Subject knowledge learning method planning system

Abstract

The invention belongs to the technical field of intelligent education, and provides a subject knowledge learning method planning system, which comprises an input data acquisition module, a knowledge graph analysis module, a knowledge graph planning classification module, a content classification module, an association combination output module, an abstract concept learning path module, an evaluation module and a planning module. Wherein functions of the output module and the planning module are associated and combined through the content classification module. And the content classification module performs third-level classification on the data subjected to second-level classification to obtain hierarchical abstract concept data information. And the association combination output module outputs learning content and abstract result data by using a neural network model, and performs grading according to difficulty. And finally, a planning module plans learning methods of abstracted and non-abstracted contents of the current subject for the user step by step according to the answering accuracy of the evaluation module.

Description

Technical Field

[0001] The invention belongs to the field of intelligent education technology, and specifically is a subject knowledge learning method planning system. Background Art

[0002] With the rapid development of educational informatization, the subject knowledge learning method planning system came into being, aiming to help learners master the knowledge of various subjects more efficiently and systematically. Based on advanced educational concepts and information technology, the system provides learners with personalized learning method planning and guidance through in-depth analysis of subject knowledge structure and accurate grasp of learners' learning behavior;

[0003] In the patent titled Learning Cognitive Path Planning System Based on Cognitive Map and Publication Number CN112001825B, it is proposed that the current teaching model is to provide indiscriminate and uniform teaching to all learners based on the same cognitive map. Although this teaching model can meet the learning needs of most learners and effectively reduce the workload of pre-teaching preparation, it cannot provide adaptive learning cognitive path planning for learners with different learning needs and learning abilities, thereby reducing teaching quality and teaching efficiency. It can be seen that the prior art is in urgent need of a teaching model that can match and adjust the learning cognitive path according to the learning needs and learning interests of different learners, and it evaluates the learning interest value of each user among several different users for each of the sub-graphs; the learning cognitive path planning module is used to determine the learning order and / or learning progress of several knowledge point data of different users according to the learning interest values ​​corresponding to all users; it can be seen that the learning cognitive path planning system based on the cognitive graph improves the degree of analysis and refinement of the cognitive graph by dividing the cognitive graph into several sub-graphs, and can also adjust the learning order and / or learning progress of different users for the corresponding knowledge point data according to the degree of interest of different learners in different sub-graphs, thereby effectively improving the teaching quality and teaching efficiency, but among students who are not interested in learning, they are generally not sensitive to the learning content, and once they are exposed to the learning content, their desire to learn will be greatly reduced, while when they are exposed to other content, their willingness to contact will not be too low.

[0004] To this end, those skilled in the art have proposed a subject knowledge learning method planning system to solve the problems raised by the background technology. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a subject knowledge learning method planning system to solve the problems of low learning desire and lack of learning planning among students in the process of spanning different subjects in the prior art.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A subject knowledge learning method planning system, comprising an input data collection module, a knowledge graph analysis module, a knowledge graph planning classification module, a content classification module, an association combination output module, an abstract concept learning path module, an evaluation module and a planning module;

[0008] The input data collection module is used to collect the learning content input by the user, and continuously detect and collect the past historical user data to form a user data collection;

[0009] The knowledge graph analysis module is used to analyze and classify the learning content input by the user and assign it to the corresponding subject according to the learning content characteristics of the user data;

[0010] The knowledge graph planning classification module is used to perform secondary classification on the data in the knowledge graph analysis module to obtain abstract concept data;

[0011] The content classification module is used to classify the abstract concept data into three levels to obtain hierarchical abstract concept data information;

[0012] The association and combination output module is used to input the hierarchical abstract concept data information into the neural network model and output the abstract result data and learning content data in combination with the big data content;

[0013] The abstract concept learning path module is used to generate corresponding abstract concept topic data and non-abstract learning real information data according to the abstract result data and the learning content data. The abstract concept topic is 1:1 identical to the non-abstract learning real information data. The abstract concept topic is the abstract information version of the non-abstract real information data.

[0014] The evaluation module and planning module are used to collect the accuracy of users' answers to abstract concept questions and non-abstract learning real information data, and provide the abstract learning planning path and 1:1 non-abstract real learning planning path of the current subject based on the accuracy of the answers combined with the neural network model.

[0015] Preferably, the knowledge graph analysis module performs feature splitting on the learning content information input into the data collection module, and classifies the input learning content information through feature splitting. The subject categories preset in the knowledge graph analysis module include Chinese, mathematics, English, physics, chemistry, biology, politics, geography and history. During the analysis and classification, it is determined whether the input learning content information belongs to any one or more of Chinese, mathematics, English, physics, chemistry, biology, politics, geography and history.

[0016] Preferably, when the knowledge graph analysis module analyzes and classifies the learning content information input into the data collection module and selects multiple preset subject categories, it determines whether the current subject has an interdisciplinary phenomenon. When both liberal arts data information and science data information appear, it is determined to be an interdisciplinary phenomenon. When an interdisciplinary phenomenon occurs, a weight value is set. The weight value of liberal arts alone and science alone is 0, and the weight value is 1 when it is determined to be an interdisciplinary phenomenon.

[0017] Preferably, the knowledge graph planning classification module is used to perform secondary classification on the data in the knowledge graph analysis module. The secondary classification in the humanities is word classes, parts of speech, and punctuation, and the secondary classification in the science is numbers and symbols. After the data in the knowledge graph analysis module is subjected to secondary classification, it is abstracted. The abstraction includes a phenomenon layer, an essential layer, and a relationship layer. The relationship layer includes a micro layer and a macro layer. In the humanities, the micro layer stores word classes, parts of speech, and punctuation, and the macro layer includes words and sentences composed of word classes and parts of speech. In the science, the micro layer stores the relationship between data and symbols, and the macro layer stores the operation instances of the current symbol. The data in the knowledge graph analysis module is subjected to secondary classification to obtain abstract concept data.

[0018] Preferably, the secondary classification abstraction concept data in the knowledge graph planning classification module further includes the following steps:

[0019] S1. Determine the goal. The goal includes the final goal and the stage goal. The final goal is the final meaning expressed by words and vocabulary in the humanities and the final result of numbers and symbols in the sciences.

[0020] S2. Stage goal. Stage goal is the process to achieve the final goal. In liberal arts, it is the combination and application of words and vocabulary; in science, it is the calculation process of numbers and symbols.

[0021] Preferably, the target data set is set in the S1 determination target and the S2 stage target.

[0022] Preferably, the content classification module is used to classify the phenomenon layer data, essence layer data and target data set in the secondary classification into three levels to obtain hierarchical abstract concept data information.

[0023] Preferably, the association combination output module is used to input hierarchical abstract concept data information into the neural network model and output abstract result data and learning content data in combination with the big data content, and utilizes the neural network model as a basis to continuously transmit content data similar to the original learning content input by the user through big data, continuously absorbs similar content data through the neural network model, continuously trains the neural network model, and generates the same type of learning content data according to the weight value.

[0024] Preferably, the same type of learning content data is divided into level one difficulty, level two difficulty and level three difficulty, level one difficulty is simple abstract concept transformation, level two difficulty is abstract concept application, and level three difficulty is complex abstract concept transformation application.

[0025] Preferably, the planning module plans the learning method of the abstract content and non-abstract content of the current subject step by step according to the abstract and non-abstract answer accuracy rates of the user obtained by the evaluation module.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] 1. The present invention collects learning content input by users through the investment of data collection module, and integrates past historical user data to form a user data collection. Subsequently, the knowledge graph analysis module analyzes and classifies these learning contents, and assigns them to corresponding subjects, such as Chinese, mathematics, English, etc., according to the characteristics of the learning contents. On this basis, the knowledge graph planning classification module further performs secondary classification to obtain abstract concept data. For example, in the subject of English, vocabulary, parts of speech, and punctuation can be used as elements of secondary classification. The content classification module performs three-level classification on these abstract concept data to obtain hierarchical abstract concept data information, providing a basis for the planning of subsequent learning paths.

[0028] 2. The present invention can not only perform feature splitting and classification of input learning content through the knowledge graph analysis module, but also determine whether there is an interdisciplinary phenomenon and set the corresponding weight value. The knowledge graph planning classification module further performs secondary classification and abstract processing on the data, clarifies the final goal and stage goal, and sets a data set for the goal, providing data support for the remaining learning content and learning goals through the data set.

[0029] 3. The present invention uses the functions of content classification module, association and output module and planning module. The content classification module classifies the data of secondary classification into three levels to obtain graded abstract concept data information. The association and output module uses a neural network model to output learning content and abstract result data, and classifies them according to difficulty. Finally, the planning module plans the learning method of abstract and non-abstract content of the current subject for users step by step according to the correct answer rate of the evaluation module. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 This is a module diagram of a subject knowledge learning method planning system of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] As attached Figure 1 As shown:

[0034] Embodiment 1: The present invention provides a subject knowledge learning method planning system, including an input data collection module, a knowledge graph analysis module, a knowledge graph planning classification module, a content classification module, an association combination output module, an abstract concept learning path module, an evaluation module and a planning module;

[0035] The input data collection module is used to collect the learning content input by the user, and continuously detect and collect the past historical user data to form a user data collection;

[0036] The knowledge graph analysis module is used to analyze and classify the learning content input by the user and assign it to the corresponding subject according to the learning content characteristics of the user data;

[0037] The knowledge graph planning classification module is used to perform secondary classification on the data in the knowledge graph analysis module to obtain abstract concept data;

[0038] The content classification module is used to classify the abstract concept data into three levels to obtain hierarchical abstract concept data information;

[0039] The association and combination output module is used to input the hierarchical abstract concept data information into the neural network model and output the abstract result data and learning content data in combination with the big data content;

[0040] The abstract concept learning path module is used to generate corresponding abstract concept topic data and non-abstract learning real information data according to the abstract result data and the learning content data. The abstract concept topic is 1:1 identical to the non-abstract learning real information data. The abstract concept topic is the abstract information version of the non-abstract real information data.

[0041] The evaluation module and planning module are used to collect the accuracy of users' answers to abstract concept questions and non-abstract learning real information data, and provide the abstract learning planning path and 1:1 non-abstract real learning planning path of the current subject based on the accuracy of the answers combined with the neural network model.

[0042] As can be seen from the above, in this system, the data collection module is first used to collect the learning content input by the user, and the historical user data is integrated to form a user data collection. Subsequently, the knowledge graph analysis module analyzes and classifies these learning contents, and assigns them to corresponding subjects according to the characteristics of the learning contents, such as Chinese, mathematics, English, etc. On this basis, the knowledge graph planning classification module further performs secondary classification to obtain abstract concept data. For example, in the English subject, vocabulary, parts of speech, and punctuation can be used as elements of secondary classification. The content classification module performs three-level classification on these abstract concept data to obtain hierarchical abstract concept data information, which provides a basis for the planning of subsequent learning paths.

[0043] Embodiment 2: This embodiment is basically the same as the previous embodiment, except that the features are further split, and whether there is an interdisciplinary phenomenon is determined based on the split features. In real learning, there will not only be learning content of a single subject, but also interdisciplinary learning content. Some common sense content appears interdisciplinary in the title, so the subject span is identified in the feature splitting process, such as Figure 1 As shown, the knowledge graph analysis module performs feature splitting on the learning content information input into the data collection module, and classifies the input learning content information through feature splitting. The subject categories preset in the knowledge graph analysis module include Chinese, mathematics, English, physics, chemistry, biology, politics, geography and history. During the analysis and classification, it is determined whether the input learning content information belongs to any one or more of Chinese, mathematics, English, physics, chemistry, biology, politics, geography and history.

[0044] Specifically, when the knowledge graph analysis module analyzes and classifies the learning content information input into the data collection module and selects multiple preset subject categories, it determines whether the current subject has an interdisciplinary phenomenon. When both liberal arts data information and science data information appear, it is determined to be an interdisciplinary phenomenon. When an interdisciplinary phenomenon occurs, a weight value is set. The weight value of the liberal arts alone and the science alone is 0, and the weight value is 1 when it is determined to be an interdisciplinary phenomenon.

[0045] Specifically, the knowledge graph planning classification module is used to perform secondary classification of the data in the knowledge graph analysis module. The secondary classification in the humanities is word classes, parts of speech, and punctuation, and the secondary classification in the science is numbers and symbols. After the data in the knowledge graph analysis module is subjected to secondary classification, it is abstracted. The abstraction includes the phenomenon layer, the essence layer, and the relationship layer. The relationship layer includes the micro layer and the macro layer. In the humanities, the micro layer stores word classes, parts of speech, and punctuation, and the macro layer includes words and sentences composed of word classes and parts of speech. In the science, the micro layer stores the relationship between data and symbols, and the macro layer stores the operation instances of the current symbol. The data in the knowledge graph analysis module is subjected to secondary classification to obtain abstract concept data.

[0046] Specifically, the secondary classification abstraction concept data in the knowledge graph planning classification module also includes the following steps:

[0047] S1. Determine the goal. The goal includes the final goal and the stage goal. The final goal is the final meaning expressed by words and vocabulary in the humanities and the final result of numbers and symbols in the sciences.

[0048] S2. Stage goal. Stage goal is the process to achieve the final goal. In liberal arts, it is the combination and application of words and vocabulary; in science, it is the calculation process of numbers and symbols.

[0049] Specifically, it is set as a target data set in the S1 determination target and the S2 stage target.

[0050] Examples of the actual process and principles of abstract concepts are:

[0051] Take I have eaten two__(apples) as an example,

[0052] The first step is to understand the relationship: what we see is the appearance of the English language (language phenomenon) --- sentences, so the relationship to be dealt with is the relationship between people and English sentences. The specific manifestation of this relationship is: seeing through the phenomenon and combining it with the essence to solve the problem --- the relationship between the phenomenon of the sentence and the essence of the sentence;

[0053] The second step is the demonstration of the relationship: the specific demonstration of the relationship between the phenomenon of the sentence and the essence of the sentence:

[0054] 1. On the surface, the classification of relationships to be dealt with:

[0055] 101. Micro level: vocabulary and words and vocabulary and punctuation;

[0056] 102. Macro level: vocabulary and sentences;

[0057] 2. From the perspective of dealing with the relationship between phenomenon and essence, look at the steps of dealing with the relationship:

[0058] Target layer

[0059] 201. Final goal: to write a correct English sentence, dealing with the macro-level relationship between spaces and sentences;

[0060] 202. Stage goal: Space, which deals with the two micro-level relationships: the close or distant relationship between the space and the words on its left and right, and the relationship between the space and punctuation marks.

[0061] Planning Layer

[0062] 3. Macro level.

[0063] On the surface, it deals with the relationship between the words representing the stage goals and the sentences they are in - the relationship between the stage goals and the final goals. In essence, it deals with the relationship between the element concept and the set concept - relationship demonstration:

[0064] Sentences are made up of words.

[0065] The sentence itself is also a collective concept. Each sentence is a sentence in a certain category of sentences, so we need to do sentence analysis. Through analysis, we know that this question essentially deals with the relationship between stage goals and final goals from a macro level.

[0066] A specific example is the relationship between the words representing the stage goals and the sentences representing the final goals - the relationship between the Chinese expression of apple in English (the original form apple le and I have eaten two__(apples). The essential characteristics of this sentence: a declarative sentence that expresses an affirmative action and has the characteristics of a simple sentence, and the topic it is about is the topic of personal life under the theme group of people and themselves.

[0067] 4. Microscopic layer

[0068] On the surface, it deals with the relationship between the vocabulary representing the stage goal and other words in the sentence, as well as its relationship with punctuation marks. In essence, it deals with the relationship between the vocabulary representing the stage goal and the functions of the categories of other words in the sentence, as well as the relationship between it and the functions of the categories of specific punctuation marks in the sentence.

[0069] Relationship example: the expression of Chinese apple in English (the relationship between the category of the original form apple - noun and the numeral of the category of two in I have eaten two__ (apple), and the test point ---- the vocabulary of the stage target is the noun apple.

[0070] Moreover, the word apple itself has no usage. Its usage comes from the usage of nouns in its category (concept, classification, number, case). Therefore, apple should handle its relationship with the nouns in its category. Similarly, the word two itself has no usage. Its usage comes from the cardinal number in the numeral in its category, which indicates the usage of quantity. Therefore, two should handle its relationship with the cardinal number in the numeral in its category.

[0071] From this, we can see that, on the surface, it is about the relationship between two and apple, but in essence, it is about the relationship between the cardinal number in the numeral (two, which represents the plural concept) and the category noun that apple belongs to - the test point is the number of the noun. The specific steps are as follows:

[0072] Deal with the relationship between the element concept of Apple as a concrete noun and the collective concept of the number rule of nouns.

[0073] The relationship between the element concept of "apple" as a plural countable noun and the set concept of "rules for the plural countable nouns";

[0074] 5. Results

[0075] 501. Results and goals: the problem of consistency - the content of the results - apps

[0076] 502. Results and plans: methodical and logical - the process of reaching results - if the process is good, the results will definitely be good.

[0077] 503. Results and application: the relationship between learning and use-----if you can learn, you can apply.

[0078] As can be seen from the above, the knowledge graph analysis module can not only split and classify the input learning content, but also determine whether there is an interdisciplinary phenomenon and set the corresponding weight value. The knowledge graph planning classification module further performs secondary classification and abstract processing on the data, clarifies the final goal and stage goals, and sets the data set for the goal.

[0079] Embodiment 3: This embodiment is basically the same as the previous embodiment, except that, when interdisciplinary phenomena occur, not only the knowledge content of one discipline but also the knowledge content of additional disciplines should be considered, and the discipline content can be integrated through abstract concepts, so that the abstract concepts can be obtained and graded to obtain better learning effects.

[0080] Specifically, the content classification module is used to classify the phenomenon layer data, essence layer data and target data set in the secondary classification into three levels to obtain hierarchical abstract concept data information.

[0081] Specifically, the association combination output module is used to input hierarchical abstract concept data information into the neural network model and output abstract result data and learning content data in combination with the big data content. The neural network model is used as a basis to continuously transmit content data similar to the original learning content input by the user through big data, and similar content data is continuously absorbed through the neural network model. The neural network model is continuously trained to generate the same type of learning content data according to the weight value.

[0082] Specifically, the same type of learning content data is divided into level one difficulty, level two difficulty and level three difficulty. Level one difficulty is simple abstract concept transformation, level two difficulty is abstract concept application, and level three difficulty is complex abstract concept transformation application.

[0083] Specifically, the planning module plans the learning method of the abstract content and non-abstract content of the current subject step by step according to the abstract and non-abstract answer accuracy rates of the user obtained by the evaluation module.

[0084] From the above, we can see that through the functions of the content classification module, the association and output module, and the planning module. The content classification module classifies the data of the secondary classification into three levels to obtain graded abstract concept data information. The association and output module uses the neural network model to output the learning content and abstract result data, and classifies them according to the difficulty. Finally, the planning module plans the learning methods of the abstract and non-abstract content of the current subject for users step by step according to the correct answer rate of the evaluation module.

[0085] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claim involved.

[0086] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A subject knowledge learning method planning system, It includes, and is characterized by: input data collection module, knowledge graph analysis module, knowledge graph planning classification module, content classification module, association combination output module, abstract concept learning path module, evaluation module and planning module; The input data collection module is used to collect the learning content input by the user, and continuously detect and collect the past historical user data to form a user data collection; The knowledge graph analysis module is used to analyze and classify the learning content input by the user and assign it to the corresponding subject according to the learning content characteristics of the user data; The knowledge graph planning classification module is used to perform secondary classification on the data in the knowledge graph analysis module to obtain abstract concept data; The content classification module is used to classify the abstract concept data into three levels to obtain hierarchical abstract concept data information; The association and combination output module is used to input the hierarchical abstract concept data information into the neural network model and output the abstract result data and learning content data in combination with the big data content; The abstract concept learning path module is used to generate corresponding abstract concept topic data and non-abstract learning real information data according to the abstract result data and the learning content data. The abstract concept topic is 1:1 identical to the non-abstract learning real information data. The abstract concept topic is the abstract information version of the non-abstract real information data. The evaluation module and planning module are used to collect the accuracy of users' answers to abstract concept questions and non-abstract learning real information data, and provide the abstract learning planning path and 1:1 non-abstract real learning planning path of the current subject based on the accuracy of the answers combined with the neural network model.

2. A subject knowledge learning method planning system as claimed in claim 1, characterized in that: The knowledge graph analysis module performs feature splitting on the learning content information input into the data collection module, and classifies the input learning content information through feature splitting. The subject categories preset in the knowledge graph analysis module include Chinese, mathematics, English, physics, chemistry, biology, politics, geography and history. During the analysis and classification, it is determined whether the input learning content information belongs to any one or more of Chinese, mathematics, English, physics, chemistry, biology, politics, geography and history.

3. A subject knowledge learning method planning system as claimed in claim 2, characterized in that: When the knowledge graph analysis module analyzes and classifies the learning content information input into the data collection module and selects multiple preset subject categories, it determines whether the current subject has an interdisciplinary phenomenon. When both liberal arts data information and science data information appear, it is determined to be an interdisciplinary phenomenon. When an interdisciplinary phenomenon occurs, a weight value is set. The weight value of the liberal arts alone and the science alone is 0, and the weight value is 1 when it is determined to be an interdisciplinary phenomenon.

4. A subject knowledge learning method planning system as claimed in claim 1, characterized in that: The knowledge graph planning classification module is used to perform secondary classification on the data in the knowledge graph analysis module. The secondary classification in the humanities is word classes, parts of speech, and punctuation, and the secondary classification in the science is numbers and symbols. After the data in the knowledge graph analysis module is subjected to secondary classification, it is abstracted. The abstraction includes the phenomenon layer, the essence layer, and the relationship layer. The relationship layer includes the micro layer and the macro layer. In the humanities, the micro layer stores word classes, parts of speech, and punctuation, and the macro layer includes words and sentences composed of word classes and parts of speech. In the science, the micro layer stores the relationship between data and symbols, and the macro layer stores the operation instances of the current symbol. The data in the knowledge graph analysis module is subjected to secondary classification to obtain abstract concept data.

5. A subject knowledge learning method planning system as claimed in claim 1, characterized in that: The secondary classification abstraction concept data in the knowledge graph planning classification module also includes the following steps: S1. Determine the goal. The goal includes the final goal and the stage goal. The final goal is the final meaning expressed by words and vocabulary in the humanities and the final result of numbers and symbols in the sciences. S2. Stage goal. Stage goal is the process to achieve the final goal. In liberal arts, it is the combination and application of words and vocabulary; in science, it is the calculation process of numbers and symbols.

6. A subject knowledge learning method planning system as claimed in claim 5, characterized in that: The target data set is set in the S1 determination target and the S2 stage target.

7. A subject knowledge learning method planning system as claimed in claim 1, characterized in that: The content classification module is used to classify the phenomenal layer data, the essential layer data and the target data set in the secondary classification into three levels to obtain hierarchical abstract concept data information.

8. A subject knowledge learning method planning system as claimed in claim 1, characterized in that: The association combination output module is used to input hierarchical abstract concept data information into the neural network model and output abstract result data and learning content data in combination with the big data content. It uses the neural network model as a basis to continuously transmit content data similar to the original learning content input by the user through big data, continuously writes similar content data through the neural network model, continuously trains the neural network model, and generates the same type of learning content data according to the weight value.

9. A subject knowledge learning method planning system as claimed in claim 8, characterized in that: The same type of learning content data is divided into level one difficulty, level two difficulty and level three difficulty. Level one difficulty is simple abstract concept transformation, level two difficulty is abstract concept application, and level three difficulty is complex abstract concept transformation application.

10. A subject knowledge learning method planning system as claimed in claim 1, characterized in that: The planning module plans the learning method of the abstract content and non-abstract content of the current subject step by step according to the abstract and non-abstract answer accuracy rates of the user obtained by the evaluation module.

Images