An intelligent nursing education management method and system based on image recognition

By dynamically updating verification images in the nursing education question bank using image recognition technology and optimizing the push strategy, the problem of high error rates and lack of verification images in nursing staff's learning has been solved, thus improving the reliability and efficiency of learning.

CN120893706BActive Publication Date: 2026-06-12THE FIRST AFFILIATED HOSPITAL ZHEJIANG UNIV COLLEGE OF MEDICINE

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
THE FIRST AFFILIATED HOSPITAL ZHEJIANG UNIV COLLEGE OF MEDICINE
Filing Date
2025-09-30
Publication Date
2026-06-12

AI Technical Summary

Technical Problem

In existing technologies, when nursing staff use question banks for learning, there are problems such as high error rates and lack of verification images for questions, resulting in poor learning reliability and low update efficiency.

Method used

By using image recognition technology, questions without verification images are dynamically updated. Based on the answers to the questions and historical push data, the questions that need to be updated are determined, the push processing strategy is optimized, and relevant images are automatically pushed to improve the reliability and efficiency of learning.

Benefits of technology

It improves the efficiency of update requirement identification and processing when the number of verification images for questions with high error rates is small, reduces unnecessary push notifications, and enhances the learning reliability for nursing staff.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120893706B_ABST
    Figure CN120893706B_ABST
Patent Text Reader

Abstract

The application provides an intelligent nursing education management method and system based on image recognition, and belongs to the technical field of education management, and specifically comprises the following steps: determining the push processing strategy of the question without a verification picture according to the identification processing scheme of the update requirement question and the historical push data of the question without a verification picture; determining the answer processing result of the question without a verification picture based on the push processing strategy; determining the update requirement question by using the answer processing result; and determining whether the push processing scheme of the question with a verification picture needs to be optimized by using the update data of the update requirement question, so that the learning reliability of nursing personnel is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention belongs to the field of education management technology, and in particular relates to an intelligent nursing education management method and system based on image recognition. Background Technology

[0002] To achieve the education and training of nursing staff, existing technical solutions often involve constructing a topic-based question bank. Specifically, in invention patent application CN202411826501.5, "A Course Teaching Resource Management System and its Management Method," a data exchange platform is constructed to facilitate data exchange within the system and with external systems, and to ensure stricter and more efficient management of user identities and data. Through rich resource types and diverse resource formats, it provides users with a wider range of learning materials and choices. However, the above technical solutions have the following drawbacks:

[0003] When nursing staff use a question bank for learning, in order to improve their impression of incorrect questions, the system automatically pushes images corresponding to the answer when they answer incorrectly, such as images of medications or nursing requirements, thereby improving the reliability of learning. However, since not all questions have verification images, how to update questions without verification images based on the results of the question answering process has become an urgent technical problem to be solved.

[0004] To address the aforementioned technical problems, this application provides an intelligent nursing education management method and system based on image recognition. Summary of the Invention

[0005] To achieve the objectives of this invention, the following technical solution is adopted:

[0006] Specifically, this application provides an intelligent nursing education management method based on image recognition, which includes:

[0007] S1 uses the question bank data of nursing staff as a basis to determine the question data where the answer does not have a verification image. Based on the question data where the verification image does not exist and the question push processing method, when it is determined that dynamic updating processing of verification images is required, the answer processing results of the questions with verification images are used to determine the identification and processing scheme of the questions with update requirements in the questions where the verification image does not exist.

[0008] S2 determines the push processing strategy for questions without verification images based on the identification and processing scheme of the updated question and the historical push data of questions without verification images. Based on the push processing strategy, it determines the solution processing result of the questions without verification images. It uses the solution processing result to determine the updated question and uses the updated data of the updated question to determine whether the push processing scheme for questions with verification images needs to be optimized.

[0009] The beneficial effects of this invention are as follows:

[0010] Based on the solution processing results of questions with verification images, a processing scheme for identifying update request questions in questions without verification images is determined. This is achieved by determining the identification and processing scheme for update request questions based on the composition of questions with verification images among questions with high error rates. This reduces the number of push processing steps required for identifying update request questions when the number of questions with verification images among high error rate questions is small, thereby improving the efficiency of update request question identification and processing. It also avoids the technical problem of poor learning reliability for nursing staff among questions with high error rates.

[0011] By utilizing updated data of the update request questions, it was determined whether the push processing scheme for questions containing verification images needed optimization. This avoided the technical problem of low proportion of questions with verification images in the push processing due to the use of a fixed push processing scheme, which led to poor learning reliability for nursing staff. By dynamically identifying the updated data of the update request questions, the impact on the update processing efficiency of the update request questions was reduced, while also ensuring that when nursing staff answered incorrectly, the corresponding answer contained relevant verification images, thus improving the learning reliability for nursing staff.

[0012] Furthermore, the question with a verification image is one in which an image related to the answer is automatically pushed when the answer is incorrect.

[0013] Furthermore, the verification images include images of medicines, images demonstrating nursing procedures, and images of medical orders.

[0014] Furthermore, the method for pushing out the questions is determined based on the number of questions pushed to the nursing staff at one time during the mock exam or the actual exam.

[0015] Furthermore, it was determined that dynamic updating of the verification images was necessary, specifically including:

[0016] Based on the question data that does not have a verification image, questions that do not have a verification image are identified and regarded as verification deviation questions. According to the composition data of the verification deviation questions in the question bank, the proportion of verification deviation questions in the question bank is determined.

[0017] Based on the question push processing method, the number of questions pushed to nursing staff at one time is determined and used as the push quantity;

[0018] Based on the number of push notifications and the proportion of verification deviation questions in the question bank, it is determined whether dynamic updates of the verification images are required.

[0019] Furthermore, the method for determining the push processing strategy for questions without verification images is as follows:

[0020] Based on the identification and processing scheme for the update request question, determine the required threshold for the number of times the update request question can be pushed.

[0021] Based on the historical push data of the questions without verification images, determine the historical push count of the questions without verification images, and use the deviation between the historical push count and the required threshold of the push processing count to determine the push count deviation value of the questions without verification images.

[0022] The push processing strategy for questions without verification images is determined based on the deviation value of the number of pushes for questions without verification images.

[0023] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described intelligent nursing education management method based on image recognition when running the computer program.

[0024] Other features and advantages will be set forth in the following description, and the objects and other advantages of the invention are realized and obtained through the structures particularly pointed out in the description and the drawings.

[0025] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0026] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0027] Figure 1 This is a flowchart of an intelligent nursing education management method based on image recognition;

[0028] Figure 2 This is a flowchart illustrating the method for determining the dynamic update process of the verification images that needs to be performed.

[0029] Figure 3 This is a flowchart illustrating the method for determining the identification and processing scheme for questions requiring updates in questions where there is no verification image.

[0030] Figure 4 This is a flowchart illustrating the method for determining the push processing strategy for questions that do not require image verification.

[0031] Figure 5 It is a framework diagram of a computer system. Detailed Implementation

[0032] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this specification, and not all embodiments. Based on the embodiments of this specification, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this specification.

[0033] In this application, based on the composition data of questions with verification images that have a high error rate (i.e., questions that push the corresponding image when the answer is incorrect), and when the number of questions with verification images that have a high error rate is small, the identification and processing scheme for update-requirement questions that do not have verification images is adjusted, thereby improving the identification and processing efficiency of update-requirement questions.

[0034] Example 1

[0035] like Figure 1 As shown, this application provides an intelligent nursing education management method based on image recognition, specifically including:

[0036] S1 uses the question bank data of nursing staff as a basis to determine the question data where the answer does not have a verification image. Based on the question data where the verification image does not exist and the question push processing method, when it is determined that dynamic updating processing of verification images is required, the answer processing results of the questions with verification images are used to determine the identification and processing scheme of the questions with update requirements in the questions where the verification image does not exist.

[0037] Furthermore, the question with a verification image is one in which an image related to the answer is automatically pushed when the answer is incorrect.

[0038] Furthermore, the verification images include images of medicines, images demonstrating nursing procedures, and images of medical orders.

[0039] Furthermore, the method for pushing out the questions is determined based on the number of questions pushed to the nursing staff at one time during the mock exam or the actual exam.

[0040] Specifically, such as Figure 2 As shown, it is determined that dynamic updating of the verification image is required, specifically including:

[0041] Based on the question data that does not have a verification image, questions that do not have a verification image are identified and regarded as verification deviation questions. According to the composition data of the verification deviation questions in the question bank, the proportion of verification deviation questions in the question bank is determined.

[0042] Based on the question push processing method, the number of questions pushed to nursing staff at one time is determined and used as the push quantity;

[0043] Based on the number of push notifications and the proportion of verification deviation questions in the question bank, it is determined whether dynamic updates of the verification images are required.

[0044] It should be noted that when the proportion of verification deviation questions in the question bank is greater than the preset deviation proportion threshold, it is determined that dynamic updating of the verification images is required because the proportion of verification deviation questions is too large.

[0045] In one possible embodiment, when the proportion of verification deviation questions in the question bank is greater than 0.3, it is determined that dynamic updating of the verification images is required.

[0046] Additionally, it is understood that when the proportion of verification deviation questions in the question bank is not greater than the preset deviation proportion threshold, based on the number of pushes, if it is determined that the number of verification deviation questions in each push processing according to the preset push processing strategy does not meet the requirements, then because the number of verification deviation questions in each push processing is large, it is determined that dynamic updating of verification images is required, so that verification deviation questions with a high error rate can be promptly adapted for verification images.

[0047] It should be noted that the preset push processing strategy determines the number of verification deviation questions to be pushed based on the product of the proportion of verification deviation questions and the number of pushes. The remaining questions are not verification deviation questions and are pushed. In a possible specific embodiment, if the number of verification deviation questions is more than 20 in each push processing according to the preset push processing strategy, it is determined that dynamic updating of the verification image is required.

[0048] Optionally, determine whether dynamic updating of the verification image is required, specifically including:

[0049] Based on the question data where no verification image exists, questions without verification images are identified and designated as verification deviation questions. The number of verification deviation questions in the question bank is determined according to the composition data of the verification deviation questions in the question bank.

[0050] Based on the question push processing method, the number of questions pushed to nursing staff at one time is determined and used as the push quantity;

[0051] Based on the number of push notifications and the number of verification deviation questions in the question bank, it is determined whether dynamic updates of the verification images are required.

[0052] Furthermore, based on the number of push notifications and the number of verification deviation questions in the question bank, it is determined whether dynamic updating of the verification images is required, specifically including:

[0053] The required number of push notifications is determined by the ratio of the number of verification deviation questions in the question bank to the number of push notifications.

[0054] Based on the required number of push notifications, determine whether dynamic updating of the verification image is necessary.

[0055] In one possible specific embodiment, when the required number of pushes exceeds a preset threshold, it is determined that dynamic updating of the verification image is required.

[0056] Specifically, such as Figure 3 As shown, the method for determining the identification and processing scheme for the update requirement question in the question where there is no verification image is as follows:

[0057] Based on the solution processing results of questions with verification images, identify the nursing staff who answered the questions with verification images, and determine the error rate of the solutions to the questions with verification images based on the solutions of the nursing staff.

[0058] Based on the error rate, determine the constituent data of the questions containing verification images within the target error rate range;

[0059] By utilizing the compositional data of questions containing verification images within the target error rate range, a scheme for identifying and processing questions requiring updates in questions where verification images do not exist is determined.

[0060] It is understandable that when the proportion of questions with verification images in the question bank is less than a preset proportion threshold, since the number of questions with verification images is small, the identification and processing of the updated question is carried out based on the solution processing result where the number of push processing times is greater than the first push processing time threshold.

[0061] In one possible specific embodiment, when the proportion of questions with verification images in the question bank is less than 0.6, in order to enable nursing staff to better determine the error type after answering the questions, the identification processing of the updated requirement questions is performed based on the answer processing results where the number of push processing times is greater than the first push processing time threshold.

[0062] Additionally, it is understandable that when the proportion of questions with verification images in the question bank is not less than a preset proportion threshold, and when the proportion of questions with verification images in the target error rate range does not meet the requirements, since the number of questions with verification images in the high error rate range is relatively small, in order to enable nursing staff to better determine the error type after answering the questions, the identification processing of the updated requirement questions is performed based on the answer processing results where the number of push processing times is greater than the first push processing time threshold.

[0063] It should be noted that the error rate range of the target is the error rate range with an error rate greater than 60%.

[0064] In one possible specific embodiment, if the proportion of questions with verification images within the target error rate range is less than 0.5, then it is determined that the answer processing results that have been pushed more than 80 times will be used to identify potential updated questions. That is, the error rate when the number of push processing times is more than 80 times will be used to identify updated question requirements.

[0065] Furthermore, when the proportion of questions with verification images within the target error rate range meets the requirements, it is necessary to further determine the nursing staff data for questions with verification images. When the average number of questions with verification images in the push notifications for different nursing staff is less than the preset question number threshold, the nursing staff cannot fully access the questions with verification images due to the influence of the push strategy. Therefore, based on the answer processing results where the number of push processing times is greater than the first push processing time threshold, the identification and processing of the update requirement questions are carried out.

[0066] Additionally, it should be noted that when the average number of questions with verification images in the push notifications from different nursing staff is not less than the preset question number threshold, the identification and processing of update request questions will be carried out based on the solution processing results where the number of push notifications exceeds the second push notification number threshold.

[0067] In one possible specific embodiment, if the average number of questions with verification images in the push notifications from different nursing staff is less than 40, then it is determined that the identification processing of the updated requirement question will be performed based on the solution processing result where the number of push processing times is greater than the first push processing time threshold, where the first push processing time is greater than the second push processing time, for example, the second push processing time is 60 times.

[0068] Optionally, the method for determining the identification and processing scheme for the update requirement question in the question where there is no verification image is as follows:

[0069] Based on the solution processing results of questions with verification images, identify the nursing staff who answered the questions with verification images, and determine the error rate of the solutions to the questions with verification images based on the solutions of the nursing staff.

[0070] Based on the error rate, determine the composition data of the questions containing verification images within different error rate ranges;

[0071] By utilizing the composition data of questions with verification images existing within different error rate ranges, a recognition and processing scheme for update requirement questions in questions without verification images is determined.

[0072] Specifically, when the proportion of questions with verification images in the question bank is less than a preset proportion threshold, since the number of questions with verification images is small, the identification and processing of the updated question is carried out based on the solution processing results where the number of push processing times is greater than the first push processing time threshold.

[0073] Additionally, it can be understood that when the proportion of questions with verification images in the question bank is not less than a preset proportion threshold, the proportion of questions with verification images in the error rate range is taken as the verification proportion, and the error rate range where the verification proportion is less than the preset verification proportion threshold is taken as the deviation range. When the maximum value of the endpoint of the error rate range corresponding to the deviation range does not meet the requirements, the identification and processing of the updated requirement questions are carried out based on the solution processing results where the number of push processing times is greater than the first push processing time threshold.

[0074] In one possible specific embodiment, the deviation interval is an error rate interval where the verification ratio is less than 0.5. When the maximum value of the endpoint of the error rate interval corresponding to the deviation interval is greater than 0.7, the identification and processing of the update requirement question is carried out based on the solution processing result where the number of push processing times is greater than the first push processing time threshold.

[0075] It should be noted that the error rate range is based on 10% and divided into equal intervals.

[0076] Furthermore, when the maximum value of the error rate interval of the deviation interval meets the requirements, the identification and processing of the update requirement question is carried out based on the solution processing result where the number of push processing times is greater than the second push processing time threshold.

[0077] S2 determines the push processing strategy for questions without verification images based on the identification and processing scheme of the updated question and the historical push data of questions without verification images. Based on the push processing strategy, it determines the solution processing result of the questions without verification images. It uses the solution processing result to determine the updated question and uses the updated data of the updated question to determine whether the push processing scheme for questions with verification images needs to be optimized.

[0078] Specifically, such as Figure 4 As shown, the method for determining the push processing strategy for questions without verification images is as follows:

[0079] Based on the identification and processing scheme for the update request question, determine the required threshold for the number of times the update request question can be pushed.

[0080] Based on the historical push data of the questions without verification images, determine the historical push count of the questions without verification images, and determine the number of questions without verification images whose historical push count is greater than the demand threshold.

[0081] Based on the number of questions with no verification images that have been pushed more than the required threshold in the past, a push processing strategy for questions with no verification images is determined.

[0082] It is understandable that when the number of questions with no verification images that have been pushed more than the required threshold in the past meets the requirements, then a preset scheme will be used to determine the push processing strategy for all questions with no verification images.

[0083] Additionally, it should be noted that when the number of questions with no verification images whose historical push count exceeds the required threshold does not meet the requirement, in different push processing processes, only questions with no verification images whose historical push count does not exceed the required threshold will be pushed to different push processing processes. That is, a random method is used to determine whether questions with no verification images whose historical push count does not exceed the required threshold are pushed to different push processing processes.

[0084] Specifically, the update requirement question is a question where the answer processing result obtained according to the update requirement question identification and processing scheme does not meet the requirements and there is no verification image.

[0085] In a possible specific embodiment, if the identification processing scheme is to identify the update requirement question based on the answer processing result when the number of push processing times is greater than the first push processing time threshold, then if the number of push processing times for the question without a verification image is greater than the first push processing time threshold, and the error rate corresponding to the answer processing result is greater than 0.3, then the question without a verification image is determined to be an update requirement question.

[0086] It should be noted that the error rate is determined based on the ratio of the number of push notifications where the solution processing result is incorrect to the number of push notifications where the question does not have a verification image.

[0087] Specifically, determining whether the push processing scheme for questions containing verification images needs optimization includes:

[0088] The number of update requirement questions is determined using the updated data of the update requirement questions;

[0089] The number of times a question does not have a verification image is used to calculate the push frequency deviation of questions that do not have a verification image. Questions with a push frequency deviation within a preset push frequency range are considered as potential updated questions.

[0090] Based on the number of update-required questions and the number of potential update-required questions, determine whether the push processing scheme for questions with verification images needs to be optimized.

[0091] Furthermore, when the sum of the number of update request questions and the number of potential update questions exceeds a preset value, it is determined that the push processing scheme for questions with verification images needs to be optimized.

[0092] Furthermore, if the sum of the number of update request questions and the number of potential update questions is not greater than a preset value, then it is determined that the push processing scheme for questions with verification images does not need to be optimized.

[0093] In one possible specific embodiment, when the sum of the number of the update request questions and the number of potential update questions is greater than 50, it is determined that the push processing scheme for questions with verification images needs to be optimized.

[0094] Example 2

[0095] Secondly, such as Figure 5 As shown, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the above-described intelligent nursing education management method based on image recognition when running the computer program.

[0096] Furthermore, the method for determining the push processing strategy for questions without verification images is as follows:

[0097] Based on the identification and processing scheme for the update request question, determine the required threshold for the number of times the update request question can be pushed.

[0098] Based on the historical push data of the questions without verification images, determine the historical push count of the questions without verification images, and use the deviation between the historical push count and the required threshold of the push processing count to determine the push count deviation value of the questions without verification images.

[0099] The push processing strategy for questions without verification images is determined based on the deviation value of the number of pushes for questions without verification images.

[0100] It should be noted that the demand threshold is either the first push processing count threshold or the second push processing count threshold, and the specific threshold is determined according to the identification and processing scheme of the update demand question.

[0101] Specifically, the push frequency deviation value is the difference between the demand threshold and the historical push frequency of the question that does not contain a verification image.

[0102] It is understandable that when the number of questions with no verification images that have been pushed more than the required threshold in the past meets the requirements, then a preset scheme will be used to determine the push processing strategy for all questions with no verification images.

[0103] In one possible specific embodiment, when the number of questions with no verification images whose historical push count exceeds the demand threshold is not less than 60, a preset scheme is used to determine the push processing strategy for all questions with no verification images. That is, the preset push processing strategy determines the number of pushes for verification deviation questions based on the product of the proportion of verification deviation questions and the number of pushes, and determines the number of pushes for questions with no verification images based on the difference between the number of pushes and the number of pushes for verification deviation questions. From the number of pushes for questions with no verification images, the questions with no verification images that need to be pushed are randomly selected.

[0104] Additionally, it is understandable that when the number of questions with no verification images that have been pushed more than the required threshold does not meet the requirements, the push processing strategy for the questions with no verification images is determined based on the push count deviation value.

[0105] It is understood that the push processing strategy for questions with no verification images is determined based on the push count deviation value, specifically including:

[0106] When the deviation value of the number of pushes for the question without a verification image is within the preset deviation value range, the question without a verification image will be used as the push target in different push processing processes.

[0107] When the deviation value of the number of pushes for a question without a verification image is not within the preset deviation value range, a random method is used in different push processing processes to determine whether the question without a verification image is a push target.

[0108] In one possible specific embodiment, when the deviation value of the number of times the question without a verification image is pushed is less than 20, the question without a verification image will be used as the push target in different push processing processes.

[0109] Example 3

[0110] Furthermore, it is determined whether the push processing scheme for questions containing verification images needs to be optimized, specifically including:

[0111] The number of update requirement questions is determined using the updated data of the update requirement questions;

[0112] The deviation value of the number of times a question with a non-existent verification image is pushed is calculated based on the historical number of pushes where the verification image does not exist.

[0113] Based on the number of update request questions and the deviation value of the number of push notifications for questions without verification images, determine whether the push notification processing scheme for questions with verification images needs to be optimized.

[0114] It is understandable that when the number of update request questions exceeds the preset threshold, the push processing scheme for questions with verification images needs to be optimized in order to ensure that the number of questions with verification images in the push questions sent to nursing staff is relatively large.

[0115] In one possible specific embodiment, when the number of update request questions is greater than 20, it is determined that the push processing scheme for questions with verification images needs to be optimized.

[0116] Furthermore, when the number of update request questions is not greater than a preset threshold, it is also necessary to determine the push frequency deviation of questions without verification images. When the number of questions with push frequency deviation within the preset push frequency range does not meet the requirements, on the one hand, the number of update request questions is small, and on the other hand, it can be quickly determined whether the number of update request questions without verification images is small. Therefore, based on this, it is determined that the push processing scheme for questions with verification images does not need to be optimized.

[0117] In one possible embodiment, if the number of questions with a push count deviation value between 0 and 15 is less than 30, then it is determined that the push processing scheme for questions with verification images does not need to be optimized.

[0118] Understandably, when the number of questions with push count deviation values ​​within the preset push count range meets the requirements, the average error rate of the questions with push count deviation values ​​within the preset push count range is determined. If the average error rate of the questions with push count deviation values ​​within the preset push count range is less than the preset error rate threshold, then on the one hand, the number of questions requiring updates is small, and on the other hand, the number of questions without verification images that can be quickly determined to be update requirements is small. Therefore, based on this, it is determined that the push processing scheme for questions with verification images does not need to be optimized.

[0119] In one possible specific embodiment, if the average error rate of questions within a preset push count range is less than 0.3, then it is determined that the push processing scheme for questions with verification images does not need to be optimized.

[0120] It should be noted that if the average error rate of questions within the preset push number range is not less than the preset error rate threshold, then if the number of update request questions is within the preset update request question number range, the push processing scheme for questions with verification images needs to be optimized. Conversely, if the number of update request questions is not within the preset update request question number range, the push processing scheme for questions with verification images does not need to be optimized.

[0121] In one possible specific embodiment, if the number of update request questions is between 10 and 20, then it is determined that the push processing scheme for questions with verification images needs to be optimized.

[0122] It is understandable that when the push processing scheme for questions with verification images needs to be optimized, the number of questions with verification images pushed will be adjusted based on the number of questions requiring updates and the number of questions whose push frequency deviation is within a preset push frequency range. Specifically, this includes:

[0123] The number of verification deviation questions to be pushed is no longer determined by multiplying the proportion of verification deviation questions by the number of pushes. Instead, the total number is the sum of the number of update requirement questions and the number of questions whose push number deviation is within a preset push number range. The number of verification deviation questions minus the total number is the identification number. The number of verification deviation questions is determined by multiplying the ratio of the identification number to the number of questions in the question bank by the push number corresponding to the preset push processing strategy. Otherwise, the number of questions with verification deviation questions is the number of pushes corresponding to the preset push processing strategy minus the number of pushes, thereby increasing the number of pushes for questions with verification images.

[0124] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments of apparatus, devices, and non-volatile computer storage media are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0125] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0126] The above description is merely one or more embodiments of this specification and is not intended to limit this specification. Various modifications and variations can be made to the one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of this specification.

Claims

1. A method for intelligent nursing education management based on image recognition, characterized in that, Specifically, it includes: Based on the question bank data of nursing staff, the question data in which the answer does not have a verification image is identified. Based on the question data in which the verification image does not exist and the question push processing method, when it is determined that dynamic updating processing of verification images is required, the answer processing results of the questions with verification images are used to determine the identification and processing scheme of the questions in which the verification image does not exist. Based on the identification and processing scheme of the updated question and the historical push data of questions without verification images, the push processing strategy for questions without verification images is determined. Based on the push processing strategy, the solution processing result of the questions without verification images is determined. The updated question is determined using the solution processing result. The updated data of the updated question is used to determine whether the push processing scheme for questions with verification images needs to be optimized. The verification image needs to be dynamically updated, specifically including: Based on the question data that does not have a verification image, questions that do not have a verification image are identified and regarded as verification deviation questions. According to the composition data of the verification deviation questions in the question bank, the proportion of verification deviation questions in the question bank is determined. Based on the question push processing method, the number of questions pushed to nursing staff at one time is determined and used as the push quantity; Based on the number of push notifications and the proportion of verification deviation questions in the question bank, it is determined whether dynamic updating of verification images is required. The method for determining the identification and processing scheme for update requirement questions in questions where no verification image exists is as follows: Based on the solution processing results of questions with verification images, identify the nursing staff who answered the questions with verification images, and determine the error rate of the solutions to the questions with verification images based on the solutions of the nursing staff. Based on the error rate, determine the constituent data of the questions containing verification images within the target error rate range; Using the compositional data of questions with verification images within the target error rate range, a scheme for identifying and processing questions requiring updates in questions without verification images is determined. The method for determining the push strategy for questions that do not have verification images is as follows: Based on the identification and processing scheme for the update request question, determine the required threshold for the number of times the update request question can be pushed. Based on the historical push data of the questions without verification images, determine the historical push count of the questions without verification images, and determine the number of questions without verification images whose historical push count is greater than the demand threshold. Based on the number of questions with no verification images whose historical push count exceeds the demand threshold, a push processing strategy for questions with no verification images is determined. The question whose answer contains a verification image is one that automatically pushes an image related to the answer when the answer is incorrect.

2. The intelligent nursing education management method based on image recognition as described in claim 1, characterized in that, The verification images include images of medicines, images demonstrating nursing procedures, and images of medical orders.

3. The intelligent nursing education management method based on image recognition as described in claim 1, characterized in that, The method for pushing out the questions is determined based on the number of questions pushed to nursing staff at one time during the mock exam or the actual exam.

4. The intelligent nursing education management method based on image recognition as described in claim 1, characterized in that, When the proportion of verification deviation questions in the question bank exceeds a preset deviation proportion threshold, it is determined that dynamic updating of the verification images is required.

5. The intelligent nursing education management method based on image recognition as described in claim 1, characterized in that, Determine whether the push processing scheme for questions containing verification images needs optimization, specifically including: The number of update requirement questions is determined using the updated data of the update requirement questions; The deviation value of the number of times a question with a non-existent verification image is pushed is calculated based on the historical number of pushes where the verification image does not exist. Based on the number of update request questions and the deviation value of the number of push notifications for questions without verification images, determine whether the push notification processing scheme for questions with verification images needs to be optimized.

6. The intelligent nursing education management method based on image recognition as described in claim 1, characterized in that, When the push processing scheme for questions with verification images needs to be optimized, the number of questions with verification images pushed is adjusted based on the number of questions requiring updates and the number of questions whose push frequency deviation is within the preset push frequency range.

7. A computer system, comprising: A memory and processor connected by communication, and a computer program stored in the memory and capable of running on the processor, characterized in that, when the processor runs the computer program, it executes an intelligent nursing education management method based on image recognition as described in any one of claims 1-6.