Intelligent Chinese subjective question scoring method and system based on big data

Abstract

The present invention provides an intelligent Chinese language subjective question grading method and system based on big data. The method obtains the answers of any two students and performs semantic recognition and conversion processing, semantic item comparison processing and scoring answer score calculation on the answers to finally determine the students' scores for Chinese language subjective questions. The method identifies and compares the answers to Chinese language subjective questions at the semantic level, thereby improving the objectivity and reliability of the scoring of Chinese language subjective questions, thereby improving students' interest and quality in Chinese language learning.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent education, and in particular to a method and system for intelligent Chinese language subjective question scoring based on big data. Background Art

[0002] At present, when students are taking Chinese language exams, corresponding Chinese subjective questions are usually set, and these Chinese subjective questions require students to answer corresponding main questions. Moreover, these Chinese subjective questions are usually divergent questions, which do not have corresponding standard answers. The examiners also score according to the students' specific answers. In actual operation, students only get their own answers to the Chinese subjective questions, which is not conducive to students' objective and comprehensive understanding of their actual answers, thereby greatly reducing students' interest in Chinese learning and the reliability of Chinese subjective question assessments. It can be seen that the existing technology needs a scoring model that can help students gain a comprehensive understanding of their own answers to Chinese subjective questions, improve students' interest and quality in Chinese learning, and improve the reliability of Chinese subjective question assessments. Summary of the Invention

[0003] In response to the defects of the existing technology, the present invention provides an intelligent Chinese language subjective question scoring method and system based on big data, which obtains the answers of several students to preset Chinese language subjective questions, and performs semantic recognition and conversion processing on the answers to obtain corresponding semantic vectors, and then compares the semantic vector corresponding to the target student with the semantic vectors corresponding to each of the other students to obtain corresponding semantic item comparison results, and determines the similarity evaluation results between the answer of the target student and each of the other students according to the semantic item comparison results, and then determines the similarity evaluation results according to the similarity evaluation results. The target student's score for the preset Chinese subjective question; it can be seen that the intelligent Chinese subjective question scoring method and system based on big data is different from the existing method of scoring Chinese subjective questions by examiners. It obtains the answers of any two students and performs semantic recognition and conversion processing, semantic item comparison processing and scoring answer score calculation on the answers to finally determine the student's score for the Chinese subjective question. It identifies and compares the answers to the Chinese subjective question at the semantic level, so as to improve the objectivity and reliability of the scoring of the Chinese subjective question answers, thereby improving students' interest and quality in Chinese learning.

[0004] The present invention provides an intelligent Chinese language subjective question scoring method based on big data, which is characterized by comprising the following steps:

[0005] Step S1: Obtain answers to a set of Chinese language subjective questions from several students, perform semantic recognition and conversion on the answers to obtain corresponding semantic vectors, and then compare the semantic vector corresponding to the target student with the semantic vectors corresponding to each of the other students to obtain corresponding semantic item comparison results;

[0006] Step S2: determining similarity evaluation results between the target student's answers and the answers of each other student based on the semantic item comparison results;

[0007] Step S3, determining the answer score of the preset Chinese subjective question of the target student based on the similarity evaluation result;

[0008] Furthermore, in step S1, answers to a set of Chinese language subjective questions from several students are obtained, and semantic recognition and conversion processing is performed on the answers to obtain corresponding semantic vectors. The semantic vector corresponding to the target student is then compared with the semantic vectors corresponding to each of the other students, thereby obtaining corresponding semantic item comparison results. Specifically, the following are included:

[0009] Step S101: obtaining answers to a number of students' pre-set Chinese language subjective questions, and performing feature word recognition processing on the answers to determine the subject text, predicate text, and object text contained in each sentence in the answers;

[0010] Step S102, converting the subject text, predicate text, and object text contained in the same sentence into a semantic vector;

[0011] In step S103, the semantic vector corresponding to the target student is compared with the semantic vector corresponding to each other student according to the following formula (1), thereby obtaining the corresponding semantic item comparison results:

[0012]

[0013] In the above formula (1), Y(A i ,A j ) represents the semantic item comparison value between the semantic vector of the i-th student and the semantic vector of the j-th student, A i represents the semantic vector of the i-th student, A j represents the semantic vector of the jth student, n represents the total number of students, m represents the total number of students except the i-th student, and the value of m is n-1, β represents the preset comparison coefficient, and its value is 0.4, Sim(A i ,A j) represents the semantic similarity between the words or phrases contained in the answer of the i-th student and the words or phrases contained in the answer of the j-th student;

[0014] Furthermore, in step S2, determining the similarity evaluation results between the target student's answers and the answers of each other student based on the semantic item comparison results specifically includes:

[0015] Based on the semantic item comparison result and the following formula (2), the similarity evaluation value between the target student and the answer of each other student is determined:

[0016]

[0017] In the above formula (2), Q(A i ,A j ) represents the similarity evaluation value between the answer of the i-th student and the answer of the j-th student, Y(A i ,A j ) represents the semantic item comparison value between the semantic vector of the i-th student and the semantic vector of the j-th student, α represents the preset similarity evaluation coefficient, and its value is 0.6, β represents the preset comparison coefficient, and its value is 0.4, n represents the total number of students, Sim(A i ,A j ) represents the semantic similarity between the words or phrases contained in the answer of the i-th student and the words or phrases contained in the answer of the j-th student;

[0018] Furthermore, in step S3, determining the answer score of the preset Chinese subjective question of the target student according to the similarity evaluation result specifically includes:

[0019] According to the similarity evaluation result and the following formula (3), the answer score of the preset Chinese subjective question of the target student is determined:

[0020]

[0021] In the above formula (3), F represents the answer score of the preset Chinese subjective question of the i-th student, Q(A i ,A j ) represents the similarity evaluation value between the answer of the i-th student and the answer of the j-th student, n represents the total number of students, M represents the full score of the preset Chinese subjective question, μ[] represents a step function, and when the value in [] is greater than or equal to 0, the result of the step function is 1, and when the value in [] is less than 0, the result of the step function is 0.

[0022] The present invention also provides an intelligent Chinese language subjective question scoring system based on big data, which is characterized by comprising a question answer recognition module, a semantic vector generation module, a semantic item comparison result generation module, a similarity evaluation result generation module and a scoring answer score determination module; wherein,

[0023] The question answer recognition module is used to obtain the answers of several students to the preset Chinese subjective questions and perform semantic recognition processing on the answers;

[0024] The semantic vector generation module is used to convert the result of the semantic recognition process to obtain the corresponding semantic vector;

[0025] The semantic item comparison result generation module is used to compare the semantic vector corresponding to the target student with the semantic vector corresponding to each other student, thereby obtaining corresponding semantic item comparison results;

[0026] The similarity evaluation result generating module is used to determine the similarity evaluation results between the target student and the answers corresponding to each other student according to the semantic item comparison result;

[0027] The scoring and answering score determination module is used to determine the answering score of the preset Chinese subjective question of the target student according to the similarity evaluation result;

[0028] Furthermore, the answer recognition module is used to obtain answers to a number of students' preset Chinese subjective questions and perform semantic recognition processing on the answers, specifically including:

[0029] Obtaining answers to a number of students' preset Chinese language subjective questions, and performing feature word recognition processing on the answers to determine the subject text, predicate text, and object text contained in each sentence in the answers;

[0030] as well as,

[0031] The semantic vector generation module converts the result of the semantic recognition process to obtain the corresponding semantic vector, specifically including:

[0032] Convert the subject text, predicate text and object text contained in the same sentence into semantic vectors;

[0033] as well as,

[0034] The semantic item comparison result generation module compares the semantic vector corresponding to the target student with the semantic vector corresponding to each other student, thereby obtaining the corresponding semantic item comparison result. Specifically, the module compares the semantic vector corresponding to the target student with the semantic vector corresponding to each other student, thereby obtaining the corresponding semantic item comparison result.

[0035] According to the following formula (1), the semantic vector corresponding to the target student is compared with the semantic vectors corresponding to each other student to obtain the corresponding semantic item comparison results:

[0036]

[0037] In the above formula (1), Y(A i ,A j ) represents the semantic item comparison value between the semantic vector of the i-th student and the semantic vector of the j-th student, A i represents the semantic vector of the i-th student, A j represents the semantic vector of the jth student, n represents the total number of students, m represents the total number of students except the i-th student, and the value of m is n-1, β represents the preset comparison coefficient, and its value is 0.4, Sim(A i ,A j ) represents the semantic similarity between the words or phrases contained in the answer of the i-th student and the words or phrases contained in the answer of the j-th student;

[0038] Furthermore, the similarity evaluation result generating module determines the similarity evaluation results between the target student and each of the other students' answers based on the semantic item comparison results, specifically including:

[0039] Based on the semantic item comparison result and the following formula (2), the similarity evaluation value between the target student and the answer of each other student is determined:

[0040]

[0041] In the above formula (2), Q(A i ,A j ) represents the similarity evaluation value between the answer of the i-th student and the answer of the j-th student, Y(A i ,A j ) represents the semantic item comparison value between the semantic vector of the i-th student and the semantic vector of the j-th student, α represents the preset similarity evaluation coefficient, and its value is 0.6, β represents the preset comparison coefficient, and its value is 0.4, n represents the total number of students, Sim(A i ,A j ) represents the semantic similarity between the words or phrases contained in the answer of the i-th student and the words or phrases contained in the answer of the j-th student;

[0042] Furthermore, the scoring and answering score determination module determines the answering score of the preset Chinese subjective question of the target student according to the similarity evaluation result, specifically including:

[0043] According to the similarity evaluation result and the following formula (3), the answer score of the preset Chinese subjective question of the target student is determined:

[0044]

[0045] In the above formula (3), F represents the answer score of the preset Chinese subjective question of the i-th student, Q(A i ,A j ) represents the similarity evaluation value between the answer of the i-th student and the answer of the j-th student, n represents the total number of students, M represents the full score of the preset Chinese subjective question, μ[] represents a step function, and when the value in [] is greater than or equal to 0, the result of the step function is 1, and when the value in [] is less than 0, the result of the step function is 0.

[0046] Compared with the existing technology, in order to address the defects of the existing technology, the present invention provides an intelligent Chinese language subjective question scoring method and system based on big data, which obtains the answers of several students to preset Chinese language subjective questions, and performs semantic recognition and conversion processing on the answers to obtain the corresponding semantic vectors, and then compares the semantic vector corresponding to the target student with the semantic vectors corresponding to each other student, thereby obtaining the corresponding semantic item comparison results, and according to the semantic item comparison results, determines the similarity evaluation results between the answer of the target student and each other student, and then according to the similarity evaluation results, determines the similarity evaluation results between the answer of the target student and each other student, and then determines the similarity evaluation results. , determine the answer score of the preset Chinese subjective question of the target student; it can be seen that the intelligent Chinese subjective question scoring method and system based on big data is different from the existing method of scoring Chinese subjective questions by examiners. It obtains the answers of any two students and performs semantic recognition and conversion processing, semantic item comparison processing and scoring answer score calculation on the answers to finally determine the student's score for the Chinese subjective question. It identifies and compares the answers to the Chinese subjective question at the semantic level, so as to improve the objectivity and reliability of the scoring of the Chinese subjective question answers, thereby improving students' interest and quality in Chinese learning.

[0047] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purposes and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0048] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1 This is a flow chart of the intelligent Chinese language subjective question scoring method based on big data provided by the present invention.

[0051] Figure 2 This is a structural diagram of the intelligent Chinese language subjective question scoring system based on big data provided by the present invention. DETAILED DESCRIPTION

[0052] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0053] See Figure 1 , which is a flow chart of a method for intelligent Chinese subjective question scoring based on big data provided by an embodiment of the present invention. The method for intelligent Chinese subjective question scoring based on big data includes the following steps:

[0054] Step S1: Obtain answers to a set of Chinese language subjective questions from several students, perform semantic recognition and conversion on the answers to obtain corresponding semantic vectors, and then compare the semantic vector corresponding to the target student with the semantic vectors corresponding to each of the other students to obtain corresponding semantic item comparison results;

[0055] Step S2: determining similarity evaluation results between the target student's answers and the answers of each other student based on the semantic item comparison results;

[0056] Step S3: Determine the answer score of the preset Chinese subjective question of the target student based on the similarity evaluation result.

[0057] The beneficial effects of the above technical solution are: the intelligent Chinese language subjective question scoring method based on big data is different from the existing method of scoring Chinese language subjective questions by examiners. It obtains the answers of any two students and performs semantic recognition and conversion processing, semantic item comparison processing and scoring answer score calculation on the answers to finally determine the student's score for the Chinese language subjective question. It identifies and compares the answers to the Chinese language subjective questions at the semantic level, thereby improving the objectivity and reliability of the scoring of the Chinese language subjective questions, thereby improving students' interest and quality in Chinese language learning.

[0058] Preferably, in step S1, answers to preset Chinese language subjective questions from several students are obtained, and semantic recognition and conversion processing is performed on the answers to obtain corresponding semantic vectors. The semantic vector corresponding to the target student is then compared with the semantic vectors corresponding to each of the other students, thereby obtaining corresponding semantic item comparison results. Specifically, the following steps are performed:

[0059] Step S101: obtaining answers to a number of students' pre-set Chinese language subjective questions, and performing feature word recognition processing on the answers to determine the subject text, predicate text, and object text contained in each sentence in the answers;

[0060] Step S102, converting the subject text, predicate text, and object text contained in the same sentence into a semantic vector;

[0061] In step S103, the semantic vector corresponding to the target student is compared with the semantic vector corresponding to each other student according to the following formula (1), thereby obtaining the corresponding semantic item comparison results:

[0062]

[0063] In the above formula (1), Y(A i ,A j ) represents the semantic item comparison value between the semantic vector of the i-th student and the semantic vector of the j-th student, A i represents the semantic vector of the i-th student, A j represents the semantic vector of the jth student, n represents the total number of students, m represents the total number of students except the i-th student, and the value of m is n-1, β represents the preset comparison coefficient, and its value is 0.4, Sim(A i ,A j ) represents the semantic similarity between the words or phrases contained in the answer of the i-th student and the words or phrases contained in the answer of the j-th student.

[0064] The beneficial effects of the above technical solution are as follows: by identifying and converting the subject, predicate and object components contained in each sentence in the answer to the test, the answer to the test can be effectively and maximally semantically refined and compressed, thereby reducing the noise component in the answer to the test and improving the accuracy of the semantic vector obtained by subsequent conversion; in addition, through the above formula (1), the semantic vectors corresponding to any two students can be fully semantically compared, thereby determining the semantic item difference comparison results between the two different semantic vectors, so as to quickly and accurately determine the semantic difference results between the two different answers to the test.

[0065] Preferably, in step S2, determining the similarity evaluation results between the target student's answers and the answers of each other student based on the semantic item comparison results specifically includes:

[0066] Based on the semantic item comparison result and the following formula (2), the similarity evaluation value between the target student and the answers of each other student is determined:

[0067]

[0068] In the above formula (2), Q(A i ,A j ) represents the similarity evaluation value between the answer of the i-th student and the answer of the j-th student, Y(A i ,A j ) represents the semantic item comparison value between the semantic vector of the i-th student and the semantic vector of the j-th student, α represents the preset similarity evaluation coefficient, and its value is 0.6, β represents the preset comparison coefficient, and its value is 0.4, n represents the total number of students, Sim(A i ,A j ) represents the semantic similarity between the words or phrases contained in the answer of the i-th student and the words or phrases contained in the answer of the j-th student.

[0069] The beneficial effect of the above technical solution is that, through the above formula (2), the semantic similarity between the answers of two different students can be determined to the greatest extent at the semantic level, thereby quantitatively judging the semantic similarity between the answers of two different students and improving the effectiveness of subsequent student test scores.

[0070] Preferably, in step S3, determining the answer score of the preset Chinese subjective question of the target student according to the similarity evaluation result specifically includes:

[0071] According to the similarity evaluation result and the following formula (3), the answer score of the preset Chinese subjective question of the target student is determined:

[0072]

[0073] In the above formula (3), F represents the answer score of the preset Chinese subjective question of the i-th student, Q(A i ,A j ) represents the similarity evaluation value between the answer of the i-th student and the answer of the j-th student, n represents the total number of students, M represents the full score of the preset Chinese subjective question, μ[] represents a step function, and when the value in [] is greater than or equal to 0, the result of the step function is 1, and when the value in [] is less than 0, the result of the step function is 0.

[0074] The beneficial effect of the above technical solution is that through the above formula (3), it is possible to facilitate the scoring of the answers to the Chinese subjective questions of any two different students through the corresponding scoring rules, thereby maximizing the objectivity and reliability of the scoring of the answers to the Chinese subjective questions.

[0075] See Figure 2 , is a schematic diagram of the structure of an intelligent Chinese subjective question scoring system based on big data provided by an embodiment of the present invention. The intelligent Chinese subjective question scoring system based on big data includes a question answer recognition module, a semantic vector generation module, a semantic item comparison result generation module, a similarity evaluation result generation module, and a scoring answer score determination module; wherein,

[0076] The answer recognition module is used to obtain the answers of several students to the preset Chinese subjective questions and perform semantic recognition processing on the answers;

[0077] The semantic vector generation module is used to convert the result of the semantic recognition process to obtain the corresponding semantic vector;

[0078] The semantic item comparison result generation module is used to compare the semantic vector corresponding to the target student with the semantic vector corresponding to each other student, thereby obtaining the corresponding semantic item comparison result;

[0079] The similarity evaluation result generating module is used to determine the similarity evaluation results between the target student and the answers of each other student according to the semantic item comparison result;

[0080] The scoring answer score determination module is used to determine the answer score of the preset Chinese language subjective question of the target student based on the similarity evaluation result.

[0081] The beneficial effects of the above technical solution are: the intelligent Chinese subjective question scoring system based on big data is different from the existing method of scoring Chinese subjective questions by examiners. It obtains the answers of any two students and performs semantic recognition and conversion processing, semantic item comparison processing and scoring answer score calculation on the answers to finally determine the students' scores for Chinese subjective questions. It identifies and compares the answers to Chinese subjective questions at the semantic level, thereby improving the objectivity and reliability of the scoring of Chinese subjective questions, thereby improving students' interest and quality in Chinese learning.

[0082] Preferably, the answer recognition module is used to obtain answers to preset Chinese subjective questions from several students and perform semantic recognition processing on the answers, specifically including:

[0083] Obtaining answers to a number of students' pre-set Chinese language subjective questions, and performing feature word recognition processing on the answers to determine the subject text, predicate text, and object text contained in each sentence in the answers;

[0084] as well as,

[0085] The semantic vector generation module converts the result of the semantic recognition process to obtain the corresponding semantic vector, specifically including:

[0086] Convert the subject text, predicate text and object text contained in the same sentence into semantic vectors;

[0087] as well as,

[0088] The semantic item comparison result generation module compares the semantic vector corresponding to the target student with the semantic vector corresponding to each other student, thereby obtaining the corresponding semantic item comparison results. Specifically, the results include:

[0089] According to the following formula (1), the semantic vector corresponding to the target student is compared with the semantic vectors corresponding to each other student to obtain the corresponding semantic item comparison results:

[0090]

[0091] In the above formula (1), Y(A i ,A j ) represents the semantic item comparison value between the semantic vector of the i-th student and the semantic vector of the j-th student, A i represents the semantic vector of the i-th student, A jrepresents the semantic vector of the jth student, n represents the total number of students, m represents the total number of students except the i-th student, and the value of m is n-1, β represents the preset comparison coefficient, and its value is 0.4, Sim(A i ,A j ) represents the semantic similarity between the words or phrases contained in the answer of the i-th student and the words or phrases contained in the answer of the j-th student.

[0092] The beneficial effects of the above technical solution are as follows: by identifying and converting the subject, predicate and object components contained in each sentence in the answer to the test, the answer to the test can be effectively and maximally semantically refined and compressed, thereby reducing the noise component in the answer to the test and improving the accuracy of the semantic vector obtained by subsequent conversion; in addition, through the above formula (1), the semantic vectors corresponding to any two students can be fully semantically compared, thereby determining the semantic item difference comparison results between the two different semantic vectors, so as to quickly and accurately determine the semantic difference results between the two different answers to the test.

[0093] Preferably, the similarity evaluation result generating module determines the similarity evaluation results between the target student and each of the other students' corresponding answers based on the semantic item comparison result, specifically including:

[0094] Based on the semantic item comparison result and the following formula (2), the similarity evaluation value between the target student and the answers of each other student is determined:

[0095]

[0096] In the above formula (2), Q(A i ,A j ) represents the similarity evaluation value between the answer of the i-th student and the answer of the j-th student, Y(A i ,A j ) represents the semantic item comparison value between the semantic vector of the i-th student and the semantic vector of the j-th student, α represents the preset similarity evaluation coefficient, and its value is 0.6, β represents the preset comparison coefficient, and its value is 0.4, n represents the total number of students, Sim(A i ,A j ) represents the semantic similarity between the words or phrases contained in the answer of the i-th student and the words or phrases contained in the answer of the j-th student.

[0097] The beneficial effect of the above technical solution is that, through the above formula (2), the semantic similarity between the answers of two different students can be determined to the greatest extent at the semantic level, thereby quantitatively judging the semantic similarity between the answers of two different students and improving the effectiveness of subsequent student test scores.

[0098] Preferably, the scoring and answering score determination module determines the answering score of the preset Chinese subjective question of the target student according to the similarity evaluation result, specifically including:

[0099] According to the similarity evaluation result and the following formula (3), the answer score of the preset Chinese subjective question of the target student is determined:

[0100]

[0101] In the above formula (3), F represents the answer score of the preset Chinese subjective question of the i-th student, Q(A i ,A j ) represents the similarity evaluation value between the answer of the i-th student and the answer of the j-th student, n represents the total number of students, M represents the full score of the preset Chinese subjective question, μ[] represents a step function, and when the value in [] is greater than or equal to 0, the result of the step function is 1, and when the value in [] is less than 0, the result of the step function is 0.

[0102] The beneficial effect of the above technical solution is that through the above formula (3), it is possible to facilitate the scoring of the answers to the Chinese subjective questions of any two different students through the corresponding scoring rules, thereby maximizing the objectivity and reliability of the scoring of the answers to the Chinese subjective questions.

[0103] As can be seen from the content of the above embodiment, the intelligent Chinese subjective question scoring method and system based on big data obtains the answers of several students to the preset Chinese subjective questions, and performs semantic recognition and conversion processing on the answers to obtain the corresponding semantic vectors. The semantic vector corresponding to the target student is then compared with the semantic vectors corresponding to each of the other students to obtain the corresponding semantic item comparison results. Based on the semantic item comparison results, the similarity evaluation results between the answer of the target student and each of the other students are determined. Based on the similarity evaluation results, the answer score of the preset Chinese subjective question of the target student is determined. It can be seen that the intelligent Chinese language subjective question scoring method and system based on big data is different from the existing method of scoring Chinese language subjective questions by examiners. It obtains the answers of any two students and performs semantic recognition and conversion processing, semantic item comparison processing and scoring answer score calculation on the answers to finally determine the students' scores for Chinese language subjective questions. It identifies and compares the answers to Chinese language subjective questions at the semantic level, thereby improving the objectivity and reliability of the scoring of Chinese language subjective questions, and can also facilitate full and comprehensive communication and scoring of Chinese language subjective questions between different students, thereby improving students' interest and quality in Chinese language learning.

[0104] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. The intelligent Chinese language subjective question scoring method based on big data is characterized by: It includes the following steps: Step S1: Obtain answers to a set of Chinese language subjective questions from several students, perform semantic recognition and conversion on the answers to obtain corresponding semantic vectors, and then compare the semantic vector corresponding to the target student with the semantic vectors corresponding to each of the other students to obtain corresponding semantic item comparison results; Step S2: determining similarity evaluation results between the target student's answers and the answers of each other student based on the semantic item comparison results; Step S3, determining the answer score of the preset Chinese subjective question of the target student based on the similarity evaluation result; Among them, in the step S1, the answers of several students to the preset Chinese subjective questions are obtained, and the answers are semantically recognized and converted to obtain corresponding semantic vectors. Then, the semantic vector corresponding to the target student is compared with the semantic vectors corresponding to each of the other students, thereby obtaining the corresponding semantic item comparison results. Specifically, the following are included: Step S101: obtaining answers to a number of students' pre-set Chinese language subjective questions and performing feature word recognition processing on the answers to determine the subject text, predicate text, and object text contained in each sentence in the answers; Step S102, converting the subject text, predicate text, and object text contained in the same sentence into a semantic vector; In step S103, the semantic vector corresponding to the target student is compared with the semantic vector corresponding to each other student according to the following formula (1), thereby obtaining the corresponding semantic item comparison results: In the above formula (1), Y(A i ,A j ) represents the semantic item comparison value between the semantic vector of the i-th student and the semantic vector of the j-th student, A i represents the semantic vector of the i-th student, A j represents the semantic vector of the jth student, n represents the total number of students, m represents the total number of students except the i-th student, and the value of m is n-1, β represents the preset comparison coefficient, and its value is 0.4, Sim(A i ,A j ) represents the semantic similarity between the words or phrases contained in the answer of the i-th student and the words or phrases contained in the answer of the j-th student.

2. The intelligent Chinese language subjective question scoring method based on big data according to claim 1 is characterized by: In step S2, determining the similarity evaluation results between the target student and each other student's answers to the questions based on the semantic item comparison results specifically includes: determining the similarity evaluation values ​​between the target student and each other student's answers to the questions based on the semantic item comparison results and the following formula (2): In the above formula (2), Q(A i ,A j ) represents the similarity evaluation value between the answer of the i-th student and the answer of the j-th student, Y(A i ,A j ) represents the semantic item comparison value between the semantic vector of the i-th student and the semantic vector of the j-th student, α represents the preset similarity evaluation coefficient, and its value is 0.6, β represents the preset comparison coefficient, and its value is 0.4, n represents the total number of students, Sim(A i ,A j ) represents the semantic similarity between the words or phrases contained in the answer of the i-th student and the words or phrases contained in the answer of the j-th student.

3. The intelligent language subjective question scoring method based on big data according to claim 2 is characterized by: In step S3, determining the answer score of the preset Chinese subjective question of the target student according to the similarity evaluation result specifically includes: According to the similarity evaluation result and the following formula (3), the answer score of the preset Chinese subjective question of the target student is determined: In the above formula (3), F represents the answer score of the preset Chinese subjective question of the i-th student, Q(A i ,A j ) represents the similarity evaluation value between the answer of the i-th student and the answer of the j-th student, n represents the total number of students, M represents the full score of the preset Chinese subjective question, μ[] represents a step function, and when the value in [] is greater than or equal to 0, the result of the step function is 1, and when the value in [] is less than 0, the result of the step function is 0.

4. The intelligent Chinese language subjective question scoring system based on big data is characterized by: It includes a question answer recognition module, a semantic vector generation module, a semantic item comparison result generation module, a similarity evaluation result generation module and a scoring answer score determination module; among them, The question answer recognition module is used to obtain the answers of several students to the preset Chinese subjective questions and perform semantic recognition processing on the answers; The semantic vector generation module is used to convert the result of the semantic recognition process to obtain the corresponding semantic vector; The semantic item comparison result generation module is used to compare the semantic vector corresponding to the target student with the semantic vector corresponding to each other student, thereby obtaining corresponding semantic item comparison results; The similarity evaluation result generating module is used to determine the similarity evaluation results between the target student and the answers corresponding to each other student according to the semantic item comparison result; The scoring and answering score determination module is used to determine the answering score of the preset Chinese subjective question of the target student according to the similarity evaluation result; The answer recognition module is used to obtain answers to a number of students' preset Chinese subjective questions and perform semantic recognition processing on the answers, specifically including: Obtaining answers to a number of students' preset Chinese language subjective questions, and performing feature word recognition processing on the answers to determine the subject text, predicate text, and object text contained in each sentence in the answers; as well as, The semantic vector generation module converts the result of the semantic recognition process to obtain the corresponding semantic vector, specifically including: Convert the subject text, predicate text and object text contained in the same sentence into semantic vectors; and The semantic item comparison result generation module compares the semantic vector corresponding to the target student with the semantic vector corresponding to each other student, thereby obtaining the corresponding semantic item comparison result. Specifically, the module compares the semantic vector corresponding to the target student with the semantic vector corresponding to each other student, thereby obtaining the corresponding semantic item comparison result. According to the following formula (1), the semantic vector corresponding to the target student is compared with the semantic vectors corresponding to each other student to obtain the corresponding semantic item comparison results: In the above formula (1), Y(A i ,A j ) represents the semantic item comparison value between the semantic vector of the i-th student and the semantic vector of the j-th student, A i represents the semantic vector of the i-th student, A j represents the semantic vector of the jth student, n represents the total number of students, m represents the total number of students except the i-th student, and the value of m is n-1, β represents the preset comparison coefficient, and its value is 0.4, Sim(A i ,A j ) represents the semantic similarity between the words or phrases contained in the answer of the i-th student and the words or phrases contained in the answer of the j-th student.

5. The intelligent Chinese language subjective question scoring system based on big data according to claim 4 is characterized by: The similarity evaluation result generating module determines the similarity evaluation results between the target student and each other student's answers based on the semantic item comparison results, specifically including: Based on the semantic item comparison result and the following formula (2), the similarity evaluation value between the target student and the answer of each other student is determined: In the above formula (2), Q(A i ,A j ) represents the similarity evaluation value between the answer of the i-th student and the answer of the j-th student, Y(A i ,A j ) represents the semantic item comparison value between the semantic vector of the i-th student and the semantic vector of the j-th student, α represents the preset similarity evaluation coefficient, and its value is 0.6, β represents the preset comparison coefficient, and its value is 0.4, n represents the total number of students, Sim(A i ,A j ) represents the semantic similarity between the words or phrases contained in the answer of the i-th student and the words or phrases contained in the answer of the j-th student.

6. The intelligent Chinese language subjective question scoring system based on big data according to claim 5, characterized in that: The scoring and answering score determination module determines the answering score of the preset Chinese subjective question of the target student according to the similarity evaluation result, specifically including: According to the similarity evaluation result and the following formula (3), the answer score of the preset Chinese subjective question of the target student is determined: In the above formula (3), F represents the answer score of the preset Chinese subjective question of the i-th student, Q(A i ,A j ) represents the similarity evaluation value between the answer of the i-th student and the answer of the j-th student, n represents the total number of students, M represents the full score of the preset Chinese subjective question, μ[] represents a step function, and when the value in [] is greater than or equal to 0, the result of the step function is 1, and when the value in [] is less than 0, the result of the step function is 0.

Images