Insect-borne infectious disease prevention and control system based on smart chip

Abstract

The present invention discloses a prevention and control system for vector-borne infectious diseases based on a smart chip, which belongs to the field of disease prevention and control technology, and includes a data acquisition module, a data processing module, a model training module, a test optimization module, a prediction and evaluation module, and a prevention and control module. The present invention solves the problem that the existing situation of vector-borne infectious diseases cannot be grasped in time, resulting in the inability to effectively prevent and control vector-borne infectious diseases, resulting in poor prevention and control effects of vector-borne infectious diseases. The present invention collects real-time patient monitoring data in real time, processes the real-time patient monitoring data, determines patient monitoring feature data, predicts and evaluates the patient monitoring feature data based on a neural network model, determines the patient prediction and evaluation results based on the smart chip, and formulates an infectious disease prevention and control plan, which can grasp the situation of vector-borne infectious diseases in time, can effectively prevent and control vector-borne infectious diseases, and can improve the prevention and control effects of vector-borne infectious diseases.

Description

Technical Field

[0001] The present invention relates to the technical field of disease prevention and control, and in particular to a prevention and control system for insect-borne infectious diseases based on a smart chip. Background Art

[0002] Insect-borne diseases are a type of infectious disease that is transmitted by arthropods to animals and humans through bites. They mainly include mosquito-borne, tick-borne, mite-borne, louse-borne and flea-borne infectious diseases. In history, they have caused serious damage, such as malaria, epidemic encephalitis B, etc.

[0003] Insect-borne diseases account for about 5% to 10% of the total number of infectious diseases in my country each year, but their deaths account for 30% to 40% of the total number of deaths from infectious diseases. There are many species of insect-borne organisms in my country, and their distribution is complex, while there is a large gap between the level of relevant monitoring and control and the requirements for epidemic prevention. At present, the long-distance transmission of insect-borne diseases is becoming more and more common, and the risk of the occurrence and spread of new insect-borne diseases is very high.

[0004] The Chinese patent with publication number CN114520058A discloses a method and device for predicting the transmission risk of vector-borne infectious diseases, wherein the method includes: obtaining historical case data of vector-borne infectious diseases nationwide and local climate and environmental data matching the data; using the historical case data as dependent variables and the local climate and environmental data as independent variables, modeling and analyzing based on a generalized additive mixed model, and verifying the model accuracy under different strategies to obtain the best fitting model; obtaining the predicted meteorological data for a preset future time; predicting the spatiotemporal distribution of vector-borne infectious diseases at a preset future time based on the meteorological data for the preset future time and the best fitting model in combination with different climate change scenarios; however, the patent has the following defects:

[0005] The current situation of vector-borne infectious diseases cannot be grasped in a timely manner, resulting in the inability to effectively prevent and control vector-borne infectious diseases, resulting in poor prevention and control effects of vector-borne infectious diseases. Summary of the invention

[0006] The purpose of the present invention is to provide an insect-borne infectious disease prevention and control system based on a smart chip, which can timely grasp the situation of insect-borne infectious diseases, effectively prevent and control insect-borne infectious diseases, improve the prevention and control effect of insect-borne infectious diseases, and solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The prevention and control system of insect-borne infectious diseases based on smart chips includes:

[0009] The data acquisition module is used to collect patient consultation data, patient imaging data and patient test data in real time, and determine the real-time patient monitoring data based on the smart chip;

[0010] A data processing module is used to retrieve, sort and extract features of real-time patient monitoring data based on smart chips, and determine patient monitoring feature data based on smart chips;

[0011] The model training module is used to train the model architecture and determine the neural network model suitable for the prevention and control of insect-borne infectious diseases;

[0012] The test optimization module is used to perform performance testing and adjustment and optimization on the neural network model, and determine the best neural network model after adjustment and optimization;

[0013] A prediction and evaluation module is used to predict and evaluate the patient monitoring characteristic data and determine the patient prediction and evaluation results based on the smart chip;

[0014] The prevention and control module is used to formulate infectious disease prevention and control plans, and to carry out intelligent prevention and control of vector-borne infectious diseases based on the infectious disease prevention and control plans.

[0015] Preferably, the data acquisition module includes:

[0016] A medical consultation collection unit is used to collect the patient's medical consultation information in real time and determine the patient's medical consultation data based on the smart chip;

[0017] An image acquisition unit is used to acquire the patient's image information in real time and determine the patient's image data based on the smart chip;

[0018] The test collection unit is used to collect the patient's test information in real time and determine the patient's test data based on the smart chip;

[0019] Among them, based on real-time collected patient consultation data, patient imaging data and patient test data;

[0020] Determine real-time data of patient monitoring based on smart chips.

[0021] Preferably, the image acquisition unit comprises:

[0022] A real-time acquisition unit, used to acquire the patient's image information in real time to obtain the patient's image data;

[0023] A grayscale image acquisition module, used to perform grayscale processing on the patient image data to obtain a grayscale image corresponding to the patient image data;

[0024] A gray value extraction module, used to extract the gray value of each pixel block in the patient image data;

[0025] The image clarity evaluation coefficient acquisition module is used to obtain the image clarity evaluation coefficient by using the clarity coefficient corresponding to the pixel block row included in the length edge and the clarity coefficient corresponding to the pixel block column included in the width edge contained in the patient image data, wherein the image clarity evaluation coefficient is obtained by the following formula:

[0026]

[0027] Where G represents the image clarity evaluation coefficient; k represents the number of pixel block rows included on the length edge of the patient image data; r represents the number of pixel block columns included on the width edge of the patient image data; k 01i represents the weight coefficient corresponding to the pixel block row contained in the length edge of the i-th row; k 02i Represents the weight coefficient corresponding to the pixel block column contained on the width edge of the i-th column; s 01i Indicates the clarity coefficient corresponding to the pixel block row contained on the i-th row length edge; s 02i Indicates the clarity coefficient corresponding to the pixel block column contained on the width edge of the i-th column;

[0028] A comparison module, used for comparing the image clarity evaluation coefficient with a preset clarity evaluation coefficient threshold;

[0029] The clarity alarm module is used to issue an abnormal clarity alarm to the patient image data when the image clarity evaluation coefficient is lower than a preset clarity evaluation coefficient threshold.

[0030] Preferably, the image clarity evaluation coefficient acquisition module includes:

[0031] A pixel block row number extraction module, used to extract the number of pixel block rows contained in the length edge contained in the patient image data;

[0032] A first grayscale value acquisition module, configured to extract, for each pixel block row included in the length edge included in the patient image data, a grayscale value of each pixel block as a first grayscale value;

[0033] The first definition coefficient acquisition module is used to obtain the definition coefficient corresponding to the pixel block row included in the length edge by using the first gray value; wherein the definition coefficient corresponding to the pixel block row included in the length edge is obtained by the following formula:

[0034]

[0035] Among them, S 01represents the clarity coefficient corresponding to the pixel block row included on the length edge; n represents the number of pixel blocks included in the pixel block row included on the i-th length edge; S i represents the gray value corresponding to the pixel block on the length of the i-th patient image data; S i-1 represents the gray value corresponding to the pixel block on the length of the i-1th patient image data; S mini S represents the minimum grayscale value corresponding to the pixel block row contained on the length edge of the i-th row; maxi Indicates the maximum grayscale value corresponding to the pixel block row contained on the length edge of the i-th row;

[0036] A pixel block column number extraction module, used to extract the number of pixel block columns included in the width edge included in the patient image data;

[0037] A second grayscale value acquisition module, for extracting the grayscale value of each pixel block as a second grayscale value according to the number of pixel block columns included in the width edge included in the patient image data;

[0038] The second definition coefficient acquisition module is used to obtain the definition coefficient corresponding to the pixel block column included in the width edge by using the second gray value, wherein the definition coefficient corresponding to the pixel block column included in the width edge is obtained by the following formula:

[0039]

[0040] Where m represents the pixel block column contained on the width edge of the i-th column; S j represents the gray value corresponding to the pixel block on the width of the jth patient image data; S j-1 represents the gray value corresponding to the pixel block on the width of the j-1th patient image data; S minj S represents the minimum grayscale value corresponding to the pixel block row contained on the width edge of the jth column; maxj Indicates the maximum grayscale value corresponding to the pixel block row contained on the j-th column width edge.

[0041] Preferably, the data processing module includes:

[0042] A data retrieval unit, used to retrieve real-time data of patient monitoring based on the smart chip;

[0043] Obtain real-time data of patient monitoring based on smart chips;

[0044] Based on the sequential retrieval method, the real-time data of patient monitoring based on smart chips are retrieved;

[0045] Check the consistency of real-time data of patient monitoring based on smart chips;

[0046] Remove data that is out of the normal range, logically unreasonable or contradictory in the real-time data of patient monitoring based on smart chips;

[0047] Process invalid and missing values ​​for real-time patient monitoring data based on smart chips;

[0048] Remove invalid and missing data that are of no value to the prevention and control of vector-borne infectious diseases contained in the real-time patient monitoring data based on smart chips;

[0049] Identify real-time patient surveillance data that is valuable for the prevention and control of vector-borne infectious diseases;

[0050] A data sorting unit, used for sorting the retrieved patient monitoring real-time data;

[0051] Obtain retrieved real-time patient monitoring data that is valuable for the prevention and control of vector-borne infectious diseases;

[0052] Based on the internal sorting method, the retrieved real-time patient monitoring data that is valuable for the prevention and control of vector-borne infectious diseases is sorted;

[0053] Determine the real-time patient monitoring data with ranking order;

[0054] A feature extraction unit, used for extracting features from the sorted patient monitoring real-time data;

[0055] Acquire sorted and ordered patient monitoring real-time data;

[0056] Extracting features from the sorted and ordered patient monitoring real-time data;

[0057] Determine patient monitoring characteristic data based on smart chips.

[0058] Preferably, the model training module includes:

[0059] A data storage unit, used for storing historical information of patients with insect-borne infectious diseases;

[0060] According to the prevention and control needs of vector-borne infectious diseases based on smart chips, historical information of patients with vector-borne infectious diseases is collected in advance, and the pre-collected historical information of patients with vector-borne infectious diseases is stored;

[0061] A data division unit, used for dividing historical information of patients with vector-borne infectious diseases;

[0062] Obtain stored historical information on patients with vector-borne infectious diseases;

[0063] To classify the historical information of patients with vector-borne infectious diseases;

[0064] Determine the training set and test set;

[0065] Model selection unit, used to select the appropriate model architecture;

[0066] According to the prevention and control needs of insect-borne infectious diseases based on smart chips;

[0067] Based on the training set, select the appropriate model architecture;

[0068] Model training unit, used to train the selected model architecture;

[0069] Get the selected model architecture;

[0070] Based on the training set, train the model architecture;

[0071] Determine a neural network model suitable for the prevention and control of vector-borne infectious diseases.

[0072] Preferably, the test optimization module includes:

[0073] Model testing unit, used to test neural network models applicable to the prevention and control of vector-borne infectious diseases;

[0074] Obtain neural network models suitable for prevention and control of vector-borne infectious diseases;

[0075] Based on the test set, the neural network model suitable for the prevention and control of vector-borne infectious diseases is tested;

[0076] Determine the test results of the neural network model based on the prevention and control of insect-borne infectious diseases;

[0077] An adjustment and optimization unit, used to adjust and optimize a neural network model suitable for the prevention and control of vector-borne infectious diseases;

[0078] Obtain test results of neural network models based on prevention and control of vector-borne infectious diseases;

[0079] Mining and analyzing the test results of neural network models based on the prevention and control of vector-borne infectious diseases;

[0080] Determine the model adjustment and optimization plan based on the prevention and control of vector-borne infectious diseases;

[0081] Based on the model adjustment and optimization scheme, the neural network model suitable for the prevention and control of vector-borne infectious diseases is adjusted and optimized;

[0082] Determine the best neural network model after adjustment and optimization.

[0083] Preferably, the prediction and evaluation module includes:

[0084] A data extraction unit, used for extracting patient monitoring characteristic data based on the smart chip;

[0085] According to the prevention and control needs of vector-borne infectious diseases based on smart chips, the patient monitoring characteristic data based on smart chips are extracted;

[0086] A prediction and evaluation unit, used for predicting and evaluating the patient monitoring characteristic data based on the smart chip;

[0087] Obtaining extracted patient monitoring feature data based on smart chips;

[0088] Obtain the best neural network model after adjustment and optimization;

[0089] Inputting the patient monitoring characteristic data into the neural network model, and performing prediction and evaluation on the patient monitoring characteristic data based on the neural network model;

[0090] Determine the patient prediction assessment results based on the smart chip.

[0091] Preferably, the prevention control module includes:

[0092] a strategy development unit to develop plans for the prevention and control of infectious diseases;

[0093] Obtain patient prediction assessment results based on smart chips;

[0094] Mining and analyzing the patient prediction and assessment results based on smart chips;

[0095] Determine the prevention and control plan of infectious diseases based on smart chips;

[0096] Intelligent prevention and control unit, used for intelligent prevention and control of insect-borne infectious diseases;

[0097] Obtain infectious disease prevention and control solutions based on smart chips;

[0098] Intelligent prevention and control of vector-borne infectious diseases based on infectious disease prevention and control plans.

[0099] Preferably, intelligent prevention and control of vector-borne infectious diseases is performed based on the infectious disease prevention and control plan, and the following operations are performed:

[0100] When the patient prediction and assessment result based on the smart chip is that the patient has an insect-borne infectious disease, the infectious disease prevention and control plan based on the smart chip is: isolate and treat the patient in a timely manner, focus on checking the places and people the patient has contacted, disinfect the contact places, diagnose the contact people one by one, and fully isolate the insect-borne infectious disease.

[0101] Compared with the prior art, the present invention has the following beneficial effects:

[0102] The present invention determines the real-time data of patient monitoring based on the smart chip by collecting patient consultation data, patient imaging data and patient examination data in real time, determines the patient monitoring feature data based on the smart chip by searching, sorting and extracting features of the real-time data of patient monitoring based on the smart chip, inputs the patient monitoring feature data into a neural network model suitable for the prevention and control of vector-borne infectious diseases, predicts and evaluates the patient monitoring feature data based on the neural network model, determines the patient prediction and evaluation results based on the smart chip, formulates an infectious disease prevention and control plan, and performs intelligent prevention and control of vector-borne infectious diseases based on the infectious disease prevention and control plan, can timely grasp the situation of vector-borne infectious diseases, can effectively prevent and control vector-borne infectious diseases, and can improve the prevention and control effect of vector-borne infectious diseases. BRIEF DESCRIPTION OF THE DRAWINGS

[0103] Figure 1 This is a module diagram of the insect-borne infectious disease prevention and control system based on a smart chip of the present invention. DETAILED DESCRIPTION

[0104] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0105] In order to solve the existing problem of not being able to timely grasp the situation of vector-borne infectious diseases, resulting in the inability to effectively prevent and control vector-borne infectious diseases, and the poor prevention and control effect of vector-borne infectious diseases, please refer to Figure 1 , this embodiment provides the following technical solutions:

[0106] The insect-borne infectious disease prevention and control system based on smart chips includes: data acquisition module, data processing module, model training module, test optimization module, prediction and evaluation module and prevention and control module.

[0107] It should be noted that through the interactive communication between the data acquisition module, the data processing module, the model training module, the test optimization module, the prediction and evaluation module and the prevention and control module, the situation of vector-borne infectious diseases can be grasped in a timely manner, the vector-borne infectious diseases can be effectively prevented and controlled, and the prevention and control effects of vector-borne infectious diseases can be improved.

[0108] Among them, the data acquisition module is used to collect patient consultation data, patient imaging data and patient test data in real time, and determine the real-time patient monitoring data based on the smart chip;

[0109] In this embodiment, as a preferred technical solution of the present invention, the data acquisition module includes:

[0110] A medical consultation collection unit is used to collect the patient's medical consultation information in real time and determine the patient's medical consultation data based on the smart chip;

[0111] An image acquisition unit is used to acquire the patient's image information in real time and determine the patient's image data based on the smart chip;

[0112] The test collection unit is used to collect the patient's test information in real time and determine the patient's test data based on the smart chip;

[0113] Among them, based on real-time collected patient consultation data, patient imaging data and patient test data;

[0114] Determine real-time data of patient monitoring based on smart chips.

[0115] Among them, the data processing module is used to retrieve, sort and extract features of the real-time data of patient monitoring based on the smart chip, and determine the patient monitoring feature data based on the smart chip;

[0116] Specifically, the image acquisition unit includes:

[0117] A real-time acquisition unit, used to acquire the patient's image information in real time to obtain the patient's image data;

[0118] A grayscale image acquisition module, used to perform grayscale processing on the patient image data to obtain a grayscale image corresponding to the patient image data;

[0119] A gray value extraction module, used to extract the gray value of each pixel block in the patient image data;

[0120] The image clarity evaluation coefficient acquisition module is used to obtain the image clarity evaluation coefficient by using the clarity coefficient corresponding to the pixel block row included in the length edge and the clarity coefficient corresponding to the pixel block column included in the width edge contained in the patient image data, wherein the image clarity evaluation coefficient is obtained by the following formula:

[0121]

[0122] Where G represents the image clarity evaluation coefficient; k represents the number of pixel block rows included on the length edge of the patient image data; r represents the number of pixel block columns included on the width edge of the patient image data; k 01i represents the weight coefficient corresponding to the pixel block row contained in the length edge of the i-th row; k 02i Represents the weight coefficient corresponding to the pixel block column contained on the width edge of the i-th column; s01i Indicates the clarity coefficient corresponding to the pixel block row contained on the i-th row length edge; s 02i Indicates the clarity coefficient corresponding to the pixel block column contained on the width edge of the i-th column;

[0123] A comparison module, used for comparing the image clarity evaluation coefficient with a preset clarity evaluation coefficient threshold;

[0124] The clarity alarm module is used to issue an abnormal clarity alarm to the patient image data when the image clarity evaluation coefficient is lower than a preset clarity evaluation coefficient threshold.

[0125] The technical effect of the above technical solution is that the patient's image data can be obtained in real time through the real-time acquisition unit, which is particularly important for medical scenarios that require immediate processing. Real-time ensures that doctors can quickly obtain the patient's latest image information, thereby making a quick and accurate diagnosis.

[0126] The grayscale image acquisition module and grayscale value extraction module perform grayscale processing on the collected image data and extract the grayscale value of each pixel block. Grayscale processing helps to simplify image information and reduce the amount of data, while grayscale value extraction provides basic data for subsequent image clarity evaluation.

[0127] The image clarity evaluation coefficient acquisition module calculates the image clarity evaluation coefficient by comprehensively considering the clarity coefficients of the pixel block rows and columns on the length and width sides and combining the corresponding weight coefficients. This method can comprehensively and objectively evaluate the clarity of the image and avoid the limitations of a single indicator evaluation.

[0128] The comparison module compares the calculated image clarity evaluation coefficient with the preset clarity evaluation coefficient threshold. Once the evaluation coefficient is lower than the threshold, the clarity alarm module will immediately trigger an alarm. This mechanism can promptly detect and handle clarity problems in image data to avoid misdiagnosis or missed diagnosis.

[0129] The entire image acquisition unit forms a complete and automated system from image data acquisition, processing to evaluation and alarm, which not only improves work efficiency but also reduces the impact of human factors on diagnostic results.

[0130] In summary, this technical solution achieves comprehensive, efficient and objective evaluation and processing of patient imaging data through real-time acquisition, grayscale processing, grayscale value extraction, image clarity evaluation and clarity abnormality alarm, providing strong technical support for medical diagnosis.

[0131] Specifically, the image clarity evaluation coefficient acquisition module includes:

[0132] A pixel block row number extraction module, used to extract the number of pixel block rows contained in the length edge contained in the patient image data;

[0133] A first grayscale value acquisition module, configured to extract, for each pixel block row included in the length edge included in the patient image data, a grayscale value of each pixel block as a first grayscale value;

[0134] The first definition coefficient acquisition module is used to obtain the definition coefficient corresponding to the pixel block row included in the length edge by using the first gray value; wherein the definition coefficient corresponding to the pixel block row included in the length edge is obtained by the following formula:

[0135]

[0136] Among them, S 01 represents the clarity coefficient corresponding to the pixel block row included on the length edge; n represents the number of pixel blocks included in the pixel block row included on the i-th length edge; S i represents the gray value corresponding to the pixel block on the length of the i-th patient image data; S i-1 represents the gray value corresponding to the pixel block on the length of the i-1th patient image data; S mini S represents the minimum grayscale value corresponding to the pixel block row contained on the length edge of the i-th row; maxi Indicates the maximum grayscale value corresponding to the pixel block row contained on the length edge of the i-th row;

[0137] A pixel block column number extraction module, used to extract the number of pixel block columns included in the width edge included in the patient image data;

[0138] A second grayscale value acquisition module, for extracting the grayscale value of each pixel block as a second grayscale value according to the number of pixel block columns included in the width edge included in the patient image data;

[0139] The second definition coefficient acquisition module is used to obtain the definition coefficient corresponding to the pixel block column included in the width edge by using the second gray value, wherein the definition coefficient corresponding to the pixel block column included in the width edge is obtained by the following formula:

[0140]

[0141] Where m represents the pixel block column contained on the width edge of the i-th column; S j represents the gray value corresponding to the pixel block on the width of the jth patient image data; S j-1 represents the gray value corresponding to the pixel block on the width of the j-1th patient image data; S minj S represents the minimum grayscale value corresponding to the pixel block row contained on the width edge of the jth column;maxj Indicates the maximum grayscale value corresponding to the pixel block row contained on the j-th column width edge.

[0142] The technical effect of the above technical solution is: through the pixel block row number extraction module and the pixel block column number extraction module, the technical solution can accurately identify the number of pixel blocks in the patient image data. Then, the gray value of each pixel block is extracted by using the first gray value acquisition module and the second gray value acquisition module, which provides an accurate data basis for the subsequent clarity evaluation.

[0143] The first definition coefficient acquisition module and the second definition coefficient acquisition module calculate the definition coefficients for the rows and columns of the pixel blocks on the length side and the width side respectively. By considering the gray value difference between each pixel block and its adjacent pixel blocks, as well as the minimum and maximum gray values ​​on each row or column, the definition of the image can be evaluated more carefully. This method not only considers the overall definition of the image, but also the definition of the local area, making the evaluation result more comprehensive and accurate.

[0144] In the image clarity evaluation coefficient acquisition module, weight coefficients are used to adjust the influence of the clarity coefficients on different rows or columns on the final evaluation coefficient. This allows the weights to be flexibly adjusted according to actual conditions to meet different application requirements.

[0145] The entire technical solution is automated, from extracting the number of pixel blocks rows and columns, to obtaining grayscale values, to calculating the clarity coefficient, and finally obtaining the image clarity evaluation coefficient, all in real time. This greatly improves work efficiency, reduces the possibility of human intervention, and ensures the objectivity and accuracy of the evaluation results.

[0146] By obtaining accurate image clarity evaluation coefficients, doctors can better understand the quality of patient imaging data and make more accurate diagnostic decisions. Especially in scenarios that require high-precision diagnosis, this technology can greatly improve the accuracy and reliability of diagnosis.

[0147] In summary, this technical solution provides strong technical support for the processing and analysis of patient imaging data through precise clarity evaluation, detailed clarity analysis, flexible weight setting, real-time and automation, and auxiliary diagnostic decision-making.

[0148] In this embodiment, as a preferred technical solution of the present invention, the data processing module includes:

[0149] A data retrieval unit, used to retrieve real-time data of patient monitoring based on the smart chip;

[0150] Obtain real-time data of patient monitoring based on smart chips;

[0151] Based on the sequential retrieval method, the real-time data of patient monitoring based on smart chips are retrieved;

[0152] Check the consistency of real-time data of patient monitoring based on smart chips;

[0153] Remove data that is out of the normal range, logically unreasonable or contradictory in the real-time data of patient monitoring based on smart chips;

[0154] Process invalid and missing values ​​for real-time patient monitoring data based on smart chips;

[0155] Remove invalid and missing data that are of no value to the prevention and control of vector-borne infectious diseases contained in the real-time patient monitoring data based on smart chips;

[0156] Identify real-time patient surveillance data that is valuable for the prevention and control of vector-borne infectious diseases;

[0157] A data sorting unit, used for sorting the retrieved patient monitoring real-time data;

[0158] Obtain retrieved real-time patient monitoring data that is valuable for the prevention and control of vector-borne infectious diseases;

[0159] Based on the internal sorting method, the retrieved real-time patient monitoring data that is valuable for the prevention and control of vector-borne infectious diseases is sorted;

[0160] Determine the real-time patient monitoring data with ranking order;

[0161] A feature extraction unit, used for extracting features from the sorted patient monitoring real-time data;

[0162] Acquire sorted and ordered patient monitoring real-time data;

[0163] Extracting features from the sorted and ordered patient monitoring real-time data;

[0164] Determine patient monitoring characteristic data based on smart chips.

[0165] Among them, the model training module is used to train the model architecture and determine the neural network model suitable for the prevention and control of insect-borne infectious diseases;

[0166] In this embodiment, as a preferred technical solution of the present invention, the model training module includes:

[0167] A data storage unit, used for storing historical information of patients with insect-borne infectious diseases;

[0168] According to the prevention and control needs of vector-borne infectious diseases based on smart chips, historical information of patients with vector-borne infectious diseases is collected in advance, and the pre-collected historical information of patients with vector-borne infectious diseases is stored;

[0169] A data division unit, used for dividing historical information of patients with vector-borne infectious diseases;

[0170] Obtain stored historical information on patients with vector-borne infectious diseases;

[0171] To classify the historical information of patients with vector-borne infectious diseases;

[0172] Determine the training set and test set;

[0173] Model selection unit, used to select the appropriate model architecture;

[0174] According to the prevention and control needs of insect-borne infectious diseases based on smart chips;

[0175] Based on the training set, select the appropriate model architecture;

[0176] Model training unit, used to train the selected model architecture;

[0177] Get the selected model architecture;

[0178] Based on the training set, train the model architecture;

[0179] Determine a neural network model suitable for the prevention and control of vector-borne infectious diseases.

[0180] Among them, the test optimization module is used to perform performance testing and adjustment optimization on the neural network model to determine the best neural network model after adjustment and optimization;

[0181] In this embodiment, as a preferred technical solution of the present invention, the test optimization module includes:

[0182] Model testing unit, used to test neural network models applicable to the prevention and control of vector-borne infectious diseases;

[0183] Obtain neural network models suitable for prevention and control of vector-borne infectious diseases;

[0184] Based on the test set, the neural network model suitable for the prevention and control of vector-borne infectious diseases is tested;

[0185] Determine the test results of the neural network model based on the prevention and control of insect-borne infectious diseases;

[0186] An adjustment and optimization unit, used to adjust and optimize a neural network model suitable for the prevention and control of vector-borne infectious diseases;

[0187] Obtain test results of neural network models based on prevention and control of vector-borne infectious diseases;

[0188] Mining and analyzing the test results of neural network models based on the prevention and control of vector-borne infectious diseases;

[0189] Determine the model adjustment and optimization plan based on the prevention and control of vector-borne infectious diseases;

[0190] Based on the model adjustment and optimization scheme, the neural network model suitable for the prevention and control of vector-borne infectious diseases is adjusted and optimized;

[0191] Determine the best neural network model after adjustment and optimization.

[0192] Among them, the prediction and evaluation module is used to predict and evaluate the patient monitoring characteristic data and determine the patient prediction and evaluation results based on the smart chip;

[0193] In this embodiment, as a preferred technical solution of the present invention, the prediction and evaluation module includes:

[0194] A data extraction unit, used for extracting patient monitoring characteristic data based on the smart chip;

[0195] According to the prevention and control needs of vector-borne infectious diseases based on smart chips, the patient monitoring characteristic data based on smart chips are extracted;

[0196] A prediction and evaluation unit, used for predicting and evaluating the patient monitoring characteristic data based on the smart chip;

[0197] Obtaining extracted patient monitoring feature data based on smart chips;

[0198] Obtain the best neural network model after adjustment and optimization;

[0199] Inputting the patient monitoring characteristic data into the neural network model, and performing prediction and evaluation on the patient monitoring characteristic data based on the neural network model;

[0200] Determine the patient prediction assessment results based on the smart chip.

[0201] Among them, the prevention and control module is used to formulate infectious disease prevention and control plans, and to carry out intelligent prevention and control of vector-borne infectious diseases based on the infectious disease prevention and control plans.

[0202] In this embodiment, as a preferred technical solution of the present invention, the prevention control module includes:

[0203] a strategy development unit to develop plans for the prevention and control of infectious diseases;

[0204] Obtain patient prediction assessment results based on smart chips;

[0205] Mining and analyzing the patient prediction and assessment results based on smart chips;

[0206] Determine the prevention and control plan of infectious diseases based on smart chips;

[0207] Intelligent prevention and control unit, used for intelligent prevention and control of insect-borne infectious diseases;

[0208] Obtain infectious disease prevention and control solutions based on smart chips;

[0209] Intelligent prevention and control of vector-borne infectious diseases based on infectious disease prevention and control plans.

[0210] In this embodiment, as a preferred technical solution of the present invention, intelligent prevention and control of insect-borne infectious diseases is performed based on the infectious disease prevention and control plan, and the following operations are performed:

[0211] When the patient prediction and assessment result based on the smart chip is that the patient has an insect-borne infectious disease, the infectious disease prevention and control plan based on the smart chip is: isolate and treat the patient in a timely manner, focus on checking the places and people the patient has contacted, disinfect the contact places, diagnose the contact people one by one, and fully isolate the insect-borne infectious disease.

[0212] Therefore, by collecting patient consultation data, patient imaging data and patient test data in real time, the real-time patient monitoring data based on the smart chip is determined, and the patient monitoring feature data based on the smart chip is determined by searching, sorting and extracting features of the real-time patient monitoring data based on the smart chip. The patient monitoring feature data is input into a neural network model suitable for the prevention and control of vector-borne infectious diseases. The patient monitoring feature data is predicted and evaluated based on the neural network model to determine the patient prediction and evaluation results based on the smart chip, and an infectious disease prevention and control plan is formulated. Based on the infectious disease prevention and control plan, intelligent prevention and control of vector-borne infectious diseases is carried out, which can timely grasp the situation of vector-borne infectious diseases, effectively prevent and control vector-borne infectious diseases, and improve the prevention and control effect of vector-borne infectious diseases.

[0213] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0214] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A prevention and control system for insect-borne infectious diseases based on smart chips, characterized in that: include: The data acquisition module is used to collect patient consultation data, patient imaging data and patient test data in real time, and determine the real-time patient monitoring data based on the smart chip; A data processing module is used to retrieve, sort and extract features of real-time patient monitoring data based on smart chips, and determine patient monitoring feature data based on smart chips; The model training module is used to train the model architecture and determine the neural network model suitable for the prevention and control of insect-borne infectious diseases; The test optimization module is used to perform performance testing and adjustment and optimization on the neural network model, and determine the best neural network model after adjustment and optimization; A prediction and evaluation module is used to predict and evaluate the patient monitoring characteristic data and determine the patient prediction and evaluation results based on the smart chip; The prevention and control module is used to formulate infectious disease prevention and control plans and to carry out intelligent prevention and control of vector-borne infectious diseases based on the infectious disease prevention and control plans; The data acquisition module comprises: An image acquisition unit is used to acquire the patient's image information in real time and determine the patient's image data based on the smart chip; Image acquisition unit, including: A real-time acquisition unit, used to acquire the patient's image information in real time to obtain the patient's image data; A grayscale image acquisition module, used to perform grayscale processing on the patient image data to obtain a grayscale image corresponding to the patient image data; A gray value extraction module, used to extract the gray value of each pixel block in the patient image data; The image clarity evaluation coefficient acquisition module is used to obtain the image clarity evaluation coefficient by using the clarity coefficient corresponding to the pixel block row included in the length edge and the clarity coefficient corresponding to the pixel block column included in the width edge contained in the patient image data, wherein the image clarity evaluation coefficient is obtained by the following formula: Where G represents the image clarity evaluation coefficient; k represents the number of pixel block rows included on the length edge of the patient image data; r represents the number of pixel block columns included on the width edge of the patient image data; k 01i represents the weight coefficient corresponding to the pixel block row contained in the length edge of the i-th row; k 02i Represents the weight coefficient corresponding to the pixel block column contained on the width edge of the i-th column; s 01i Indicates the clarity coefficient corresponding to the pixel block row contained on the i-th row length edge; s 02i Indicates the clarity coefficient corresponding to the pixel block column contained on the width edge of the i-th column; A comparison module, used for comparing the image clarity evaluation coefficient with a preset clarity evaluation coefficient threshold; A clarity alarm module, used for issuing an abnormal clarity alarm to the patient image data when the image clarity evaluation coefficient is lower than a preset clarity evaluation coefficient threshold; The image clarity evaluation coefficient acquisition module comprises: A pixel block row number extraction module, used to extract the number of pixel block rows contained in the length edge contained in the patient image data; A first grayscale value acquisition module, configured to extract, for each pixel block row included in the length edge included in the patient image data, a grayscale value of each pixel block as a first grayscale value; A first definition coefficient acquisition module, used for acquiring a definition coefficient corresponding to a pixel block row included in a length edge by using the first gray value; A pixel block column number extraction module, used to extract the number of pixel block columns included in the width edge included in the patient image data; A second grayscale value acquisition module, for extracting the grayscale value of each pixel block as a second grayscale value according to the number of pixel block columns included in the width edge included in the patient image data; The second definition coefficient acquisition module is used to use the second gray value to acquire the definition coefficient corresponding to the pixel block column included in the width edge.

2. The insect-borne infectious disease prevention and control system based on smart chip according to claim 1 is characterized in that: The data acquisition module comprises: A medical consultation collection unit is used to collect the patient's medical consultation information in real time and determine the patient's medical consultation data based on the smart chip; The test collection unit is used to collect the patient's test information in real time and determine the patient's test data based on the smart chip; Among them, based on real-time collected patient consultation data, patient imaging data and patient test data; Determine real-time data of patient monitoring based on smart chips.

3. The insect-borne infectious disease prevention and control system based on smart chip according to claim 2 is characterized in that: in, The clarity coefficient corresponding to the pixel block row included in the length edge is obtained by the following formula: Among them, S 01 represents the clarity coefficient corresponding to the pixel block row included in the length edge; n represents the number of pixel blocks included in the pixel block row included in the length edge of the i-th row; S i represents the gray value corresponding to the pixel block on the length of the i-th patient image data; S i-1 represents the gray value corresponding to the pixel block on the length of the i-1th patient image data; S mini S represents the minimum grayscale value corresponding to the pixel block row contained on the length edge of the i-th row; maxi Indicates the maximum grayscale value corresponding to the pixel block row contained on the length edge of the i-th row; The clarity coefficient corresponding to the pixel block column included in the width edge is obtained by the following formula: Where m represents the pixel block column contained on the width edge of the i-th column; S j represents the gray value corresponding to the pixel block on the width of the jth patient image data; S j-1 represents the gray value corresponding to the pixel block on the width of the j-1th patient image data; S minj S represents the minimum grayscale value corresponding to the pixel block row contained on the width edge of the jth column; maxj Indicates the maximum grayscale value corresponding to the pixel block row contained on the j-th column width edge.

4. The insect-borne infectious disease prevention and control system based on smart chip according to claim 3 is characterized in that: The data processing module comprises: A data retrieval unit, used to retrieve real-time data of patient monitoring based on the smart chip; Obtain real-time data of patient monitoring based on smart chips; Based on the sequential retrieval method, the real-time data of patient monitoring based on smart chips are retrieved; Check the consistency of real-time data of patient monitoring based on smart chips; Remove data that is out of the normal range, logically unreasonable or contradictory in the real-time data of patient monitoring based on smart chips; Process invalid and missing values ​​for real-time patient monitoring data based on smart chips; Remove invalid and missing data that are of no value to the prevention and control of vector-borne infectious diseases contained in the real-time patient monitoring data based on smart chips; Identify real-time patient surveillance data that is valuable for the prevention and control of vector-borne infectious diseases; A data sorting unit, used for sorting the retrieved patient monitoring real-time data; Obtain retrieved real-time patient monitoring data that is valuable for the prevention and control of vector-borne infectious diseases; Based on the internal sorting method, the retrieved real-time patient monitoring data that is valuable for the prevention and control of vector-borne infectious diseases is sorted; Determine the real-time patient monitoring data with ranking order; A feature extraction unit, used for extracting features from the sorted patient monitoring real-time data; Acquire sorted and ordered patient monitoring real-time data; Extracting features from the sorted and ordered patient monitoring real-time data; Determine patient monitoring characteristic data based on smart chips.

5. The insect-borne infectious disease prevention and control system based on smart chip according to claim 4 is characterized in that: The model training module includes: A data storage unit, used for storing historical information of patients with insect-borne infectious diseases; According to the prevention and control needs of vector-borne infectious diseases based on smart chips, historical information of patients with vector-borne infectious diseases is collected in advance, and the pre-collected historical information of patients with vector-borne infectious diseases is stored; A data division unit, used for dividing historical information of patients with vector-borne infectious diseases; Obtain stored historical information on patients with vector-borne infectious diseases; To classify the historical information of patients with vector-borne infectious diseases; Determine the training set and test set; A model selection unit, used to select the model architecture; According to the prevention and control needs of insect-borne infectious diseases based on smart chips; Based on the training set, select the model architecture; Model training unit, used to train the selected model architecture; Get the selected model architecture; Based on the training set, train the model architecture; Determine a neural network model suitable for the prevention and control of vector-borne infectious diseases.

6. The insect-borne infectious disease prevention and control system based on smart chip according to claim 5 is characterized in that: The test optimization module includes: Model testing unit, used to test neural network models applicable to the prevention and control of vector-borne infectious diseases; Obtain neural network models suitable for prevention and control of vector-borne infectious diseases; Based on the test set, the neural network model suitable for the prevention and control of vector-borne infectious diseases is tested; Determine the test results of the neural network model based on the prevention and control of insect-borne infectious diseases; An adjustment and optimization unit, used to adjust and optimize a neural network model suitable for the prevention and control of vector-borne infectious diseases; Obtain test results of neural network models based on prevention and control of vector-borne infectious diseases; Mining and analyzing the test results of neural network models based on the prevention and control of vector-borne infectious diseases; Determine the model adjustment and optimization plan based on the prevention and control of vector-borne infectious diseases; Based on the model adjustment and optimization scheme, the neural network model suitable for the prevention and control of vector-borne infectious diseases is adjusted and optimized; Determine the best neural network model after adjustment and optimization.

7. The insect-borne infectious disease prevention and control system based on smart chip according to claim 6 is characterized in that: The prediction and evaluation module comprises: A data extraction unit, used for extracting patient monitoring characteristic data based on the smart chip; According to the prevention and control needs of vector-borne infectious diseases based on smart chips, the patient monitoring characteristic data based on smart chips are extracted; A prediction and evaluation unit, used for predicting and evaluating the patient monitoring characteristic data based on the smart chip; Obtaining extracted patient monitoring feature data based on smart chips; Obtain the best neural network model after adjustment and optimization; Inputting the patient monitoring characteristic data into the neural network model, and performing prediction and evaluation on the patient monitoring characteristic data based on the neural network model; Determine the patient prediction assessment results based on the smart chip.

8. The insect-borne infectious disease prevention and control system based on smart chip according to claim 7 is characterized in that: The prevention control module includes: a strategy development unit to develop plans for the prevention and control of infectious diseases; Obtain patient prediction assessment results based on smart chips; Mining and analyzing the patient prediction and assessment results based on smart chips; Determine the prevention and control plan of infectious diseases based on smart chips; Intelligent prevention and control unit, used for intelligent prevention and control of insect-borne infectious diseases; Obtain infectious disease prevention and control solutions based on smart chips; Intelligent prevention and control of vector-borne infectious diseases based on infectious disease prevention and control plans.

9. The insect-borne infectious disease prevention and control system based on smart chip according to claim 8 is characterized in that: Carry out intelligent prevention and control of vector-borne infectious diseases based on the infectious disease prevention and control plan, and perform the following operations: When the patient prediction and assessment result based on the smart chip is that the patient has an insect-borne infectious disease, the infectious disease prevention and control plan based on the smart chip is: isolate and treat the patient in a timely manner, focus on checking the places and people the patient has contacted, disinfect the contact places, diagnose the contact people one by one, and fully isolate the insect-borne infectious disease.

Images