Teaching effect testing method and system for intelligent teaching equipment

Abstract

The invention discloses an intelligent teaching equipment teaching effect test method, which comprises the following steps: S1, acquiring image data of intelligent teaching equipment, S2, inputting a vehicle running image into a pre-training convolutional neural network model, and acquiring an actual running track and a correct running track of a vehicle; s3, comparing the actual running track with the correct running track, and judging whether the vehicle can correctly enter the parking space or not; if not, taking the conclusion that the parking lot cannot be correctly entered as the content of the test report; if so, executing S4; s4, inputting the teaching image into the OCR model, and identifying teaching characters in the teaching image; s5, inputting the preprocessed teaching characters into the NLP model to obtain a detection report of the teaching characters; and S6, taking the conclusion that the user can correctly enter the storage location, the teaching characters and the detection report of the teaching characters as test report contents. The method is high in test efficiency and uniform in test standard.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and more particularly to a method and system for testing teaching effects of intelligent teaching equipment. Background Art

[0002] With the rapid development of information technology, intelligent teaching equipment is increasingly used in the field of driving education. These devices usually integrate various sensors and algorithms, and can provide a rich interactive experience. However, they also bring difficulties to the test tasks, and the difficulty requirements for the tests are getting higher and higher.

[0003] At present, the testing of the teaching effect of intelligent teaching equipment mostly adopts the method of manual evaluation, which not only has low testing efficiency but also has inconsistent testing standards.

[0004] Therefore, how to provide a method and system for testing the teaching effectiveness of intelligent teaching equipment, which not only has high testing efficiency but also has unified testing standards, is a problem that technical personnel in this field urgently need to solve. Summary of the invention

[0005] In view of this, an object of the present invention is to provide a method and system for testing teaching effectiveness of intelligent teaching equipment.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] A method for testing the teaching effect of an intelligent teaching device comprises the following steps:

[0008] S1: Acquire image data of an intelligent teaching device, wherein the image data includes a teaching image of the intelligent teaching device and a vehicle running image corresponding to the teaching image;

[0009] S2: Input the vehicle running image into the pre-trained convolutional neural network model to obtain the actual running trajectory and correct running trajectory of the vehicle;

[0010] S3: Compare the actual running trajectory with the correct running trajectory to determine whether the vehicle can enter the storage location correctly; if not, the conclusion that the vehicle cannot enter the storage location correctly is included in the test report; if yes, execute S4;

[0011] S4: input the teaching image into the OCR model to recognize the teaching text in the teaching image;

[0012] S5: input the preprocessed teaching text into the NLP model to obtain a detection report of the teaching text;

[0013] S6: The conclusion of being able to correctly enter the storage location, the teaching text, and the test report of the teaching text are used as the test report content.

[0014] Preferably, the pre-trained convolutional neural network model is obtained based on the following steps:

[0015] Acquire image data of the intelligent teaching device under different teaching scenarios and different teaching methods as an initial data set; wherein the image data includes a teaching image of the intelligent teaching device and a vehicle running image corresponding to the teaching image;

[0016] Performing data enhancement on the initial data set to obtain an enhanced data set; wherein the data enhancement method includes rotation, scaling and brightness adjustment;

[0017] Dividing the enhanced dataset into a training set, a validation set, and a test set;

[0018] Using the training set to train the convolutional neural network model;

[0019] Using the validation set to validate the trained convolutional neural network model, and then adjusting the parameters of the convolutional neural network model based on the validation results;

[0020] The test set is used to evaluate the convolutional neural network model after parameter adjustment to obtain the pre-trained convolutional neural network model.

[0021] Preferably, the above method further includes S7: displaying the test report content of S3 or S6 on a visualization tool.

[0022] Preferably, the preprocessing in S5 includes removing noise from the teaching text and standardizing the format of the teaching text.

[0023] Preferably, the NLP model is used to perform grammar detection and spelling correction to obtain grammatical problems, spelling problems and spelling correction suggestions in the teaching text.

[0024] A teaching effect testing system for intelligent teaching equipment, comprising a data acquisition unit, a pre-trained convolutional neural network model, a trajectory comparison unit, an OCR model, an NLP model, and a test report acquisition unit;

[0025] The data acquisition unit is used to acquire image data of the intelligent teaching device, wherein the image data includes a teaching image of the intelligent teaching device and a vehicle running image corresponding to the teaching image;

[0026] The pre-trained convolutional neural network model is used to extract the actual running trajectory and the correct running trajectory of the vehicle in the vehicle running image;

[0027] The trajectory comparison unit is used to compare the actual running trajectory with the correct running trajectory to determine whether the vehicle can enter the storage location correctly;

[0028] The OCR model is used to recognize the teaching text in the teaching image;

[0029] The NLP model is used to obtain a detection report of the preprocessed teaching text;

[0030] The test report acquisition unit is used to obtain the test report content of the intelligent teaching device; specifically, if the vehicle can enter the storage location correctly, the test report content includes: the conclusion that it can enter the storage location correctly, the teaching text, and the inspection report of the teaching text; if the vehicle cannot enter the storage location correctly, the test report content includes: the conclusion that it cannot enter the storage location correctly.

[0031] Preferably, the above system further comprises a pre-trained convolutional neural network model acquisition unit;

[0032] The pre-trained convolutional neural network model acquisition unit includes a data set acquisition unit, a data enhancement unit, a data set division unit, a training unit, a parameter adjustment unit and a testing unit;

[0033] The data set acquisition unit is used to acquire an initial data set, and the initial data set includes image data of the intelligent teaching device under different teaching scenarios and different teaching methods; wherein the image data includes a teaching image of the intelligent teaching device and a vehicle running image corresponding to the teaching image;

[0034] The data enhancement unit is used to perform data enhancement on the initial data set to obtain an enhanced data set; wherein the data enhancement method includes rotation, scaling and brightness adjustment;

[0035] The data set division unit is used to divide the enhanced data set into a training set, a validation set and a test set;

[0036] The training unit is used to train the convolutional neural network model using the training set;

[0037] The parameter adjustment unit is used to verify the trained convolutional neural network model using the verification set, and then adjust the parameters of the convolutional neural network model based on the verification result;

[0038] The testing unit is used to evaluate the convolutional neural network model after parameter adjustment using the test set to obtain a pre-trained convolutional neural network model.

[0039] Preferably, the above system further comprises a visual display unit;

[0040] The visualization display unit is used to display the test report content on a visualization tool.

[0041] Preferably, the above system further comprises a pre-processing unit;

[0042] The preprocessing unit is used to remove noise in the teaching text and standardize the format of the teaching text.

[0043] Preferably, the NLP model includes a grammar detection unit and a spelling correction unit;

[0044] The grammar detection unit is used to detect grammatical errors in the teaching text and obtain grammatical problems existing in the teaching text;

[0045] The spelling correction unit is used to detect spelling errors in the teaching text and obtain spelling problems and spelling correction suggestions existing in the teaching text.

[0046] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a method and system for testing the teaching effect of an intelligent teaching device, which not only has high testing efficiency but also has unified testing standards. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] 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 embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0048] Figure 1 The present invention provides a flow chart of a method for testing the teaching effect of an intelligent teaching device. DETAILED DESCRIPTION

[0049] 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.

[0050] The embodiment of the present invention discloses a method for testing the teaching effect of an intelligent teaching device, comprising the following steps:

[0051] S1: Acquire image data of an intelligent teaching device, wherein the image data includes a teaching image of the intelligent teaching device and a vehicle running image corresponding to the teaching image;

[0052] S2: Input the vehicle running image into the pre-trained convolutional neural network model to obtain the actual running trajectory and correct running trajectory of the vehicle;

[0053] S3: Compare the actual running trajectory with the correct running trajectory to determine whether the vehicle can enter the storage location correctly; if not, the conclusion that the vehicle cannot enter the storage location correctly is included in the test report, and S7 is executed; if yes, S4 is executed;

[0054] S4: input the teaching image into the OCR model to recognize the teaching text in the teaching image;

[0055] S5: input the preprocessed teaching text into the NLP model to obtain a detection report of the teaching text;

[0056] Furthermore, the preprocessing includes removing noise from the teaching text and standardizing the format of the teaching text.

[0057] Furthermore, the NLP model is used to perform grammar detection and spelling correction to obtain grammatical problems, spelling problems and spelling correction suggestions in the teaching text.

[0058] S6: The conclusion that the storage location can be correctly entered, the teaching text, and the test report of the teaching text are used as the test report content;

[0059] S7: Display the test report content on the visualization tool.

[0060] Furthermore, the pre-trained convolutional neural network model is obtained based on the following steps:

[0061] Acquire image data of the intelligent teaching device under different teaching scenarios and different teaching methods as an initial data set; wherein the image data includes a teaching image of the intelligent teaching device and a vehicle running image corresponding to the teaching image;

[0062] Performing data enhancement on the initial data set to obtain an enhanced data set; wherein the data enhancement method includes rotation, scaling and brightness adjustment;

[0063] Dividing the enhanced dataset into a training set, a validation set, and a test set;

[0064] Using the training set to train the convolutional neural network model;

[0065] Using the validation set to validate the trained convolutional neural network model, and then adjusting the parameters of the convolutional neural network model based on the validation results;

[0066] It can be understood that: the parameters include the weight and bias of the convolution kernel, the weight and bias of the output layer;

[0067] The test set is used to evaluate the convolutional neural network model after parameter adjustment to obtain the pre-trained convolutional neural network model.

[0068] It is understandable that:

[0069] The present invention deploys the pre-trained convolutional neural network model, OCR model, and NLP model in a suitable environment (such as a cloud server, an edge device, etc.) to obtain a test system; and regularly performs an overall evaluation on the pre-trained convolutional neural network model, OCR model, and NLP model, wherein the evaluation content includes vehicle trajectory detection accuracy, OCR recognition accuracy, and NLP processing effect; and according to the evaluation results, adjusts the parameters of the pre-trained convolutional neural network model, replaces the OCR model with higher recognition accuracy and the NLP model with better processing effect, so as to obtain a test system with higher vehicle trajectory detection accuracy, higher OCR recognition accuracy, and better NLP processing effect.

[0070] The present invention inputs the image data of the intelligent teaching device to be tested into the test system, and then obtains the test result (i.e. the test report content) of the current teaching content of the intelligent teaching device;

[0071] The teaching content is adjusted according to the test results, and then the image data corresponding to the adjusted teaching content is input into the test system, and this cycle is repeated until a test report without any problems is obtained.

[0072] A teaching effect testing system for intelligent teaching equipment, comprising a data acquisition unit, a pre-trained convolutional neural network model, a trajectory comparison unit, an OCR model, an NLP model, and a test report acquisition unit;

[0073] The data acquisition unit is used to acquire image data of the intelligent teaching device, wherein the image data includes a teaching image of the intelligent teaching device and a vehicle running image corresponding to the teaching image;

[0074] The pre-trained convolutional neural network model is used to extract the actual running trajectory and the correct running trajectory of the vehicle in the vehicle running image;

[0075] The trajectory comparison unit is used to compare the actual running trajectory with the correct running trajectory to determine whether the vehicle can enter the storage location correctly;

[0076] The OCR model is used to recognize the teaching text in the teaching image;

[0077] The NLP model is used to obtain a detection report of the preprocessed teaching text;

[0078] The test report acquisition unit is used to obtain the test report content of the intelligent teaching device; specifically, if the vehicle can enter the storage location correctly, the test report content includes: the conclusion that it can enter the storage location correctly, the teaching text, and the inspection report of the teaching text; if the vehicle cannot enter the storage location correctly, the test report content includes: the conclusion that it cannot enter the storage location correctly.

[0079] Furthermore, the above system also includes a pre-trained convolutional neural network model acquisition unit;

[0080] The pre-trained convolutional neural network model acquisition unit includes a data set acquisition unit, a data enhancement unit, a data set division unit, a training unit, a parameter adjustment unit and a testing unit;

[0081] The data set acquisition unit is used to acquire an initial data set, and the initial data set includes image data of the intelligent teaching device under different teaching scenarios and different teaching methods; wherein the image data includes a teaching image of the intelligent teaching device and a vehicle running image corresponding to the teaching image;

[0082] The data enhancement unit is used to perform data enhancement on the initial data set to obtain an enhanced data set; wherein the data enhancement method includes rotation, scaling and brightness adjustment;

[0083] The data set division unit is used to divide the enhanced data set into a training set, a validation set and a test set;

[0084] The training unit is used to train the convolutional neural network model using the training set;

[0085] The parameter adjustment unit is used to verify the trained convolutional neural network model using the verification set, and then adjust the parameters of the convolutional neural network model based on the verification result;

[0086] It can be understood that: the parameters include the weights and biases of the convolution kernel, the weights and biases of the output layer;

[0087] The testing unit is used to evaluate the convolutional neural network model after parameter adjustment using the test set to obtain a pre-trained convolutional neural network model.

[0088] Furthermore, the above system also includes a visual display unit;

[0089] The visualization display unit is used to display the test report content on a visualization tool.

[0090] Furthermore, the above system also includes a pre-processing unit;

[0091] The preprocessing unit is used to remove noise in the teaching text and standardize the format of the teaching text.

[0092] Further, the NLP model includes a grammar detection unit and a spelling correction unit;

[0093] The grammar detection unit is used to detect grammatical errors in the teaching text and obtain grammatical problems existing in the teaching text;

[0094] The spelling correction unit is used to detect spelling errors in the teaching text and obtain spelling problems and spelling correction suggestions existing in the teaching text.

[0095] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0096] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for testing the teaching effect of an intelligent teaching device, characterized in that: The following steps are involved: S1: Acquire image data of an intelligent teaching device, wherein the image data includes a teaching image of the intelligent teaching device and a vehicle running image corresponding to the teaching image; S2: Input the vehicle running image into the pre-trained convolutional neural network model to obtain the actual running trajectory and correct running trajectory of the vehicle; S3: Compare the actual running trajectory with the correct running trajectory to determine whether the vehicle can correctly enter the storage location; if not, the conclusion that the vehicle cannot correctly enter the storage location is included in the test report; If yes, execute S4; S4: input the teaching image into the OCR model to recognize the teaching text in the teaching image; S5: input the preprocessed teaching text into the NLP model to obtain a detection report of the teaching text; S6: The conclusion of being able to correctly enter the storage location, the teaching text, and the test report of the teaching text are used as the test report content.

2. The teaching effect testing method of an intelligent teaching device according to claim 1, characterized in that: The pre-trained convolutional neural network model is obtained based on the following steps: Acquire image data of the intelligent teaching device under different teaching scenarios and different teaching methods as an initial data set; wherein the image data includes a teaching image of the intelligent teaching device and a vehicle running image corresponding to the teaching image; Performing data enhancement on the initial data set to obtain an enhanced data set; wherein the data enhancement method includes rotation, scaling and brightness adjustment; Dividing the enhanced dataset into a training set, a validation set, and a test set; Using the training set to train the convolutional neural network model; Using the validation set to validate the trained convolutional neural network model, and then adjusting the parameters of the convolutional neural network model based on the validation results; The test set is used to evaluate the convolutional neural network model after parameter adjustment to obtain the pre-trained convolutional neural network model.

3. The teaching effect testing method of an intelligent teaching device according to claim 1 is characterized in that: Also includes S7: Display the test report content of S3 or S6 on the visualization tool.

4. The teaching effect testing method of an intelligent teaching device according to claim 1, characterized in that: The preprocessing in S5 includes removing noise from the teaching text and normalizing the format of the teaching text.

5. The teaching effect testing method of an intelligent teaching device according to claim 1, characterized in that: The NLP model is used to perform grammar detection and spelling correction to obtain grammatical problems, spelling problems and spelling correction opinions in the teaching text.

6. A teaching effect testing system for intelligent teaching equipment, characterized in that: It includes data acquisition unit, pre-trained convolutional neural network model, trajectory comparison unit, OCR model, NLP model, and test report acquisition unit; The data acquisition unit is used to acquire image data of the intelligent teaching device, wherein the image data includes a teaching image of the intelligent teaching device and a vehicle running image corresponding to the teaching image; The pre-trained convolutional neural network model is used to extract the actual running trajectory and the correct running trajectory of the vehicle in the vehicle running image; The trajectory comparison unit is used to compare the actual running trajectory with the correct running trajectory to determine whether the vehicle can enter the storage location correctly; The OCR model is used to recognize the teaching text in the teaching image; The NLP model is used to obtain a detection report of the preprocessed teaching text; The test report acquisition unit is used to obtain the test report content of the intelligent teaching device; specifically, if the vehicle can enter the storage location correctly, the test report content includes: the conclusion that it can enter the storage location correctly, the teaching text, and the inspection report of the teaching text; if the vehicle cannot enter the storage location correctly, the test report content includes: the conclusion that it cannot enter the storage location correctly.

7. The intelligent teaching equipment teaching effect testing system according to claim 6 is characterized in that: It also includes a pre-trained convolutional neural network model acquisition unit; The pre-trained convolutional neural network model acquisition unit includes a data set acquisition unit, a data enhancement unit, a data set division unit, a training unit, a parameter adjustment unit and a testing unit; The data set acquisition unit is used to acquire an initial data set, and the initial data set includes image data of the intelligent teaching device under different teaching scenarios and different teaching methods; wherein the image data includes a teaching image of the intelligent teaching device and a vehicle running image corresponding to the teaching image; The data enhancement unit is used to perform data enhancement on the initial data set to obtain an enhanced data set; wherein the data enhancement method includes rotation, scaling and brightness adjustment; The data set division unit is used to divide the enhanced data set into a training set, a validation set and a test set; The training unit is used to train the convolutional neural network model using the training set; The parameter adjustment unit is used to verify the trained convolutional neural network model using the verification set, and then adjust the parameters of the convolutional neural network model based on the verification result; The testing unit is used to evaluate the convolutional neural network model after parameter adjustment using the test set to obtain a pre-trained convolutional neural network model.

8. The intelligent teaching equipment teaching effect testing system according to claim 6 is characterized in that: It also includes a visual display unit; The visualization display unit is used to display the test report content on a visualization tool.

9. The intelligent teaching equipment teaching effect testing system according to claim 6, characterized in that: Also includes a pre-processing unit; The preprocessing unit is used to remove noise in the teaching text and standardize the format of the teaching text.

10. The intelligent teaching equipment teaching effect testing system according to claim 6, characterized in that: The NLP model includes a grammar detection unit and a spelling correction unit; The grammar detection unit is used to detect grammatical errors in the teaching text and obtain grammatical problems existing in the teaching text; The spelling correction unit is used to detect spelling errors in the teaching text and obtain spelling problems and spelling correction suggestions existing in the teaching text.

Images