A Smart Storage Management Method for Nursing Clinical Data

Abstract

The present invention relates to the technical field of data management, and particularly relates to a method for intelligent storage management of nursing clinical data. The method includes: obtaining the nursing clinical data of each target user within a predetermined time period, and determining the comprehensive infectivity index of the same disease according to the diagnosis and treatment data of all target users suffering from the same disease; determining the final infection degree of the disease suffered by the current target user; determining the comprehensive infection characteristics of each target user based on the final infection degree of the disease suffered by each target user and the comprehensive infectivity index of the disease, and classifying each target user according to the comprehensive infection characteristics; taking each category of target users as a group to be compressed, and performing grouped parallel compression on the nursing clinical data of the target users within each group to be compressed, obtaining the compressed data of each category of users and storing them classified. In this way, the present invention improves the data compression efficiency, saves computing resources and improves the data processing efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and particularly to a smart storage management method for nursing clinical data. Background Art

[0002] In today's medical and public health fields, key indicators such as the prevalence, infectivity, cure rate, and transmission rate of diseases are of great significance for disease prevention and control, medical resource allocation, and treatment plan formulation. Nursing clinical data, as an important part of medical data, has unique complexity and diversity. It covers various information of patients during hospitalization or receiving nursing services, including vital sign monitoring data such as body temperature, heart rate, blood pressure, respiratory rate, etc., which can reflect the physical function status of patients in real time.

[0003] In some scenarios, the amount of nursing clinical data is increasing exponentially. In the process of processing the integration of these massive data, data compression technology becomes a key link. Medical data not only includes patients' basic information, diagnosis records, but also involves long-term treatment process data, etc., with a huge amount of data. Currently, the unified compression storage method is often used to compress all the data of all patients uniformly. In this way, the compression efficiency is low. In the subsequent data analysis stage, since the main focus is on specific data related to the diseases of specific patients, the comprehensive unified compression makes it necessary to decompress all the overall data when retrieving the data of specific patients, which not only consumes a large amount of computer resources but also significantly prolongs the data processing time, seriously affecting the timeliness and accuracy of medical decisions. Thus, the above-mentioned compression efficiency and data processing efficiency of nursing clinical data are low, and a large amount of computing resources will be wasted. Summary of the Invention

[0004] In order to solve the technical problems of low compression efficiency and data processing efficiency of nursing clinical data, and wasting a large amount of computing resources, the purpose of the present invention is to provide a smart storage management method for nursing clinical data, and the specific technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present invention provides a method for intelligent storage management of nursing clinical data, including: obtaining the nursing clinical data of each target user within a predetermined time period, where the nursing clinical data includes the diseases suffered by the target user; determining the comprehensive infectivity index of the same disease according to the diagnosis and treatment data of all target users suffering from the same disease; determining the final infection degree of the disease suffered by the current target user based on the comprehensive infectivity index, the diseases suffered by each target user, and the complications of each disease suffered by each target user; determining the infectious comprehensive characteristics of each target user based on the final infection degree of the diseases suffered by each target user and the comprehensive infectivity index of the disease, and classifying each target user according to the infectious comprehensive characteristics; taking each category of target users as a group to be compressed, and performing grouped parallel compression on the nursing clinical data of the target users within each group to be compressed, obtaining the compressed data of each category of users and storing them classified.

[0006] Optionally, determining the comprehensive infectivity index of the same disease according to the diagnosis and treatment data of all target users suffering from the same disease includes: determining the curability rate of the same disease according to the cure time and the disease time of all target users suffering from the same disease and the number of first patients with the same disease within a predetermined time period; dividing the predetermined time period into multiple time periods, and determining that the first ratio between the new cases of the same disease in the current time period and the total number of the same disease in the current time period relative to the previous time period is the new case ratio of the current time period; arranging the new case ratios of each time period in chronological order and performing fitting to obtain a fitting curve; determining the initial infectivity index of the same disease according to the absolute value of the slope of the fitting curve and the curability rate; using the number of first patients with the same disease within a predetermined time period and the number of second patients with the complications of the same disease to determine the comprehensive influence index of the complications on the same disease; determining the comprehensive infectivity index of the same disease according to the initial infectivity index and the comprehensive influence index.

[0007] Optionally, determining the curability rate of the same disease according to the cure time and the disease time of all target users suffering from the same disease and the number of first patients with the same disease within a predetermined time period includes: calculating the first average time of the cure time of all target users suffering from the same disease and the second average time of the disease time of all target users suffering from the same disease; calculating the second ratio between the first average time and the second average time, and performing normalization processing on the second ratio to obtain a normalized value; determining that the first product between the normalized value and the number of first patients is the curability rate of the same disease.

[0008] Optionally, determining the initial infectivity index of the same disease according to the absolute value of the slope of the fitting curve and the curability rate includes: determining that the third ratio between the absolute value of the slope and the curability rate is the initial infectivity index of the same disease.

[0009] Optionally, determining the comprehensive impact index of complications on the same disease using the number of first patients with the same disease and the number of second patients with complications of the same disease within a predetermined time period includes: determining the fourth ratio between the number of second patients with each complication and the number of first patients, and superimposing the fourth ratios to obtain the comprehensive impact index of complications on the same disease.

[0010] Optionally, determining the comprehensive infectivity index of the same disease based on the initial infectivity index and the comprehensive impact index includes: determining the second product between the initial infectivity index and the comprehensive impact index as the comprehensive infectivity index of the same disease.

[0011] Optionally, determining the final infection degree of the disease suffered by the current target user based on the comprehensive infectivity index, the diseases suffered by each target user, and the complications of each disease suffered by each target user includes:

[0012] Clustering the diseases based on the comprehensive infectivity index to obtain multiple clusters, and the comprehensive infectivity indexes of the diseases in the same cluster are similar;

[0013] Determining the fifth ratio between the comprehensive impact index of each complication of each disease in the cluster on it and the number of complications of each disease as the average impact degree of each complication caused by each disease;

[0014] Obtaining the median of the average impact degrees of all diseases in the cluster;

[0015] Counting the target cluster where the current target user is located, and determining the average value of the medians of all target clusters, and taking the average value as the initial infection degree of the current target user; determining the difference between the current target user and other target users in the target cluster according to the disease suffered by the current target user in the target cluster and the median of the target cluster; obtaining the average difference between the current target user and other target users in all target clusters; determining the final infection degree of the current target user according to the average difference and the initial infection degree.

[0016] Optionally, determining the difference between the current target user and other target users in the target cluster according to the disease suffered by the current target user in the target cluster and the median of the target cluster includes: when the number of diseases suffered by the current target user in the target cluster is one, determining the absolute value of the first difference between the average impact degree of each complication caused by the disease suffered by the current target user and the cluster center as the difference; when the number of diseases suffered by the current target user in the target cluster is multiple, calculating the second difference between the average impact degree of each complication caused by each disease suffered by the current target user and the cluster center; superimposing the second differences and taking the absolute value to obtain the difference.

[0017] Optionally, determining the final infection degree of the current target user according to the average difference and the initial infection degree includes: calculating a first sum value between a predetermined value and the average difference; determining a third product between the first sum value and the initial infection degree as the final infection degree of the current target user.

[0018] Optionally, determining the comprehensive infection characteristics of each target user based on the final infection degree of the disease suffered by each target user and the comprehensive infectivity index of the disease includes: calculating a fourth product between the comprehensive infectivity index and the final infection degree of each disease suffered by the target user, and superimposing each fourth product to obtain a second sum value; performing normalization processing on the second sum value to obtain the comprehensive infection characteristics of the target user.

[0019] The present invention has the following beneficial effects: First, obtain the nursing clinical data of each target user within a predetermined time period, where the nursing clinical data includes the diseases suffered by the target user; then determine the comprehensive infectivity index of the same disease according to the diagnosis and treatment data of all target users suffering from the same disease; and determine the final infection degree of the disease suffered by the current target user based on the comprehensive infectivity index, the disease suffered by each target user, and the complications of each disease suffered by each target user; secondly, determine the comprehensive infection characteristics of each target user based on the final infection degree of the disease suffered by each target user and the comprehensive infectivity index of the disease; and classify each target user according to the comprehensive infection characteristics; finally, take each category of target users as a group to be compressed, and perform grouped parallel compression on the nursing clinical data of the target users in each group to be compressed, obtain the compressed data of each category of users and store them classified.

[0020] In this way, the embodiment of the present invention can evaluate the infection degree of the disease of the user and the comprehensive infectivity index, so as to determine the comprehensive infection characteristics of each user, and perform more refined hierarchical management on each user based on the comprehensive infection characteristics.

[0021] After classifying each user based on the comprehensive infection characteristics, perform grouped parallel compression on the nursing clinical data of each category of users, which improves the data compression efficiency. In the subsequent data analysis stage, when it is necessary to retrieve the data of a specific patient, only the compressed data corresponding to the specific patient needs to be decompressed, instead of decompressing all the data, which saves computing resources and improves the data processing efficiency. Description of the Drawings

[0022] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0023] Figure 1 Flowchart of a method for intelligent storage management of nursing clinical data provided by an embodiment of the present invention;

[0024] Figure 2 Structure diagram of a system for intelligent storage management of nursing clinical data provided by an embodiment of the present invention;

[0025] Figure 3 Structure diagram of a system for intelligent storage management of nursing clinical data provided by another embodiment of the present invention. Detailed implementation manners

[0026] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of a method for intelligent storage management of nursing clinical data proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0027] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0028] The following specifically describes the specific solution of a method for intelligent storage management of nursing clinical data provided by the present invention in combination with the accompanying drawings.

[0029] Embodiment 1:

[0030] Please refer to Figure 1 , which shows the flowchart of a method for intelligent storage management of nursing clinical data provided by an embodiment of the present invention, including:

[0031] S101, Obtain the nursing clinical data of each target user within a predetermined time period, and the nursing clinical data includes the diseases suffered by the target user.

[0032] Specifically, the predetermined time period can be determined according to the actual situation. In the embodiments of the present invention, the value is half a year. The target users refer to the patients seeking medical treatment in a certain hospital, and the nursing clinical data can be obtained from the medical records of the patients in the electronic medical record system of the hospital information system. Among them, the nursing clinical data includes but is not limited to the basic information of the target users, diagnosis and treatment information (including the diagnosis results of doctors, treatment plans, etc.), any complications that occur during the treatment of the disease by the patients, the recovery time of the patients from admission to discharge, and the disease time of the patients from getting sick to recovery, etc.

[0033] S102. Determine the comprehensive infectivity index of the same disease according to the diagnosis and treatment data of all target users suffering from the same disease.

[0034] Specifically, in the embodiments of the present invention, by evaluating the comprehensive infectivity index of the disease, it is beneficial for the health department to be able to prepare resources in advance, take timely prevention and control measures, and reduce the spread and impact of the disease. Specifically, in the embodiments of the present invention, through the analysis of the disease and the identification of complications, the comprehensive infectivity index of each disease is evaluated. Generally speaking, one patient corresponds to one case, and usually there are multiple diseases in one case. Among all patients, the number a of all users suffering from the same disease A is obtained. The larger the number, the more common the disease A is in the population, and the higher its universality. For example, influenza, etc., then the comprehensive infectivity index of the corresponding disease is larger. In addition, the high universality of disease A means that it is more common in the population, but this does not exclude the possibility that it still has a high infectivity, such as viral cold or influenza, etc. Therefore, when evaluating the universality of disease A, not only the frequency of its occurrence in the population needs to be considered, but also its curability and transmission ability need to be further analyzed. Then the comprehensive infectivity index of the disease is determined.

[0035] Further, as an optional embodiment of the present invention, determining the comprehensive infectivity index of the same disease according to the diagnosis and treatment data of all target users suffering from the same disease includes: determining the curability of the same disease according to the recovery time and disease time of all target users suffering from the same disease and the number of the first patients suffering from the same disease within the predetermined time period; dividing the predetermined time period into multiple time periods evenly, and determining that the first ratio between the new number of the same disease in the current time period and the total number of the same disease in the current time period relative to the previous time period is the new addition ratio of the current time period; arranging the new addition ratios of each time period in chronological order and then fitting to obtain a fitting curve; determining the initial infectivity index of the same disease according to the absolute value of the slope of the fitting curve and the curability; using the number of the first patients suffering from the same disease within the predetermined time period and the number of the second patients suffering from the complications of the same disease to determine the comprehensive influence index of the complications on the same disease; and determining the comprehensive infectivity index of the same disease according to the initial infectivity index and the comprehensive influence index.

[0036] Specifically, in the embodiments of the present invention, taking disease A as an example, for disease A, the cure time and the disease time of each patient suffering from disease A are obtained. If the average cure time of disease A is relatively long and the cure rate is relatively low, then this may mean that the disease has strong infectivity or is difficult to treat, thereby increasing the risk of its spread in the population.

[0037] Among them, when determining the curability rate, as an optional embodiment of the present invention, according to the cure time and the disease time of all target users suffering from the same disease and the number of first patients with the same disease within a predetermined time period, determining the curability rate of the same disease includes: calculating the first average time of the cure time of all target users suffering from the same disease and the second average time of the disease time of all target users suffering from the same disease; calculating the second ratio between the first average time and the second average time, and performing a normalization process on the second ratio to obtain a normalized value; determining the first product between the normalized value and the number of first patients as the curability rate of the same disease.

[0038] Specifically, the embodiments of the present invention specifically use the following formula to calculate the curability rate:

[0039]

[0040] In the above formula, is the curability rate of disease A, which is used to evaluate the quality of the treatment effect. The higher the curability rate, the more common and better the treatment effect of disease A. is the number of first patients suffering from disease A within a predetermined time period. is the average cure time of the cure time of all target users suffering from disease A, that is, the first average time. The shorter the average cure time, usually the more effective the treatment or the lighter the disease. is the average disease time of the disease time of all target users suffering from disease A, that is, the second average time. represents the speed at which patients are cured within the average disease time. The smaller the value of means that the time required for cure is shorter relative to the disease time, indicating that the treatment is more effective or the disease is easier to control. represents a normalization function, which is used to perform a normalization process on

[0041] Furthermore, in the embodiments of the present invention, within a predetermined time period, the predetermined time period is evenly divided into several equal time periods by month. Then, the new increase ratio of the same disease in each time period relative to the previous time period is statistically calculated.

[0042] Specifically, taking disease A as an example, the embodiments of the present invention specifically use the following formula to calculate the new increase ratio:

[0043]

[0044] In the above formula, represents the new increase ratio of disease A in the current time period relative to the previous time period. represents the new increase quantity of disease A in the x-th time period relative to disease A in the previous time period. represents the total quantity of disease A in the x-th time period. A larger value of means that the proportion of new cases is relatively high, which may indicate that the transmission speed of disease A is relatively fast or the epidemic situation has worsened during this time period, and the corresponding comprehensive infectivity index is also relatively high.

[0045] Furthermore, in the embodiment of the present invention, after arranging the new increase ratios of each time period in time sequence, a new increase ratio time sequence period is obtained. Then, the new increase ratios in the new increase ratio time sequence period are fitted to obtain a fitting curve, and the absolute value K of the slope of the fitting curve is obtained. The larger K is, the faster the increase rate of the medical records of disease A is, the stronger the uncontrollability is, and the greater the possibility of being an infectious disease is.

[0046] Furthermore, as an optional embodiment of the present invention, determining the initial infectivity index of the same disease according to the absolute value of the slope of the fitting curve and the curability rate includes: determining the third ratio between the absolute value of the slope and the curability rate as the initial infectivity index of the same disease.

[0047] Specifically, taking disease A as an example in the embodiment of the present invention, the following formula is specifically used in the embodiment of the present invention to calculate the initial infectivity index:

[0048]

[0049] In the above formula, is the initial infectivity index of disease A, A larger value indicates that disease A is both difficult to treat and has a relatively high infectivity. is the curability rate of disease A. The higher e is, it may mean that disease A is not only common but also has a good treatment effect, and the corresponding initial infectivity index of disease A is smaller. is the absolute value of the slope of the fitting curve of the new increase ratio.

[0050] Further, the occurrence of each disease is usually accompanied by the occurrence of other related diseases. The higher the frequency of the occurrence of complications, it may indicate that the condition of the disease is more serious, or the patient's body reacts more strongly to the disease. Among all the cases of patients with disease A, identify the number h of other complications that occur and the number j of the second occurrences of each complication in the patients. The more h is, it may mean that the condition of disease A is more serious, or the patient's body reacts more strongly to the disease. The larger j is, it may mean that the correlation between complication B and disease A is stronger, or the prevalence of this complication B causing disease A in patients is higher. Among them, as an optional embodiment of the present invention, determining the comprehensive influence index of a complication on the same disease by using the number of the first occurrences of the same disease and the number of the second occurrences of the complications of the same disease within a predetermined time period includes: determining the fourth ratio between the number of the second occurrences of each complication and the number of the first occurrences, and superimposing the fourth ratios to obtain the comprehensive influence index of the complication on the same disease.

[0051] Specifically, taking disease A as an example, the embodiment of the present invention specifically calculates the comprehensive influence index of disease A by using the following formula:

[0052]

[0053] In the above formula, represents the comprehensive influence index of disease A. A high value may mean that there are more or more serious complications caused by disease A. is the number of the first occurrences of patients with disease A within a predetermined time period. is the number of the second occurrences of the i-th complication of disease A. is the number of complications, used to reflect the frequency of evaluating the i-th complication. The larger its value is, it indicates that the correlation between this complication and disease A is stronger, or the possibility of this complication causing disease A in patients is higher.

[0054] Further, as an optional embodiment of the present invention, determining the comprehensive infectivity index of the same disease according to the initial infectivity index and the comprehensive influence index includes: determining the second product between the initial infectivity index and the comprehensive influence index as the comprehensive infectivity index of the same disease.

[0055] Specifically, taking disease A as an example, the embodiment of the present invention specifically calculates the comprehensive infectivity index of disease A by using the following formula:

[0056]

[0057] In the above formula, is the comprehensive infectivity index of disease A, A larger value indicates that disease A is a disease that is both difficult to treat and highly contagious, and more stringent prevention and control measures need to be taken. Represents the comprehensive impact index of disease A. Is the initial infectivity index of disease A.

[0058] S103. Determine the final infection degree of the disease suffered by the current target user based on the comprehensive infectivity index, the diseases suffered by each target user, and the complications of each disease suffered by each target user.

[0059] Specifically, in the embodiments of the present invention, a relatively high degree of similarity in disease conditions can initially identify highly infectious diseases. Patients with these diseases often require more isolation facilities and protective measures. Therefore, in the embodiments of the present invention, the diseases are first classified to further determine the relevant patient population, and then the final infection degree of the clinical manifestations of each patient is further obtained.

[0060] Further, as an optional embodiment of the present invention, determining the final infection degree of the disease suffered by the current target user based on the comprehensive infectivity index, the diseases suffered by each target user, and the complications of each disease suffered by each target user includes: clustering each disease based on the comprehensive infectivity index to obtain a plurality of clusters, and the comprehensive infectivity indexes of the diseases in the same cluster are similar; determining the fifth ratio between the comprehensive impact index of the complications of each disease in the cluster on it and the number of complications of each disease as the average impact degree of each complication caused by each disease; obtaining the median of the average impact degrees of all diseases in the cluster; counting the target cluster where the current target user is located, and determining the average value of the medians of all target clusters, and taking the average value as the initial infection degree of the current target user; determining the difference between the current target user and other target users in the target cluster according to the disease suffered by the current target user in the target cluster and the median of the target cluster; obtaining the average difference in the differences between the current target user and other target users in all target clusters; and determining the final infection degree of the current target user according to the average difference and the initial infection degree.

[0061] Specifically, in the embodiments of the present invention, the comprehensive infectivity index is used to cluster all diseases to obtain several clusters, and the comprehensive infectivity indexes of the diseases in each cluster are similar or close. It should be noted that each patient may be classified into one or more clusters because a patient may suffer from multiple diseases. In the embodiments of the present invention, all diseases are clustered, so a patient may correspond to one or more clusters.

[0062] Furthermore, under the influence of complications, the patient's condition may deteriorate. However, due to individual differences in physical constitution, different degrees of infection may be manifested. Therefore, when classifying nursing clinical data, classification cannot be based solely on the infectivity of the disease. Considering the patient's degree of infection is conducive to hierarchical management of patients.

[0063] Furthermore, in the embodiment of the present invention, taking disease A in cluster C as an example, the average influence degree of each complication caused by disease A is calculated by the following formula: , where is the comprehensive influence index of the complication of disease A on it, is the number of complications of disease A. The average influence degree The higher it is, the more serious the impact of each complication is, although the number of complications may not be large; if this ratio is lower, it may indicate that although there are more complications, the impact of each complication is relatively light.

[0064] Furthermore, in the embodiment of the present invention, the median m of the average influence degrees of all diseases in cluster C is obtained. The median m represents the central level of the cluster and is used as the characteristic value of each cluster.

[0065] Furthermore, in the embodiment of the present invention, taking the current target user as patient X as an example, all the target clusters where patient X is located are counted, denoted as the relevant clusters of patient X. Then, the average value of the median m of all the relevant clusters of patient X is obtained. is used as the initial infection degree of patient X. In this way, in the embodiment of the present invention, based on the overall manifestation of the disease, the initial infection degree of the patient is obtained. However, there are still individual differences in the patient himself. Therefore, in the embodiment of the present invention, the differences between patient X and other patients in each cluster where patient X is located are counted, and the relative infection degree of patient X is obtained. Taking this as a correction factor, the final infection degree of patient X is more accurately represented on the overall initial infection degree.

[0066] Furthermore, in the embodiment of the present invention, in the w-th relevant cluster of patient X, the difference between patient X and other patients is calculated. The embodiment of the present invention realizes this by comparing the distance between the disease characteristics of patient X and the median of the target cluster (the median represents the characteristic value of the target cluster).

[0067] Further, as an alternative embodiment of the present invention, determining the difference between the current target user in the target cluster and other target users according to the disease suffered by the current target user in the target cluster and the median of the target cluster includes: when there is only one disease suffered by the current target user in the target cluster, determining the absolute value of the first difference between the average impact degree of each complication caused by the disease suffered by the current target user and the cluster center as the difference; when there are multiple diseases suffered by the current target user in the target cluster, calculating the second difference between the average impact degree of each complication caused by each disease suffered by the current target user and the cluster center; taking the absolute value after superimposing each second difference to obtain the difference.

[0068] Specifically, taking the w-th related cluster of patient X as an example in the embodiment of the present invention, if there is only one disease A of patient X in the w-th related cluster of patient X, the embodiment of the present invention calculates the difference using the following formula:

[0069]

[0070] In the above formula, is the difference between patient X and other patients in the w-th related cluster of patient X. is the average impact degree of disease A suffered by patient X in the w-th related cluster. is the median of the w-th related cluster of patient X, that is, the eigenvalue of the w-th related cluster of patient X. is the comprehensive impact index of the complication of disease A on it, is the number of complications of disease A.

[0071] Further, if there are multiple diseases of patient X in the w-th related cluster of patient X, such as u1, u2, u3, the embodiment of the present invention calculates the difference using the following formula:

[0072]

[0073] In the above formula, is the difference between patient X and other patients in the w-th related cluster of patient X. The greater the difference, the more serious the possible infection degree may be. U is the number of diseases that patient X has in the w-th related cluster of patient X. represents the average impact degree of the u-th disease, is the median of the w-th related cluster of patient X, that is, the eigenvalue of the w-th related cluster of patient X. is the comprehensive impact index of the complication of disease A on it, is the number of complications of disease A.

[0074] Further, obtain the average of the differences from other patients in each relevant cluster of patient X. .

[0075] Further, as an optional embodiment of the present invention, determining the final infection degree of the current target user according to the average difference and the initial infection degree includes: calculating the first sum value between a predetermined value and the average difference; determining the third product of the first sum value and the initial infection degree as the final infection degree of the current target user.

[0076] Specifically, in the embodiment of the present invention, the predetermined value can be taken according to the actual situation. In the embodiment of the present invention, the value is 1. The following formula is specifically used to calculate the final infection degree:

[0077]

[0078] In the above formula, represents the final infection degree of the target user. is the initial infection degree of the target user. represents the average of the differences from other patients in each relevant cluster of the target user, that is, the average difference.

[0079] S104. Based on the final infection degree of the diseases suffered by each target user and the comprehensive infectivity index of the diseases, determine the comprehensive infection characteristics of each target user, and classify each target user according to the comprehensive infection characteristics.

[0080] Specifically, after determining the final infection degree and the comprehensive infectivity index of the user in the embodiment of the present invention, the comprehensive infection characteristics of each user are determined. Among them, as an optional embodiment of the present invention, determining the comprehensive infection characteristics of each target user based on the final infection degree of the diseases suffered by each target user and the comprehensive infectivity index of the diseases includes: calculating the fourth product between the comprehensive infectivity index and the final infection degree of each disease suffered by the target user, and adding up each fourth product to obtain a second sum value; performing a normalization process on the second sum value to obtain the comprehensive infection characteristics of the target user.

[0081] Among them, the following formula is specifically used in the embodiment of the present invention to calculate the comprehensive infection characteristics of the target user:

[0082]

[0083] In the above formula, represents the comprehensive infection characteristics of the target user. is the comprehensive infectivity index of the p-th disease of the target user. P is the number of diseases of the target user. represents the final infection degree of the target user. represents the normalization function, which is used for Perform normalization processing.

[0084] Furthermore, in the embodiments of the present invention, the comprehensive infection characteristics of each user are obtained and the users are divided into four categories. Among them, users with a comprehensive infection characteristic W less than 0.4 are classified into the mild symptom category. Users with a comprehensive infection characteristic W greater than or equal to 0.4 and less than 0.6 are classified into the moderate symptom category. Users with a comprehensive infection characteristic W greater than or equal to 0.6 and less than 0.8 are classified into the severe symptom category. Users with a comprehensive infection characteristic W greater than 0.8 are classified into the critical condition category.

[0085] It should be noted that there may be other types of classifying users according to the comprehensive infection characteristic W according to the actual situation, and the embodiments of the present invention do not limit this here.

[0086] S105: Take each category of target users as a group to be compressed, and perform grouped parallel compression on the nursing clinical data of the target users in each group to be compressed, obtain the compressed data of each category of users and store them by category.

[0087] Specifically, in the embodiments of the present invention, each category of target users is used as a group to be compressed for grouped compression. The embodiments of the present invention use the block Huffman coding algorithm to perform parallel compression on the nursing clinical data of the users in each group to be compressed, obtain the compressed coding set of each group of users, and use the classification label of each compressed coding set as the label of the compressed coding set. The embodiments of the present invention store the compressed coding set and its label in the database to complete data integration storage.

[0088] The embodiments of the present invention can evaluate the infection degree of users with diseases and the comprehensive infectivity index, thereby determining the comprehensive infection characteristics of each user. Based on this comprehensive infection characteristic, more refined hierarchical management is carried out for each user. After classifying each user based on this comprehensive infection characteristic, the nursing clinical data of each category of users is grouped and compressed in parallel, which can compress the nursing clinical data of various categories of users at the same time, improving the data compression efficiency. In the subsequent data analysis stage, when it is necessary to retrieve the data of a specific patient, only the compressed data corresponding to the specific patient needs to be decompressed, rather than decompressing all the data, saving computing resources and improving the data processing efficiency.

[0089] Embodiment 2:

[0090] Corresponding to the intelligent storage management method of nursing clinical data provided in the above embodiment, based on the same technical concept, the embodiments of the present invention also provide an intelligent storage management system for nursing clinical data. This intelligent storage management system for nursing clinical data is used to execute the above intelligent storage management method of nursing clinical data. Figure 2 For a schematic structural diagram of an intelligent storage management system for nursing clinical data provided by an embodiment of the present invention, as Figure 2As shown in the figure. The intelligent storage management system 200 for nursing clinical data includes: an acquisition module 201, configured to acquire the nursing clinical data of each target user within a predetermined time period, where the nursing clinical data includes the diseases suffered by the target user; a determination module 202, configured to determine the comprehensive infectivity index of the same disease according to the diagnosis and treatment data of all target users suffering from the same disease; the determination module 202 is further configured to determine the final infection degree of the disease suffered by the current target user based on the comprehensive infectivity index, the diseases suffered by each target user, and the complications of each disease suffered by each target user; the determination module 202 is further configured to determine the comprehensive infection characteristics of each target user based on the final infection degree of the diseases suffered by each target user and the comprehensive infectivity index of the diseases, and classify each target user according to the comprehensive infection characteristics; a storage module 203, configured to use each category of target users as a group to be compressed, perform grouped parallel compression on the nursing clinical data of the target users within each group to be compressed, and obtain the compressed data of each category of users and store them classified.

[0091] The embodiment of the present invention can evaluate the infection degree of users with diseases and the comprehensive infectivity index, so as to determine the comprehensive infection characteristics of each user, perform more refined hierarchical management on each user based on the comprehensive infection characteristics, and after classifying each user based on the comprehensive infection characteristics, perform grouped parallel compression on the nursing clinical data of each category of users, which can compress the nursing clinical data of various categories of users at the same time, improving the data compression efficiency. In the subsequent data analysis stage, when it is necessary to retrieve the data of a specific patient, only the compressed data corresponding to the specific patient needs to be decompressed, instead of decompressing all the data, saving computing resources and improving the data processing efficiency.

[0092] Embodiment Three:

[0093] Corresponding to the intelligent storage management method for nursing clinical data provided in the above embodiment, based on the same technical concept, the embodiment of the present invention further provides an intelligent storage management system for nursing clinical data, and this intelligent storage management system for nursing clinical data is used to execute the above intelligent storage management method for nursing clinical data. Figure 3 The structural schematic diagram of an intelligent storage management system for nursing clinical data provided by another embodiment of the present invention is as Figure 3 shown. The intelligent storage management system for nursing clinical data may vary greatly due to configuration or performance, and may include one or more processors 301 and a memory 302. The memory 302 is used to store computer programs that can run on the processor 301. The processor 301 is used to execute the programs stored in the memory 302 to implement the above Figure 1Each step in the method embodiments. Among them, the memory 302 can be transient storage or persistent storage. The application programs stored in the memory 302 can include one or more modules (not shown in the figure), and each module can include a series of computer-executable instructions in the intelligent storage management system for nursing clinical data.

[0094] Furthermore, the processor 301 can be set to communicate with the memory 302 and execute a series of computer-executable instructions in the memory 302 on the intelligent storage management system for nursing clinical data. The intelligent storage management system for nursing clinical data can also include one or more power supplies 303, one or more wired or wireless network interfaces 304, one or more input / output interfaces 305, and one or more keyboards 306.

[0095] Specifically in this embodiment, the intelligent storage management system for nursing clinical data includes a processor, a communication interface, a memory, and a communication bus; among them, the processor, the communication interface, and the memory complete mutual communication through the bus; the memory is used to store computer programs; the processor is used to execute the programs stored on the memory to implement the above Figure 1 Each step in the method embodiments, and has the beneficial effects of the above method embodiments. To avoid repetition, the embodiments of the present invention will not be described in detail here.

[0096] It should be noted that the intelligent storage management system for nursing clinical data provided by the embodiments of the present invention and the intelligent storage management method for nursing clinical data provided by the embodiments of the present invention are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the foregoing intelligent storage management method for nursing clinical data and has the same or similar beneficial effects. The repeated parts will not be described in detail.

[0097] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0098] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for intelligent storage management of nursing clinical data, characterized in that, Including: Obtain the nursing clinical data of each target user within a predetermined time period, where the nursing clinical data includes the diseases suffered by the target user; Determine the comprehensive infectivity index of the same disease according to the diagnosis and treatment data of all target users suffering from the same disease; Based on the comprehensive infectivity index, the diseases suffered by each target user, and the complications of each disease suffered by each target user, determine the final infection degree of the diseases suffered by the current target user; Based on the final infection degree of the diseases suffered by each target user and the comprehensive infectivity index of the diseases, determine the comprehensive infection characteristics of each target user, and classify each target user according to the comprehensive infection characteristics; Take each category of target users as a group to be compressed, and perform grouped parallel compression on the nursing clinical data of the target users within each group to be compressed, obtain the compressed data of each category of users, and store them classified.

2. The intelligent storage management method for nursing clinical data according to claim 1, characterized in that The determining the comprehensive infectivity index of the same disease according to the diagnosis and treatment data of all target users suffering from the same disease includes: Determine the curability rate of the same disease according to the cure time and illness time of all target users suffering from the same disease and the number of first patients with the same disease within the predetermined time period; Divide the predetermined time period into multiple time periods, and determine that the first ratio between the new increase quantity of the same disease in the current time period and the total quantity of the same disease in the current time period relative to the previous time period is the new increase ratio of the current time period; Arrange the new increase ratios of each time period in chronological order and perform fitting to obtain a fitting curve; Determine the initial infectivity index of the same disease according to the absolute value of the slope of the fitting curve and the curability rate; Use the number of first patients with the same disease and the number of second patients with the complications of the same disease within the predetermined time period to determine the comprehensive influence index of the complications on the same disease; Determine the comprehensive infectivity index of the same disease according to the initial infectivity index and the comprehensive influence index.

3. The intelligent storage management method for nursing clinical data according to claim 2, wherein The determining the curability rate of the same disease according to the cure time and illness time of all target users suffering from the same disease and the number of first patients with the same disease within the predetermined time period includes: Calculate the first average time of the cure time of all target users suffering from the same disease and the second average time of the illness time of all target users suffering from the same disease; Calculate the second ratio between the first average time and the second average time, and perform normalization processing on the second ratio to obtain a normalized value; Determine that the first product between the normalized value and the number of first patients is the curability rate of the same disease.

4. The intelligent storage management method for nursing clinical data according to claim 2, wherein The determining the initial infectivity index of the same disease according to the absolute value of the slope of the fitting curve and the curability rate includes: Determine that the third ratio between the absolute value of the slope and the curability rate is the initial infectivity index of the same disease.

5. The intelligent storage management method for nursing clinical data according to claim 2, wherein Determining the comprehensive influence index of the complication on the same disease by using the first number of patients with the same disease and the second number of patients with the complication of the same disease within the predetermined time period includes: Determining a fourth ratio between the second number of patients with each complication and the first number of patients, and adding up the fourth ratios to obtain the comprehensive influence index of the complication on the same disease.

6. The intelligent storage management method for nursing clinical data according to claim 2, wherein The determining the comprehensive infectivity index of the same disease according to the initial infectivity index and the comprehensive influence index includes: Determining the second product between the initial infectivity index and the comprehensive influence index as the comprehensive infectivity index of the same disease.

7. The intelligent storage management method for nursing clinical data according to any one of claims 1-6, characterized in that The determining the final infection degree of the disease suffered by the current target user based on the comprehensive infectivity index, the diseases suffered by each target user, and the complications of each disease suffered by each target user includes: Clustering the diseases based on the comprehensive infectivity index to obtain a plurality of clusters, and the comprehensive infectivity indexes of the diseases in the same cluster are similar; Determining a fifth ratio between the comprehensive influence index of the complication of each disease in the cluster on it and the number of complications of each disease as the average influence degree of each complication caused by each disease; Obtaining the median of the average influence degrees of all diseases in the cluster, where the median represents the central level of the cluster, and using the median as the characteristic value of each cluster; Counting the target cluster where the current target user is located, and determining the average value of the medians of all the target clusters, and taking the average value as the initial infection degree of the current target user; Determining the difference between the current target user and other target users in the target cluster according to the disease suffered by the current target user in the target cluster and the median of the target cluster; Obtaining the average difference in the difference between the current target user and other target users in all the target clusters; Determining the final infection degree of the current target user according to the average difference and the initial infection degree.

8. The intelligent storage management method for nursing clinical data according to claim 7, characterized in that The determining the difference between the current target user and other target users in the target cluster according to the disease suffered by the current target user in the target cluster and the median of the target cluster includes: When there is one disease suffered by the current target user in the target cluster, determining the absolute value of the first difference between the average influence degree of each complication caused by the disease suffered by the current target user and the cluster center as the difference; When there are multiple diseases suffered by the current target user in the target cluster, calculating the second difference between the average influence degree of each complication caused by each disease suffered by the current target user and the cluster center; Taking the absolute value after adding up the second differences to obtain the difference.

9. The intelligent storage management method for nursing clinical data according to claim 7, wherein The determining the final infection degree of the current target user according to the average difference and the initial infection degree includes: Calculating the first sum value between a predetermined value and the average difference; Determine that the third product between the first sum value and the initial infection degree is the final infection degree of the current target user.

10. The intelligent storage management method for nursing clinical data according to claim 1, wherein The determining of the comprehensive infection characteristics of each target user based on the final infection degree of the disease suffered by each target user and the comprehensive infectivity index of the disease includes: Calculate the fourth product between the comprehensive infectivity index of each disease suffered by the target user and the final infection degree, and superimpose each of the fourth products to obtain a second sum value; Perform a normalization process on the second sum value to obtain the comprehensive infection characteristics of the target user.

Images