PTE spoken language evaluation method and teaching system

Abstract

The invention discloses a PTE spoken language evaluation method and a teaching system, relates to the technical field of spoken language evaluation, solves the technical problems of high subjectivity, non-uniform standards and influence on evaluation results, and aims to calculate evaluation values through multi-dimensional parameters and match the evaluation values with preset scoring intervals. One-sidedness and inaccuracy caused by single-dimension evaluation or subjective evaluation are avoided, the evaluation result more objectively reflects the spoken language ability of the user, the evaluation value is matched with the set grade interval, the generated evaluation result is simple and clear, follow-up analysis and improvement are facilitated, and user experience is improved. A standardized process is provided for spoken language evaluation through a clear scoring interval and a matching mechanism, different evaluations can be carried out according to the same standard, the consistency and comparability of the evaluations are improved, meanwhile, the defects of evaluation personnel in different aspects are visually reflected, and follow-up targeted teaching guidance is facilitated.

Description

Technical Field

[0001] The present invention relates to the technical field of oral assessment, and in particular to a PTE oral assessment method and teaching system. Background Art

[0002] As an important medium of interpersonal communication, spoken language plays an extremely important role in real life. With the continuous development of social economy and the intensification of globalization, people have put forward higher and higher requirements for the efficiency of language learning and the objectivity, fairness and large-scale testing of language assessment. Traditional assessment methods may have problems such as strong subjectivity and inconsistent standards.

[0003] According to the publication number CN103559892A, a spoken language evaluation method and system are disclosed, which include: receiving a speech signal to be evaluated; using at least two different speech recognition systems to respectively obtain speech fragments corresponding to each basic speech unit in the speech signal; extracting evaluation features corresponding to different feature types from the speech fragments; calculating the original scores of the evaluation features; optimizing and fusing the original scores obtained based on different speech recognition systems according to the feature types to obtain a comprehensive score of the evaluation features; and calculating the score of the speech signal according to the comprehensive scores of different evaluation features.

[0004] However, some existing evaluation methods have problems such as strong subjectivity and inconsistent standards when they are used. Furthermore, different evaluation scores will occur when oral English is evaluated, which will affect the final evaluation results. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a PTE oral assessment method and teaching system, which solves the problems of strong subjectivity and inconsistent standards that affect the assessment results.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a PTE oral assessment method, the method specifically comprising the following steps: Step 1: Obtain the evaluation topic and evaluation information of the evaluation user; Step 2: Based on the evaluation topic, the spoken content in the evaluation information of the evaluation user is evaluated and analyzed, and the content value is calculated according to the error situation of the spoken content; Step 3: Based on the evaluation questions, the oral pronunciation in the evaluation information of the evaluation user is evaluated and analyzed, and the pronunciation value is calculated according to the errors in the oral pronunciation; Step 4: Based on the evaluation questions, the oral fluency in the evaluation information of the evaluation user is evaluated and analyzed, and the fluency value is calculated according to the pauses in the oral pronunciation; Step 5: Calculate the evaluation value of the evaluation user based on the obtained content value, pronunciation value and fluency value, evaluate the evaluation user based on the evaluation value, and generate the evaluation result.

[0007] As a further solution of the present invention, the evaluation topic in step 1 includes oral test content, and the evaluation information of the evaluated user includes oral pronunciation, oral content and oral fluency.

[0008] As a further solution of the present invention, the specific method of evaluating and analyzing the spoken content in the evaluation information of the evaluation user in step 2 is: Obtain the test questions and the standard content answers corresponding to the test questions, then obtain the oral content of the test user, and compare and evaluate the oral content with the standard content answers; According to the assessment questions, the oral content of the assessment user is matched with the standard content answers to determine whether there are any anomalies between the oral content and the standard content answers. If there are any anomalies, the corresponding oral content is obtained and recorded as abnormal spoken content. If there are no anomalies, the corresponding spoken content is marked and recorded as normal spoken content. All abnormal spoken contents are obtained and labeled as i, where i=1, 2, ..., j, where j represents the number of abnormal spoken contents.

[0009] As a further solution of the present invention, the specific method of calculating the content value according to the error situation of the spoken content in step 2 is: The number of abnormal characters corresponding to the abnormal spoken content i is obtained and recorded as Ci, and the proportion of the abnormal character number Ci is calculated and recorded as Zi. Similarly, the proportion values ​​of all abnormal spoken content i are obtained, and the sum of the proportion values ​​is calculated and recorded as Zp. Then the number of missing key information in the spoken content is obtained and recorded as K, and the corresponding missing proportion Z is calculated. K , and calculate Zp and Z K The sum of the values ​​is recorded as the missing rate, and the corresponding content value analysis is performed based on the missing rate; The missing rate is obtained, and the missing rate and the evaluation interval are judged to obtain the evaluation score, and the obtained evaluation score is recorded as the content value.

[0010] As a further solution of the present invention, the specific method of evaluating and analyzing the spoken pronunciation in the evaluation information of the evaluation user in step 3 is: Obtain the spoken content corresponding to the assessment user, and obtain the recognizable spoken content as the recognized content, match the obtained recognized content with the standard content answer, and at the same time obtain the characters with pronunciation deviation in the recognized content and record them as n, where n=1, 2, ..., m, where m represents the number of pronunciation deviation characters, and record the calculated proportion of the pronunciation deviation characters as the deviation character proportion value; Then, the spoken content is processed into sentences to obtain multiple groups of spoken sentences, and the pronunciation deviation characters in the spoken sentences are obtained at the same time. Then, the deviation ratio of key information in the spoken sentences is obtained and recorded as the key ratio. At the same time, the sum of the deviation character ratio and the key ratio is calculated and recorded as the deviation rate. The oral pronunciation of the evaluation user is evaluated according to the obtained deviation rate, and the corresponding evaluation interval is obtained. Based on the evaluation interval where the deviation rate is located, the corresponding evaluation analysis is obtained, and the evaluation score is recorded as the pronunciation value.

[0011] As a further solution of the present invention, the specific method of evaluating and analyzing the oral fluency in the evaluation information of the evaluation user in step 4 is: The oral content of the evaluation user is obtained, and the oral content is divided into sentences to obtain multiple groups of oral sentences, denoted as a, and a=1, 2, ..., b, where b represents the number of oral sentences. At the same time, the oral sentences a with pauses are obtained and denoted as pre-processed oral sentences, and the pause duration corresponding to the pre-processed oral sentences is obtained, and the obtained pause duration is compared with a preset value. If the pause duration is greater than the preset value, the pre-processed oral sentence is marked as a paused oral sentence, and the proportion of the paused oral sentences is calculated. Otherwise, if the pause duration is less than the preset value, it is not processed.

[0012] As a further solution of the present invention, the specific method of calculating the fluency value according to the pause situation of spoken pronunciation in step 4 is: Obtain the evaluation time corresponding to spoken sentence a, record it as Ta, obtain the number of characters of spoken sentence a, record it as La, then calculate the speaking speed of the spoken sentence, record it as Va, and so on, calculate the speaking speed of all spoken sentences a, and similarly calculate the speaking speed of paused spoken sentences, record it as Vg, and g=1, 2, ..., f, where f represents the number of paused spoken sentences; The mean of the sum of the Vg and Va values ​​is calculated, and the calculated mean is used as the fluency value of the spoken pronunciation.

[0013] As a further solution of the present invention, the specific method of generating the evaluation results in step 5 is: The obtained content value, pronunciation value and fluency value are recorded as N, F and R respectively, and then the obtained parameters are substituted into the formula Calculate the evaluation value Q of the evaluated user, where , and The proportional coefficient is preset, and the obtained evaluation value Q is matched with the scoring interval to obtain a matching result, and the evaluation result is generated based on the matching result.

[0014] A PTE oral teaching system, comprising an information collection unit, an adaptive analysis unit and an information output unit; An information collection unit, which is used to collect evaluation questions and user evaluation information, and transmit the collected evaluation questions and user evaluation information to the adaptive analysis unit; An adaptive analysis unit, which is used to analyze the user evaluation information according to the acquired evaluation questions, and respectively calculate the content value, pronunciation value and fluency value corresponding to the spoken content by analyzing the spoken content, spoken pronunciation and spoken speed, and calculate the evaluation value of the evaluation user by combining the three, and then evaluate and analyze the evaluation user according to the evaluation value to generate the evaluation result, and then transmit the evaluation result to the information output unit; An information output unit is used to display the obtained evaluation results to the corresponding operator.

[0015] The present invention provides a PTE oral assessment method and teaching system. Compared with the prior art, it has the following beneficial effects: The present invention calculates the evaluation value through multi-dimensional parameters and matches it with the preset scoring interval, avoiding the one-sidedness and inaccuracy brought by single-dimensional evaluation or subjective evaluation, so that the evaluation result reflects the user's oral ability more objectively, and matches the evaluation value with the set level interval. The generated evaluation result is simple and clear. Both the evaluation user and the relevant personnel can quickly understand the level of the oral level, which is convenient for subsequent analysis and improvement. The clear scoring interval and matching mechanism provide a standardized process for oral evaluation. Different evaluations can be carried out according to the same standards, which improves the consistency and comparability of the evaluation. At the same time, it intuitively reflects the defects of the evaluators in different aspects, which is convenient for subsequent targeted teaching guidance. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of the steps of the present invention; Figure 2 This is a block diagram of the system principle of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] For example, see Figure 1 The present application provides a PTE oral assessment method, which specifically includes the following steps: Step 1: Obtain the evaluation topic and the evaluation information of the evaluation user, wherein the evaluation topic includes the oral test content, and the evaluation information of the evaluation user includes the oral pronunciation, oral content and oral fluency.

[0019] Step 2: Based on the evaluation topic, the spoken content in the evaluation information of the evaluation user is evaluated and analyzed, and the content value is calculated according to the error situation of the spoken content.

[0020] First, the evaluation questions and the corresponding standard content answers are obtained, then the oral content of the evaluation user is obtained, and the oral content is compared and evaluated with the standard content answers. The specific evaluation method is: According to the assessment questions, the oral content of the assessment user is matched with the standard content answer to determine whether there is an abnormality between the oral content and the standard content answer. If there is an abnormality, the corresponding oral content is obtained and recorded as abnormal oral content. If there is no abnormality, the corresponding oral content is marked and recorded as normal oral content. Here, a sentence or a paragraph in the oral content is compared with the standard content answer. At the same time, punctuation marks "," and "." are usually used as sentence or paragraph labels. For example, in the "Read Aloud" question type, all words in the text must be read aloud. Replacement, filling in words, and missing words will all result in deductions. In the "Retell Lecture" and "Describe Image" question types, the key information in the given content or picture must be expressed as comprehensively as possible. If there is an error in a sentence during the description, it will be screened and recorded as abnormal oral content. All abnormal oral contents are obtained and labeled as i, and i=1, 2, ..., j, where j represents the number of abnormal oral contents. Next, the number of abnormal characters corresponding to the abnormal spoken content i is obtained and recorded as Ci, where the number of abnormal characters here represents words or Chinese characters. At the same time, the proportion of the number of abnormal characters Ci is calculated and recorded as Zi. Similarly, the proportion of all abnormal spoken content i is obtained, and the sum of the proportions is calculated and recorded as Zp. Then, the number of missing key information in the spoken content is obtained and recorded as K, and the corresponding missing proportion Z is calculated. K , and calculate Zp and Z K The sum of the values ​​is recorded as the missing rate, and the corresponding content value analysis is performed based on the missing rate; Obtain the missing rate, and judge the missing rate and the evaluation interval to obtain the evaluation score, and record the obtained evaluation score as the content value. Specifically, if the missing rate is less than 30%, 6-8 points (out of 10 points) can be obtained; if the missing rate is between 30% and 60%, 3-5 points can be obtained; if the missing rate is higher than 60%, 0-2 points can be obtained, and the division of the scores here is set by the operator.

[0021] Step three, based on the evaluation questions, the oral pronunciation in the evaluation information of the evaluation user is evaluated and analyzed, and the pronunciation value is calculated according to the errors in the oral pronunciation.

[0022] The spoken content corresponding to the assessment user is obtained, and the recognizable spoken content is obtained and recorded as the recognized content. The obtained recognized content is matched with the standard content answer. The match here means that there are characters in the standard content answer that need to be emphasized or have stress. For example, in an English oral assessment, the assessment question is to describe a city landscape picture, and the standard content answer is "Tall buildings stand along the bus tree. ([tɔ: l'bɪldɪŋzstændə'lɒŋðə'bɪzistri: t])", where "tall", "buildings", "busy" and other words need to be stressed, which is the stress situation in the standard content answer. At the same time, the characters with pronunciation deviation in the recognized content are obtained and recorded as n, and n=1, 2, ..., m, where m represents the number of pronunciation deviation characters, and the corresponding percentage of the pronunciation deviation characters is recorded as the deviation character percentage. Assuming that the total number of characters (number of words) in the user's spoken content is 6, the deviation character percentage = 2÷6≈0.33. And here is the total number, then the spoken content is processed into sentences to obtain multiple groups of spoken sentences, and the pronunciation deviation characters in the spoken sentences are obtained at the same time. Then the deviation percentage of the key information in the spoken sentence is obtained and recorded as the key percentage. Specifically, it is represented here that there is a deviation in the corresponding spoken pronunciation in the key information, and the corresponding key information is set by the operator. At the same time, the sum of the deviation character percentage and the key percentage is calculated and recorded as the deviation rate; assuming that the key information set by the operator is the two words "buildings" and "busy", then the key percentage = 2÷2=1 (because the two key information set here have pronunciation deviations). Calculate the sum of the deviation character ratio and the key ratio, and record it as the deviation rate, that is, deviation rate = 0.33 + 1 = 1.33 (this is just an example. In actual applications, the data may need to be reasonably adjusted or normalized).

[0023] The oral pronunciation of the evaluation user is evaluated according to the obtained deviation rate to obtain the corresponding evaluation interval, and the evaluation interval here is the evaluation interval of oral pronunciation, and the corresponding evaluation analysis is obtained based on the evaluation interval where the deviation rate is located, and the evaluation score is recorded as the pronunciation value.

[0024] Finally, the oral pronunciation of the evaluation user is evaluated according to the obtained deviation rate to obtain the corresponding evaluation interval. Assume that the evaluation interval is divided into: the deviation rate is less than 0.2 for excellent (9-10 points), 0.2-0.5 for good (7-8 points), 0.5-0.8 for medium (5-6 points), 0.8-1.2 for poor (3-4 points), and greater than 1.2 for poor (0-2 points). Then the deviation rate of this user is 1.33, which is in the poor evaluation interval, and the evaluation score (pronunciation value) is 0-2 points.

[0025] Step 4: Based on the evaluation questions, the oral fluency in the evaluation information of the evaluation user is evaluated and analyzed, and the fluency value is calculated according to the pauses in the oral pronunciation.

[0026] Acquire the oral content of the evaluation user, and divide the oral content into sentences to obtain multiple groups of oral sentences, denoted as a, and a=1, 2, ..., b, where b represents the number of oral sentences, and at the same time, obtain the oral sentences a with pauses as pre-processed oral sentences, and obtain the pause duration corresponding to the pre-processed oral sentences, compare the obtained pause duration with a preset value, and the specific value of the preset value is set by the operator. If the pause duration is greater than the preset value, the pre-processed oral sentence is marked as a paused oral sentence, and the number ratio of the paused oral sentences is calculated. On the contrary, if the pause duration is less than the preset value, it is not processed; At the same time, the evaluation time corresponding to the spoken sentence a is obtained, recorded as Ta, and the number of characters in the spoken sentence a is obtained, recorded as La, and then the speaking speed of the spoken sentence is calculated, recorded as Va, and the specific calculation formula is , and so on, the speaking speed of all spoken sentences a is calculated, and the spoken sentences here are spoken sentences without pauses. Similarly, the speaking speed of paused spoken sentences is calculated and recorded as Vg, and g=1, 2, ..., f, where f represents the number of paused spoken sentences, and g here represents the number of paused spoken sentences; The mean of the sum of the Vg and Va values ​​is calculated, and the calculated mean is used as the fluency value of the spoken pronunciation.

[0027] Step 5: Calculate the evaluation value of the evaluation user based on the obtained content value, pronunciation value and fluency value, evaluate the evaluation user based on the evaluation value, and generate the evaluation result.

[0028] The obtained content value, pronunciation value and fluency value are recorded as N, F and R respectively, and then the obtained parameters are substituted into the formula Calculate the evaluation value Q of the evaluated user, where , and It is a preset proportional coefficient, and the obtained evaluation value Q is matched with the scoring interval to obtain a matching result, and the specific range of the scoring interval here is set by the operator, and the evaluation result is generated based on the matching result.

[0029] In a specific example, for example, in an oral assessment, after a series of calculations and analyses, the content value N=7 (full score 10 points), the pronunciation value F=8 (full score 10 points), and the fluency value R=6 (full score 10 points) are obtained. Then, these acquired parameters are substituted into a specific formula to calculate the assessment value Q of the assessed user. Assuming that the preset proportional coefficients are α=0.4, β=0.3, and γ=0.3 (these proportional coefficients are set in advance by the operator according to the assessment focus and requirements), then the assessment value Q=α×N+β×F+γ×R, that is, Q=0.4×7+0.3×8+0.3×6=2.8+2.4+1.8=7, and then the obtained assessment value Q is matched with the scoring interval. Assume that the operator sets the scoring range as follows: 9 to 10 points for excellent, 7 to 8 points for good, 5 to 6 points for medium, 3 to 4 points for poor, and 0 to 2 points for bad. Since the evaluation value Q = 7, the evaluation result is good.

[0030] For example 2, please refer to Figure 2 The present application provides a PTE oral assessment system, comprising: an information collection unit, an adaptive analysis unit and an information output unit.

[0031] An information collection unit, which is used to collect evaluation questions and user evaluation information, and transmit the collected evaluation questions and user evaluation information to the adaptive analysis unit; An adaptive analysis unit is used to analyze the user evaluation information according to the acquired evaluation questions, and to respectively calculate the content value, pronunciation value and fluency value corresponding to the spoken content by analyzing the three aspects of spoken content, spoken pronunciation and spoken speed, and to calculate the evaluation value of the evaluation user by combining the three, and to evaluate and analyze the evaluation user according to the evaluation value to generate an evaluation result, and then transmit the evaluation result to the information output unit, and the processing method here is the same as the processing process of step two, step three, step four and step five in embodiment one.

[0032] An information output unit is used to display the obtained evaluation results to the corresponding operator.

[0033] Specifically, according to the obtained evaluation results, the operator will provide targeted teaching to the evaluation users based on different situations. For example, if the evaluation users have shortcomings in oral pronunciation and oral speed during the evaluation process, the subsequent teaching can focus on the above two aspects.

[0034] Some of the data in the above formulas are dimensionless and numerically calculated. Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0035] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A PTE oral assessment method, characterized in that: The method specifically comprises the following steps: Step 1: Obtain the evaluation topic and evaluation information of the evaluation user; Step 2: Based on the evaluation topic, the spoken content in the evaluation information of the evaluation user is evaluated and analyzed, and the content value is calculated according to the error situation of the spoken content; Step 3: Based on the evaluation questions, the oral pronunciation in the evaluation information of the evaluation user is evaluated and analyzed, and the pronunciation value is calculated according to the errors in the oral pronunciation; Step 4: Based on the evaluation questions, the oral fluency in the evaluation information of the evaluation user is evaluated and analyzed, and the fluency value is calculated according to the pauses in the oral pronunciation; Step 5: Calculate the evaluation value of the evaluation user based on the obtained content value, pronunciation value and fluency value, evaluate the evaluation user based on the evaluation value, and generate the evaluation result.

2. A PTE oral assessment method according to claim 1, characterized in that: The evaluation questions in step 1 include oral test content, and the evaluation information of the evaluation user includes oral pronunciation, oral content and oral fluency.

3. A PTE oral assessment method according to claim 1, characterized in that: The specific method of evaluating and analyzing the spoken content in the evaluation information of the evaluation user in step 2 is: Obtain the test questions and the standard content answers corresponding to the test questions, then obtain the oral content of the test user, and compare and evaluate the oral content with the standard content answers; According to the assessment questions, the oral content of the assessment user is matched with the standard content answers to determine whether there are any anomalies between the oral content and the standard content answers. If there are any anomalies, the corresponding oral content is obtained and recorded as abnormal spoken content. If there are no anomalies, the corresponding spoken content is marked and recorded as normal spoken content. All abnormal spoken contents are obtained and labeled as i, where i=1, 2, ..., j, where j represents the number of abnormal spoken contents.

4. A PTE oral assessment method according to claim 1, characterized in that: The specific method of calculating the content value according to the error situation of the spoken content in step 2 is: The number of abnormal characters corresponding to the abnormal spoken content i is obtained and recorded as Ci, and the proportion of the abnormal character number Ci is calculated and recorded as Zi. Similarly, the proportion values ​​of all abnormal spoken content i are obtained, and the sum of the proportion values ​​is calculated and recorded as Zp. Then the number of missing key information in the spoken content is obtained and recorded as K, and the corresponding missing proportion Z is calculated. K , and calculate Zp and Z K The sum of the values ​​is recorded as the missing rate, and the corresponding content value analysis is performed based on the missing rate; The missing rate is obtained, and the missing rate and the evaluation interval are judged to obtain the evaluation score, and the obtained evaluation score is recorded as the content value.

5. A PTE oral assessment method according to claim 1, characterized in that: The specific method of evaluating and analyzing the oral pronunciation in the evaluation information of the evaluation user in step 3 is: Obtain the spoken content corresponding to the assessment user, and obtain the recognizable spoken content as the recognized content, match the obtained recognized content with the standard content answer, and at the same time obtain the characters with pronunciation deviation in the recognized content and record them as n, where n=1, 2, ..., m, where m represents the number of pronunciation deviation characters, and record the calculated proportion of the pronunciation deviation characters as the deviation character proportion value; Then, the spoken content is processed into sentences to obtain multiple groups of spoken sentences, and the pronunciation deviation characters in the spoken sentences are obtained at the same time. Then, the deviation ratio of key information in the spoken sentences is obtained and recorded as the key ratio. At the same time, the sum of the deviation character ratio and the key ratio is calculated and recorded as the deviation rate. The oral pronunciation of the evaluation user is evaluated according to the obtained deviation rate, and the corresponding evaluation interval is obtained. Based on the evaluation interval where the deviation rate is located, the corresponding evaluation analysis is obtained, and the evaluation score is recorded as the pronunciation value.

6. A PTE oral assessment method according to claim 1, characterized in that: The specific method of evaluating and analyzing the oral fluency in the evaluation information of the evaluation user in step 4 is as follows: The oral content of the evaluation user is obtained, and the oral content is divided into sentences to obtain multiple groups of oral sentences, denoted as a, and a=1, 2, ..., b, where b represents the number of oral sentences. At the same time, the oral sentences a with pauses are obtained and denoted as pre-processed oral sentences, and the pause duration corresponding to the pre-processed oral sentences is obtained, and the obtained pause duration is compared with a preset value. If the pause duration is greater than the preset value, the pre-processed oral sentence is marked as a paused oral sentence, and the proportion of the paused oral sentences is calculated. Otherwise, if the pause duration is less than the preset value, it is not processed.

7. A PTE oral assessment method according to claim 1, characterized in that: The specific method of calculating the fluency value according to the pauses in spoken pronunciation in step 4 is: Obtain the evaluation time corresponding to spoken sentence a, record it as Ta, obtain the number of characters of spoken sentence a, record it as La, then calculate the speaking speed of the spoken sentence, record it as Va, and so on, calculate the speaking speed of all spoken sentences a, and similarly calculate the speaking speed of paused spoken sentences, record it as Vg, and g=1, 2, ..., f, where f represents the number of paused spoken sentences; The mean of the sum of the Vg and Va values ​​is calculated, and the calculated mean is used as the fluency value of the spoken pronunciation.

8. A PTE oral assessment method according to claim 1, characterized in that: The specific method of generating the evaluation results in step 5 is: The obtained content value, pronunciation value and fluency value are recorded as N, F and R respectively, and then the obtained parameters are substituted into the formula Calculate the evaluation value Q of the evaluated user, where , and The proportional coefficient is preset, and the obtained evaluation value Q is matched with the scoring interval to obtain a matching result, and the evaluation result is generated based on the matching result.

9. A PTE oral teaching system, used to execute a PTE oral assessment method according to any one of claims 1 to 8, characterized in that: It includes an information collection unit, an adaptive analysis unit and an information output unit; An information collection unit, which is used to collect evaluation questions and user evaluation information, and transmit the collected evaluation questions and user evaluation information to the adaptive analysis unit; An adaptive analysis unit, which is used to analyze the user evaluation information according to the acquired evaluation questions, and respectively calculate the content value, pronunciation value and fluency value corresponding to the spoken content by analyzing the spoken content, spoken pronunciation and spoken speed, and calculate the evaluation value of the evaluation user by combining the three, and then evaluate and analyze the evaluation user according to the evaluation value to generate the evaluation result, and then transmit the evaluation result to the information output unit; An information output unit is used to display the obtained evaluation results to the corresponding operator.

Images