by the embodiment comprises: example reporting step; a principle description modification step; modifying artificial intelligence codes; and replacing the artificial intelligence codes. According to the method, the system and the robot, the dominant right is returned to the hands of the teacher again through sampling examination on the basis of deep learning and big data by sampling examination of the learning auxiliary examples of the artificial intelligence and reporting to the teacher, meanwhile, the artificial intelligence has certain degree of freedom, the effect and the effect of the artificial intelligence can be continuously exerted, and the workload of the teacher in supervising the artificial intelligence is reduced. And teachers can modify the principle description of the artificial intelligence algorithm to directly intervene and improve the learning auxiliary process of the artificial intelligence, so that the adverse current situation of the artificial intelligence education can be greatly changed, and the method has extremely important and profound significance for the healthy development of the artificial intelligence education.
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 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: example reporting step; a principle description modification step; modifying artificial intelligence codes; and replacing the artificial intelligence codes. The technical effects are as follows: the method is based on deep learning and big data, the master right is returned to the hands of the teacher again through sampling and reporting the learning auxiliary examples of the artificial intelligence, meanwhile, the artificial intelligence has certain freedom degree, the effect and the effect of the artificial intelligence can be continuously played, and the workload of the teacher for supervising the artificial intelligence is reduced. And teachers can modify the principle description of the artificial intelligence algorithm to directly intervene and improve the learning auxiliary process of the artificial intelligence, so that the adverse current situation of the artificial intelligence education can be greatly changed, and the method has extremely important and profound significance for the healthy development of the artificial intelligence education.
In a preferred embodiment, the method further comprises: and (5) an example definition step. The technical effects are as follows: the method obtains a large number of examples based on big data, and the examples are divided into different types, so that all service types which can be provided by artificial intelligence participation learning assistance can be covered, and further the deviation and the problems existing in various types of artificial intelligence education services are overcome.
In a preferred embodiment, the method further comprises: and setting the preset rule specifically. The technical effects are as follows: according to the method, the workload of teachers for supervising the artificial intelligence algorithm is relieved through different sampling modes based on the big data, the sample for spot check can be representative, the situation of the big data of the whole example can be basically represented, and the problem of the sample example for spot check can basically cover the problem of the example with the problem in the big data of the example.
In a preferred embodiment, as shown in fig. 2, the method further comprises: a step of constructing a prediction model by using a program segment principle description; describing the using step of the prediction model by using a program segment principle; the input-output calculation process principle describes the steps. The technical effects are as follows: the method obtains the principle description according to the program segment based on deep learning, so that teachers who do not understand artificial intelligence codes can understand the principle description, and the principle description of the program segment is natural language, so that teachers can modify the principle description according to own teaching ideas and teaching requirements, so that the artificial intelligence program can meet the requirements of the teachers, and the teachers can lead artificial intelligence algorithms, and further fundamentally lead artificial intelligence services.
In a preferred embodiment, the method further comprises: and the robot modifies the code. The technical effects are as follows: according to the method, the robot is used for modifying the codes, so that the workload of an artificial intelligence research and development engineer is reduced, the modified codes are not necessarily usable or operable, but at least can be referred by the artificial intelligence research and development engineer, the workload of the artificial intelligence research and development engineer can be reduced, and the efficiency and the practicability of the method are improved.
In a preferred embodiment, as shown in fig. 3, the method further comprises: constructing a code prediction model; and using the code prediction model. The technical effects are as follows: the method predicts the code through principle description based on deep learning, so that the robot can modify the code.
PREFERRED EMBODIMENTS OF THE PRESENT INVENTION
Example definition step: the method comprises the steps of recommending primary learning content of students through artificial intelligence as a primary recommendation example, replying primary learning consultation of the students through the artificial intelligence as a primary consultation example, evaluating primary learning effect of the students through the artificial intelligence as a primary evaluation example, using the primary recommendation example or the primary consultation example or the primary evaluation example as a primary artificial intelligence auxiliary example, using the artificial intelligence recommendation, the artificial intelligence consultation, the artificial intelligence evaluation or other preset services as service types of the artificial intelligence auxiliary example, and forming big data of the artificial intelligence auxiliary example by collecting the artificial intelligence auxiliary example in real time.
Example reporting step: acquiring a plurality of preset artificial intelligence auxiliary instances of a preset type according to a preset rule or randomly from a recent instance in a course or a classroom of a teacher, acquiring input data and output data of the artificial intelligence auxiliary instances, and calculating a principle description of a calculation process of obtaining the output data from the input data, wherein the principle description is used as report information of the artificial intelligence auxiliary instances; sending the report information to the teacher;
the preset rules comprise one or more preset rules among an example of a student with poor learning score, an example of a student with the problem of learning 'food preference and food preference', an example of a student with dissatisfaction with artificial intelligence service (explaining that the artificial intelligence service has defects), an example of a student with complaint and discrimination on artificial intelligence, an example of a student with too frequent artificial intelligence service (explaining that the artificial intelligence service may be depended on and can be judged by using a preset threshold value of frequent times), and an example of a student with very few artificial intelligence service (explaining that the artificial intelligence service may have defects and can be judged by using a preset threshold value of frequent times);
the method comprises the following steps of (1) describing a prediction model by a program segment principle: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a program segment principle description prediction model; taking each program code segment in the training and testing sample and the principle description corresponding to each program code segment as the input and expected output of the program segment principle description prediction model, and training and testing the program segment principle description prediction model;
description of the principle of the program segment the prediction model usage steps: calculating a program code segment to be predicted as an input of a program segment principle description prediction model, and taking an obtained output as a principle description corresponding to the program code segment;
the input and output calculation process principle description step: acquiring a program code segment set called by a calculation process for obtaining output data from input data through calculation, using the program code segment set as an artificial intelligence code set, inputting each program code segment in the artificial intelligence code set into a program segment principle description prediction model, and integrating after calculating to obtain the principle description of each program code segment to obtain the principle description of the calculation process for obtaining the output data from the input data through calculation;
principle description the modification step: judging whether the teacher modifies the principle description in the received report information, if so, receiving modification information of the teacher on the principle description in the report information, sending the report information and the modification information to research and development related personnel or robots of the artificial intelligence code set, and executing an artificial intelligence code modification step; if not, executing an artificial intelligence code replacing step;
a code 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 code prediction model; taking each program segment principle description in the training and testing sample and a program code segment corresponding to each program segment principle description as the input and expected output of a code prediction model, and training and testing the code prediction model;
the code prediction model using step: calculating the principle description of a program segment to be predicted as the input of a code prediction model, and taking the obtained output as a program code segment corresponding to the principle description of the program segment;
and the robot code modification step: acquiring the report information and the modification information received by the robot, modifying each program segment principle description corresponding to the modification information according to the modification information to obtain each modified program segment principle description, inputting each modified program segment principle description into a code prediction model, calculating to obtain a program code segment corresponding to each modified program segment principle description, and replacing the corresponding program code segment in the artificial intelligence code set with the program code segment corresponding to each modified program segment principle description to obtain an artificial intelligence code set obtained after modifying the artificial intelligence code set;
the method comprises the following steps of assisting an artificial intelligence research and development engineer: and sending the artificial intelligence code set obtained by modifying the artificial intelligence code set obtained by the step of modifying the codes by the robot to research and development related personnel of the artificial intelligence code set for reference by the research and development related personnel of the artificial intelligence code set.
Modifying artificial intelligence codes: receiving an artificial intelligence code set obtained by modifying the artificial intelligence code set by the research and development related personnel or the robot, calling the artificial intelligence code set obtained by modifying, inputting the input data to obtain updated report information, sending the updated report information to the teacher, taking the updated report information as the received report information, and re-executing the principle description modification step;
artificial intelligence code replacement: and judging whether the teacher modifies the principle description in the received report information at least once, if so, replacing the artificial intelligence code set used by the student before the first modification with the artificial intelligence code set obtained after the most recent modification online or offline.
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 (9)
1. An artificial intelligence method, the method comprising:
example reporting step: acquiring a plurality of preset artificial intelligence auxiliary instances of a preset type according to a preset rule or randomly from a recent instance in a course or a classroom of a teacher, acquiring input data and output data of the artificial intelligence auxiliary instances, and calculating a principle description of a calculation process of obtaining the output data from the input data, wherein the principle description is used as report information of the artificial intelligence auxiliary instances; sending the report information to the teacher;
principle description the modification step: judging whether the teacher modifies the principle description in the received report information, if so, receiving modification information of the teacher on the principle description in the report information, sending the report information and the modification information to research and development related personnel or robots of the artificial intelligence code set, and executing an artificial intelligence code modification step; if not, executing an artificial intelligence code replacing step;
modifying artificial intelligence codes: receiving an artificial intelligence code set obtained by modifying the artificial intelligence code set by the research and development related personnel or the robot, calling the artificial intelligence code set obtained by modifying, inputting the input data to obtain updated report information, sending the updated report information to the teacher, taking the updated report information as the received report information, and re-executing the principle description modification step;
artificial intelligence code replacement: judging whether the teacher modifies the principle description in the received report information at least once, if so, replacing the artificial intelligence code set used by the student before the modification for the first time with the artificial intelligence code set obtained after the most recent modification online or offline;
the method comprises the following steps of (1) describing a prediction model by a program segment principle: initializing a deep learning model or a neural network or a machine learning model or a quantum computing model as a program segment principle description prediction model; taking each program code segment in the training and testing sample and the principle description corresponding to each program code segment as the input and expected output of the program segment principle description prediction model, and training and testing the program segment principle description prediction model;
description of the principle of the program segment the prediction model usage steps: calculating a program code segment to be predicted as an input of a program segment principle description prediction model, and taking an obtained output as a principle description corresponding to the program code segment;
the input and output calculation process principle description step: acquiring a program code segment set called by a calculation process for obtaining output data from input data through calculation, using the program code segment set as an artificial intelligence code set, inputting each program code segment in the artificial intelligence code set into a program segment principle description prediction model, and integrating after calculating to obtain the principle description of each program code segment to obtain the principle description of the calculation process for obtaining the output data from the input data through calculation.
2. The artificial intelligence method of claim 1, wherein the method further comprises:
example definition step: the method comprises the steps of recommending primary learning content of students through artificial intelligence as a primary recommendation example, replying primary learning consultation of the students through the artificial intelligence as a primary consultation example, evaluating primary learning effect of the students through the artificial intelligence as a primary evaluation example, using the primary recommendation example or the primary consultation example or the primary evaluation example as a primary artificial intelligence auxiliary example, using the artificial intelligence recommendation, the artificial intelligence consultation, the artificial intelligence evaluation or other preset services as service types of the artificial intelligence auxiliary example, and forming big data of the artificial intelligence auxiliary example by collecting the artificial intelligence auxiliary example in real time.
3. The artificial intelligence method of claim 1, wherein the method further comprises:
the preset rules comprise one or more preset rules among an example of preferentially selecting students with poor learning scores, an example of preferentially selecting students with the problem of learning 'food preference' and 'food preference', an example of preferentially selecting students who are unsatisfied with artificial intelligence services, an example of preferentially selecting students who complain about artificial intelligence and have discrimination, an example of preferentially selecting students who use artificial intelligence services too frequently and an example of preferentially selecting students who use artificial intelligence services rarely.
4. The artificial intelligence method of claim 1, wherein the method further comprises:
and the robot code modification step: the method comprises the steps of obtaining report information and modification information received by a robot, describing principle of each program section corresponding to the modification information, modifying the corresponding principle description of each program section according to the modification information to obtain corresponding modified principle description of each program section, inputting the modified principle description of each program section into a code prediction model, calculating to obtain program code sections corresponding to the modified principle description of each program section, and replacing corresponding program code sections in an artificial intelligence code set with the program code sections corresponding to the modified principle description of each program section to obtain an artificial intelligence code set obtained after modifying the artificial intelligence code set.
5. The artificial intelligence method of claim 4, wherein the method further comprises:
a code 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 code prediction model; taking each program segment principle description in the training and testing sample and a program code segment corresponding to each program segment principle description as the input and expected output of a code prediction model, and training and testing the code prediction model;
the code prediction model using step: and calculating the principle description of the program segment to be predicted as the input of the code prediction model, and taking the obtained output as the program code segment corresponding to the principle description of the program segment.
6. An artificial intelligence system, characterized in that the system is adapted to implement the steps of the method of any of claims 1-5.
7. An artificial intelligence device, wherein the device is configured to implement the steps of the method of any of claims 1-5.
8. 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 5 are carried out when the program is executed by the processor.
9. 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 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110228044.XA CN112965703B (en) | 2021-03-02 | 2021-03-02 | Teacher leading artificial intelligence education robot for overcoming multi-head leaders |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110228044.XA CN112965703B (en) | 2021-03-02 | 2021-03-02 | Teacher leading artificial intelligence education robot for overcoming multi-head leaders |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112965703A CN112965703A (en) | 2021-06-15 |
| CN112965703B true CN112965703B (en) | 2022-04-01 |
Family
ID=76276266
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110228044.XA Active CN112965703B (en) | 2021-03-02 | 2021-03-02 | Teacher leading artificial intelligence education robot for overcoming multi-head leaders |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112965703B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271153A (en) * | 2018-08-22 | 2019-01-25 | 深圳点猫科技有限公司 | A kind of educational system based on programming obtains the method and electronic equipment of programming language |
| KR20200103187A (en) * | 2019-02-14 | 2020-09-02 | 주식회사 위즈스쿨 | Method And Apparatus for Providing Coding Educational Platform based on AI Tutor |
| CN111639744A (en) * | 2020-04-15 | 2020-09-08 | 北京迈格威科技有限公司 | Student model training method and device and electronic equipment |
| CN112215506A (en) * | 2020-10-20 | 2021-01-12 | 深圳市爱云信息科技有限公司 | Intelligent digital education AI classroom big data management platform and device |
| CN112330507A (en) * | 2020-11-03 | 2021-02-05 | 深圳市爱云信息科技有限公司 | Big data platform and device of wisdom education AIOT student growth ability model |
| CN112365183A (en) * | 2020-11-26 | 2021-02-12 | 江西台德智慧科技有限公司 | Artificial intelligence education method and device |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190102722A1 (en) * | 2017-10-03 | 2019-04-04 | International Business Machines Corporation | System and method enabling dynamic teacher support capabilities |
| US10635409B2 (en) * | 2018-01-15 | 2020-04-28 | Cognizant Technology Solutions India Pvt. Ltd. | System and method for improving software code quality using artificial intelligence techniques |
| JP6931624B2 (en) * | 2018-05-22 | 2021-09-08 | 株式会社日立製作所 | Learning support device and learning support method |
| US10970490B2 (en) * | 2019-05-16 | 2021-04-06 | International Business Machines Corporation | Automatic evaluation of artificial intelligence-based processes |
-
2021
- 2021-03-02 CN CN202110228044.XA patent/CN112965703B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109271153A (en) * | 2018-08-22 | 2019-01-25 | 深圳点猫科技有限公司 | A kind of educational system based on programming obtains the method and electronic equipment of programming language |
| KR20200103187A (en) * | 2019-02-14 | 2020-09-02 | 주식회사 위즈스쿨 | Method And Apparatus for Providing Coding Educational Platform based on AI Tutor |
| CN111639744A (en) * | 2020-04-15 | 2020-09-08 | 北京迈格威科技有限公司 | Student model training method and device and electronic equipment |
| CN112215506A (en) * | 2020-10-20 | 2021-01-12 | 深圳市爱云信息科技有限公司 | Intelligent digital education AI classroom big data management platform and device |
| CN112330507A (en) * | 2020-11-03 | 2021-02-05 | 深圳市爱云信息科技有限公司 | Big data platform and device of wisdom education AIOT student growth ability model |
| CN112365183A (en) * | 2020-11-26 | 2021-02-12 | 江西台德智慧科技有限公司 | Artificial intelligence education method and device |
Non-Patent Citations (3)
| Title |
|---|
| 人工智能的文艺梦想和机器人的未来;朱定局;《华南师范大学学报( 社会科学版)》;20190930(第5期);第183-188页 * |
| 教学用固定区域智能清障机器人的设计;燕居怀;《教育现代化》;20180430(第18期);第316-317页 * |
| 深度学习在智能机器人中的应用研究综述;龙慧;《计算机科学》;20181130;第45卷(第11A期);第43-52页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112965703A (en) | 2021-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Funke | Solving complex problems: Exploration and control of complex systems | |
| CN111274411A (en) | Course recommendation method and device, electronic equipment and readable storage medium | |
| US20200401503A1 (en) | System and Method for Testing Artificial Intelligence Systems | |
| CN111209472B (en) | Railway accident fault association and accident fault cause analysis method and system | |
| Jugo et al. | Increasing the adaptivity of an intelligent tutoring system with educational data mining: a system overview | |
| CN111126552A (en) | Intelligent learning content pushing method and system | |
| CN114388103A (en) | Algorithm for teenager psychological early warning analysis | |
| CN111626372A (en) | Online teaching supervision management method and system | |
| CN111754370B (en) | Artificial intelligence-based online education course management method and system | |
| CN112965703B (en) | Teacher leading artificial intelligence education robot for overcoming multi-head leaders | |
| CN108229683B (en) | Information processing method and device based on IRT | |
| Perkusich et al. | A Bayesian network approach to assist on the interpretation of software metrics | |
| CN116362929A (en) | Cognitive diagnosis method and device for joint topic qualitative analysis probability matrix decomposition | |
| CN111415326A (en) | Method and system for detecting abnormal state of railway contact net bolt | |
| Arsham et al. | Comparison of the learning algorithms for evidence-based BBN modeling: A case study on ship grounding accidents | |
| CN108614771A (en) | A kind of Modeling Teaching of Mathematics learning system | |
| Ferrari et al. | Model Generation from Requirements with LLMs: an Exploratory Study | |
| Solomonov et al. | Using neural networks in building a psychological typology | |
| Shibata et al. | Evaluation of Automatic Collaborative Learning Process Coding Using Deep Learning Methods Based on Multi-Dimensional Coding Scheme | |
| CN117540012B (en) | Text generation method and system | |
| CN118550753B (en) | Cloud platform fault repairing method, device, host equipment, program product and system | |
| CN118394561B (en) | Method and device for diagnosing server fault, storage medium and electronic equipment | |
| Biswas et al. | Towards a Deeper Understanding of K-12 Students' CT and Engineering Design Processes | |
| Du et al. | Question Difficulty Priori Evaluation Based on Fuzzy Logic in Programming System | |
| Malandri et al. | Contrastive Explanations of Text Classifiers as a Service |
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 |