An intelligent management system and method for health education content for gynecological care

Abstract

The present invention discloses an intelligent management system and method for health education content for gynecological care, the method comprising the following steps: S1, collecting basic information and health status, as well as basic preference; determining keywords; S2, selecting the most appropriate content library of health education materials according to patient data; S3, monitoring behavior data and health status, obtaining real-time preference, re-extracting and determining keywords; and outputting scores for educational content at the same time; S4, determining the educational scores of different patients for designated educational content, obtaining an average score, and updating the database; S5, dynamically adjusting the recommendation list according to the ranking results, relevance and weight of keywords, and realizing intelligent management of health education content. It can automatically screen and recommend appropriate health education content according to the needs and preferences of patients, making the allocation of medical resources more reasonable and efficient, and realizing accurate grasp of patient needs and provision of personalized services.

Description

Technical Field

[0001] The present invention relates to the field of medical care information technology, and in particular to a treatment or health improvement plan, and specifically to an intelligent management system and method for health education content for gynecological care. Background Art

[0002] In the current medical care field, especially in gynecological care, health education is an important means to improve patients' self-management ability, promote recovery and prevent disease recurrence. Its effectiveness and pertinence are particularly important. However, with the continuous advancement of medical technology and the increasing diversification of patient needs, the traditional gynecological care health education model has exposed many limitations.

[0003] At present, many health education activities in gynecological nursing are often carried out as routine, lacking in-depth understanding and effective response to patients' individual needs. This "one-size-fits-all" education method is not only difficult to stimulate patients' interest in learning, but may also greatly reduce the educational effect because the content is out of touch with the actual needs of patients. At the same time, different patients have significant differences in age, cultural background, health status, etc., and their needs for health education content are also different. However, current gynecological nursing health education often ignores these individual differences, resulting in a lack of pertinence and effectiveness of educational content.

[0004] Therefore, it is necessary to improve the deficiencies in the prior art to solve the above problems. Summary of the invention

[0005] The present invention overcomes the deficiencies of the prior art and provides an intelligent management system and method for health education content for gynecological care.

[0006] To achieve the above object, the technical solution adopted by the present invention is: a method for intelligent management of health education content for gynecological care, comprising the following steps:

[0007] S1. Collect the patient's basic information and health status, as well as the basic preference of health education content; determine keywords based on the basic preference;

[0008] S2, integrating the collected patient data into the system, and the intelligent recommendation engine selects the most appropriate content library of health education materials from the database based on the patient data according to the keywords and the average score of the corresponding content in the database;

[0009] S3. Monitor the patient's behavior data and health status in real time, obtain the real-time preference of health education content based on the behavior data and health status, and re-extract and determine keywords; at the same time, output the patient's score for the education content and synchronize it to the database;

[0010] S4. for the content library, determining the education scores of different patients for the specified education content, obtaining the average score of the corresponding education content, and using it to update the database;

[0011] S5. Dynamically adjust the recommendation list based on the ranking results, relevance and weight of keywords to achieve intelligent management of health education content.

[0012] In a preferred embodiment of the present invention, the step S1 includes the following sub-steps:

[0013] S11. Collect the patient’s basic information and health status;

[0014] S12, based on the patient's interest in different health education topics, previous feedback on health education content, and the patient's search for specific health information, obtain the basic preference for health education content;

[0015] S13. Determine keywords based on basic preference, including necessary keywords and non-essential keywords.

[0016] In a preferred embodiment of the present invention, in step S12, the patient's interest score is calculated: ,in, It is Patients on the topic Interest score, is the interest score weight, is the number of topics;

[0017] Calculate the patient's feedback score: ,in, It is Patients on content Feedback score, is the feedback score weight, is the amount of content;

[0018] Calculate the search score for a patient: ,in, It is Patients to information sources Search score of is the search score weight, is the number of information sources;

[0019] Calculate the Patient preference: ,in , , is the weight coefficient used to adjust the importance of different scoring parts.

[0020] In a preferred embodiment of the present invention, in step S13, a preference score is calculated based on the patient's basic preference: ,in, It is The patient's Preference, It is The weight of preference, is the dimension, is the number of preference dimensions;

[0021] Calculate the health status score: ,in, It is The patient's The health status indicator is The preference dimension, Yes The health status indicator is The weights on the preference dimensions, is the number of health status dimensions;

[0022] Calculate the basic information score: ,in, It is The patient's Basic information attributes, It is The weight of basic information, is the number of basic information dimensions;

[0023] Calculate the composite score: ,in, is a machine learning model. is a model parameter used to , , Mapping to keyword scores ,according to The value is high or low. From multiple keywords, the ones with the highest scores are selected as necessary keywords, and the rest are non-essential keywords.

[0024] In a preferred embodiment of the present invention, the step S2 includes the following sub-steps:

[0025] S21. Normalize the patient's basic information, health status and preference scores, remove duplicate, incomplete or abnormal data items, ensure that the data is on the same scale, and integrate them into the system;

[0026] S22. extract necessary keywords according to the patient's preference score, and for each necessary keyword, query the database for relevant content and obtain the average score of these contents;

[0027] S23. Use machine learning models to analyze patient data and content libraries to find the best matching content, and select the content with the highest score to recommend to patients based on the recommendation score.

[0028] In a preferred embodiment of the present invention, in step S22, the necessary keyword score is calculated according to the patient's preference score: ,in, Is the theme Interest score, Is the theme The weight of

[0029] Calculate the average score of your content: ,in, is the amount of content, It is the content The score, It is the content Number of times it was preferred by patients.

[0030] In a preferred embodiment of the present invention, in step S23, the recommended content is calculated: ,in, From the content library Select the content with the highest recommendation score , It is for content Recommendation score.

[0031] In a preferred embodiment of the present invention, the step S3 includes the following sub-steps:

[0032] S31. Record and collect the patient's behavior data in real time through the system's built-in log, and record and collect the patient's health status in real time through the health report submitted by the patient regularly;

[0033] S32, based on the collected real-time behavior data and health status, obtain the real-time preference of health education content, re-extract keywords, determine necessary keywords and non-essential keywords, and rank different keywords by weight;

[0034] S33. Synchronize the patient's score evaluation results on the educational content into the database.

[0035] In a preferred embodiment of the present invention, in step S32, a real-time preference score is calculated based on the real-time behavior data and health status: , where the value of each behavioral data is standardized or normalized to ensure that the weights can be applied fairly to all variables; The function represents the maximum value of the behavior data among all users or sessions; is the total time spent watching educational videos, is the number of pauses, is the number of repeated views, is the percentage of exercise completion, is the participation rate of interactive Q&A, It is an indicator of health status, which is a combination of multiple health parameters. , , , , , They are the weights of viewing time, number of pauses, repeated viewing, exercise completion, interactive question-and-answer participation, and health status;

[0036] Relevance score for extracted keywords: ,in, It is The relevance score of the keywords, is the total number of times users interact with the content, It is The weight of the interaction is decayed according to the freshness of the interaction. is the keyword With The cosine similarity between interactive contents is used to measure the correlation between content and user preferences;

[0037] Dynamically adjust keyword weights and extract necessary keywords: , ,in, is the normalized keyword relevance score, is the total number of keywords, It is a list of keywords sorted in descending order based on relevance score.

[0038] The present invention provides a system for intelligent management of health education content for gynecological care, comprising:

[0039] Information collection module, used to collect and store the patient's basic information and health status;

[0040] Preference assessment module, used to identify and assess patients’ preferences for different health education contents;

[0041] The behavior tracking module is used to monitor the patient's behavior data in real time when learning health education content, and transmit the behavior data to the preference evaluation module;

[0042] A keyword extraction module is used to extract and determine corresponding keywords based on the patient's preference for health education content;

[0043] A data content library for storing and managing health education materials required by patients;

[0044] A personalized recommendation module is used to generate personalized educational content recommendations for patients based on the patient's keyword data and the average score of health education materials in the data content library;

[0045] The scoring management module is used to update the average score of the corresponding health education materials in the data content library according to the patient's score on the education content.

[0046] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0047] The present invention provides an intelligent management system and method for health education content for gynecological care. Through deepening personalized health education, optimizing the intelligent recommendation system, promoting patient self-management and disease recovery, and optimizing medical service processes, etc., it can automatically screen and recommend appropriate health education content according to the patient's needs and preferences, so as to make the allocation of medical resources more reasonable and efficient, help reduce unnecessary waste of medical resources, improve the overall benefit of medical services, achieve accurate grasp of patient needs and provision of personalized services, improve the quality and efficiency of medical services, and promote patients' health recovery and improvement of their quality of life.

[0048] In the present invention, by comprehensively considering the patient's interests, feedback and search behavior to calculate the preference, the system can more accurately grasp the patient's personalized preferences, provide a strong basis, make the recommended health education content closer to the patient's actual needs, and by labeling the patient with keywords, it is helpful to segment the patient group and identify the needs of different patient groups, so that relevant health education information can be accurately pushed to the patient, and it is helpful for medical staff to better understand the patient's cognitive level and behavioral habits and adopt more effective health education strategies. Through targeted health education, the patient's compliance can be enhanced, the treatment effect and patient satisfaction can be improved, so as to provide patients with more personalized medical services.

[0049] In the present invention, by real-time monitoring and analysis of patient behavior data, combined with keyword determination and weight sorting, it is possible to more accurately and dynamically select and adjust the most appropriate health education material recommendation list, ensure that the recommended content is always consistent with the patient's current status and needs, ensure the relevance and personalization of the recommended content, and then provide accurate health education and personalized support, so that patients can better understand and execute medical advice, thereby improving treatment effects. At the same time, by real-time updating of education content scores in the database, it can be ensured that the recommended content in the database always reflects the latest user preferences and behavior data, thereby improving the personalization and effectiveness of health education content. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work.

[0051] Figure 1 is a flow chart of a method for intelligent management of health education content for gynecological care according to a preferred embodiment of the present invention;

[0052] Figure 2 It is a structural diagram of an intelligent management system for health education content for gynecological care according to a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0055] like Figure 1 As shown, a method for intelligent management of health education content for gynecological care includes the following steps:

[0056] S1. Collect the patient's basic information and health status, as well as the basic preference of health education content; determine keywords based on the basic preference;

[0057] S2, integrating the collected patient data into the system, and the intelligent recommendation engine selects the most appropriate content library of health education materials from the database based on the patient data according to the keywords and the average score of the corresponding content in the database;

[0058] S3. Monitor the patient's behavior data and health status in real time, obtain the real-time preference of health education content based on the behavior data and health status, and re-extract and determine keywords; at the same time, output the patient's score for the education content and synchronize it to the database;

[0059] S4. for the content library, determining the education scores of different patients for the specified education content, obtaining the average score of the corresponding education content, and using it to update the database;

[0060] S5. Dynamically adjust the recommendation list based on the ranking results, relevance and weight of keywords to achieve intelligent management of health education content.

[0061] It should be noted that through the deepening of personalized health education, the optimization of intelligent recommendation systems, the promotion of patient self-management and disease recovery, and the optimization of medical service processes, it is possible to automatically screen and recommend appropriate health education content based on the needs and preferences of patients, making the allocation of medical resources more reasonable and efficient, helping to reduce unnecessary waste of medical resources, and improving the overall benefits of medical services. It achieves accurate grasp of patient needs and the provision of personalized services, improves the quality and efficiency of medical services, and promotes patients' health recovery and improved quality of life.

[0062] In some specific embodiments, the step of S1 includes the following sub-steps:

[0063] S11. Collect the patient’s basic information and health status;

[0064] S12, based on the patient's interest in different health education topics, previous feedback on health education content, and the patient's search for specific health information, obtain the basic preference for health education content;

[0065] S13. Determine keywords based on basic preference, including necessary keywords and non-essential keywords.

[0066] In this embodiment, in step S11, basic information and health status of gynecological patients are collected during registration. The basic information includes name, age, contact information, address, language, ethnicity, marital status, occupation, and education level; the health status includes current medical history, that is, the recovery stage of gynecological diseases.

[0067] For example, the patient's health condition, the patient's current medical history is uterine fibroids, she underwent laparoscopic surgery for myomectomy, and is currently in the postoperative recovery stage. The wound heals well, but she occasionally has mild abdominal discomfort and fatigue.

[0068] In this embodiment, in step S12, the patient's interest score is calculated: ,in, It is Patients on the topic Interest score, is the interest score weight, is the number of topics;

[0069] Calculate the patient's feedback score: ,in, It is Patients on content Feedback score, is the feedback score weight, is the amount of content;

[0070] Calculate the search score for a patient: ,in, It is Patients to information sources Search score of is the search score weight, is the number of information sources;

[0071] Calculate the Patient preference: ,in , , is the weight coefficient, which is used to adjust the importance of different scoring parts;

[0072] Among them, the weights in different scoring parts are calculated in combination with the existing entropy weight method. The entropy weight method is an objective weight allocation method that determines the weight based on the discrete degree of the data rather than based on subjective judgment. The combination of the two ensures the distribution of weights. Specifically, calculate the indicator proportion: For the standardized data, calculate each indicator In each sample The proportion of , ,in It is The sample in The value of each influencing factor;

[0073] Calculate information entropy: Calculate the information entropy of each indicator using the weight , ,in, , is the sample size;

[0074] Calculate the coefficient of variation and weights: Coefficient of variation , calculate the weight according to the coefficient of difference .

[0075] In order to ensure that the preference scores are within a reasonable range, normalization is performed: ,in, and are the minimum and maximum preference scores of all patients, respectively.

[0076] In this embodiment, in step S13, the preference score is calculated according to the patient's basic preference: ,in, It is The patient's Preference, It is The weight of preference, is the dimension, is the number of preference dimensions;

[0077] Calculate the health status score: ,in, It is The patient's The health status indicator is The preference dimension, Yes The health status indicator is The weights on the preference dimensions, is the number of health status dimensions;

[0078] Calculate the basic information score: ,in, It is The patient's Basic information attributes, It is The weight of basic information, is the number of basic information dimensions;

[0079] Calculate the composite score: ,in, is a machine learning model. is a model parameter used to , , Mapping to keyword scores ,according to The value is high or low. From multiple keywords, the ones with the highest scores are selected as necessary keywords, and the rest are non-essential keywords.

[0080] It should be noted that the entropy weight method is used to calculate , , The weights of preference, health status and basic information are shown in Table 1. The calculation steps of entropy weight method are consistent with those in S12.

[0081] In some specific embodiments, the step of S2 includes the following sub-steps:

[0082] S21. Normalize the patient's basic information, health status and preference scores, remove duplicate, incomplete or abnormal data items, ensure that the data is on the same scale, and integrate them into the system;

[0083] S22. extract necessary keywords according to the patient's preference score, and for each necessary keyword, query the database for relevant content and obtain the average score of these contents;

[0084] S23. Use machine learning models to analyze patient data and content libraries to find the best matching content, and select the content with the highest score to recommend to patients based on the recommendation score.

[0085] In this embodiment, in step S21, it is necessary to remove duplicate data from the collected patient data and identify and process outliers: outliers may be caused by data entry errors or special circumstances of the patient, and need to be processed according to the actual situation, such as replacing them with mean, median or deleting them; normalization processing is specifically to scale the data so that it falls into a small specific interval, such as [0,1] or [-1,1], which helps to eliminate the impact of the dimension on the result, and can adopt minimum or maximum normalization, Z-score normalization, etc.

[0086] In this embodiment, in step S22, the necessary keyword score is calculated according to the patient's preference score: ,in, Is the theme Interest score, Is the theme The weight of

[0087] Calculate the average score of your content: ,in, is the amount of content, It is the content The score, It is the content Number of times it was preferred by patients.

[0088] It should be noted that the entropy weight method is used to calculate Theme of the expression The calculation steps of the entropy weight method are consistent with those in S12.

[0089] In this embodiment, in step S23, the recommended content is calculated: ,in, From the content library Select the content with the highest recommendation score , It is for content Recommendation score.

[0090] In some specific embodiments, the step of S3 includes the following sub-steps:

[0091] S31. Record and collect the patient's behavior data in real time through the system's built-in log, and record and collect the patient's health status in real time through the health report submitted by the patient regularly;

[0092] S32, based on the collected real-time behavior data and health status, obtain the real-time preference of health education content, re-extract keywords, determine necessary keywords and non-essential keywords, and rank different keywords by weight;

[0093] S33. Synchronize the patient's score evaluation results on the educational content into the database.

[0094] In this embodiment, in step S31, the behavioral data refers to the record of the patient's interaction with the health education content, including: the time of watching the educational video, the number of pauses, the segments watched repeatedly, the completion of exercises, and the participation in interactive Q&A; at the same time, the behavioral data is converted into numerical form, including: the time of watching the educational video is converted into the total viewing time or the average viewing time; the number of pauses is converted into the actual number of uses; the segments watched repeatedly are converted into the total time or number of repeated viewings; the exercise completion status is converted into the completion percentage; the interactive Q&A participation is converted into the number of participations or the participation rate.

[0095] In this embodiment, in step S32, a real-time preference score is calculated based on the real-time behavior data and health status: , where the value of each behavioral data is standardized or normalized to ensure that the weights can be applied fairly to all variables; The function represents the maximum value of the behavior data among all users or sessions; is the total time spent watching educational videos, is the number of pauses, is the number of repeated views, is the percentage of exercise completion, is the participation rate of interactive Q&A, It is an indicator of health status, which is a combination of multiple health parameters. , , , , , They are the weights of viewing time, number of pauses, repeated viewing, exercise completion, interactive question-and-answer participation, and health status;

[0096] Relevance score for extracted keywords: ,in, It is The relevance score of the keywords, is the total number of times users interact with the content. It is The weight of the interaction is decayed according to the freshness of the interaction. is the keyword With The cosine similarity between interactive contents is used to measure the correlation between content and user preferences;

[0097] Dynamically adjust keyword weights and extract necessary keywords: , ,in, is the normalized keyword relevance score, is the total number of keywords, It is a list of keywords sorted in descending order based on relevance score.

[0098] It should be noted that the entropy weight method is used to calculate , , , , , , The number of views, pauses, repeat views, exercise completion, interactive Q&A participation, health status, and The calculation steps of the entropy weight method are the same as those in S12.

[0099] In some specific embodiments, in step S4, it is ensured that the educational content scores stored in the database reflect the latest user preferences and behavior data. For each educational content, the average score is calculated based on the different patients' preferences for a specific educational content. The average score, ,in, It is The total number of ratings of educational content, It is Patients The score of educational content, is a decay function that gives higher weight to recent feedback, , is the base of natural logarithms, is the decay rate, It’s feedback time;

[0100] For each educational content , using the average score calculated above To update the relevant records in the database.

[0101] In some specific implementation schemes, in step S5, when dynamically adjusting the recommendation list, the priority of each educational content is calculated based on the ranking results, relevance and weight of the keywords. Suitability for current patients: ,in, It is The relevance score of the keywords, It is The weight of the keywords, Based on the average score of educational content The adjustment function is based on To increase or decrease the value , for example, if Below a certain threshold, It can be a constant less than 1, or even 0 (indicating that the content is completely ignored);

[0102] For the patient education content list, according to the calculated fitness , sort all educational contents and recommend the corresponding health education contents to patients.

[0103] like Figure 2 As shown, a system for intelligent management of health education content for gynecological care includes:

[0104] Information collection module, used to collect and store the patient's basic information and health status;

[0105] Preference assessment module, used to identify and assess patients’ preferences for different health education contents;

[0106] The behavior tracking module is used to monitor the patient's behavior data in real time when learning health education content, and transmit the behavior data to the preference evaluation module;

[0107] A keyword extraction module is used to extract and determine corresponding keywords based on the patient's preference for health education content;

[0108] A data content library for storing and managing health education materials required by patients;

[0109] A personalized recommendation module is used to generate personalized educational content recommendations for patients based on the patient's keyword data and the average score of health education materials in the data content library;

[0110] The scoring management module is used to update the average score of the corresponding health education materials in the data content library according to the patient's score on the education content.

[0111] In some specific implementation schemes, the patient collects and stores basic information and health status through the information collection module, and identifies and evaluates the patient's preference for different health education contents through the preference evaluation module, and transmits the preference data to the keyword extraction module, extracts and determines the corresponding keywords for the patient's preference, and the personalized recommendation module generates personalized education content recommendations for the patient based on the patient's keyword data and the average score of the health education materials in the data content library. At the same time, the behavior tracking module monitors the patient's behavior data in learning health education content in real time, and transmits the behavior tracking data to the preference evaluation module, re-identifies and evaluates the patient's real-time preference for different health education contents through the preference evaluation module, and transmits the real-time preference data to the keyword extraction module, extracts and re-determines the corresponding keywords for the patient's preference, and the scoring management module obtains the average score data of the corresponding education content from different patients' scores for the education content, and transmits it to the data content library to update the score of the health education material. The personalized recommendation module dynamically adjusts the patient's education content list in real time according to the real-time keyword sorting results, relevance and weight, so as to achieve the purpose of intelligent management of health education content.

[0112] It should be noted that the intelligent management system for health education content can implement the steps in the intelligent management method for health education content in the above embodiment, and can achieve the same technical effects. Please refer to the description in the above embodiment and no detailed description will be given here.

[0113] The above is based on the ideal embodiment of the present invention. Through the above description, it is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is limited by the attached claims rather than the above description, and it is intended to include all changes within the meaning and scope of the equivalent elements of the claims. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0114] In addition, it should be understood that although the present specification is described according to implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment may also be appropriately combined to form other implementation modes that can be understood by those skilled in the art.

Claims

1. A method for intelligent management of health education content for gynecological nursing, characterized in that: The following steps are involved: S1. Collect the patient's basic information and health status, as well as basic preferences for health education content; Determine keywords based on basic preference; S2, integrating the collected patient data into the system, and the intelligent recommendation engine selects the most appropriate content library of health education materials from the database based on the patient data according to the keywords and the average score of the corresponding content in the database; S3. Monitor the patient's behavior data and health status in real time, obtain the real-time preference of health education content based on the behavior data and health status, and re-extract and determine keywords; at the same time, output the patient's score for the education content and synchronize it to the database; S4. for the content library, determining the education scores of different patients for the specified education content, obtaining the average score of the corresponding education content, and using it to update the database; S5. Dynamically adjust the recommendation list based on the ranking results, relevance and weight of keywords to achieve intelligent management of health education content; The step S1 includes the following sub-steps: S11. Collect the patient’s basic information and health status; S12, based on the patient's interest in different health education topics, previous feedback on health education content, and the patient's search for specific health information, obtain the basic preference for health education content; S13. Determine keywords based on the basic preference, including necessary keywords and non-essential keywords involved; In step S12, the patient's interest score is calculated: ,in, It is Patients on the topic Interest score, is the interest score weight, is the number of topics; Calculate the patient's feedback score: ,in, It is Patients on content Feedback score, is the feedback score weight, is the amount of content; Calculate the search score for a patient: ,in, It is Patients to information sources Search score of is the search score weight, is the number of information sources; Calculate the Patient preference: ,in , , is the weight coefficient, which is used to adjust the importance of different scoring parts; In step S13, the preference score is calculated according to the patient's basic preference: ,in, It is The patient's Preference, It is The weight of preference, is the dimension, is the number of preference dimensions; Calculate the health status score: ,in, It is The patient's The health status indicator is The preference dimension, Yes The health status indicator is The weights on the preference dimensions, is the number of health status dimensions; Calculate the basic information score: ,in, It is The patient's Basic information attributes, It is The weight of basic information, is the number of basic information dimensions; Calculate the composite score: ,in, is a machine learning model, is a model parameter used to , , Mapping to keyword scores ,according to The value is high or low. From multiple keywords, the ones with the highest scores are selected as necessary keywords, and the rest are non-essential keywords; The step S2 includes the following sub-steps: S21. Normalize the patient's basic information, health status and preference scores, remove duplicate, incomplete or abnormal data items, ensure that the data is on the same scale, and integrate them into the system; S22. extract necessary keywords according to the patient's preference score, and for each necessary keyword, query the database for relevant content and obtain the average score of these contents; S23. Use machine learning models to analyze patient data and content libraries to find the best matching content. Based on the recommendation scores, select the content with the highest score and recommend it to the patient to generate an initial recommendation list.

2. The method for intelligent management of health education content for gynecological nursing according to claim 1, characterized in that: In step S22, the necessary keyword score is calculated according to the patient's preference score: ,in, Is the theme Interest score, Is the theme The weight of Calculate the average score of your content: ,in, is the amount of content, It is the content The score, It is the content Number of times it was preferred by patients.

3. The method for intelligent management of health education content for gynecological nursing according to claim 1, characterized in that: In the step S23, the recommended content is calculated: ,in, From the content library Select the content with the highest recommendation score , It is for content Recommendation score.

4. The method for intelligent management of health education content for gynecological nursing according to claim 1, characterized in that: The step S3 includes the following sub-steps: S31. Record and collect the patient's behavior data in real time through the system's built-in log, and record and collect the patient's health status in real time through the health report submitted by the patient regularly; S32, based on the collected real-time behavior data and health status, obtain the real-time preference of health education content, re-extract keywords, determine necessary keywords and non-essential keywords, and rank different keywords by weight; S33. Synchronize the patient's score evaluation results on the educational content into the database.

5. The method for intelligent management of health education content for gynecological nursing according to claim 4, characterized in that: In step S32, a real-time preference score is calculated based on the real-time behavior data and health status: , where the value of each behavioral data is standardized or normalized to ensure that the weights can be applied fairly to all variables; The function represents the maximum value of the behavior data among all users or sessions; is the total time spent watching educational videos, is the number of pauses, is the number of repeated views, is the percentage of exercise completion, is the participation rate of interactive Q&A, It is an indicator of health status, which is a combination of multiple health parameters. , , , , , They are the weights of viewing time, number of pauses, repeated viewing, exercise completion, interactive question-and-answer participation, and health status; Relevance score for extracted keywords: ,in, It is The relevance score of the keywords, is the total number of times users interact with the content, It is The weight of the interaction is decayed according to the freshness of the interaction. is the keyword With The cosine similarity between interactive contents is used to measure the correlation between content and user preferences; Dynamically adjust keyword weights and extract necessary keywords: , ,in, is the normalized keyword relevance score, is the total number of keywords, It is a list of keywords sorted in descending order based on relevance score.

6. A system based on a method for intelligent management of health education content for gynecological nursing according to any one of claims 1 to 5, characterized in that: include: Information collection module, used to collect and store the patient's basic information and health status; Preference assessment module, used to identify and assess patients’ preferences for different health education contents; The behavior tracking module is used to monitor the patient's behavior data in real time when learning health education content, and transmit the behavior data to the preference evaluation module; A keyword extraction module is used to extract and determine corresponding keywords based on the patient's preference for health education content; A data content library for storing and managing health education materials required by patients; A personalized recommendation module is used to generate personalized educational content recommendations for patients based on the patient's keyword data and the average score of health education materials in the data content library; The scoring management module is used to update the average score of the corresponding health education materials in the data content library according to the patient's score on the education content.

Images