Medical information pushing method based on smart medical big data and smart medical system
By building user profiles and dynamically adjusting push content based on interest feedback data, the problem of mismatch between information and user needs in existing technologies has been solved, achieving a more efficient utilization of information.
Patent Information
- Application Number
- CN202511594177.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-03
- Publication Date
- 2026-02-03
AI Technical Summary
Existing methods of pushing medical information cannot accurately deliver information based on users' personalized needs and real-time changes in interests, resulting in a mismatch between information and user needs and low information utilization.
By acquiring multimodal user data, user profiles are built, and combined with interest feedback behavior data, push content is dynamically adjusted to match information with user needs.
It improves the matching accuracy and utilization rate of information push, ensuring that the pushed content better meets users' personalized needs and real-time interests.
Smart Images
Figure CN121460131A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of information pushing, in particular to a medical information pushing method based on smart medical big data and a smart medical system. BACKGROUND
[0002] The medical information pushing method aims to provide accurate and personalized medical information and services for users. In the current medical information pushing scenario, medical data sources are extensive and complex, covering hospital electronic medical records, physical examination reports, wearable device monitoring data, and user medical search records on the network, etc.
[0003] Traditional information pushing methods are mostly "one-size-fits-all" general pushing, which cannot accurately push information according to the personalized needs and real-time interest changes of users. At the same time, medical data is often in a scattered state, lacking effective integration and utilization, making it difficult to form a comprehensive and accurate understanding of users, resulting in a mismatch between the pushed information and user needs, and low information utilization. SUMMARY
[0004] The present application aims to provide a medical information pushing method based on smart medical big data and a smart medical system, which aims to solve the technical problems of mismatch between the pushed information and user needs and low information utilization in the prior art.
[0005] To achieve the above-mentioned purpose, the present application adopts a medical information pushing method based on smart medical big data, comprising the following steps: Respectively acquire user multi-modal data, extract features from the multi-modal data, and construct a user portrait according to the features; Acquire user interest feedback behavior data, identify the current behavior of the user, and output interest feedback data; Integrate the medical information database, acquire the primary pushing strategy based on the user portrait, and dynamically adjust the pushing content according to the interest feedback data.
[0006] Among them, in the step of respectively acquiring user multi-modal data, extracting features from the multi-modal data, and constructing a user portrait according to the features: Respectively acquire user medical records, health monitoring, online behavior, and regional environment data, and extract and construct features; According to the extracted features, construct the user portrait from multiple dimensions, and output the user portrait data.
[0007] Among them, in the step of respectively acquiring user medical records, health monitoring, online behavior, and regional environment data, and extracting and constructing features: Acquire user medical record data and extract disease, treatment, medication, and physiological index features; Acquire user health monitoring data, and extract motion, heart rate characteristics; Acquire user online behavior data, and extract attention field, interest preference, appeal characteristics; Acquire user regional environment data, and extract geographical, environmental impact characteristics.
[0008] Among them, in the step of acquiring user interest feedback behavior data, identifying user current behavior, and outputting interest feedback data: Real-time acquisition of user behavior data, and pre-processing of behavior data; Defining invalid interest feedback behavior and valid interest feedback behavior, matching behavior data, and acquiring matching data.
[0009] Among them, after the step of defining invalid interest feedback behavior and valid interest feedback behavior, matching behavior data, and acquiring matching data: According to the matching data, the behavior data matching identifier is given.
[0010] Among them, after the step of according to the matching data, the behavior data matching identifier is given: Filtering invalid interest feedback data according to the matching identifier, and outputting valid interest feedback data.
[0011] Among them, in the step of integrating medical information database, acquiring primary push strategy based on user portrait, and dynamically adjusting push content according to interest feedback data: Collect medical information, and classify and label medical information to establish a medical information database; Receive user portrait data, filter matching information matched with the user from the medical information database, and develop a primary push strategy according to the matching information.
[0012] Among them, after the step of receiving user portrait data, filtering matching information matched with the user from the medical information database, and developing a primary push strategy according to the matching information: Receive valid interest feedback data, filter and optimize the content in the primary push strategy, and update the user portrait.
[0013] Among them, after the step of receiving valid interest feedback data, filtering and optimizing the content in the primary push strategy, and updating the user portrait: Analyze the similarity between users, predict the interest degree of users to medical information, and push interest content.
[0014] The application also provides a smart medical system, comprising a user portrait construction module, an interest feedback behavior identification module, and an information dynamic push module; wherein: The user portrait construction module is used for respectively acquiring user multi-modal data, performing feature extraction on the multi-modal data, and constructing a user portrait according to the features. The interest feedback behavior recognition module is used for acquiring user interest feedback behavior data, recognizing the current behavior of the user, and outputting interest feedback data. The information dynamic pushing module is used for integrating a medical information database, acquiring a primary pushing strategy based on the user portrait, and dynamically adjusting the pushing content according to the interest feedback data.
[0015] The medical information pushing method based on the big data of intelligent medical treatment and the intelligent medical system of the present application adopt the user portrait construction module, the interest feedback behavior recognition module, and the information dynamic pushing module to perform the following steps: respectively acquiring user multi-modal data, performing feature extraction on the multi-modal data, and constructing a user portrait according to the features; acquiring user interest feedback behavior data, recognizing the current behavior of the user, and outputting interest feedback data; integrating a medical information database, acquiring a primary pushing strategy based on the user portrait, and dynamically adjusting the pushing content according to the interest feedback data; formulating a primary pushing strategy through the user portrait, and dynamically adjusting the pushing content according to the interest feedback data, so as to increase the matching degree between the pushed information and the user demand, and improve the information utilization rate. BRIEF DESCRIPTION OF DRAWINGS
[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.
[0017] Figure 1 It is the step flow chart of the medical information pushing method based on the big data of intelligent medical treatment of the present application.
[0018] Figure 2 It is the step flow chart of S100 of the present application.
[0019] Figure 3 It is the step flow chart of S200 of the present application.
[0020] Figure 4 It is the step flow chart of S300 of the present application.
[0021] Figure 5 It is the structure principle diagram of the intelligent medical system of the present application.
[0022] Figure 6 It is the structure principle diagram of the electronic device of the present application.
[0023] 401-user portrait construction module, 402-interest feedback behavior recognition module, 403-information dynamic pushing module. DETAILED DESCRIPTION
[0024] The exemplary embodiments will be described in detail herein with reference to the accompanying drawings. In the following description, unless otherwise indicated, like numbers in the different drawings represent similar or analogous elements. The implementations described in the following exemplary embodiments are not meant to represent all implementations consistent with the present disclosure.
[0025] The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in the present application and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "and / or," as used herein, refers to and encompasses any and all possible combinations of one or more of the associated listed items.
[0026] It is to be understood that, although the terms first, second, third, etc. can be used herein to describe various information, these terms are not intended to denote a temporal or chronological order. Rather, these terms are used only as labels to distinguish different sets of the information from each other. For example, a first information can be termed a second information, and similarly, a second information can also be termed a first information, without departing from the scope of the present application. As used herein, the word "if' can be construed to mean "when" or "in response to determining" or "in response to a determination" depending on the context.
[0027] Referring to Figures 1-4 The present application provides a medical information pushing method based on intelligent medical big data, comprising the following steps: S100: respectively acquiring user multi-modal data, performing feature extraction on the multi-modal data, and constructing a user portrait according to the features.
[0028] In the present embodiment, user multi-modal data is acquired respectively, feature extraction is performed on the multi-modal data, and a user portrait is constructed according to the features. The specific process is as follows: S101: acquiring user medical record data and extracting disease, treatment, medication, and physiological index features; S102: acquiring user health monitoring data and extracting exercise and heart rate features; S103: acquiring user online behavior data and extracting attention field, interest preference, and appeal features; S104: acquiring user regional environment data and extracting geographical and environmental impact features; S105: constructing a user portrait from multiple dimensions according to the extracted features, and outputting user portrait data.
[0029] In the above process, medical record data is acquired and features are extracted, data acquisition: user's medical record data is acquired from hospital electronic medical record systems, medical examination equipment and other channels. These data include but are not limited to disease diagnosis records, treatment plans, medication records, and physiological index test results, etc.
[0030] Feature extraction: natural language processing techniques and data mining algorithms are used to extract key features from medical record data. For disease characteristics, the types and severity of the user's disease are determined; treatment characteristics cover treatment methods (such as drug treatment, surgical treatment), treatment cycle, etc.; medication characteristics include drug name, dosage, frequency, etc.; physiological index characteristics extract important indicators such as blood glucose, blood pressure, blood lipids, etc.
[0031] Acquire health monitoring data and extract features, data acquisition: collect user's health monitoring data by means of wearable devices (such as smart bands, smart watches), household health monitoring instruments (such as electronic sphygmomanometers, blood glucose meters), etc. These devices can record user's movement steps, movement distance, movement duration, heart rate changes, etc. in real time or periodically.
[0032] Feature extraction: statistical analysis is performed on health monitoring data to extract movement features and heart rate features. Movement features can include daily exercise amount, exercise intensity (evaluated by movement steps, movement duration, etc.), exercise type preference, etc.; heart rate features focus on resting heart rate, exercise heart rate range, heart rate recovery time, etc.
[0033] Acquire online behavior data and extract features, data acquisition: acquire online behavior data through user's operation records on medical related websites, APPs. Including user browsed medical information pages, searched keywords, participated health discussion topics, collected and shared content, etc.
[0034] Feature extraction: use text mining and user behavior analysis techniques to extract user's focus areas, interest preferences and appeal features. Focus areas can be determined as children's health, cardiovascular disease, TCM health preservation, etc.; interest preferences can be further divided into interest degrees in diet health, exercise fitness, disease prevention, etc.; appeal features analyze whether users are seeking disease treatment suggestions, health preservation knowledge or medical product recommendations, etc.
[0035] Acquire regional environmental data and extract features, data acquisition: acquire environmental data of the user's region from meteorological departments, environmental monitoring agencies, etc. including geographic location information (such as city, region), climate conditions (such as temperature, humidity, precipitation), air quality index (PM2.5, PM10, etc.), water quality, etc. For example, the user's city has poor air quality recently, with high PM2.5 concentration.
[0036] Feature extraction: extract geographical features and environmental impact features. Geographical features explicitly indicate the geographical location and surrounding environment characteristics of the user; environmental impact features analyze the possible impact of environmental factors on user health, such as air pollution may cause respiratory diseases, poor water quality may cause gastrointestinal problems, etc.
[0037] Construct user portrait and output data, portrait construction: integrate the extracted medical record features, health monitoring features, online behavior features and regional environment features, and construct a comprehensive and three-dimensional user portrait from multiple dimensions such as health status, interest preferences, living habits and environmental impact.
[0038] Data output: output the constructed user portrait in a structured data format, which is convenient for subsequent medical information pushing and other application scenarios. The output data can include user's basic information, feature labels, interest weights, etc.
[0039] S200: Obtain user interest feedback behavior data, identify user current behavior, and output interest feedback data.
[0040] In this embodiment, the user interest feedback behavior data is obtained, the user current behavior is identified, and the interest feedback data is output. The specific process is as follows: S201: Real-time collection of user behavior data and pre-processing of behavior data; S202: Define invalid interest feedback behavior and valid interest feedback behavior, match behavior data, and obtain matching data; S203: According to the matching data, assign a matching identifier to the behavior data; S204: Filter invalid interest feedback data according to the matching identifier, and output valid interest feedback data.
[0041] In the above process, real-time collection of behavior data and pre-processing, data collection: through the front-end page burying of medical related platform, server log recording and other ways, real-time collection of user behavior data. Including user's click operation, browsing time, page jump and other behavior information.
[0042] Data preprocessing: clean and convert the collected raw behavior data, remove duplicate, error and invalid data. Standardize the data, unify the data format and coding, for subsequent analysis and processing. For example, convert different sources of time stamp to standard time format.
[0043] Define behavior types and match data, behavior definition: define the definition of invalid interest feedback behavior and effective interest feedback behavior. Invalid interest feedback behavior includes short high-frequency clicks (more than 3 consecutive clicks on the same information within 1 second), non-target area clicks (clicking on areas unrelated to medical information in the information push interface, such as ad slots, blank spaces, etc.), abnormal time operations (performing a large number of operations at a time period when the user is usually not active, such as 2-5 am, and the operation behavior is inconsistent with daily habits), quick return operations (clicking on information and returning to the previous interface within 2 seconds), etc.; effective interest feedback behavior is consistent with normal operation logic and user interest expression, such as long-time browsing of a certain type of medical information, collecting and sharing operations, etc.
[0044] Data matching: match the pre-processed behavior data with the defined behavior types to obtain matching data. For example, determine whether the user's click behavior is short high-frequency clicks, and whether the browsing behavior is long-time browsing of valid information, etc.
[0045] According to the matching result, each behavior data is given a corresponding matching identifier. For example, for invalid interest feedback behavior, the identifier "0" is given; for effective interest feedback behavior, the identifier "1" is given. Through the identifier, different types of behavior data can be clearly distinguished.
[0046] Data filtering: filter out invalid interest feedback data according to the matching identifier, and only keep valid interest feedback data. This can improve the quality and accuracy of the data, and provide more valuable reference for subsequent medical information push.
[0047] Data output: output the filtered valid interest feedback data in a suitable format, such as JSON format, for subsequent processing and analysis. The output data can include user ID, behavior type, behavior time, behavior object, etc.
[0048] S300: Integrate medical information database, obtain primary push strategy based on user portrait, and dynamically adjust push content according to interest feedback data.
[0049] In this embodiment, the medical information database is integrated, the primary push strategy is obtained based on the user portrait, and the push content is dynamically adjusted according to the interest feedback data. The specific process is as follows: S301: Collect medical information, classify and label the medical information, and establish a medical information database; S302: Receive user portrait data, filter matching information from the medical information database that matches the user, and develop a primary push strategy based on the matching information; S303: Receive valid interest feedback data, filter and optimize the content in the primary push strategy, and update the user portrait; S304: Analyze the similarity between users, predict the user's interest in medical information, and push interesting content.
[0050] In the above process, medical information is collected and a database is established. Information collection: Collect medical information from multiple authoritative channels, including professional medical journals, reports published by authoritative medical research institutions, popular science content on hospital websites, policies and regulations published by government health departments, and health guidelines.
[0051] Classification and labeling: classify and label the collected medical information according to disease type, treatment area, information form (such as articles, videos, and pictures), and add keyword tags to each piece of information for subsequent retrieval and matching.
[0052] Database establishment: Store the classified and labeled medical information in the database to establish a medical information database. The database can use a relational database (such as MySQL) or a non-relational database (such as MongoDB), according to the characteristics and needs of the data.
[0053] Information screening: Receive user profile data and filter matching information from the medical information database according to the characteristics in the user profile. For example, for users interested in cardiovascular disease prevention, filter out relevant information about cardiovascular disease diet, exercise, and drug treatment.
[0054] Strategy development: Develop a primary push strategy based on matching information, determine the content, frequency, and channel of the push. For example, develop a strategy for users interested in cardiovascular disease prevention to push 3 relevant articles per week, and push the channel to medical APP message push and email.
[0055] Optimize push content and update user profile, content optimization: Receive effective interest feedback data and analyze user feedback on the content in the primary push strategy. According to the user's interest preferences and feedback, filter and optimize the push content.
[0056] Profile update: Update the user profile based on effective interest feedback data and content optimization. Adjust the user's interest tags and weights to make the user profile more accurately reflect the user's current interests and needs.
[0057] Predict interest level and push content, similarity analysis: Analyze the similarity between users, calculate the similarity of user profiles, and find user groups with similar interests and needs.
[0058] Interest prediction: predicting the degree of interest of users in medical information based on the similarity between users and historical behavior data. For example, for newly added users, their interest in different types of medical information is predicted based on their similarity to the existing user group.
[0059] Content pushing: pushing medical content that users may be interested in to users according to the interest prediction results. Personalized pushing is adopted to improve the accuracy and effectiveness of pushing.
[0060] Corresponding to the foregoing embodiments of the medical information pushing method based on smart medical big data, the present application also provides embodiments of a smart medical system.
[0061] Figure 5 is a block diagram of a smart medical system according to an exemplary embodiment. Referring to Figure 5 , the system can include a user portrait construction module 401, an interest feedback behavior identification module 402, and an information dynamic pushing module 403; wherein: The user portrait construction module 401 is configured to respectively acquire user multi-modal data, perform feature extraction on the multi-modal data, and construct a user portrait according to the features; The interest feedback behavior identification module 402 is configured to acquire user interest feedback behavior data, identify the current behavior of the user, and output interest feedback data; The information dynamic pushing module 403 is configured to integrate a medical information database, acquire a primary pushing strategy based on the user portrait, and dynamically adjust the pushing content according to the interest feedback data.
[0062] In the present embodiment, the user portrait construction module 401 respectively acquires user multi-modal data, performs feature extraction on the multi-modal data, and constructs a user portrait according to the features; the interest feedback behavior identification module 402 acquires user interest feedback behavior data, identifies the current behavior of the user, and outputs interest feedback data; the information dynamic pushing module 403 integrates a medical information database, acquires a primary pushing strategy based on the user portrait, and dynamically adjusts the pushing content according to the interest feedback data; by formulating a primary pushing strategy based on the user portrait, and dynamically adjusting the pushing content according to the interest feedback data, the matching degree between the pushed information and the user demand is increased, and the information utilization rate is improved.
[0063] As to the system in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, and will not be described in detail here.
[0064] For the system embodiment, since it basically corresponds to the method embodiment, the relevant part can be seen from the part of the method embodiment. The device embodiment described above is only illustrative, wherein the units described as separate components can or can not be physically separated, and the components displayed as units can or can not be physical units, i.e., can be located in one place or distributed to multiple network units. Part or all of the modules can be selected to achieve the purpose of the application according to actual needs. Those skilled in the art can understand and implement without creative labor.
[0065] Correspondingly, the application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the medical information pushing method based on smart medical big data as described above. As Figure 6 As shown in the figure, a hardware structure diagram of a smart medical system provided by an embodiment of the application is in any device with data processing capability, in addition to Figure 6 In addition to the processor, the memory and the network interface shown in the figure, the device in the embodiment is usually provided with other hardware according to the actual function of the device with data processing capability, which will not be described here.
[0066] Correspondingly, the application also provides a computer readable storage medium, which stores computer instructions, and the instructions are executed by a processor to implement the medical information pushing method based on smart medical big data as described above. The computer readable storage medium can be an internal storage unit of any device with data processing capability, such as a hard disk or a memory. The computer readable storage medium can also be an external storage device, such as a plug-in hard disk, a smart media card (SMC), an SD card, a flash card, etc. Further, the computer readable storage medium can include both the internal storage unit of any device with data processing capability and the external storage device. The computer readable storage medium is used to store the computer program and other programs and data required by the device with data processing capability, and can also be used to temporarily store data that has been output or will be output.
[0067] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the application embrace any and all variations of the present application that fall within the scope of the general inventive concept as defined in the claims and that include alterations, modifications and improvements made to the application as disclosed herein.
[0068] It is to be understood that the application is not limited to the precise construction hereinafter described and as shown in the attached drawings, and that various changes in form and detail can be made to the application without departing from the scope thereof.
Claims
1.A medical information pushing method based on smart medical big data, characterized in that, The method comprises the following steps: respectively acquiring user multi-modal data, extracting features from the multi-modal data, and constructing a user portrait according to the features; acquire user interest feedback behavior data, identify user current behavior, and output interest feedback data; Integrate the medical information database, obtain the primary push strategy based on the user portrait, and dynamically adjust the push content according to the interest feedback data. 2.The medical information pushing method based on smart medical big data of claim 1, wherein, In the step of respectively acquiring user multi-modal data, extracting features from the multi-modal data, and constructing a user portrait according to the features: respectively acquire user medical records, health monitoring, online behavior, and regional environment data, and extract and construct features; According to the extracted features, construct the user portrait from multiple dimensions, and output the user portrait data. 3.The medical information pushing method based on smart medical big data of claim 2, wherein, In the step of respectively acquiring user medical records, health monitoring, online behavior, and regional environment data, and extracting and constructing features: acquire user medical record data, and extract disease, treatment, medication, and physiological index features; acquire user health monitoring data, and extract exercise and heart rate features; acquire user online behavior data, and extract attention area, interest preference, and appeal features; acquire user regional environment data, and extract geographical and environmental impact features. 4.The medical information pushing method based on smart medical big data of claim 1, wherein, In the step of acquiring user interest feedback behavior data, identifying user current behavior, and outputting interest feedback data: Collect user behavior data in real time and preprocess the behavior data; Define invalid interest feedback behavior and valid interest feedback behavior, match the behavior data, and obtain matching data. 5.The medical information pushing method based on smart medical big data according to claim 4, wherein, After the step of defining invalid interest feedback behavior and valid interest feedback behavior, matching the behavior data, and obtaining matching data: According to the matching data, assign a matching identifier to the behavior data. 6.The medical information pushing method based on smart medical big data according to claim 5, wherein, After the step of assigning a matching identifier to the behavior data according to the matching data: Filter invalid interest feedback data according to the matching identifier, and output valid interest feedback data. 7.The medical information pushing method based on smart medical big data of claim 1, wherein, In the step of integrating the medical information database, obtaining the primary push strategy based on the user portrait, and dynamically adjusting the push content according to the interest feedback data: Collect medical information, classify and label the medical information, and establish a medical information database; Receive user portrait data, filter matching information matching the user from the medical information database, and develop a primary push strategy according to the matching information. 8.The medical information pushing method based on smart medical big data of claim 7, wherein, After the step of receiving user portrait data, filtering matching information matching the user from the medical information database, and developing a primary push strategy according to the matching information: Receive valid interest feedback data, filter and optimize the content in the primary push strategy, and update the user portrait. 9.The medical information pushing method based on smart medical big data of claim 8, wherein, After the step of receiving valid interest feedback data, filtering and optimizing the content in the primary push strategy, and updating the user portrait: Analyze the similarity between users, predict the interest degree of users to medical information, and push interesting content. 10.A smart medical system applied to the medical information pushing method based on smart medical big data according to claim 1, characterized in that, It comprises a user portrait construction module, an interest feedback behavior identification module, and an information dynamic push module; wherein: The user portrait construction module is used to respectively acquire user multi-modal data, extract features from the multi-modal data, and construct a user portrait according to the features; The interest feedback behavior recognition module is configured to acquire user interest feedback behavior data, recognize the current behavior of the user, and output interest feedback data. The information dynamic pushing module is configured to integrate a medical information database, acquire a primary pushing strategy based on a user portrait, and dynamically adjust the pushing content according to the interest feedback data.