Digital mobile medical treatment-based anaphylactic disease inquiry auxiliary system and method

Abstract

The invention relates to the technical field of medical data processing, and discloses an anaphylactic disease inquiry auxiliary system and method based on digital mobile medical treatment, and the system comprises a digital mobile medical treatment module, an environment monitoring module, a prediction module, a correction module, and a risk calculation module. Wherein the digital mobile medical module is used for acquiring an allergy history of a user, user positioning and an allergy case of an area where the user is located; the environment monitoring module is used for collecting the concentration and the environment factor of each allergen in the area where the user is located; the prediction module is used for predicting the concentration of each allergen in the area where the user is located; the correction module is used for correcting the concentration predicted value of each allergen; the risk calculation module is used for performing allergy early warning on the user; by integrating multiple advanced technologies and methods, the accuracy and timeliness of allergy early warning are improved, and the allergy management ability and life quality of the user are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical data processing, and in particular to a digital mobile medical-based allergic disease consultation auxiliary system and method. Background Art

[0002] Allergic diseases include but are not limited to allergic rhinitis, asthma, eczema, etc. Their pathogenesis is complex and is affected by multiple factors such as genetics and environment. The incidence of allergic diseases worldwide has shown an increasing trend year by year, becoming one of the important factors affecting people's quality of life. In recent years, digital mobile healthcare has been widely used in the field of health management due to its convenience, real-time and low cost. The popularity of mobile terminals such as smartphones and wearable devices enables patients to monitor their health status anytime and anywhere, and transmit data to doctors or other medical service providers. In addition, the development of technologies such as cloud computing, big data, and artificial intelligence has also provided strong support for digital mobile healthcare, enabling functions such as remote medical consultation and personalized health advice.

[0003] Although digital mobile medical care has shown great potential in the management of allergic diseases, it still faces many challenges in its actual application. At present, most digital mobile medical applications rely on users to actively input relevant information, such as symptoms, medication status, etc. This method not only increases the burden on users, but also may lead to inaccurate or incomplete data. In addition, environmental factors such as air quality, humidity, temperature, etc. also have a great impact on the occurrence of allergic symptoms, but existing mobile medical applications often ignore the monitoring and analysis of these external factors. The onset of allergic diseases often has a certain regularity and periodicity, but there are large differences between individuals. Most of the existing early warning systems are based on group statistical data, lack customized early warning mechanisms based on individual characteristics, and cannot promptly and effectively remind patients to take preventive measures.

[0004] For example, the patent application with publication number CN106815477A discloses a method, system and terminal device for allergy warning. The method includes: collecting patient allergy information; calling allergy factor data to compare with patient allergy information to obtain a comparison result; judging the content of allergy warning according to the comparison result. By recording the patient's onset time, location, allergy symptoms, allergens and other information, summarizing the patient's onset causes and patterns, and using technical assistance, reminding and warning patients from multiple dimensions of time, location, and allergen type, the patient's allergy incidence rate is reduced and the patient's quality of life is improved.

[0005] For example, the patent application with publication number CN106384008A discloses an allergic rhinitis prediction method and prediction system based on an incremental neural network model, which includes the following steps: establishing an allergic rhinitis daily data database; training the neural network model; collecting daily life data and sending it to the server, saving it to the user's daily data record table; extracting the data of the day from the user's daily data record table to form an n-dimensional vector, normalizing it and inputting it into the allergic rhinitis pathology neural network model to predict the probability of allergic rhinitis; the smart home allergic rhinitis care device determines whether the probability value of allergic rhinitis is greater than 0.5; if the user is determined to have allergic rhinitis, the user goes to the hospital for examination by himself, and transmits the examination results back to the server through the smart home allergic rhinitis care device, and the server determines whether the examination results are correct; when the examination results are wrong, the incremental algorithm is executed to dynamically correct the neural network model. The invention predicts accurately and tailors the neural network model for each user.

[0006] The above patents all have the problem raised by this background technology: they ignore the monitoring and analysis of external factors and fail to promptly and effectively remind patients to take preventive measures.

[0007] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention and should not be regarded as an acknowledgement or any form of suggestion that the information constitutes the prior art already known to ordinary technicians in this field. Summary of the invention

[0008] The technical problem to be solved by the present invention is to overcome the defects of the prior art and provide an auxiliary system and method for diagnosis of allergic diseases based on digital mobile medical care, which improves the accuracy and timeliness of allergy warning by integrating multiple advanced technologies and methods.

[0009] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0010] On the one hand, the present invention provides an allergic disease consultation auxiliary system based on digital mobile medical care, comprising a digital mobile medical care module, an environmental monitoring module, a prediction module, a correction module, and a risk calculation module; wherein:

[0011] The digital mobile medical module is used to obtain the user's allergy history, user location, and obtain allergy cases in the user's area based on the user's location;

[0012] The environmental monitoring module is used to detect the concentration of each allergen in the user's area and collect environmental factors in the user's area;

[0013] The prediction module is used to predict the concentration of each allergen in the user's area;

[0014] The correction module corrects the predicted concentration value of each allergen based on the environmental factors;

[0015] The risk calculation module provides allergy warnings to users based on their allergy history, allergy cases in their area, and the corrected predicted allergen concentration.

[0016] As a preferred solution of the digital mobile medical consultation auxiliary system for allergic diseases described in the present invention, the digital mobile medical module includes a user interface unit, a positioning unit, and a query unit; wherein:

[0017] The user interface unit is used for user registration and login, and provides an allergy history entry function;

[0018] The positioning unit is used to obtain the user's location;

[0019] The query unit is used to obtain allergy cases in the area where the user is located in the past M days, where M is a positive integer;

[0020] The environmental monitoring module includes an allergen detection unit and an environmental factor unit; wherein:

[0021] The allergen detection unit is deployed with a sensor network for detecting the concentration of each allergen in real time;

[0022] The environmental factor unit obtains the environmental factors for the next day by calling the API interface of the public meteorological service; the environmental factors include rainfall and average wind speed.

[0023] As a preferred solution of the digital mobile medical consultation auxiliary system for allergic diseases of the present invention, the prediction module includes a data processing unit and a prediction model unit; wherein the data processing unit is used to establish a time series of the concentration of each allergen; the method is as follows:

[0024] The data processing unit sends a query instruction to the allergen detection unit, and the allergen detection unit responds to the query instruction and returns the concentration of each allergen in the last M days; the data processing unit cleans and normalizes the concentration of any allergen in the last M days, and organizes it into a time series with a length of Q in chronological order, where M=Q.

[0025] As a preferred solution of the digital mobile medical consultation auxiliary system for allergic diseases of the present invention, the prediction model unit is configured with a concentration prediction model for predicting the concentration of each allergen in the area where the user is located; the input of the concentration prediction model is the time series of the concentration of any allergen, and the output is the predicted concentration value of the corresponding allergen in the next day; for any specified allergen, the model equation is as follows:

[0026]

[0027] Among them, y t represents the predicted concentration of the specified allergen on day t; c is a constant parameter; y t-i represents the concentration value of the allergen on the ti day; the value range of i is 1, 2, ..., p, p is the first order of the model equation; α i Represents y t-i The weight coefficient of t-j represents the difference between the predicted concentration and the concentration value of the allergen on day tj; the value range of j is 1, 2, ..., q, where q is the second order of the model equation; β j Represents ε t-j The weight parameter of .

[0028] As a preferred solution of the digital mobile medical consultation auxiliary system for allergic diseases of the present invention, the fitting method of the concentration prediction model is as follows:

[0029] For any allergen, autocorrelation and partial autocorrelation plots were drawn based on the time series of concentration;

[0030] Determine the first order p of the model equation based on the autocorrelation graph; determine the second order q of the model equation based on the partial autocorrelation graph; specifically as follows: the autocorrelation graph drops sharply and is truncated after the first order p; the partial autocorrelation graph drops sharply and is truncated after the second order q;

[0031] The model equation is fitted based on the time series of allergen concentration; the maximum likelihood estimation is used to determine the value of the constant parameters and each weight coefficient;

[0032] The model equation of each allergen was fitted separately to obtain the concentration prediction model.

[0033] As a preferred solution of the digital mobile medical consultation auxiliary system for allergic diseases of the present invention, the correction module includes a first correction unit; the first correction unit is configured with a first correction strategy, which is as follows:

[0034] The first correction unit obtains the rainfall of the next day from the environmental factor unit; if the rainfall of the next day is not zero, the correction of the predicted concentration value of each allergen of the next day is triggered, and the formula is as follows:

[0035] Y1 = Y0 - f(R, Y0);

[0036] Wherein, Y0 represents the predicted concentration value of any allergen in the next day; Y1 represents the predicted concentration value corrected by the first correction unit; and f(R, Y0) represents the first correction function.

[0037] As a preferred solution of the digital mobile medical consultation auxiliary system for allergic diseases of the present invention, the correction module further includes a second correction unit; the second correction unit is configured with a second correction strategy, which is as follows:

[0038] The second correction unit obtains the average wind speed for the next day from the environmental factor unit; the second correction unit is also configured with a wind speed threshold. If the average wind speed for the next day is greater than the wind speed threshold, the correction of the predicted concentration value of each allergen for the next day is triggered, and the formula is as follows:

[0039] Y2=Y+g(W,Y0);

[0040] Among them, Y2 represents the concentration prediction value corrected by the second correction unit; if the rainfall in the next day is zero, Y is equal to the concentration prediction value Y0 of the allergen in the next day; if the rainfall in the next day is not zero, Y is equal to the concentration prediction value Y1 corrected by the first correction unit; g(W, Y0) represents the second correction function.

[0041] As a preferred solution of the digital mobile medical consultation assistance system for allergic diseases described in the present invention, wherein: the risk calculation module includes a risk calculation unit; the risk calculation unit is configured with a risk calculation model for calculating the risk probability of user allergies; the risk calculation model is any one of a support vector machine, a multi-layer perceptron, and a Transformer model; the output of the risk calculation model is the risk probability of user allergies; the input of the risk calculation model includes the user's allergy history, allergy cases in the user's area, and a corrected allergen concentration prediction value; wherein the user's allergy history includes the allergy type and the corresponding number of allergies, the allergy time of any allergy, and the corresponding allergen.

[0042] As a preferred solution of the digital mobile medical consultation assistance system for allergic diseases described in the present invention, the risk calculation module also includes an allergy warning unit; the allergy warning unit is configured with an allergy risk threshold, and when the risk probability of user allergy calculated by the risk calculation unit is greater than the allergy risk threshold, allergy warning information is sent to the user interface unit; the user interface unit also provides an information push function, and when the allergy warning information is received, the allergy warning information is pushed to the user; the allergy warning information includes allergy risk prompts, allergen concentration predicted values, and preventive measures recommendations.

[0043] In a second aspect, the present invention provides a digital mobile medical consultation auxiliary method for allergic diseases, comprising the following steps:

[0044] S1: Obtain the user's allergy history and user location;

[0045] S2: Obtain allergy cases in the user's area based on the user's location, and obtain the concentration of each allergen in the user's area;

[0046] S3: Calculate the predicted concentration value of each allergen in the user's area;

[0047] S4: Collecting environmental factors of the area where the user is located, and revising the predicted concentration value of each allergen based on the environmental factors;

[0048] S5: Provide allergy warning to the user based on the user's allergy history, allergy cases in the user's area and the corrected allergen concentration prediction value.

[0049] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0050] The environmental monitoring module detects the concentration of allergens in real time and obtains statistical information on allergy cases in the user's area, quickly understands the allergy trend in the area, and provides dynamic data support for allergy warnings. It conducts time series prediction of allergen concentrations and predicts the concentration of allergens for the next day in advance to provide users with a basis for early warning. It corrects the prediction results in combination with environmental factors to improve the accuracy of the prediction.

[0051] Based on the user's allergy history, allergy cases in the area and the corrected allergen concentration prediction value, the risk probability of the user's allergy is calculated, allergy warning information is automatically pushed to the user, and personalized preventive measures are provided to help users better manage allergy symptoms. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0053] Figure 1 A schematic diagram of the structure of the allergic disease consultation auxiliary system based on digital mobile medical care provided by the present invention;

[0054] Figure 2 A flow chart of the digital mobile medical consultation auxiliary method for allergic diseases provided by the present invention;

[0055] Figure 3 This is a flow chart of the fitting method of the concentration prediction model provided by the present invention. DETAILED DESCRIPTION

[0056] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0057] Example 1

[0058] This embodiment introduces a digital mobile medical consultation assistance system for allergic diseases. Figure 1 , including digital mobile medical module, environmental monitoring module, prediction module, correction module, and risk calculation module; among them:

[0059] The digital mobile medical module is used to obtain the user's allergy history, user location, and obtain allergy cases in the user's area based on the user's location; it includes a user interface unit, a positioning unit, and a query unit; wherein:

[0060] The user interface unit is used for user registration and login, and provides an allergy history entry function;

[0061] The positioning unit is used to obtain the user's location; the user's current location is determined through a high-precision GPS positioning service, which is convenient for dividing the user's area for subsequent accurate allergy warnings.

[0062] The query unit is used to obtain allergy cases in the user's area in the past M days, where M is a positive integer; the query unit retrieves statistical data on allergy cases in the user's area from the database of the public health department through an API interface, including detailed information such as allergy type, number of allergy cases, allergens, time of allergy occurrence, etc., so as to provide subsequent allergy warnings.

[0063] The environmental monitoring module is used to detect the concentration of each allergen in the user's area and collect environmental factors in the user's area; it includes an allergen detection unit and an environmental factor unit; wherein:

[0064] The allergen detection unit is deployed with a sensor network for real-time detection of the concentration of each allergen; the sensor data deployed in the user's area is obtained through a cloud server to obtain the allergen concentration in the user's area; common allergens can be detected, such as pollen, dust mites, pet hair, particulate matter in the air, mold spores, etc.

[0065] The environmental factor unit obtains the environmental factors for the next day by calling the API interface of the public meteorological service; the environmental factors include rainfall and average wind speed; these environmental factors are crucial for the correction of the predicted value of allergen concentration.

[0066] The prediction module is used to predict the concentration of each allergen in the area where the user is located; it includes a data processing unit and a prediction model unit; wherein:

[0067] The data processing unit is used to establish a time series of the concentration of each allergen; the method is as follows:

[0068] The data processing unit sends a query instruction to the allergen detection unit, and the allergen detection unit responds to the query instruction and returns the concentration of each allergen in the last M days; the data processing unit cleans and normalizes the concentration of any allergen in the last M days and arranges it into a time series with a length of Q in chronological order, where M=Q;

[0069] The prediction model unit is configured with a concentration prediction model for predicting the concentration of each allergen in the area where the user is located; the input of the concentration prediction model is the time series of the concentration of any allergen, and the output is the predicted concentration value of the corresponding allergen in the next day; for any specified allergen, the model equation is as follows:

[0070]

[0071] Among them, y t represents the predicted concentration of the specified allergen on day t; c is a constant parameter; y t-i represents the concentration value of the allergen on the ti day; the value range of i is 1, 2, ..., p, p is the first order of the model equation; α i Represents y t-i The weight coefficient of t-j represents the difference between the predicted concentration and the concentration value of the allergen on day tj; the value range of j is 1, 2, ..., q, where q is the second order of the model equation; β j Represents ε t-j The weight parameter of .

[0072] Reference Figure 3 , the fitting method of the concentration prediction model is as follows:

[0073] For any allergen, autocorrelation and partial autocorrelation plots were drawn based on the time series of concentration;

[0074] Determine the first order p of the model equation based on the autocorrelation graph; determine the second order q of the model equation based on the partial autocorrelation graph; specifically as follows: the autocorrelation graph drops sharply and is truncated after the first order p; the partial autocorrelation graph drops sharply and is truncated after the second order q;

[0075] The model equation is fitted based on the time series of allergen concentration; the maximum likelihood estimation is used to determine the value of the constant parameters and each weight coefficient;

[0076] The model equation of each allergen was fitted separately to obtain the concentration prediction model.

[0077] Optionally, after the data processing unit establishes a time series for the concentration of each allergen, it performs a stationarity test on the time series of each allergen concentration, determines the differential order and performs a differential operation; the input of the concentration prediction model is the time series of the concentration of any allergen after the differential operation, and the output is the differential value of the predicted value of the corresponding allergen concentration in the next day; the differential value of the predicted value is reversed by performing a differential operation to obtain the predicted value of the concentration of the corresponding allergen in the next day. The stationarity of the time series is ensured by the differential operation, making the prediction more accurate.

[0078] The correction module corrects the concentration prediction value of each allergen based on the environmental factor; it includes a first correction unit and a second correction unit;

[0079] The first correction unit is configured with a first correction strategy, which is as follows:

[0080] The first correction unit obtains the rainfall of the next day from the environmental factor unit; if the rainfall of the next day is not zero, the correction of the predicted concentration value of each allergen of the next day is triggered, and the formula is as follows:

[0081] Y1 = Y0 - f(R, Y0);

[0082] Wherein, Y0 represents the predicted concentration value of any allergen in the next day; Y1 represents the predicted concentration value after correction by the first correction unit; f(R, Y0) represents the first correction function, and the first correction function is set and function fitting is performed by those skilled in the art based on actual needs;

[0083] Rainfall usually reduces the concentration of allergens in the air because rain can settle allergens such as pollen and dust mites in the air to the ground. Therefore, the greater the rainfall, the greater the degree of decrease in allergen concentration. As the rainfall continues to increase, the rate of decrease in allergen concentration will gradually decrease. Therefore, the specific form of an optional first correction function is as follows:

[0084] f(R, Y0)=Y0·(1-exp(-k·R));

[0085] Among them, R represents the rainfall in the next day; k is the adjustment coefficient, and the value is determined by parameter fitting. Based on the adjustment of the first correction function, the predicted value of the allergen concentration can take the special situation of precipitation into account, making the concentration prediction more accurate.

[0086] The second correction unit is configured with a second correction strategy, which is as follows:

[0087] The second correction unit obtains the average wind speed for the next day from the environmental factor unit; the second correction unit is also configured with a wind speed threshold. If the average wind speed for the next day is greater than the wind speed threshold, the correction of the predicted concentration value of each allergen for the next day is triggered, and the formula is as follows:

[0088] Y2=Y+g(W,Y0);

[0089] Wherein, Y2 represents the concentration prediction value corrected by the second correction unit; if the rainfall in the next day is zero, Y is equal to the concentration prediction value Y0 of the allergen in the next day; if the rainfall in the next day is not zero, Y is equal to the concentration prediction value Y1 corrected by the first correction unit; g(W, Y0) represents the second correction function, and the second correction function is set and function fitting is performed by those skilled in the art based on actual needs;

[0090] Wind speed usually increases the concentration of allergens in the air, because stronger winds will blow up allergens such as pollen and dust mites from the ground, plants, and buildings, and resuspend them in the air. Therefore, the greater the wind speed, the greater the increase in allergen concentration. However, as the wind speed increases, the increase in allergen concentration may gradually weaken. This is because when the wind speed reaches a certain threshold, the allergens in the air have been fully diffused, and further increasing the wind speed will weaken the effect of increasing the concentration. Therefore, the specific form of an optional second correction function is as follows:

[0091] g(W, Y0)=μ·Y0·(1-exp(-d·W));

[0092] Wherein, W represents the average wind speed for the next day; μ represents the weight coefficient, and d represents the adjustment coefficient, and the values ​​of both are determined by parameter fitting.

[0093] The risk calculation module provides an allergy warning to the user based on the user's allergy history, allergy cases in the user's area, and the corrected allergen concentration prediction value, including a risk calculation unit and an allergy warning unit;

[0094] The risk calculation unit is configured with a risk calculation model for calculating the risk probability of user allergies; the risk calculation model is any one of a support vector machine, a multi-layer perceptron, and a Transformer model; the output of the risk calculation model is the risk probability of user allergies; the input of the risk calculation model includes the user's allergy history, allergy cases in the user's area, and the corrected predicted value of allergen concentration; wherein the user's allergy history includes the allergy type and the corresponding number of allergies, the allergy time of any allergy, and the corresponding allergen; optionally, the allergy history also includes the frequency of allergies (e.g., occasional / frequent), the duration of each allergy, and the time point when the most recent allergy occurred. The allergy cases in the user's area include the allergy type and the corresponding number of allergies and allergens. A process for calculating the risk probability of user allergies using a risk calculation model is as follows:

[0095] Data cleaning of the user's allergy history and allergy cases in the user's area, removal of duplicate records and processing of missing values;

[0096] Convert the timestamp to date format and perform one-hot encoding on the categorical features;

[0097] Extract features from input data, including user features, regional features, and environmental features; for example, regional features include user ID, allergy type, number of allergies, recent allergy frequency (such as the number of allergies in the past month), and allergen list, where allergy type and allergen list are encoded in one-hot; regional features include regional ID, regional ID, allergy type, number of allergic people, and allergen list, where allergy type and allergen list are encoded in one-hot; environmental features include the corrected concentration prediction values ​​of various allergens, which have been standardized;

[0098] The above features are combined to form a complete feature matrix, and the feature matrix is ​​input into the risk calculation model, which calculates and outputs the risk probability of the user's allergy. The risk calculation model can extract a variety of nonlinear features from the above inputs and learn the impact of these features on the allergy probability through weight distribution. In addition to intuitive personal and environmental features, regional features as part of the input can largely make up for some other influencing factors that are difficult to quantify and consider, thereby improving the accuracy of risk probability calculation.

[0099] The allergy warning unit is configured with an allergy risk threshold. When the risk probability of user allergy calculated by the risk calculation unit is greater than the allergy risk threshold, allergy warning information is sent to the user interface unit; the user interface unit also provides an information push function. When the allergy warning information is received, the allergy warning information is pushed to the user; the allergy warning information includes allergy risk prompts, predicted values ​​of allergen concentrations, and preventive measures recommendations, such as wearing masks, reducing going out, etc.

[0100] Example 2

[0101] This embodiment is the second embodiment of the present invention; it is based on the same inventive concept as embodiment 1, Figure 2 This embodiment introduces a digital mobile medical consultation auxiliary method for allergic diseases, which includes the following steps:

[0102] S1: Obtain the user's allergy history and user location; provide user interaction functions and operation interfaces through mini-programs or mobile apps; determine the user's current location through high-precision GPS positioning services to facilitate the division of the user's area.

[0103] S2: Based on the user's location, obtain the allergy cases in the user's area and the concentration of each allergen in the user's area; obtain the allergy cases in the user's area by calling the API interface of the public health department, and obtain the concentration of each allergen in the user's area through the sensor network.

[0104] S3: Calculate the predicted concentration value of each allergen in the area where the user is located; process the time series of the concentration of each allergen separately based on the pre-fitted time series prediction model, and obtain the predicted concentration value of each allergen from the calculation.

[0105] S4: Collect environmental factors of the area where the user is located, and correct the predicted concentration value of each allergen based on the environmental factors; the collected environmental factors include rainfall and average wind speed, and the predicted concentration value of each allergen is corrected by rainfall and average wind speed in turn.

[0106] S5: Provide allergy warning to users based on their allergy history, allergy cases in their area, and the corrected allergen concentration prediction value. The risk probability of user allergies is calculated through the trained risk calculation model. When the risk probability of user allergies is higher than the preset allergy risk threshold, an allergy warning message is sent to the user.

[0107] The specific functional implementation of each of the above modules is described in Example 1, in conjunction with the relevant content of the allergic disease consultation assistance system based on digital mobile medical care, which will not be elaborated here.

[0108] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the purpose and scope of protection of the present invention, which are all within the protection of the present invention.

Claims

1. A digital mobile medical consultation assistance system for allergic diseases, characterized by: It includes digital mobile medical module, environmental monitoring module, prediction module, correction module and risk calculation module; among which: The digital mobile medical module is used to obtain the user's allergy history, user location, and obtain allergy cases in the user's area based on the user's location; The environmental monitoring module is used to detect the concentration of each allergen in the user's area and collect environmental factors in the user's area; The prediction module is used to predict the concentration of each allergen in the user's area; The correction module corrects the predicted concentration value of each allergen based on the environmental factors; The risk calculation module provides allergy warnings to users based on their allergy history, allergy cases in their area, and the corrected predicted allergen concentration.

2. The allergic disease consultation assistance system based on digital mobile medical care as claimed in claim 1, characterized in that: The digital mobile medical module includes a user interface unit, a positioning unit, and a query unit; wherein: The user interface unit is used for user registration and login, and provides an allergy history entry function; The positioning unit is used to obtain the user's location; The query unit is used to obtain allergy cases in the area where the user is located in the past M days, where M is a positive integer; The environmental monitoring module includes an allergen detection unit and an environmental factor unit; wherein: The allergen detection unit is deployed with a sensor network for detecting the concentration of each allergen in real time; The environmental factor unit obtains the environmental factors for the next day by calling the API interface of the public meteorological service; the environmental factors include rainfall and average wind speed.

3. The allergic disease consultation auxiliary system based on digital mobile medical care as claimed in claim 2, characterized in that: The prediction module includes a data processing unit and a prediction model unit; wherein the data processing unit is used to establish a time series of the concentration of each allergen; the method is as follows: The data processing unit sends a query instruction to the allergen detection unit, and the allergen detection unit responds to the query instruction and returns the concentration of each allergen in the last M days; the data processing unit cleans and normalizes the concentration of any allergen in the last M days, and organizes it into a time series with a length of Q in chronological order, where M=Q.

4. The allergic disease consultation assistance system based on digital mobile medical care as claimed in claim 3, characterized in that: The prediction model unit is configured with a concentration prediction model for predicting the concentration of each allergen in the area where the user is located; the input of the concentration prediction model is the time series of the concentration of any allergen, and the output is the predicted concentration value of the corresponding allergen in the next day; for any specified allergen, the concentration prediction model equation is as follows: Among them, y t represents the predicted concentration of the specified allergen on day t; c is a constant parameter; y t-i represents the concentration value of the allergen on the ti day; the value range of i is 1, 2, ..., p, p is the first order of the model equation; α i Represents y t-i The weight coefficient of t-j represents the difference between the predicted concentration and the concentration value of the allergen on day tj; the value range of j is 1, 2, ..., q, where q is the second order of the model equation; β j Represents ε t-j The weight parameter of .

5. The allergic disease consultation auxiliary system based on digital mobile medical care as claimed in claim 4, characterized in that: The fitting method of the concentration prediction model is as follows: For any allergen, autocorrelation and partial autocorrelation plots were drawn based on the time series of concentration; Determine the first order p of the model equation based on the autocorrelation graph; determine the second order q of the model equation based on the partial autocorrelation graph; The model equation is fitted based on the time series of allergen concentration; the maximum likelihood estimation is used to determine the value of the constant parameters and each weight coefficient; The model equation of each allergen was fitted separately to obtain the concentration prediction model.

6. The allergic disease consultation auxiliary system based on digital mobile medical care as claimed in claim 5, characterized in that: The correction module includes a first correction unit; the first correction unit is configured with a first correction strategy, which is as follows: The first correction unit obtains the rainfall of the next day from the environmental factor unit; if the rainfall of the next day is not zero, the correction of the predicted concentration value of each allergen of the next day is triggered, and the formula is as follows: Y1 = Y0 - f(R, Y0); Wherein, Y0 represents the predicted concentration value of any allergen in the next day; Y1 represents the predicted concentration value corrected by the first correction unit; and f(R, Y0) represents the first correction function.

7. The allergic disease consultation auxiliary system based on digital mobile medical care as claimed in claim 6, characterized in that: The correction module further includes a second correction unit; the second correction unit is configured with a second correction strategy, which is as follows: The second correction unit obtains the average wind speed for the next day from the environmental factor unit; the second correction unit is also configured with a wind speed threshold. If the average wind speed for the next day is greater than the wind speed threshold, the correction of the predicted concentration value of each allergen for the next day is triggered, and the formula is as follows: Y2=Y+g(W,Y0); Among them, Y2 represents the concentration prediction value corrected by the second correction unit; if the rainfall in the next day is zero, Y is equal to the concentration prediction value Y0 of the allergen in the next day; if the rainfall in the next day is not zero, Y is equal to the concentration prediction value Y1 corrected by the first correction unit; g(W, Y0) represents the second correction function.

8. The allergic disease consultation auxiliary system based on digital mobile medical care as claimed in claim 7, characterized in that: The risk calculation module includes a risk calculation unit; the risk calculation unit is configured with a risk calculation model for calculating the risk probability of user allergies; the risk calculation model is any one of a support vector machine, a multi-layer perceptron, and a Transformer model; the output of the risk calculation model is the risk probability of user allergies; the input of the risk calculation model includes the user's allergy history, allergy cases in the user's area, and a corrected allergen concentration prediction value; wherein the user's allergy history includes the allergy type and the corresponding number of allergies, the allergic time of any allergy, and the corresponding allergen.

9. The allergic disease consultation auxiliary system based on digital mobile medical care as claimed in claim 8, characterized in that: The risk calculation module also includes an allergy warning unit; the allergy warning unit is configured with an allergy risk threshold. When the risk probability of user allergy calculated by the risk calculation unit is greater than the allergy risk threshold, allergy warning information is sent to the user interface unit; the user interface unit also provides an information push function. When the allergy warning information is received, the allergy warning information is pushed to the user; the allergy warning information includes allergy risk prompts, allergen concentration predicted values, and preventive measures recommendations.

10. A digital mobile medical consultation assistance method for allergic diseases, implemented based on the digital mobile medical consultation assistance system for allergic diseases according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1: Obtain the user's allergy history and user location; S2: Obtain allergy cases in the user's area based on the user's location, and obtain the concentration of each allergen in the user's area; S3: Calculate the predicted concentration value of each allergen in the user's area; S4: Collecting environmental factors of the area where the user is located, and revising the predicted concentration value of each allergen based on the environmental factors; S5: Provide allergy warning to the user based on the user's allergy history, allergy cases in the user's area and the corrected allergen concentration prediction value.

Images