Online evaluation system, method, electronic device and storage medium for pet doctors

Abstract

The present application provides a system, method, electronic device and storage medium for online assessment of pet doctors. The system verifies the identities of the pet doctors and the assessors, and then, when the pet doctors and the assessors log in to the system, selects multiple assessment questions from a preset assessment question bank based on the pet doctors' basic information, historical diagnosis records and online community evaluations; obtains first voice data of the assessor describing any one of the multiple assessment questions to the pet doctors; obtains the response time of the pet doctors to any one of the assessment questions based on the first voice data, and determines whether the pet doctors have cheated based on the response time. The embodiment of the present application uses the response time of the pet doctors to each assessment question to determine whether the pet doctors have cheated, which is conducive to solving the problem of difficulty in identifying cheating in online assessments.

Description

Technical Field

[0001] The present application relates to the field of computer network technology, and in particular to an online evaluation system, method, electronic device and storage medium for veterinarians. Background Art

[0002] With the development of Internet technology, the trend of online assessment in schools, hospitals and other industries has become very obvious, and the assessment methods are also diverse, such as online question banks, questionnaires, computer-based exams, etc. At present, there are also some online assessment systems for pet doctors, which can meet the basic requirements of pet doctor titles and business ability assessments. However, in the absence of invigilators or invigilation methods, the existing online assessment systems for pet doctors have certain cheating risks. How to identify cheating in the assessment to ensure the fairness of the assessment is an urgent problem to be solved. Summary of the invention

[0003] In response to the above problems, the present application provides a system, method, electronic device and storage medium for online evaluation of pet physicians, which are conducive to cheating detection in online evaluation of pet physicians.

[0004] To achieve the above-mentioned purpose, the first aspect of the embodiment of the present application provides an online evaluation system for pet doctors, which includes a video acquisition module, an identity authentication module, a test question selection module, a voice acquisition module, a cheating analysis module and a blacklist module, and each module is communicatively connected; wherein:

[0005] A video acquisition module, used for acquiring a first video image of the veterinarian and a second video image of the assessor;

[0006] An identity verification module is used to obtain a first facial feature of the pet physician based on a first video image, and to obtain a second facial feature of the reviewer based on a second video image; and to receive a first login request submitted by the pet physician and a second login request submitted by the reviewer, to authenticate the pet physician according to the first login request and the first facial feature, and to allow the pet physician to log in to the pet physician online evaluation system if the identity verification is successful, to authenticate the reviewer according to the second login request and the second facial feature, and to allow the reviewer to log in to the pet physician online evaluation system if the identity verification is successful;

[0007] The test question selection module is used to select multiple test questions from a preset test question bank based on the basic information of the veterinarian, historical diagnosis records and online community evaluations, and display the multiple test questions in sequence on the assessor's terminal device;

[0008] A voice acquisition module, used to acquire first voice data of an assessor describing any one of a plurality of assessment topics to a veterinarian;

[0009] A cheating analysis module, used to obtain the response time of the veterinarian to any assessment question based on the first voice data, and determine whether the veterinarian has cheated according to the response time;

[0010] The blacklist module is used to end the evaluation and add the veterinarian to the blacklist if the veterinarian is found to have cheated.

[0011] In combination with the first aspect, in a possible implementation, the cheating analysis module includes a cheating analysis unit. In determining whether the pet doctor has cheated according to the reply time, the cheating analysis unit is specifically used to:

[0012] Obtaining an end time point of the first voice data;

[0013] Obtaining the starting time point of the second voice data of the veterinarian answering any assessment question;

[0014] When the response time is greater than or equal to the first preset time, and the time interval between the end time point and the start time point is greater than or equal to the second preset time, it is determined that the veterinarian has cheated.

[0015] In combination with the first aspect, in a possible implementation, the cheating analysis module further includes a duration prediction unit. In terms of obtaining the duration of the pet doctor's answer to any assessment question based on the first voice data, the duration prediction unit is specifically used to:

[0016] Obtaining the speech speed information of the veterinarian based on the reference voice data;

[0017] Obtaining the historical average answer length of at least one assessment question in the preset assessment question bank that belongs to the same question type as any assessment question;

[0018] Predict the response time based on speech rate information and historical average response length.

[0019] In combination with the first aspect, in a possible implementation manner, when any assessment topic is not the first assessment topic among multiple assessment topics, in predicting the response duration according to the speech speed information and the historical average response length, the duration prediction unit is specifically used to:

[0020] Obtain the correlation between any assessment question and the previous assessment question of any assessment question;

[0021] Determine the correction constant based on the correlation between any assessment question and the previous assessment question;

[0022] The response duration is calculated using speech rate information, historical average response length, and a correction constant.

[0023] In combination with the first aspect, in a possible implementation manner, the duration prediction unit is further configured to:

[0024] Get reference answers to any assessment question;

[0025] The first preset duration is calculated using the speech rate information and the reference answer.

[0026] In combination with the first aspect, in a possible implementation, the first login request includes the first identification information of the pet physician end of the pet physician online evaluation system and the first mobile phone number of the pet physician for receiving the SMS verification code, and the identity authentication module also includes a pet physician identity authentication unit. In terms of authenticating the pet physician according to the first login request and the first facial feature, the pet physician identity authentication unit is specifically used to:

[0027] Generate a first SMS verification code, and establish a four-element association relationship between the first SMS verification code, the first mobile phone number, the first identification information, and the first facial feature to be matched of the veterinarian, where the first facial feature to be matched is a facial feature of a pre-extracted template facial image of the veterinarian;

[0028] Send a first SMS verification code to the first mobile phone number;

[0029] Receiving a third login request submitted by the veterinarian through the veterinarian terminal, the third login request including the first mobile phone number to be verified, the first SMS verification code to be verified, and the first identification information to be verified;

[0030] The third login request is verified using the four-element association relationship, and when the first mobile phone number to be verified, the first SMS verification code to be verified, the first identification information to be verified, and the first facial feature match the first mobile phone number, the first SMS verification code, the first identification information, and the first facial feature to be matched respectively, it is determined that the veterinarian's identity authentication is passed;

[0031] If any one of the first mobile phone number to be verified and the first mobile phone number, the first SMS verification code to be verified and the first SMS verification code, the first identification information to be verified and the first identification information, and the first facial feature and the first facial feature to be matched does not match, it is determined that the veterinarian's identity authentication has failed.

[0032] A second aspect of the present application embodiment provides a method for online evaluation of pet doctors, the method comprising:

[0033] capturing a first video image of the veterinarian and a second video image of the assessor;

[0034] Obtaining a first facial feature of the pet physician based on the first video image, and obtaining a second facial feature of the reviewer based on the second video image; and receiving a first login request submitted by the pet physician and a second login request submitted by the reviewer, performing identity authentication on the pet physician according to the first login request and the first facial feature, and allowing the pet physician to log in to the pet physician online assessment system if the identity authentication is passed, performing identity authentication on the reviewer according to the second login request and the second facial feature, and allowing the reviewer to log in to the pet physician online assessment system if the identity authentication is passed;

[0035] Based on the basic information of the veterinarian, historical diagnosis records and online community evaluations, multiple evaluation questions are selected from the preset evaluation question bank, and the multiple evaluation questions are displayed in sequence on the assessor's terminal device;

[0036] Acquire first voice data of an assessor describing any one of a plurality of assessment topics to a veterinarian;

[0037] Obtaining the length of time it takes the veterinarian to answer any assessment question based on the first voice data, and determining whether the veterinarian has cheated based on the length of time it takes to answer the question;

[0038] If the veterinarian is found to have cheated, the assessment will be terminated and the veterinarian will be added to the blacklist.

[0039] In conjunction with the second aspect, in a possible implementation, determining whether the veterinarian has cheated based on the length of the response time includes:

[0040] Obtaining an end time point of the first voice data;

[0041] Obtaining the starting time point of the second voice data of the veterinarian answering any assessment question;

[0042] When the response time is greater than or equal to the first preset time, and the time interval between the end time point and the start time point is greater than or equal to the second preset time, it is determined that the veterinarian has cheated.

[0043] In conjunction with the second aspect, in a possible implementation, obtaining the length of time it takes the veterinarian to answer any assessment question based on the first voice data includes:

[0044] Obtaining the speech speed information of the veterinarian based on the reference voice data;

[0045] Obtaining the historical average answer length of at least one assessment question in the preset assessment question bank that belongs to the same question type as any assessment question;

[0046] Predict the response time based on speech rate information and historical average response length.

[0047] In conjunction with the second aspect, in a possible implementation, when any assessment question is not the first assessment question among multiple assessment questions, the response time is predicted based on the speech speed information and the historical average response length, including:

[0048] Obtain the correlation between any assessment question and the previous assessment question of any assessment question;

[0049] Determine the correction constant based on the correlation between any assessment question and the previous assessment question;

[0050] The response duration is calculated using speech rate information, historical average response length, and a correction constant.

[0051] In conjunction with the second aspect, in a possible implementation manner, the method further includes:

[0052] Get reference answers to any assessment question;

[0053] The first preset duration is calculated using the speech rate information and the reference answer.

[0054] In combination with the second aspect, in a possible implementation, the first login request includes first identification information of the pet physician end of the pet physician online evaluation system and a first mobile phone number of the pet physician for receiving a text message verification code, and the identity verification of the pet physician is performed according to the first login request and the first facial feature, including:

[0055] Generate a first SMS verification code, and establish a four-element association relationship between the first SMS verification code, the first mobile phone number, the first identification information, and the first facial feature to be matched of the veterinarian, where the first facial feature to be matched is a facial feature of a pre-extracted template facial image of the veterinarian;

[0056] Send a first SMS verification code to the first mobile phone number;

[0057] Receiving a third login request submitted by the veterinarian through the veterinarian terminal, the third login request including the first mobile phone number to be verified, the first SMS verification code to be verified, and the first identification information to be verified;

[0058] The third login request is verified using the four-element association relationship, and when the first mobile phone number to be verified, the first SMS verification code to be verified, the first identification information to be verified, and the first facial feature match the first mobile phone number, the first SMS verification code, the first identification information, and the first facial feature to be matched respectively, it is determined that the veterinarian's identity authentication is passed;

[0059] If any one of the first mobile phone number to be verified and the first mobile phone number, the first SMS verification code to be verified and the first SMS verification code, the first identification information to be verified and the first identification information, and the first facial feature and the first facial feature to be matched does not match, it is determined that the veterinarian's identity authentication has failed.

[0060] A third aspect of an embodiment of the present application provides an electronic device, which includes an input device and an output device, and also includes a processor suitable for implementing one or more instructions; and a memory, wherein the memory stores one or more computer programs, and the one or more computer programs are suitable for being loaded by the processor and executing the steps in the method described in the second aspect.

[0061] A fourth aspect of an embodiment of the present application provides a computer storage medium, which stores one or more instructions, and the one or more instructions are suitable for being loaded by a processor and executing the steps in the method described in the second aspect.

[0062] The above solution of the present application includes at least the following beneficial effects:

[0063] The online evaluation system for pet doctors provided in the embodiment of the present application collects a first video image of the pet doctor and a second video image of the reviewer; obtains a first facial feature of the pet doctor based on the first video image, and obtains a second facial feature of the reviewer based on the second video image; and receives a first login request submitted by the pet doctor and a second login request submitted by the reviewer, authenticates the pet doctor according to the first login request and the first facial feature, and allows the pet doctor to log in to the online evaluation system for pet doctors if the identity authentication is passed, authenticates the reviewer according to the second login request and the second facial feature, and allows the reviewer to log in to the online evaluation system for pet doctors if the identity authentication is passed; selects multiple evaluation questions from a preset evaluation question bank based on the basic information, historical diagnosis records and online community evaluations of the pet doctor, and displays the multiple evaluation questions in sequence on the terminal device of the reviewer; obtains first voice data of the reviewer describing any one of the multiple evaluation questions to the pet doctor; obtains the response time of the pet doctor to any one of the evaluation questions based on the first voice data, and determines whether the pet doctor has cheated according to the response time; if the pet doctor has cheated, ends the current evaluation and adds the pet doctor to the blacklist. In this way, during the assessment, it can be determined whether the pet doctor has cheated based on the length of time the pet doctor takes to answer each assessment question. For example, if the response time is too long, it can be determined that the pet doctor is searching for answers, and therefore he can be determined to have cheated in the assessment. This will help solve the problem of difficulty in identifying cheating in online assessments, and thus help ensure the fairness of the assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0065] Figure 1 A schematic diagram of an application environment provided for an embodiment of the present application;

[0066] Figure 2 A block diagram of an online evaluation system for pet doctors provided in an embodiment of the present application;

[0067] Figure 3 A block diagram of an identity authentication module provided in an embodiment of the present application;

[0068] Figure 4 A schematic diagram of the structure of a feature extractor provided in an embodiment of the present application;

[0069] Figure 5A A block diagram of another identity authentication module provided in an embodiment of the present application;

[0070] Figure 5B A schematic diagram of an interface for submitting a login request provided in an embodiment of the present application;

[0071] Figure 5C A schematic diagram of another interface for submitting a login request provided in an embodiment of the present application;

[0072] Figure 6 A flowchart of an online pet doctor evaluation method provided in an embodiment of the present application;

[0073] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0074] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only 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 should fall within the scope of protection of the present application.

[0075] The terms "including" and "having" and any variations thereof that appear in the specification, claims and drawings of this application 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 may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices. In addition, the terms "first", "second" and "third" are used to distinguish different objects, rather than to describe a specific order.

[0076] See also Figure 1 , Figure 1 A schematic diagram of an application environment provided in an embodiment of the present application, such as Figure 1 As shown, the application environment includes a pet doctor terminal 101, an assessor terminal 102 and a server 103, wherein the pet doctor terminal 101 runs a pet doctor end of a pet doctor online assessment system, the assessor terminal 102 runs a assessor end, and the server 103 provides an operating environment for the service end of the pet doctor online assessment system. Specifically, the pet doctor enters the pet doctor end of the pet doctor online evaluation system through the pet doctor terminal 101, and the reviewer enters the reviewer end of the pet doctor online evaluation system through the reviewer terminal 102. When both the pet doctor and the reviewer successfully enter the pet doctor online evaluation system, the server 103 selects multiple evaluation questions from the preset pet doctor evaluation question bank in combination with the pet doctor's basic information, historical diagnosis records and online community evaluations, and displays the multiple evaluation questions on the reviewer terminal 102. The reviewer describes the evaluation questions to the pet doctor in the form of voice evaluation. The server 103 predicts the response time of the pet doctor to the evaluation question based on the reviewer's voice data. When the response time exceeds a certain threshold, the server 103 can determine that the pet doctor has cheated. For example, when the response time exceeds a certain time, it can be determined that the pet doctor is querying the answer, which can determine that he has cheated. The server 103 immediately ends this online evaluation and can add the pet doctor to the blacklist. In this application environment, the reviewer can conduct a one-to-one evaluation or a many-to-one evaluation on the pet doctor.

[0077] See also Figure 2 , Figure 2 A block diagram of an online evaluation system for pet doctors provided in an embodiment of the present application, such as Figure 2 As shown, the online evaluation system for pet doctors includes a video acquisition module, an identity authentication module, a test question selection module, a voice acquisition module, a cheating analysis module and a blacklist module, and each module is communicatively connected.

[0078] The video acquisition module is used to acquire a first video image of the pet doctor and a second video image of the reviewer. Specifically, the video acquisition module can be connected to the pet doctor terminal 101 and the reviewer terminal 102, and use the image acquisition device on the pet doctor terminal 101 to acquire a video image of the pet doctor to be evaluated, and obtain the first video image of the pet doctor, and use the image acquisition device on the reviewer terminal 102 to acquire a video image of the reviewer, and obtain the second video image of the pet doctor.

[0079] The identity authentication module is used to obtain the first facial feature of the pet doctor based on the first video image, and obtain the second facial feature of the reviewer based on the second video image; and receive a first login request submitted by the pet doctor and a second login request submitted by the reviewer, authenticate the pet doctor according to the first login request and the first facial feature, and allow the pet doctor to log in to the pet doctor online evaluation system if the identity authentication is passed, authenticate the reviewer according to the second login request and the second facial feature, and allow the reviewer to log in to the pet doctor online evaluation system if the identity authentication is passed;

[0080] Specifically, Figure 3 As shown, the identity authentication module includes a frame selection unit and a feature extraction unit. In terms of obtaining the first facial feature of the pet physician based on the first video image, the frame selection unit is specifically used to perform facial quality detection on the first video image to select a frame image with the highest facial quality score of the pet physician from the first video image, and send the frame image to the feature extraction unit. The feature extraction unit is specifically used to send a request for facial feature extraction to the pet physician terminal 101 when receiving the frame image, and when receiving a message from the pet physician terminal 101 that the pet physician agrees to the request, call a pre-trained neural network model to extract facial features from the frame image to obtain the first facial feature of the pet physician. Optionally, YOLO (You Only Look Once)-V3 can be used to extract facial features, as shown in FIG. Figure 4As shown in the figure, for the input image, the YOLO-V3 detector performs 32-fold downsampling through several convolutional layers after the 79th layer to obtain a 13*13 feature map, and performs 16-fold downsampling of the feature map output by the 91st layer through several convolutional layers to obtain a 26*26 feature map. Finally, the feature map of the 91st layer is upsampled, the upsampled feature map is fused with the feature map of the 36th layer, and then downsampled 8 times to obtain a 52*52 feature map. The 13*13 feature map and the 26*26 feature map are upsampled by bilinear interpolation and other methods to make their size 52*52, and then the features at the corresponding positions of the three 52*52 feature maps are added and the average is calculated to obtain the final extracted facial features. Optionally, in terms of face quality detection, the frame selection unit can specifically calculate the face quality score based on indicators such as the size, angle, clarity, and degree of occlusion of the face in the video image, such as mapping the value of each indicator to a range of 0 to 1 as the score of each indicator, and then performing weighted summation of the scores of each indicator to obtain the face quality score. It should be understood that in terms of obtaining the second facial features of the reviewer based on the second video image, the frame selection unit and the feature extraction unit use the same method as the first facial features to obtain the second facial features of the reviewer, and no further explanation will be given here.

[0081] The first login request includes the first identification information of the pet doctor end of the pet doctor online evaluation system and the first mobile phone number of the pet doctor for receiving the SMS verification code, such as Figure 5A As shown, the identity authentication module further includes a pet physician identity authentication unit. In terms of authenticating the identity of the pet physician according to the first login request and the first facial feature, the pet physician identity authentication unit is specifically used to:

[0082] Generate a first SMS verification code, and establish a four-element association relationship between the first SMS verification code, the first mobile phone number, the first identification information, and the first facial feature to be matched of the veterinarian, where the first facial feature to be matched is a facial feature of a pre-extracted template facial image of the veterinarian;

[0083] Send a first SMS verification code to the first mobile phone number;

[0084] Receiving a third login request submitted by the veterinarian through the veterinarian terminal, the third login request including the first mobile phone number to be verified, the first SMS verification code to be verified, and the first identification information to be verified;

[0085] The third login request is verified using the four-element association relationship, and when the first mobile phone number to be verified, the first SMS verification code to be verified, the first identification information to be verified, and the first facial feature match the first mobile phone number, the first SMS verification code, the first identification information, and the first facial feature to be matched respectively, it is determined that the veterinarian's identity authentication is passed;

[0086] If any one of the first mobile phone number to be verified and the first mobile phone number, the first SMS verification code to be verified and the first SMS verification code, the first identification information to be verified and the first identification information, and the first facial feature and the first facial feature to be matched does not match, it is determined that the veterinarian's identity authentication has failed.

[0087] Specifically, the veterinarian requests the veterinarian identity authentication unit in the server 103 to log in to the veterinarian online evaluation system through the veterinarian terminal of the veterinarian online evaluation system. Figure 5B The login button shown in the figure can submit the request to the pet doctor's identity verification unit. The pet doctor's identity verification unit returns the request to the pet doctor. Figure 5C The login authorization page shown is used by the veterinarian to fill in the mobile phone number for receiving SMS verification codes, wherein the veterinarian identity verification unit also adds an identification information to the login authorization page (for example: adding the identification information to the cookie of the login authorization page, the identification information is the first identification information), which is equivalent to nonce and is used to identify the veterinarian end. The first identification information can only be used by a specific individual. At the same time, even if another individual intercepts the first identification information, it cannot be verified by the veterinarian identity verification unit to prevent information leakage during the assessment. Pet physician clicks Figure 5C The verification code is sent to submit the first login request. Exemplarily, the first login request may be an authorization request link, which includes the first identification information and the first mobile phone number of the veterinarian. When the veterinarian identity authentication unit receives the first login request, it verifies the first identification information. If the verification is successful, it generates a first SMS verification code, such as "564890", and establishes the four-element association relationship shown in Table 1:

[0088] Table 1

[0089] Phone number 13812301230 First identification information hxabesfdsdff First SMS verification code 564890 The first facial feature to be matched 111000922299

[0090] After storing the four-element association relationship shown in Table 1, the pet doctor identity verification unit sends a first SMS verification to the first mobile phone number of the pet doctor. Figure 5CEnter the first SMS verification code in the SMS verification code column shown, click the Submit button, and then send a third login request to the pet physician identity authentication unit. It should be understood that the third login request usually includes the first mobile phone number to be verified, the first SMS verification code to be verified, and the first identification information to be verified. When the first facial feature extracted by the feature extraction unit is obtained, the pet physician identity authentication unit verifies the third login request and the first facial feature using the four-element association relationship shown in Table 1. If the first mobile phone number to be verified, the first SMS verification code to be verified, the first identification information to be verified, and the first facial feature all match the recorded four-element association relationship, it is determined that the pet physician's identity authentication is passed. If any one of the first mobile phone number to be verified, the first SMS verification code to be verified, the first identification information to be verified, and the first facial feature does not match the four-element association relationship shown in Table 1, it is determined that the pet physician's identity authentication has failed.

[0091] The second login request includes the second identification information of the assessor of the online pet doctor assessment system and the second mobile phone number of the assessor for receiving the SMS verification code. Figure 5A As shown, the identity authentication module further includes an assessor identity authentication unit. In terms of authenticating the assessor according to the second login request and the second facial feature, the assessor identity authentication unit is specifically used to:

[0092] Generate a second SMS verification code, and establish a four-element association relationship between the second SMS verification code, the second mobile phone number, the second identification information, and the second facial feature to be matched of the reviewer, where the second facial feature to be matched is the facial feature of the template facial image of the reviewer extracted in advance;

[0093] Send a second SMS verification code to the second mobile phone number;

[0094] Receiving a fourth login request submitted by the reviewer through the reviewer terminal, the fourth login request including a second mobile phone number to be verified, a second SMS verification code to be verified, and a second identification information to be verified;

[0095] The fourth login request is verified using the four-element association relationship, and when the second mobile phone number to be verified, the second SMS verification code to be verified, the second identification information to be verified, and the second facial feature match the second mobile phone number, the second SMS verification code, the second identification information, and the second facial feature to be matched respectively, it is determined that the reviewer's identity authentication is passed;

[0096] If any one of the second mobile phone number to be verified and the second mobile phone number, the second SMS verification code to be verified and the second SMS verification code, the second identification information to be verified and the second identification information, and the second facial feature and the second facial feature to be matched does not match, it is determined that the reviewer's identity authentication has failed.

[0097] It should be noted that the identity authentication method of the reviewer is the same as that of the pet doctor, and no further explanation is given here. It can be seen that the pet doctor identity authentication unit and the reviewer identity authentication unit use the pre-established four-element association relationship to authenticate the pet doctor and the reviewer, respectively, which is conducive to avoiding the situation of counterfeiting to enter the pet doctor online evaluation system, so as to ensure the fairness of the online evaluation.

[0098] Among them, the test question selection module is used to select multiple test questions from the preset test question bank based on the basic information of the veterinarian, historical diagnosis records and online community evaluations, and display the multiple test questions in sequence on the assessor's terminal device.

[0099] Specifically, when the identity authentication of the pet doctor and the assessor is passed, the identity authentication module sends a prompt message to the test question selection module, and the test question selection module then selects questions based on the basic information of the pet doctor (such as the pet doctor's years of practice), historical diagnosis records and online community evaluations of the pet doctor. For example, from implementing laboratory tests, imaging, puncture techniques and other diagnostic procedures; analyzing laboratory and examination reports and results, making diagnoses, determining and implementing pet medical plans; prescribing, explaining the pet's medication requirements and care methods to the pet owner or caregiver; using necessary medical equipment, instruments, drugs, oxygen supply, nutritional supplements, blood transfusions, alternative treatments and other means to treat pet diseases, etc., the number of historical diagnosis records of the pet doctor is counted, and the number of historical diagnoses in each aspect is obtained, and the proportion of the number of historical diagnoses in each aspect in the total number of historical diagnosis records is calculated. For example, the proportion of using necessary medical equipment, instruments, drugs, oxygen supply, nutritional supplements, blood transfusions, alternative treatments and other means to treat pet diseases is 0.65, the highest among all proportions, indicating that the pet doctor is usually more proficient in pet treatment in this aspect. The online community also counts the number of star ratings for veterinarians. For example, 5 stars means very satisfied. The number of 5-star ratings is counted and the proportion of each star rating is expressed as a percentage. For example, if 60 out of 100 reviews are 5 stars, the proportion of 5 stars is 0.6. The veterinarian's years of practice, the proportion of various aspects of the historical diagnosis record, and the proportion of each star rating of the online community rating are sorted into a one-dimensional vector (that is, a one-dimensional vector is obtained based on the veterinarian's basic information, historical diagnosis records, and online community evaluations), such as [3, 0.65, 0.2, 0.03, 0, 0, 0.25...], and at the same time, all evaluation questions in the preset evaluation question bank are text-vectorized to obtain a one-dimensional vectorized representation of each evaluation question, and the similarity between the above one-dimensional vector and the one-dimensional vectorized representation is calculated, and the evaluation questions in the preset evaluation question bank are sorted from low to high according to the similarity to obtain an evaluation question sequence, and the top k evaluation questions in the evaluation question sequence are selected as the above multiple evaluation questions, wherein k is a preset number, k is greater than 1, and the test question selection module displays the top k evaluation questions in the order of their appearance in the evaluation question sequence on the reviewer terminal 102, which can be specifically displayed on the reviewer end of the veterinarian online evaluation system. In this implementation, the test question selection module organizes the pet physician's basic information, historical diagnosis records, and online community evaluations into a one-dimensional vector, then extracts the text vector representation of the test questions in the preset test question bank, and selects the top k test questions with lower similarity to evaluate the pet physician. This can avoid selecting test questions that the pet physician is frequently exposed to and is good at, which is conducive to promoting the all-round development of the pet physician.

[0100] The voice acquisition module is used to acquire the first voice data of the assessor describing any one of the multiple assessment topics to the veterinarian. Specifically, based on the voice or video assessment mode, the assessor can describe any one of the multiple assessment topics to the veterinarian online, and the veterinarian will then respond. The voice of the assessor describing the any one of the assessment topics is called the first voice data.

[0101] The cheating analysis module is used to obtain the length of time it takes the pet doctor to answer any assessment question based on the first voice data, and determine whether the pet doctor has cheated based on the length of time it takes to answer. Specifically, the cheating analysis module also includes a length prediction unit. In terms of obtaining the length of time it takes the pet doctor to answer any assessment question based on the first voice data, the length prediction unit is specifically used to:

[0102] Obtaining the speech speed information of the veterinarian based on the reference voice data;

[0103] Obtaining the historical average answer length of at least one assessment question in the preset assessment question bank that belongs to the same question type as any assessment question;

[0104] Predict the response time based on speech rate information and historical average response length.

[0105] Specifically, the reference voice data can be the opening speech of the pet doctor, such as the voice of the pet doctor's self-introduction, or when any assessment question is not the first question-and-answer assessment question, the reference voice data can also be the voice of the pet doctor answering the assessment question before any assessment question. The duration prediction unit detects the reference voice data through the speech speed detection technology to obtain the speech speed information of the pet doctor. For any assessment question, the duration prediction unit determines at least one assessment question belonging to the same type of question from the preset assessment question bank. For example, if any assessment question belongs to the category of "using necessary medical equipment, instruments, drugs, oxygen supply, nutritional supplements, blood transfusion, alternative treatment and other means to treat pet diseases", then select at least one assessment question that has been used for assessment from this type of question, and count the total response time of all voice data that answer the at least one assessment question, and then divide it by the number of response voices to obtain the historical average response length of at least one assessment question. When any one of the assessment questions is the first one of the multiple assessment questions, the duration prediction unit calculates the answer duration of the any one of the assessment questions using the following formula:

[0106] L=L a / V;

[0107] Among them, L represents the response time in minutes. aIt indicates the historical average answer length of at least one assessment question. V indicates the speaking speed information in words per minute.

[0108] When any assessment question is not the first assessment question among the multiple assessment questions, in terms of predicting the response time according to the speech speed information and the historical average response length, the response time prediction unit is specifically used to:

[0109] Obtain the correlation between any assessment question and the previous assessment question of any assessment question;

[0110] Determine the correction constant based on the correlation between any assessment question and the previous assessment question;

[0111] The response duration is calculated using speech rate information, historical average response length, and a correction constant.

[0112] Specifically, the duration prediction unit uses a semantic extraction model to extract a first semantic feature of any evaluation question, and uses an LDA topic model to extract a first topic feature of any evaluation question, splices the first semantic feature and the first topic feature into a first feature, uses a semantic extraction model to extract a second semantic feature of a previous evaluation question of any evaluation question, and uses an LDA topic model to extract a second topic feature of the previous evaluation question, splices the second semantic feature and the second semantic feature into a second feature, calculates the similarity between the first feature and the second feature, and obtains a first feature. The relevance of the previous assessment question. For two assessment questions with higher relevance, the veterinarian's response time to the second assessment question is usually shorter. For two assessment questions with little relevance, the previous assessment question has no effect on the response time of the current assessment question. Therefore, in the embodiment of the present application, when the relevance of any assessment question to the previous assessment question of any assessment question is greater than the preset value, the relevance-correction constant table is queried to obtain the correction constant corresponding to the relevance. For example, if the relevance is 0.7, which is greater than the preset value 0.5, the corresponding correction constant can be -0.7, and so on. The time prediction unit uses the following formula to calculate the response time of any assessment question:

[0113] L=L a / V+ΔT;

[0114] Among them, ΔT represents the correction constant, which can be set by conducting big data analysis on the types of assessment questions and the speaking speed of historical assessors. For example, some subjective assessment questions require a large number of statements. After big data analysis, it is found that people with fast speaking speed have relatively short response time, so their correction constant is usually smaller than that of people with slow speaking speed, and so on.

[0115] Furthermore, the duration prediction unit is also used for:

[0116] Get reference answers to any assessment question;

[0117] The first preset duration is calculated using the speech rate information and the reference answer.

[0118] Assuming the length (number of words) of the reference reply is L1, the duration prediction unit uses the following formula to calculate the first preset duration:

[0119] L2=L1 / V;

[0120] Among them, L2 represents the first preset duration.

[0121] The cheating analysis module includes a cheating analysis unit. In determining whether the pet doctor has cheated based on the reply time, the cheating analysis unit is specifically used to:

[0122] Obtaining an end time point of the first voice data;

[0123] Obtaining the starting time point of the second voice data of the veterinarian answering any assessment question;

[0124] When the response time is greater than or equal to the first preset time, and the time interval between the end time point and the start time point is greater than or equal to the second preset time, it is determined that the veterinarian has cheated.

[0125] Specifically, the time interval between the end time point of the first voice data and the start time point of the second voice data is used as the veterinarian's thinking time. If the time interval is greater than or equal to the second preset time length and the response time length is greater than or equal to the first preset time length, the cheating analysis unit determines that the veterinarian may be retrieving the answer, and it can be determined that the veterinarian has cheated.

[0126] The blacklist module is used to terminate the evaluation and add the pet doctor to the blacklist if the pet doctor cheats. The pet doctor added to the blacklist can be punished accordingly afterwards, or used as a reference for job grade evaluation, etc.

[0127] It can be seen that Figure 2The online evaluation system for pet doctors shown in the figure collects a first video image of the pet doctor and a second video image of the reviewer; obtains a first facial feature of the pet doctor based on the first video image, and obtains a second facial feature of the reviewer based on the second video image; and receives a first login request submitted by the pet doctor and a second login request submitted by the reviewer, authenticates the pet doctor according to the first login request and the first facial feature, and allows the pet doctor to log in to the online evaluation system for pet doctors if the identity authentication is passed, authenticates the reviewer according to the second login request and the second facial feature, and allows the reviewer to log in to the online evaluation system for pet doctors if the identity authentication is passed; selects multiple evaluation questions from a preset evaluation question bank based on the basic information, historical diagnosis records and online community evaluations of the pet doctor, and displays the multiple evaluation questions in sequence on the terminal device of the reviewer; obtains first voice data of the reviewer describing any one of the multiple evaluation questions to the pet doctor; obtains the response time of the pet doctor to any one of the evaluation questions based on the first voice data, and determines whether the pet doctor has cheated according to the response time; if the pet doctor has cheated, ends the evaluation and adds the pet doctor to the blacklist. In this way, during the assessment, it can be determined whether the pet doctor has cheated based on the length of time the pet doctor takes to answer each assessment question. For example, if the response time is too long, it can be determined that the pet doctor is searching for answers, and therefore he can be determined to have cheated in the assessment. This will help solve the problem of difficulty in identifying cheating in online assessments, and thus help ensure the fairness of the assessment.

[0128] The present application also provides an online evaluation method for pet doctors, which is applied to electronic devices. Figure 6 The online evaluation method for pet doctors includes steps 601-606:

[0129] 601: Acquire a first video image of the veterinarian and a second video image of the assessor;

[0130] 602: obtaining a first facial feature of the pet doctor based on the first video image, and obtaining a second facial feature of the reviewer based on the second video image; and receiving a first login request submitted by the pet doctor and a second login request submitted by the reviewer, performing identity authentication on the pet doctor according to the first login request and the first facial feature, and allowing the pet doctor to log in to the pet doctor online evaluation system if the identity authentication is passed, performing identity authentication on the reviewer according to the second login request and the second facial feature, and allowing the reviewer to log in to the pet doctor online evaluation system if the identity authentication is passed;

[0131] 603: Based on the basic information of the veterinarian, historical diagnosis records and online community evaluations, multiple evaluation questions are selected from a preset evaluation question bank, and the multiple evaluation questions are displayed in sequence on the terminal device of the assessor;

[0132] 604: Acquire first voice data of the assessor describing any one of the multiple assessment topics to the veterinarian;

[0133] 605: Obtaining the length of time it takes the veterinarian to answer any assessment question based on the first voice data, and determining whether the veterinarian has cheated according to the length of time it takes to answer the question;

[0134] 606: If the veterinarian is found to have cheated, the assessment will be terminated and the veterinarian will be added to the blacklist.

[0135] For example, the veterinarian's cheating behavior is determined based on the length of the response time, including:

[0136] Obtaining an end time point of the first voice data;

[0137] Obtaining the starting time point of the second voice data of the veterinarian answering any assessment question;

[0138] When the response time is greater than or equal to the first preset time, and the time interval between the end time point and the start time point is greater than or equal to the second preset time, it is determined that the veterinarian has cheated.

[0139] Exemplarily, obtaining the length of time it takes a veterinarian to answer any assessment question based on the first voice data includes:

[0140] Obtaining the speech speed information of the veterinarian based on the reference voice data;

[0141] Obtaining the historical average answer length of at least one assessment question in the preset assessment question bank that belongs to the same question type as any assessment question;

[0142] Predict the response time based on speech rate information and historical average response length.

[0143] Exemplarily, when any assessment question is not the first assessment question among multiple assessment questions, the response time is predicted based on the speech speed information and the historical average response length, including:

[0144] Obtain the correlation between any assessment question and the previous assessment question of any assessment question;

[0145] Determine the correction constant based on the correlation between any assessment question and the previous assessment question;

[0146] The response duration is calculated using speech rate information, historical average response length, and a correction constant.

[0147] Exemplarily, the method further includes:

[0148] Get reference answers to any assessment question;

[0149] The first preset duration is calculated using the speech rate information and the reference answer.

[0150] Exemplarily, the first login request includes first identification information of the pet doctor end of the pet doctor online evaluation system and a first mobile phone number of the pet doctor for receiving a text message verification code, and the identity authentication of the pet doctor is performed according to the first login request and the first facial feature, including:

[0151] Generate a first SMS verification code, and establish a four-element association relationship between the first SMS verification code, the first mobile phone number, the first identification information, and the first facial feature to be matched of the veterinarian, where the first facial feature to be matched is a facial feature of a pre-extracted template facial image of the veterinarian;

[0152] Send a first SMS verification code to the first mobile phone number;

[0153] Receiving a third login request submitted by the veterinarian through the veterinarian terminal, the third login request including the first mobile phone number to be verified, the first SMS verification code to be verified, and the first identification information to be verified;

[0154] The third login request is verified using the four-element association relationship, and when the first mobile phone number to be verified, the first SMS verification code to be verified, the first identification information to be verified, and the first facial feature match the first mobile phone number, the first SMS verification code, the first identification information, and the first facial feature to be matched respectively, it is determined that the veterinarian's identity authentication is passed;

[0155] If any one of the first mobile phone number to be verified and the first mobile phone number, the first SMS verification code to be verified and the first SMS verification code, the first identification information to be verified and the first identification information, and the first facial feature and the first facial feature to be matched does not match, it is determined that the veterinarian's identity authentication has failed.

[0156] in, Figure 6 The specific implementation method of the online evaluation method for pet doctors shown can be referred to Figure 2 The description of the online veterinarian evaluation system shown will not be repeated here to avoid repetition.

[0157] It can be seen that in Figure 6In the online evaluation method for pet doctors shown, a first video image of the pet doctor and a second video image of the reviewer are collected; a first facial feature of the pet doctor is obtained based on the first video image, and a second facial feature of the reviewer is obtained based on the second video image; and a first login request submitted by the pet doctor and a second login request submitted by the reviewer are received, the pet doctor's identity is authenticated according to the first login request and the first facial feature, and if the identity authentication is passed, the pet doctor is allowed to log in to the online evaluation system for pet doctors, and the reviewer's identity is authenticated according to the second login request and the second facial feature, and if the identity authentication is passed, the reviewer is allowed to log in to the online evaluation system for pet doctors; based on the basic information, historical diagnosis records and online community evaluations of the pet doctor, multiple evaluation questions are selected from a preset evaluation question bank, and the multiple evaluation questions are displayed in sequence on the terminal device of the reviewer; first voice data of the reviewer describing any one of the multiple evaluation questions to the pet doctor is obtained; based on the first voice data, the response time of the pet doctor to any one of the evaluation questions is obtained, and the pet doctor's cheating behavior is determined according to the response time; if the pet doctor has cheated, the current evaluation is terminated and the pet doctor is added to the blacklist. In this way, during the assessment, it can be determined whether the pet doctor has cheated based on the length of time the pet doctor takes to answer each assessment question. For example, if the response time is too long, it can be determined that the pet doctor is searching for answers, and therefore he can be determined to have cheated in the assessment. This will help solve the problem of difficulty in identifying cheating in online assessments, and thus help ensure the fairness of the assessment.

[0158] Based on the description of the above method embodiment, the present application embodiment also provides an electronic device. Figure 7 The electronic device at least includes a processor 701, an input device 702, an output device 703 and a memory 704. The processor 701, the input device 702, the output device 703 and the memory 704 in the electronic device may be connected via a bus or other means.

[0159] The memory 704 may be stored in the memory of the electronic device, the memory 704 is used to store a computer program, the computer program includes program instructions, and the processor 701 is used to execute the program instructions stored in the memory 704. The processor 701 (or CPU (Central Processing Unit)) is the computing core and control core of the electronic device, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function.

[0160] In one embodiment, the processor 701 of the electronic device provided in the embodiment of the present application can be used to process a series of veterinarian online evaluation methods:

[0161] capturing a first video image of the veterinarian and a second video image of the assessor;

[0162] Obtaining a first facial feature of the pet physician based on the first video image, and obtaining a second facial feature of the reviewer based on the second video image; and receiving a first login request submitted by the pet physician and a second login request submitted by the reviewer, performing identity authentication on the pet physician according to the first login request and the first facial feature, and allowing the pet physician to log in to the pet physician online assessment system if the identity authentication is passed, performing identity authentication on the reviewer according to the second login request and the second facial feature, and allowing the reviewer to log in to the pet physician online assessment system if the identity authentication is passed;

[0163] Based on the basic information of the veterinarian, historical diagnosis records and online community evaluations, multiple evaluation questions are selected from the preset evaluation question bank, and the multiple evaluation questions are displayed in sequence on the assessor's terminal device;

[0164] Acquire first voice data of an assessor describing any one of a plurality of assessment topics to a veterinarian;

[0165] Obtaining the length of time it takes the veterinarian to answer any assessment question based on the first voice data, and determining whether the veterinarian has cheated based on the length of time it takes to answer the question;

[0166] If the veterinarian is found to have cheated, the assessment will be terminated and the veterinarian will be added to the blacklist.

[0167] In another embodiment, the processor 701 determines whether the veterinarian has cheated according to the reply time, including:

[0168] Obtaining an end time point of the first voice data;

[0169] Obtaining the starting time point of the second voice data of the veterinarian answering any assessment question;

[0170] When the response time is greater than or equal to the first preset time, and the time interval between the end time point and the start time point is greater than or equal to the second preset time, it is determined that the veterinarian has cheated.

[0171] In another embodiment, the processor 701 obtains the length of time it takes the veterinarian to answer any assessment question based on the first voice data, including:

[0172] Obtaining the speech speed information of the veterinarian based on the reference voice data;

[0173] Obtaining the historical average answer length of at least one assessment question in the preset assessment question bank that belongs to the same question type as any assessment question;

[0174] Predict the response time based on speech rate information and historical average response length.

[0175] In another embodiment, when any assessment question is not the first assessment question among multiple assessment questions, the processor 701 predicts the response time according to the speech rate information and the historical average response length, including:

[0176] Obtain the correlation between any assessment question and the previous assessment question of any assessment question;

[0177] Determine the correction constant based on the correlation between any assessment question and the previous assessment question;

[0178] The response duration is calculated using speech rate information, historical average response length, and a correction constant.

[0179] In yet another embodiment, the processor 701 is further configured to:

[0180] Get reference answers to any assessment question;

[0181] The first preset duration is calculated using the speech rate information and the reference answer.

[0182] Exemplarily, the electronic device may be an independent physical server, a server cluster or a distributed system, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, and basic cloud computing services such as big data and artificial intelligence platforms. The electronic device includes but is not limited to a processor 701, an input device 702, an output device 703, and a memory 704. It may also include a memory, a power supply, an application client module, and the like. The input device 702 may be a keyboard, a touch screen, a radio frequency receiver, and the like, and the output device 703 may be a speaker, a display, a radio frequency transmitter, and the like. It will be understood by those skilled in the art that the schematic diagram is merely an example of an electronic device and does not constitute a limitation on the electronic device, and may include more or fewer components than shown, or combine certain components, or different components.

[0183] It should be noted that since the processor 701 of the electronic device implements the steps in the above-mentioned pet physician online evaluation method when executing the computer program, the embodiments of the above-mentioned pet physician online evaluation method are all applicable to the electronic device and can achieve the same or similar beneficial effects.

[0184] The embodiment of the present application also provides a computer storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It is understandable that the computer storage medium here can include both the built-in storage medium in the terminal and the extended storage medium supported by the terminal. The computer storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor 701 are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer storage medium here can be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as at least one disk storage; optionally, it can also be at least one computer storage medium located away from the aforementioned processor 701. In one embodiment, the processor 701 can load and execute one or more instructions stored in the computer storage medium to implement the corresponding steps of the above-mentioned method for online evaluation of pet doctors.

[0185] Exemplarily, the computer program of the computer storage medium includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0186] It should be noted that since the computer program of the computer storage medium implements the steps of the above-mentioned pet physician online evaluation method when executed by the processor, all embodiments of the above-mentioned pet physician online evaluation method are applicable to the computer storage medium and can achieve the same or similar beneficial effects.

[0187] 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 and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. An online evaluation system for pet doctors, characterized in that: The online evaluation system for pet doctors includes a video acquisition module, an identity authentication module, a test question selection module, a voice acquisition module, a cheating analysis module and a blacklist module, and each module is connected in communication; wherein: The video acquisition module is used to acquire a first video image of the veterinarian and a second video image of the assessor; The identity authentication module is used to obtain the first facial feature of the pet doctor based on the first video image, and obtain the second facial feature of the reviewer based on the second video image; and receive a first login request submitted by the pet doctor and a second login request submitted by the reviewer, authenticate the pet doctor according to the first login request and the first facial feature, and allow the pet doctor to log in to the pet doctor online evaluation system if the identity authentication is passed, authenticate the reviewer according to the second login request and the second facial feature, and allow the reviewer to log in to the pet doctor online evaluation system if the identity authentication is passed; The test question selection module is used to select multiple test questions from a preset test question bank based on the basic information, historical diagnosis records and online community evaluations of the veterinarian, and display the multiple test questions in sequence on the terminal device of the assessor; The voice acquisition module is used to acquire first voice data of the assessor describing any one of the multiple assessment topics to the veterinarian; The cheating analysis module is used to obtain the length of time it takes the veterinarian to answer any one of the assessment questions based on the first voice data, and determine whether the veterinarian has cheated according to the length of time it takes to answer the question; The blacklist module is used to terminate the evaluation and add the pet doctor to the blacklist if the pet doctor cheats. The cheating analysis module includes a duration prediction unit. In terms of obtaining the duration of the pet doctor's answer to any one of the assessment questions based on the first voice data, the duration prediction unit is specifically used to: Obtaining the speech speed information of the veterinarian based on the reference voice data; Obtaining a historical average answer length of at least one evaluation question in the preset evaluation question bank that belongs to the same type of question as any one of the evaluation questions; Predicting the response time based on the speech speed information and the historical average response length; Wherein, when the any one of the evaluation questions is the first one of the multiple evaluation questions, the duration prediction unit calculates the answer duration of the any one of the evaluation questions using the following formula: L=L a / V; Wherein, L represents the duration of the response, in minutes, a represents the historical average answer length of the at least one assessment question, and V represents the speech speed information in words / minute; In the case that any one of the evaluation questions is not the first evaluation question among the multiple evaluation questions, in predicting the response time according to the speech speed information and the historical average response length, the response time prediction unit is specifically used to: Obtaining the relevance between any one of the assessment questions and a previous assessment question of the any one of the assessment questions; Determine a correction constant according to the correlation between any one of the assessment questions and the previous assessment question; The response time is calculated by using the speech speed information, the historical average response length and the correction constant through the following formula: L=L a / V+ΔT; Wherein, ΔT represents the correction constant.

2. The system according to claim 1, characterized in that The cheating analysis module includes a cheating analysis unit. In determining whether the pet doctor has cheated according to the reply time, the cheating analysis unit is specifically used to: Obtaining an end time point of the first voice data; Obtaining the starting time point of the second voice data of the veterinarian answering any one of the assessment questions; When the response time is greater than or equal to the first preset time, and the time interval between the end time point and the start time point is greater than or equal to the second preset time, it is determined that the veterinarian has cheated.

3. The system according to claim 2, characterized in that The duration prediction unit is further used for: Obtain a reference answer to any of the assessment questions; The first preset duration is calculated using the speech rate information and the reference answer.

4. The system according to any one of claims 1 to 3, characterized in that: The first login request includes the first identification information of the pet physician end of the pet physician online evaluation system and the first mobile phone number of the pet physician for receiving the SMS verification code. The identity authentication module also includes a pet physician identity authentication unit. In terms of authenticating the pet physician according to the first login request and the first facial feature, the pet physician identity authentication unit is specifically used to: Generate a first SMS verification code, and establish a four-element association relationship among the first SMS verification code, the first mobile phone number, the first identification information, and a first facial feature to be matched of the veterinarian, wherein the first facial feature to be matched is a facial feature of a pre-extracted template facial image of the veterinarian; Sending the first SMS verification code to the first mobile phone number; Receiving a third login request submitted by the veterinarian through the veterinarian terminal, wherein the third login request includes a first mobile phone number to be verified, a first SMS verification code to be verified, and a first identification information to be verified; The third login request is verified by using the four-element association relationship, and when the first mobile phone number to be verified, the first SMS verification code to be verified, the first identification information to be verified, and the first facial feature respectively match the first mobile phone number, the first SMS verification code, the first identification information, and the first facial feature to be matched, it is determined that the identity authentication of the pet physician is passed; If any one of the first mobile phone number to be verified and the first mobile phone number, the first SMS verification code to be verified and the first SMS verification code, the first identification information to be verified and the first identification information, and the first facial feature and the first facial feature to be matched does not match, it is determined that the veterinarian's identity authentication has failed.

5. A method for evaluating veterinarians online, characterized in that: The online evaluation method for pet doctors includes: capturing a first video image of the veterinarian and a second video image of the assessor; Obtaining a first facial feature of the veterinarian based on the first video image, and obtaining a second facial feature of the reviewer based on the second video image; and receiving a first login request submitted by the veterinarian and a second login request submitted by the reviewer, performing identity authentication on the veterinarian according to the first login request and the first facial feature, and allowing the veterinarian to log in to the veterinarian online assessment system if the identity authentication is passed, performing identity authentication on the reviewer according to the second login request and the second facial feature, and allowing the reviewer to log in to the veterinarian online assessment system if the identity authentication is passed; Acquire first voice data of any one of a plurality of evaluation topics described by the assessor to the veterinarian; Obtaining the length of time it takes the veterinarian to answer any one of the assessment questions based on the first voice data, and determining whether the veterinarian has cheated according to the length of time it takes to answer the question; If the veterinarian has cheated, the assessment will be terminated and the veterinarian will be added to the blacklist. The step of obtaining the length of time taken by the veterinarian to answer any one of the assessment questions based on the first voice data includes: Obtaining the speech speed information of the veterinarian based on the reference voice data; Obtaining a historical average answer length of at least one assessment question in a preset assessment question bank that belongs to the same question type as any one of the assessment questions; Predicting the response time based on the speech speed information and the historical average response length; Wherein, when the any one of the assessment questions is the first one of the multiple assessment questions, the answering time of the any one of the assessment questions is calculated by the following formula: L=L a / V; Wherein, L represents the duration of the response, in minutes, a represents the historical average answer length of the at least one assessment question, and V represents the speech speed information in words / minute; In the case that any one of the evaluation questions is not the first evaluation question among the multiple evaluation questions, predicting the response time according to the speech speed information and the historical average response length includes: Obtaining the relevance between any one of the assessment questions and a previous assessment question of the any one of the assessment questions; Determine a correction constant according to the correlation between any one of the assessment questions and the previous assessment question; The response time is calculated by using the speech speed information, the historical average response length and the correction constant through the following formula: L=L a / V+ΔT; Wherein, ΔT represents the correction constant.

6. The method according to claim 5, characterized in that Determining that the veterinarian has cheated based on the response time includes: Obtaining an end time point of the first voice data; Obtaining the starting time point of the second voice data of the veterinarian answering any one of the assessment questions; When the response time is greater than or equal to the first preset time, and the time interval between the end time point and the start time point is greater than or equal to the second preset time, it is determined that the veterinarian has cheated.

7. An electronic device, comprising an input device and an output device, characterized in that: Also includes: a processor adapted to implement one or more computer programs; as well as, A memory storing one or more computer programs, wherein the one or more computer programs are suitable for being loaded by the processor and executing the method according to any one of claims 5 to 6.

8. A computer storage medium, characterized in that: The computer storage medium stores one or more instructions, and the one or more instructions are suitable for being loaded by a processor and executing the method according to any one of claims 5-6.

Images