A method for monitoring ideological and political education based on semantic analysis

Abstract

The present invention discloses a ideological and political education monitoring method based on semantic analysis, belonging to the technical field of semantic processing. First, the present invention extracts the ideological and political education video text and divides it into sequences, and records the corresponding speech; then it counts the word frequencies to construct a frequency set, calculates the sound-word following value according to the frequency and the speech amplitude fluctuation value and forms a sequence; then it screens abnormal and normal pairs of word groups, calculates the sequence feature adjustment coefficient; finally, it inputs the sound-word following sequence into an evaluation model, performs feature adjustment and initial score optimization based on the adjustment coefficient, and obtains the ideological and political education quality score.

Description

Technical Field

[0001] The present invention relates to the technical field of semantic processing, and in particular to a method for monitoring ideological and political education based on semantic analysis. Background Art

[0002] With the rapid development of information technology, online education and video teaching have gradually become important forms of ideological and political education. However, how to effectively monitor and evaluate the teaching quality of ideological and political education videos. The existing monitoring technologies for ideological and political education mainly rely on traditional questionnaire surveys and classroom observations. These methods are often highly subjective and inefficient, and it is difficult to comprehensively reflect the real learning status of students. In addition, when analyzing video content, existing technologies usually only focus on a single dimension of text or speech, and fail to fully utilize the correlation between text and speech for comprehensive evaluation. This results in a lack of accuracy in the evaluation of the quality of ideological and political education. Summary of the Invention

[0003] In view of the above deficiencies in the prior art, the method for monitoring ideological and political education based on semantic analysis provided by the present invention solves the problem of low accuracy in the evaluation of the quality of ideological and political education existing in the prior art.

[0004] In order to achieve the above invention purpose, the technical solution adopted by the present invention is: A method for monitoring ideological and political education based on semantic analysis, comprising the following steps:

[0005] S1. Extract the text in the ideological and political education video, divide the text into text sequences by sentence, and record the speech of the read text sequences to obtain a speech set;

[0006] S2. Count the frequency of each word in the text sequences in the ideological and political education text set to construct a frequency set;

[0007] S3. Calculate a sound-word following value according to the fluctuation value of the frequency in the frequency set and the fluctuation value of the amplitude in the speech set, and construct a sound-word following sequence;

[0008] S4. According to the sound-word following values in the sound-word following sequence, screen out abnormal pairs of word groups and normal pairs of word groups, and calculate a sequence feature adjustment coefficient;

[0009] S5. Input the sound-word following sequence corresponding to the ideological and political education video into an ideological and political education quality evaluation model, perform feature adjustment based on the sequence feature adjustment coefficient, and optimize the initial score based on the change of the sequence feature adjustment coefficient over time to obtain an ideological and political education quality score.

[0010] Further, S3 includes the following sub-steps:

[0011] S31. Subtract the frequency of the \(i\)-th word in the frequency set from the frequency of the \((i + 1)\)-th word to obtain the \(i\)-th frequency fluctuation value, where \(i\) is the serial number.

[0012] S32. Divide each frequency fluctuation value by the maximum frequency fluctuation value to obtain the normalized frequency fluctuation value.

[0013] S33. Extract the speech segments corresponding to each word in the speech set, and extract the amplitude mean value for each speech segment.

[0014] S34. Subtract the amplitude mean value of the \(i\)-th word from the amplitude mean value of the \((i + 1)\)-th word to obtain the \(i\)-th amplitude fluctuation value.

[0015] S35. Divide the \(i\)-th amplitude fluctuation value by the maximum amplitude fluctuation value to obtain the normalized amplitude fluctuation value.

[0016] S36. Calculate the sound-word following value according to the normalized frequency fluctuation value and the normalized amplitude fluctuation value with the same serial number.

[0017] S37. Arrange the respective sound-word following values in sequence to construct a sound-word following sequence.

[0018] Further, S36 includes the following sub-steps:

[0019] S361. Calculate the difference coefficient according to the normalized frequency fluctuation value and the normalized amplitude fluctuation value with the same serial number.

[0020] S362. Calculate the direction coefficient according to the normalized frequency fluctuation value and the normalized amplitude fluctuation value with the same serial number.

[0021] S363. Multiply the direction coefficient by the difference coefficient to obtain the sound-word following value.

[0022] Further, the formula for calculating the difference coefficient in S361 is: , where \(\epsilon\) i is the \(i\)-th difference coefficient, \(F\) f,i is the \(i\)-th normalized frequency fluctuation value, \(F\) a,i is the \(i\)-th normalized amplitude fluctuation value, and \(|\ |\) is the absolute value operation;

[0023] The process of calculating the direction coefficient in S362 is specifically as follows: when both \(F\) f,i and \(F\) a,i are greater than 0 or both are less than 0, assign the value 1 to the direction coefficient; when one of \(F\) f,i and \(F\) a,i is negative and the other is positive, assign the value -1 to the direction coefficient.

[0024] Further, S4 includes the following sub-steps:

[0025] S41. Select two words corresponding to the phonetic-word following values greater than 0 in the phonetic-word following sequence to form a normal pair phrase group;

[0026] S42. Select two words corresponding to the phonetic-word following values less than 0 in the phonetic-word following sequence to form an abnormal pair phrase group;

[0027] S43. Search for the paragraphs in which the normal pair phrase groups appear in combination in the ideological and political education text collection, and count the frequency of combined appearance and the paragraph space ratio;

[0028] S44. Search for the paragraphs in which the abnormal pair phrase groups appear in combination in the ideological and political education text collection, and count the frequency of combined appearance and the paragraph space ratio;

[0029] S45. Calculate the ideological and political value indexes of the normal pair phrase groups and the abnormal pair phrase groups respectively according to the frequency of combined appearance and the paragraph space ratio;

[0030] S46. Calculate the sequence feature adjustment coefficient according to the ideological and political value indexes of the normal pair phrase groups and the abnormal pair phrase groups, and the corresponding phonetic-word following values in the phonetic-word following sequence.

[0031] Furthermore, the formula for calculating the ideological and political value index of the normal pair phrase group in S45 is: , where γ no,n is the ideological and political value index of the nth normal pair phrase group, f no,n,m is the frequency of the nth normal pair phrase group appearing in the mth paragraph, P no,n,m is the ratio of the mth paragraph in which the nth normal pair phrase group appears to the paragraph space of the ideological and political education text collection, N no,n is the number of paragraphs in which the nth normal pair phrase group appears, e is the natural constant, and m and n are positive integers;

[0032] The formula for calculating the ideological and political value index of the abnormal pair phrase group in S45 is: , where γ ab,n is the ideological and political value index of the nth abnormal pair phrase group, f ab,n,m is the frequency of the nth abnormal pair phrase group appearing in the mth paragraph, P ab,n,m is the ratio of the mth paragraph in which the nth abnormal pair phrase group appears to the paragraph space of the ideological and political education text collection, N ab,n is the number of paragraphs in which the nth abnormal pair phrase group appears.

[0033] Furthermore, S46 includes the following sub-steps:

[0034] S461. Calculate the normal estimate according to the ideological and political value index of the normal pair phrase group and the corresponding phonetic-word following value in the phonetic-word following sequence;

[0035] S462. Calculate the anomaly estimate value based on the ideological and political value index of the phrase pair for the anomaly and the corresponding phonetic word following value in the phonetic word following sequence;

[0036] S463. Add the normal estimate value and the normal estimate value to obtain the sequence feature adjustment coefficient.

[0037] Furthermore, the formula for calculating the normal estimate value in S461 is: , where P no is the normal estimate value, γ no,n is the ideological and political value index of the nth normal phrase pair, μ n is the phonetic word following value corresponding to the nth normal phrase pair, M no is the number of normal phrase pairs, and n is a positive integer;

[0038] The formula for calculating the anomaly estimate value in S462 is: , where P ab is the anomaly estimate value, γ ab,k is the ideological and political value index of the kth abnormal phrase pair, μ k is the phonetic word following value corresponding to the kth abnormal phrase pair, M ab is the number of abnormal phrase pairs, and k is a positive integer.

[0039] Furthermore, the ideological and political education quality assessment model in S5 includes: multiple feature extraction modules, an adder, and a scoring optimization layer;

[0040] Each feature extraction module is used to process a phonetic word following sequence and perform sequence feature adjustment based on the sequence feature adjustment coefficient to obtain a sequence adjustment feature value;

[0041] The adder is used to add up the respective sequence adjustment feature values to obtain an initial score;

[0042] The scoring optimization layer is used to optimize the initial score according to the temporal changes of the respective sequence feature adjustment coefficients to obtain the ideological and political education quality score.

[0043] Furthermore, each feature extraction module includes a BiLSTM layer, a fully connected layer, and a sequence feature adjustment layer connected in sequence;

[0044] The expression of the sequence feature adjustment layer is: , where H is the sequence adjustment feature value output by the sequence feature adjustment layer, h is the sequence feature value output by the fully connected layer, tanh is the hyperbolic tangent function, and φ is the sequence feature adjustment coefficient;

[0045] The expression of the scoring optimization layer is: , where S is the ideological and political education quality score output by the scoring optimization layer, S in is the initial score, φA is the mean value of the sequence feature adjustment coefficients for the second half of the time period, and φ B is the mean value of the sequence feature adjustment coefficients for the first half of the time period, and D is the normalization parameter.

[0046] The beneficial effects of the present invention are as follows:

[0047] 1. By extracting the text in the ideological and political education video and dividing it into text sequences, and simultaneously recording the corresponding voices to obtain a voice set, the present invention collects data from two dimensions of text and voice, changes the limitation of only focusing on a single dimension in the past, and can obtain more comprehensive information related to the ideological and political education process.

[0048] 2. The present invention calculates the word-voice following value based on the fluctuation values of the frequency set and the voice set and constructs a word-voice following sequence, making full use of the correlation between text and voice. Since the word-voice following situation can reflect the key content of education and the emphasis in voice, when teachers explain key knowledge, they will emphasize it through the weight of voice. By analyzing the word-voice following sequence, these key contents and the emphasis points in the teacher's voice can be clearly identified, so as to better understand the teaching process and provide a key basis for the evaluation of teaching effects.

[0049] 3. The present invention screens out abnormal pair phrases and normal pair phrases based on the word-voice following sequence and calculates the sequence feature adjustment coefficient, which can quantify the abnormal and normal states in the teaching process.

[0050] 4. The present invention inputs the word-voice following sequence into the ideological and political education quality evaluation model, combines the sequence feature adjustment coefficient for feature adjustment and initial score optimization, and comprehensively considers the ideological and political education quality from multiple angles. By dynamically adjusting features and optimizing scores, the present invention overcomes the disadvantages of strong subjectivity and low efficiency of traditional evaluation methods, making the final ideological and political education quality score better reflect the actual teaching effect and improving the evaluation accuracy of ideological and political education quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a flowchart of an ideological and political education monitoring method based on semantic analysis;

[0052] Figure 2 is a structural schematic diagram of an ideological and political education quality evaluation model. DETAILED DESCRIPTION OF THE INVENTION

[0053] The following describes the specific embodiments of the present invention to facilitate those skilled in the art of the present technology to understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific embodiments. For those of ordinary skill in the art of the present technology, as long as various changes are within the spirit and scope of the present invention defined and determined by the appended claims, these changes are obvious, and all inventions and creations using the concept of the present invention are within the scope of protection.

[0054] As Figure 1 shown, a method for monitoring ideological and political education based on semantic analysis includes the following steps:

[0055] S1. Extract the text in the ideological and political education video, divide the text into text sequences by sentence, and record the voices reading the text sequences to obtain a voice set;

[0056] S2. Count the frequencies of each word in the text sequences in the ideological and political education text set to construct a frequency set;

[0057] S3. Calculate the word-voice following value according to the fluctuation value of the frequencies in the frequency set and the fluctuation value of the amplitudes in the voice set, and construct a word-voice following sequence;

[0058] S4. According to the word-voice following values in the word-voice following sequence, screen out abnormal pair phrases and normal pair phrases, and calculate the sequence feature adjustment coefficient;

[0059] S5. Input the word-voice following sequence corresponding to the ideological and political education video into the ideological and political education quality evaluation model, perform feature adjustment based on the sequence feature adjustment coefficient, and optimize the initial score based on the change of the sequence feature adjustment coefficient over time to obtain the ideological and political education quality score.

[0060] In the present invention, each word in the text sequence in S2 refers to the word after removing the conjunctions. For example, for the sentence "Vocational education aims to cultivate professional and technical talents who meet the social needs", after removing the conjunctions "aims to", "who", and "meet", the words in the text sequence include: vocational education, cultivate, social needs, professional and technical talents.

[0061] In this embodiment, S3 is specifically as follows: First, subtract the frequency of the (i + 1)-th word from the frequency of the i-th word in the frequency set to obtain the i-th frequency fluctuation value, where i is the number; then divide each frequency fluctuation value by the maximum frequency fluctuation value to complete normalization. Next, extract the amplitude mean of the voice segments corresponding to each word in the voice set, subtract the amplitude mean of the adjacent words to obtain the amplitude fluctuation value and divide it by the maximum amplitude fluctuation value for normalization. Then, calculate the word-voice following value from the normalized frequency fluctuation value and the normalized amplitude fluctuation value, and arrange the word-voice following values in sequence to construct the word-voice following sequence.

[0062] In this embodiment, S3 includes the following sub-steps:

[0063] S31. Subtract the frequency of the (i + 1)-th word from the frequency of the i-th word in the frequency set to obtain the i-th frequency fluctuation value, where i is the number;

[0064] S32. Divide each frequency fluctuation value by the maximum frequency fluctuation value to obtain the normalized frequency fluctuation value;

[0065] S33. Extract the speech segments corresponding to each word in the speech set, and extract the amplitude mean value for each speech segment;

[0066] S34. Subtract the amplitude mean value of the i-th word from the amplitude mean value of the (i + 1)-th word to obtain the i-th amplitude fluctuation value;

[0067] S35. Divide the i-th amplitude fluctuation value by the maximum amplitude fluctuation value to obtain the normalized amplitude fluctuation value;

[0068] S36. Calculate the phoneme-word following value according to the normalized frequency fluctuation value and the normalized amplitude fluctuation value with the same number;

[0069] S37. Arrange the phoneme-word following values in sequence to construct a phoneme-word following sequence.

[0070] In the text analysis of the present invention, by calculating the frequency fluctuation value, the change of the word frequency in the ideological and political education text can be intuitively displayed, which helps to identify the key turning points and core content of the content. In terms of speech analysis, extracting the amplitude mean value of the speech segment and calculating the fluctuation value can reflect the change of the speech intensity of the teacher during the teaching process, which is usually related to the emphasized content. The normalization process enables the speech data and the text data to be analyzed on the same scale. The present invention calculates the phoneme-word following value to closely associate the text and the speech. When the phoneme-word following value is large, it means that the teacher's speech emphasis highly coincides with the text key points, and the teaching effect is good. Finally, the constructed phoneme-word following sequence records the dynamic change of this phoneme-word relationship during the teaching process.

[0071] In this embodiment, the first implementation manner of S36 is specifically as follows: take the absolute value of the difference between the normalized frequency fluctuation value and the amplitude fluctuation value, and take the reciprocal of the absolute value to obtain the difference coefficient. When the normalized frequency fluctuation value and the amplitude fluctuation value are both positive or negative, the direction coefficient is assigned 1. When the normalized frequency fluctuation value and the amplitude fluctuation value are one positive and one negative, the direction coefficient is assigned -1. Multiply the difference coefficient and the direction coefficient to obtain the phoneme-word following value.

[0072] More preferably, the second implementation manner of S36 is specifically as follows: calculate the difference coefficient according to the normalized frequency fluctuation value and the amplitude fluctuation value; then calculate the direction coefficient according to the positive and negative of the two; finally, multiply the two to obtain the phoneme-word following value.

[0073] The second implementation manner specifically includes the following sub-steps:

[0074] S361. Calculate the difference coefficient according to the normalized frequency fluctuation value and the normalized amplitude fluctuation value with the same number;

[0075] S362. Calculate the direction coefficient according to the normalized frequency fluctuation value and the normalized amplitude fluctuation value with the same number;

[0076] S363. Multiply the direction coefficient by the difference coefficient to obtain the phoneme-word following value.

[0077] In this embodiment, the formula for calculating the difference coefficient in S361 is: , where ε i is the i-th difference coefficient, F f,i is the i-th normalized frequency fluctuation value, F a,i is the i-th normalized amplitude fluctuation value, and | | represents the absolute value operation;

[0078] The process of calculating the direction coefficient in S362 is specifically as follows: When both F f,i and F a,i are greater than 0 or both are less than 0, assign the value 1 to the direction coefficient; When one of F f,i and F a,i is negative and the other is positive, assign the value -1 to the direction coefficient.

[0079] By calculating the difference coefficient, the present invention can accurately quantify the degree of difference between the two; When calculating the direction coefficient, the value is assigned according to the positive and negative relationship between the two, which carefully depicts the association of their change directions.

[0080] In this embodiment, S4 is specifically as follows: According to the positive and negative of the values in the phoneme-word following sequence, the corresponding words are respectively screened into normal pair phrases and abnormal pair phrases; Then search for the paragraphs in which the two types of phrases appear in combination in the ideological and political education text set, and count their appearance frequencies and paragraph length ratios; Calculate the ideological and political value indices of the normal pair phrases and the abnormal pair phrases respectively; Finally, combine the ideological and political value index with the phoneme-word following value to calculate the sequence feature adjustment coefficient.

[0081] S4 includes the following sub-steps:

[0082] S41. Screen two words corresponding to the phoneme-word following values greater than 0 in the phoneme-word following sequence to form normal pair phrases;

[0083] S42. Screen two words corresponding to the phoneme-word following values less than 0 in the phoneme-word following sequence to form abnormal pair phrases;

[0084] S43. Search for the paragraphs in which the normal pair phrases appear in combination in the ideological and political education text set, and count the frequency of combined appearance and the paragraph length ratio;

[0085] S44. Search for the paragraphs in which the abnormal pair phrases appear in combination in the ideological and political education text set, and count the frequency of combined appearance and the paragraph length ratio;

[0086] S45. Calculate the ideological and political value indices of the normal pair phrases and the abnormal pair phrases respectively according to the frequency of combined appearance and the paragraph length ratio;

[0087] S46. Calculate the sequence feature adjustment coefficient based on the ideological and political value indices of normal and abnormal phrase pairs, and the corresponding phoneme following values in the phoneme following sequence.

[0088] In the present invention, "combination" means that two words in a normal phrase pair or an abnormal phrase pair appear simultaneously in a sentence of the ideological and political education text set.

[0089] According to the sub-steps of step S3, the i-th phoneme following value corresponds to the i-th word and the (i + 1)-th word. Therefore, in the present invention, by screening the positive and negative of the phoneme following values, the phrase pairs are divided into normal phrase pairs and abnormal phrase pairs, which can effectively distinguish the parts of the ideological and political education where the voice and text match well and poorly. By counting the frequency of occurrence of the phrase pairs in the text set and the ratio of the paragraph length, the ideological and political value index is calculated, realizing the quantitative evaluation of the importance and influence of different phrase pairs in ideological and political education.

[0090] In this embodiment, the formula for calculating the ideological and political value index of the normal phrase pair in S45 is: , where γ no,n is the ideological and political value index of the n-th normal phrase pair, f no,n,m is the frequency of occurrence of the combination of the n-th normal phrase pair in the m-th paragraph, P no,n,m is the ratio of the length of the m-th paragraph in which the combination of the n-th normal phrase pair appears to the total length of the paragraphs in the ideological and political education text set, N no,n is the number of paragraphs in which the combination of the n-th normal phrase pair appears, e is the natural constant, and m and n are positive integers;

[0091] The formula for calculating the ideological and political value index of the abnormal phrase pair in S45 is: , where γ ab,n is the ideological and political value index of the n-th abnormal phrase pair, f ab,n,m is the frequency of occurrence of the combination of the n-th abnormal phrase pair in the m-th paragraph, P ab,n,m is the ratio of the length of the m-th paragraph in which the combination of the n-th abnormal phrase pair appears to the total length of the paragraphs in the ideological and political education text set, N ab,n is the number of paragraphs in which the combination of the n-th abnormal phrase pair appears.

[0092] The present invention comprehensively considers factors such as the frequency of occurrence of phrase pairs in different paragraphs, the ratio of paragraph length, and the number of paragraphs, and uses an exponential formula to quantify the value of normal and abnormal phrase pairs in ideological and political education. Phrase pairs with a high frequency and a large ratio of paragraph length correspond to a higher index, which can accurately measure their importance and make the evaluation more objective and accurate.

[0093] In this embodiment, S46 includes the following sub-steps:

[0094] S461. Calculate the normal valuation based on the ideological and political value index of the normal phrase pairs and the corresponding phoneme-word following values in the phoneme-word following sequence. The calculation process of the normal valuation is as follows: Multiply the ideological and political value index of each normal phrase pair by its corresponding phoneme-word following value, and then sum up the product results of all normal phrase pairs;

[0095] S462. Calculate the abnormal valuation based on the ideological and political value index of the abnormal phrase pairs and the corresponding phoneme-word following values in the phoneme-word following sequence. The calculation process of the abnormal valuation is as follows: Multiply the ideological and political value index of each abnormal phrase pair by its corresponding phoneme-word following value, and then sum up the product results of all abnormal phrase pairs;

[0096] S463. Add the normal valuation and the abnormal valuation to obtain the sequence feature adjustment coefficient.

[0097] In this embodiment, the formula for calculating the normal valuation in S461 is: , where P no is the normal valuation, γ no,n is the ideological and political value index of the nth normal phrase pair, μ n is the phoneme-word following value corresponding to the nth normal phrase pair, M no is the number of normal phrase pairs, and n is a positive integer;

[0098] The formula for calculating the abnormal valuation in S462 is: , where P ab is the abnormal valuation, γ ab,k is the ideological and political value index of the kth abnormal phrase pair, μ k is the phoneme-word following value corresponding to the kth abnormal phrase pair, M ab is the number of abnormal phrase pairs, and k is a positive integer.

[0099] The present invention combines the ideological and political value indexes and phoneme-word following values of normal and abnormal phrase pairs, calculates the normal valuation and the abnormal valuation respectively, comprehensively considers the value of the content in ideological and political education and the cooperation of the speech text, and then comprehensively evaluates the teaching state, which can more accurately reflect the actual effect of ideological and political teaching.

[0100] As Figure 2 shown, the ideological and political education quality evaluation model in S5 includes: multiple feature extraction modules, an adder, and a scoring optimization layer;

[0101] Each feature extraction module is used to process a phoneme-word following sequence and perform sequence feature adjustment based on the sequence feature adjustment coefficient to obtain a sequence adjustment feature value;

[0102] The adder is used to add up the sequence adjustment feature values to obtain an initial score;

[0103] The scoring optimization layer is used to optimize the initial score according to the temporal variation of the coefficients adjusted by each sequence feature, and obtain the ideological and political education quality score.

[0104] In this embodiment, each feature extraction module includes a BiLSTM layer, a fully connected layer, and a sequence feature adjustment layer connected in sequence;

[0105] The expression of the sequence feature adjustment layer is: , where H is the sequence adjustment feature value output by the sequence feature adjustment layer, h is the sequence feature value output by the fully connected layer, tanh is the hyperbolic tangent function, and φ is the sequence feature adjustment coefficient;

[0106] The expression of the scoring optimization layer is: , where S is the ideological and political education quality score output by the scoring optimization layer, S in is the initial score, φ A is the mean value of the sequence feature adjustment coefficients in the second half of the time, φ B is the mean value of the sequence feature adjustment coefficients in the first half of the time, and D is the normalization parameter.

[0107] In this embodiment, the normalization parameter is set according to experiments or requirements.

[0108] In an ideological and political education video, when divided by sentences, there can be text sequences at multiple time points. Therefore, the time is divided into the first half of the time and the second half of the time.

[0109] The present invention uses each BiLSTM layer to process a phoneme-word following sequence, extract feature values, then uses a fully connected layer to synthesize each feature value to obtain the sequence feature value output by the fully connected layer. The sequence feature adjustment layer adjusts h according to the magnitude of the sequence feature adjustment coefficient φ. The hyperbolic tangent function is used to map the sequence feature adjustment coefficient φ to between -1 and 1, making the adjustment adaptive. The larger the sequence feature adjustment coefficient φ, the more significant the enhancement effect on the sequence feature value h, indicating that the segment of speech matches the text focus better.

[0110] In this embodiment, the BiLSTM layer can also be replaced by an LSTM layer.

[0111] The present invention can effectively capture the dynamic changes in the teaching situation at different stages of the ideological and political education process by comparing the mean values of the sequence feature adjustment coefficients in the second half of the time and the first half of the time (φ A and φ B ). If φ A -φ B ≥0, it indicates that there are positive changes in the teaching characteristics in the second half compared to the first half, and the score will increase accordingly; conversely, if φ A -φ BIf <0, it indicates that there may be problems in the latter part of the teaching, and the score will be reduced, thus dynamically reflecting the quality changes in the teaching process.

[0112] Based on the dynamic changes in the teaching process, the present invention optimizes the initial score, changing the limitations of single static scoring. This method takes into account the stage differences in teaching, making the final ideological and political education quality score more in line with the actual teaching effect and improving the accuracy and reliability of the scoring.

[0113] The present invention extracts the text in the ideological and political education video and divides it into text sequences, and at the same time records the corresponding voices to obtain a voice set, collecting data from two dimensions of text and voice, changing the limitation of only focusing on a single dimension in the past and being able to obtain more comprehensive information related to the ideological and political education process.

[0114] The present invention calculates the word-voice following value based on the fluctuation values of the frequency set and the voice set and constructs a word-voice following sequence, making full use of the correlation between text and voice. Since the word-voice following situation can reflect the key content of education and the emphasis in voice, when teachers explain key knowledge, they will emphasize it through the weight of voice. By analyzing the word-voice following sequence, these key contents and the emphasis points in the teacher's voice can be clearly identified, so as to better understand the teaching process and provide a key basis for teaching effect evaluation.

[0115] The present invention screens out abnormal pair phrases and normal pair phrases based on the word-voice following sequence and calculates the sequence feature adjustment coefficient, which can quantify the abnormal and normal states in the teaching process.

[0116] The present invention inputs the word-voice following sequence into the ideological and political education quality evaluation model, combines the sequence feature adjustment coefficient to conduct feature adjustment and initial score optimization, and comprehensively considers the ideological and political education quality from multiple perspectives. By dynamically adjusting features and optimizing scores, it overcomes the disadvantages of strong subjectivity and low efficiency of traditional evaluation methods, making the final ideological and political education quality score better reflect the actual teaching effect and improving the evaluation accuracy of ideological and political education quality.

[0117] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for monitoring ideological and political education based on semantic analysis, characterized in that: The following steps are involved: S1, extracting text from ideological and political education videos, dividing the text into text sequences by sentence, and recording the voice of reading the text sequence to obtain a voice set; S2, counting the frequency of each word in the text sequence appearing in the ideological and political education text set, and constructing a frequency set; S3, according to the fluctuation value of the frequency in the frequency set and the fluctuation value of the amplitude in the speech set, calculate the sound-word following value and construct the sound-word following sequence; S4, according to the sound-word following value in the sound-word following sequence, screen out abnormal word pairs and normal word pairs, and calculate the sequence feature adjustment coefficient; S5, inputting the sound-word following sequence corresponding to the ideological and political education video into the ideological and political education quality assessment model, and performing feature adjustment based on the sequence feature adjustment coefficient, and optimizing the initial score based on the temporal change of the sequence feature adjustment coefficient, to obtain the ideological and political education quality score; The S3 comprises the following sub-steps: S31, subtract the frequency of the i-th word in the frequency set from the frequency of the i+1-th word to obtain the i-th frequency fluctuation value, where i is a number; S32, dividing each frequency fluctuation value by the maximum frequency fluctuation value to obtain a normalized frequency fluctuation value; S33, extracting the speech segment corresponding to each word in the speech set, and extracting the amplitude mean value for each speech segment; S34, subtracting the amplitude mean of the i-th word from the amplitude mean of the i+1-th word to obtain the i-th amplitude fluctuation value; S35, dividing the i-th amplitude fluctuation value by the maximum amplitude fluctuation value to obtain a normalized amplitude fluctuation value; S36, calculating the sound word following value according to the normalized frequency fluctuation value and the normalized amplitude fluctuation value of the same number; S37, arranging the sound-word following values ​​in sequence to construct a sound-word following sequence; The S4 comprises the following sub-steps: S41, selecting two words corresponding to the sound-word following values ​​greater than 0 in the sound-word following sequence to form a normal pair of words; S42, selecting two words corresponding to the sound-word following values ​​less than 0 in the sound-word following sequence to form an abnormal pair of words; S43, searching for paragraphs where the phrases appear normally in the ideological and political education text set, and counting the frequency of the combination and the paragraph length ratio; S44, searching for paragraphs where the abnormal pair of words appears in the ideological and political education text set, and counting the frequency of the combination and the paragraph length ratio; S45. Calculate the ideological and political value index of normal phrases and abnormal phrases respectively according to the frequency of occurrence of the combination and the paragraph length ratio; S46. Calculate the sequence feature adjustment coefficient based on the ideological and political value index of the normal phrase pair and the abnormal phrase pair, and the corresponding sound-word following value in the sound-word following sequence.

2. The method for monitoring ideological and political education based on semantic analysis according to claim 1 is characterized in that: The S36 comprises the following sub-steps: S361, calculating a difference coefficient according to the normalized frequency fluctuation value and the normalized amplitude fluctuation value of the same number; S362, calculating a directional coefficient according to a normalized frequency fluctuation value and a normalized amplitude fluctuation value of the same number; S363. Multiply the direction coefficient by the difference coefficient to obtain the sound-word following value.

3. The method for monitoring ideological and political education based on semantic analysis according to claim 2 is characterized in that: The formula for calculating the coefficient of difference in S361 is: , where ε i is the i-th difference coefficient, F f,i is the ith normalized frequency fluctuation value, F a,i is the ith normalized amplitude fluctuation value, | | is the absolute value operation; The process of calculating the directional coefficient in S362 is specifically as follows: f,i and F a,i When both are greater than 0 or less than 0, the directional coefficient is assigned a value of 1; f,i and F a,i When one is negative and the other is positive, the directional coefficient is assigned a value of -1.

4. The method for monitoring ideological and political education based on semantic analysis according to claim 1 is characterized in that: The formula for calculating the ideological and political value index of a normal phrase in S45 is: , where γ no,n is the ideological and political value index of the nth normal pair of phrases, f no,n,m is the frequency of the nth normal phrase combination appearing in the mth paragraph, P no,n,m is the ratio of the length of the mth paragraph in the nth normal phrase combination to the length of the ideological and political education text set, N no,n is the number of paragraphs where the nth normal pair of phrases appears, e is a natural constant, and m and n are positive integers; The formula for calculating the ideological and political value index of the abnormal phrase in S45 is: , where γ ab,n is the ideological and political value index of the nth abnormal pair of phrases, f ab,n,m is the frequency of the nth abnormal phrase combination appearing in the mth paragraph, P ab,n,m N is the ratio of the length of the mth paragraph in the ideological and political education text set where the nth abnormal phrase combination appears. ab,n The number of paragraphs in which the nth abnormal phrase combination appears.

5. The method for monitoring ideological and political education based on semantic analysis according to claim 1 is characterized in that: The S46 comprises the following sub-steps: S461, calculating a normal valuation based on the normal ideological and political value index of the phrase and the corresponding sound-word following value in the sound-word following sequence; S462, calculating anomaly valuation according to the ideological and political value index of the anomaly to the phrase and the corresponding sound-word following value in the sound-word following sequence; S463. Add the normal estimate and the normal estimate to obtain the sequence characteristic adjustment coefficient.

6. The method for monitoring ideological and political education based on semantic analysis according to claim 5 is characterized in that: The formula for calculating the normal valuation in S461 is: , where P no is the normal valuation, γ no,n is the ideological and political value index of the nth normal phrase, μ n is the sound-word following value corresponding to the nth normal phrase, M no is the number of normal phrases, n is a positive integer; The formula for calculating the abnormal valuation in S462 is: , where P ab is the abnormal valuation, γ ab,k is the ideological and political value index of the kth abnormal pair of phrases, μ k is the phonetic word following value corresponding to the kth abnormal phrase, M ab is the number of abnormal phrases, and k is a positive integer.

7. The method for monitoring ideological and political education based on semantic analysis according to claim 1 is characterized in that: The ideological and political education quality assessment model in S5 includes: multiple feature extraction modules, adders and scoring optimization layers; Each of the feature extraction modules is used to process a sound-word following sequence, and to adjust the sequence features based on the sequence feature adjustment coefficient to obtain a sequence adjustment feature value; The adder is used to add the adjusted characteristic values ​​of each sequence to obtain an initial score; The scoring optimization layer is used to optimize the initial scoring according to the temporal changes of each sequence feature adjustment coefficient to obtain the ideological and political education quality score.

8. The method for monitoring ideological and political education based on semantic analysis according to claim 7 is characterized in that: Each of the feature extraction modules includes a BiLSTM layer, a fully connected layer, and a sequence feature adjustment layer connected in sequence; The expression of the sequence feature adjustment layer is: , where H is the sequence adjustment feature value output by the sequence feature adjustment layer, h is the sequence feature value output by the fully connected layer, tanh is the hyperbolic tangent function, and φ is the sequence feature adjustment coefficient; The expression of the score optimization layer is: , where S is the ideological and political education quality score output by the score optimization layer, S in is the initial score, φ A is the mean of the sequence characteristic adjustment coefficient in the second half of the period, φ B is the mean of the sequence characteristic adjustment coefficient in the first half of the period, and D is the normalization parameter.

Images