User health data processing method based on terminal

Abstract

The invention provides a user health data processing method based on a terminal. The method comprises the following steps: acquiring health associated information data of a user; preprocessing the health associated information data to obtain health feeling type data; performing primary processing on the health feeling type data, and performing secondary processing on a primary processing result based on preset syndrome type data and a preset calculation model to obtain syndrome type pointing data; and carrying out secondary processing on the syndrome type pointing data, and outputting a processing result to a specified terminal. By means of the design, the problems that in the prior art, associated data collection and automatic judgment and screening between subjective feelings of users and traditional Chinese medicine syndromes cannot be well processed, and consequently the comprehensiveness and accuracy of judgment results are poor are solved.

Description

Technical Field

[0001] This invention relates to the field of human health data processing technology, and in particular to a terminal-based method for processing user health data. Background Technology

[0002] With an aging population and increased health awareness, users' demand for accurate assessments of their health status is growing. Traditional health data processing methods often rely on single-dimensional data (such as physical examination indicators and questionnaire scores), making it difficult to comprehensively reflect the correlation between users' subjective feelings (such as fatigue, insomnia, and shortness of breath) and traditional Chinese medicine syndromes (such as Qi deficiency, Yin deficiency, and Yang deficiency). Traditional methods are inefficient, prone to bias in comprehensive judgments, have low accuracy, and lack comprehensiveness. To address this issue, some institutions have improved traditional data processing methods.

[0003] For example, the prior art with publication number CN110781216A discloses a method for mining association rules of traditional Chinese medicine symptoms. It collects symptom data of a target disease from a medical information management backend; according to the input model parameters, it performs association rule analysis on the collected symptom data through a preset association rule algorithm to obtain the association rules of the symptom data; it determines whether the obtained association rules of the symptom data meet the conditions corresponding to the input model parameters; if not, it adjusts the model parameters and performs association rule analysis again according to the adjusted model parameters, thereby obtaining the symptom combinations that usually accompany the target disease.

[0004] However, this existing technology still has shortcomings. Although it has solved some of the problems of health data processing and efficiency, it still has not solved the problem of data collection and automated judgment and screening that correlates users' subjective feelings with TCM syndrome types, and cannot effectively improve the comprehensiveness and accuracy of the overall judgment results. Summary of the Invention

[0005] Therefore, it is necessary to provide a terminal-based user health data processing method to address the shortcomings of existing technologies in handling the correlation between users' subjective feelings and TCM syndrome types, which leads to deficiencies in the comprehensiveness and accuracy of the judgment results.

[0006] This invention provides a terminal-based user health data processing method, which includes:

[0007] Obtain users' health-related information data;

[0008] The health-related information data is preprocessed to obtain health perception type data;

[0009] The health perception type data is subjected to primary processing, and the primary processing results are further processed based on preset certificate type data and preset calculation model to obtain certificate type pointing data.

[0010] The certificate type pointing data is subjected to secondary processing, and the processing result is output to the designated terminal;

[0011] The preset certificate type is configured to be associated with the health perception type data.

[0012] In the above scheme, the number of feeling types included in the health feeling type data is configured as M, and the number of preset certificate types included in the preset certificate type data is configured as N.

[0013] The method for performing primary processing on the health perception type data, and then performing secondary processing on the primary processing results based on preset syndrome data and a preset calculation model to obtain syndrome-indicating data, includes:

[0014] Each of the M types of sensation is judged to see if it meets the preset standard conditions in order to obtain the screening results;

[0015] According to preset standard rules, the filtering results are associated and configured with N preset certificate types to obtain configuration results;

[0016] Based on the preset calculation model, the configuration results are calculated and statistically analyzed accordingly, and the certificate type pointing data is output.

[0017] In the above scheme, the method of determining whether each of the M types of sensations meets the preset standard conditions to obtain the screening results includes:

[0018] Values ​​are assigned to each of the M types of sensations based on preset rules;

[0019] If the value assigned to one of the described sensation types meets the standard conditions, then the described sensation type is retained;

[0020] If the value assigned to one of the described sensation types does not meet the standard conditions, then that sensation type is deleted.

[0021] In the above scheme, the standard rules include at least:

[0022] Each of the sensation types in the filtering results is configured to correspond to one of four distinct values ​​among the N preset types.

[0023] In the above scheme, the method for secondary processing of the certificate type pointing data includes:

[0024] Sort the data pointing to the certificate type by size and / or calculate the difference;

[0025] Based on the preset screening criteria and the above sorting calculation results, the expected number of the preset certificate types are selected.

[0026] In the above scheme, the method for obtaining the user's health-related information data includes:

[0027] Provides an interface for user information input;

[0028] The user's initial information data is obtained through the information input interface;

[0029] The primary information data is preprocessed to obtain the health-related information data;

[0030] The information input interface is configured to be associated only with the health-related information data, and the primary information data includes user identity information data.

[0031] The method for preprocessing the primary information data includes:

[0032] The user identity information data is parsed from the primary information data;

[0033] Generate a unique target tag that matches the user identity information data;

[0034] The unique target marker is associated and bound with the primary information data.

[0035] In the above scheme, the method for preprocessing the primary information data further includes:

[0036] The unique target marker is matched with information data in a preset database to form a target association.

[0037] If a match is successful, the target data that matches the unique target marker in the preset database is retrieved and integrated with the primary information data to form the health association information data;

[0038] If the matching fails, the primary information data will be directly defined as the health-related information data.

[0039] In the above scheme, the method for obtaining the user's health-related information data further includes:

[0040] The target data is output to the user information input interface and pre-filled in a matching manner so that the user can quickly complete the information input and comparison through the user information input interface.

[0041] In the above scheme, the method for preprocessing the health-related information data includes:

[0042] The health-related information data is packaged, integrated, processed, and transmitted to the server.

[0043] The health-related information data stored on the server is parsed and classified to obtain the health feeling type data.

[0044] In the above scheme, the method of outputting the processing result to the designated terminal includes: converting the data processed by the secondary processing into the expected form of the result, and transmitting it to the designated terminal via the network;

[0045] The expected format includes at least one or more of the following: graphics, charts, text replies, and recommendation lists.

[0046] The above technical solution has the following advantages or beneficial effects: In this invention, when a user inputs relevant information through a terminal device, the related data is transmitted to a cloud server, thereby completing the acquisition of the user's health-related information data. Next, in the cloud server, the health-related information data is preprocessed to obtain health perception type data. Then, the health perception type data undergoes primary processing to obtain a primary processing result. This primary processing result is then subjected to secondary processing based on preset syndrome type data and a preset calculation model stored in the database, ultimately yielding syndrome type pointing data. Next, the syndrome type pointing data undergoes secondary processing. Finally, the server outputs the secondary processing result to a designated terminal, such as a user device. This solves the problem that existing technologies cannot effectively handle the collection and automated judgment and screening of data related to the user's subjective feelings and TCM syndrome types, resulting in deficiencies in the comprehensiveness and accuracy of the judgment results. Attached Figure Description

[0047] Figure 1 This is a schematic diagram of the process steps of the terminal-based user health data processing method of the present invention during execution in one embodiment;

[0048] Figure 2 This is a schematic diagram of the process steps of the terminal-based user health data processing method of the present invention when executed in another embodiment;

[0049] Figure 3 This is a schematic diagram of the process steps of the terminal-based user health data processing method of the present invention when executed in another embodiment;

[0050] Figure 4 This is a schematic diagram of the process steps of the terminal-based user health data processing method of the present invention when executed in another embodiment;

[0051] Figure 5 This is a schematic diagram of the process steps of the terminal-based user health data processing method of the present invention when executed in another embodiment;

[0052] Figure 6 This is a schematic diagram of the process steps of the terminal-based user health data processing method of the present invention when executed in another embodiment;

[0053] Figure 7 This is a schematic diagram of the process steps of the terminal-based user health data processing method of the present invention when executed in another embodiment;

[0054] Figure 8 This is a schematic diagram of the process steps when the terminal-based user health data processing method of the present invention is executed in another embodiment. Detailed Implementation

[0055] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the specific details described below are only a part of the embodiments of the present invention, and the present invention can be implemented in many other embodiments different from those described herein. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the present invention.

[0056] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly attached to the other element or there may be an intervening element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or there may be an intervening element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible implementation.

[0057] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0058] This invention provides a terminal-based method for processing user health data, such as... Figure 1 As shown, its execution includes at least the following steps:

[0059] Step S100: Obtain the user's health-related information data;

[0060] Step S200: Preprocess the health-related information data to obtain health perception type data;

[0061] Step S300: Perform primary processing on the health perception type data, and perform secondary processing on the primary processing results based on preset certificate type data and preset calculation model to obtain certificate type pointing data;

[0062] Step S400: Perform secondary processing on the certificate type pointing data and output the processing result to the designated terminal;

[0063] The preset certificate type is configured to be associated with the health perception type data.

[0064] In a specific embodiment, after a user inputs relevant information through a terminal device, the associated data is transmitted to a cloud server, thereby acquiring the user's health-related information data. Next, on the cloud server, the health-related information data is preprocessed to obtain health perception type data. Then, the health perception type data undergoes primary processing to obtain a primary processing result. This primary processing result is then subjected to secondary processing based on preset certificate type data and a preset calculation model stored in the database, ultimately yielding certificate type pointing data. Next, the certificate type pointing data undergoes secondary processing. Finally, the server outputs the secondary processing result to the designated terminal.

[0065] The aforementioned user health-related information data may include identity information, marital status, education level, residential status, dietary habits, frequency of exercise, exercise methods, smoking and drinking history, medical history and past medical history, and medication information, as well as data such as height, weight, waist circumference, hip circumference, left and right hand grip strength, and 4-meter walking speed.

[0066] The health experience data mentioned above includes the following 33 TCM symptoms: 1. Dizziness; 2. Forgetfulness; 3. Tinnitus or hearing loss; 4. Dry or blurry eyes; 5. Dry mouth and throat; 6. Flushed cheeks; 7. Pale complexion; 8. Pale lips; 9. Palpitations; 10. Chest tightness or dull chest pain; 11. Shortness of breath or wheezing; 12. Frequent cough; 13. Abdominal distension or abdominal pain; 14. Lower back and knee weakness or limb pain; 15. Slowed or clumsy movements; 16. Weak legs making it difficult to stand for long periods or prone to falls; 17. Muscle relaxation or weakness. 18. Lifting heavy objects; 19. Hand or head tremors or leg cramps; 20. Numbness in the limbs; 21. Emaciation; 22. Cold hands and feet or feeling cold and afraid of wind; 23. Hot palms and soles or hot flashes; 24. Night sweats; 25. Excessive sweating during the day, especially with exertion; 26. Frequent colds; 27. Weakness and fatigue; 28. Lethargy; 29. ​​Irritability; 30. Insomnia, vivid dreams or easy awakening; 31. Sleepiness after sitting for a long time during the day; 32. Decreased appetite or eating less; 33. Frequent urination at night or difficulty controlling urination; 44. Loose stools or difficulty defecating. (Some or more of these symptoms may also be present.)

[0067] The preset syndrome types included in the above preset syndrome type data can include the following 13 syndrome types: heart qi deficiency, heart yang deficiency, heart blood deficiency, heart yin deficiency, lung qi deficiency, lung yin deficiency, spleen qi deficiency, spleen yang deficiency, liver blood deficiency, liver yin deficiency, kidney essence deficiency, kidney yin deficiency, and kidney yang deficiency.

[0068] The designated terminal mentioned above can be a user's terminal device to inform the user of the inspection and evaluation results, or it can be a lower-level information processing terminal device to trigger subsequent business logic.

[0069] To facilitate understanding and explanation, the above steps S100-S400 will be further disassembled and explained below with reference to the embodiments.

[0070] In one scheme, the number of feeling types included in the health feeling type data is configured as M, and the number of preset certificate types included in the preset certificate type data is configured as N;

[0071] Among them, such as Figure 2 As shown, step S300 includes:

[0072] Step S310: Determine whether each of the M types of sensation meets the preset standard conditions to obtain the screening results;

[0073] Step S320: According to preset standard rules, associate and configure the screening results with N preset certificate types to obtain configuration results;

[0074] Step S330 performs corresponding calculations and statistics on the configuration results based on the preset calculation model, and outputs the certificate type pointing data.

[0075] Among them, such as Figure 3 As shown, step S310 includes:

[0076] Step S311: Assign values ​​to each of the M types of sensations based on preset rules;

[0077] Step S312: If the value assigned to one of the sensation types satisfies the standard condition, then the sensation type is retained;

[0078] Step S313: If the value assigned to one of the sensation types does not meet the standard conditions, then delete the sensation type.

[0079] The preset rules include:

[0080] The sensation type is defined as having two states: "present" and "absent".

[0081] When the sensation type is associated with the "present" state, the sensation type is configured to correspond to a certain value, such as "1".

[0082] When the sensation type is associated with the "none" state, the sensation type is configured to correspond to another different value, such as "0".

[0083] In step S320 above, the standard rules may include at least:

[0084] Each of the sensation types in the screening results is defined as having one of four property types: "no corresponding symptom", "primary symptom", "secondary symptom" and "concurrent symptom". These four property types are configured to correspond to four different values.

[0085] Each of the sensation types in the filtering results is configured to correspond to one of four distinct values ​​among the N preset types.

[0086] In one scheme, such as Figure 4 As shown, the step of performing secondary processing on the certificate type pointing data in step S400 includes:

[0087] Step S410: Sort the certificate type pointing data by size and / or calculate the difference;

[0088] Step S420: Based on the preset screening criteria and the above sorting calculation results, select the expected number of the preset certificate types.

[0089] In one scheme, such as Figure 5 As shown, step S100 includes:

[0090] Step S110: Provide a user information input interface;

[0091] Step S120: Obtain the user's initial information data through the information input interface;

[0092] Step S130: Preprocess the primary information data to obtain the health-related information data;

[0093] The information input interface is configured to be associated only with the health-related information data, and the primary information data includes user identity information data.

[0094] Among them, such as Figure 6 As shown, step S200, which involves preprocessing the primary information data, includes:

[0095] Step S210: Parse the user identity information data from the primary information data;

[0096] Step S220: Generate a unique target tag that matches the user identity information data;

[0097] Step S230: Associate and bind the unique target marker with the primary information data.

[0098] In addition, such as Figure 7 As shown, the step of preprocessing the primary information data in step S200 may further include:

[0099] Step S240: Perform target association matching between the unique target marker and the information data in the preset database;

[0100] Step S250: If the match is successful, retrieve the target data that matches the unique target mark from the preset database and integrate it with the primary information data to form the health association information data;

[0101] Step S260: If the matching fails, the primary information data is directly defined as the health-related information data.

[0102] In one scheme, step S100 may further include:

[0103] The target data is output to the user information input interface and pre-filled in a matching manner so that the user can quickly complete the information input and comparison through the user information input interface.

[0104] In one scheme, such as Figure 8 As shown, step S200, which involves preprocessing the primary information data, includes:

[0105] Step S270: Package and integrate the health-related information data, and transmit it to the server.

[0106] Step S280: The health-related information data stored in the server is parsed and classified to obtain the health feeling type data.

[0107] In one scheme, such as Figure 4 As shown, step S400, which involves outputting the processing result to a specified terminal, includes:

[0108] Step S430: Convert the data processed in the secondary stage into the desired form and transmit it to the designated terminal via the network.

[0109] The expected format includes at least one or more of the following: graphics, charts, text replies, and recommendation lists.

[0110] To facilitate understanding and explanation, the above implementation steps will be illustrated and explained in more detail below with specific examples.

[0111] For step S100, which is to obtain the user's health-related information data.

[0112] Specifically, in this embodiment, the present invention can provide users with a standardized information input interface through multimodal terminals, including but not limited to smartphone apps, WeChat mini-programs, community medical self-service terminals, and home health monitoring devices, aiming to collect multi-dimensional related information covering the user's health status.

[0113] The data collection process specifically includes the following four levels:

[0114] First, the user identity information layer. Basic user identity information (such as name, age, gender, ID number, and contact information) is obtained through real-name authentication or anonymized identifiers (such as ID card number, mobile phone number, and community health record number). This information is not only a unique identifier for user data but also the foundation for subsequent association with historical health records and personalized analysis. For example, elderly people in the community can quickly log in to the system by swiping their ID card or entering their mobile phone number, and the system automatically links their past physical examination records or traditional Chinese medicine consultation history.

[0115] Second, the subjective health perception layer. This is one of the core data sources of this invention, which collects users' current subjective discomfort symptoms through a structured questionnaire. Taking the differentiation of the five internal organs deficiency syndrome in the elderly as an example, the questionnaire contains 33 standardized symptoms (such as dizziness, forgetfulness, palpitations, shortness of breath, and soreness of the waist and knees). Each symptom is presented as a binary option of "yes (1) / no (0)", ensuring the simplicity of user input and machine readability. The selection of symptoms can refer to the national standard of TCM clinical diagnosis and treatment terminology (GB / T 16751.2-2021), which mainly covers the typical manifestations of the five internal organs (heart, liver, spleen, lung, and kidney) deficiency syndrome (such as heart qi deficiency corresponding to "palpitations and shortness of breath", and kidney yang deficiency corresponding to "soreness of the waist and knees and aversion to cold"), while avoiding indicators that are difficult to identify digitally, such as tongue appearance and pulse appearance.

[0116] Third, the lifestyle and background information layer. This includes the user's marital status, education level, living environment, dietary habits, frequency and type of daily exercise, smoking and drinking history, past medical history, and current medication status. This type of information is used to construct the social and environmental context of the user's health status, assisting in the accuracy of syndrome calculation.

[0117] Fourth, the physical examination data layer. In community healthcare terminals or professional medical institutions, the system supports the collection of objective physiological indicators via IoT devices, such as height, weight (for calculating BMI), waist circumference (to assess abdominal fat accumulation), hip circumference (to help determine the risk of metabolic syndrome), left and right hand grip strength (reflecting muscle strength and aging), and 4-meter walking speed (to assess lower limb function and mobility). Combining this data with subjective symptoms can further enhance the multidimensionality of the diagnostic model (for example, when decreased grip strength and "muscle relaxation" symptoms coexist, it is more likely to be diagnosed as "spleen qi deficiency").

[0118] For step S200, the health-related information data is preprocessed to obtain health perception type data.

[0119] In specific embodiments, preprocessing is a key step connecting raw data with core computing. Its goal is to transform multi-source heterogeneous primary information data into structured "health feeling type data", that is, the digital expression of users' subjective discomfort symptoms.

[0120] Specifically, step S200 can be divided into three progressive sub-steps:

[0121] The first step is identity resolution and uniqueness binding.

[0122] The system first parses user identity information from primary data (e.g., recognizing ID card numbers via OCR and validating phone number formats using regular expressions), and then generates a unique target tag (such as a UUID or anonymized identity identifier) ​​based on an encryption algorithm (e.g., the SHA-256 hash function). This tag is strongly associated with the primary data (including identity information, symptom questionnaires, lifestyle habits, etc.) to ensure traceability and continuous analysis of data from multiple user interactions (e.g., periodic retesting). For example, when user A first uses the app and enters their ID card number, the system generates a unique tag, and all subsequent data associated with this tag is included in the same health record.

[0123] Part Two: Database Matching and Information Integration.

[0124] The unique target tag will be used to query a preset database (such as a community elderly health record database, a traditional Chinese medicine syndrome knowledge base, or a regional medical sharing platform) to match the user's historical health information. The database may contain the user's past symptom records (such as the "fatigue" symptom selection from six months ago), traditional Chinese medicine diagnosis results (such as historical "spleen qi deficiency" diagnosis), and physical examination indicators (such as hemoglobin levels and blood pressure). If a match is successful (e.g., the tag exists in the database and is within its validity period), the system will retrieve the matched target data (e.g., the historically selected "lower back and knee pain = 1") and integrate it with the current primary information data to form more comprehensive health-related information data (e.g., the newly added "frequent urination at night = 1," combined with the historical "lower back and knee pain = 1," more strongly suggests a "kidney yang deficiency" diagnosis). If a match fails (e.g., a new user or the tag is not registered in the database), the current primary information data will be directly used as health-related information data for subsequent processing.

[0125] The third step is user-friendly population and data optimization.

[0126] To reduce the burden of repetitive input for users, the system outputs the matched target data to the information input interface to pre-fill the user's current input.

[0127] For example, if the database records user B's age as "68 years old" and marital status as "married," then the "Age" field in the current questionnaire will automatically display "68 years old" (which the user can modify), and the "Marital Status" dropdown menu will default to "Married." Furthermore, the system cleans and standardizes the initial data: removing invalid characters (such as spaces and special symbols), standardizing units (such as height to "centimeters" and weight to "kilograms"), and correcting obvious logical errors (such as displaying a prompt when the age is entered as "150 years old"). Finally, the cleaned and integrated data is labeled as "health-related information data," serving as the core input for subsequent preprocessing.

[0128] Furthermore, health-related information data (focusing on symptom-related binary status data, such as "dizziness = 1, no chest tightness = 0") will be packaged and uploaded to the cloud server via a secure transmission protocol.

[0129] Subsequently, the server-side uses a parsing engine to classify and process the data as follows:

[0130] First, the user's subjective feedback of discomfort symptoms (i.e., health feeling type data, such as the checked "yes" symptoms) is separated, and redundant information without diagnostic significance is removed (such as unchecked symptoms are regarded as "no" by default); then the symptom data is stored in a structured manner to provide standardized input for subsequent syndrome correlation calculation.

[0131] For step S300, the health feeling type data is initially processed, and then a second processing is performed based on the preset certificate type data and the preset calculation model to obtain certificate type pointing data.

[0132] In specific embodiments, this step is the core calculation link of the present invention. Through a three-level process of "screening, association, and calculation", the user's subjective symptoms are transformed into quantifiable syndrome-indicating data, namely the probability score of each TCM syndrome.

[0133] The specific implementation steps include:

[0134] The first step is preliminary processing. Specifically, this involves filtering and standardizing the data on health perception types.

[0135] Specifically, in this embodiment, the health perception type data includes M types of perception (taking the elderly five-organ deficiency syndrome model as an example, M=33, that is, the symptoms that the user selected as "present" out of 33 symptoms), and the preset syndrome data includes N types of syndromes (N=13, that is, 13 types of five-organ deficiency syndromes such as heart qi deficiency, heart yang deficiency, and heart blood deficiency). First, the M types of perception are screened for effectiveness to ensure that only symptoms related to the syndrome diagnosis are retained.

[0136] The specific implementation method is as follows:

[0137] First, assign values ​​and determine standard conditions. Assign values ​​to each sensation type based on preset rules (e.g., symptom "present = 1, absent = 0"), and determine whether to retain them based on standard conditions. For example, only retain symptoms explicitly selected by the user (status = 1), or exclude obviously contradictory data (e.g., simultaneously selecting "no palpitations" and "palpitations").

[0138] More specific screening rules may include: the clinical relevance of symptoms (e.g., although "pale tongue" is a common symptom in Traditional Chinese Medicine, it is excluded by default due to the difficulty of digital recognition) and the minimum threshold for syndrome differentiation diagnosis (e.g., at least one primary symptom must be present). For example, if a symptom is selected by the user (value 1) and meets the syndrome differentiation diagnosis rules (e.g., it belongs to the primary, secondary, or concurrent symptom of any of the 13 syndrome types), then the symptom type is retained; otherwise, it is deleted.

[0139] Then, standard rules are applied. Each sensation type in the screening results corresponds to one of four distinct values ​​among the N preset syndrome types (e.g., 8 points for primary symptom, 3 points for secondary symptom, 1 point for concurrent symptom, and 0 points for no corresponding symptom). This rule ensures that the weight differences of different symptoms in syndrome type calculation are clearly distinguished.

[0140] The primary symptom (such as palpitations due to deficiency of heart qi) contributes the most to the syndrome score (8 points), followed by the secondary symptom (such as chest tightness) (3 points), and the secondary symptom (such as excessive sweating during the day) contributes the least (1 point). The standard rules can be based on GB / T 16751.2-2021[S].

[0141] The second step is to configure the association. Specifically, this involves establishing a mapping relationship between symptoms and syndrome types.

[0142] In a specific embodiment, the filtered sensation types are associated with N preset syndrome types according to preset standard rules, forming a "symptom-syndrome-weight" mapping table. For example, if a user selects "palpitation" (status = 1), the system identifies it as a primary symptom (weight 8 points) in syndromes such as heart qi deficiency, heart yang deficiency, and heart blood deficiency. The mapping table records: "palpitation corresponds to heart qi deficiency (8 points), heart yang deficiency (8 points), heart blood deficiency (8 points), and heart yin deficiency (8 points)". If "chest tightness" (status = 1) is selected, since it is a secondary symptom of heart qi deficiency (weight 3 points), the table records: "chest tightness corresponds to heart qi deficiency (3 points), heart yang deficiency (3 points), and heart blood deficiency (3 points)..." etc. The configuration process iterates through all filtered sensation types, matching each one to its role in each syndrome type (primary symptom / secondary symptom / concurrent symptom / no corresponding symptom), and assigning corresponding weights, ultimately generating an association matrix containing M×N records.

[0143] The third step involves secondary processing. Specifically, this involves quantifying the score rate of the certificate type.

[0144] The core calculations are performed on the configuration results based on a preset calculation model, with the goal of generating the score rate for each certificate type. The calculation process is as follows:

[0145] First, symptom scores are generated. Each symptom is automatically scored based on its assigned value in each syndrome type (e.g., primary symptom 8 points, secondary symptom 3 points, concurrent symptom 1 point, no corresponding symptom 0 points). For example, if the user selects "palpitation" (primary symptom of heart qi deficiency, 8 points; primary symptom of heart yang deficiency, 8 points; primary symptom of heart blood deficiency, 8 points), the scores for heart qi deficiency, heart yang deficiency, and heart blood deficiency syndrome types will each increase by 8 points; if "chest tightness" (secondary symptom of heart qi deficiency, 3 points) is also selected, the score for heart qi deficiency syndrome type will increase by an additional 3 points.

[0146] Then, the syndrome score rate is calculated: the total score of all related symptoms of each syndrome (as the numerator) is divided by the total score of all symptoms (main symptom + secondary symptom + concurrent symptom) of that syndrome (as the denominator) to obtain the syndrome score rate, which ranges from 0% to 100%.

[0147] For example, the total score for the syndrome of heart qi deficiency is calculated as follows:

[0148] 3 primary symptoms × 8 points (palpitations, shortness of breath, fatigue) + 4 secondary symptoms × 3 points (chest tightness, cold hands and feet, etc.) + 8 secondary symptoms × 1 point (forgetfulness, pale complexion, etc.) = 24 + 12 + 8 = 44 points; If the total score of the symptoms selected by the user is 35 points (e.g., 16 points for primary symptoms "palpitations and shortness of breath", 3 points for secondary symptoms "chest tightness", 1 point for secondary symptoms "forgetfulness", etc.), then the score rate of heart qi deficiency syndrome is 35 / 44≈79.5%.

[0149] By traversing all N syndrome types, the system outputs the score rate of each syndrome type (e.g., 79.5% for heart qi deficiency, 62.3% for heart blood deficiency, 48.1% for kidney yang deficiency, etc.) as syndrome type indicator data.

[0150] For step S400, which involves secondary processing of the certificate type pointer data and outputting it to the designated terminal, the processing steps are roughly as follows:

[0151] The first step is to perform secondary processing. Specifically, this involves screening and sorting the key evidence types.

[0152] Specifically, to avoid overwhelming users with too many certificate types, the system filters and sorts the certificate type scores, according to the following rules:

[0153] First, sort the syndromes. Specifically, sort all syndromes from highest to lowest score rate, such as Qi deficiency of the heart (80%) > Blood deficiency of the heart (75%) > Yin deficiency of the kidneys (52%) > ... etc.

[0154] Then, a standard screening process is performed. Specifically, the top two syndrome types with the highest score rates are prioritized (e.g., heart qi deficiency, heart blood deficiency). If a third syndrome type exists and its score rate is higher than 50% (e.g., kidney yin deficiency 52% > 50%), or lower than 50% but less than 5% different from the second syndrome type's score rate (e.g., kidney yang deficiency 48% vs. heart blood deficiency 75%, a difference of 27%, which does not meet the requirement; however, if the third syndrome type is spleen yang deficiency 49% and the second syndrome type is spleen yin deficiency 51%, a difference of 2%, then it may be included), then this third syndrome type is also included. The final output will contain a maximum of 3 syndrome types.

[0155] The second step is to output to the terminal. Specifically, this involves multimodal presentation and user interaction.

[0156] Specifically, the results of secondary processing are converted into a terminal-friendly format to improve user readability and application value.

[0157] Output formats include, but are not limited to, the following:

[0158] Visual charts: such as bar charts of syndrome type score rates, used to visually compare the scores of each syndrome type; radar charts, used to show the coverage of related symptoms for each syndrome type; and pie charts, used to show the proportion of major syndrome types.

[0159] Text information: such as "Your diagnosis results: Heart Qi deficiency (score rate 80%, main symptoms: palpitations, shortness of breath), Heart Blood deficiency (score rate 75%, main symptoms: insomnia, pale complexion), Kidney Yin deficiency (score rate 52%, main symptoms: frequent urination at night, hot palms and soles)".

[0160] Recommended list: such as recommended interventions: replenish heart qi; nourish blood and calm the mind; if there is significant soreness and weakness in the lower back and knees, kidney-tonifying dietary therapy can be added.

[0161] Finally, the data is transmitted to the user terminal (such as a mobile app, community medical screen, or home health terminal) via network (such as Wi-Fi, 4G / 5G), Bluetooth, or local transmission.

[0162] To facilitate understanding and explanation, we will use WeChat Mini Programs as an example to illustrate the concept.

[0163] This embodiment takes a WeChat mini-program as an example to explain in detail the implementation process of the present invention in a real-world scenario, covering user operation flow, data processing logic, calculation details and output presentation.

[0164] Step 1: Collection of Health-Related Information

[0165] When users open the mini-program, they are first taken to the "Identity Information Filling" page. This page adopts a step-by-step guided design. The first step requires users to enter required fields (name, age, gender, contact information), and the second step is for optional fields (marital status, education level, and residence status).

[0166] The user will then be directed to the "Physical Examination Data" page, where they can choose whether to synchronize data via a community healthcare terminal (e.g., height and weight already measured) or to enter it manually. If the user chooses to enter it manually, the system will calculate the BMI index in real time and display the reference range.

[0167] The core component is the "33-item symptom questionnaire" page. Symptoms are displayed categorized by the five internal organs (e.g., "Heart-related: palpitations, chest tightness, shortness of breath..."), with a clear "Yes / No" radio button below each symptom. After the user selects symptoms, the system counts the number of selected symptoms in real time (e.g., "8 symptoms selected") to avoid omissions. Additionally, a "History" entry is provided at the bottom of the page (if the user has previously completed the questionnaire), allowing for quick loading and modification of previous results.

[0168] Finally, users supplement their "lifestyle and background" information: exercise frequency, dietary habits, smoking and drinking history, past medical history, and current medications.

[0169] Step 2: Data Preprocessing

[0170] The mini-program frontend transmits all user-inputted data (including identity information, symptom questionnaires, lifestyle habits, etc.) to the cloud server via API. The server-side preprocessing process is as follows:

[0171] The first step is identity resolution and uniqueness binding. The user-input ID number is parsed, and its format validity is validated using regular expressions. Then, a unique target identifier is generated using the SHA-256 algorithm. If the user selects anonymous mode (without providing an ID number), a random UUID is generated as a temporary identifier.

[0172] The second step is database matching and information integration. The unique target tag is queried in the community's elderly health record database. If a match is found (e.g., a record from six months ago corresponding to the UID was found where "lower back and knee pain = 1" and "fatigue = 1"), then the historical symptom data is retrieved and integrated with the current questionnaire data (if "palpitation = 1" is added, then the merged data will be "palpitation = 1, lower back and knee pain = 1, fatigue = 1"). If a match fails (e.g., for a new user), then the current primary information data is used directly.

[0173] The third step is user-friendly data entry and cleaning. The matched historical data is output to the mini-program frontend to pre-fill the user's current input (e.g., automatically displaying the last entered age "68 years old" and past symptoms "lower back and knee pain"). Simultaneously, the system cleans the input data, validates its logic, and standardizes its format (e.g., the "frequent cough" option is standardized to "yes / no" instead of "occasionally / frequently / always"). Finally, the cleaned data is labeled as health-related information, with a focus on extracting symptom-related binary states (e.g., "palpitations = 1, no chest tightness = 0").

[0174] The third step is the correlation calculation of syndrome types. The cloud server loads a pre-stored data model, which includes assignment rules for 13 syndrome types and 33 symptoms (e.g., primary symptom 8 points, secondary symptom 3 points, concurrent symptom 1 point). The calculation process consists of the following sub-steps:

[0175] First, symptom score generation. Each symptom selected by the user (status = 1) is iterated through, and its corresponding score is accumulated based on its role in each syndrome type (primary symptom / secondary symptom / concurrent symptom). For example, user Aunt Zhang selected "palpitation (primary symptom, 8 points)," "shortness of breath (primary symptom, 8 points)," "fatigue (concurrent symptom, 1 point)," "lower back and knee pain (concurrent symptom, 1 point)," and "frequent urination at night (concurrent symptom, 1 point)."

[0176] Heart Qi Deficiency Syndrome: Palpitation (main symptom, 8 points), shortness of breath (main symptom, 8 points), fatigue (accompanying symptom, 1 point), examination score = 8 + 8 + 1 = 17 points;

[0177] Heart Yang Deficiency Syndrome: Palpitation (main symptom, 8 points), shortness of breath (main symptom, 8 points), examination score = 8 + 8 = 16 points;

[0178] Kidney Yang Deficiency Syndrome: Soreness and weakness of the lower back and knees (accompanying symptom, 1 point), frequent urination at night (accompanying symptom, 1 point), examination score = 1 + 1 = 2 points;

[0179] The calculation for other certificate types follows the same principle.

[0180] Second, the total score for each syndrome type is calculated. According to the model rules, the total score for each syndrome type is a fixed value. For example, the total score for the Heart Qi Deficiency syndrome = 3 main symptoms × 8 (24 points) + 4 secondary symptoms × 3 (12 points) + 8 concurrent symptoms × 1 (8 points) = 44 points; the total score for the Kidney Yang Deficiency syndrome = 3 main symptoms × 8 (24 points) + 4 secondary symptoms × 3 (12 points) + 9 concurrent symptoms × 1 (9 points) = 45 points.

[0181] Third, the score rate for each syndrome type is calculated. The total score of the symptoms for each syndrome type is divided by the total assigned score to obtain the score rate. For example, the score for the syndrome of heart qi deficiency is 17 points, and the total assigned score is 44 points. The score rate is approximately 17 / 44 ≈ 38.6% (if the user selects more symptoms related to heart qi deficiency, such as "chest tightness (secondary symptom, 3 points)" and "cold hands and feet (secondary symptom, 3 points)," the score may increase to 23 points, and the score rate will be approximately 23 / 44 ≈ 52.3%).

[0182] Finally, after a complete calculation (assuming the user selected the 3 primary symptoms and 2 secondary symptoms of heart qi deficiency), the score rate of heart qi deficiency may reach 70%-80%, the score rate of heart blood deficiency is 60%-70%, and the score rate of kidney yin deficiency is 50%-60%. The final output is the first 3 syndrome types (such as heart qi deficiency 80%, heart blood deficiency 75%, and kidney yin deficiency 52%).

[0183] Step 4: Result Output. The server returns the three highest-scoring certificate types to the mini-program frontend via API, and the frontend converts them into one or more of the following formats:

[0184] Visual charts, such as bar charts displayed at the top of the "Diagnosis Results" page, with the horizontal axis representing the syndrome name (heart qi deficiency, heart blood deficiency, kidney yin deficiency) and the vertical axis representing the score rate (80%, 75%, 52%), and the bars differentiated by color (e.g., red for heart qi deficiency, blue for heart blood deficiency, and green for kidney yin deficiency), intuitively display the main problems.

[0185] Text information, such as the text below, states: "Your health condition may lean towards heart qi deficiency (score rate 80%): common symptoms include palpitations, shortness of breath, and fatigue; heart blood deficiency (score rate 75%): common symptoms include insomnia and pale complexion; kidney yin deficiency (score rate 52%): common symptoms include frequent urination at night and hot palms and soles."

[0186] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0187] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that those skilled in the art can make various modifications, substitutions, and improvements without departing from the concept of the present invention, and these should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of this invention should be determined by the claims.

Claims

1. A terminal-based user health data processing method, characterized in that, include: Obtain users' health-related information data; The health-related information data is preprocessed to obtain health perception type data; The health perception type data is subjected to primary processing, and the primary processing results are further processed based on preset certificate type data and preset calculation model to obtain certificate type pointing data. The certificate type pointing data is subjected to secondary processing, and the processing result is output to the designated terminal; The preset certificate type is configured to be associated with the health perception type data.

2. The user health data processing method based on a terminal according to claim 1, characterized in that, The number of feeling types included in the health feeling type data is configured as M, and the number of preset certificate types included in the preset certificate type data is configured as N. The method for performing primary processing on the health perception type data, and then performing secondary processing on the primary processing results based on preset syndrome data and a preset calculation model to obtain syndrome-indicating data, includes: Each of the M types of sensation is judged to see if it meets the preset standard conditions in order to obtain the screening results; According to preset standard rules, the filtering results are associated and configured with N preset certificate types to obtain configuration results; Based on the preset calculation model, the configuration results are calculated and statistically analyzed accordingly, and the certificate type pointing data is output.

3. The terminal-based user health data processing method according to claim 2, characterized in that, The method for determining whether each of the M types of sensation meets a preset standard condition to obtain the screening results includes: The M types of sensations are assigned values ​​one by one based on preset rules; If the value assigned to one of the described sensation types meets the standard conditions, then the described sensation type is retained; If the value assigned to one of the described sensation types does not meet the standard conditions, then that sensation type is deleted.

4. The terminal-based user health data processing method according to claim 2, characterized in that, The standard rules include at least the following: Each of the sensation types in the filtering results is configured to correspond to one of four distinct values ​​among the N preset types.

5. The terminal-based user health data processing method according to claims 1-4, characterized in that, The method for secondary processing of the certificate type pointing data includes: Sort the data pointing to the certificate type by size and / or calculate the difference; Based on the preset screening criteria and the above sorting calculation results, the expected number of the preset certificate types are selected.

6. The terminal-based user health data processing method according to any one of claims 1-4, characterized in that, The method for obtaining user health-related information data includes: Provides an interface for user information input; The user's initial information data is obtained through the information input interface; The primary information data is preprocessed to obtain the health-related information data; The information input interface is configured to be associated only with the health-related information data, and the primary information data includes user identity information data. The method for preprocessing the primary information data includes: The user identity information data is parsed from the primary information data; Generate a unique target tag that matches the user identity information data; The unique target marker is associated and bound with the primary information data.

7. The terminal-based user health data processing method according to claim 6, characterized in that, The method for preprocessing the primary information data further includes: The unique target marker is matched with information data in a preset database to form a target association. If a match is successful, the target data that matches the unique target marker in the preset database is retrieved and integrated with the primary information data to form the health association information data; If the matching fails, the primary information data will be directly defined as the health-related information data.

8. The terminal-based user health data processing method according to claim 7, characterized in that, The method for obtaining users' health-related information data further includes: The target data is output to the user information input interface and pre-filled in a matching manner so that the user can quickly complete the information input and comparison through the user information input interface.

9. The terminal-based user health data processing method according to any one of claims 1-4, characterized in that, The method for preprocessing the health-related information data includes: The health-related information data is packaged, integrated, processed, and transmitted to the server. The health-related information data stored on the server is parsed and classified to obtain the health feeling type data.

10. The terminal-based user health data processing method according to any one of claims 1-4, characterized in that, The method for outputting the processing result to a designated terminal includes: converting the data processed by the secondary process into a result in the expected form and transmitting it to the designated terminal via a network; The expected format includes at least one or more of the following: graphics, charts, text replies, and recommendation lists.

Images