Multi-dimensional medical education evaluation method and system based on speech recognition

Abstract

The invention relates to the technical field of education evaluation, and particularly discloses a multi-dimensional medical education evaluation method and system based on voice recognition, and the method comprises the following steps: obtaining a voice segment based on a voice signal in a process that a student answers a medical education evaluation test question, and obtaining a text segment based on the voice segment; grouping the characters according to the sequence of the characters, determining a target word according to the similarity degree of grouping, and obtaining a first keyword in the target word; obtaining a second keyword based on a preset keyword list, and determining a keyword sequence; obtaining the part of speech of the second keyword; and obtaining a part-of-speech sequence, and determining an evaluation score based on the part-of-speech sequence and the first keyword. According to the invention, the reliability and robustness of educational evaluation are improved.

Description

Technical Field

[0001] The present invention relates to the field of education evaluation technology, and in particular to a multi-dimensional medical education evaluation method and system based on speech recognition. Background Art

[0002] Speech recognition is a technology that converts sound signals into readable text. It captures sound through a microphone or other audio input device, then uses acoustic models and language models to analyze and match the characteristics of the sound, and finally outputs the corresponding text content.

[0003] Medical education refers to the cultivation and assessment of the theoretical knowledge, clinical skills and professional qualities of medical students and medical staff in the field of medical care through systematic course teaching, clinical internships and continuing education. The existing evaluation methods mainly rely on written tests and interviews, which are not only cumbersome and time-consuming, but also single-dimensional and subjective in scoring, making it difficult to truly reflect learners' language expression ability, communication skills and clinical thinking in diagnosis and treatment scenarios.

[0004] With the maturity of deep learning and speech recognition technology, intelligent analysis and real-time feedback based on sound have become possible. It can not only automatically identify pronunciation accuracy, terminology usage, speaking speed and intonation, but also combine natural language processing to evaluate response logic and humanistic care literacy, injecting new vitality and opportunities into medical education evaluation. Summary of the invention

[0005] The purpose of the present invention is to provide a multi-dimensional medical education evaluation method and system based on speech recognition to solve the following technical problems: The traditional evaluation method is not only cumbersome and time-consuming, but also single-dimensional and subjective in scoring, making it difficult to truly reflect learners' language expression ability, communication skills and clinical thinking in diagnosis and treatment scenarios.

[0006] The purpose of the present invention can be achieved by the following technical solutions: A multi-dimensional medical education evaluation method based on speech recognition comprises the following steps: Acquire a speech signal of a student when answering a single medical education evaluation test question, slice the speech signal to obtain a speech segment, and convert the speech segment into a text form, which is recorded as a text segment; Sorting the characters in a single text segment, grouping the characters based on the sorting, determining a pending word based on the similarity between two adjacent groups, obtaining a target word based on the pending word, and determining a first keyword based on the position of the target word in the sorting; Extract keywords from the text segment based on a preset keyword list, denoted as the second keywords, and sort the second keywords to obtain a keyword sorting; obtain the part-of-speech of the second keywords, where the part-of-speech includes symptoms, examinations, diagnoses, and treatments. Sort the part-of-speech in the order of the keyword sorting to obtain a part-of-speech sorting, and determine an evaluation score based on the part-of-speech sorting and the first keyword.

[0007] As a further solution of the present invention: the speech segment satisfies the following constraints: Number the speech segment, C KS （a+1） -C JS a ≥ Cys, C KS （a+1） represents the time stamp corresponding to the start point of the speech segment numbered a + 1, C JS a ≥ represents the time stamp corresponding to the end point of the speech segment numbered a, Cys represents a preset time stamp difference, a ∈ [1, n - 1], and n represents the total number of the speech segments.

[0008] As a further solution of the present invention: the process of determining the first keyword includes: Step 1: Sort the characters in a single text segment in the order in which they appear in the text segment to obtain a character sorting. Starting from the first character in the character sorting, divide adjacent m characters into the same group, where m is a preset number of characters; Step 2: When the similarity degree of characters in any two of the groups is greater than a preset similarity degree threshold, combine the characters in these two groups to obtain a to-be-determined word, and obtain the similarity degree between the to-be-determined word and the keywords in the keyword list; Mark the keyword corresponding to the maximum similarity degree as the target word; Step 3: Obtain a new number of characters m' = m - 1, repeat Step 1 and Step 2, obtain a new target word, and repeat the above steps until the new number of characters is greater than a preset number-of-characters threshold; Obtain two groups corresponding to a single target word, denoted as group i and group i - 1, and the sorting position W of the first character in group i - 1 in the character sorting i-1 is in the left of the sorting position W i as the target position; i-1 Step 4: Obtain all the target positions, count the number of occurrences of the target words corresponding to the target positions within the sorting position range [WMB - W, WMB + W], and obtain the target word corresponding to the maximum number of occurrences as the first keyword, where WMB represents the sorting position of the target position in the character sorting, and W represents the preset number of sorting positions.

[0009] As a further solution of the present invention: The process of determining the evaluation score based on the part-of-speech sorting and the first keyword includes: Obtain the first part of speech F1 in the part-of-speech sorting, and determine whether the part of speech F1 is the symptom; If so, let the evaluation score P1 = 1, and start from the second part of speech in the part-of-speech sorting to determine the first part of speech F2 that is not the symptom, and determine whether the part of speech F2 is an examination; If so, obtain the new evaluation score P2 = P1 + 1, and start from the part of speech F2 to determine the first part of speech F3 that is not the examination, and determine whether the part of speech F3 is a diagnosis; If so, obtain the new evaluation score P3 = P2 + 1, and start from the part of speech F3 to determine the first part of speech F4 that is not the diagnosis, and determine whether the part of speech F4 is a treatment; If so, obtain the new evaluation score P4 = P3 + 1.

[0010] As a further solution of the present invention: The process of determining the evaluation score based on the part-of-speech sorting and the first keyword further includes a judgment step: If the part of speech F1 is not a symptom, obtain the timestamp CF1 corresponding to the part of speech F1, obtain the first keyword whose corresponding timestamp is within the timestamp range [CF1 - C, CF1 + C], denoted as the pending word, and obtain the part of speech of the pending word, where C is a preset value; When there is a part of speech of the pending word that is a symptom, let the evaluation score P1 = 0.5, and execute the subsequent steps; when there is no part of speech of the pending word that is an examination, let the evaluation score P1 = 0, and execute the subsequent steps.

[0011] As a further solution of the present invention: The process of determining the evaluation score based on the part-of-speech sorting and the first keyword further includes: When the part of speech F2 is not an examination, execute the judgment step; When the part of speech F2 is not a diagnosis, execute the judgment step; When the part of speech F2 is not a treatment, execute the judgment step.

[0012] As a further solution of the present invention: The part of speech of the second keyword and the pending word is based on manual annotation.

[0013] A multi-dimensional medical education evaluation system based on speech recognition, comprising: Acquisition module: Obtain the speech signal of a student during the process of answering a single medical education evaluation question, slice the speech signal to obtain speech segments, and convert the speech segments into text form, denoted as text segments; First keyword module: Sort the characters in a single text segment, group the characters based on the sorting, determine the pending words according to the similarity between adjacent groups, obtain the target words based on the pending words, and determine the first keyword according to the position of the target word in the sorting; Second keyword module: Extract the keywords in the text segment based on a preset keyword list, denoted as the second keyword, sort the second keyword to obtain a keyword sorting; obtain the part of speech of the second keyword, and the part of speech includes symptoms, examinations, diagnoses, and treatments; Evaluation module: Sort the part of speech in the order of the keyword sorting to obtain a part-of-speech sorting, and determine the evaluation score based on the part-of-speech sorting and the first keyword.

[0014] Advantages of the present invention: Compared with the prior art: 1) Through the speech slicing method based on a preset timestamp difference, the present invention can effectively cope with the intermittent speech phenomenon caused by pauses or stutters during the student's answering process. This method maintains a sufficient time interval between each speech segment, ensuring that the sliced text segments have high coherence and integrity, and significantly reducing the errors caused by overlapping or missing speech signals, ensuring that the subsequent speech-to-text can more accurately complete the recognition task and reducing the error rate; 2) The multi-round iterative keyword extraction method based on sliding window grouping and similarity determination proposed by the present invention can effectively compensate for the oral flaws that occur when students have discontinuous pronunciation, repeated characters, or stutters. By calculating the similarity of a preset character number sliding window and adjacent groups, the discontinuous characters are combined into pending words, and multiple rounds of similarity matching are performed in a predefined term library, enabling the restoration of the most appropriate professional terms from noisy text segments; 3) In view of the repeated pronunciations and stutters caused by students' lack of proficiency in oral answers, the present invention innovatively introduces a first keyword extraction mechanism based on character sliding window grouping and similarity matching. When there are repeated or discontinuous middle characters in a certain term, it is difficult for traditional direct matching methods based on a preset keyword list to accurately identify. Through multiple rounds of sliding window grouping, adjacent group similarity determination, and iterative refinement, the present invention can restore the most appropriate medical term from the noisy text and determine the first keyword by counting the positions of high-frequency target words. During the thinking chain evaluation process, when the extraction of the second keyword fails or is missing, this first keyword is used to assist in judging whether the student unfolds according to the logic of "symptom - examination - diagnosis - treatment", significantly improving the system's fault tolerance for unsmooth answers and evaluation accuracy, and contributing to the digital transformation and intelligent development of medical education. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention will be further described below with reference to the accompanying drawings.

[0016] Figure 1 It is a schematic flowchart of a multi-dimensional medical education evaluation method based on speech recognition according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0018] Please refer to Figure 1 As shown, the present invention is a multi-dimensional medical education evaluation method based on speech recognition, including the following steps: Obtain the speech signal of a student during the process of answering a single medical education evaluation question, slice the speech signal to obtain speech segments, and convert the speech segments into text form, denoted as text segments; In a preferred embodiment of the present invention, the speech segments satisfy the following constraints: Number the speech segments, C KS （a+1） -C JS a ≥Cys, C KS （a+1） represents the time stamp corresponding to the start point of the speech segment numbered a + 1, C JS a ≥ represents the time stamp corresponding to the end point of the speech segment numbered a, Cys represents a preset time stamp difference, a ∈ [1, n - 1], and n represents the total number of the speech segments; Exemplarily, when a student answers the question "What is heart failure" in a test, the system starts recording from 0.00 seconds when he starts speaking and continues recording until 18.70 seconds. At this time, he pauses for 2.30 seconds due to thinking (i.e., 21.00 seconds, the starting point of the second paragraph minus 18.70 seconds, the ending point of the first paragraph), and since 2.30s ≥ Cys, the period from 0.00 - 18.70 seconds is defined as the first paragraph; the second paragraph starts recording from 21.00 seconds to 35.20 seconds, and pauses again for 2.50 seconds (37.70 seconds, the starting point of the third paragraph minus 35.20 seconds, the ending point of the second paragraph), and since 2.50s ≥ Cys, the period from 21.00 - 35.20 seconds is defined as the second paragraph; the third paragraph is recorded from 37.70 seconds to 52.10 seconds. After the recording is completed, the system sends these three segments of voice into the recognition engine respectively, and obtains the corresponding text fragments: the first paragraph is "Heart failure refers to the systemic circulatory disorder caused by insufficient cardiac pumping function", the second paragraph is "Patients often present with fatigue, shortness of breath and lower extremity edema", and the third paragraph is "Routine examinations include electrocardiogram, echocardiogram and blood biochemistry, etc.". In this way, the silent interval between each voice segment is not less than Cys, making the sliced text fragments both coherent and complete, providing a clear and reliable written basis for subsequent medical education evaluation; Sort the characters in a single said text fragment, group the characters based on the sorting, determine the candidate words according to the similarity degree between adjacent two groups, obtain the target words based on the candidate words, and determine the first keyword according to the position of the said target word in the sorting; In another preferred embodiment of the present invention, the process of determining the first keyword includes: Step 1: Sort the characters in a single said text fragment in the order of their appearance in the text fragment to obtain a character sorting. Starting from the first character in the character sorting, divide adjacent m characters into the same group, where m is a preset number of characters; Step 2: When the similarity degree of the characters in any two said groups is greater than the preset similarity degree threshold, combine the characters in these two groups to obtain candidate words, and obtain the similarity degree between the said candidate words and the keywords in the keyword list; Mark the keyword corresponding to the maximum similarity degree as the target word; Step 3: Obtain a new number of characters m' = m - 1, repeat Step 1 and Step 2, obtain a new target word, and repeat the above steps until the new number of characters is greater than the preset number of character threshold; Obtain two groups corresponding to a single said target word, denoted as group i and group i - 1, and the sorting position W of the first character in the group i - 1 in the character sorting i-1 at the sorting position W i on the left, and the said sorting position Wi-1 as the target position; Step 4: Obtain all the target positions, count the number of occurrences of the target words corresponding to the target positions within the sorting position interval [WMB - W, WMB + W], and obtain the target word corresponding to the maximum number of occurrences as the first keyword. WMB represents the sorting position of the target position in the character sorting, and W represents the preset number of sorting positions. It should be noted that in actual spoken Q&A, students often have interrupted, repeated, or jumping pronunciations due to unfamiliarity with complex medical terms. For example, when trying to express "coronary atherosclerotic heart disease", it may be pronounced as "coronary - artery - athero - athero - atherosclerotic - heart - heart - disease", making it difficult for the direct matching method based on the preset keyword list to locate the core concept. To solve this problem, the present invention robustly restores the true intention of students in complex noise by grouping characters in the text fragment in multiple rounds and combining any characters. Exemplarily, for the text fragment "Coronary athero - atherosclerotic heart disease is a chronic ischemic heart disease caused by coronary atherosclerosis", which is more than 30 characters in length. First, arrange all the characters in the order of appearance as: [coronary, artery, athero, athero, atherosclerotic, heart, heart, disease, is, coronary, artery, athero, atherosclerotic, caused, by, chronic, ischemic, heart, disease]; Assume the initial sliding window length m = 8. Then take the first 8 characters "coronary artery athero - athero" as group A, and take the 9 - 16th characters "atherosclerotic heart disease is" as group B. In these 16 characters, the system constructs several candidate words by randomly selecting 1 to 8 characters according to the mathematical permutation and combination method, and calculates the similarity of each candidate word with the entries such as "coronary atherosclerotic heart disease", "coronary atherosclerosis", and "chronic ischemic heart disease" in the preset term library one by one. Finally, "coronary atherosclerotic heart disease" is selected as the target word with the highest similarity, and at the same time, record its starting position 1 in the original sequence. Then decrease m to 7 and re - divide the groups (the first 7 characters "coronary artery athero - athero" and the 8 - 14th characters "atherosclerotic heart heart"). In these 14 characters, also perform arbitrary combination matching, and again identify "coronary atherosclerotic heart disease" and record the position 1. When m = 6, the groups "coronary artery athero - atherosclerotic" and "atherosclerotic heart disease is coronary" match to obtain "coronary atherosclerotic heart disease" and record the position 1. When m = 5 and 4, the term is located multiple times in different 8 - 10 - character groups, and record the positions 3 and 5. Until m = 3, the groups "coronary artery athero" and "atherosclerotic" also successfully extract the core term and record the position 4. Finally, summarize all the target positions {1, 1, 1, 3, 5, 4}; For any target position, set the corresponding target position interval, and determine the first keyword corresponding to the target position interval. After determination, use other target positions to determine new first keywords, and finally obtain all the first keywords; through this multi-round iterative sliding window and arbitrary character combination strategy, the present invention can effectively filter out repeated and jumping character noises in the stuttering expressions of students, accurately extract the most representative long terms, and ensure the robustness and accuracy of medical concept recognition; Extract the keywords in the text fragment based on a preset keyword list, denoted as the second keywords, and sort the second keywords to obtain a keyword sorting; obtain the part-of-speech of the second keywords, and the part-of-speech includes symptoms, examinations, diagnoses, and treatments; Sort the part-of-speech in the order of the keyword sorting to obtain a part-of-speech sorting, and determine an evaluation score based on the part-of-speech sorting and the first keyword; In a preferred embodiment of the present invention, the process of determining an evaluation score based on the part-of-speech sorting and the first keyword includes: Obtain the part-of-speech F1 at the first place in the part-of-speech sorting, and determine whether the part-of-speech F1 is the symptom; If so, let the evaluation score P1 = 1, and start from the part-of-speech at the second place in the part-of-speech sorting to determine the first part-of-speech F2 that is not the symptom, and determine whether the part-of-speech F2 is an examination; If so, obtain a new evaluation score P2 = P1 + 1, and start from the part-of-speech F2 to determine the first part-of-speech F3 that is not the examination, and determine whether the part-of-speech F3 is a diagnosis; If so, obtain a new evaluation score P3 = P2 + 1, and start from the part-of-speech F3 to determine the first part-of-speech F4 that is not the diagnosis, and determine whether the part-of-speech F4 is a treatment; If so, obtain a new evaluation score P4 = P3 + 1; Exemplarily, assume that in a certain text segment, the system has extracted the first keyword "acute myocardial infarction" through the foregoing method. Then, six terms, namely "chest pain", "shortness of breath", "electrocardiogram", "echocardiogram", "acute myocardial infarction", and "thrombolytic therapy", are matched from the preset keyword list, and a keyword sorting is formed according to their order of appearance in the segment. Then, according to the part of speech of each term ("chest pain" and "shortness of breath" are symptoms; "electrocardiogram" and "echocardiogram" are examinations; "acute myocardial infarction" is a diagnosis; "thrombolytic therapy" is a treatment), a part-of-speech sorting [symptom, symptom, examination, examination, diagnosis, treatment] is obtained. The system first takes the first F1 = symptom in the part-of-speech sorting, and after judging it as a symptom, sets P1 = 1; then skips the second symptom, and starts from the third position to locate the first non-symptom F2 = examination. After judging it as an examination, sets P2 = P1 + 1 = 2; then locates the first non-examination F3 = diagnosis after F2. After judging it as a diagnosis, sets P3 = P2 + 1 = 3; finally, locates the first non-diagnosis F4 = treatment after F3. After judging it as a treatment, sets P4 = P3 + 1 = 4. Thus, the entire scoring process is completed, and the evaluation score of this answer segment is finally obtained as 4 points; In a preferred embodiment of the present invention, the process of determining the evaluation score based on the part-of-speech sorting and the first keyword further includes a judgment step: If the part of speech F1 is not a symptom, obtain the timestamp CF1 corresponding to the part of speech F1, obtain the first keyword whose corresponding timestamp is within the timestamp interval [CF1 - C, CF1 + C], denoted as the pending word, and obtain the part of speech of the pending word, where C is a preset value; When there is a pending word whose part of speech is a symptom, set the evaluation score P1 = 0.5, and execute the subsequent steps; when there is no pending word whose part of speech is an examination, set the evaluation score P1 = 0, and execute the subsequent steps; It can be understood that the process of determining the evaluation score based on the part-of-speech sorting and the first keyword further includes: When the part of speech F2 is not an examination, execute the judgment step; When the part of speech F3 is not a diagnosis, execute the judgment step; When the part of speech F4 is not a treatment, execute the judgment step; It should be noted that in an oral answer, the system extracts the second keyword sequence from the student's answer. The first keyword F1 is recognized as "electrocardiogram examination", and its corresponding timestamp CF1 is 12.5 seconds. Since F1 does not belong to "symptom", the system enters the judgment step. When the preset constant C = 3 seconds (which can be preset according to experience) is taken, the time interval [CF1 - C, CF1 + C] = [9.5s, 15.5s] is constructed. The first keyword obtained by the previous sliding window combination method is retrieved within this interval. Assuming that "chest pain" is matched at 13.2 seconds and its part of speech is "symptom", it is determined that there is a pending word with the part of speech of symptom, and the evaluation score P1 = 0.5 is set, and the subsequent scoring continues; if no first keyword with the part of speech of symptom is retrieved within [9.5s, 15.5s], it is determined that there is no qualified pending word, and the evaluation score P1 = 0 is set. Subsequently, if the same situation as F1 occurs for F2, F3, and F4 (that is, F2 is not examination, F3 is not diagnosis, and F4 is not treatment), the subsequent F2, F2, and F4 are scored according to the same logic; by using the core terms and their time information extracted by the previous sliding window combination, partial scores can be given when the student does not explicitly mention the symptom but the corresponding concept already exists in the context, so as to compensate for the direct matching failure caused by the student's oral inarticulateness or omission of symptoms; It can be understood that the parts of speech of the second keyword and the pending word are based on manual annotation; A multi-dimensional medical education evaluation system based on speech recognition, comprising: Acquisition module: Obtain the voice signal of the student during the process of answering a single medical education evaluation question, slice the voice signal to obtain voice segments, and convert the voice segments into text form, denoted as text segments; First keyword module: Sort the characters in a single text segment, group the characters based on the sorting, determine the pending word according to the similarity degree between adjacent two groups, obtain the target word based on the pending word, and determine the first keyword according to the position of the target word in the sorting; Second keyword module: Extract the keywords in the text segment based on a preset keyword list, denoted as the second keyword, sort the second keyword to obtain the keyword sorting; obtain the part of speech of the second keyword, and the part of speech includes symptom, examination, diagnosis, and treatment; Evaluation module: Sort the parts of speech in the order of the keyword sorting to obtain the part of speech sorting, and determine the evaluation score based on the part of speech sorting and the first keyword.

[0019] The above has described in detail an embodiment of the present invention, but the above content is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made according to the scope of the application of the present invention shall still fall within the scope covered by the patent of the present invention.

Claims

1. A multi-dimensional medical education evaluation method based on speech recognition, characterized in that: The following steps are involved: Acquire a speech signal of a student when answering a single medical education evaluation test question, slice the speech signal to obtain a speech segment, and convert the speech segment into a text form, which is recorded as a text segment; Sorting the characters in a single text segment, grouping the characters based on the sorting, determining a pending word based on the similarity between two adjacent groups, obtaining a target word based on the pending word, and determining a first keyword based on the position of the target word in the sorting; Extracting keywords from the text segment based on a preset keyword list, recording them as second keywords, sorting the second keywords to obtain a keyword ranking; obtaining the part of speech of the second keyword, the part of speech including symptom, examination, diagnosis and treatment; The parts of speech are sorted in the order of the keyword sorting to obtain a part of speech sorting, and an evaluation score is determined based on the part of speech sorting and the first keyword.

2. According to claim 1, a multi-dimensional medical education evaluation method based on speech recognition is characterized in that: The speech segment satisfies the following constraints: Number the voice segments, C KS （a+1） -C JS a ≥Cys, C KS （a+1） Indicates the timestamp corresponding to the starting point of the voice segment numbered a+1, C JS a ≥ represents the timestamp corresponding to the end point of the voice segment numbered a, Cys represents a preset timestamp difference, a∈[1, n-1], and n represents the total number of the voice segments.

3. According to claim 1, a multi-dimensional medical education evaluation method based on speech recognition is characterized in that: The process of determining the first keyword includes: Step 1: sorting the characters in a single text segment according to the order in which they appear in the text segment to obtain a character sorting, and starting from the first character in the character sorting, dividing m adjacent characters into the same group, where m is a preset number of characters; Step 2: When the similarity between characters in any two of the groups is greater than a preset similarity threshold, the characters in the two groups are combined to obtain a pending word, and the similarity between the pending word and a keyword in the keyword list is obtained; Marking the keyword corresponding to the maximum similarity as the target word; Step 3: Obtain a new number of characters m'=m-1, repeat the steps 1 and 2, obtain a new target word, and repeat the above steps until the new number of characters is greater than a preset character number threshold; Get two groups corresponding to the single target word, recorded as group i and group i-1, the first character in group i-1 is sorted in the character sorting position W i-1 In sorting position W i The left side of the sort position W i-1 as the target location; Step 4: Obtain all the target positions, count the number of occurrences of the target words corresponding to the target positions in the sorting position interval [WMB-W, WMB+W], obtain the target word corresponding to the maximum number of times as the first keyword, WMB represents the sorting position of the target position in the character sorting, and W represents the number of preset sorting positions.

4. According to claim 3, a multi-dimensional medical education evaluation method based on speech recognition is characterized in that: The process of determining the evaluation score based on the part-of-speech ranking and the first keyword includes: Obtaining the first part of speech F1 in the part of speech ranking, and determining whether the part of speech F1 is the symptom; If so, set the evaluation score P1=1, and determine the first part of speech F2 that is not the symptom from the second part of speech in the part of speech ranking, and determine whether the part of speech F2 is a check; If yes, a new evaluation score P2=P1+1 is obtained, and starting from the part of speech F2, the first part of speech F3 that is not the inspection is determined, and whether the part of speech F3 is a diagnosis is determined; If yes, a new evaluation score P3=P2+1 is obtained, and starting from the part of speech F3, the first part of speech F4 that is not the diagnosis is determined, and whether the part of speech F4 is treatment is determined; If so, obtain a new evaluation score P4=P3+1.

5. According to claim 4, a multi-dimensional medical education evaluation method based on speech recognition is characterized in that: The process of determining the evaluation score based on the part-of-speech ranking and the first keyword further includes a judgment step: If the part of speech F1 is not a symptom, obtain the timestamp CF1 corresponding to the part of speech F1, obtain the first keyword whose corresponding timestamp is in the timestamp interval [CF1-C, CF1+C], record it as the pending word, obtain the part of speech of the pending word, and C is a preset value; When the part of speech of the pending word is symptom, set the evaluation score P1=0.5 and execute the subsequent steps; when the part of speech of the pending word is not check, set the evaluation score P1=0 and execute the subsequent steps.

6. The multi-dimensional medical education evaluation method based on speech recognition according to claim 5 is characterized in that: The process of determining the evaluation score based on the part-of-speech ranking and the first keyword further includes: When the part of speech F2 is not checked, executing the judging step; When the part of speech F2 is not diagnostic, executing the judging step; When the part of speech F2 is not treatment, the judging step is performed.

7. The multi-dimensional medical education evaluation method based on speech recognition according to claim 5 is characterized in that: The parts of speech of the second keyword and the undetermined word are based on manual annotation.

8. A multi-dimensional medical education evaluation system based on speech recognition, characterized in that: include: Acquisition module: obtaining voice signals of students when they are answering a single medical education evaluation test question, slicing the voice signals to obtain voice segments, and converting the voice segments into text form, which are recorded as text segments; The first keyword module: sorts the characters in a single text segment, groups the characters based on the sorting, determines a pending word based on the similarity between two adjacent groups, obtains a target word based on the pending word, and determines the first keyword based on the position of the target word in the sorting; Second keyword module: extract keywords from the text segment based on a preset keyword list, record them as second keywords, sort the second keywords to obtain keyword sorting; obtain the part of speech of the second keyword, the part of speech includes symptom, examination, diagnosis and treatment; Evaluation module: sorting the parts of speech according to the order of the keyword sorting to obtain a part of speech sorting, and determining an evaluation score based on the part of speech sorting and the first keyword.

Images