A personalized gynecological care recommendation method based on effect evaluation

By constructing a topology map of gynecological diseases knowledge graph and blockchain technology, a personalized gynecological nursing recommendation platform was established, and the problems of data accuracy and individual differences in the existing technology were solved, and the accurate recommendation and accuracy of personalized nursing methods were achieved. .

CN118553441BActive Publication Date: 2024-11-22CHANGCHUN UNIV OF CHINESE MEDICINE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411021298.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-22
Estimated Expiration
2044-07-29

AI Technical Summary

Technical Problem

The prior art is difficult to ensure the accuracy and completeness of data in personalized gynecological care, resulting in inaccuracy or imperfection of nursing plans and large differences between different individuals. How to adjust the nursing plans in a timely manner and how to automatically monitor and process the effectiveness evaluation data. Improving the accuracy of nursing methods is an urgent problem.

Method used

Construct the knowledge graph topology of gynecological diseases at each stage of progress, and establish a gynecological nursing recommendation platform based on blockchain technology. By monitoring patient symptoms, evaluating effects, recommending personalized nursing methods, and using deep learning and fuzzy comprehensive evaluation technology to carry out Data analysis and estimates ensure the accuracy of care methods.

Benefits of technology

It has achieved personalized gynecological nursing methods recommendations for different stages, improved treatment effect and quality of life, enhanced the accuracy and personalization of nursing methods, and provided more effective medical services.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118553441B_ABST
    Figure CN118553441B_ABST
Patent Text Reader

Abstract

A personalized gynecological nursing recommendation method based on effect evaluation relates to the technical field of gynecological nursing method recommendation, constructs a knowledge graph topology corresponding to each gynecological disease at each progress stage and stores it in a nursing method graph library, and adds a stage effect evaluation level and an average effect evaluation level to the edge structure between the gynecological disease and the nursing method in the knowledge graph topology; constructs a gynecological nursing recommendation platform based on blockchain technology, monitors the symptom set of the target patient and uploads the symptom set to the gynecological nursing recommendation platform, and the gynecological nursing recommendation platform obtains recommended nursing methods according to the symptom set of the target patient; the gynecological nursing recommendation platform determines whether the standard stage effect evaluation level within the target patient's feedback cycle meets the requirements, and if not, recommends personalized nursing methods for the target patient, thereby improving the accuracy and effect of the gynecological nursing method and providing patients with more personalized and effective medical services.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of gynecological nursing method recommendation, and in particular to a personalized gynecological nursing recommendation method based on effect evaluation. Background Art

[0002] The prior art CN117524405B "A gynecological nursing method intelligent selection system based on cloud computing" includes a monitoring center, which is communicatively connected to a domain semantic database, a symptom diagnosis module, a nursing method module and a nursing feedback module; the domain semantic database maps the symptom set, the disease set and the gynecological nursing method set into a multi-node network based on the information provided by domain experts; the symptom diagnosis module is used to obtain the disease diagnosis confidence of the symptom set and the symptom diagnosis confidence of the disease set, and obtain the most relevant disease node corresponding to the patient's current symptom set; the nursing method module is used to screen out the preferred gynecological nursing method node; the nursing feedback module is used to construct a feedback process sequence, and determine whether to replace the preferred gynecological nursing method node based on the real-time feedback evaluation level generated by the patient and the nursing staff, so as to optimize each step of the patient's gynecological nursing process and improve the quality of the patient's gynecological nursing.

[0003] The prior art CN117542498B "A gynecological care management system and method based on big data analysis" evaluates the inquiry status of gynecological care implemented by the first object, processes and analyzes the voice data of the whole process of gynecological care inquiry implemented by the first object, and can obtain whether the work done by the first object when implementing the gynecological care inquiry is in place; evaluates the harvest status of the gynecological care implemented by the first object, processes and analyzes the voice data of the whole process of gynecological care answer implemented by the second object, and can obtain whether the physical condition of the second object is normal.

[0004] Personalized care methods usually require the acquisition of personal health data, which may involve privacy issues and require careful handling and protection of personal information. The effectiveness of personalized care methods depends on the accuracy and completeness of the data used. If the data is inaccurate or lacks important information, it may lead to inaccurate or imperfect care plans. At the same time, there are differences between different individuals. The same care method may have different effects on different individuals. The individual's physiology and living environment may change, and the care plan needs to be adjusted in a timely manner. At the same time, how to automatically monitor, count, process, analyze and share data on the effectiveness evaluation of care methods is an issue that we urgently need to solve. Summary of the invention

[0005] In order to solve the above technical problems, the object of the present invention is to provide a personalized gynecological care recommendation method based on effect evaluation, comprising the following steps:

[0006] Step s1: construct the knowledge graph topology corresponding to each gynecological disease at each progress stage and store it in the nursing method graph library, and add the stage effect evaluation level and the average effect evaluation level to the edge structure between gynecological diseases and nursing methods in the knowledge graph topology;

[0007] Step s2: Building a gynecological nursing recommendation platform based on blockchain technology, monitoring the symptom set of the target patient and uploading the symptom set to the gynecological nursing recommendation platform, and the gynecological nursing recommendation platform obtains recommended nursing methods based on the symptom set of the target patient;

[0008] Step s3: The gynecological nursing recommendation platform determines whether the standard stage effect evaluation level within the target patient's feedback cycle meets the requirements. If not, it recommends personalized nursing methods for the target patient.

[0009] Furthermore, the process of constructing the knowledge graph topology corresponding to each gynecological disease at each progress stage and storing it in the nursing method graph library includes:

[0010] Obtaining a number of gynecological diseases and nursing methods corresponding to the gynecological diseases, and obtaining a number of symptom sets and nursing methods corresponding to different disease stages of each gynecological disease, wherein the symptom set includes a number of symptoms;

[0011] A gynecological disease is divided into periods according to the disease period. A disease period is regarded as a stage to form a progress stage. The symptom set and nursing method corresponding to a gynecological disease in a certain progress stage are obtained. The gynecological disease, symptom set and nursing method are regarded as a point structure, and the gynecological disease is connected with the symptom set and nursing method to generate an edge structure. The knowledge graph topology corresponding to a gynecological disease in a certain progress stage is constructed. Similarly, the knowledge graph topology corresponding to each gynecological disease in each progress stage is obtained and stored in the nursing method graph library.

[0012] Furthermore, the process of adding the stage effect evaluation level and the average effect evaluation level to the edge structure between gynecological diseases and nursing methods in the knowledge graph topology includes:

[0013] Obtain the patient's historical disease diagnosis records and historical nursing effect evaluation records, wherein the historical disease diagnosis records include the patient's symptom set time series, gynecological diseases, progress stage, and nursing methods within the feedback cycle, and the historical nursing effect evaluation records include the stage effect evaluation level of each feedback cycle corresponding to the nursing method and the average effect evaluation level corresponding to the nursing method obtained according to the stage effect evaluation level of each feedback cycle corresponding to the nursing method;

[0014] According to the patient's historical disease diagnosis records, the corresponding knowledge graph topology of the patient in the nursing method graph library is extracted. At the same time, according to the patient's historical nursing effect evaluation records, the stage effect evaluation level and the average effect evaluation level are added to the edge structure between gynecological diseases and nursing methods in the knowledge graph topology.

[0015] Furthermore, the process of obtaining the stage effect evaluation level of each feedback cycle corresponding to the nursing method includes:

[0016] Obtain the gynecological diseases diagnosed, the progress stage diagnosed, and the nursing methods used within the patient feedback cycle, match the diagnosed gynecological diseases and the progress stage diagnosed with the nursing method atlas library, extract the knowledge graph topology corresponding to the diagnosed gynecological diseases and the progress stage diagnosed, extract the symptom set in the knowledge graph topology, and pre-set the severity level threshold interval of the symptom set;

[0017] At the end timestamp of the feedback cycle, the patient's symptom set is obtained, the literal values ​​corresponding to several symptoms in the symptom set are extracted, the literal values ​​corresponding to the several symptoms are compared with the severity level threshold intervals corresponding to the several symptoms, the severity level of each symptom is obtained, the severity level of each symptom is used as an evaluation index, the indicator weight matrix and the effect evaluation level of the evaluation index are preset, the membership matrix of the evaluation index for different effect evaluation levels is obtained through fuzzy comprehensive evaluation, and the effect evaluation level is obtained according to the membership matrix and the indicator weight matrix.

[0018] Furthermore, a gynecological care recommendation platform is constructed based on blockchain technology. The process of monitoring the symptom set of the target patient and uploading the symptom set to the gynecological care recommendation platform includes:

[0019] The gynecological care recommendation platform is provided with a number of blockchain nodes and a nursing method atlas library. The blockchain nodes are linked to each other to form a blockchain network. The blockchain nodes are used to store the patient's historical disease diagnosis records and historical nursing effect evaluation records, and the blockchain nodes are linked to the intelligent terminal within a preset range. The intelligent terminal is used to monitor the patient's symptom set and encrypt the symptom set and upload it to the blockchain node. The blockchain node decrypts the received patient's symptom set, packages the decrypted symptom set into a new block, and broadcasts the new block to the entire blockchain network, adds the new block to the end of the blockchain, and updates the symptom set in the new block to the local blockchain copy of the blockchain node.

[0020] Furthermore, the process of obtaining recommended nursing methods according to the symptom set of the target patient by the gynecological nursing recommendation platform includes:

[0021] Match the symptom set in the new block with the knowledge graph topology in the nursing method graph library, obtain a knowledge graph topology whose symptom set included in the knowledge graph topology is consistent with the symptom set in the new block, extract gynecological diseases, progress stages and nursing methods in the knowledge graph topology, obtain the nursing method with the highest average effect evaluation level between gynecological diseases, mark the nursing method as a recommended nursing method, mark the stage effect evaluation level and the average effect evaluation level between the gynecological disease and the recommended nursing method as a standard stage effect evaluation level and a standard average effect evaluation level, and feed back the gynecological disease, progress stage, recommended nursing method and standard stage effect evaluation level to the Zhilian terminal.

[0022] Furthermore, the gynecological nursing recommendation platform determines whether the standard stage effect evaluation level in the target patient feedback cycle meets the requirements. If not, the process of recommending personalized nursing methods for the target patient includes:

[0023] Construct a symptom set prediction model based on deep learning, use the historical disease diagnosis records and historical nursing effect evaluation records of patients stored in each blockchain node in the gynecological care recommendation platform as training data, train the symptom set prediction model through the training data, and output the trained symptom set prediction model;

[0024] Extract the standardized treatment steps in the recommended nursing method, segment the recommended nursing method according to the standardized treatment steps, use the standardized treatment steps as the segmentation nodes of the recommended nursing method, divide the recommended nursing method into several feedback cycles, obtain the stage effect evaluation level of the recommended nursing method at the end timestamp of the feedback cycle, and simultaneously obtain the standard stage effect evaluation level corresponding to the feedback cycle, compare the stage effect evaluation level with the standard stage effect evaluation level, if the stage effect evaluation level is less than the standard stage effect evaluation level, obtain the symptom set time series sequence of the target patient in the feedback cycle, input the symptom set time series sequence and the recommended nursing method into the symptom set estimation model, output the estimated stage effect evaluation level of the target patient in several feedback cycles according to the symptom set estimation model, obtain the estimated average effect evaluation level according to the estimated stage effect evaluation level in the several feedback cycles, compare the estimated average effect evaluation level with the standard average effect evaluation level, if the estimated average effect evaluation level is less than the standard average effect evaluation level, recommend personalized nursing methods for the target patients.

[0025] Furthermore, the process of recommending personalized nursing methods for target patients includes:

[0026] Obtain the symptom set time series sequence of the target patient within the feedback cycle, perform similarity matching between the symptom set time series sequence and the symptom set time series sequence of other patients in the local blockchain copy, and obtain the symptom set similarity between other patients and the target patient;

[0027] Filter out the top ten other patients with the highest symptom set similarity, obtain the stage effect evaluation levels of the nursing methods corresponding to the top ten other patients in the feedback cycle, filter out other nursing methods corresponding to the highest stage effect evaluation level, and use the nursing methods as new recommended nursing methods.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] 1. Construct the knowledge graph topology corresponding to each gynecological disease at each progress stage and store it in the nursing method graph library, and add the stage effect evaluation level and average effect evaluation level to the edge structure between gynecological diseases and nursing methods in the knowledge graph topology, so as to recommend personalized gynecological nursing methods for gynecological diseases at different stages, so as to minimize the progression of the disease and provide the best treatment effect and quality of life for patients.

[0030] 2. Build a gynecological care recommendation platform based on blockchain technology, monitor the symptom set of the target patient and upload the symptom set to the gynecological care recommendation platform. The gynecological care recommendation platform obtains recommended care methods based on the symptom set of the target patient. The gynecological care recommendation platform determines whether the standard stage effect evaluation level within the target patient's feedback cycle meets the requirements. If not, it recommends personalized care methods for the target patient, improves the accuracy and effectiveness of gynecological care methods, and provides patients with more personalized and effective medical services. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a schematic diagram of a personalized gynecological care recommendation method based on effect evaluation in an embodiment of the present application.

[0032] Figure 2 This is a knowledge graph topology map corresponding to an early gynecological disease j in an embodiment of the present application. DETAILED DESCRIPTION

[0033] The following is a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0034] like Figure 1As shown in the figure, a personalized gynecological care recommendation method based on effect evaluation includes the following steps:

[0035] Step s1: construct the knowledge graph topology corresponding to each gynecological disease at each progress stage and store it in the nursing method graph library, and add the stage effect evaluation level and the average effect evaluation level to the edge structure between gynecological diseases and nursing methods in the knowledge graph topology;

[0036] Step s2: Building a gynecological nursing recommendation platform based on blockchain technology, monitoring the symptom set of the target patient and uploading the symptom set to the gynecological nursing recommendation platform, and the gynecological nursing recommendation platform obtains recommended nursing methods based on the symptom set of the target patient;

[0037] Step s3: The gynecological nursing recommendation platform determines whether the standard stage effect evaluation level within the target patient's feedback cycle meets the requirements. If not, it recommends personalized nursing methods for the target patient.

[0038] It should be further explained that, in the specific implementation process, the process of constructing the knowledge graph topology corresponding to each gynecological disease at each progress stage and storing it in the nursing method graph library includes:

[0039] Obtaining a number of gynecological diseases and nursing methods corresponding to the gynecological diseases, and obtaining a number of symptom sets and nursing methods corresponding to different disease stages of each gynecological disease, wherein the symptom set includes a number of symptoms;

[0040] A gynecological disease is divided into periods according to the disease period. A disease period is regarded as a stage to form a progress stage. The symptom set and nursing method corresponding to a gynecological disease in a certain progress stage are obtained. The gynecological disease, symptom set and nursing method are regarded as a point structure, and the gynecological disease is connected with the symptom set and nursing method to generate an edge structure. The knowledge graph topology corresponding to a gynecological disease in a certain progress stage is constructed. Similarly, the knowledge graph topology corresponding to each gynecological disease in each progress stage is obtained and stored in the nursing method graph library.

[0041] It should be further explained that, in the present invention, examples are given for the knowledge graph topology corresponding to each gynecological disease at each progress stage. For example, the symptom set JSC and nursing method JXD corresponding to the early gynecological disease j are obtained, and the early gynecological disease j, the symptom set JSC and the nursing method JXD are used as point structures, and the early gynecological disease j is connected with the symptom set JSC and the nursing method JXD to generate an edge structure, and the knowledge graph topology corresponding to the early gynecological disease j is constructed. The knowledge graph topology corresponding to the early gynecological disease j is as follows: Figure 2 shown.

[0042] It should be further explained that, in the present invention, the disease stages of gynecological diseases generally include early, middle and late stages; in the early stage, gynecological diseases may only show mild symptoms or no symptoms, but lesions already exist; the middle stage may be accompanied by aggravation of symptoms and progression of the disease, and more active treatment interventions may be required, such as drug therapy, surgery or other nursing measures; the late stage is generally a stage where the disease is already more serious, and may be accompanied by severe symptoms and complications; the focus of treatment may be on relieving symptoms, improving the quality of life, and prolonging the patient's survival time. In the late stage, comprehensive treatment and lifelong care may be necessary;

[0043] It should be further explained that, in the specific implementation process, the process of adding the stage effect evaluation level and the average effect evaluation level to the edge structure between gynecological diseases and nursing methods in the knowledge graph topology includes:

[0044] Obtain the patient's historical disease diagnosis records and historical nursing effect evaluation records. It should be noted that the patient's historical disease diagnosis records and historical nursing effect evaluation records are obtained from the blockchain node in the gynecological nursing recommendation platform. The historical disease diagnosis records include the patient's symptom set time series, gynecological diseases, progress stages, and nursing methods within the feedback cycle. The historical nursing effect evaluation records include the stage effect evaluation level of each feedback cycle corresponding to the nursing method and the average effect evaluation level corresponding to the nursing method obtained according to the stage effect evaluation level of each feedback cycle corresponding to the nursing method;

[0045] According to the patient's historical disease diagnosis records, the corresponding knowledge graph topology of the patient in the nursing method graph library is extracted. At the same time, according to the patient's historical nursing effect evaluation records, the stage effect evaluation level and the average effect evaluation level are added to the edge structure between gynecological diseases and nursing methods in the knowledge graph topology.

[0046] It should be further explained that, in the specific implementation process, the process of obtaining the stage effect evaluation level of each feedback cycle corresponding to the nursing method includes:

[0047] Obtain the gynecological diseases diagnosed, the progress stage diagnosed, and the nursing methods used within the patient feedback cycle, match the diagnosed gynecological diseases and the progress stage diagnosed with the nursing method atlas library, extract the knowledge graph topology corresponding to the diagnosed gynecological diseases and the progress stage diagnosed, extract the symptom set in the knowledge graph topology, and pre-set the severity level threshold interval of the symptom set;

[0048] The patient's symptom set is obtained at the end timestamp of the feedback cycle, and the literal values ​​corresponding to several symptoms in the symptom set are extracted, wherein the literal values ​​corresponding to several symptoms represent the numerical attribute characteristics of the symptoms, for example, urination frequency value, frequency of abnormal vaginal secretion, menstrual period, menstrual volume, etc. The literal values ​​corresponding to the several symptoms are compared with the severity level threshold intervals corresponding to the several symptoms to obtain the severity level of each symptom, and the severity level of each symptom is used as an evaluation index, and the indicator weight matrix and effect evaluation level of the evaluation index are preset, and the membership matrix of the evaluation index for different effect evaluation levels is obtained through fuzzy comprehensive evaluation judgment, and the effect evaluation level is obtained according to the membership matrix and the indicator weight matrix.

[0049] It should be further explained that, in the specific implementation process, the process of obtaining the effect evaluation level of the patient's symptom set according to the membership matrix and the indicator weight matrix includes:

[0050] The indicator weight matrix and the membership matrix of the evaluation indicator are integrated through a formula to obtain a fuzzy comprehensive evaluation matrix of the evaluation indicator, the membership of the evaluation indicator for different effect evaluation levels is obtained according to the fuzzy comprehensive evaluation matrix, the effect evaluation level with the highest membership corresponding to the evaluation indicator is screened out, and the effect evaluation level with the highest membership corresponding to the evaluation indicator is used as the effect evaluation level finally corresponding to the evaluation indicator;

[0051] Wherein, the formula is:

[0052] ;

[0053] in, is the fuzzy comprehensive evaluation matrix of the evaluation index, is the indicator weight matrix of the evaluation indicator, is the membership matrix, The weight matrix representing the evaluation index is multiplied by the elements at the corresponding positions of the membership matrix. and It is a weighted parameter for controlling the balance between the weight matrix and the membership matrix in the fuzzy comprehensive evaluation matrix of the evaluation index.

[0054] It should be further explained that, in the specific implementation process, the process of building a gynecological care recommendation platform based on blockchain technology, monitoring the symptom set of the target patient and uploading the symptom set to the gynecological care recommendation platform includes:

[0055] A gynecological care recommendation platform is constructed based on blockchain technology. A number of blockchain nodes and a nursing method atlas library are set in the gynecological care recommendation platform. The number of blockchain nodes are linked to each other to form a blockchain network. The blockchain nodes are used to store the patient's historical disease diagnosis records and historical nursing effect evaluation records, and the blockchain nodes are communicated with the intelligent terminal within a preset range. The intelligent terminal is used to monitor the patient's symptom set and encrypt the symptom set and upload it to the blockchain node. The intelligent terminal can be a wireless communication device such as a mobile phone or a computer. The patient, nurse or doctor can input the patient's symptom set into the intelligent terminal in real time. The blockchain node decrypts the received patient's symptom set, packages the decrypted symptom set into a new block, broadcasts the new block to the entire blockchain network, adds the new block to the end of the blockchain, and updates the symptom set in the new block to the local blockchain copy of the blockchain node.

[0056] It should be further explained that, in the specific implementation process, the gynecological nursing recommendation platform obtains the recommended nursing method based on the symptom set of the target patient, including:

[0057] The gynecological care recommendation platform matches the symptom set in the new block with the knowledge graph topology in the nursing method graph library, obtains a knowledge graph topology whose symptom set included in the knowledge graph topology is consistent with the symptom set in the new block, extracts gynecological diseases, progress stages and nursing methods in the knowledge graph topology, obtains the nursing method with the highest average effect evaluation level between gynecological diseases, marks the nursing method as a recommended nursing method, marks the stage effect evaluation level and the average effect evaluation level between gynecological diseases and recommended nursing methods as standard stage effect evaluation level and standard average effect evaluation level, and feeds back the gynecological diseases, progress stages, recommended nursing methods and standard stage effect evaluation levels to the Zhilian terminal.

[0058] It should be further explained that, in the specific implementation process, the gynecological nursing recommendation platform determines whether the standard stage effect evaluation level in the target patient feedback cycle meets the requirements. If not, the process of recommending personalized nursing methods for the target patient includes:

[0059] A symptom set prediction model was built based on deep learning, and the historical disease diagnosis records and historical nursing effect evaluation records of patients stored in each blockchain node in the gynecological care recommendation platform were used as test sets and training sets;

[0060] Input the training set into the symptom set prediction model for training until the loss function training is stable, save the model parameters, test the symptom set prediction model with the test set until it meets the preset requirements, and output the symptom set prediction model;

[0061] Extract the standardized treatment steps in the recommended nursing method, segment the recommended nursing method according to the standardized treatment steps, use the standardized treatment steps as the segmentation nodes of the recommended nursing method, divide the recommended nursing method into several feedback cycles, obtain the stage effect evaluation level of the recommended nursing method at the end timestamp of the feedback cycle, and simultaneously obtain the standard stage effect evaluation level corresponding to the feedback cycle, compare the stage effect evaluation level with the standard stage effect evaluation level, if the stage effect evaluation level is less than the standard stage effect evaluation level, obtain the symptom set time series sequence of the target patient in the feedback cycle, input the symptom set time series sequence and the recommended nursing method into the symptom set estimation model, output the estimated stage effect evaluation level of the target patient in several feedback cycles according to the symptom set estimation model, obtain the estimated average effect evaluation level according to the estimated stage effect evaluation level in the several feedback cycles, compare the estimated average effect evaluation level with the standard average effect evaluation level, if the estimated average effect evaluation level is less than the standard average effect evaluation level, recommend personalized nursing methods for the target patients.

[0062] It should be further explained that, in the specific implementation process, the process of recommending personalized nursing methods for target patients includes:

[0063] Obtain the symptom set time series sequence of the target patient within the feedback cycle, perform similarity matching between the symptom set time series sequence and the symptom set time series sequence of other patients in the local blockchain copy, and obtain the symptom set similarity between other patients and the target patient;

[0064] Filter out the top ten other patients with the highest symptom set similarity, obtain the stage effect evaluation levels of the nursing methods corresponding to the top ten other patients in the feedback cycle, filter out other nursing methods corresponding to the highest stage effect evaluation level, and use the nursing methods as new recommended nursing methods.

[0065] It should be further explained that, in the specific implementation process, the symptom set time series sequence is matched with the symptom set time series sequence of other patients in the local blockchain copy for similarity, and the calculation formula for obtaining the similarity between the symptom sets of other patients and the target patient is:

[0066] ;

[0067] ;

[0068] in, Indicates the similarity of the symptom set between other patients and the target patient, represents the similarity of the symptom of the i-th category between other patients and the target patient, represents the literal value of the target patient's symptom of type i at time t, The literal value of the symptom of the i-th category of other patients at time t; represents the literal average of the target patient's symptom category i, represents the literal average of the symptom of the i-th category of other patients, n represents the total number of moments of the feedback cycle, Indicates the number of other patients who have the same symptoms as the target patient. Indicates the total number of symptom types included in the symptom set of the target patient, , Indicates the conversion factor.

[0069] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A personalized gynecological care recommendation method based on effect evaluation, characterized in that: The following steps are involved: Step s1: construct the knowledge graph topology corresponding to each gynecological disease at each progress stage and store it in the nursing method graph library, and add the stage effect evaluation level and the average effect evaluation level to the edge structure between gynecological diseases and nursing methods in the knowledge graph topology; The process of constructing the knowledge graph topology corresponding to each gynecological disease at each progress stage and storing it in the nursing method graph library includes: Obtaining a number of gynecological diseases and nursing methods corresponding to the gynecological diseases, and obtaining a number of symptom sets and nursing methods corresponding to different disease stages of each gynecological disease, wherein the symptom set includes a number of symptoms; Divide a gynecological disease into periods according to the disease period, and take a disease period as a stage to form a progress stage. Obtain the symptom set and nursing method corresponding to a gynecological disease at a certain progress stage. Take the gynecological disease, symptom set and nursing method as point structures, and connect the gynecological disease with the symptom set and nursing method to generate an edge structure, and construct a knowledge graph topology corresponding to a gynecological disease at a certain progress stage. Similarly, obtain the knowledge graph topology corresponding to each gynecological disease at each progress stage and store it in the nursing method graph library; Step s2: Building a gynecological nursing recommendation platform based on blockchain technology, monitoring the symptom set of the target patient and uploading the symptom set to the gynecological nursing recommendation platform, and the gynecological nursing recommendation platform obtains recommended nursing methods based on the symptom set of the target patient; The process of building a gynecological care recommendation platform based on blockchain technology, monitoring the symptom set of the target patient and uploading the symptom set to the gynecological care recommendation platform includes: The gynecological care recommendation platform is provided with a number of blockchain nodes and a nursing method atlas library. The blockchain nodes are linked to each other to form a blockchain network. The blockchain nodes are used to store the patient's historical disease diagnosis records and historical nursing effect evaluation records, and the blockchain nodes are linked to the Zhilian terminal within a preset range. The Zhilian terminal is used to monitor the patient's symptom set and encrypt and upload the symptom set to the blockchain node. The blockchain node decrypts the received patient's symptom set, packages the decrypted symptom set into a new block, broadcasts the new block to the entire blockchain network, adds the new block to the end of the blockchain, and updates the symptom set in the new block to the local blockchain copy of the blockchain node. The process of the gynecological care recommendation platform to obtain recommended care methods based on the symptom set of the target patient includes: Match the symptom set in the new block with the knowledge graph topology in the nursing method atlas library, obtain the knowledge graph topology whose symptom set included in the knowledge graph topology is consistent with the symptom set in the new block, extract the gynecological diseases, progress stages and nursing methods in the knowledge graph topology, obtain the nursing method with the highest average effect evaluation level between the gynecological diseases, mark the nursing method as the recommended nursing method, mark the stage effect evaluation level and the average effect evaluation level between the gynecological disease and the recommended nursing method as the standard stage effect evaluation level and the standard average effect evaluation level, and feed back the gynecological disease, progress stage, recommended nursing method and standard stage effect evaluation level to the Zhilian terminal; Step s3: The gynecological nursing recommendation platform determines whether the standard stage effect evaluation level within the target patient's feedback cycle meets the requirements. If not, it recommends personalized nursing methods for the target patient; The gynecological nursing recommendation platform determines whether the standard stage effect evaluation level in the target patient feedback cycle meets the requirements. If not, the process of recommending personalized nursing methods for the target patient includes: Construct a symptom set prediction model based on deep learning, use the historical disease diagnosis records and historical nursing effect evaluation records of patients stored in each blockchain node in the gynecological care recommendation platform as training data, train the symptom set prediction model through the training data, and output the trained symptom set prediction model; Extract the standardized treatment steps in the recommended nursing method, segment the recommended nursing method according to the standardized treatment steps, use the standardized treatment steps as the segmentation nodes of the recommended nursing method, divide the recommended nursing method into several feedback cycles, obtain the stage effect evaluation level of the recommended nursing method at the end timestamp of the feedback cycle, and simultaneously obtain the standard stage effect evaluation level corresponding to the feedback cycle, compare the stage effect evaluation level with the standard stage effect evaluation level, if the stage effect evaluation level is less than the standard stage effect evaluation level, obtain the symptom set time series sequence of the target patient in the feedback cycle, input the symptom set time series sequence and the recommended nursing method into the symptom set estimation model, output the estimated stage effect evaluation level of the target patient in several feedback cycles according to the symptom set estimation model, obtain the estimated average effect evaluation level according to the estimated stage effect evaluation level in the several feedback cycles, compare the estimated average effect evaluation level with the standard average effect evaluation level, if the estimated average effect evaluation level is less than the standard average effect evaluation level, recommend personalized nursing methods for the target patients.

2. A personalized gynecological care recommendation method based on effect evaluation according to claim 1, characterized in that: The process of adding the stage effect evaluation level and the average effect evaluation level to the edge structure between gynecological diseases and nursing methods in the knowledge graph topology graph includes: Obtain the patient's historical disease diagnosis records and historical nursing effect evaluation records, wherein the historical disease diagnosis records include the patient's symptom set time series, gynecological diseases, progress stage, and nursing methods within the feedback cycle, and the historical nursing effect evaluation records include the stage effect evaluation level of each feedback cycle corresponding to the nursing method and the average effect evaluation level corresponding to the nursing method obtained according to the stage effect evaluation level of each feedback cycle corresponding to the nursing method; According to the patient's historical disease diagnosis records, the corresponding knowledge graph topology of the patient in the nursing method graph library is extracted. At the same time, according to the patient's historical nursing effect evaluation records, the stage effect evaluation level and the average effect evaluation level are added to the edge structure between gynecological diseases and nursing methods in the knowledge graph topology.

3. A personalized gynecological care recommendation method based on effect evaluation according to claim 2, characterized in that: The process of obtaining the stage effect evaluation level of each feedback cycle corresponding to the nursing method includes: Obtain the gynecological diseases diagnosed, the progress stage diagnosed, and the nursing methods used within the patient feedback cycle, match the diagnosed gynecological diseases and the progress stage diagnosed with the nursing method atlas library, extract the knowledge graph topology corresponding to the diagnosed gynecological diseases and the progress stage diagnosed, extract the symptom set in the knowledge graph topology, and pre-set the severity level threshold interval of the symptom set; At the end timestamp of the feedback cycle, the patient's symptom set is obtained, the literal values ​​corresponding to several symptoms in the symptom set are extracted, the literal values ​​corresponding to the several symptoms are compared with the severity level threshold intervals corresponding to the several symptoms, the severity level of each symptom is obtained, the severity level of each symptom is used as an evaluation index, the indicator weight matrix and the effect evaluation level of the evaluation index are preset, the membership matrix of the evaluation index for different effect evaluation levels is obtained through fuzzy comprehensive evaluation, and the effect evaluation level is obtained according to the membership matrix and the indicator weight matrix.

4. A personalized gynecological care recommendation method based on effect evaluation according to claim 3, characterized in that: The process of recommending personalized care for targeted patients includes: Obtain the symptom set time series sequence of the target patient within the feedback cycle, perform similarity matching between the symptom set time series sequence and the symptom set time series sequence of other patients in the local blockchain copy, and obtain the symptom set similarity between other patients and the target patient; Filter out the top ten other patients with the highest symptom set similarity, obtain the stage effect evaluation levels of the nursing methods corresponding to the top ten other patients in the feedback cycle, filter out other nursing methods corresponding to the highest stage effect evaluation level, and use the nursing methods as new recommended nursing methods.