A digital interactive learning model system and operation method

Abstract

The present invention relates to the field of digital technology, and in particular to a digital interactive learning model system and an operation method. In the present invention, a digital interactive learning model is tested, a test question sentence is input into the digital interactive learning model, an output reply sentence is matched with a test reply sentence corresponding to a pre-stored test question sentence, features in the reply sentence and the test reply sentence are respectively extracted, the operation of the model is analyzed based on the number of identical features, the ambiguity of the test question sentence is analyzed according to the number of associated words of each feature in the test question sentence, and the degree of influence of the test question sentence on the operation of the model is analyzed according to the ambiguity of the test question sentence. The more the number of associated words, the more interpretations of the question sentence, and the greater the influence on the operation of the model. The operation of the model is analyzed according to the number of associated words. When there are many associated words, the number of subsequent reply sentences is increased to improve the interactive learning efficiency of the model.

Description

Technical Field

[0001] The present invention relates to the field of digital technology, and in particular to a digital interactive learning model system and an operating method. Background Art

[0002] The digital interactive learning model system is a system that combines modern information technology and educational theory. It improves learning efficiency and quality by providing a highly interactive and personalized learning experience. Existing technologies obtain the data and models of the current simulation system, and use three-dimensional simulation technology to present the results of real-time interaction in the form of animation, so that operators can obtain a complete operational interactive experience. However, the impact of polysemous keywords on the interactive learning process is not considered.

[0003] Chinese Patent Publication No. CN114973835A discloses a digital, deeply immersive, interactive learning model training system and implementation method. The system features an equipment training simulation workbench equipped with a virtual reality interactive results display module, an operation simulation module, and an intelligent trainer module. A data interaction link framework is used to access the current simulation system's data and models, providing data interfaces and basic data interaction services for all modules of the equipment training simulation workbench. The acquired data information is then presented in the form of animated real-time interactive results using 3D simulation technology. This system effectively enables operators to gain a complete interactive operational experience, quickly learn complete equipment operating requirements, and shorten the lead time for on-boarding.

[0004] However, the prior art still has the following problems:

[0005] Polysemous keywords will have an impact on interactive learning and affect the efficiency of interactive learning. Summary of the Invention

[0006] To this end, the present invention provides a digital interactive learning model system and an operating method to overcome the problem in the prior art that polysemous keywords may affect interactive learning and affect the efficiency of interactive learning.

[0007] To achieve the above objectives, the present invention provides a digital interactive learning model system. It includes:

[0008] A model building module for building a digital interactive learning model based on the response data;

[0009] A test question module, which is connected to the model building module and stores test question sentences and test answer sentences corresponding to the test question sentences, and is used to output the test question sentences;

[0010] A feature extraction module, connected to the test question module, for extracting features from the test question sentence;

[0011] an interactive module connected to the model building module and the feature extraction module, configured to input the features of the single test question sentence extracted by the feature extraction module into the digital interactive learning model and output a reply sentence of the digital interactive learning model;

[0012] a test verification module connected to the test question module, the feature extraction module, and the interactive module, configured to analyze whether the operation of the digital interactive learning model is qualified based on the degree of matching between the reply statement and the test reply statement, perform a secondary analysis on whether the operation of the digital interactive learning model is qualified based on the number of features extracted by the feature extraction module, and determine the type of interference intensity for the operation of the digital interactive learning model based on the number of associated features of the features in the test question statement;

[0013] A self-adjustment module is connected to the test verification module and is used to determine a processing method for the question test based on the interference intensity type determined by the test verification module, including:

[0014] The feature extraction method is judged to be unqualified.

[0015] Alternatively, it is determined that the test question statement is ambiguous, and the number of reply statements following the corresponding test question statement is increased based on non-matching keywords between the test reply statement and the reply statement.

[0016] The present invention provides a method for operating a digital interactive learning model, comprising:

[0017] Build a digital learning model;

[0018] Inputting a test reply statement into the digital learning model to obtain a reply statement, and analyzing whether the operation of the digital interactive learning model is qualified based on the matching degree between the test reply statement and the characteristics of the reply statement;

[0019] Conducting a secondary analysis on whether the digital interactive learning model is qualified based on the number of features of the test question sentences;

[0020] Determining the interference intensity type for the operation of the digital interactive learning model based on the associated feature number of the features in the test question sentence, and judging that the feature extraction method is unqualified according to the interference intensity type,

[0021] Alternatively, it is determined that the test question statement is ambiguous, and the number of reply statements following the corresponding test question statement is increased based on non-matching keywords between the test reply statement and the reply statement.

[0022] Furthermore, the test verification module is used to analyze whether the operation of the digital interactive learning model is qualified based on the matching degree between the reply statement and the test reply statement, wherein:

[0023] The matching degree is the ratio of the number of features that are the same between the response statement and the test response statement based on the test verification module to the total number of features in the test response statement.

[0024] Furthermore, the test verification module is used to analyze whether the operation of the digital interactive learning model is qualified based on the matching degree between the reply statement and the test reply statement, including:

[0025] The test verification module determines whether the operation of the digital interactive learning model is qualified;

[0026] The test verification module determines whether the operation of the digital interactive learning model is qualified based on the number of features extracted by the feature extraction module, or,

[0027] The test verification module determines that the operation of the digital interactive learning model is unqualified, and determines the interference intensity type for the operation of the digital interactive learning model based on the associated feature number of the features in the test question sentence.

[0028] Furthermore, the test verification module performs a secondary analysis on whether the operation of the digital interactive learning model is qualified based on the characteristic quantity representation parameters, wherein:

[0029] The feature quantity characterization parameter is the ratio of the number of features extracted by the feature extraction module to the total number of features of the test question sentence.

[0030] Furthermore, the test verification module performs a secondary analysis on whether the operation of the digital interactive learning model is qualified based on the characteristic quantity representation parameters, including:

[0031] The test verification module determines whether the operation of the digital interactive learning model is qualified or unqualified, and determines the interference intensity type for the operation of the digital interactive learning model based on the associated feature number of the features in the test question sentence.

[0032] Furthermore, the test verification module determines the interference intensity type for the operation of the digital interactive learning model based on the number of associated features of the features in the test question sentence, including: a strong interference type and a weak interference type.

[0033] Furthermore, the self-adjustment module determines a processing method for the question test based on the interference intensity type determined by the test verification module, including:

[0034] The self-adjusting module determines that the method for extracting the features of the test question sentence is unqualified, or determines that the features of the test question sentence are ambiguous.

[0035] Furthermore, the self-adjusting module increases the number of reply statements following the corresponding test question statement based on the non-matching keywords between the test reply statement and the reply statement, including:

[0036] Identify features in the test response sentences,

[0037] Identify features in the response sentence,

[0038] Features that are different between the test reply sentence and the reply sentence are determined as non-matching keywords.

[0039] Furthermore, the self-adjusting module increases the number of reply statements following the corresponding test question statement based on non-matching keywords between the test reply statement and the reply statement, wherein:

[0040] The increase in the number of response sentences following the test question sentence is positively correlated with the number of non-matching keywords.

[0041] Compared with the prior art, the beneficial effect of the present invention lies in that the digital interactive learning model is tested in the present invention, a test question statement is input into the digital interactive learning model, the output reply statement is matched with the test reply statement corresponding to the pre-stored test question statement, the features in the reply statement and the test reply statement are extracted respectively, and the operation of the model is analyzed based on the number of the same features. Taking into account the polysemy of some words, the polysemy of the test question statement is analyzed according to the number of associated words of each feature in the test question statement, so as to analyze the degree of influence of the test question statement on the operation of the model according to the polysemy of the test question statement. The more the number of associated words, the more interpretations of the question statement, and the greater the impact on the operation of the model. The operation of the model is analyzed according to the number of associated words. When there are many associated words, the number of subsequent reply statements is increased to improve the interactive learning efficiency of the model.

[0042] Furthermore, in the present invention, the number of corresponding reply statements is increased according to the number of keywords that do not match the test reply statement and the reply statement. The more unmatched keywords there are, the greater the deviation between the reply statement recognized by the model and the test reply statement. The number of subsequent reply statements is increased according to the number of unmatched keywords, and relevant statements are output to improve the accuracy of the reply, thereby further improving the interactive learning efficiency of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a structural diagram of the digital interactive learning model system of the present invention;

[0044] Figure 2 A flowchart of the operation method of the digital interactive learning model;

[0045] Figure 3A flow chart for analyzing whether the operation of the digital interactive learning model is qualified;

[0046] Figure 4 A flowchart for determining whether the operation of the digital interactive learning model is qualified for secondary analysis. DETAILED DESCRIPTION

[0047] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0048] It should be noted that the data in this embodiment are obtained by comprehensive analysis and evaluation of the historical data of the six months before the current determination and the corresponding historical determination results by the system of the present invention. It can be understood by those skilled in the art that the system of the present invention can determine the above parameters for each of the above parameters by selecting the value with the highest proportion as the preset standard parameter based on the data distribution, using weighted summation to use the obtained value as the preset standard parameter, substituting each historical data into a specific formula and using the value obtained by the formula as the preset standard parameter, or other selection methods, as long as the system of the present invention can clearly define the different specific situations in the single determination process through the obtained values.

[0049] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0050] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside", and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0051] Furthermore, it should be noted that, in the description of the present invention, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed connections, detachable connections, or integral connections; mechanical connections or electrical connections; direct connections or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0052] See also Figure 1 As shown, it is a structural block diagram of the digital interactive learning model system of the present invention.

[0053] The digital interactive learning model system provided by the embodiment of the present invention includes:

[0054] A model building module for building a digital interactive learning model based on the response data;

[0055] A test question module, which is connected to the model building module and stores test question sentences and test answer sentences corresponding to the test question sentences, and is used to output the test question sentences;

[0056] A feature extraction module, connected to the test question module, for extracting features from the test question sentence;

[0057] an interactive module connected to the model building module and the feature extraction module, configured to input the features of the single test question sentence extracted by the feature extraction module into the digital interactive learning model and output a reply sentence of the digital interactive learning model;

[0058] a test verification module connected to the test question module, the feature extraction module, and the interactive module, configured to analyze whether the operation of the digital interactive learning model is qualified based on the degree of matching between the reply statement and the test reply statement, perform a secondary analysis on whether the operation of the digital interactive learning model is qualified based on the number of features extracted by the feature extraction module, and determine the type of interference intensity for the operation of the digital interactive learning model based on the number of associated features of the features in the test question statement;

[0059] A self-adjustment module is connected to the test verification module and is used to determine a processing method for the question test based on the interference intensity type determined by the test verification module, including:

[0060] The feature extraction method is judged to be unqualified.

[0061] Alternatively, it is determined that the test question statement is ambiguous, and the number of reply statements following the corresponding test question statement is increased based on non-matching keywords between the test reply statement and the reply statement.

[0062] Specifically, in this embodiment, there is no limitation on the specific structures of the model building module, the test question module, the feature extraction module, the interactive module, the test verification module, and the self-adjustment module, which can be composed of logical components including field programmable processors, computers, and microprocessors in computers.

[0063] See also Figure 2 As shown, it is a flow chart of the operation method of the digital interactive learning model.

[0064] The method for operating a digital interactive learning model provided by an embodiment of the present invention includes:

[0065] Build a digital learning model;

[0066] Inputting a test reply statement into the digital learning model to obtain a reply statement, and analyzing whether the operation of the digital interactive learning model is qualified based on the matching degree between the test reply statement and the characteristics of the reply statement;

[0067] Conducting a secondary analysis on whether the digital interactive learning model is qualified based on the number of features of the test question sentences;

[0068] Determining the interference intensity type for the operation of the digital interactive learning model based on the associated feature number of the features in the test question sentence, and judging that the feature extraction method is unqualified according to the interference intensity type,

[0069] Alternatively, it is determined that the test question statement is ambiguous, and the number of reply statements following the corresponding test question statement is increased based on non-matching keywords between the test reply statement and the reply statement.

[0070] Specifically, the test verification module is used to analyze whether the operation of the digital interactive learning model is qualified based on the matching degree between the reply statement and the test reply statement, wherein:

[0071] The matching degree is the ratio of the number of features that are the same between the response statement and the test response statement based on the test verification module to the total number of features in the test response statement.

[0072] See also Figure 3 As shown, it is a flow chart for analyzing whether the operation of the digital interactive learning model is qualified.

[0073] Specifically, the test verification module is used to analyze whether the operation of the digital interactive learning model is qualified based on the matching degree between the response statement and the test response statement, including:

[0074] If the matching degree is greater than or equal to the first preset matching degree standard threshold, the test verification module determines that the operation of the digital interactive learning model is qualified;

[0075] If the matching degree is less than the first preset matching degree standard threshold and greater than or equal to the second preset matching degree standard threshold, the test verification module determines whether the operation of the digital interactive learning model is qualified based on the number of features extracted by the feature extraction module and performs a secondary analysis;

[0076] If the matching degree is less than the second preset matching degree evaluation value, the test verification module determines that the operation of the digital interactive learning model is unqualified, and determines the interference intensity type for the operation of the digital interactive learning model based on the associated feature number of the features in the test question statement.

[0077] Specifically, in this embodiment, the matching degree is the ratio of the same features between the reply statement and the test reply statement, as well as the similar features (such as synonyms) to the total number of features of the test reply statement. The first preset matching degree standard threshold is selected between the interval [0.85, 0.95], and the second preset matching degree evaluation value is selected between the interval [0.65, 0.8].

[0078] Specifically, the test verification module performs a secondary analysis on whether the operation of the digital interactive learning model is qualified based on the characteristic quantity representation parameters, wherein:

[0079] The feature quantity characterization parameter is the ratio of the number of features extracted by the feature extraction module to the total number of features of the test question sentence.

[0080] See also Figure 4 As shown, it is a flow chart for determining whether the operation of the secondary analysis digital interactive learning model is qualified.

[0081] Specifically, the test verification module performs a secondary analysis on whether the operation of the digital interactive learning model is qualified based on the characteristic quantity representation parameters, including:

[0082] If the feature quantity characterization parameter is greater than or equal to the preset feature quantity characterization parameter standard threshold, the test verification module determines that the operation of the digital interactive learning model is qualified;

[0083] If the feature quantity representation parameter is less than the preset feature quantity representation parameter standard threshold, the test verification module determines that the operation of the digital interactive learning model is unqualified, and determines the interference intensity type for the operation of the digital interactive learning model based on the associated feature number of the features in the test question statement.

[0084] Specifically, in this embodiment, the preset characteristic quantity characterization parameter standard threshold is selected in the interval [0.65-0.75].

[0085] Specifically, the test verification module determines the interference intensity type for the operation of the digital interactive learning model based on the number of associated features of the features in the test question sentence, including:

[0086] If the correlation feature number is greater than or equal to the preset correlation feature number, the test verification module determines that the operation of the digital interactive model is a strong interference type;

[0087] If the number of associated features is less than the preset number of associated features, the test verification module determines that the operation of the digital interactive model is a weak interference type.

[0088] Specifically, in this embodiment, the number of associated features is the number of synonymous features of each feature in the test question sentence. The preset number of associated features is obtained in advance. Several test question sentences are obtained, the features in the test question sentences are extracted, the synonymous features of each feature are retrieved respectively, the number of synonymous features is counted, and the mean value of the number of synonymous features of each test question sentence is solved. The preset number of associated features is 0.8 to 0.9 times the mean value.

[0089] Specifically, the self-adjustment module determines a processing method for the question test based on the interference intensity type determined by the test verification module, including:

[0090] If the operation of the digital interactive model is of a strong interference type, the self-adjustment module determines that the extraction method of the features of the test question sentence is unqualified;

[0091] If the operation of the digital interactive model is of a strong interference type, the self-adjustment module determines that the feature of the test question sentence has ambiguity.

[0092] Specifically, the self-adjustment module increases the number of reply statements following the corresponding test question statement based on the non-matching keywords between the test reply statement and the reply statement, including:

[0093] Identify features in the test response sentences,

[0094] Identify features in the response sentence,

[0095] Features that are different between the test reply sentence and the reply sentence are determined as non-matching keywords.

[0096] Specifically, the self-adjustment module increases the number of reply statements following the corresponding test question statement based on non-matching keywords between the test reply statement and the reply statement, wherein:

[0097] The increase in the number of response sentences following the test question sentence is positively correlated with the number of non-matching keywords.

[0098] In this embodiment, optionally,

[0099] Compare the number of non-matching keywords with the first preset number standard threshold and the second preset number standard threshold,

[0100] If the number of non-matching keywords is less than or equal to the first preset number standard threshold, the number of first reply sentences is increased, and the number of first reply sentences is 0.2 times the number of initial reply sentences;

[0101] If the number of non-matching keywords is greater than the first preset number standard threshold and less than or equal to the second preset number standard threshold, then increase the number of second reply sentences, and the number of second reply sentences is 0.25 times the number of initial reply sentences;

[0102] If the number of non-matching keywords is greater than the second preset quantity standard threshold, the number of third reply statements is increased, and the number of third reply statements is 0.3 times the number of initial reply statements.

[0103] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0104] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that the present invention is susceptible to various modifications and variations. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A digital interactive learning model system, characterized in that: include: A model building module for building a digital interactive learning model based on the response data; A test question module, which is connected to the model building module and stores test question sentences and test answer sentences corresponding to the test question sentences, and is used to output the test question sentences; A feature extraction module, connected to the test question module, for extracting features from the test question sentence; an interactive module connected to the model building module and the feature extraction module, configured to input the features of the single test question sentence extracted by the feature extraction module into the digital interactive learning model and output a reply sentence of the digital interactive learning model; a test verification module connected to the test question module, the feature extraction module, and the interactive module, configured to analyze whether the operation of the digital interactive learning model is qualified based on the degree of matching between the reply statement and the test reply statement, perform a secondary analysis on whether the operation of the digital interactive learning model is qualified based on the number of features extracted by the feature extraction module, and determine the type of interference intensity for the operation of the digital interactive learning model based on the number of associated features of the features in the test question statement; A self-adjustment module is connected to the test verification module and is used to determine a processing method for the question test based on the interference intensity type determined by the test verification module, including: The feature extraction method is judged to be unqualified. Or, determining that the test question sentence has ambiguity, and increasing the number of reply sentences following the corresponding test question sentence based on non-matching keywords between the test reply sentence and the reply sentence; The test verification module performs a secondary analysis on whether the operation of the digital interactive learning model is qualified based on the characteristic quantity representation parameters, wherein: The feature quantity characterization parameter is the ratio of the number of features extracted by the feature extraction module to the total number of features of the test question sentence.

2. The digital interactive learning model system according to claim 1, characterized in that: The test verification module is used to analyze whether the operation of the digital interactive learning model is qualified based on the matching degree between the reply statement and the test reply statement, wherein: The matching degree is the ratio of the number of features that are the same between the response statement and the test response statement based on the test verification module to the total number of features in the test response statement.

3. The digital interactive learning model system according to claim 1, characterized in that: The test verification module is used to analyze whether the operation of the digital interactive learning model is qualified based on the matching degree between the response statement and the test response statement, including: The test verification module determines whether the operation of the digital interactive learning model is qualified; The test verification module determines whether the operation of the digital interactive learning model is qualified based on the number of features extracted by the feature extraction module, or, The test verification module determines that the operation of the digital interactive learning model is unqualified, and determines the interference intensity type for the operation of the digital interactive learning model based on the associated feature number of the features in the test question sentence.

4. The digital interactive learning model system according to claim 1, characterized in that: The test verification module performs a secondary analysis on whether the operation of the digital interactive learning model is qualified based on the characteristic quantity representation parameters, including: The test verification module determines whether the operation of the digital interactive learning model is qualified or unqualified, and determines the interference intensity type for the operation of the digital interactive learning model based on the associated feature number of the features in the test question sentence.

5. The digital interactive learning model system according to claim 1, characterized in that: The test verification module determines the interference intensity type for the operation of the digital interactive learning model based on the associated feature number of the features in the test question sentence, including: a strong interference type and a weak interference type.

6. The digital interactive learning model system according to claim 5, characterized in that: The self-adjustment module determines a processing method for the question test based on the interference intensity type determined by the test verification module, including: The self-adjusting module determines that the method for extracting the features of the test question sentence is unqualified, or determines that the features of the test question sentence are ambiguous.

7. The digital interactive learning model system according to claim 1, characterized in that: The self-adjusting module increases the number of reply statements following the corresponding test question statement based on non-matching keywords between the test reply statement and the reply statement, including: Identify features in the test response sentences, Identify features in the response sentence, Features that are different between the test reply sentence and the reply sentence are determined as non-matching keywords.

8. The digital interactive learning model system according to claim 1, characterized in that: The self-adjusting module increases the number of reply statements following the corresponding test question statement based on non-matching keywords between the test reply statement and the reply statement, wherein: The increase in the number of response sentences following the test question sentence is positively correlated with the number of non-matching keywords.

9. A method for operating a digital interactive learning model of the system according to any one of claims 1 to 8, characterized in that: include: Build a digital learning model; Inputting a test reply statement into the digital learning model to obtain a reply statement, and analyzing whether the operation of the digital interactive learning model is qualified based on the matching degree between the test reply statement and the characteristics of the reply statement; Conducting a secondary analysis on whether the digital interactive learning model is qualified based on the number of features of the test question sentences; Determining the interference intensity type for the operation of the digital interactive learning model based on the associated feature number of the features in the test question sentence, and judging that the feature extraction method is unqualified according to the interference intensity type, Alternatively, it is determined that the test question statement is ambiguous, and the number of reply statements following the corresponding test question statement is increased based on non-matching keywords between the test reply statement and the reply statement.

Images