Physician evaluation method, device, electronic device and storage medium

Through segmented processing and analysis of video assessment, the problem of low efficiency in offline assessment of pet doctor exams is solved, efficient pet doctor exams are achieved, and user experience is improved.

CN114819474BActive Publication Date: 2024-11-26NEW RUIPENG PET HEALTHCARE GRP CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210222588.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-03-07
Publication Date
2024-11-26
Estimated Expiration
2042-03-07

AI Technical Summary

Technical Problem

The pet doctor exam is currently conducted offline, requiring a lot of human and material resources, and the evaluation efficiency is low and the user experience is poor.

Method used

Through video assessment, the pet doctor's evaluation video is obtained, and the segments are processed into theoretical evaluation and clinical operation evaluation, and speech analysis and action analysis are performed, the evaluation score is calculated, and the evaluation results are determined.

Benefits of technology

The assessment process has been simplified, resources have been saved, user experience has been improved, and efficient assessment of pet doctors has been achieved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114819474B_ABST
    Figure CN114819474B_ABST
Patent Text Reader

Abstract

The embodiment of the present application discloses a physician evaluation method, device, electronic device and storage medium. The method includes: obtaining an evaluation video of a pet physician; determining a first video segment and a second video segment from the evaluation video, wherein the first video segment is a video segment of a theoretical evaluation of the pet physician, and the second video segment is a video segment of a clinical operation evaluation of the pet physician; performing voice analysis on the first video segment to obtain a first evaluation score; extracting the second video segment to obtain multiple frames of images to be identified, wherein the multiple frames of images to be identified record the operation process of a clinical evaluation item of the pet physician; performing motion analysis on the multiple frames of images to be identified to obtain a second evaluation score; determining the evaluation result of the pet physician based on the first evaluation score and the second evaluation score, which not only simplifies the evaluation process and saves resources, but also improves the user experience.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of video processing technology, and in particular to a physician evaluation method, device, electronic device and storage medium. Background Art

[0002] At present, veterinarian examinations are all conducted offline, and veterinarians need to go to designated locations for assessment. This assessment method not only requires a large amount of manpower and material resources, but also has low assessment efficiency and poor user assessment experience. Summary of the invention

[0003] The embodiments of the present application provide a physician evaluation method, device, electronic device and storage medium, which simplify the evaluation process and enhance the user's evaluation experience through video evaluation.

[0004] In a first aspect, an embodiment of the present application provides a physician evaluation method, the method comprising:

[0005] Get the veterinarian's evaluation video;

[0006] Determine a first video segment and a second video segment from the evaluation video, the first video segment being a video segment of the veterinarian's theoretical evaluation, and the second video segment being a video segment of the veterinarian's clinical operation evaluation;

[0007] Performing voice analysis on the first video segment to obtain a first evaluation score;

[0008] Extracting the second video segment to obtain multiple frames of images to be identified, wherein the multiple frames of images to be identified record the operation process of a clinical evaluation item of the veterinarian;

[0009] Performing motion analysis on multiple frames of images to be recognized to obtain a second evaluation score;

[0010] The veterinarian's evaluation result is determined based on the first evaluation score and the second evaluation score.

[0011] In a second aspect, an embodiment of the present application provides a physician evaluation device, the device comprising: an acquisition unit and a processing unit;

[0012] An acquisition unit, used for acquiring the evaluation video of the veterinarian;

[0013] A processing unit, used to determine a first video segment and a second video segment from the evaluation video, wherein the first video segment is a video segment of the veterinarian's theoretical evaluation, and the second video segment is a video segment of the veterinarian's clinical operation evaluation;

[0014] Performing voice analysis on the first video segment to obtain a first evaluation score;

[0015] Extracting the second video segment to obtain multiple frames of images to be identified, wherein the multiple frames of images to be identified record the operation process of a clinical evaluation item of the veterinarian;

[0016] Performing motion analysis on multiple frames of images to be recognized to obtain a second evaluation score;

[0017] The veterinarian's evaluation result is determined based on the first evaluation score and the second evaluation score.

[0018] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, the processor is connected to a memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device performs the method of the first aspect.

[0019] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program enables a computer to execute the method of the first aspect.

[0020] In a fifth aspect, an embodiment of the present application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and is computer-operable to cause the computer to execute the method of the first aspect.

[0021] Implementing the embodiments of the present application has the following beneficial effects:

[0022] It can be seen that in the embodiment of the present application, an evaluation video of a pet doctor is obtained; a first video segment and a second video segment are determined from the evaluation video, wherein the first video segment is a video segment for a theoretical evaluation of the pet doctor, and the second video segment is a video segment for a clinical operation evaluation of the pet doctor; then a voice analysis is performed on the first video segment to obtain a first evaluation score; the second video segment is extracted to obtain a plurality of frames of images to be identified, wherein the plurality of frames of images to be identified record the operation process of a clinical evaluation item of the pet doctor; then a motion analysis is performed on the plurality of frames of images to be identified to obtain a second evaluation score; finally, the evaluation result of the pet doctor is obtained according to the first evaluation score and the second evaluation score. This video-based evaluation method processes the evaluation video of the pet doctor to obtain the corresponding evaluation result, which not only simplifies the evaluation process and saves resources, but also improves the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0024] Figure 1 A schematic diagram of a physician evaluation system provided in an embodiment of the present application;

[0025] Figure 2 A flowchart of a physician evaluation method provided in an embodiment of the present application;

[0026] Figure 3 A flowchart of a method for obtaining similarity based on first text information and a first standard answer text provided in an embodiment of the present application;

[0027] Figure 4a A schematic diagram of a first candidate image provided in an embodiment of the present application;

[0028] Figure 4b A schematic diagram of an operating part contour image provided in an embodiment of the present application;

[0029] Figure 4c A schematic diagram of a first position point provided in an embodiment of the present application;

[0030] Figure 5 A block diagram of the functional units of a physician evaluation device provided in an embodiment of the present application;

[0031] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0033] The terms "first", "second", "third" and "fourth" etc. in the specification, claims and drawings of the present application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0034] Reference to "embodiments" herein means that a particular feature, result, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0035] See also Figure 1 , Figure 1 The following is a schematic diagram of a physician evaluation system provided in an embodiment of the present application. The physician evaluation system includes a pet hospital terminal 10 and a physician evaluation device 20.

[0036] Exemplarily, the physician evaluation device 20 can obtain a pet physician evaluation video from the pet hospital end 10, wherein the evaluation video includes the pet physician's theoretical evaluation stage and clinical operation evaluation stage. The evaluation video can be shot by the pet physician and uploaded to the pet hospital end 10, or it can be captured by the pet hospital using a unified camera device. This application is not limited here.

[0037] Correspondingly, the physician evaluation device 20 segments the evaluation video to obtain a first video segment and a second video segment, wherein the first video segment is used for theoretical evaluation, that is, the first video segment is composed of the theoretical evaluation stage of the pet physician, and the second video segment is used for clinical operation evaluation, that is, the second video segment is composed of the clinical operation evaluation stage of the pet physician.

[0038] Then, the physician evaluation device 20 performs voice analysis on the first video segment to obtain a first evaluation score; the physician evaluation device 20 extracts the second video segment to obtain multiple frames of images to be identified, wherein the multiple frames of images to be identified record the operation process of a clinical evaluation item of the pet physician. It should be noted that in the present application, the voice analysis of the first video segment and the extraction of the second video segment can be performed simultaneously, or the process of voice analysis of the first video segment can be performed first, and then the process of extraction of the second video segment can be performed, or the process of extraction of the second video segment can be performed first, and then the process of voice analysis of the first video segment can be performed. The present application does not limit the execution order. Then, the multiple frames of images to be identified are subjected to motion analysis to obtain a second evaluation score; finally, the evaluation result of the pet physician is determined based on the first evaluation score and the second evaluation score.

[0039] It can be seen that in the embodiment of the present application, an evaluation video of a pet doctor is obtained; a first video segment and a second video segment are determined from the evaluation video, wherein the first video segment is a video segment for a theoretical evaluation of the pet doctor, and the second video segment is a video segment for a clinical operation evaluation of the pet doctor; then a voice analysis is performed on the first video segment to obtain a first evaluation score; the second video segment is extracted to obtain a plurality of frames of images to be identified, wherein the plurality of frames of images to be identified record the operation process of a clinical evaluation item of the pet doctor; then a motion analysis is performed on the plurality of frames of images to be identified to obtain a second evaluation score; finally, the evaluation result of the pet doctor is obtained according to the first evaluation score and the second evaluation score. This video-based evaluation method processes the evaluation video of the pet doctor to obtain the corresponding evaluation result, which not only simplifies the evaluation process and saves resources, but also improves the user experience.

[0040] See also Figure 2 , Figure 2 A flowchart of a physician evaluation method provided in an embodiment of the present application. The method is applied to the above-mentioned physician evaluation device 20. The method includes but is not limited to steps 201-206:

[0041] 201: Get the veterinarian's evaluation video.

[0042] The evaluation video is obtained by filming the theoretical evaluation stage and the clinical operation evaluation stage of the pet doctor. Therefore, the evaluation video includes the theoretical evaluation stage and the clinical operation evaluation stage of the pet doctor.

[0043] 202: Determine a first video segment and a second video segment from the assessment video.

[0044] Among them, the first video segment is used for theoretical evaluation, that is, the first video segment is shot during the theoretical evaluation stage of the pet doctor, and the second video segment is used for clinical operation evaluation, that is, the second video segment is shot during the clinical operation evaluation stage of the pet doctor.

[0045] 203: Perform voice analysis on the first video segment to obtain a first evaluation score.

[0046] In an embodiment of the present application, voice analysis is performed on the first video segment to obtain a first evaluation score, which specifically includes: performing voice recognition on the first video segment to obtain voice stream data; segmenting the voice stream data according to the preset answer time for each question in the theoretical evaluation to obtain at least one sub-voice stream, wherein each sub-voice stream in the at least one sub-voice stream corresponds to a question in the theoretical evaluation; converting the at least one sub-voice stream to obtain at least one text message, wherein at least one text message corresponds one-to-one to at least one sub-voice stream; obtaining a similarity based on the first text message and the first standard answer text, wherein the first text message is any one of the at least one text message, and the first standard answer text is the correct answer to the question corresponding to the sub-voice stream corresponding to the first text message; determining the first evaluation score based on the similarity corresponding to the first text message, that is, determining the first evaluation score of the veterinarian for the question.

[0047] Exemplarily, the first video segment is uploaded to the speech recognition model, and a speech data stream is extracted from the first video segment, where the speech data stream can also be understood as audio data. Then, according to the preset answering time for each question in the theoretical assessment, the speech data stream is segmented to obtain at least one sub-speech stream.

[0048] For example, suppose there are a total of 15 questions in the theoretical assessment, and the order of these 15 questions is 7 multiple-choice questions, 5 true-or-false questions, 2 short-answer questions, and 1 case analysis question. Then, the answering time is pre-set for each question of each question type, where the answering time can include the time used to play the question. For example, the answering time for the multiple-choice questions can be set to 2 minutes, the answering time for the true-or-false questions can be set to 2 minutes, the answering time for the short-answer questions can be set to 10 minutes, and the answering time for the case analysis questions can be set to 15 minutes. Then, the answering time summary set for the 15 questions can be expressed as: [2,2,2,2,2,2,2,2,2,2,2,2,10,10,15], and then the voice data stream is segmented according to the answering time summary set to obtain 15 sub-voice streams.

[0049] Further, the 15 sub-voice streams are transformed to obtain 15 text information. Here, any one of the 15 sub-voice streams is used as an example for explanation. For example, the first sub-voice stream is used as an example. The first sub-voice stream is transformed to obtain text information. Here, the first sub-voice stream can be recognized by natural language processing technology to obtain text information. Then, according to the method of transforming the first sub-voice stream to obtain text information, the 15 sub-voice streams are transformed into text to obtain 15 text information, wherein the 15 text information correspond to the 15 sub-voice streams one by one.

[0050] After obtaining the text information, in an embodiment of the present application, a method for obtaining similarity based on the first text information and the first standard answer text is provided, such as Figure 3 As shown, the method includes steps 301-308:

[0051] 301: Analyze the first text information to obtain a first question text and a first answer text.

[0052] Among them, the first text information is any one of the at least one text information, and the first answer text is the answer of the pet doctor to the question. Here we still use the example of the above 15 text information, that is, the first text information here is any one of the 15 text information, and the first text information is analyzed to obtain the first question text and the first answer text. If the question corresponding to the first text information is the second multiple-choice question, then the first answer text is the answer of the pet doctor to the second multiple-choice question; in addition, since the pre-set answer time includes the time used to play the question, the time value used to play the question can be pre-set, such as pre-setting the answer time for the multiple-choice question to 2 minutes, and pre-setting the time used to play the multiple-choice question to 1 minute, and then analyze the first text information, and use the text located before the end time of playing the multiple-choice question as the played question text, that is, the first question text.

[0053] 302: Determine whether the type of the first question text is a subjective question or an objective question.

[0054] Exemplarily, when the first question text is an objective question, step 303 is executed, and when the first question text is a subjective question, step 304 is executed.

[0055] Exemplarily, to determine the type of the first question text, that is, whether the question type corresponding to the first question text is an objective question or a subjective question, the above example is still used. The objective questions can include the above 7 multiple-choice questions and 5 judgment questions, and the subjective questions can include the above 2 short-answer questions and 1 case analysis question.

[0056] 303: If the first answer text and the first standard answer text are the same, the similarity is determined to be 1; if the first answer text and the first standard answer text are not the same, the similarity is determined to be 0.

[0057] Among them, the first standard answer text is the correct answer to the question corresponding to the sub-voice stream corresponding to the first text information. For example, if the question corresponding to the first text information is multiple-choice question No. 2, then the first standard answer text is the correct answer to multiple-choice question No. 2.

[0058] Exemplarily, when the first question text is an objective question, for example, when the question corresponding to the first question text is multiple-choice question 1, the first answer text identified is [A], and the correct answer to multiple-choice question 1 is obtained. If the correct answer to multiple-choice question 1 is [A], that is, the first standard answer text is [A], then the similarity is determined to be 1; if the correct answer to multiple-choice question 1 is not [A], then the similarity is determined to be 0.

[0059] 304: Extract keywords from the first answer text to obtain multiple semantic keywords and multiple professional terminology keywords.

[0060] In an embodiment of the present application, keywords may be extracted from the first answer text based on the TF-IDF algorithm and the TextRank algorithm in the Jieba word segmentation system, but the present application does not limit this.

[0061] For example, when the first question text is a subjective question, for example, when the question corresponding to the first question text is the short answer question 1, the first answer text is identified as "First, the pancreas has two functions, exocrine and endocrine. Due to the special location of the pancreas and its complex functions, it affects the digestive and metabolic functions when it is sick. Pancreatitis is one of the most common digestive system diseases in dogs and cats. It is mainly divided into acute and chronic types. Then, the common causes of acute pancreatitis are overeating, excessive intake of greasy food, spoiled food, sudden changes in feed, drug effects, and acute pancreatitis. The clinical symptoms are mainly manifested as / loss of appetite / anterior abdominal pain / nausea / vomiting, etc. / the treatment measures for acute pancreatitis can be / supportive therapy / inhibition of pancreatic exocrine secretion / improvement of pancreatic blood circulation". Then, keyword extraction was performed on the first answer text to obtain multiple semantic keywords: "pancreas / function / disease / acute / chronic / cause / clinical / symptoms / treatment / measures" and multiple professional terminology keywords: "acute pancreatitis / overeating / drug effects / loss of appetite / nausea / vomiting / supportive therapy / inhibition of pancreatic exocrine secretion / improvement of pancreatic blood circulation".

[0062] 305: Extract keywords from the first standard answer text to obtain a standard semantic keyword library and a standard professional terminology keyword library.

[0063] Among them, the standard semantic keyword library is composed of multiple standard semantic keywords in the first standard answer text, and the standard professional terminology keyword library is composed of multiple standard professional terminology keywords in the first standard answer text.

[0064] Exemplarily, according to the method of extracting keywords from the first answer text to obtain multiple semantic keywords and multiple professional terminology keywords, keyword extraction is performed on the first standard answer text to obtain a standard semantic keyword library composed of multiple standard semantic keywords: "pancreas / acute / cause / symptoms / diagnosis / treatment / measures" and a professional terminology keyword library composed of multiple standard professional terminology keywords: "overeating / excessive intake of greasy food / frozen food / spoiled food / biliary tract disease / surgery / drug effects / metabolic disorders / loss of appetite / loss of appetite / anterior abdominal pain / abdominal wall tension / sensitivity / nausea / vomiting / gastrointestinal bleeding / jaundice / intestinal paralysis / intestinal infarction / peritonitis / blood tests / enzyme assays / imaging examinations / supportive therapy / inhibition of pancreatic exocrine secretion / inhibition of pancreatic enzyme activity / improvement of pancreatic blood circulation / control of infection".

[0065] 306: Screening multiple semantic keywords in a standard semantic keyword library to obtain at least one candidate semantic keyword.

[0066] In an embodiment of the present application, each of the multiple semantic keywords is screened in a standard semantic keyword library to obtain at least one candidate semantic keyword. In other words, if the semantic keyword can be found in the standard semantic keyword library, the semantic keyword is determined as a candidate semantic keyword. For example, the candidate semantic keywords obtained are "pancreas / acute / cause / symptoms / treatment / measures", that is, there are 6 candidate semantic keywords.

[0067] 307: Screening multiple professional terminology keywords in a standard professional terminology keyword library to obtain at least one candidate professional terminology keyword.

[0068] Exemplarily, each of the multiple professional terminology keywords is screened in the standard semantic keyword library to obtain at least one candidate professional terminology keyword. In other words, if the professional terminology keyword can be found in the standard semantic keyword library, the professional terminology keyword is determined as a candidate professional terminology keyword. For example, the candidate professional terminology keywords obtained include "acute pancreatitis / overeating / drug effect / loss of appetite / nausea / vomiting / supportive therapy / inhibition of pancreatic exocrine secretion / improvement of pancreatic blood circulation", that is, there are 9 candidate professional terminology keywords.

[0069] 308: Obtain a first ratio of the number of candidate semantic keywords to the number of standard semantic keywords and a second ratio of the number of candidate professional terminology keywords to the number of standard professional terminology keywords.

[0070] 309: Determine the similarity according to the first ratio and the second ratio.

[0071] The similarity can be obtained by formula (1):

[0072]

[0073] Among them, K is the similarity, M is the first ratio, N is the second ratio, P is the first weight coefficient, and Q is the second weight coefficient.

[0074] It should be noted that the similarity obtained according to formula (1) has a value range of [0,1], and the greater the number of candidate semantic keywords, the greater the first ratio; the greater the number of candidate professional terminology keywords, the greater the second ratio, which means that the closer the answer content is to the standard answer, the greater the similarity value will be.

[0075] Based on this, in an embodiment of the present application, a method for determining a first evaluation score according to a similarity corresponding to the first text information is provided, and the method includes steps S1-S3:

[0076] S1: Get the score of the first question corresponding to the similarity.

[0077] For example, if the question corresponding to the first question text is the first multiple-choice question, the first question score of the first multiple-choice question is obtained, for example, the first question score may be 2 points; if the question corresponding to the first question text is the first short-answer question, the first question score of the first short-answer question is obtained, for example, the first question score may be 8 points.

[0078] S2: taking the product of the similarity and the score of the first question as the first score corresponding to the first text information.

[0079] For example, if the first question text corresponds to the first multiple-choice question, and the first answer text is the same as the first standard answer text, the similarity is determined to be 1, and then the product of the similarity and the first question score, that is, "1*2", is used as the first score. 1 When , the first score is "8*K 1 ”.

[0080] S3: Sum the multiple first scores corresponding to the multiple text information to obtain a first evaluation score.

[0081] Exemplarily, according to the method of obtaining the first score based on the similarity corresponding to the first text information and the score of the first question, multiple similarities corresponding to multiple text information and multiple first question scores are calculated to obtain multiple first scores; then the multiple first scores are summed up as the first evaluation score.

[0082] 204: Extract the second video segment to obtain multiple frames of images to be recognized.

[0083] Among them, multiple frames of images to be identified record the operation process of a clinical evaluation project of a veterinarian.

[0084] Exemplarily, the multiple frames of images to be identified record the operation process of a veterinarian suturing a pet's wound.

[0085] It should be noted that this application is only described by taking the example that the veterinarian only evaluates one clinical evaluation item during the evaluation process. In actual application, the veterinarian can evaluate multiple clinical evaluation items. When evaluating multiple clinical items, multiple second video segments can be identified, and each second video segment records the operation process of one clinical evaluation item. The processing process of each second video segment is similar to the content in step 204 and will not be described again.

[0086] 205: Perform motion analysis on the multiple frames of images to be recognized to obtain a second evaluation score.

[0087] In an embodiment of the present application, a method for performing motion analysis on multiple frames of images to be recognized to obtain a second evaluation score is provided. The method specifically includes steps A1-A3:

[0088] A1: Perform three-dimensional reconstruction on multiple frames of images to be identified to obtain a three-dimensional target image.

[0089] The three-dimensional target image includes the operation site in the clinical assessment operation project. In the embodiment of the present application, three-dimensional reconstruction is performed on multiple frames of images to be identified to obtain a three-dimensional target image, which specifically includes:

[0090] Screen multiple frames of images to be identified to obtain at least one candidate image, wherein the candidate image is an image containing the entire operation part; perform contour scanning on the first candidate image to obtain an operation part contour image corresponding to the first candidate image, wherein the first candidate image is any one of the at least one candidate image; determine a first position point from the operation part contour image, wherein the first position point is the contact point between the hand or the instrument held by the hand of the veterinarian and the operation part in the clinical evaluation project; determine at least one first position point from at least one operation part contour image corresponding to at least one candidate image, wherein at least one first position point corresponds one-to-one to at least one candidate image; connect at least one first position point in sequence according to the time series of at least one candidate image to determine the depth information of the operation part; obtain a three-dimensional target image based on the depth information and the operation part contour image.

[0091] For ease of understanding, this application uses the example of suturing the abdomen of a pet as an example. For example, since the multiple frames of images to be identified record the operation process of a clinical assessment item of the pet doctor, that is, the entire operation process of the pet doctor suturing the wound on the pet's abdomen, it is necessary to screen the multiple frames of images to be identified to obtain at least one candidate image containing all the features of the operation site, and the candidate image contains the wound site on the pet's abdomen; for example, the images that can be screened out include the following: Figure 4a The first candidate image is then scanned to obtain an operation site contour image, that is, a contour image of the pet's abdominal wound site. The operation site contour image is as shown in FIG. Figure 4b Then, the first position point is determined from the contour image of the wound site, that is, the contact point between the suturing instrument held by the veterinarian and the wound site. The first position point is as shown in FIG. Figure 4c As shown; then according to the method of determining the first position point from the wound site contour image, at least one first position point is determined from at least one wound site contour image corresponding to at least one candidate image; then the at least one first position point is sequentially connected according to the time series of at least one candidate image to determine the depth information of the wound site; the depth of the wound site is determined according to the depth information, and finally a three-dimensional target image is constructed according to the depth of the wound site and the wound site contour image.

[0092] A2: Mark the three-dimensional target image to obtain multiple key points for the operation site.

[0093] In an embodiment of the present application, the contact points between the veterinarian's hands or hand-held instruments and the operating parts in the clinical evaluation items in the three-dimensional target image are marked, and the marked multiple contact points are determined as key points for the operating parts.

[0094] Exemplarily, multiple contact points between the suturing instrument held by the veterinarian and the abdomen of the pet in the three-dimensional target image are identified, and the multiple contact points are determined as multiple key points.

[0095] A3: Get the second assessment score based on multiple key points.

[0096] Based on this, in an embodiment of the present application, a method for obtaining a second evaluation score according to multiple key points is provided, and the method specifically includes steps B1-B6:

[0097] B1: Establish a spatial rectangular coordinate system with the center of the operating part as the coordinate origin.

[0098] Exemplarily, the center of the wound site can be found based on the depth of the wound site and the contour image of the wound site. Then, with the center of the wound site as the coordinate origin, the direction parallel to the ground and pointing directly forward as the X-axis, the direction parallel to the ground and pointing horizontally to the right as the Y-axis, and the direction perpendicular to the ground and pointing directly upward as the Z-axis, a three-dimensional rectangular coordinate system is established.

[0099] B2: Obtain the coordinates of the first key point in the three-dimensional rectangular coordinate system and the coordinates of the reference key point.

[0100] Wherein, the first key point is any one of multiple key points, and the key point is the reference position corresponding to the first key point at the operation site;

[0101] Exemplarily, during the process of suturing a pet's abdominal wound, in practical applications, in order to present a better wound healing effect, there will be a starting point, an ending point of suturing, and the reference positions of each suture point, that is, the reference positions of multiple key points. Therefore, obtain the coordinates of the first key point and the coordinates of the reference key point in the three-dimensional rectangular coordinate system, and the coordinates of the reference key point are the preset reference positions corresponding to the first key point at the operation site.

[0102] B3: Calculate the difference distance between the first key point and the reference key point according to the coordinates of the first key point and the coordinates of the reference key point.

[0103] B4: Obtain at least one abnormal key point from multiple key points.

[0104] Wherein, for any one of the at least one abnormal key points, the corresponding difference distance is greater than or equal to the threshold.

[0105] B5: Calculate the completion degree of the veterinarian according to the number of abnormal key points and the first time.

[0106] Wherein, the completion degree represents the completion situation of the veterinarian for the above-mentioned clinical evaluation items, and the first time is the time difference between the first moment corresponding to the last frame of the multiple frames of images to be recognized and the second moment corresponding to the first frame of the images to be recognized.

[0107] Wherein, the completion degree can be obtained through formula (2):

[0108]

[0109] Wherein, W is the completion degree, 0 < c < 1, 0 < d < 1, x is the number of abnormal key points, t is the first time, in seconds, i is the third weight coefficient, and j is the fourth weight coefficient.

[0110] It should be noted that the completion value obtained according to formula (2) is in the range of [0,1], and the more abnormal key points there are and the longer the first time is, the smaller the completion value of the veterinarian will be.

[0111] B6: The product of the completion rate and the score of the second question is taken as the second assessment score.

[0112] The score of the second question is the score corresponding to the clinical assessment item. For example, if the score of the clinical assessment item of suturing the abdominal wound of a pet is 30 points, that is, the score of the second question is 30 points, then the second assessment score is "W*30".

[0113] 206: Determine the evaluation result of the veterinarian according to the first evaluation score and the second evaluation score.

[0114] In the embodiment of the present application, the first evaluation score and the second evaluation score are summed to obtain a target evaluation score; then the evaluation result of the veterinarian is determined according to the target evaluation score. For example, if the target evaluation score is in the first interval, the evaluation result of the veterinarian is excellent; if the target evaluation score is in the second interval, the evaluation result of the veterinarian is good; if the target evaluation score is in the third interval, the evaluation result of the veterinarian is qualified; if the target evaluation score is in the fourth interval, the evaluation result of the veterinarian is unqualified, that is, the evaluation fails.

[0115] It can be seen that in the embodiment of the present application, an evaluation video of a pet doctor is obtained; a first video segment and a second video segment are determined from the evaluation video, wherein the first video segment is a video segment for a theoretical evaluation of the pet doctor, and the second video segment is a video segment for a clinical operation evaluation of the pet doctor; then a voice analysis is performed on the first video segment to obtain a first evaluation score; the second video segment is extracted to obtain a plurality of frames of images to be identified, wherein the plurality of frames of images to be identified record the operation process of a clinical evaluation item of the pet doctor; then a motion analysis is performed on the plurality of frames of images to be identified to obtain a second evaluation score; finally, the evaluation result of the pet doctor is obtained according to the first evaluation score and the second evaluation score. This video-based evaluation method processes the evaluation video of the pet doctor to obtain the corresponding evaluation result, which not only simplifies the evaluation process and saves resources, but also improves the user experience.

[0116] See also Figure 5 , Figure 5 This is a functional unit block diagram of a physician evaluation device provided in an embodiment of the present application. The physician evaluation device 500 includes: an acquisition unit 501 and a processing unit 502;

[0117] The acquisition unit 501 is used to acquire the evaluation video of the veterinarian;

[0118] The processing unit 502 is used to determine a first video segment and a second video segment from the evaluation video, wherein the first video segment is a video segment of the veterinarian's theoretical evaluation, and the second video segment is a video segment of the veterinarian's clinical operation evaluation;

[0119] Performing voice analysis on the first video segment to obtain a first evaluation score;

[0120] Extracting the second video segment to obtain multiple frames of images to be identified, wherein the multiple frames of images to be identified record the operation process of a clinical evaluation item of the veterinarian;

[0121] Performing motion analysis on multiple frames of images to be recognized to obtain a second evaluation score;

[0122] The veterinarian's evaluation result is determined based on the first evaluation score and the second evaluation score.

[0123] In one embodiment of the present application, in performing speech analysis on the first video segment to obtain the first evaluation score, the processing unit 502 is specifically configured to:

[0124] Performing voice recognition on the first video segment to obtain a voice data stream;

[0125] According to the preset answering time of each question in the theoretical assessment, the voice data stream is divided to obtain at least one sub-voice stream, and each sub-voice stream in the at least one sub-voice stream corresponds to each question in the theoretical assessment one by one;

[0126] Converting at least one sub-voice stream to obtain at least one text message, wherein the at least one text message corresponds to the at least one sub-voice stream;

[0127] A similarity is obtained according to the first text information and the first standard answer text, wherein the first text information is any one of the at least one text information, and the first standard answer text is a correct answer to the question corresponding to the first text information;

[0128] A first evaluation score is determined according to the similarity corresponding to the first text information.

[0129] In one embodiment of the present application, in terms of obtaining the similarity according to the first text information and the first standard answer text, the processing unit 502 is specifically configured to:

[0130] Analyze the first text information to obtain a first question text and a first answer text;

[0131] When the first question text is an objective question, and the first answer text is the same as the first standard answer text, the similarity is determined to be 1; if the first answer text is not the same as the first standard answer text, the similarity is determined to be 0.

[0132] In one embodiment of the present application, in terms of obtaining the similarity according to the first text information and the first standard answer text, the processing unit 502 is specifically configured to:

[0133] Analyze the first text information to obtain a first question text and a first answer text;

[0134] When the first question text is a subjective question, keyword extraction is performed on the first answer text to obtain multiple semantic keywords and multiple professional terminology keywords;

[0135] Extract keywords from the first standard answer text to obtain a standard semantic keyword library and a standard professional terminology keyword library, wherein the standard semantic keyword library is composed of multiple standard semantic keywords in the first standard answer text, and the standard professional terminology keyword library is composed of multiple standard professional terminology keywords in the first standard answer text;

[0136] Screening the multiple semantic keywords in a standard semantic keyword library to obtain at least one candidate semantic keyword;

[0137] Screening multiple professional term keywords in a standard professional term keyword library to obtain at least one candidate professional term keyword;

[0138] Obtaining a first ratio of the number of candidate semantic keywords to the number of standard semantic keywords and a second ratio of the number of candidate professional terminology keywords to the number of standard professional terminology keywords;

[0139] Determining a similarity based on the first ratio and the second ratio;

[0140] Among them, the similarity can be obtained by formula (3):

[0141]

[0142] Among them, K is the similarity, M is the first ratio, N is the second ratio, P is the first weight coefficient, and Q is the second weight coefficient.

[0143] In one embodiment of the present application, in determining the first evaluation score according to the similarity corresponding to the first text information, the processing unit 502 is specifically configured to:

[0144] Get the score of the first question corresponding to the similarity;

[0145] The product of the similarity and the first question score is used as the first score corresponding to the first text information;

[0146] The multiple first scores corresponding to the multiple text information are summed up to obtain the first evaluation score.

[0147] In an embodiment of the present application, in terms of performing action analysis on multiple frames of images to be recognized to obtain a second evaluation score, the processing unit 502 is specifically configured to:

[0148] Perform three-dimensional reconstruction on multiple frames of images to be recognized to obtain a three-dimensional target image, where the three-dimensional target image includes the operation part in the clinical evaluation operation item;

[0149] Mark the three-dimensional target image to obtain multiple key points for the operation part;

[0150] Obtain the second evaluation score according to the multiple key points.

[0151] In an embodiment of the present application, in terms of obtaining the second evaluation score according to the multiple key points, the processing unit 502 is specifically configured to:

[0152] Establish a spatial rectangular coordinate system with the center of the operation part as the coordinate origin;

[0153] Obtain the coordinates of the first key point in the spatial rectangular coordinate system and the coordinates of the reference key point, where the first key point is any one of the multiple key points, and the reference key point is the reference position corresponding to the first key point in the operation part;

[0154] Calculate the difference distance between the first key point and the reference key point according to the coordinates of the first key point and the coordinates of the reference key point;

[0155] Obtain at least one abnormal key point from the multiple key points, where the difference distance corresponding to any one of the at least one abnormal key points is greater than or equal to the threshold;

[0156] Calculate the completion degree of the veterinarian according to the number of abnormal key points and the first time, where the completion degree represents the completion situation of the veterinarian for the clinical evaluation item, and the first time is the time difference between the first moment corresponding to the last frame of the images to be recognized and the second moment corresponding to the first frame of the images to be recognized;

[0157] Take the product of the completion degree and the second question score as the second evaluation score, where the second question score is the score corresponding to the clinical evaluation item;

[0158] Among them, the completion degree can be obtained through formula (4):

[0159]

[0160] Among them, W is the completion degree, 0 < c < 1, 0 < d < 1, x is the number of abnormal key points, t is the first time, in seconds, i is the third weight coefficient, and j is the fourth weight coefficient.

[0161] Refer to Figure 6, Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device 600 includes a transceiver 601, a processor 602 and a memory 603. They are connected via a bus 604. The memory 603 is used to store computer programs and data, and can transmit the data stored in the memory 603 to the processor 602.

[0162] The processor 602 is used to read the computer program in the memory 603 and perform the following operations:

[0163] Control transceiver 601 to obtain the evaluation video of the veterinarian;

[0164] Determine a first video segment and a second video segment from the evaluation video, the first video segment being a video segment of the veterinarian's theoretical evaluation, and the second video segment being a video segment of the veterinarian's clinical operation evaluation;

[0165] Performing voice analysis on the first video segment to obtain a first evaluation score;

[0166] Extracting the second video segment to obtain multiple frames of images to be identified, wherein the multiple frames of images to be identified record the operation process of a clinical evaluation item of the veterinarian;

[0167] Performing motion analysis on multiple frames of images to be recognized to obtain a second evaluation score;

[0168] The veterinarian's evaluation result is determined based on the first evaluation score and the second evaluation score.

[0169] In one embodiment of the present application, in performing voice analysis on the first video segment to obtain a first evaluation score, the processor 602 is specifically configured to perform the following steps:

[0170] Performing voice recognition on the first video segment to obtain a voice data stream;

[0171] According to the preset answering time of each question in the theoretical assessment, the voice data stream is divided to obtain at least one sub-voice stream, and each sub-voice stream in the at least one sub-voice stream corresponds to each question in the theoretical assessment one by one;

[0172] Converting at least one sub-voice stream to obtain at least one text message, wherein the at least one text message corresponds to the at least one sub-voice stream;

[0173] A similarity is obtained according to the first text information and the first standard answer text, wherein the first text information is any one of the at least one text information, and the first standard answer text is a correct answer to the question corresponding to the first text information;

[0174] A first evaluation score is determined according to the similarity corresponding to the first text information.

[0175] In one embodiment of the present application, in terms of obtaining the similarity according to the first text information and the first standard answer text, the processor 602 is specifically configured to perform the following steps:

[0176] Analyze the first text information to obtain a first question text and a first answer text;

[0177] When the first question text is an objective question, and the first answer text is the same as the first standard answer text, the similarity is determined to be 1; if the first answer text is not the same as the first standard answer text, the similarity is determined to be 0.

[0178] In one embodiment of the present application, in terms of obtaining the similarity according to the first text information and the first standard answer text, the processor 602 is specifically configured to perform the following steps:

[0179] Analyze the first text information to obtain a first question text and a first answer text;

[0180] When the first question text is a subjective question, keyword extraction is performed on the first answer text to obtain multiple semantic keywords and multiple professional terminology keywords;

[0181] Extract keywords from the first standard answer text to obtain a standard semantic keyword library and a standard professional terminology keyword library, wherein the standard semantic keyword library is composed of multiple standard semantic keywords in the first standard answer text, and the standard professional terminology keyword library is composed of multiple standard professional terminology keywords in the first standard answer text;

[0182] Screening the multiple semantic keywords in a standard semantic keyword library to obtain at least one candidate semantic keyword;

[0183] Screening multiple professional term keywords in a standard professional term keyword library to obtain at least one candidate professional term keyword;

[0184] Obtaining a first ratio of the number of candidate semantic keywords to the number of standard semantic keywords and a second ratio of the number of candidate professional terminology keywords to the number of standard professional terminology keywords;

[0185] Determining a similarity based on the first ratio and the second ratio;

[0186] Determine similarity based on the number of candidate semantic keywords and the number of candidate professional terminology keywords;

[0187] Among them, the similarity can be obtained by formula (5):

[0188]

[0189] Among them, K is the similarity, M is the first ratio, N is the second ratio, P is the first weight coefficient, and Q is the second weight coefficient.

[0190] In one embodiment of the present application, in determining the first evaluation score according to the similarity corresponding to the first text information, the processor 602 is specifically configured to perform the following steps:

[0191] Get the score of the first question corresponding to the similarity;

[0192] The product of the similarity and the first question score is used as the first score corresponding to the first text information;

[0193] The multiple first scores corresponding to the multiple text information are summed up to obtain the first evaluation score.

[0194] In one embodiment of the present application, in performing motion analysis on multiple frames of images to be recognized to obtain a second evaluation score, the processor 602 is specifically configured to perform the following steps:

[0195] Perform three-dimensional reconstruction on multiple frames of images to be identified to obtain a three-dimensional target image, wherein the three-dimensional target image includes the operation site in the clinical assessment operation item;

[0196] Mark the three-dimensional target image to obtain multiple key points for the operation part;

[0197] Based on multiple key points, a second assessment score is obtained.

[0198] In one embodiment of the present application, in terms of obtaining the second evaluation score according to the multiple key points, the processor 602 is specifically configured to perform the following steps:

[0199] Taking the center of the operating part as the coordinate origin, establish a spatial rectangular coordinate system;

[0200] Obtaining coordinates of a first key point and a reference key point in a spatial rectangular coordinate system, wherein the first key point is any one of the plurality of key points, and the reference key point is a reference position corresponding to the first key point at the operating part;

[0201] Calculate the difference distance between the first key point and the reference key point according to the coordinates of the first key point and the coordinates of the reference key point;

[0202] Acquire at least one abnormal key point from the multiple key points, wherein a difference distance corresponding to any one of the at least one abnormal key point is greater than or equal to a threshold;

[0203] Calculate the completion degree of the veterinarian based on the number of abnormal key points and the first time. The completion degree represents the completion situation of the veterinarian for the clinical assessment items. The first time is the time difference between the first moment corresponding to the last frame of the multiple frames of待识别图像 (to-be-recognized images) and the second moment corresponding to the first frame of the待识别图像 (to-be-recognized images).

[0204] Take the product of the completion degree and the second question score as the second assessment score. The second question score is the score corresponding to the clinical assessment item.

[0205] Among them, the completion degree can be obtained through formula (6):

[0206]

[0207] Among them, W is the completion degree, 0 < c < 1, 0 < d < 1, x is the number of abnormal key points, t is the first time, in seconds, i is the third weight coefficient, and j is the fourth weight coefficient.

[0208] Specifically, the above transceiver 601 can be Figure 5 the acquisition unit 501 of the physician assessment device 500 in the embodiment of Figure 5 and the above processor 602 can be

[0209] It should be understood that the electronic devices in this application may include smartphones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, handheld computers, laptop computers, mobile Internet devices MID (Mobile Internet Devices, abbreviated as: MID), or wearable devices, etc. The above electronic devices are only examples, not exhaustive, and include but are not limited to the above electronic devices. In practical applications, the above electronic devices may also include: intelligent vehicle terminals, computer devices, etc.

[0210] This application embodiment also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement part or all of the steps of any one of the physician assessment methods recorded in the above method embodiments.

[0211] This application embodiment also provides a computer program product. The computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any one of the physician assessment methods recorded in the above method embodiments.

[0212] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present application.

[0213] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0214] In the several embodiments provided in the present application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0215] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0216] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of a software program module.

[0217] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of each embodiment method of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0218] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0219] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A physician evaluation method, characterized in that: The method includes: Obtaining the assessment video of the pet doctor; Determining a first video segment and a second video segment from the assessment video, where the first video segment is the video segment of the theoretical assessment of the pet doctor, and the second video segment is the video segment of the clinical operation assessment of the pet doctor; Performing speech analysis on the first video segment to obtain a first assessment score; Extracting the second video segment to obtain multiple frames of images to be recognized, and the multiple frames of images to be recognized record the operation process of a clinical assessment item of the pet doctor; Performing three-dimensional reconstruction on the multiple frames of images to be recognized to obtain a three-dimensional target image, and the three-dimensional target image includes the operation part in the clinical assessment item; Marking the three-dimensional target image to obtain multiple key points for the operation part; Taking the center of the operation part as the coordinate origin to establish a space rectangular coordinate system; Obtaining the coordinates of a first key point in the space rectangular coordinate system and the coordinates of a reference key point, where the first key point is any one of the multiple key points, and the reference key point is the reference position corresponding to the first key point in the operation part; Calculating the difference distance between the first key point and the reference key point according to the coordinates of the first key point and the coordinates of the reference key point; Obtaining at least one abnormal key point from the multiple key points, where the difference distance corresponding to any one of the at least one abnormal key points is greater than or equal to a threshold; Calculating the completion degree of the pet doctor according to the number of abnormal key points and a first time, where the completion degree represents the completion situation of the pet doctor for the clinical assessment item, and the first time is the time difference between the first moment corresponding to the last frame of the multiple frames of images to be recognized and the second moment corresponding to the first frame of the multiple frames of images to be recognized; Taking the product of the completion degree and the second question score as the second assessment score, where the second question score is the score corresponding to the clinical assessment item; Wherein, the completion degree satisfies the following formula: Where W is the completion degree, 0 < c < 1, 0 < d < 1, x is the number of abnormal key points, t is the first time in seconds, i is the third weight coefficient, and j is the fourth weight coefficient; Determining the assessment result of the pet doctor according to the first assessment score and the second assessment score.

2. The method according to claim 1, characterized in that: The performing speech analysis on the first video segment to obtain a first assessment score includes: Performing speech recognition on the first video segment to obtain a speech data stream; Dividing the speech data stream according to the preset answering time for each question in the theoretical assessment to obtain at least one sub-speech stream, and each sub-speech stream in the at least one sub-speech stream corresponds to each question in the theoretical assessment one by one; Converting the at least one sub-speech stream to obtain at least one text information, and the at least one text information corresponds to the at least one sub-speech stream one by one; Obtaining a similarity based on a first text message and a first standard answer text, wherein the first text message is any one of the at least one text message, and the first standard answer text is a correct answer to a question corresponding to the first text message; The first assessment score is determined according to the similarity corresponding to the first text information.

3. The method according to claim 2, characterized in that The obtaining of similarity according to the first text information and the first standard answer text includes: Analyze the first text information to obtain a first question text and a first answer text; When the first question text is an objective question, and the first answer text is the same as the first standard answer text, the similarity is determined to be 1; if the first answer text is different from the first standard answer text, the similarity is determined to be 0.

4. The method according to claim 2, characterized in that: The obtaining of similarity according to the first text information and the first standard answer text includes: Analyze the first text information to obtain a first question text and a first answer text; When the first question text is a subjective question, performing keyword extraction on the first answer text to obtain a plurality of semantic keywords and a plurality of professional terminology keywords; Perform keyword extraction on the first standard answer text to obtain a standard semantic keyword library and a standard professional terminology keyword library, wherein the standard semantic keyword library is composed of a plurality of standard semantic keywords in the first standard answer text, and the standard professional terminology keyword library is composed of a plurality of standard professional terminology keywords in the first standard answer text; Screening the plurality of semantic keywords in the standard semantic keyword library to obtain at least one candidate semantic keyword; Screening the plurality of professional terminology keywords in the standard professional terminology keyword library to obtain at least one candidate professional terminology keyword; Obtaining a first ratio of the number of candidate semantic keywords to the number of standard semantic keywords and a second ratio of the number of candidate professional terminology keywords to the number of standard professional terminology keywords; determining the similarity according to the first ratio and the second ratio; The similarity satisfies the following formula: Among them, K is the similarity, M is the first ratio, N is the second ratio, P is the first weight coefficient, and Q is the second weight coefficient.

5. The method according to any one of claims 2 to 4, characterized in that: Determining the first evaluation score according to the similarity corresponding to the first text information includes: Obtaining a first question score corresponding to the similarity; The product of the similarity and the first question score is used as a first score corresponding to the first text information; The multiple first scores corresponding to the multiple text information are summed up to obtain the first evaluation score.

6. A physician evaluation device, characterized in that: The device comprises: an acquisition unit and a processing unit; The acquisition unit is used to acquire the evaluation video of the veterinarian; The processing unit is used to determine a first video segment and a second video segment from the evaluation video, wherein the first video segment is a video segment of the theoretical evaluation of the veterinarian, and the second video segment is a video segment of the clinical operation evaluation of the veterinarian; Performing voice analysis on the first video segment to obtain a first evaluation score; Extract the second video segment to obtain multiple frames of images to be recognized, which record the operation process of a clinical assessment item of the pet doctor; Perform three-dimensional reconstruction on the multiple frames of images to be recognized to obtain a three-dimensional target image, which includes the operation part in the clinical assessment item; Mark the three-dimensional target image to obtain multiple key points for the operation part; Establish a space rectangular coordinate system with the center of the operation part as the coordinate origin; Obtain the coordinates of the first key point in the space rectangular coordinate system and the coordinates of the reference key point, where the first key point is any one of the multiple key points, and the reference key point is the reference position corresponding to the first key point in the operation part; Calculate the difference distance between the first key point and the reference key point according to the coordinates of the first key point and the coordinates of the reference key point; Obtain at least one abnormal key point from the multiple key points, where the difference distance corresponding to any one of the at least one abnormal key points is greater than or equal to the threshold; Calculate the completion degree of the pet doctor according to the number of abnormal key points and the first time, where the completion degree represents the completion situation of the pet doctor for the clinical assessment item, and the first time is the time difference between the first moment corresponding to the last frame of the images to be recognized and the second moment corresponding to the first frame of the images to be recognized; Take the product of the completion degree and the second question score as the second assessment score, where the second question score is the score corresponding to the clinical assessment item; Wherein, the completion degree satisfies the following formula: Where W is the completion degree, 0 < c < 1, 0 < d < 1, x is the number of abnormal key points, t is the first time in seconds, i is the third weight coefficient, and j is the fourth weight coefficient; Determine the assessment result of the pet doctor according to the first assessment score and the second assessment score.

7. An electronic device, characterized in that: Including: A processor and a memory, the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory so that the electronic device executes the method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by the processor to implement the method according to any one of claims 1-5.