CN114003715A - Negative feedback matching method for evolution type object - Google Patents
Negative feedback matching method for evolution type object Download PDFInfo
- Publication number
- CN114003715A CN114003715A CN202111656395.7A CN202111656395A CN114003715A CN 114003715 A CN114003715 A CN 114003715A CN 202111656395 A CN202111656395 A CN 202111656395A CN 114003715 A CN114003715 A CN 114003715A
- Authority
- CN
- China
- Prior art keywords
- environment
- feedback
- determining
- negative feedback
- factor
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 230000007613 environmental effect Effects 0.000 claims abstract description 35
- 230000001737 promoting effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 14
- 238000012360 testing method Methods 0.000 description 191
- 230000009471 action Effects 0.000 description 15
- 230000008569 process Effects 0.000 description 9
- 238000011156 evaluation Methods 0.000 description 8
- 238000009877 rendering Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000000354 decomposition reaction Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012545 processing Methods 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
- G06F16/33—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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Educational Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The application discloses a negative feedback matching method for an evolution type object. The negative feedback matching method for the evolution type object comprises the following steps: determining a first environmental content factor; determining a first environmental presentation scenario from the first environmental content factor; sending the first environmental presentation scene to the object; calculating a first feedback value of the object to the first environment presentation scene; when the first feedback value is negative feedback, determining the negative feedback type of the object according to the first environment content factor; determining a second environment presentation scene according to the negative feedback type and the first environment content factor; and matching the object with the second environment presentation scene, thereby improving the teaching effect in the classroom.
Description
Technical Field
The application relates to the technical field of matching between objects and targets, in particular to a negative feedback matching method for an evolution type object in classroom teaching.
Background
Automatic pushing of subjects in the prior art is commonly applied to intelligent classroom teaching. Currently, there are two general solutions to the problem of implementing topic push. One is to push based on the label (or big data, knowledge graph), and the premise is to build a label association system; another is to perform an enumeration push during the course production.
In the process of realizing the prior art, the inventor finds that:
there are two distinct disadvantages to topic push based on tags (or big data, knowledge graph): firstly, all pushing logics are based on the unified association relationship and pushing priority between the labels, and specific pushing setting cannot be carried out on each knowledge point or topic; secondly, the system can only push according to the labels of the questions and can not push according to the item options of the questions, namely, the system can not push according to different answering contents of each student. In enumeration push, the disadvantage is that the enumeration workload increases exponentially with the complexity of the push rule, and excessive enumeration is a great obstacle to the efficiency of course making.
Therefore, it is necessary to provide a related technical solution for pushing test questions, which effectively combines the classroom contents and has high curriculum production efficiency.
Disclosure of Invention
The embodiment of the application provides a technical scheme for pushing test questions, which effectively combines classroom contents and has high course making efficiency, and is used for solving the technical problem that the course making efficiency is poor due to poor relevance and excessive enumeration between the pushed test questions, actual knowledge points in a classroom and individual students.
The application provides an evolutionary object-oriented negative feedback matching method, which comprises the following steps:
determining a first environmental content factor;
determining a first environmental presentation scenario from the first environmental content factor;
sending the first environmental presentation scene to the object;
calculating a first feedback value of the object to the first environment presentation scene;
when the first feedback value is negative feedback, determining the negative feedback type of the object according to the first environment content factor;
determining a second environment presentation scene according to the negative feedback type and the first environment content factor;
matching the object with the second ambient presentation scene.
Further, before determining the negative feedback type of the object according to the first environment content factor when the first feedback value is negative feedback, the method further includes:
generating a negative feedback type set corresponding to the first environment content factor according to an enumeration strategy;
wherein the negative feedback type belongs to the set of negative feedback types.
Further, the method comprises the following steps:
calculating a second feedback value of the object to the second environment presentation scene;
when the second feedback value is negative feedback, determining a third environment presentation scene again according to the negative feedback type and the first environment content factor;
matching the object with the third environmental presentation scenario.
Further, the method comprises the following steps:
calculating a second feedback value of the object to the second environment presentation scene;
when the second feedback value is positive feedback, determining a second environment content factor according to a first updating strategy;
determining a third environment presentation scene according to the second environment content factor;
matching the object with the third environmental presentation scenario.
Further, the method comprises the following steps:
calculating a second feedback value of the object to the second environment presentation scene;
and when the second feedback value is positive feedback, matching the object with the first environment presentation scene again.
Further, the method comprises the following steps:
calculating a second feedback value of the object to the second environment presentation scene;
when the second feedback value is positive feedback, determining a third environment presentation scene again according to the first environment content factor;
matching the object with the third environmental presentation scenario.
Further, the method comprises the following steps:
calculating a third feedback value of the object to the third environment presentation scenario;
when the third feedback value is negative feedback, determining an environment complexity factor corresponding to the third environment presentation scene;
reducing the environment complexity factor by one unit to form an updated environment complexity factor;
determining a fourth environment presentation scene according to the negative feedback type, the first environment content factor and the updated environment complexity factor;
matching the object with the fourth environment presentation scenario.
Further, the method comprises the following steps:
calculating a third feedback value of the object to the third environment presentation scenario;
when the third feedback value is positive feedback, determining a fourth environment presentation scene according to the negative feedback type and the first environment content factor;
matching the object with the fourth environment presentation scenario.
Further, the method comprises the following steps:
calculating a third feedback value of the object to the third environment presentation scenario;
when the third feedback value is positive feedback, determining an environment complexity factor corresponding to the third environment presentation scene;
promoting the environment complexity factor by one unit to form an updated environment complexity factor;
determining a fourth environment presentation scene according to the negative feedback type, the first environment content factor and the updated environment complexity factor;
matching the object with the fourth environment presentation scenario.
Further, the first environmental content factor belongs to a set of knowledge point attribute values;
the negative feedback type is an error point attribute value.
The embodiment provided by the application has at least the following beneficial effects: by combining the knowledge points and the error points, the recommended questions are ensured to be pointed, so that the teaching effect in the classroom is effectively improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a flowchart of a negative feedback matching method for an evolutionary object according to an embodiment of the present disclosure;
FIG. 2 is a flowchart illustrating a first step of a negative feedback matching method for an evolutionary object according to an embodiment of the present application;
FIG. 3 is a flowchart illustrating a second step included in the method for negative feedback matching for an evolutionary object according to an embodiment of the present application;
FIG. 4 is a flowchart illustrating a third step included in the negative feedback matching method for an evolutionary object according to an embodiment of the present application;
fig. 5 is a flowchart of a fourth step included in the negative feedback matching method for an evolutionary object according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be described in detail and completely with reference to the following specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, a negative feedback matching method for an evolutionary object provided by the present application includes the following steps:
s100: determining a first environmental content factor;
s200: determining a first environmental presentation scenario from the first environmental content factor;
s300: sending the first environmental presentation scene to the object;
s400: calculating a first feedback value of the object to the first environment presentation scene;
s500: when the first feedback value is negative feedback, determining the negative feedback type of the object according to the first environment content factor;
s600: determining a second environment presentation scene according to the negative feedback type and the first environment content factor;
s700: matching the object with the second ambient presentation scene.
It is noted that the first environmental content factor may be understood as a first content attribute value determined for characterizing a particular content comprised by a particular object. The first environment presentation scene may be understood as a first specific object determined according to a first content attribute value or the like of specific content included in the specific object. An object may be understood as a specific object for which a specific goal needs to be recommended. The first feedback value may be understood as a corresponding first evaluation value calculated after the specific object performs the preset action according to the matched first specific target. Negative feedback can be interpreted as a non-compliance with the expected results. The negative feedback type may be understood as a specific non-compliant type that does not comply with an expected result after a specific object performs a preset action. The second context presentation scenario may be understood as a second specific goal determined by the first content attribute value and the type of specific non-compliance that does not comply with the expected result after the specific object performs the preset action. In a specific application scenario, the method and the device can be used for pushing the test questions in the intelligent classroom. Specifically, the question bank used in the intelligent classroom can be associated and processed according to the knowledge points and the error points. The association processing can be understood as combing the knowledge points of the topics in the topic library and sorting out the error points corresponding to each knowledge point. The first environmental content factor is understood herein to be a first knowledge point attribute value determined from a plurality of knowledge points in the question bank. The first environment presentation scenario herein may be understood as a first candidate test question determined based on knowledge points characterized by the first environment content factor. The object here may be a specific target learner for which a recommended test question is required. The first feedback value here can be understood as a corresponding first test result calculated after the target learner performs a test according to the transmitted test question. Negative feedback here may be understood as a test failure. The negative feedback type here can be understood as a specific error point occurring when the target learner tests. The second environment presentation scenario may be understood as a second candidate test question determined based on the knowledge points characterized by the first environment content factors and the specific error points occurring when the target learner tests. In a specific implementation process, the application scenario may be that an intelligent classroom performs related classroom testing activities such as mathematics, Chinese, English, and the like, and a test question library constructed in advance according to the association of knowledge points and error points is adopted. It should be noted that the knowledge points and the error points may be adjusted accordingly according to the actual classroom test conditions, such as adding, modifying, deleting, and the like. When test questions are pushed specifically, a specific knowledge point closely related to the current teaching activity is determined from a plurality of knowledge points contained in a question bank and serves as a first knowledge point attribute value; determining specific candidate test questions as first candidate test questions from test questions corresponding to the knowledge points represented by the first knowledge point attribute value; sending the first candidate test question to the target learner; the target learner tests according to the sent first candidate test question and calculates to obtain a corresponding first test result; when the first test result is that the test is not passed, determining a specific error point which appears when the target learner tests according to the attribute value of the first knowledge point; further determining a second candidate test question according to the specific error point and the attribute value of the first knowledge point; matching the target learner with the second candidate test question. For example: specifically, in a mathematical test question pushing scene, the attribute value of a first knowledge point is assumed to be 'prime factorization'; the first candidate test determined from the question bank is "split 182 into prime factors", option a is "182 =2 × 91", the corresponding error point of option a is "not split up", option B is "182 =1 × 2 × 7 × 13", the corresponding error point of option B is "1 is not a prime number and cannot appear", option C is "182 =7 × 2 × 13", the corresponding error point of option C is "to be arranged from small to large", option D is "182 =2 × 7 × 13", and option D is the correct option; pushing the topic "decompose 182 prime factors" to the target learner; if the target learner selects the option C when testing the sent question, the first test result is that the test is not passed; according to the contents of the knowledge points and the options C of the prime factorization, the error points of the target learner can be determined to be arranged from small to large; determining other questions corresponding to the error points which need to be arranged from small to large and the knowledge points which need to be subjected to prime factor decomposition, and selecting one question from the other questions as a second candidate test question; and sending the second candidate test question to the target learner. By analyzing the test result of the target learner, subsequent test question pushing is carried out according to the knowledge points and the error points in a targeted manner, the recommended questions are ensured to be associated with the test condition of the target learner, the target learner is facilitated to master the corresponding knowledge points, and the teaching effect in a classroom is improved.
Further, in a preferred embodiment provided by the present application, before the step of determining the negative feedback type of the object according to the first environment content factor when the first feedback value is negative feedback, the method further includes:
generating a negative feedback type set corresponding to the first environment content factor according to an enumeration strategy;
wherein the negative feedback type belongs to the set of negative feedback types.
It is to be understood that the enumeration strategy herein is directed to enumerate. The elements in the negative feedback type set are derived in enumerated form from the corresponding first context content factor. The negative feedback type here is an element of a negative feedback type set. Specifically, in an application scenario, the negative feedback type set may be understood as a set of error points shown in an enumerated form corresponding to a knowledge point characterized by a first knowledge point attribute value. Such as: in the pushing of the mathematical test questions, assuming that the first knowledge point attribute value is "prime factorization", that is, the knowledge point to be examined here is "prime factorization", the error point set corresponding to the preset first knowledge point attribute value ("no decomposition is completed", "1 is prime number cannot appear", and "it is to be arranged from small to large") may be generated in an enumeration form according to an enumeration strategy. Obviously, the error points can be correspondingly increased, reduced, modified and the like according to the actual classroom requirements. By enumerating the error points corresponding to the knowledge points in a targeted manner, the enumeration workload is effectively reduced, and the course making efficiency is improved.
Specifically, referring to fig. 2, in a preferred embodiment provided herein, the method further includes the following steps:
s801: calculating a second feedback value of the object to the second environment presentation scene;
s901: when the second feedback value is negative feedback, determining a third environment presentation scene again according to the negative feedback type and the first environment content factor;
SA 01: matching the object with the third environmental presentation scenario.
It is obvious that the second feedback value can be understood as a corresponding second evaluation value calculated after the specific object performs the preset action according to the matched second specific target. The third context presentation scenario may be understood as a third specific goal determined by the first content attribute value and the type of specific non-compliance that does not comply with the expected result after the specific object performs the preset action. In the application scenario of pushing test questions in an intelligent classroom, the second feedback value here can be understood as a corresponding second test result calculated by the target learner after testing according to the sent second candidate test question, and the third environment presentation scenario here can be understood as a third candidate test question determined according to the knowledge point represented by the first environment content factor and the specific error point occurring when the target learner tests. In a specific implementation process, the target learner tests according to the sent second candidate test question and calculates to obtain a corresponding second test result; when the second test result is that the test fails, further determining a third candidate test question according to the first knowledge point attribute value and the specific error point of the target learner, which is determined by the first test result; matching the target learner with the third candidate test question. Obviously, the third candidate test question and the second candidate test question can be understood as similar questions containing the same knowledge points and error points. By combining the multiple test results of the target learner, subsequent test questions are pushed according to the knowledge points and the error points in a targeted manner, so that the target learner can master the corresponding knowledge points, and the teaching effect in a classroom is improved.
Further, referring to fig. 3, in a preferred embodiment provided herein, the method further includes the following steps:
s802: calculating a second feedback value of the object to the second environment presentation scene;
s902: when the second feedback value is positive feedback, determining a second environment content factor according to a first updating strategy;
SA 02: determining a third environment presentation scene according to the second environment content factor;
SB 02: matching the object with the third environmental presentation scenario.
It is understood that the second feedback value may be understood as a corresponding second evaluation value calculated after the specific object performs the preset action according to the matched second specific target. Positive feedback may be understood to be consistent with the expected results. A first update policy may be understood as a set first way of updating a specific target. The second context factor may be understood as a second content attribute value determined for characterizing a particular content comprised by a particular object. The third context presentation scenario may be understood as a third specific goal determined from the second content attribute value. In the application scenario of pushing test questions in an intelligent classroom, the second feedback value can be understood as a corresponding second test result calculated by the target learner after testing according to the sent second candidate test question. The positive feedback here is to be understood as test pass. The first update strategy can be a preset update rule, and the update rule can be used for updating knowledge points associated with classroom teaching activities or other knowledge points needed by actual teaching. The content factor of the second environment is understood to be a second knowledge point attribute value determined from a plurality of knowledge points in the question bank. The third environment presenting scenario may be understood as a third candidate test question determined according to the knowledge point characterized by the second knowledge point attribute value. In a specific implementation process, the target learner tests according to the sent second candidate test question and calculates to obtain a corresponding second test result; when the second test result is that the test is passed, determining a second knowledge point attribute value according to a preset updating rule, namely determining another knowledge point different from the knowledge point represented by the first knowledge point attribute value; at the moment, determining a third candidate test question according to the newly determined attribute value of the second knowledge point; matching the target learner with the third candidate test question. Obviously, the third candidate test question and the second candidate test question can be understood as questions respectively containing different knowledge points. By combining the multiple test results of the target learner, the pushed test questions are adjusted in time according to the test results, and subsequent test question pushing is performed according to the knowledge points and the error points in a targeted manner, so that the target learner can master the corresponding knowledge points, and the teaching effect in a classroom is improved.
Specifically, in a preferred embodiment provided herein, the method further includes the following steps:
calculating a second feedback value of the object to the second environment presentation scene;
and when the second feedback value is positive feedback, matching the object with the first environment presentation scene again.
It should be noted that the second feedback value may be understood as a corresponding second evaluation value calculated after the specific object performs the preset action according to the matched second specific target. Positive feedback may be understood to be consistent with the expected results. In the application scenario of pushing test questions in an intelligent classroom, the second feedback value can be understood as a corresponding second test result calculated by the target learner after testing according to the sent second candidate test question. The positive feedback here is to be understood as test pass. In a specific implementation mode, the target learner tests according to the sent second candidate test question and calculates to obtain a corresponding second test result; and matching the target learner with the first candidate test question again when the second test result is that the test is passed. Obviously, whether the target learner really masters the relevant knowledge points or not can be further confirmed by testing the question of the target learner who makes a mistake for the first time again, and subsequent test question pushing is carried out according to the knowledge points and the mistake points in a targeted manner, so that the target learner can master the corresponding knowledge points, and the teaching effect in a classroom is further improved.
Further, in a preferred embodiment provided herein, the method further comprises the steps of:
calculating a second feedback value of the object to the second environment presentation scene;
when the second feedback value is positive feedback, determining a third environment presentation scene again according to the first environment content factor;
matching the object with the third environmental presentation scenario.
It is understood that the second feedback value may be understood as a corresponding second evaluation value calculated after the specific object performs the preset action according to the matched second specific target. Positive feedback may be understood to be consistent with the expected results. The third context presentation scenario may be understood as a third specific goal determined from the first content attribute value. In the application scenario of pushing test questions in an intelligent classroom, the second feedback value can be understood as a corresponding second test result calculated by the target learner after testing according to the sent second candidate test question. The positive feedback here is to be understood as test pass. The third environment presentation scenario herein may be understood as a third candidate test question determined according to the knowledge points characterized by the first environment content factors. In a specific implementation mode, the target learner tests according to the sent second candidate test question and calculates to obtain a corresponding second test result; when the second test result is that the test is passed, determining a third candidate test question again according to the knowledge point represented by the first environment content factor; matching the target learner with the third candidate test question. Obviously, the knowledge points examined by the first candidate test question, the second candidate test question and the third candidate test question are the same. The new question with the same knowledge point is determined according to the knowledge point of the wrong question made by the target learner for the first time, so that whether the target learner really masters the related knowledge point can be further determined, subsequent test question pushing is carried out according to the knowledge point and the wrong point in a targeted manner, the target learner can master the corresponding knowledge point, and the teaching effect in a classroom is further improved.
Specifically, referring to fig. 4, in a preferred embodiment provided herein, the method further includes the following steps:
SB 011: calculating a third feedback value of the object to the third environment presentation scenario;
SC 011: when the third feedback value is negative feedback, determining an environment complexity factor corresponding to the third environment presentation scene;
SD 011: reducing the environment complexity factor by one unit to form an updated environment complexity factor;
SE 011: determining a fourth environment presentation scene according to the negative feedback type, the first environment content factor and the updated environment complexity factor;
SF 011: matching the object with the fourth environment presentation scenario.
It is obvious that the third feedback value can be understood as a corresponding third evaluation value calculated after the specific object performs the preset action according to the matched third specific target. The environmental complexity factor may be understood as an attribute value that characterizes the level of complexity of a particular target. Reducing the environmental complexity factor by one unit may be understood as reducing the attribute value used to characterize the complexity level of a particular target to the size of the adjacent attribute value. The fourth environment rendering scenario may be understood as a fourth specific goal determined according to the first content attribute value, the specific non-compliant type of the specific object that is not compliant with the expected result after performing the preset action, and a new attribute value for representing the complexity level of the specific goal. In the application scenario of pushing test questions in an intelligent classroom, the third feedback value may be understood as a corresponding third test result calculated by a target learner after testing according to a sent third candidate test question, the environment complexity factor may be understood as an attribute value for representing a test question difficulty level, reducing one unit of the environment complexity factor may be understood as reducing the attribute value for representing the test question difficulty level to an adjacent attribute value, and the fourth environment presentation scenario may be understood as a fourth candidate test question determined according to a knowledge point represented by the first knowledge point attribute value, a specific error point occurring when the target learner tests, and a new test question difficulty level. It can be understood that when the target learner continuously tests questions with the same knowledge point, the same error point and the same test question difficulty level, and continuous errors occur, the question difficulty corresponding to the knowledge point and the error point may exceed the capability range of the target learner. At this time, in order to allow the target learner to effectively grasp the related knowledge points and error points, the difficulty level of the question may be reduced. In a specific implementation process, the target learner tests according to the sent third candidate test question and calculates to obtain a corresponding third test result; when the third test result is that the test does not pass, determining the attribute value of the test question difficulty level of the third candidate test question; reducing the attribute value representing the test question difficulty level to an adjacent value to obtain the attribute value of the test question difficulty level with the question difficulty level lower by one level; according to the first knowledge point attribute value, the specific error point of the target learner, which is determined by the first test result, and the attribute value of the test question difficulty level which is one level lower than the question difficulty level, further determining a fourth candidate test question; and matching the target learner with the fourth candidate test question. Obviously, the fourth candidate test question and the third candidate test question can be understood as questions containing the same knowledge points and error points but with different question difficulties. By combining the multiple test results of the target learner, subsequent test questions are pushed according to the knowledge points, error points and test question difficulty levels in a targeted manner, so that the target learner can master the corresponding knowledge points, and the teaching effect in a classroom is improved.
Further, referring to fig. 5, in a preferred embodiment provided herein, the method further includes the following steps:
SB 012: calculating a third feedback value of the object to the third environment presentation scenario;
SC 012: when the third feedback value is positive feedback, determining a fourth environment presentation scene according to the negative feedback type and the first environment content factor;
SD 012: matching the object with the fourth environment presentation scenario.
It is understood that the third feedback value may be understood as a corresponding third evaluation value calculated after the specific object performs the preset action according to the matched third specific target. Positive feedback may be understood to be consistent with the expected results. The fourth environment rendering scenario may be understood as a fourth specific goal determined by the first content property value and the specific type of non-compliance that does not comply with the expected result after the specific object performs the preset action. In the application scenario of pushing test questions in an intelligent classroom, the third feedback value can be understood as a corresponding third test result calculated by a target learner after testing according to a sent third candidate test question, and the fourth environment presentation scenario can be understood as a fourth candidate test question determined according to a knowledge point represented by the first knowledge point attribute value and a specific error point occurring when the target learner tests. In a specific implementation process, the target learner tests according to the sent third candidate test question and calculates to obtain a corresponding third test result; when the third test result is that the test is passed, further determining a fourth candidate test question according to the first knowledge point attribute value and the specific error point of the target learner, which is determined by the first test result; and matching the target learner with the fourth candidate test question. Obviously, the fourth candidate test question and the third candidate test question can be understood as the same type of questions containing the same knowledge points and error points. When the target learner tests the same type of questions, the target learner can determine whether the target learner really masters the corresponding knowledge points and error points by continuously pushing the same type of test questions. By combining the multiple test results of the target learner, subsequent test questions are pushed according to the knowledge points and the error points in a targeted manner, so that the target learner can really master the corresponding knowledge points, and the teaching effect in a classroom is improved.
Specifically, in a preferred embodiment provided herein, the method further includes the following steps:
calculating a third feedback value of the object to the third environment presentation scenario;
when the third feedback value is positive feedback, determining an environment complexity factor corresponding to the third environment presentation scene;
promoting the environment complexity factor by one unit to form an updated environment complexity factor;
determining a fourth environment presentation scene according to the negative feedback type, the first environment content factor and the updated environment complexity factor;
matching the object with the fourth environment presentation scenario.
It is obvious that the third feedback value can be understood as a corresponding third evaluation value calculated after the specific object performs the preset action according to the matched third specific target. The environmental complexity factor may be understood as an attribute value that characterizes the level of complexity of a particular target. Raising the environment complexity factor by one unit may be understood as raising the attribute value used to characterize the complexity level of a particular target to the size of the adjacent attribute value. The fourth environment rendering scenario may be understood as a fourth specific goal determined according to the first content attribute value, the specific non-compliant type of the specific object that is not compliant with the expected result after performing the preset action, and a new attribute value for representing the complexity level of the specific goal. In the application scenario of pushing test questions in an intelligent classroom, the third feedback value may be understood as a corresponding third test result calculated by a target learner after testing according to a sent third candidate test question, the environment complexity factor may be understood as an attribute value for representing a test question difficulty level, raising one unit of the environment complexity factor may be understood as raising the attribute value for representing the test question difficulty level to an adjacent attribute value, and the fourth environment presentation scenario may be understood as a fourth candidate test question determined according to a knowledge point represented by the first knowledge point attribute value, a specific error point occurring when the target learner tests, and a new test question difficulty level. It can be understood that when the target learner continuously tests questions of the same test question difficulty level, the situation that the continuous test passes is presented, it indicates that the target learner may already master the test questions of the corresponding test question difficulty level. At this time, in order to make the target learner further grasp the related knowledge points and error points, the difficulty level of the question can be raised. In a specific implementation mode, the target learner tests according to the sent third candidate test question and calculates to obtain a corresponding third test result; when the third test result is that the test is passed, determining the attribute value of the test question difficulty level of the third candidate test question; the attribute value representing the test question difficulty level is promoted to an adjacent numerical value, and the attribute value of the test question difficulty level with the question difficulty level higher by one level is obtained; according to the first knowledge point attribute value, the specific error point of the target learner, which is determined by the first test result, and the attribute value of the test question difficulty level with the question difficulty level higher by one level, further determining a fourth candidate test question; and matching the target learner with the fourth candidate test question. Obviously, the fourth candidate test question and the third candidate test question can be understood as test questions with different subject difficulties. By combining the multiple test results of the target learner, the test question difficulty is pertinently adjusted, the target learner can master deeper knowledge points, and the teaching effect in a classroom is improved.
Further, in a preferred embodiment provided herein, the first environmental content factor belongs to a set of knowledge point attribute values;
the negative feedback type is an error point attribute value.
It is noted that the first environmental content factor may be understood as a first content attribute value determined for characterizing a particular content comprised by a particular object. The negative feedback type may be understood as a specific non-compliant type that does not comply with an expected result after a specific object performs a preset action. In an application scenario of pushing test questions in an intelligent classroom, the first environment content factor may be further defined as an element in a set of attribute values of knowledge points, and is used for representing the knowledge points to be investigated corresponding to the test questions. The set of knowledge point attribute values here is to be understood as that the test questions in the question bank of related subjects may relate to the set of related knowledge points. The negative feedback type can be further defined as an error point attribute value used for characterizing one of the error points which may occur and correspond to each knowledge point. Obviously, the knowledge points and the error points can be set in advance according to the corresponding specific learning content. Through quantizing the related knowledge points and error points in the form of labels, the question pushing efficiency can be effectively improved.
The embodiment provided by the application has at least the following beneficial effects: by combining the knowledge points and the error points, the questions can be recommended in a targeted manner, so that the teaching effect in the classroom is effectively improved.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (10)
1. A negative feedback matching method for an evolution type object is characterized by comprising the following steps:
determining a first environmental content factor;
determining a first environmental presentation scenario from the first environmental content factor;
sending the first environmental presentation scene to the object;
calculating a first feedback value of the object to the first environment presentation scene;
when the first feedback value is negative feedback, determining the negative feedback type of the object according to the first environment content factor;
determining a second environment presentation scene according to the negative feedback type and the first environment content factor;
matching the object with the second ambient presentation scene.
2. The method of claim 1, wherein prior to the step of determining the type of negative feedback of the object based on the first environmental content factor when the first feedback value is negative feedback, the method further comprises:
generating a negative feedback type set corresponding to the first environment content factor according to an enumeration strategy;
wherein the negative feedback type belongs to the set of negative feedback types.
3. The method of claim 1, further comprising the steps of:
calculating a second feedback value of the object to the second environment presentation scene;
when the second feedback value is negative feedback, determining a third environment presentation scene again according to the negative feedback type and the first environment content factor;
matching the object with the third environmental presentation scenario.
4. The method of claim 1, further comprising the steps of:
calculating a second feedback value of the object to the second environment presentation scene;
when the second feedback value is positive feedback, determining a second environment content factor according to a first updating strategy;
determining a third environment presentation scene according to the second environment content factor;
matching the object with the third environmental presentation scenario.
5. The method of claim 1, further comprising the steps of:
calculating a second feedback value of the object to the second environment presentation scene;
and when the second feedback value is positive feedback, matching the object with the first environment presentation scene again.
6. The method of claim 1, further comprising the steps of:
calculating a second feedback value of the object to the second environment presentation scene;
when the second feedback value is positive feedback, determining a third environment presentation scene again according to the first environment content factor;
matching the object with the third environmental presentation scenario.
7. The method of claim 3, further comprising the steps of:
calculating a third feedback value of the object to the third environment presentation scenario;
when the third feedback value is negative feedback, determining an environment complexity factor corresponding to the third environment presentation scene;
reducing the environment complexity factor by one unit to form an updated environment complexity factor;
determining a fourth environment presentation scene according to the negative feedback type, the first environment content factor and the updated environment complexity factor;
matching the object with the fourth environment presentation scenario.
8. The method of claim 3, further comprising the steps of:
calculating a third feedback value of the object to the third environment presentation scenario;
when the third feedback value is positive feedback, determining a fourth environment presentation scene according to the negative feedback type and the first environment content factor;
matching the object with the fourth environment presentation scenario.
9. The method of any one of claims 4 or 6, further comprising the steps of:
calculating a third feedback value of the object to the third environment presentation scenario;
when the third feedback value is positive feedback, determining an environment complexity factor corresponding to the third environment presentation scene;
promoting the environment complexity factor by one unit to form an updated environment complexity factor;
determining a fourth environment presentation scene according to the negative feedback type, the first environment content factor and the updated environment complexity factor;
matching the object with the fourth environment presentation scenario.
10. The method of claim 1, wherein the first environmental content factor belongs to a set of knowledge point attribute values;
the negative feedback type is an error point attribute value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111656395.7A CN114003715A (en) | 2021-12-31 | 2021-12-31 | Negative feedback matching method for evolution type object |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111656395.7A CN114003715A (en) | 2021-12-31 | 2021-12-31 | Negative feedback matching method for evolution type object |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114003715A true CN114003715A (en) | 2022-02-01 |
Family
ID=79932390
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111656395.7A Pending CN114003715A (en) | 2021-12-31 | 2021-12-31 | Negative feedback matching method for evolution type object |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114003715A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150099256A1 (en) * | 2013-12-17 | 2015-04-09 | Chien Cheng Liu | Intelligent teaching and tutoring test method |
| CN106227809A (en) * | 2016-07-22 | 2016-12-14 | 广东小天才科技有限公司 | Test question pushing method and device |
| CN109035088A (en) * | 2018-07-19 | 2018-12-18 | 江苏黄金屋教育发展股份有限公司 | Adaptive learning method based on mistake topic |
| CN110287293A (en) * | 2019-07-08 | 2019-09-27 | 上海乂学教育科技有限公司 | Automatically topic management system is pushed away |
| CN113763767A (en) * | 2021-08-25 | 2021-12-07 | 赣州市加薪教育科技有限公司 | Learning test question pushing method and device, computer equipment and storage medium |
-
2021
- 2021-12-31 CN CN202111656395.7A patent/CN114003715A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150099256A1 (en) * | 2013-12-17 | 2015-04-09 | Chien Cheng Liu | Intelligent teaching and tutoring test method |
| CN106227809A (en) * | 2016-07-22 | 2016-12-14 | 广东小天才科技有限公司 | Test question pushing method and device |
| CN109035088A (en) * | 2018-07-19 | 2018-12-18 | 江苏黄金屋教育发展股份有限公司 | Adaptive learning method based on mistake topic |
| CN110287293A (en) * | 2019-07-08 | 2019-09-27 | 上海乂学教育科技有限公司 | Automatically topic management system is pushed away |
| CN113763767A (en) * | 2021-08-25 | 2021-12-07 | 赣州市加薪教育科技有限公司 | Learning test question pushing method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102015075B1 (en) | Method, apparatus and computer program for operating a machine learning for providing personalized educational contents based on learning efficiency | |
| Paquette et al. | Comparing machine learning to knowledge engineering for student behavior modeling: a case study in gaming the system | |
| US20170154542A1 (en) | Automated grading for interactive learning applications | |
| CN112507140A (en) | Personalized intelligent learning recommendation method, device, equipment and storage medium | |
| CN110941723A (en) | Method, system and storage medium for constructing knowledge graph | |
| US11120701B2 (en) | Adaptive presentation of educational content via templates | |
| CN109389870B (en) | Data self-adaptive adjusting method and device applied to electronic teaching | |
| US20140349272A1 (en) | Method for evaluating performance of a user on an e-learning system | |
| CN110929020B (en) | Knowledge point mastering degree analysis method based on test results | |
| Gil | Short project-based learning with MATLAB applications to support the learning of video-image processing | |
| CN117252047B (en) | Teaching information processing method and system based on digital twinning | |
| CN115544241A (en) | Intelligent pushing method and device for online operation | |
| CN110609947A (en) | Learning content recommendation method, terminal and storage medium of intelligent learning system | |
| KR102075936B1 (en) | Method, apparatus and computer program for operating a machine learning for providing personalized educational contents based on learning efficiency | |
| García et al. | Using rules discovery for the continuous improvement of e-learning courses | |
| CN114492803A (en) | Knowledge graph-based question and answer generation method and device and automatic examination question generation system | |
| CN113742453A (en) | Artificial intelligence wrong question correlation method and system | |
| CN116483948B (en) | Cloud computing-based SaaS operation and maintenance management method, system, device and storage medium | |
| CN111310036A (en) | Self-adaptive learning task pushing method and device, electronic equipment and storage medium | |
| CN114003715A (en) | Negative feedback matching method for evolution type object | |
| CN114240705A (en) | Question bank information processing method | |
| CN112860983B (en) | Method, system, equipment and readable storage medium for pushing learning content | |
| US20160210349A1 (en) | Generating content relationships based on aggregate user solicited feedback | |
| CN115129971A (en) | Course recommendation method and device based on capability evaluation data and readable storage medium | |
| US10453354B2 (en) | Automatically generated flash cards |
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 |