Prostate cancer postoperative health management propaganda method and system based on Internet +

Abstract

The invention provides a prostate cancer postoperative health management propaganda method and system based on Internet +. The method comprises the following steps: acquiring historical postoperative health data; discretizing each health feature in the encrypted historical postoperative health data to obtain a plurality of health discrete features, determining feature gain factors, and mapping the historical postoperative health data according to all the feature gain factors to obtain a mapping data set; determining data exclusion degrees among the mapping data points in the mapping data set, converting the mapping data set into postoperative health generalization data according to all the data exclusion degrees, and training a health assessment model by using the postoperative health generalization data; and obtaining postoperative health data of the patient, inputting the postoperative health data into the health assessment model for health assessment, and pushing personalized health propaganda information according to a health assessment result. By adopting the scheme, a more accurate health assessment model can be constructed, so that the accuracy of the generated personalized propaganda information is improved.

Description

Technical Field

[0001] The present application relates to the technical field of postoperative health management, and more specifically, to an Internet+-based prostate cancer postoperative health management promotion method and system. Background Art

[0002] With the rapid development of Internet + healthcare, digital health management models are playing an increasingly important role in the rehabilitation process of patients after prostate cancer surgery. Traditional postoperative health management often relies on regular outpatient follow-up and patient self-management, but due to information lag, limited medical resources and low patient compliance, the postoperative rehabilitation effect may be affected. Internet +-based prostate cancer postoperative health management promotion, through the integration of artificial intelligence, big data, mobile Internet and telemedicine technologies, provides patients with continuous, accurate and personalized health promotion and intervention, helping patients to recover scientifically and improve their quality of life.

[0003] At present, the content of Internet health education is mainly general popular science information, but there are large individual differences among postoperative patients, including age, underlying diseases, postoperative complications, living habits, etc. How to build a more accurate health assessment model requires more in-depth algorithm optimization and data analysis. At the same time, insufficient patient compliance is also a major difficulty in postoperative health management. Many patients may pay more attention to rehabilitation management in the early postoperative period, but as time goes by, they are prone to slackness, resulting in a decrease in postoperative review rate and weakened health management effect. Therefore, how to build a more accurate health assessment model to improve the accuracy of the generated personalized promotional information is a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides an Internet+-based prostate cancer postoperative health management promotion method and system, which can build a more accurate health assessment model to improve the accuracy of the generated personalized promotion information.

[0005] In a first aspect, the present application provides an Internet+-based prostate cancer postoperative health management promotion method, comprising the following steps: Obtaining historical postoperative health data of patients undergoing prostate cancer surgery on an Internet platform, and then encrypting the historical postoperative health data; Discretize each health feature in the encrypted historical postoperative health data to obtain a plurality of health discrete features, and then determine the feature gain factor of each health discrete feature, map the historical postoperative health data according to all the feature gain factors, and obtain a mapping data set corresponding to the historical postoperative health data; Determining data dissimilarity between each mapping data point in the mapping data set, converting the mapping data set into postoperative health generalization data according to all data dissimilarity, and using the postoperative health generalization data to train a health assessment model; Obtain the postoperative health data of the target prostate cancer patients, input the postoperative health data of the target prostate cancer patients into the trained health assessment model for health assessment, and then push personalized health promotion information to the target prostate cancer patients on the Internet platform based on the health assessment results.

[0006] Preferably, the historical postoperative health data includes urine volume characteristic data, hematuria characteristic data, blood pressure characteristic data and quality of life characteristic data.

[0007] Preferably, the encryption processing of the historical postoperative health data is to encrypt the sensitive information of the postoperative prostate cancer patients in the historical postoperative health data.

[0008] Preferably, each health feature in the encrypted historical postoperative health data is discretized to obtain a plurality of health discrete features, specifically including: For each health feature in the encrypted historical postoperative health data, equally divide the data in the health feature to obtain a plurality of discretized segments of the health feature; The data composed of all discretized segments are combined as health discrete features, and then multiple health discrete features are obtained.

[0009] Preferably, determining the feature gain factor of each health discrete feature specifically includes: For each health discrete feature, determine the information entropy of each discretized segment in the health discrete feature; Determine the feature gain entropy of the health discrete feature according to the information entropy of all discretized segments; The feature gain factor of the healthy discrete feature is determined based on the feature gain entropy, and then the feature gain factor of each healthy discrete feature is obtained.

[0010] Preferably, converting the mapping data set into postoperative health generalization data according to all data heterogeneity specifically includes: Filter out all redundant data pairs in the mapping data set according to all data heterogeneity; All redundant data pairs are removed from the mapping data set to obtain postoperative health generalization data.

[0011] Preferably, the personalized health promotion information is pushed to the target prostate cancer postoperative patients on the Internet platform according to the health assessment results, specifically including: Determine the health status of the target post-procedural prostate cancer patient according to each score in the health assessment result; Based on the health status, personalized health promotion information is generated, and then the personalized health promotion information is pushed to target prostate cancer postoperative patients on the Internet platform.

[0012] In a second aspect, the present application provides an Internet+-based prostate cancer postoperative health management advocacy system, which is used to execute an Internet+-based prostate cancer postoperative health management advocacy method, wherein the Internet+-based prostate cancer postoperative health management advocacy system includes a data processing unit, and the data processing unit includes: A data acquisition module is used to acquire historical postoperative health data of patients after prostate cancer surgery on the Internet platform, and then encrypt the historical postoperative health data; A data mapping module is used to discretize each health feature in the encrypted historical postoperative health data to obtain a plurality of health discrete features, and then determine the feature gain factor of each health discrete feature, and map the historical postoperative health data according to all the feature gain factors to obtain a mapping data set corresponding to the historical postoperative health data; A model training module, used to determine the data heterogeneity between each mapping data point in the mapping data set, convert the mapping data set into postoperative health generalization data according to all the data heterogeneity, and use the postoperative health generalization data to train the health assessment model; The information push module is used to obtain the postoperative health data of the target prostate cancer patients after surgery, input the postoperative health data of the target prostate cancer patients after surgery into the trained health assessment model for health assessment, and then push personalized health promotion information to the target prostate cancer patients after surgery on the Internet platform based on the health assessment results.

[0013] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned Internet+-based prostate cancer postoperative health management promotion method.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are executed on a computer, the computer implements the above-mentioned Internet+-based prostate cancer postoperative health management promotion method.

[0015] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: The present application provides an Internet+-based prostate cancer postoperative health management promotion method and system, which obtains historical postoperative health data of prostate cancer postoperative patients on an Internet platform, and then encrypts the historical postoperative health data; discretizes each health feature in the encrypted historical postoperative health data to obtain multiple health discrete features, and then determines the feature gain factor of each health discrete feature, maps the historical postoperative health data according to all the feature gain factors, and obtains a mapping data set corresponding to the historical postoperative health data; determines the data heterogeneity between each mapping data point in the mapping data set, converts the mapping data set into postoperative health generalization data according to all the data heterogeneity, and uses the postoperative health generalization data to train a health assessment model; obtains the postoperative health data of the target prostate cancer postoperative patient, inputs the postoperative health data of the target prostate cancer postoperative patient into the trained health assessment model for health assessment, and then pushes personalized health promotion information to the target prostate cancer postoperative patient on the Internet platform according to the health assessment result.

[0016] It can be seen that in this application, first, the encrypted historical postoperative health data is discretized, and the feature gain factor is calculated to complete the data mapping. Discretization can reduce data noise and make it easier for the model to learn key patterns, while the feature gain factor can measure the impact of various health features on postoperative recovery, ensuring that the model focuses on the most important information; then, by determining the data dissimilarity in the mapped data set and converting the data set into postoperative health generalization data accordingly, it helps to remove redundant information in the data and retain more representative health features, which can improve the training efficiency and accuracy of the model, so that the health estimation model can be trained on higher quality generalized data and reduce the risk of overfitting; finally, by inputting the postoperative health data of the target prostate cancer postoperative patient into the trained health assessment model for health assessment, the patient's health status can be accurately obtained, and personalized health promotion information can be pushed based on the evaluation results, which helps to improve the accuracy of generating personalized promotion information.

[0017] In summary, the technical solution adopted in this application can build a more accurate health assessment model to improve the accuracy of the generated personalized promotional information. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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 labor.

[0019] Figure 1 is an exemplary flow chart of an Internet+-based prostate cancer postoperative health management promotion method according to some embodiments of the present application; Figure 2 is an exemplary flow chart of determining feature gain factors of various health discrete features according to some embodiments of the present application; Figure 3 is an exemplary flow chart for determining postoperative health generalization data according to some embodiments of the present application; Figure 4 is a schematic diagram of exemplary hardware and / or software of a data processing unit according to some embodiments of the present application; Figure 5 It is a structural schematic diagram of a computer device for implementing an Internet+-based prostate cancer postoperative health management promotion method according to some embodiments of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are 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 are within the scope of protection of this application.

[0021] The embodiment of the present application provides a method and system for health management and promotion of postoperative prostate cancer based on Internet+, the core of which is to obtain the historical postoperative health data of postoperative prostate cancer patients on the Internet platform, and then encrypt the historical postoperative health data; discretize each health feature in the encrypted historical postoperative health data to obtain multiple health discrete features, and then determine the feature gain factor of each health discrete feature, map the historical postoperative health data according to all the feature gain factors, and obtain the mapping data set corresponding to the historical postoperative health data; determine the data heterogeneity between each mapping data point in the mapping data set, convert the mapping data set into postoperative health generalization data according to all the data heterogeneity, and use the postoperative health generalization data to train the health assessment model; obtain the postoperative health data of the target postoperative prostate cancer patient, input the postoperative health data of the target postoperative prostate cancer patient into the trained health assessment model for health assessment, and then push personalized health promotion information to the target postoperative prostate cancer patient on the Internet platform according to the health assessment result. The above scheme can be used to build a more accurate health assessment model to improve the accuracy of the generated personalized promotion information.

[0022] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 , which is an exemplary flow chart of an Internet+-based prostate cancer postoperative health management promotion method according to some embodiments of the present application. The Internet+-based prostate cancer postoperative health management promotion method 100 mainly includes the following steps: In step 101, historical postoperative health data of patients after prostate cancer surgery is obtained on an Internet platform, and then the historical postoperative health data is encrypted.

[0023] In specific implementation, the API interface and data import function can be used to connect various data sources to obtain the historical postoperative health data of patients after prostate cancer surgery on the Internet platform; it should be noted that, in the present application, the historical postoperative health data includes urine volume characteristic data, hematuria characteristic data, blood pressure characteristic data and quality of life characteristic data.

[0024] In some embodiments, the encryption processing of the historical postoperative health data is to encrypt the sensitive information of the patients after prostate cancer surgery in the historical postoperative health data; in the specific implementation, first, it is necessary to identify which fields in the historical postoperative health data contain sensitive information. Usually, sensitive information includes but is not limited to: personal identity information, medical records and medical data; then, symmetric encryption is used to encrypt the sensitive information in the historical postoperative health data to obtain the encrypted historical postoperative health data.

[0025] In step 102, each health feature in the encrypted historical postoperative health data is discretized to obtain a plurality of health discrete features, and then the feature gain factor of each health discrete feature is determined. The historical postoperative health data is mapped according to all the feature gain factors to obtain a mapping data set corresponding to the historical postoperative health data.

[0026] In some embodiments, the health features in the encrypted historical postoperative health data are discretized to obtain multiple health discrete features in the following manner, namely: For each health feature in the encrypted historical postoperative health data, equally divide the data in the health feature to obtain a plurality of discretized segments of the health feature; The data composed of all discretized segments are combined as health discrete features, and then multiple health discrete features are obtained.

[0027] In the specific implementation, first, for each health feature in the encrypted historical postoperative health data, the data in the health feature can be divided equally, that is, the data in the health feature can be divided according to the set time length, so that the data in the health feature can be divided into multiple discrete segments. The main goal of discretization is to convert continuous features into discrete categories to improve the interpretability of the data; then, the data composed of all discretized segments can be combined as health discrete features to obtain multiple health discrete features, which represent the discretized health features.

[0028] Preferably, in some embodiments, reference Figure 2 As shown, this figure is an exemplary flow chart of determining the feature gain factor of each health discrete feature in some embodiments of the present application. In this embodiment, determining the feature gain factor of each health discrete feature can be implemented by the following steps: In step 1021, for each health discrete feature, the information entropy of each discretized segment in the health discrete feature is determined; In step 1022, the feature gain entropy of the healthy discrete feature is determined according to the information entropy of all discretized segments; In step 1023, the feature gain factor of the healthy discrete feature is determined based on the feature gain entropy, and then the feature gain factor of each healthy discrete feature is obtained.

[0029] In specific implementation, first, for each healthy discrete feature, the information entropy of each discretized segment in the healthy discrete feature can be determined by calculating the Shannon entropy; then, the feature gain entropy of the healthy discrete feature can be determined according to the information entropy of all discretized segments, where the feature gain entropy represents the degree of reduction of the overall data uncertainty by the healthy discrete feature. In actual implementation, the feature gain entropy can be determined according to the following formula:

[0030] in, Represents the feature gain entropy of the healthy discrete feature a, represents the information entropy of the healthy discrete feature a, N represents the number of discretized segments in the healthy discrete feature a, represents the information entropy of the i-th discretized segment in the health discrete feature a, The weight corresponding to the i-th discretized segment in the healthy discrete feature a can be determined by calculating the Shannon entropy, and the ratio of the discretized segment to the healthy discrete feature can be used as the weight corresponding to the discretized segment; finally, the feature gain factor of the healthy discrete feature can be determined based on the feature gain entropy, wherein the feature gain factor is an indicator of the degree of information gain in the overall data of the corresponding healthy discrete feature. In actual implementation, the feature gain entropy of each healthy discrete feature can be determined by the above method, so that the ratio of the feature gain entropy of the healthy discrete feature to the sum of the feature gain entropies of all healthy discrete features is used as the feature gain factor of the healthy discrete feature. The feature gain factor of each healthy discrete feature can be obtained by the above method.

[0031] In some embodiments, the historical postoperative health data is mapped according to all characteristic gain factors to obtain a mapping data set corresponding to the historical postoperative health data. In actual implementation, the mapping of the historical postoperative health data can be expressed by the following formula:

[0032] in, represents the mapping dataset corresponding to the historical postoperative health data generated by mapping, represents the modulus operation in the hash function, Indicates the size of the hash table, represents the feature gain factor of the jth health discrete feature in the historical postoperative health data, Represents the jth health discrete feature in the historical postoperative health data, and m represents the total number of health discrete features in the historical postoperative health data. The mapping of the historical postoperative health data can be completed through the above method, so that the historical postoperative health data can be mapped from a high-dimensional space to a low-dimensional space to achieve efficient data processing operations.

[0033] It should be noted that discretizing the encrypted historical postoperative health data and calculating the feature gain factor to complete the data mapping can help improve the accuracy and personalization of the health assessment model. Discretization can reduce data noise and make it easier for the model to learn key patterns, while the feature gain factor can measure the impact of various health characteristics on postoperative recovery, ensuring that the model focuses on the most important information. By mapping the data set, the original complex data is converted into structured, high-information data, reducing the data dimension, improving the training effect of the machine learning algorithm, and enhancing the ability to classify and predict postoperative health status.

[0034] In step 103, the data dissimilarity between each mapping data point in the mapping data set is determined, the mapping data set is converted into postoperative health generalization data according to all data dissimilarity, and the health assessment model is trained using the postoperative health generalization data.

[0035] In some embodiments, the data dissimilarity between each mapping data point in the mapping data set is determined; it should be noted that in the present application, the data dissimilarity represents the degree of data exclusion between the mapping data points; in specific implementation, first, the Euclidean distance between each mapping data point in the mapping data set can be determined; then, based on the Euclidean distance between each mapping data point, the data dissimilarity between each mapping data point can be determined. In actual implementation, the data dissimilarity can be determined by the following formula:

[0036] in, Represents the mapping data point With mapped data points The data heterogeneity between Represents the mapping data point With mapped data points The Euclidean distance between Represents the mapping data point With mapped data points The Euclidean distance between them, u represents the total number of mapping data points in the mapping data set. The data heterogeneity between each mapping data point in the mapping data set can be determined by the above method.

[0037] Preferably, in some embodiments, reference Figure 3 As shown, this figure is an exemplary flow chart for determining postoperative health generalization data in some embodiments of the present application. In this embodiment, converting the mapping data set into postoperative health generalization data according to all data heterogeneity can be achieved by the following steps: In step 1031, all redundant data pairs in the mapping data set are screened out according to all data dissimilarity; In step 1032, all redundant data pairs are removed from the mapping data set to obtain postoperative health generalization data.

[0038] In the specific implementation, first, a threshold can be set according to historical experiments and data analysis to determine the data dissimilarity of all data less than the threshold, and the mapping data point pairs corresponding to the screened data dissimilarity can be used as redundant data pairs, thus filtering out all redundant data pairs in the mapping data set; then, all redundant data pairs can be eliminated in the mapping data set, thereby mapping all remaining data back to the high-dimensional space, and the output data can be used as postoperative health generalization data, which contains the most representative and most differentiated data points in the original data set, ensuring the validity and representativeness of the data.

[0039] In some embodiments, the health assessment model is trained using the postoperative health generalization data; in specific implementation, first, a suitable health assessment model can be selected. The health assessment model selected in this application is a support vector machine (SVM). The support vector machine is suitable for classification problems and can effectively classify different health states and effectively classify high-dimensional data; then, the health assessment model can be trained using the health generalization data, and the specific training and optimization process will not be repeated here; it should be noted that by using the postoperative health generalization data to train the health assessment model, the prediction accuracy of the model can be improved, and the patient's health status can be effectively identified.

[0040] It should be noted that by determining the data heterogeneity in the mapping data set and converting the data set into postoperative health generalization data based on it, it is helpful to remove redundant information in the data and retain more representative health features, which can improve the training efficiency and accuracy of the model, so that the health estimation model can be trained on higher quality generalization data and reduce the risk of overfitting. Generalization data can more realistically reflect the health status of patients, thereby providing a more accurate basis for generating personalized health promotion information.

[0041] In step 104, the postoperative health data of the target prostate cancer postoperative patient is obtained, and the postoperative health data of the target prostate cancer postoperative patient is input into the trained health assessment model for health assessment, and then personalized health promotion information is pushed to the target prostate cancer postoperative patient on the Internet platform based on the health assessment results.

[0042] In specific implementation, first, the postoperative health data of the target prostate cancer patients after surgery can be collected through the Internet platform. The postoperative health data of the target prostate cancer patients after surgery include urine volume characteristic data, blood and urine characteristic data, blood pressure characteristic data and quality of life characteristic data, and the postoperative health data of the target prostate cancer patients after surgery need to be encrypted to ensure the privacy and security of the patients; then, the collected postoperative health data of the target prostate cancer patients after surgery can be preprocessed, including removing invalid values, outlier processing, standardization processing, etc., to ensure that the data format is consistent; finally, the processed postoperative health data of the target prostate cancer patients after surgery can be input into the trained health assessment model, and the health assessment model analyzes the patient's recovery status based on the postoperative health data, thereby generating a health assessment result, which includes the scores of the target prostate cancer patients after surgery in terms of urine volume, blood and urine, blood pressure and quality of life.

[0043] In some embodiments, the personalized health promotion information may be pushed to the target postoperative prostate cancer patients on the Internet platform according to the health assessment results in the following manners, namely: Determine the health status of the target post-procedural prostate cancer patient according to each score in the health assessment result; Based on the health status, personalized health promotion information is generated, and then the personalized health promotion information is pushed to target prostate cancer postoperative patients on the Internet platform.

[0044] In specific implementation, first, the health status of the target prostate cancer postoperative patient can be determined based on each score in the health assessment result, and each score in the health assessment result can be weighted and summed, wherein the corresponding weight can be preset according to historical experience; then, the weighted summation result can be compared with the health status level table set in the system to obtain the health status of the target prostate cancer postoperative patient, for example, a good recovery state (no obvious complications, good recovery, and high quality of life), a moderate recovery state (there are some minor complications or health problems, but the overall recovery is good), a state requiring attention (there are more obvious complications or health problems, the recovery progress is slow, and intensive care is required), and an urgent state of attention (health Poor condition, high risk of complications, and need timely intervention); furthermore, personalized health promotion information can be generated based on health status. For example, for patients in a good recovery state, personalized health promotion information may include healthy diet recommendations (such as intake of high-protein, low-fat foods), moderate exercise (such as walking, stretching, etc.), regular check-up recommendations, etc., provide mentality adjustment techniques, encourage patients to maintain a positive and optimistic attitude, provide positive incentives for the recovery process, and enhance patients' self-confidence and compliance; finally, personalized health promotion information can be pushed to target prostate cancer postoperative patients on the Internet platform, for example, real-time notifications can be sent to patients' mobile phones, tablets and other devices to ensure that patients can obtain the latest health promotion information in a timely manner.

[0045] It should be noted that by inputting the postoperative health data of the target prostate cancer patients into the trained health assessment model for health assessment, the patient's health status can be accurately obtained, and personalized health promotion information can be pushed based on the assessment results, which helps to improve the accuracy of generating personalized promotion information.

[0046] It can be seen that in this application, first, the encrypted historical postoperative health data is discretized, and the feature gain factor is calculated to complete the data mapping. Discretization can reduce data noise and make it easier for the model to learn key patterns, while the feature gain factor can measure the impact of various health features on postoperative recovery, ensuring that the model focuses on the most important information; then, by determining the data dissimilarity in the mapped data set and converting the data set into postoperative health generalization data accordingly, it helps to remove redundant information in the data and retain more representative health features, which can improve the training efficiency and accuracy of the model, so that the health estimation model can be trained on higher quality generalized data and reduce the risk of overfitting; finally, by inputting the postoperative health data of the target prostate cancer postoperative patient into the trained health assessment model for health assessment, the patient's health status can be accurately obtained, and personalized health promotion information can be pushed based on the evaluation results, which helps to improve the accuracy of generating personalized promotion information.

[0047] In summary, the technical solution adopted in this application can build a more accurate health assessment model to improve the accuracy of the generated personalized promotional information.

[0048] In addition, in another aspect of the present application, in some embodiments, the present application provides an Internet+-based prostate cancer postoperative health management advocacy system, the Internet+-based prostate cancer postoperative health management advocacy system includes a data processing unit, reference Figure 4 , which is a schematic diagram of exemplary hardware and / or software of a data processing unit according to some embodiments of the present application, the data processing unit 400 includes: a data acquisition module 401, a data mapping module 402, a model training module 403 and an information push module 404, which are described as follows: Data acquisition module 401, in this application, data acquisition module 401 is mainly used to obtain historical postoperative health data of patients after prostate cancer surgery on the Internet platform, and then encrypt the historical postoperative health data; Data mapping module 402, in this application, the data mapping module 402 is mainly used to discretize each health feature in the encrypted historical postoperative health data to obtain multiple health discrete features, and then determine the feature gain factor of each health discrete feature, and map the historical postoperative health data according to all the feature gain factors to obtain a mapping data set corresponding to the historical postoperative health data; Model training module 403, in this application, the model training module 403 is mainly used to determine the data heterogeneity between each mapping data point in the mapping data set, convert the mapping data set into postoperative health generalization data according to all data heterogeneity, and use the postoperative health generalization data to train the health assessment model; The information push module 404 in this application is mainly used to obtain the postoperative health data of the target prostate cancer patients after surgery, input the postoperative health data of the target prostate cancer patients after surgery into the trained health assessment model for health assessment, and then push personalized health promotion information to the target prostate cancer patients after surgery on the Internet platform based on the health assessment results.

[0049] The above describes in detail an example of an Internet+-based prostate cancer postoperative health management promotion method and system provided in an embodiment of the present application. It can be understood that in order to realize the above functions, the corresponding device includes a hardware structure and / or software module corresponding to each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0050] In some embodiments, the present application also provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned Internet+-based prostate cancer postoperative health management promotion method.

[0051] In some embodiments, reference Figure 5 , the dotted line in the figure indicates that the unit or the module is optional. The figure is a schematic diagram of the structure of a computer device for a prostate cancer postoperative health management promotion method based on Internet+ according to an embodiment of the present application. The prostate cancer postoperative health management promotion method based on Internet+ described in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a memory 502 and at least one communication unit 505. The computer device 500 can be a terminal device, a server or a chip.

[0052] The processor 501 may be a general-purpose processor or a special-purpose processor. For example, the processor 501 may be a central processing unit (CPU), which may be used to control the computer device 500, execute software programs, and process data of the software programs. The computer device 500 may also include a communication unit 505 to implement signal input (reception) and output (transmission).

[0053] For example, the computer device 500 may be a chip, the communication unit 505 may be an input and / or output circuit of the chip, or the communication unit 505 may be a communication interface of the chip, and the chip may be a component of a terminal device, a network device, or other device.

[0054] For another example, the computer device 500 may be a terminal device or a server, and the communication unit 505 may be a transceiver of the terminal device or the server, or the communication unit 505 may be a transceiver circuit of the terminal device or the server.

[0055] The computer device 500 may include one or more memories 502, on which a program 504 is stored. The program 504 can be executed by the processor 501 to generate instructions 503, so that the processor 501 performs the method described in the above method embodiment according to the instructions 503. Optionally, data (such as a target audit model) can also be stored in the memory 502. Optionally, the processor 501 can also read the data stored in the memory 502, and the data can be stored at the same storage address as the program 504, or the data can be stored at a different storage address from the program 504.

[0056] The processor 501 and the memory 502 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of the terminal device.

[0057] It should be understood that each step of the above method embodiment can be completed by a hardware-based logic circuit or software-based instructions in the processor 501. The processor 501 can be a central processing unit, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, such as discrete gates, transistor logic devices or discrete hardware components.

[0058] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0059] For example, in some embodiments, the present application also provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are executed on a computer, the computer implements the above-mentioned Internet+-based prostate cancer postoperative health management promotion method.

[0060] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0061] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for promoting health management after prostate cancer surgery based on Internet+, characterized in that: The steps include: Obtaining historical postoperative health data of patients undergoing prostate cancer surgery on an Internet platform, and then encrypting the historical postoperative health data; Discretize each health feature in the encrypted historical postoperative health data to obtain a plurality of health discrete features, and then determine the feature gain factor of each health discrete feature, map the historical postoperative health data according to all the feature gain factors, and obtain a mapping data set corresponding to the historical postoperative health data; Determining data dissimilarity between each mapping data point in the mapping data set, converting the mapping data set into postoperative health generalization data according to all data dissimilarity, and using the postoperative health generalization data to train a health assessment model; Obtain the postoperative health data of the target prostate cancer patients, input the postoperative health data of the target prostate cancer patients into the trained health assessment model for health assessment, and then push personalized health promotion information to the target prostate cancer patients on the Internet platform based on the health assessment results.

2. The Internet+-based prostate cancer postoperative health management promotion method according to claim 1, characterized in that: The historical postoperative health data includes urine volume characteristic data, hematuria characteristic data, blood pressure characteristic data and quality of life characteristic data.

3. The Internet+-based prostate cancer postoperative health management promotion method according to claim 1, characterized in that: The encryption processing of the historical postoperative health data is to encrypt the sensitive information of the postoperative prostate cancer patients in the historical postoperative health data.

4. The Internet+-based prostate cancer postoperative health management promotion method according to claim 1, characterized in that: Discretize each health feature in the encrypted historical postoperative health data to obtain multiple health discrete features, including: For each health feature in the encrypted historical postoperative health data, equally divide the data in the health feature to obtain a plurality of discretized segments of the health feature; The data consisting of all discretized segments are combined as health discrete features, and then multiple health discrete features are obtained.

5. The Internet+-based prostate cancer postoperative health management promotion method according to claim 1, characterized in that: The characteristic gain factors for determining each health discrete characteristic specifically include: For each health discrete feature, determine the information entropy of each discretized segment in the health discrete feature; Determine the feature gain entropy of the health discrete feature according to the information entropy of all discretized segments; The feature gain factor of the healthy discrete feature is determined based on the feature gain entropy, and then the feature gain factor of each healthy discrete feature is obtained.

6. The Internet+-based prostate cancer postoperative health management promotion method according to claim 1, characterized in that: Converting the mapping data set into postoperative health generalization data according to all data heterogeneity specifically includes: Filter out all redundant data pairs in the mapping data set according to all data heterogeneity; All redundant data pairs are removed from the mapping data set to obtain postoperative health generalization data.

7. The Internet+-based prostate cancer postoperative health management promotion method according to claim 1, characterized in that: According to the health assessment results, personalized health promotion information is pushed to the target prostate cancer postoperative patients on the Internet platform, including: Determine the health status of the target post-procedural prostate cancer patient according to each score in the health assessment result; Based on the health status, personalized health promotion information is generated, and then the personalized health promotion information is pushed to target prostate cancer postoperative patients on the Internet platform.

8. An Internet+-based prostate cancer postoperative health management advocacy system, used to execute an Internet+-based prostate cancer postoperative health management advocacy method as claimed in any one of claims 1 to 7, the Internet+-based prostate cancer postoperative health management advocacy system comprising a data processing unit, characterized in that: The data processing unit comprises: A data acquisition module is used to acquire historical postoperative health data of patients after prostate cancer surgery on the Internet platform, and then encrypt the historical postoperative health data; A data mapping module is used to discretize each health feature in the encrypted historical postoperative health data to obtain a plurality of health discrete features, and then determine the feature gain factor of each health discrete feature, and map the historical postoperative health data according to all the feature gain factors to obtain a mapping data set corresponding to the historical postoperative health data; A model training module, used to determine the data heterogeneity between each mapping data point in the mapping data set, convert the mapping data set into postoperative health generalization data according to all the data heterogeneity, and use the postoperative health generalization data to train the health assessment model; The information push module is used to obtain the postoperative health data of the target prostate cancer patients after surgery, input the postoperative health data of the target prostate cancer patients after surgery into the trained health assessment model for health assessment, and then push personalized health promotion information to the target prostate cancer patients after surgery on the Internet platform based on the health assessment results.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes an Internet+-based prostate cancer postoperative health management promotion method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions or codes, and when the instructions or codes are executed on a computer, the computer implements an Internet+-based prostate cancer postoperative health management promotion method as described in any one of claims 1 to 7.

Images