Gynecological and obstetrical nursing information management method and system

Abstract

The invention relates to the field of information management, in particular to a gynaecology and obstetrics nursing information management method and system. The gynaecology and obstetrics nursing information management system comprises a gynaecology and obstetrics nursing information acquisition module, a network environment data acquisition module, an encryption strategy selection module, a gynaecology and obstetrics nursing information encryption transmission module and a real-time training module. According to the method, the corresponding encryption strategy is quickly selected for the current network environment through the encryption strategy selection model, and then the gynecological nursing information is encrypted and transmitted through the selected encryption strategy, so that the network transmission performance and the resource utilization rate in the network transmission process can be improved on the basis of ensuring the transmission security; and the encryption strategy selection model is trained in real time through reinforcement learning, so that the encryption strategy selection model can better fit an actual network environment.

Description

Technical Field

[0001] This invention relates to the field of information management, specifically to a method and system for managing obstetric and gynecological nursing information. Background Technology

[0002] In obstetrics and gynecology nursing information management, the secure transmission of information is of paramount importance. This information includes pregnant and postpartum women's health data, medical records, nursing plans, medication use records, etc., involving personal privacy and the confidentiality of medical data.

[0003] Existing technologies generally use fixed encryption algorithms and parameter settings, maintaining the same encryption strategy regardless of changes in network environment and data sensitivity. This approach cannot adapt to the dynamic needs of different network environments and data characteristics, resulting in excessively high encryption strength in some cases, leading to reduced transmission efficiency and wasted system resources; while in other cases, the encryption strength is insufficient, posing a risk of data leakage and tampering. Summary of the Invention

[0004] This invention uses an encryption strategy selection model to quickly select the corresponding encryption strategy for the current network environment, and then uses the selected encryption strategy to encrypt and transmit obstetric and gynecological nursing information. This can improve network transmission performance and resource utilization during network transmission while ensuring transmission security. Furthermore, the encryption strategy selection model is trained in real time through reinforcement learning, which makes the encryption strategy selection model more closely match the actual network environment.

[0005] A method for managing obstetric and gynecological nursing information includes: Obtain information on obstetric and gynecological nursing; Obtain current network environment data; The current network environment data is fed into the encryption strategy selection model for processing, and the encryption strategy is output. The key generator is configured with an encryption strategy, and a key pair is generated using the configured key generator. The obstetrics and gynecology nursing information is then encrypted using the key pair to obtain encrypted obstetrics and gynecology nursing information. Finally, the encrypted obstetrics and gynecology nursing information is transmitted to the cloud server. The encryption strategy selection model is built on a decision tree model, and the positive training samples for encryption strategy selection used to train the encryption strategy selection model are generated through a population optimization algorithm. The management of obstetric and gynecological nursing information also includes real-time training of the encryption strategy selection model through reinforcement learning.

[0006] As a preferred aspect of the present invention, training the encryption strategy selection model specifically includes the following steps: Obtain several positive training samples for encryption strategy selection. These samples include feature network environment data and the corresponding optimal encryption strategy. Combine all the positive training samples into a positive training set for encryption strategy selection. Input the positive training set into the parameter-initialized encryption strategy selection model for training. Obtain the accuracy of the encryption strategy selection model and determine whether the accuracy is higher than a preset threshold. If the accuracy is higher than the preset threshold, output the trained encryption strategy selection model. Otherwise, continue training the encryption strategy selection model using the positive training set.

[0007] As a preferred aspect of the present invention, the positive training samples for selecting encryption strategies are generated through a population optimization algorithm, specifically including the following steps: Featured network environment data are selected sequentially from the network environment database. The optimal encryption strategy corresponding to the selected featured network environment data is determined by the population optimization algorithm. Then, the selected featured network environment data and the corresponding optimal encryption strategy are combined to form an encryption strategy selection positive training sample. The network environment database stores several sets of characteristic network environment data. The construction of the network environment database includes the following steps: acquiring several sets of network environment data, performing cluster analysis on all acquired network environment data, and outputting several network environment data clusters F. i Let i = 1, 2, 3, ..., I, where I is the total number of network environment data clusters. Calculate F for each network environment data cluster. i The corresponding weight percentage δ i Network environment data cluster F i Weighting percentage δ i For network environment data cluster F i The ratio of the number of network environment data points to the total number of network environment data points, for each network environment data cluster F. i Perform the following operations to cluster network environment data cluster F i Randomly select floor (δ) i ·Q i ) network environment data points are stored as feature network environment data in the network environment database, where floor is the floor function and Q is the floor function. i For network environment data cluster F i The total amount of data in the network environment.

[0008] As a preferred aspect of the present invention, the optimal encryption strategy corresponding to the selected characteristic network environment data is determined by a swarm optimization algorithm, specifically including the following steps: Construct several individual cryptographic strategies, then combine all the individual cryptographic strategies into a simulated population set; set the maximum number of iterations; For each encryption policy simulation individual, calculate the fitness of the corresponding encryption policy simulation individual; Based on the fitness of individuals corresponding to the encryption strategy, the simulated population set is simulated and iterated using a genetic algorithm; When the number of iterations reaches the maximum, the optimal encryption strategy corresponding to the selected feature network environment data is output as the simulation individual with the highest fitness.

[0009] As a preferred aspect of the present invention, the specific steps for calculating the fitness of the simulated individual under the encryption strategy are as follows: The current characteristic network environment data is concatenated with the encryption policy simulation individuals to construct the data to be evaluated. The data to be evaluated is then fed into the encryption policy evaluation model for processing, and the encryption policy evaluation value is output. The output encryption policy evaluation value is used as the fitness of the encryption policy simulation individual.

[0010] As a preferred aspect of the present invention, the encryption strategy evaluation model is established based on a BP neural network, and the training of the encryption strategy evaluation model specifically includes the following steps: Obtain several evaluation training samples, which include network environment data, encryption policies, and feedback values. The corresponding feedback values ​​are weighted sums of security evaluation values, performance evaluation values, and cost-benefit evaluation values. Combine all evaluation training samples into an evaluation training set, and then feed the evaluation training set into the parameter-initialized encryption policy evaluation model for training. Using the feedback values ​​as the target, calculate the loss value and determine whether the loss value is within a preset range. If the loss value is within the preset range, output the trained encryption policy evaluation model; otherwise, continue training the encryption policy evaluation model using the evaluation training set.

[0011] As a preferred aspect of the present invention, the encryption strategy selection model is trained in real time using reinforcement learning, specifically including the following steps: After acquiring network environment data and the corresponding encryption policy, obtain the feedback value after executing the corresponding encryption policy; combine the network environment data and encryption policy into real-time training samples, and feed the real-time training samples into the encryption policy evaluation model and the target encryption policy evaluation model respectively, and output the encryption policy evaluation value and the target encryption policy evaluation value. The encryption strategy selection model is trained in real time based on the difference between the target encryption strategy evaluation value and the feedback value; the encryption strategy evaluation model is trained in real time based on the difference between the encryption strategy evaluation value and the feedback value. At preset intervals, the original target encryption strategy evaluation model is replaced by the encryption strategy evaluation model as the target encryption strategy evaluation model; and in the initial state, the encryption strategy evaluation model and the target encryption strategy evaluation model are consistent.

[0012] The present invention also provides an obstetrics and gynecology nursing information management system, comprising: The obstetrics and gynecology nursing information acquisition module is used to acquire obstetrics and gynecology nursing information; The network environment data acquisition module is used to acquire current network environment data; The encryption strategy selection module is used to input the current network environment data into the encryption strategy selection model for processing and output encryption strategies. The encryption strategy selection model is built based on the decision tree model, and the positive training samples for encryption strategy selection used to train the encryption strategy selection model are generated through population optimization algorithm. The obstetrics and gynecology nursing information encryption transmission module is used to configure the key generator through encryption strategy, generate key pairs through the configured key generator, encrypt the obstetrics and gynecology nursing information through the key pairs, obtain encrypted obstetrics and gynecology nursing information, and finally transmit the encrypted obstetrics and gynecology nursing information to the cloud server. The real-time training module is used to train the encryption strategy selection model in real time through reinforcement learning.

[0013] The present invention has the following advantages: 1. This invention uses an encryption strategy selection model to quickly select the corresponding encryption strategy for the current network environment, and then uses the selected encryption strategy to encrypt and transmit obstetric and gynecological nursing information. This can improve network transmission performance and resource utilization during network transmission while ensuring transmission security. Furthermore, the encryption strategy selection model is trained in real time through reinforcement learning, which makes the encryption strategy selection model more closely match the actual network environment.

[0014] 2. This invention performs cluster analysis on several network environment data sets, selects network environment data from different network environment data clusters in a proportional manner as feature network environment data, and further constructs a network environment database. The feature network environment data in the network environment database can roughly reflect different network conditions. The encryption strategy selection model is trained using positive training samples composed of these feature network environment data and their corresponding optimal encryption strategies, which can improve the accuracy of the encryption strategy selection model for encryption strategy output.

[0015] 3. Obtain feedback values ​​after executing the output encryption strategy under different network environments, and train the encryption strategy selection model in real time based on the difference between the feedback values ​​and the target encryption strategy evaluation value output by the target encryption strategy evaluation model, so that the encryption strategy output by the encryption strategy selection model can better match the actual network conditions; at the same time, setting the target encryption strategy evaluation value can ensure the stability of training over a period of time. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the obstetrics and gynecology nursing information management system used in an embodiment of the present invention. Detailed Implementation

[0017] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of this invention.

[0018] Example 1: A method for managing obstetric and gynecological nursing information, comprising: Obtaining obstetric and gynecological nursing information includes patient vital sign monitoring data and nursing guidance. Patient vital sign monitoring data can be uploaded and obtained through various vital sign monitoring devices, and nursing guidance can be obtained through conversations, records, and other methods. As this obstetric and gynecological nursing information is the patient's personal privacy data, it needs to be kept confidential to ensure the patient's information security and to achieve the management of obstetric and gynecological nursing information. Obtain current network environment data, including current network bandwidth, network latency, and device load. This data allows for analysis of the current network situation. Different encryption strategies are needed to encrypt obstetric and gynecological nursing information depending on the network conditions. The current network environment data is fed into the encryption strategy selection model for processing, and the encryption strategy is output. The encryption strategy includes different encryption algorithms, key lengths and encryption modes. By selecting the corresponding encryption strategy for different network environments, the performance of network transmission and the utilization rate of resources during network transmission can be improved while ensuring transmission security. The key generator is configured with an encryption strategy, and a key pair is generated using the configured key generator. The obstetrics and gynecology nursing information is then encrypted using the key pair to obtain encrypted obstetrics and gynecology nursing information. Finally, the encrypted obstetrics and gynecology nursing information is transmitted to the cloud server. The encryption strategy selection model is built on the decision tree model, which is a tree-based algorithm including root nodes, internal nodes, and leaf nodes. The positive training samples for encryption strategy selection used to train the encryption strategy selection model are generated through a population optimization algorithm. It should be noted that the encryption strategy selection model built on the decision tree model can quickly obtain encryption strategies based on rule-based partitioning, which is extremely important in information management processes that require efficiency. In the process of managing obstetric and gynecological nursing information, reinforcement learning is also used to train the encryption strategy selection model in real time. Due to the uncertainty of the network environment, the initially trained encryption strategy selection model may not be able to cope with all network conditions. Therefore, reinforcement learning is used to achieve interaction with the real-time network environment and collect real-time feedback to optimize the encryption strategy selection model, so that the encryption strategy selection model is more in line with the actual network environment and obtains the encryption strategy with the highest adaptability.

[0019] This application uses an encryption strategy selection model to quickly select the corresponding encryption strategy for the current network environment, and then uses the selected encryption strategy to encrypt and transmit obstetric and gynecological nursing information. This can improve network transmission performance and resource utilization during network transmission while ensuring transmission security. Furthermore, the encryption strategy selection model is trained in real time through reinforcement learning, which makes the encryption strategy selection model more closely match the actual network environment.

[0020] Training a model for selecting encryption strategies involves the following steps: Several positive training samples for encryption strategy selection are obtained. These samples include feature network environment data and the corresponding optimal encryption strategy. It should be noted that these positive training samples are obtained by simulating the optimal encryption strategy under different standard network environments using a population optimization algorithm. All these positive training samples are combined into a positive training set for encryption strategy selection. This training set is then fed into a parameter-initialized encryption strategy selection model for training. During training, some features are selected as root nodes from the network environment data, and nodes are selected layer by layer based on the information entropy gain, with pruning used to prevent overfitting, until the target condition is met, such as conditional entropy being less than a set threshold. The accuracy of the encryption strategy selection model is then obtained, and it is determined whether the accuracy exceeds a preset threshold. This preset threshold is set by the developers based on experience. If the accuracy exceeds the preset threshold, the trained encryption strategy selection model is output; otherwise, the model continues to be trained using the positive training set.

[0021] The process of generating encryption strategies and selecting positive training samples through a swarm optimization algorithm includes the following steps: Featured network environment data are selected sequentially from the network environment database. The optimal encryption strategy corresponding to the selected featured network environment data is determined by the population optimization algorithm. Then, the selected featured network environment data and the corresponding optimal encryption strategy are combined to form an encryption strategy selection positive training sample. The network environment database stores several sets of characteristic network environment data. The construction of the network environment database includes the following steps: acquiring several sets of network environment data, performing cluster analysis on all acquired network environment data, using the k-means algorithm, and outputting several network environment data clusters F. i Let i = 1, 2, 3, ..., I, where I is the total number of network environment data clusters. Calculate F for each network environment data cluster. i The corresponding weight percentage δ i Network environment data cluster F i Weighting percentage δ i For network environment data cluster F i The ratio of the number of network environment data points to the total number of network environment data points, for each network environment data cluster F. i Perform the following operations to cluster network environment data cluster F i Randomly select floor (δ) i ·Q i ) network environment data points are stored as feature network environment data in the network environment database, where floor is the floor function and Q is the floor function. i For network environment data cluster F i The total amount of data in the network environment.

[0022] This application performs cluster analysis on several network environment data sets, selects network environment data from different network environment data clusters according to a certain proportion as feature network environment data, and further constructs a network environment database. The feature network environment data in the network environment database can roughly reflect different network conditions. Using these feature network environment data sets and their corresponding optimal encryption strategies as positive training samples to train the encryption strategy selection model can improve the accuracy of the encryption strategy selection model for encryption strategy output.

[0023] The optimal encryption strategy for the selected characteristic network environment data is determined using a swarm optimization algorithm, specifically including the following steps: Construct several individual encryption strategy simulations, and then combine all the individual encryption strategy simulations into a simulated population set. It should be noted that in the process of constructing individual encryption strategy simulations, discrete data such as encryption algorithms and encryption modes can be assigned values ​​using encoding, while key length can be assigned values ​​using continuous data; set the maximum number of iterations; For each encryption policy simulation individual, the fitness of the corresponding encryption policy simulation individual is calculated. The fitness of the encryption policy simulation individual can reflect whether the encryption policy corresponding to the encryption policy simulation individual is suitable for the current characteristic network environment data. The specific steps for calculating the fitness of individuals corresponding to the encryption strategy simulation are as follows: The current characteristic network environment data is concatenated with the encryption policy simulation individuals to construct the data to be evaluated. The data to be evaluated is then fed into the encryption policy evaluation model for processing, and the encryption policy evaluation value is output. The output encryption policy evaluation value is used as the fitness of the encryption policy simulation individual. Based on the fitness of individuals corresponding to the encryption strategy, the simulated population set is simulated and iterated through a genetic algorithm. During this process, selection, recombination and mutation operations are performed. It should be noted that the mutation of discrete data is to transform it into other codes, while the mutation of continuous data is to transform it into a random number within a range. When the number of iterations reaches the maximum, the optimal encryption strategy corresponding to the selected feature network environment data is output as the simulation individual with the highest fitness.

[0024] The encryption policy evaluation model is built based on a backpropagation neural network. The training of the encryption policy evaluation model includes the following steps: Several evaluation training samples are obtained, including network environment data, encryption strategies, and feedback values. It should be noted that these training samples are acquired during actual data transmission, and the corresponding feedback values ​​are a weighted sum of security assessment values, performance assessment values, and cost-benefit assessment values. The security assessment evaluates the encryption strategy's ability to resist various attacks, and can employ methods such as cryptographic attack complexity analysis. The performance assessment evaluates the performance after implementing the encryption strategy, such as a comprehensive analysis of decryption speed, data transmission rate, and network latency. The cost-benefit assessment evaluates the resource consumption of implementing the encryption strategy. All evaluation training samples are combined into an evaluation training set, which is then fed into a parameter-initialized encryption strategy evaluation model for training. Using the feedback values ​​as the target, a loss value is calculated, and it is determined whether the loss value falls within a preset range. The preset range is determined by the developers. If the loss value is within the preset range, the trained encryption strategy evaluation model is output; otherwise, the model is further trained using the evaluation training set.

[0025] The encryption strategy selection model is trained in real time using reinforcement learning, specifically including the following steps: After acquiring network environment data and the corresponding encryption policy, obtain the feedback value after executing the corresponding encryption policy; combine the network environment data and encryption policy into real-time training samples, and feed the real-time training samples into the encryption policy evaluation model and the target encryption policy evaluation model respectively, and output the encryption policy evaluation value and the target encryption policy evaluation value. The encryption strategy selection model is trained in real time based on the difference between the target encryption strategy evaluation value and the feedback value. Specifically, the parameters in the encryption strategy selection model are adjusted to reduce the difference between the target encryption strategy evaluation value and the feedback value. The encryption strategy evaluation model is trained in real time based on the difference between the encryption strategy evaluation value and the feedback value. At preset intervals, the original target encryption strategy evaluation model is replaced by the encryption strategy evaluation model as the target encryption strategy evaluation model; and in the initial state, the encryption strategy evaluation model and the target encryption strategy evaluation model are consistent.

[0026] This application obtains feedback values ​​after executing the output encryption strategy under different network environments, and trains the encryption strategy selection model in real time based on the difference between the feedback values ​​and the target encryption strategy evaluation value output by the target encryption strategy evaluation model, so that the encryption strategy output by the encryption strategy selection model can better conform to the actual network conditions; at the same time, setting the target encryption strategy evaluation value can ensure the stability of training over a period of time.

[0027] Example 2: A gynecological and obstetric nursing information management system, such as... Figure 1 As shown, it includes: The obstetrics and gynecology nursing information acquisition module is used to acquire obstetrics and gynecology nursing information, including patient vital sign monitoring data and nursing guidance. Patient vital sign monitoring data can be uploaded and acquired through various vital sign monitoring devices, and nursing guidance can be acquired through conversations, records, and other methods. As this obstetrics and gynecology nursing information is the patient's personal privacy data, it needs to be kept confidential to ensure patient information security and achieve management of obstetrics and gynecology nursing information. The network environment data acquisition module is used to acquire current network environment data, including current network bandwidth, network latency, and device load. This network environment data can be used to analyze the current network situation. Different encryption strategies are required to encrypt obstetric and gynecological nursing information for different network conditions. The encryption strategy selection module is used to input the current network environment data into the encryption strategy selection model for processing and output encryption strategies. The encryption strategies include different encryption algorithms, key lengths, and encryption modes. By selecting the corresponding encryption strategies for different network environments, the performance of network transmission and the utilization rate of resources during network transmission can be improved while ensuring transmission security. The encryption strategy selection model is built based on the decision tree model, which is a tree-based algorithm including root nodes, internal nodes, and leaf nodes. The positive training samples for encryption strategy selection used to train the encryption strategy selection model are generated through a population optimization algorithm. It should be noted that the encryption strategy selection model based on the decision tree model can quickly obtain encryption strategies based on rule-based partitioning, which is extremely important in information management processes that require efficiency. The obstetrics and gynecology nursing information encryption transmission module is used to configure the key generator through encryption strategy, generate key pairs through the configured key generator, encrypt the obstetrics and gynecology nursing information through the key pairs, obtain encrypted obstetrics and gynecology nursing information, and finally transmit the encrypted obstetrics and gynecology nursing information to the cloud server. The real-time training module is used to train the encryption strategy selection model in real time through reinforcement learning. Due to the uncertainty of the network environment, the initially trained encryption strategy selection model may not be able to cope with all network conditions. Therefore, reinforcement learning is used to interact with the real-time network environment and collect real-time feedback to optimize the encryption strategy selection model, making the encryption strategy selection model more in line with the actual network environment and obtaining the encryption strategy with the highest adaptability.

[0028] It should be understood that those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims. Parts not described in detail in this specification are prior art known to those skilled in the art.

Claims

1. A method for managing obstetric and gynecological nursing information, characterized in that, include: Obtain information on obstetric and gynecological nursing; Obtain current network environment data; The current network environment data is fed into the encryption strategy selection model for processing, and the encryption strategy is output. The key generator is configured with an encryption strategy, and a key pair is generated using the configured key generator. The obstetrics and gynecology nursing information is then encrypted using the key pair to obtain encrypted obstetrics and gynecology nursing information. Finally, the encrypted obstetrics and gynecology nursing information is transmitted to the cloud server. The encryption strategy selection model is built on a decision tree model, and the positive training samples for encryption strategy selection used to train the encryption strategy selection model are generated through a population optimization algorithm. The management of obstetric and gynecological nursing information also includes real-time training of the encryption strategy selection model through reinforcement learning.

2. The method for managing obstetric and gynecological nursing information according to claim 1, characterized in that, Training a model for selecting encryption strategies involves the following steps: Obtain several positive training samples for encryption strategy selection. These samples include feature network environment data and the corresponding optimal encryption strategy. Combine all the positive training samples into a positive training set for encryption strategy selection. Input the positive training set into the parameter-initialized encryption strategy selection model for training. Obtain the accuracy of the encryption strategy selection model and determine whether the accuracy is higher than a preset threshold. If the accuracy is higher than the preset threshold, output the trained encryption strategy selection model. Otherwise, continue training the encryption strategy selection model using the positive training set.

3. The method for managing obstetric and gynecological nursing information according to claim 2, characterized in that, The process of generating encryption strategies and selecting positive training samples through a swarm optimization algorithm includes the following steps: Featured network environment data are selected sequentially from the network environment database. The optimal encryption strategy corresponding to the selected featured network environment data is determined by the population optimization algorithm. Then, the selected featured network environment data and the corresponding optimal encryption strategy are combined to form an encryption strategy selection positive training sample. The network environment database stores several sets of characteristic network environment data. The construction of the network environment database includes the following steps: acquiring several sets of network environment data, performing cluster analysis on all acquired network environment data, and outputting several network environment data clusters F. i Let i = 1, 2, 3, ..., I, where I is the total number of network environment data clusters. Calculate F for each network environment data cluster. i The corresponding weight percentage δ i Network environment data cluster F i Weighting percentage δ i For network environment data cluster F i The ratio of the number of network environment data points to the total number of network environment data points, for each network environment data cluster F. i Perform the following operations to cluster network environment data cluster F i Randomly select floor (δ) i ·Q i ) network environment data points are stored as feature network environment data in the network environment database, where floor is the floor function and Q is the floor function. i For network environment data cluster F i The total amount of data in the network environment.

4. The method for managing obstetric and gynecological nursing information according to claim 3, characterized in that, The optimal encryption strategy for the selected characteristic network environment data is determined using a swarm optimization algorithm, specifically including the following steps: Construct several individual cryptographic strategies, then combine all the individual cryptographic strategies into a simulated population set; set the maximum number of iterations; For each encryption policy simulation individual, calculate the fitness of the corresponding encryption policy simulation individual; Based on the fitness of individuals corresponding to the encryption strategy, the simulated population set is simulated and iterated using a genetic algorithm; When the number of iterations reaches the maximum, the optimal encryption strategy corresponding to the selected feature network environment data is output as the simulation individual with the highest fitness.

5. The method for managing obstetric and gynecological nursing information according to claim 4, characterized in that, The specific steps for calculating the fitness of individuals corresponding to the encryption strategy simulation are as follows: The current characteristic network environment data is concatenated with the encryption policy simulation individuals to construct the data to be evaluated. The data to be evaluated is then fed into the encryption policy evaluation model for processing, and the encryption policy evaluation value is output. The output encryption policy evaluation value is used as the fitness of the encryption policy simulation individual.

6. The method for managing obstetric and gynecological nursing information according to claim 5, characterized in that, The encryption policy evaluation model is built based on a backpropagation neural network. The training of the encryption policy evaluation model includes the following steps: Obtain several evaluation training samples, which include network environment data, encryption policies, and feedback values. The corresponding feedback values ​​are weighted sums of security evaluation values, performance evaluation values, and cost-benefit evaluation values. Combine all evaluation training samples into an evaluation training set, and then feed the evaluation training set into the parameter-initialized encryption policy evaluation model for training. Using the feedback values ​​as the target, calculate the loss value and determine whether the loss value is within a preset range. If the loss value is within the preset range, output the trained encryption policy evaluation model; otherwise, continue training the encryption policy evaluation model using the evaluation training set.

7. The method for managing obstetric and gynecological nursing information according to claim 6, characterized in that, The encryption strategy selection model is trained in real time using reinforcement learning, specifically including the following steps: After acquiring network environment data and the corresponding encryption policy, obtain the feedback value after executing the corresponding encryption policy; combine the network environment data and encryption policy into real-time training samples, and feed the real-time training samples into the encryption policy evaluation model and the target encryption policy evaluation model respectively, and output the encryption policy evaluation value and the target encryption policy evaluation value. The encryption strategy selection model is trained in real time based on the difference between the target encryption strategy evaluation value and the feedback value; the encryption strategy evaluation model is trained in real time based on the difference between the encryption strategy evaluation value and the feedback value. At preset intervals, the original target encryption strategy evaluation model is replaced by the encryption strategy evaluation model as the target encryption strategy evaluation model; and in the initial state, the encryption strategy evaluation model and the target encryption strategy evaluation model are consistent.

8. A gynecological and obstetric nursing information management system, characterized in that, The system employs a method for managing obstetric and gynecological nursing information as described in any one of claims 1-7, comprising: The obstetrics and gynecology nursing information acquisition module is used to acquire obstetrics and gynecology nursing information; The network environment data acquisition module is used to acquire current network environment data; The encryption strategy selection module is used to input the current network environment data into the encryption strategy selection model for processing and output encryption strategies. The encryption strategy selection model is built based on the decision tree model, and the positive training samples for encryption strategy selection used to train the encryption strategy selection model are generated through population optimization algorithm. The obstetrics and gynecology nursing information encryption transmission module is used to configure the key generator through encryption strategy, generate key pairs through the configured key generator, encrypt the obstetrics and gynecology nursing information through the key pairs, obtain encrypted obstetrics and gynecology nursing information, and finally transmit the encrypted obstetrics and gynecology nursing information to the cloud server. The real-time training module is used to train the encryption strategy selection model in real time through reinforcement learning.

Images