Multilateral collaborative computing and resource allocation method for online diagnosis of chronic diseases

Abstract

The present invention relates to the technical field of computing resource allocation, and in particular to a multilateral collaborative computing and resource allocation method for online diagnosis of chronic diseases, the method comprising: obtaining, through multilateral collaborative computing, a score table set corresponding to each online diagnosis of each target patient during their current treatment period, as well as their blood pressure data and electrocardiogram data during the current treatment period; performing score distribution analysis and processing based on the local score value sequence corresponding to the target patient; segmenting the local score value sequence, blood pressure data sequence, and electrocardiogram data sequence corresponding to the target patient; correcting the target comprehensive score value; determining the resource allocation priority corresponding to each target patient based on the corrected score value corresponding to each target patient and the distance between each target patient and the hospital, and performing resource allocation based on the resource allocation priority. The present invention realizes online medical resource allocation and improves the rationality of online medical resource allocation.

Description

Technical Field

[0001] The present invention relates to the technical field of computing resource allocation, and in particular to a multilateral collaborative computing and resource allocation method for online diagnosis of chronic diseases. Background Art

[0002] The treatment process for patients with chronic diseases is often lengthy, and monitoring of their progress is often necessary during treatment. To streamline the treatment process and improve efficiency, online diagnosis is often used during treatment. Due to the large number of chronic disease patients and limited online medical resources, hospitals often struggle to provide real-time online diagnosis services for all patients who submit online diagnosis requests. Consequently, there are often many online diagnosis requests from chronic disease patients, meaning that there are many patients requiring online medical resource allocation. Online medical resources often include the medical resources required for online diagnosis, which are computing resources. Currently, a common method for allocating online medical resources to chronic disease patients requiring online resource allocation is to allocate resources based on the time at which these patients submit their online diagnosis requests. This means that the earlier a patient submits an online diagnosis request, the sooner they are allocated online medical resources.

[0003] However, when allocating online medical resources based on online diagnosis application time, the following technical problems often arise:

[0004] The monitoring data abnormalities of different chronic disease patients who send online diagnosis applications are often different, and the urgency of resource allocation for patients with different monitoring data abnormalities is often different. If online medical resources are allocated only based on the time of online diagnosis application, it may lead to the late allocation of online medical resources to some patients with more serious monitoring data abnormalities, resulting in the failure to allocate online medical resources to these patients in a timely manner, and thus resulting in poor rationality of online medical resource allocation. Summary of the Invention

[0005] In order to solve the technical problem of poor rationality in online medical resource allocation, the present invention proposes a multilateral collaborative computing and resource allocation method for online diagnosis of chronic diseases.

[0006] In a first aspect, the present invention provides a multilateral collaborative computing and resource allocation method for online diagnosis of chronic diseases, the method comprising:

[0007] Obtain the score sheet set corresponding to each online diagnosis of each target patient during their current treatment period, as well as their blood pressure data and electrocardiogram data during the current treatment period, and obtain the score sheet set sequence, blood pressure data sequence, and electrocardiogram data sequence corresponding to each target patient;

[0008] Based on the score table set sequence corresponding to each target patient, a local score value sequence is constructed, and score distribution analysis and processing is performed based on the local score value sequence corresponding to each target patient to obtain a target comprehensive score value;

[0009] Segment the local score value sequence corresponding to each target patient to obtain local score value segments;

[0010] Segmenting the blood pressure data sequence and electrocardiogram data sequence corresponding to each target patient according to all local score value segments corresponding to each target patient to obtain blood pressure data segments and electrocardiogram data segments;

[0011] Correcting the target comprehensive score value corresponding to each target patient based on all local score value segments, all blood pressure data segments, and all electrocardiogram data segments corresponding to each target patient to obtain a corrected score value;

[0012] According to the corrected score value corresponding to each target patient and the distance between each target patient and the hospital, the resource allocation priority corresponding to each target patient is determined, and resources are allocated based on the resource allocation priority.

[0013] In combination with the first aspect above, in a possible implementation, constructing a local score value sequence based on a score table set sequence corresponding to each target patient includes:

[0014] Determine any target patient as a marked patient, and form a score value set with the score values ​​corresponding to all score tables in each score table set in the score table set sequence corresponding to the marked patient, to obtain a score value set sequence corresponding to the marked patient;

[0015] The mean of all score values ​​in each score value set in the score value set sequence corresponding to the marked patient is determined as the local score value, so as to obtain the local score value sequence corresponding to the marked patient.

[0016] In conjunction with the first aspect above, in one possible implementation, performing score distribution analysis based on the local score value sequence corresponding to each target patient to obtain a target comprehensive score value includes:

[0017] Determine any target patient as a marked patient, perform linear fitting on the local score value sequence corresponding to the marked patient, and obtain a fitting straight line corresponding to the marked patient;

[0018] Determine an initial comprehensive score value corresponding to the marked patient according to the slope of the fitting line corresponding to the marked patient and the last local score value in the local score value sequence corresponding to the marked patient;

[0019] Determining the consistency of the scores corresponding to the marked patient according to the number of score sheets in each score sheet set in the score sheet set sequence corresponding to the marked patient;

[0020] The target comprehensive score value corresponding to the marked patient is determined based on the initial comprehensive score value and the score consistency corresponding to the marked patient, wherein the initial comprehensive score value and the score consistency are both positively correlated with the target comprehensive score value.

[0021] In combination with the first aspect above, in one possible implementation, determining the initial comprehensive score value corresponding to the marked patient based on the slope of the fitted straight line corresponding to the marked patient and the last local score value in the local score value sequence corresponding to the marked patient includes:

[0022] determining a normalized value of the slope of the fitting line corresponding to the marked patient as a target slope corresponding to the marked patient;

[0023] Determining the last local score value in the local score value sequence corresponding to the marked patient as the most recent score value corresponding to the marked patient;

[0024] The product of the target slope and the most recent score value corresponding to the marked patient is normalized to obtain an initial comprehensive score value corresponding to the marked patient.

[0025] In combination with the first aspect above, in a possible implementation, determining the consistency of the score corresponding to the marked patient according to the number of score tables in each score table set in the sequence of score table sets corresponding to the marked patient includes:

[0026] Determine the number of score sheets in each score sheet set in the score sheet set sequence corresponding to the marked patient as the target representative number, and obtain a target representative number sequence corresponding to the marked patient;

[0027] rounding the mean of all modes in the target representative quantity sequence corresponding to the marked patient to obtain a reference quantity corresponding to the marked patient;

[0028] Determining any one score sheet in the score sheet set sequence corresponding to the marked patient as a marked score sheet, and screening out score sheets of the same type as the marked score sheet from the score sheet set sequence corresponding to the marked patient to form a score sheet group corresponding to the marked score sheet, thereby obtaining a score sheet group corresponding to each score sheet;

[0029] Determine the number of scoring sheets in the scoring sheet group corresponding to each scoring sheet as the number of standards corresponding to each scoring sheet;

[0030] Screening out the largest standard quantity among the reference quantities from the standard quantities corresponding to all the score tables in the score table set sequence corresponding to the marked patient, to form a standard quantity set corresponding to the marked patient;

[0031] If the standard quantity corresponding to the scoring table belongs to the standard quantity set, the scoring table is determined as a commonly used scoring table, and the scoring table set in which the commonly used scoring table exists is determined as a commonly used scoring table set;

[0032] If the standard quantity corresponding to the scoring table does not belong to the standard quantity set, the scoring table is determined to be a special scoring table, and the scoring table set in which all the scoring tables are special scoring tables is determined to be a special scoring table set;

[0033] The score consistency corresponding to the marked patient is determined based on the number of commonly used score table sets in the score table set sequence corresponding to the marked patient, the differences between different commonly used score table sets, and the differences between the commonly used score table sets and the special score table sets.

[0034] In combination with the first aspect above, in a possible implementation, segmenting the local score value sequence corresponding to each target patient to obtain local score value segments includes:

[0035] The APCA algorithm is used to segment the local score value sequence corresponding to each target patient to obtain multiple local score value segments corresponding to each target patient.

[0036] In combination with the first aspect above, in one possible implementation, segmenting the blood pressure data sequence and electrocardiogram data sequence corresponding to each target patient according to all local score value segments corresponding to each target patient to obtain blood pressure data segments and electrocardiogram data segments includes:

[0037] Determine any target patient as a marked patient, and determine the time period corresponding to each local score value segment corresponding to the marked patient as a local time period;

[0038] The blood pressure data of the marked patient corresponding to the blood pressure data sequence whose corresponding collection moments belong to the same local time period are used to form a blood pressure data segment corresponding to the local time period, thereby obtaining a plurality of blood pressure data segments corresponding to the marked patient;

[0039] The ECG data of the ECG data sequence corresponding to the marked patient, whose corresponding collection moments belong to the same local time period, are formed into ECG data segments, thereby obtaining a plurality of ECG data segments corresponding to the marked patient.

[0040] In combination with the first aspect above, in one possible implementation, the target comprehensive score corresponding to each target patient is corrected based on all local score value segments, all blood pressure data segments, and all electrocardiogram data segments corresponding to each target patient to obtain a corrected score value, including:

[0041] Determine any target patient as a marked patient, and determine the average of all local score values ​​in each local score value segment corresponding to the marked patient as the overall score index, to obtain the overall score index sequence corresponding to the marked patient;

[0042] Performing abnormality analysis on each blood pressure data segment to obtain a target blood pressure abnormality factor corresponding to a local time period corresponding to each blood pressure data segment;

[0043] Similarly, each ECG data segment is subjected to abnormal analysis and processing to obtain a target ECG abnormality factor corresponding to a local time period corresponding to each ECG data segment;

[0044] The product of the target blood pressure abnormality factor and the target electrocardiogram abnormality factor corresponding to each local time period is determined as the target overall abnormality factor corresponding to each local time period;

[0045] The target overall abnormality factors corresponding to all local time periods corresponding to the marked patient are used to form a target overall abnormality factor sequence corresponding to the marked patient;

[0046] Normalizing the Pearson correlation coefficient between the target overall abnormality factor sequence and the overall scoring index sequence corresponding to the marked patient to obtain the target similarity corresponding to the marked patient;

[0047] The product of the target similarity and the target comprehensive score corresponding to the marked patient is normalized to obtain a revised score corresponding to the marked patient.

[0048] In conjunction with the first aspect above, in one possible implementation, performing abnormality analysis on each blood pressure data segment to obtain a target blood pressure abnormality factor corresponding to a local time period corresponding to each blood pressure data segment includes:

[0049] Performing blood pressure abnormality detection on each blood pressure data segment to obtain abnormal blood pressure data, and forming abnormal blood pressure data sub-segments from continuous abnormal blood pressure data within each blood pressure data segment;

[0050] Clustering all abnormal blood pressure data sub-segments within each blood pressure data segment to obtain abnormal blood pressure clusters, and selecting the abnormal blood pressure cluster with the largest total duration from all abnormal blood pressure clusters corresponding to each blood pressure data segment as the target abnormal blood pressure cluster corresponding to each blood pressure data segment;

[0051] According to the total number of all abnormal blood pressure data in each blood pressure data segment and the number of abnormal blood pressure data in its corresponding target abnormal blood pressure cluster, the target blood pressure abnormality factor corresponding to the local time period corresponding to each blood pressure data segment is determined.

[0052] In conjunction with the first aspect above, in one possible implementation, determining the resource allocation priority corresponding to each target patient based on the modified score corresponding to each target patient and the distance between each target patient and the hospital includes:

[0053] Determine any target patient as a marked patient, classify each hospital into different levels, and obtain the target level corresponding to each hospital;

[0054] Screening out the hospital closest to the address of the marked patient from all hospitals corresponding to each target level as the reference hospital for the marked patient at each target level;

[0055] Determine the distance between the reference hospital of the marked patient at each target level and the address of the marked patient as the marked distance of the marked patient at each target level;

[0056] Determine the richness of offline medical resources corresponding to the marked patient according to the marked distance of the marked patient at all target levels, wherein the marked distance is negatively correlated with the richness of offline medical resources;

[0057] The resource allocation priority corresponding to the marked patient is determined based on the offline medical resource richness and the revised score value corresponding to the marked patient, wherein the offline medical resource richness is negatively correlated with the resource allocation priority, and the revised score value is positively correlated with the resource allocation priority.

[0058] In a second aspect, the present invention provides a multilateral collaborative computing and resource allocation system for online diagnosis of chronic diseases, the system comprising:

[0059] The data acquisition module is used to obtain the score table set corresponding to each online diagnosis of each target patient during the current treatment period, as well as the blood pressure data and electrocardiogram data of the target patient during the current treatment period, and obtain the score table set sequence, blood pressure data sequence and electrocardiogram data sequence corresponding to each target patient;

[0060] A construction and processing module is used to construct a local score value sequence based on the score table set sequence corresponding to each target patient, and perform score distribution analysis and processing based on the local score value sequence corresponding to each target patient to obtain a target comprehensive score value;

[0061] A score value segmentation module is used to segment the local score value sequence corresponding to each target patient to obtain local score value segments;

[0062] A data sequence segmentation module is used to segment the blood pressure data sequence and electrocardiogram data sequence corresponding to each target patient according to all local score value segments corresponding to each target patient to obtain blood pressure data segments and electrocardiogram data segments;

[0063] A score correction module is used to correct the target comprehensive score value corresponding to each target patient based on all local score value segments, all blood pressure data segments and all electrocardiogram data segments corresponding to each target patient to obtain a corrected score value;

[0064] The determination and resource allocation module is used to determine the resource allocation priority corresponding to each target patient based on the corrected score value corresponding to each target patient and the distance between each target patient and the hospital, and to allocate resources based on the resource allocation priority.

[0065] In a third aspect, a server is provided, comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to call and execute the executable program code from the memory, so that the device executes the method of the first aspect or any possible implementation of the first aspect.

[0066] In a fourth aspect, a computer program product is provided, comprising: a computer program code, which, when executed on a computer, enables the computer to execute the method in the first aspect or any possible implementation of the first aspect.

[0067] In a fifth aspect, a computer-readable storage medium is provided, which stores a computer program code. When the computer program code runs on a computer, the computer executes the method in the above-mentioned first aspect or any possible implementation of the first aspect.

[0068] The present invention has the following beneficial effects:

[0069] The multilateral collaborative computing and resource allocation method for online diagnosis of chronic diseases of the present invention realizes online medical resource allocation, solves the technical problem of poor rationality of online medical resource allocation, and improves the rationality of online medical resource allocation. Specifically, when performing online medical resource allocation, the present invention comprehensively considers a set of scoring tables that characterize the abnormal conditions of monitoring data at the diagnosis time corresponding to different online diagnoses, and analyzes the scoring table set sequence, blood pressure data sequence, and electrocardiogram data sequence, thereby adaptively quantifying the resource allocation priority corresponding to each target patient. Ultimately, resource allocation is achieved based on the resource allocation priority, and the rationality of online medical resource allocation is improved to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. 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 paying any creative work.

[0071] Figure 1 This is a flow chart of a multilateral collaborative computing and resource allocation method for online diagnosis of chronic diseases according to the present invention;

[0072] Figure 2 This is a schematic diagram of the structure of a multilateral collaborative computing and resource allocation system for online diagnosis of chronic diseases according to the present invention;

[0073] Figure 3 The figure is a structural diagram of a computer device of the present invention. DETAILED DESCRIPTION

[0074] To further illustrate the technical means and effects employed by the present invention to achieve its intended objectives, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementations, structures, features, and effects of the technical solutions proposed by the present invention. In the following description, references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0075] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0076] The multilateral collaborative computing and resource allocation method for online diagnosis of chronic diseases is a method that integrates cloud computing, edge computing, the Internet of Things, and other technologies to provide health management services for patients with chronic diseases. It aims to improve the efficiency and accuracy of online diagnosis of chronic diseases through multilateral collaborative computing, while optimizing resource allocation. Multilateral collaborative computing primarily integrates data resources from different platforms to achieve interconnection and efficient sharing of information. The data used in this invention often comes from different platforms, thus achieving multilateral collaborative computing to a certain extent.

[0077] refer to Figure 1 , shows the process of some embodiments of a multilateral collaborative computing and resource allocation method for online diagnosis of chronic diseases according to the present invention. The multilateral collaborative computing and resource allocation method for online diagnosis of chronic diseases includes the following steps:

[0078] Step S1, obtain the score table set corresponding to each online diagnosis of each target patient during his / her current treatment period, as well as the blood pressure data and electrocardiogram data during his / her current treatment period, and obtain the score table set sequence, blood pressure data sequence and electrocardiogram data sequence corresponding to each target patient.

[0079] The target patient may be a chronic disease patient who has submitted an online diagnosis application at the current moment and has not been allocated online medical resources. For example, the chronic disease patient may be a patient with coronary heart disease. The current treatment time period of the target patient may be the time period corresponding to the treatment process of the target patient with the current moment as the end moment, that is, it can represent the process in which the target patient is undergoing chronic disease treatment. Online diagnosis can be a doctor's diagnosis of the disease online. For example, online diagnosis can be achieved through a video call between the patient and the doctor. In actual situations, the more severe the patient's condition is, the more abnormal the corresponding monitoring data is. Since the scoring table is mainly used to assess the severity of the patient's condition and the prognostic risk, the scoring table can, to a certain extent, represent the abnormality of the monitoring data. Therefore, the scoring table set corresponding to the online diagnosis can include the scoring table used by the doctor when performing the online diagnosis, which can represent the abnormality of the monitoring data at the diagnosis time corresponding to the online diagnosis. For example, scoring tables may include, but are not limited to, the GRACE (Global Registry of Acute Coronary Events) scoring table, the TIMI (Thrombolysis In Myocardial Infarction) scoring table, and the SYNTAX (Synergy between PCI with TAXUS and Cardiac Surgery) scoring table. Blood pressure data can represent a patient's blood pressure and may be normalized data. For example, blood pressure data can be represented by the normalized sum of the patient's systolic and diastolic blood pressures at the same moment. Electrocardiogram (ECG) data can represent cardiac activity and is typically presented in numerical form. For example, ECG data can be represented by the normalized sum of the patient's P wave (atrial depolarization), QRS wave (ventricular depolarization), and T wave (ventricular repolarization) values ​​at the same moment. The P wave value, QRS wave value, and T wave value can be numerical values ​​converted from the P wave, QRS wave, and T wave, respectively. The P wave represents atrial depolarization and is typically associated with atrial contraction. The QRS wave represents ventricular depolarization and is the most prominent part of the electrocardiogram, usually associated with ventricular contraction. The T wave represents ventricular repolarization and is usually associated with ventricular relaxation.

[0080] As an example, this step may include the following steps:

[0081] The first step is to obtain the score table set corresponding to each online diagnosis of each target patient during his / her current treatment period, and obtain the score table set sequence corresponding to each target patient.

[0082] For example, during the current treatment period of a target patient, the score sheets used in the online diagnosis completed by the target patient can be collected to form a score sheet set corresponding to the online diagnosis. The score sheet sets corresponding to all online diagnoses of the target patient during the current treatment period can also be combined to form a score sheet set sequence. The score sheet set sequence is a time series.

[0083] It's important to note that the same chronic disease patient may receive online diagnoses from different doctors in different hospitals during their long-term treatment. The types and number of scoring tables used by different doctors during online diagnoses often vary. For example, one doctor may use two scoring tables, while another may use three. Even if different doctors use the same number of scoring tables, the types of scoring tables may vary. Therefore, obtaining a collection of scoring tables corresponding to different online diagnoses can facilitate subsequent data integration and analysis, thereby facilitating the allocation of online medical resources.

[0084] The second step is to obtain the blood pressure data and electrocardiogram data of each target patient during the current treatment period, and obtain the blood pressure data sequence and electrocardiogram data sequence corresponding to each target patient.

[0085] For example, a blood pressure monitoring bracelet and a smartwatch can be used to collect blood pressure data and electrocardiogram (ECG) data from a target patient during their current treatment period. All blood pressure data collected during the current treatment period can be combined into a blood pressure data sequence, and all ECG data collected during the current treatment period can be combined into an ECG data sequence. The blood pressure data sequence and the ECG data sequence are time series.

[0086] Step S2: construct a local score value sequence based on the score table set sequence corresponding to each target patient, and perform score distribution analysis based on the local score value sequence corresponding to each target patient to obtain a target comprehensive score value.

[0087] As an example, this step may include the following steps:

[0088] In the first step, any target patient is determined as a marked patient, and the score values ​​corresponding to all score tables in each score table set in the score table set sequence corresponding to the marked patient are combined into a score value set to obtain the score value set sequence corresponding to the marked patient.

[0089] The score value corresponding to the score table may be a numerical value calculated using the score table. A larger value tends to indicate that the patient's condition may be more serious, and that the patient's monitoring data may be more abnormal.

[0090] It should be noted that the scoring value sets in the scoring value set sequence may correspond one-to-one to the scoring table sets in the scoring table set sequence.

[0091] In the second step, the mean of all score values ​​in each score value set in the score value set sequence corresponding to the marked patient is determined as the local score value, thereby obtaining the local score value sequence corresponding to the marked patient.

[0092] It should be noted that the local scoring values ​​in the local scoring value sequence may correspond one-to-one to the scoring table sets in the scoring table set sequence.

[0093] In the third step, any target patient is determined as a marked patient, and a linear fitting is performed on the local score value sequence corresponding to the marked patient to obtain a fitting straight line corresponding to the marked patient.

[0094] For example, a scatter plot is constructed with the serial number of the local score value in the local score value sequence as the horizontal axis and the local score value in the local score value sequence corresponding to the marked patient as the vertical axis, and a straight line is fitted to the scatter plot to obtain a fitting straight line corresponding to the marked patient.

[0095] The fourth step, based on the slope of the fitted straight line corresponding to the marked patient and the last local score value in the local score value sequence corresponding to the marked patient, determines the initial comprehensive score value corresponding to the marked patient, which may include the following sub-steps:

[0096] In the first sub-step, the normalized value of the slope of the fitting line corresponding to the marked patient is determined as the target slope corresponding to the marked patient.

[0097] In the second sub-step, the last local score value in the local score value sequence corresponding to the marked patient is determined as the most recent score value corresponding to the marked patient.

[0098] It should be noted that the last local score value in the local score value sequence corresponding to the marked patient can often represent the abnormality of the monitoring data obtained during the most recent online diagnosis of the marked patient.

[0099] The third sub-step is to normalize the product of the target slope corresponding to the marked patient and the most recent score value to obtain the initial comprehensive score value corresponding to the marked patient.

[0100] For example, the formula for determining the initial comprehensive score corresponding to the marked patient can be:

[0101] ; Where P is the initial comprehensive score value corresponding to the marked patient. is the normalization function. k is the target slope corresponding to the marked patient. A is the recent score value corresponding to the marked patient.

[0102] It should be noted that when k is larger, it often indicates that the score representing the disease risk during the marked patient's current treatment period is showing an increasing trend, which often indicates that the marked patient's condition is more likely to worsen, which often indicates that the monitoring data of the marked patient who submitted the online diagnosis application is relatively more abnormal, which often indicates that online medical resources need to be allocated to the marked patient more quickly. When A is larger, it often indicates that the score representing the disease risk of the most recent online diagnosis during the marked patient's current treatment period is higher, which often indicates that the marked patient's condition is more likely to worsen at this stage, which often indicates that the monitoring data of the marked patient who submitted the online diagnosis application is relatively more abnormal. Therefore, when P is larger, it often indicates that online medical resources need to be allocated to the marked patient more quickly.

[0103] The fifth step, based on the number of score sheets in each score sheet set in the score sheet set sequence corresponding to the marked patient, determines the consistency of the scores corresponding to the marked patient, which may include the following sub-steps:

[0104] In the first sub-step, the number of score sheets in each score sheet set in the score sheet set sequence corresponding to the marked patient is determined as the target representative number, thereby obtaining a target representative number sequence corresponding to the marked patient.

[0105] The target representative quantity in the target representative quantity sequence may correspond one-to-one to the score table set in the score table set sequence.

[0106] The second sub-step is to round the mean of all modes in the target representative quantity sequence corresponding to the above-mentioned marked patients to obtain the reference quantity corresponding to the above-mentioned marked patients.

[0107] It should be noted that there are often multiple or single modes in a set of data. Therefore, there may be multiple or single modes in the target representative quantity sequence. Therefore, the embodiment of the present invention performs mean calculation when using the mode in the target representative quantity sequence.

[0108] In the third sub-step, any one score sheet in the score sheet set sequence corresponding to the marked patient is determined as the marked score sheet, and score sheets of the same type as the marked score sheet are screened out from the score sheet set sequence corresponding to the marked patient to form a score sheet group corresponding to the marked score sheet, thereby obtaining a score sheet group corresponding to each score sheet.

[0109] For example, if the score table set sequence corresponding to the marked patient includes 4 score table sets, these 4 score table sets are: {first GRACE score table, first TIMI score table, first SYNTAX score table}, {second GRACE score table, second TIMI score table}, {third TIMI score table, third SYNTAX score table}, {fourth GRACE score table, fourth TIMI score table, fourth SYNTAX score table}, and the marked score table is the second GRACE score table, then the score table group corresponding to the second GRACE score table can include: all score table sets containing GRACE score tables in the score table set sequence, so the score table group corresponding to the second GRACE score table can be {first GRACE score table, second GRACE score table, fourth GRACE score table}.

[0110] In the fourth sub-step, the number of scoring sheets in the scoring sheet group corresponding to each scoring sheet is determined as the standard number corresponding to each scoring sheet.

[0111] It should be noted that in the set of scoring tables corresponding to the marked patient, the number of standards corresponding to the same type of scoring table is often the same. In the set of scoring tables corresponding to the marked patient, the number of standards corresponding to all scoring tables is often one-to-one corresponding to the type of scoring table, that is, one scoring table often corresponds to one number of standards.

[0112] The fifth sub-step is to select the largest standard quantity in the reference quantity from the standard quantities corresponding to all the score tables in the score table set sequence corresponding to the marked patient, to form the standard quantity set corresponding to the marked patient.

[0113] For example, the different standard quantities corresponding to all score sheets in the score sheet set sequence corresponding to the marked patient can be sorted in descending order, and the sequence obtained at this time can be recorded as a simplified score sequence, and the first reference quantity standard quantities in the simplified score sequence can be used to form a standard quantity set.

[0114] In the sixth sub-step, if the standard quantity corresponding to the scoring table belongs to the above standard quantity set, the scoring table is determined as a commonly used scoring table, and the scoring table set containing the commonly used scoring tables is determined as a commonly used scoring table set.

[0115] Among them, there are commonly used scoring tables in the commonly used scoring table set.

[0116] It should be noted that the scoring tables in the commonly used scoring table set are often scoring tables used in most online diagnoses.

[0117] In the seventh sub-step, if the standard quantity corresponding to the scoring table does not belong to the above standard quantity set, the scoring table is determined to be a special scoring table, and the scoring table set in which all the scoring tables are special scoring tables is determined to be a special scoring table set.

[0118] Among them, there are no commonly used scoring tables in the special scoring table set.

[0119] It should be noted that the scoring tables in the special scoring table set are often scoring tables that are rarely used in online diagnosis.

[0120] The eighth sub-step is to determine the consistency of the scores corresponding to the marked patients based on the number of commonly used score table sets in the score table set sequence corresponding to the marked patients, the differences between different commonly used score table sets, and the differences between the commonly used score table sets and the special score table sets.

[0121] For example, the formula for determining the consistency of the scores corresponding to the marked patients can be:

[0122] ;

[0123] ;

[0124] ;

[0125] Where L is the score consistency corresponding to the marked patient. S is the number of score table sets in the score table set sequence corresponding to the marked patient. n is the number of commonly used score table sets in the score table set sequence corresponding to the marked patient. is a natural exponential function. B represents the mean difference between different commonly used score sets in the score set sequence corresponding to the marked patient. C represents the mean difference between the commonly used score set and the special score set in the score set sequence corresponding to the marked patient. i is the index of the commonly used score set in the score set sequence corresponding to the marked patient. Represents the difference between the i-th commonly used rating table set and the i+1-th commonly used rating table set. It is the number of commonly used scoring tables in the union of the i-th commonly used scoring table set and the i+1-th commonly used scoring table set in the scoring table set sequence corresponding to the marked patient. is the number of common scoring tables in the intersection of the i-th common scoring table set and the i+1-th common scoring table set in the scoring table set sequence corresponding to the marked patient. N is the number of special scoring table sets in the scoring table set sequence corresponding to the marked patient. j is the index of the special scoring table set in the scoring table set sequence corresponding to the marked patient. Represents the difference between the i-th common rating table set and the j-th special rating table set. It is the number of score tables in the union of the i-th common score table set and the j-th special score table set in the score table set sequence corresponding to the marked patient. It is the number of score tables in the intersection of the i-th common score table set and the j-th special score table set in the score table set sequence corresponding to the marked patient.

[0126] It should be noted that when A larger value indicates that there are more commonly used scoring tables corresponding to the marked patient, which often indicates that the scoring table types used in different online diagnoses for the marked patient are relatively consistent. When B is smaller, it often indicates that the different commonly used scoring tables corresponding to the marked patient are more similar to each other, which often indicates that the content of the different commonly used scoring tables used in online diagnoses for the marked patient is relatively similar, which often indicates that the commonly used disease analysis directions for the marked patient are relatively consistent. When C is smaller, it often indicates that the commonly used scoring table sets corresponding to the marked patient are more similar to the special scoring table sets, which often indicates that the content of the commonly used scoring tables and special scoring tables used in online diagnoses for the marked patient is relatively similar, which often indicates that the disease analysis directions reflected in the commonly used scoring tables and special scoring tables for the marked patient are relatively consistent. Therefore, when L is larger, it often indicates that the scoring table types used in different online diagnoses for the marked patient are relatively uniform, which often indicates that the scoring criteria used in different online diagnoses for the marked patient are more similar, which often indicates that the sequence of scoring table sets corresponding to the marked patient is more meaningful for reference.

[0127] Step 6: Determine the target comprehensive score value corresponding to the marked patient based on the initial comprehensive score value and score consistency corresponding to the marked patient.

[0128] Among them, the initial comprehensive score value and score consistency can be positively correlated with the target comprehensive score value.

[0129] For example, the formula for determining the target comprehensive score corresponding to the marked patient can be:

[0130] ;in, is the target comprehensive score value corresponding to the marked patient. is the normalization function. P is the initial comprehensive score corresponding to the marked patient. L is the score consistency corresponding to the marked patient.

[0131] It should be noted that when P is larger, it often means that online medical resources need to be allocated to marked patients more quickly. L can be used as the weight of P, that is, L can be used to modify P. When L is larger, it often means that the scoring table types used in different online diagnoses for marked patients are relatively more unified, and the scoring standards used in different online diagnoses for marked patients are more similar, and the scoring table set sequence corresponding to the marked patients is more meaningful for reference. Therefore, when The larger it is, the more likely it is that online medical resources need to be allocated to marked patients more quickly.

[0132] Step S3: segment the local score value sequence corresponding to each target patient to obtain local score value segments.

[0133] As an example, the APCA (Adaptive Piecewise Constant Approximation) algorithm can be used to segment the local score value sequence corresponding to each target patient to obtain multiple local score value segments corresponding to each target patient. A local score value segment is a segment of the local score value sequence.

[0134] It should be noted that the elements in the same segment obtained by segmentation using the APCA algorithm are often similar.

[0135] Step S4: segmenting the blood pressure data sequence and electrocardiogram data sequence corresponding to each target patient according to all local score value segments corresponding to each target patient to obtain blood pressure data segments and electrocardiogram data segments.

[0136] As an example, this step may include the following steps:

[0137] In the first step, any target patient is determined as a marked patient, and the time period corresponding to each local score value segment corresponding to the marked patient is determined as a local time period.

[0138] It should be noted that the local scoring values ​​in the local scoring value sequence can correspond one-to-one with the scoring table set in the scoring table set sequence. The scoring table set in the scoring table set sequence can correspond one-to-one with the online diagnosis. Therefore, the local scoring values ​​in the local scoring value sequence can correspond one-to-one with the online diagnosis.

[0139] The start time of the time period corresponding to the local score value segment may be the start time of the online diagnosis corresponding to the first local score value in the local score value segment, and the end time of the time period corresponding to the local score value segment may be the end time of the online diagnosis corresponding to the last local score value in the local score value segment.

[0140] In the second step, the blood pressure data corresponding to the marked patient's blood pressure data sequence and the corresponding blood pressure data collected at the same local time period are combined to form a blood pressure data segment corresponding to the local time period, thereby obtaining multiple blood pressure data segments corresponding to the marked patient.

[0141] In the third step, the ECG data sequences corresponding to the marked patients, whose corresponding collection moments belong to the same local time period, are grouped into ECG data segments to obtain multiple ECG data segments corresponding to the marked patients.

[0142] Step S5: Correcting the target comprehensive score value corresponding to each target patient based on all local score value segments, all blood pressure data segments, and all electrocardiogram data segments corresponding to each target patient to obtain a corrected score value.

[0143] As an example, this step may include the following steps:

[0144] In the first step, any target patient is determined as a marked patient, and the mean of all local score values ​​in each local score value segment corresponding to the marked patient is determined as the overall score index to obtain the overall score index sequence corresponding to the marked patient.

[0145] The second step is to perform abnormal analysis on each blood pressure data segment to obtain the target blood pressure abnormality factor corresponding to the local time period corresponding to each blood pressure data segment, which may include the following sub-steps:

[0146] In the first sub-step, blood pressure abnormality detection is performed on each blood pressure data segment to obtain abnormal blood pressure data, and continuous abnormal blood pressure data in each blood pressure data segment constitute an abnormal blood pressure data sub-segment.

[0147] It's important to note that high blood pressure can affect vascular tolerance, potentially leading to the onset of chronic diseases. For example, high blood pressure often leads to coronary heart disease. Therefore, abnormal blood pressure data can often be screened based on a threshold, with blood pressure data exceeding the threshold considered abnormal.

[0148] In the second sub-step, all abnormal blood pressure data sub-segments in each blood pressure data segment are clustered to obtain abnormal blood pressure clusters, and the abnormal blood pressure cluster with the largest total duration is selected from all abnormal blood pressure clusters corresponding to each blood pressure data segment as the target abnormal blood pressure cluster corresponding to each blood pressure data segment.

[0149] The total duration corresponding to the abnormal blood pressure cluster may be equal to the sum of the durations corresponding to all abnormal blood pressure data subsegments within the abnormal blood pressure cluster.

[0150] For example, the duration between the start times of every two abnormal blood pressure data sub-segments in the blood pressure data segment can be used as the clustering distance, and all abnormal blood pressure data sub-segments in the blood pressure data segment can be clustered using the K-means clustering algorithm. The cluster cluster obtained by clustering at this time is used as the abnormal blood pressure cluster, where the K value in the K-means clustering algorithm can be obtained by the elbow method.

[0151] The third sub-step is to determine the target blood pressure abnormality factor corresponding to the local time period corresponding to each blood pressure data segment based on the total number of all abnormal blood pressure data in each blood pressure data segment and the number of abnormal blood pressure data in its corresponding target abnormal blood pressure cluster.

[0152] For example, the formula for determining the target blood pressure abnormality factor corresponding to the local time period corresponding to the blood pressure data segment can be:

[0153] ; Wherein, Q is the target blood pressure abnormality factor corresponding to the local time period corresponding to the blood pressure data segment. is the total number of all abnormal blood pressure data in the blood pressure data segment. q is the number of blood pressure data in the blood pressure data segment. is the number of abnormal blood pressure data in the target abnormal blood pressure cluster corresponding to the blood pressure data segment.

[0154] It should be noted that when When the value is larger, it often means that there are more abnormal blood pressure data in the blood pressure data segment, which often means that the blood pressure data segment is relatively more abnormal. The larger Q is, the more abnormal blood pressure data in the blood pressure data segment is concentrated, and the more persistent the abnormal blood pressure in the blood pressure data segment is. Therefore, the larger Q is, the more abnormal the blood pressure data segment is.

[0155] In the third step, similarly, each ECG data segment is subjected to abnormal analysis and processing to obtain a target ECG abnormality factor corresponding to a local time period corresponding to each ECG data segment.

[0156] It should be noted that the method for obtaining the target ECG abnormality factor corresponding to the local time period can be the same as the method for obtaining the target blood pressure abnormality factor corresponding to the local time period. Specifically, the ECG data segment can be regarded as the blood pressure data segment, and the target blood pressure abnormality factor obtained at this time is the target ECG abnormality factor.

[0157] In the fourth step, the product of the target blood pressure abnormality factor and the target electrocardiogram abnormality factor corresponding to each local time period is determined as the target overall abnormality factor corresponding to each local time period.

[0158] For example, the formula for determining the target overall anomaly factor corresponding to a local time period can be:

[0159] ;in, is the target overall abnormality factor corresponding to the ath local time segment corresponding to the marked patient. a is the sequence number of the local time segment corresponding to the marked patient. is the target blood pressure abnormality factor corresponding to the a-th local time period corresponding to the marked patient. It is the target ECG abnormality factor corresponding to the a-th local time period corresponding to the marked patient.

[0160] It should be noted that when The larger the value is, the more abnormal the blood pressure data in the ath local time period corresponding to the marked patient is. The larger the value is, the more abnormal the ECG data in the ath local time period corresponding to the marked patient is. The larger the value is, the more abnormal the blood pressure data and electrocardiogram data of the marked patient in the a-th local time period are, and the more abnormal the body monitoring data of the marked patient in the a-th local time period are.

[0161] The fifth step is to construct a target overall abnormality factor sequence corresponding to the above-mentioned marked patient by combining the target overall abnormality factors corresponding to all local time periods corresponding to the above-mentioned marked patient.

[0162] In the sixth step, the Pearson correlation coefficient between the target overall abnormality factor sequence and the overall scoring index sequence corresponding to the above-mentioned marked patients is normalized to obtain the target similarity corresponding to the above-mentioned marked patients.

[0163] It should be noted that the target overall abnormality factor sequence corresponding to the marked patient can represent the physical abnormality of the marked patient during his or her current treatment period. The overall scoring index sequence corresponding to the marked patient can represent the disease risk assessment of the marked patient during his or her current treatment period. Therefore, when the target similarity corresponding to the marked patient is greater, it often means that the target overall abnormality factor sequence and the overall scoring index sequence corresponding to the marked patient are more similar, and it often means that during the marked patient's current treatment period, the changes in the scoring results of different online diagnoses are more consistent with the changes in patient monitoring data, and it often means that the scoring tables used for different online diagnoses are more credible, and it often means that the target comprehensive scoring value calculated previously can better represent the urgency of online medical resource allocation.

[0164] In the seventh step, the product of the target similarity and the target comprehensive score corresponding to the above-mentioned marked patient is normalized to obtain the corrected score corresponding to the above-mentioned marked patient.

[0165] For example, the formula for determining the corrected score value corresponding to the marked patient can be:

[0166] ;in, is the corrected score value corresponding to the marked patient. is the normalization function. G is the target similarity corresponding to the labeled patient. is the target comprehensive score value corresponding to the marked patient.

[0167] It should be noted that when The larger the value, the more likely it is that online medical resources need to be allocated to marked patients more quickly. G can be used as The larger the G, the more similar the target overall abnormality factor sequence and the overall score index sequence corresponding to the marked patient are. This often indicates that during the marked patient's current treatment period, the score changes of different online diagnoses are more consistent with the changes in patient monitoring data. This often indicates that the score tables used for different online diagnoses are more credible. This often indicates that the target comprehensive score value calculated previously can better represent the urgency of online medical resource allocation. Therefore, when The larger it is, the more likely it is that online medical resources need to be allocated to marked patients more quickly.

[0168] Step S6: Determine the resource allocation priority corresponding to each target patient according to the corrected score value corresponding to each target patient and the distance between each target patient and the hospital, and perform resource allocation based on the resource allocation priority.

[0169] As an example, this step may include the following steps:

[0170] In the first step, any target patient is identified as a marked patient, and each hospital is graded to obtain the target grade corresponding to each hospital.

[0171] Among them, the target level corresponding to the hospital can represent the richness of the hospital's medical resources related to chronic diseases. The larger the value, the richer the medical resources related to chronic diseases, and the target level can be expressed in a numerical value.

[0172] For example, hospitals can be divided into tertiary, secondary, and primary hospitals. The target level for tertiary hospitals can be higher than that for secondary hospitals, and the target level for secondary hospitals can be higher than that for primary hospitals. For example, the target level for tertiary hospitals can be set to 3, the target level for secondary hospitals can be set to 2, and the target level for primary hospitals can be set to 1. Tertiary hospitals, also known as Class A hospitals, are hospitals with the strongest medical service capabilities, typically possessing strong scientific research, teaching, and treatment capabilities, and capable of providing highly specialized and complex medical services. Secondary hospitals have stronger medical service capabilities, but are smaller in scale than tertiary hospitals and handle less complex cases. Primary hospitals are basic hospitals, primarily responsible for the diagnosis and treatment of common and frequently occurring diseases at the grassroots level, and have relatively weak technical capabilities.

[0173] In the second step, the hospital closest to the address of the marked patient is selected from all hospitals corresponding to each target level as the reference hospital for the marked patient at each target level.

[0174] Among them, if any target level is determined as a marked level, the hospital corresponding to the marked level may be a hospital whose corresponding target level is the marked level.

[0175] The third step is to determine the distance between the reference hospital of the marked patient at each target level and the address of the marked patient as the marked distance of the marked patient at each target level.

[0176] The fourth step is to determine the richness of offline medical resources corresponding to the marked patients based on the marked distances of the marked patients at all target levels.

[0177] Among them, the marking distance can be negatively correlated with the richness of offline medical resources.

[0178] For example, the formula for determining the richness of offline medical resources corresponding to the marked patient can be:

[0179] Where D is the richness of offline medical resources corresponding to the marked patient. F is the total number of categories at the target level. h is the category number of the target level. It is the hth target level. is the marking distance of the marked patient at the hth target level.

[0180] It should be noted that when The larger it is, the more abundant the medical resources of the corresponding hospital are. The smaller the value, the smaller the distance between the marked patient and the corresponding hospital. Therefore, when D is larger, it often means that the medical resources near the marked patient's residence are relatively abundant.

[0181] The fifth step is to determine the resource allocation priority corresponding to the above-marked patients based on the offline medical resource richness and revised score value corresponding to the above-marked patients.

[0182] Among them, the richness of offline medical resources can be negatively correlated with the priority of resource allocation, and the modified score value can be positively correlated with the priority of resource allocation.

[0183] For example, the formula for determining the resource allocation priority corresponding to the marked patient can be:

[0184] ;in, It is the resource allocation priority corresponding to the marked patient. is the normalization function. is the corrected score value corresponding to the marked patient. D is the richness of offline medical resources corresponding to the marked patient.

[0185] It should be noted that when The larger it is, the more likely it is that online medical resources need to be allocated to marked patients more quickly. Can be used as When D is larger, it often means that the medical resources near the marked patient's residence are relatively abundant, and it often means that the marked patient is more likely to choose to go to an offline hospital for examination. The larger it is, the more likely it is that online medical resources need to be allocated to marked patients more quickly.

[0186] Step 6: Allocate resources based on resource allocation priorities.

[0187] For example, all target patients may be sorted in descending order based on the resource allocation priorities corresponding to all target patients, and online diagnosis resources may be allocated to the target patients in sequence according to the order of the target patients.

[0188] It should be noted that the higher the resource allocation priority, the more necessary it is to arrange online diagnosis for target patients in a timely manner.

[0189] refer to Figure 2 Based on the same inventive concept as the above method embodiment, the present invention provides a multilateral collaborative computing and resource allocation system for online diagnosis of chronic diseases. The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of a multilateral collaborative computing and resource allocation method for online diagnosis of chronic diseases may include:

[0190] Data acquisition module 201 is used to obtain the score table set corresponding to each online diagnosis of each target patient during the current treatment period, as well as the blood pressure data and electrocardiogram data of the target patient during the current treatment period, to obtain the score table set sequence, blood pressure data sequence, and electrocardiogram data sequence corresponding to each target patient;

[0191] The construction and processing module 202 is used to construct a local score value sequence based on the score table set sequence corresponding to each target patient, and perform score distribution analysis and processing based on the local score value sequence corresponding to each target patient to obtain a target comprehensive score value;

[0192] The score value segmentation module 203 is used to segment the local score value sequence corresponding to each target patient to obtain local score value segments;

[0193] The data sequence segmentation module 204 is configured to segment the blood pressure data sequence and the electrocardiogram data sequence corresponding to each target patient according to all the local score value segments corresponding to each target patient, thereby obtaining blood pressure data segments and electrocardiogram data segments;

[0194] The score correction module 205 is used to correct the target comprehensive score value corresponding to each target patient based on all local score value segments, all blood pressure data segments, and all ECG data segments corresponding to each target patient to obtain a corrected score value;

[0195] The determination and resource allocation module 206 is used to determine the resource allocation priority corresponding to each target patient according to the modified score value corresponding to each target patient and the distance between each target patient and the hospital, and to allocate resources based on the resource allocation priority.

[0196] Figure 3 FIG. 1 is a schematic diagram of the structure of a computer device provided by an embodiment of the present invention. For example, Figure 3 As shown, the computer device 300 includes: a memory 301, a processor 302, and a computer program 303 stored in the memory 301 and running on the processor 302, wherein when the processor 302 executes the computer program 303, the computer device can execute any of the multilateral collaborative computing and resource allocation methods for online diagnosis of chronic diseases introduced above.

[0197] Based on the same inventive concept as the above-described method embodiments, the present invention provides a server comprising a memory and a processor. The memory is configured to store executable program code, and the processor is configured to retrieve and execute the executable program code from the memory, thereby enabling the device to execute any of the above-described multilateral collaborative computing and resource allocation methods for online chronic disease diagnosis.

[0198] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer program product, which includes: computer program code, which, when running on a computer, enables the computer to execute any one of the above-mentioned multilateral collaborative computing and resource allocation methods for online diagnosis of chronic diseases.

[0199] Based on the same inventive concept as the above-mentioned method embodiment, the present invention provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes any one of the above-mentioned multilateral collaborative computing and resource allocation methods for online diagnosis of chronic diseases.

[0200] In summary, when allocating online medical resources, the present invention comprehensively considers a set of scoring tables that characterize the abnormal conditions of monitoring data at the diagnosis time corresponding to different online diagnoses, and analyzes the scoring table set sequence, blood pressure data sequence, and electrocardiogram data sequence, thereby adaptively quantifying the resource allocation priority corresponding to each target patient. Finally, resource allocation is achieved based on the resource allocation priority, and the rationality of online medical resource allocation is improved to a certain extent.

[0201] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A multilateral collaborative computing and resource allocation method for online diagnosis of chronic diseases, characterized by: The following steps are involved: Obtain the score sheet set corresponding to each online diagnosis of each target patient during their current treatment period, as well as their blood pressure data and electrocardiogram data during the current treatment period, and obtain the score sheet set sequence, blood pressure data sequence, and electrocardiogram data sequence corresponding to each target patient; Based on the score table set sequence corresponding to each target patient, a local score value sequence is constructed, and score distribution analysis and processing is performed based on the local score value sequence corresponding to each target patient to obtain a target comprehensive score value; Segment the local score value sequence corresponding to each target patient to obtain local score value segments; Segmenting the blood pressure data sequence and electrocardiogram data sequence corresponding to each target patient according to all local score value segments corresponding to each target patient to obtain blood pressure data segments and electrocardiogram data segments; Correcting the target comprehensive score value corresponding to each target patient based on all local score value segments, all blood pressure data segments, and all electrocardiogram data segments corresponding to each target patient to obtain a corrected score value; Determine the resource allocation priority for each target patient based on the corrected score value corresponding to each target patient and the distance between each target patient and the hospital, and allocate resources based on the resource allocation priority; The scoring distribution analysis and processing based on the local scoring value sequence corresponding to each target patient to obtain the target comprehensive scoring value includes: Determine any target patient as a marked patient, perform linear fitting on the local score value sequence corresponding to the marked patient, and obtain a fitting straight line corresponding to the marked patient; Determine an initial comprehensive score value corresponding to the marked patient according to the slope of the fitting line corresponding to the marked patient and the last local score value in the local score value sequence corresponding to the marked patient; Determining the consistency of the scores corresponding to the marked patient according to the number of score sheets in each score sheet set in the score sheet set sequence corresponding to the marked patient; Determining a target comprehensive score value corresponding to the marked patient based on the initial comprehensive score value and the score consistency corresponding to the marked patient, wherein both the initial comprehensive score value and the score consistency are positively correlated with the target comprehensive score value; The determining, based on the number of score sheets in each score sheet set in the score sheet set sequence corresponding to the marked patient, the score consistency corresponding to the marked patient includes: Determine the number of score sheets in each score sheet set in the score sheet set sequence corresponding to the marked patient as the target representative number, and obtain a target representative number sequence corresponding to the marked patient; rounding the mean of all modes in the target representative quantity sequence corresponding to the marked patient to obtain a reference quantity corresponding to the marked patient; Determining any one score sheet in the score sheet set sequence corresponding to the marked patient as a marked score sheet, and screening out score sheets of the same type as the marked score sheet from the score sheet set sequence corresponding to the marked patient to form a score sheet group corresponding to the marked score sheet, thereby obtaining a score sheet group corresponding to each score sheet; Determine the number of scoring sheets in the scoring sheet group corresponding to each scoring sheet as the number of standards corresponding to each scoring sheet; Screening out the largest standard quantity among the reference quantities from the standard quantities corresponding to all the score tables in the score table set sequence corresponding to the marked patient, to form a standard quantity set corresponding to the marked patient; If the standard quantity corresponding to the scoring table belongs to the standard quantity set, the scoring table is determined as a commonly used scoring table, and the scoring table set in which the commonly used scoring table exists is determined as a commonly used scoring table set; If the standard quantity corresponding to the scoring table does not belong to the standard quantity set, the scoring table is determined to be a special scoring table, and the scoring table set in which all the scoring tables are special scoring tables is determined to be a special scoring table set; The score consistency corresponding to the marked patient is determined based on the number of commonly used score table sets in the score table set sequence corresponding to the marked patient, the differences between different commonly used score table sets, and the differences between the commonly used score table sets and the special score table sets.

2. A multilateral collaborative computing and resource allocation method for online diagnosis of chronic diseases according to claim 1, characterized in that: The constructing of a local score value sequence based on the score table set sequence corresponding to each target patient includes: Determine any target patient as a marked patient, and form a score value set with the score values ​​corresponding to all score tables in each score table set in the score table set sequence corresponding to the marked patient, to obtain a score value set sequence corresponding to the marked patient; The mean of all score values ​​in each score value set in the score value set sequence corresponding to the marked patient is determined as the local score value, so as to obtain the local score value sequence corresponding to the marked patient.

3. The method of multilateral collaborative computing and resource allocation for online diagnosis of chronic diseases according to claim 1 is characterized in that: Determining the initial comprehensive score value corresponding to the marked patient based on the slope of the fitting line corresponding to the marked patient and the last local score value in the local score value sequence corresponding to the marked patient includes: determining a normalized value of the slope of the fitting line corresponding to the marked patient as a target slope corresponding to the marked patient; Determining the last local score value in the local score value sequence corresponding to the marked patient as the most recent score value corresponding to the marked patient; The product of the target slope and the most recent score value corresponding to the marked patient is normalized to obtain an initial comprehensive score value corresponding to the marked patient.

4. The method of multilateral collaborative computing and resource allocation for online diagnosis of chronic diseases according to claim 1 is characterized in that: The segmenting of the local score value sequence corresponding to each target patient to obtain local score value segments includes: The APCA algorithm is used to segment the local score value sequence corresponding to each target patient to obtain multiple local score value segments corresponding to each target patient.

5. The method of multilateral collaborative computing and resource allocation for online diagnosis of chronic diseases according to claim 1 is characterized in that: The blood pressure data sequence and electrocardiogram data sequence corresponding to each target patient are segmented according to all local score value segments corresponding to each target patient to obtain blood pressure data segments and electrocardiogram data segments, including: Determine any target patient as a marked patient, and determine the time period corresponding to each local score value segment corresponding to the marked patient as a local time period; The blood pressure data of the marked patient corresponding to the blood pressure data sequence whose corresponding collection moments belong to the same local time period are used to form a blood pressure data segment corresponding to the local time period, thereby obtaining a plurality of blood pressure data segments corresponding to the marked patient; The ECG data of the ECG data sequence corresponding to the marked patient, whose corresponding collection moments belong to the same local time period, are formed into ECG data segments, thereby obtaining a plurality of ECG data segments corresponding to the marked patient.

6. The method of multilateral collaborative computing and resource allocation for online diagnosis of chronic diseases according to claim 5 is characterized in that: The target comprehensive score value corresponding to each target patient is corrected based on all local score value segments, all blood pressure data segments, and all electrocardiogram data segments corresponding to each target patient to obtain a corrected score value, including: Determine any target patient as a marked patient, and determine the average of all local score values ​​in each local score value segment corresponding to the marked patient as the overall score index, to obtain the overall score index sequence corresponding to the marked patient; Performing abnormality analysis on each blood pressure data segment to obtain a target blood pressure abnormality factor corresponding to a local time period corresponding to each blood pressure data segment; Similarly, each ECG data segment is subjected to abnormal analysis and processing to obtain a target ECG abnormality factor corresponding to a local time period corresponding to each ECG data segment; The product of the target blood pressure abnormality factor and the target electrocardiogram abnormality factor corresponding to each local time period is determined as the target overall abnormality factor corresponding to each local time period; The target overall abnormality factors corresponding to all local time periods corresponding to the marked patient are used to form a target overall abnormality factor sequence corresponding to the marked patient; Normalizing the Pearson correlation coefficient between the target overall abnormality factor sequence and the overall scoring index sequence corresponding to the marked patient to obtain the target similarity corresponding to the marked patient; The product of the target similarity and the target comprehensive score corresponding to the marked patient is normalized to obtain a revised score corresponding to the marked patient.

7. The method of multilateral collaborative computing and resource allocation for online diagnosis of chronic diseases according to claim 6 is characterized in that: The abnormality analysis process is performed on each blood pressure data segment to obtain a target blood pressure abnormality factor corresponding to a local time period corresponding to each blood pressure data segment, including: Performing blood pressure abnormality detection on each blood pressure data segment to obtain abnormal blood pressure data, and forming abnormal blood pressure data sub-segments from continuous abnormal blood pressure data within each blood pressure data segment; Clustering all abnormal blood pressure data sub-segments within each blood pressure data segment to obtain abnormal blood pressure clusters, and selecting the abnormal blood pressure cluster with the largest total duration from all abnormal blood pressure clusters corresponding to each blood pressure data segment as the target abnormal blood pressure cluster corresponding to each blood pressure data segment; According to the total number of all abnormal blood pressure data in each blood pressure data segment and the number of abnormal blood pressure data in its corresponding target abnormal blood pressure cluster, the target blood pressure abnormality factor corresponding to the local time period corresponding to each blood pressure data segment is determined.

8. The method of multilateral collaborative computing and resource allocation for online diagnosis of chronic diseases according to claim 1 is characterized in that: Determining the resource allocation priority corresponding to each target patient based on the modified score value corresponding to each target patient and the distance between each target patient and the hospital includes: Determine any target patient as a marked patient, classify each hospital into different levels, and obtain the target level corresponding to each hospital; Screening out the hospital closest to the address of the marked patient from all hospitals corresponding to each target level as the reference hospital for the marked patient at each target level; Determine the distance between the reference hospital of the marked patient at each target level and the address of the marked patient as the marked distance of the marked patient at each target level; Determine the richness of offline medical resources corresponding to the marked patient according to the marked distance of the marked patient at all target levels, wherein the marked distance is negatively correlated with the richness of offline medical resources; The resource allocation priority corresponding to the marked patient is determined based on the offline medical resource richness and the revised score value corresponding to the marked patient, wherein the offline medical resource richness is negatively correlated with the resource allocation priority, and the revised score value is positively correlated with the resource allocation priority.

Images