Data weight clustering marking method and device based on big data set and storage medium

Abstract

The invention discloses a data weight clustering marking method and device based on a big data set and a storage medium, and relates to the technical field of weight clustering marking, and the method comprises the following steps: carrying out the statistics of a weight set of sign data based on the big data set; analyzing the weight set through a clustering algorithm to obtain weight clustering points of the physical sign data; calculating clustering values of the physical sign data based on the weight clustering points, and performing clustering marking on the physical sign data according to the clustering values of different physical sign data; the method is used for solving the problems that according to an existing weight clustering marking technology, the deviation of analysis results of clustering points is large, clustering analysis is difficult to conduct on different medical data, and consequently the final clustering marking result is not accurate enough.

Description

Technical Field

[0001] The present invention relates to the technical field of weighted clustering labeling, and in particular to a data weighted clustering labeling method, device and storage medium based on a large data set. Background Art

[0002] Weighted clustering labeling technology refers to a method that combines data weight assignment, clustering analysis and labeling process to effectively classify and label data in a data set. In this technology, each data point is grouped and clustered according to its importance.

[0003] The existing weighted clustering labeling technology usually directly performs cluster analysis on the distribution map after constructing it. There are usually several free points in the distribution map. The proportion of such points is very small, but it will affect the results of the clustering points. The clustering algorithm itself is an abstract algorithm and there is no absolutely correct result. However, the existence of free points will increase the error of the analysis results of the clustering points. Only by clustering the dense area can the accuracy of the clustering points be improved. In addition, when the existing weighted clustering labeling technology is applied in the medical field, it is difficult to normalize different medical data. Different data have different units and different standards, which are difficult to unify when performing cluster analysis. For example, in the patent application with publication number CN109978007A, a disease risk factor extraction method based on attribute weight clustering is disclosed. This scheme is to directly perform cluster analysis without eliminating the influence of free points, resulting in a large deviation in the results of the clustering points obtained by analysis. The existing weighted clustering labeling technology also has the problem that the analysis results of the clustering points are large in deviation and it is difficult to perform cluster analysis on different medical data, resulting in the final clustering labeling results being inaccurate. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the prior art to at least a certain extent, by establishing a vital sign data record database based on a large data set to store each data record, then analyzing and statistically analyzing a weight set of the vital sign data based on the vital sign data record database, then analyzing the weight set to obtain a cluster group after excluding free coordinate points, then analyzing the cluster group through a clustering algorithm to obtain weight cluster points of the vital sign data, then calculating the cluster value of the vital sign data based on the weight cluster point, then sorting and numbering the cluster values ​​of different vital sign data to obtain a cluster queue, and finally clustering and marking the vital sign data based on the cluster queue, so as to solve the problem that the existing weight clustering marking technology still has large deviations in the analysis results of the cluster points and it is difficult to perform cluster analysis on different medical data, resulting in the final cluster marking result being inaccurate.

[0005] To achieve the above objectives, in a first aspect, the present application provides a data weight clustering labeling method based on a large data set, comprising the following steps:

[0006] Based on large data sets, statistical weight sets of vital signs data;

[0007] The weight set is analyzed by clustering algorithm to obtain weight clustering points of vital sign data;

[0008] The clustering value of the vital sign data is calculated based on the weighted clustering points, and then the vital sign data is clustered and marked according to the clustering values ​​of different vital sign data.

[0009] Furthermore, based on the large data set, the weight set of statistical vital sign data includes the following sub-steps:

[0010] Based on the large data set, a vital sign data record database is established to store each data record;

[0011] A weight set of statistical vital sign data is analyzed based on the vital sign data record database.

[0012] Furthermore, based on the large data set, establishing a vital sign data record database to store each data record includes the following sub-steps:

[0013] For any physical sign data, a physical sign data recording database is established, and each physical sign data has a corresponding physical sign data recording database;

[0014] The data records stored in the physical sign data record database include data numbers, data weights, data values ​​and evaluation values;

[0015] The data number is the sorting number of the data record in the vital sign data record database; the data weight is the weight corresponding to the vital sign data in the field to which this data record applies; the data value is the value of the vital sign data of the patient monitored by this data record; and the evaluation value is the final calculated result of the health evaluation calculation of the patient involved in the data record.

[0016] Furthermore, analyzing and calculating the weight set of the statistical vital sign data based on the vital sign data record database includes the following sub-steps:

[0017] Calculate the data value and divide it by the evaluation value, and mark the result as the data ratio;

[0018] Mark the data weight and data proportion in a data record as a set of sign weight groups;

[0019] Count all the weight groups of physical signs in the same physical sign data record database and integrate them into a weight set;

[0020] Each of the vital sign data has a corresponding weight set.

[0021] Furthermore, the weight set is analyzed by a clustering algorithm to obtain weight clustering points of the vital sign data, including the following sub-steps:

[0022] A plane rectangular coordinate system including only the first quadrant is established with the physical sign weight as the X-axis and the data proportion as the Y-axis, which is named as a data weight distribution diagram. Each weight set is constructed with an independent data weight distribution diagram;

[0023] All the weight groups of the physical signs in the same weight set are entered into the data weight distribution map, and the coordinate points therein are named as data weight points. A circle is constructed with any data weight point as the center and the first correlation distance as the radius, and is named as the correlation circle. It is then found whether there is a data weight point in the correlation circle. If so, a data correlation signal is output, and if not, a data non-correlation signal is output;

[0024] If a data association signal is output, the data weight in the association circle is marked as an association point, and then an association circle is constructed with the association point as the center and the first association distance as the radius, and the judgment is made again;

[0025] When the data association signal is no longer output, the data weight point as the center of the circle and the associated points are all marked as cluster coordinate points. At the same time, the cluster coordinate points obtained in this analysis are summarized into a cluster group, and they will no longer be used as data weight points for subsequent cluster coordinate point analysis;

[0026] Reconstruct the cluster group for correlation circle analysis until all data weight points are converted into cluster coordinate points and then stop the analysis. At this time, several cluster groups are obtained. The number of cluster coordinate points in the cluster group is marked as the number of clusters. It is determined whether the number of clusters is less than or equal to the first error number. If so, a cluster error signal is output, and if not, a cluster correct signal is output;

[0027] If a clustering error signal is output, the cluster group is dissolved, and the cluster coordinate points in it are marked as free coordinate points. Each cluster group is analyzed to obtain a number of free coordinate points.

[0028] The remaining cluster groups are analyzed using the mean shift clustering algorithm, and the center points obtained from the analysis are marked as weighted cluster points.

[0029] Furthermore, calculating the clustering value of the vital sign data based on the weighted clustering points, and then clustering and marking the vital sign data according to the clustering values ​​of different vital sign data includes the following sub-steps:

[0030] The clustering values ​​of the vital sign data are calculated based on the weighted clustering points, and then the clustering values ​​of different vital sign data are sorted and numbered to obtain a clustering queue;

[0031] The vital sign data were clustered and labeled based on the cluster cohort.

[0032] Furthermore, the clustering values ​​of the vital sign data are calculated based on the weighted clustering points, and the clustering values ​​of different vital sign data are sorted and numbered to obtain the clustering queue, which includes the following sub-steps:

[0033] For any physical sign data, the average value of the weighted clustering points of the physical sign data is calculated, and the calculation result is marked as the clustering value;

[0034] In order from small to large, the cluster values ​​of all physical sign data are sorted and numbered, and the symbol P is used to represent the cluster values. n Indicates, where n is a non-zero natural number and n is the serial number of P, the maximum value of n is marked as max(n), and the cluster queue is obtained after sorting and numbering.

[0035] Furthermore, clustering and labeling the vital sign data based on the clustering cohort includes the following sub-steps:

[0036] In the cluster queue, P n With n as the horizontal axis and the cluster value as the vertical axis, a rectangular coordinate system containing only the first quadrant is established, named the classification labeling diagram;

[0037] The classification mark graph is analyzed by the mean shift clustering algorithm, and the center point obtained by the analysis is marked as the classification mark point, and a number of classification mark points are obtained through the analysis;

[0038] Sort and number the classification mark points in ascending order, using the symbol T i Indicates, where i is a non-zero natural number and i is the serial number of T, the maximum value of i is marked as max(i), and max(i) cluster groups are established, each named as the i-th group, and the symbol R i express;

[0039] Starting from n=1 and i=1, calculate |P n -T i |, mark the calculation result as S(n,i), where (n,i) is the serial number of S, and determine whether i is equal to max(i). If not, set i+1 and calculate S(n,i) again. If not, set n+1 and reset i to 1, and recalculate S(n,i);

[0040] By calculating, we get several S(n,i), start from n=1, find the minimum value in S(n,i), mark i as h, and set P n Incorporate R h , where R h R represents i=h i ; Determine whether n is equal to max(n). If so, stop searching. If not, add n+1 and search and group again.

[0041] Calculate max(i) / 2, mark the result as f, and replace R with i≥f i Mark as important data of physical signs, and set R i Labelled as secondary data.

[0042] In a second aspect, the present application provides an electronic device, including a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the above method are performed.

[0043] In a third aspect, the present application provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the above method are performed.

[0044] Beneficial effects of the present invention: The present invention establishes a vital sign data record database based on a large data set to store each data record, then analyzes and statistics the weight set of the vital sign data based on the vital sign data record database, then analyzes the weight set to exclude free coordinate points to obtain cluster groups, and then analyzes the cluster groups through a clustering algorithm to obtain weight cluster points of the vital sign data. The advantage is that the free coordinate points in the data weight distribution diagram are eliminated, and then the cluster groups are analyzed through a clustering algorithm to effectively improve the accuracy of the cluster analysis, eliminate the influence of small-proportion points on the cluster analysis results, and improve the accuracy and rationality of weight clustering;

[0045] The present invention calculates the clustering value of the vital sign data based on the weighted clustering points, sorts and numbers the clustering values ​​of different vital sign data to obtain the clustering queue, and finally clusters and marks the vital sign data based on the clustering queue. The advantage is that the weighted clustering points of different vital sign data are obtained through the previous cluster analysis, and the weighted clustering points unify the different vital sign data and are no longer limited by the different units and standards between different vital sign data. In addition, since the vital sign data in the human body are complex and diverse, the same vital sign data exist in different organs, but the influence of some vital sign data in most organs or tissues is relatively small. If they are not marked, medical staff may spend time and effort to monitor them, but the effect is minimal. By clustering and marking all the vital sign data, important vital sign data and secondary vital sign data are screened out, and medical staff can reduce the monitoring of secondary vital sign data and spend more energy and resources to monitor important vital sign data, thereby improving the accuracy and effectiveness of weighted cluster marking. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a flow chart of the steps of the method of the present invention;

[0047] Figure 2is a data weight distribution diagram of the present invention;

[0048] Figure 3 A schematic diagram of the association circle and the association point of the present invention;

[0049] Figure 4 is a schematic diagram of the distribution of cluster groups of the present invention;

[0050] Figure 5 The data weight distribution diagram of the present invention with free coordinate points removed;

[0051] Figure 6 It is a schematic diagram of weighted clustering points of the present invention;

[0052] Figure 7 It is a classification mark diagram of the present invention;

[0053] Figure 8 Schematic diagram of the classification marking points of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] Example 1, please refer to Figure 1 As shown, the present application provides a data weight clustering labeling method based on a large data set, comprising the following steps:

[0056] Step S1, based on the large data set, calculates the weight set of vital sign data; Step S1 includes the following sub-steps:

[0057] Step S101, based on the large data set, establish a vital sign data record database to store each data record;

[0058] Step S101 includes the following sub-steps:

[0059] Step S101.1, for any physical sign data, a physical sign data recording database is established, the physical sign data includes respiratory rate, blood pressure, alanine aminotransferase, alkaline phosphatase and other data for evaluating the health status of different organs in the human body, and each physical sign data has a corresponding physical sign data recording database established;

[0060] In specific implementation, the vital sign data in this embodiment are monitoring data of various tissues and organs in the human body for evaluating human health, such as respiratory rate can be used to evaluate the patient's lung health and the patient's overall health, such as blood pressure can evaluate the patient's heart health, and alanine aminotransferase and alkaline phosphatase can be used to evaluate the patient's liver health. Some vital sign data can simultaneously evaluate the health status of multiple tissues or organs in the patient's body, and when the vital sign data are applied in different aspects, their data weights will also change accordingly. Many vital sign data have little effect on other parts except special tissues or organs, which is not enough to reflect the health status of the human body, but medical staff may spend time and energy to monitor them, wasting manpower and material resources. This embodiment aims to find out vital sign data that plays an important role in the human body through clustering tags, so that medical staff can spend more manpower and material resources to monitor important vital sign data and improve the effect of patient vital sign monitoring;

[0061] Step S101.2, the data records stored in the vital sign data record database include data numbers, data weights, data values, and evaluation values;

[0062] Step S101.3, the data number is the sorting number of the data record in the vital sign data record database; the data weight is the weight corresponding to the vital sign data in the field to which this data record applies; the data value is the value of the vital sign data of the patient monitored by this data record; and the evaluation value is the final calculated result of the health evaluation calculation of the patient involved in the data record;

[0063] In the specific implementation, taking the vital sign data glucose as an example, part of the data of the glucose vital sign data record database constructed based on the large data set is shown in the following Table 1:

[0064] Table 1 Partial data of glucose vital sign data record database

[0065]

[0066] When vital sign data is used to assess the health status of users, in addition to basic threshold comparison, different health index calculation formulas are used to calculate an assessment value for assessing the patient's health status. When assessing different tissues, organs or physiological characteristics of patients, the health index calculation formulas are different, so vital sign data also have different data weights. The data in the vital sign data record database are directly obtained by connecting with the hospital's big data set, which stores a huge amount of medical data;

[0067] Step S102, analyzing and calculating a weight set of the vital sign data based on the vital sign data record database;

[0068] Step S102 includes the following sub-steps:

[0069] Step S102.1, calculating the data value divided by the evaluation value, and marking the calculation result as the data proportion;

[0070] Step S102.2, marking the data weight and data proportion in a data record as a set of physical sign weight groups;

[0071] Step S102.3, counting all the physical sign weight groups in the same physical sign data record database, and integrating them into a weight set;

[0072] Step S102.4, each vital sign data has a corresponding weight set;

[0073] In the specific implementation, taking Table 1 as an example, in the data No. 100001, the data value is 3.9, the evaluation value is 36.79, and the data proportion is calculated to be 0.106, that is, 10.6%. The calculation result retains three decimal places. In the data No. 100001, the data weight is 0.33, that is, (0.33, 10.6%) is a set of physical sign weight groups; the physical sign data of glucose are recorded in the database to record the physical sign weight group of each data, and the weight set is obtained by integration. Since the weight set obtained in this embodiment is the weight set of glucose, it is named the glucose weight set. The weight sets of different physical sign data are independent of each other. The glucose weight set includes several physical sign weight groups such as (0.33, 10.6%), (0.34, 14.2%) and (0.58, 12.1%).

[0074] Step S2, analyzing the weight set by a clustering algorithm to obtain weight clustering points of the vital sign data; Step S2 includes the following sub-steps:

[0075] See also Figure 2 As shown, in step S201, a plane rectangular coordinate system including only the first quadrant is established with the physical sign weight as the X-axis and the data proportion as the Y-axis, which is named as a data weight distribution diagram, and each weight set is constructed with an independent data weight distribution diagram;

[0076] See also Figure 3 As shown, in step S202, all the body weight groups in the same weight set are entered into the data weight distribution map, and the coordinate points therein are named as data weight points. A circle is constructed with any data weight point as the center and the first correlation distance as the radius, and is named as the correlation circle. It is checked whether there is a data weight point in the correlation circle. If so, a data correlation signal is output, and if not, a data non-correlation signal is output;

[0077] Step S203, if a data association signal is output, the data weight in the association circle is marked as an association point, and then an association circle is constructed with the association point as the center and the first association distance as the radius, and judgment is made again;

[0078] Step S204: when the data association signal is no longer output, the data weight point as the circle center and the associated points are all marked as cluster coordinate points, and the cluster coordinate points obtained in this analysis are summarized into a cluster group, and they will no longer be used as data weight points for subsequent cluster coordinate point analysis;

[0079] In the specific implementation, the data weight distribution diagram is as follows Figure 2 As shown, Figure 2 Each coordinate point in is a set of feature weights. Figure 2 It is only the data weight distribution diagram of the vital sign data "glucose"; the first association distance is obtained by historical analysis. The function of the first association distance is to pre-process the data weight distribution diagram before cluster analysis, find out the free coordinate points in the data weight distribution diagram, and achieve the purpose of improving the accuracy of cluster analysis; the first association distance is set in the range of 0.02 to 0.1, and the preferred first association distance is set to 0.05. The relationship between the association circle and the association point is as follows Figure 3 As shown, Figure 3 In the figure, the black circle is the data weight point within the association circle, that is, the association point, and the data weight point outside the association circle is not the association point;

[0080] See also Figure 4 As shown, step S205, reconstruct the cluster group for correlation circle analysis, and stop the analysis until all the data weight points are converted into cluster coordinate points. At this time, a number of cluster groups are obtained, and the number of cluster coordinate points in the cluster group is marked as the number of clusters. It is determined whether the number of clusters is less than or equal to the first error number. If so, a cluster error signal is output, and if not, a cluster correct signal is output;

[0081] Step S206: if a clustering error signal is output, the cluster group is dissolved, and the cluster coordinate points therein are marked as free coordinate points, and each cluster group is analyzed to obtain a number of free coordinate points;

[0082] See also Figures 5 and 6 As shown, step S207, the remaining cluster groups are analyzed by the mean shift clustering algorithm, and the center points obtained by the analysis are marked as weighted cluster points;

[0083] In the specific implementation, usually, at least 5 cluster coordinate points are required to form a cluster group, so the first error number is set to 5; the distribution of cluster groups is as follows Figure 4 As shown, Figure 4 The three largest cluster groups in the cluster are marked with different colors, and the remaining uncolored coordinate points are all free coordinate points. By eliminating free coordinate points, the existing mean shift clustering algorithm is used to directly Figure 5Cluster analysis can greatly improve the processing speed and accuracy of cluster analysis; by analyzing the weighted cluster points, Figure 6 As shown, the clustering weights are 0.2895, 0.6263 and 0.7206 respectively, retaining four decimal places. The clustering weights only consider the value of the X-axis, not the value of the Y-axis.

[0084] Step S3, calculating the clustering value of the vital sign data based on the weighted clustering points, and then clustering and marking the vital sign data according to the clustering values ​​of different vital sign data; Step S3 includes the following sub-steps:

[0085] Step S301, calculating the clustering value of the vital sign data based on the weighted clustering points, and then sorting and numbering the clustering values ​​of different vital sign data to obtain a clustering queue;

[0086] Step S301 includes the following sub-steps:

[0087] Step S301.1, for any physical sign data, calculate the average value of the weighted clustering points of the physical sign data, and mark the calculation result as the clustering value;

[0088] Step S301.2, sort and number the cluster values ​​of all vital sign data in ascending order, using the symbol P n Indicates, where n is a non-zero natural number and n is the serial number of P, the maximum value of n is marked as max(n), and the cluster queue is obtained after sorting and numbering;

[0089] In the specific implementation, the cluster value obtained by calculation is 0.5455, and the calculation result is retained to four decimal places. The cluster value calculated in this embodiment is the glucose cluster value. When sorting, it is necessary to integrate the cluster values ​​of all vital sign data for sorting and numbering. The cluster values ​​from P1 to P1 are obtained by sorting. 88 , where 1≤n≤88, max(n)=88;

[0090] Step S302, clustering and marking the vital sign data based on the clustering queue;

[0091] Step S302 includes the following sub-steps:

[0092] See also Figures 7 and 8 As shown, step S302.1, clustering queue P n With n as the horizontal axis and the cluster value as the vertical axis, a rectangular coordinate system containing only the first quadrant is established, named the classification labeling diagram;

[0093] Step S302.2, analyzing the classification mark graph by using a mean shift clustering algorithm, marking the center point obtained by the analysis as a classification mark point, and obtaining a plurality of classification mark points by the analysis;

[0094] Step S302.3, sort and number the classification mark points in ascending order, using the symbol T i Indicates, where i is a non-zero natural number and i is the serial number of T, the maximum value of i is marked as max(i), and max(i) cluster groups are established, each named as the i-th group, and the symbol R i express;

[0095] In the specific implementation, the classification labeling map is constructed as follows Figure 7 As shown in the figure, the classification mark map is analyzed by the mean shift clustering algorithm, and the classification mark points are obtained as follows Figure 8 As shown, T1 to T6 are obtained by sorting and numbering, 1≤i≤6, max(i)=6, and 6 cluster groups are established, namely the first cluster group, the second cluster group, the third cluster group, the fourth cluster group, the fifth cluster group and the sixth cluster group, that is, R1 to R6;

[0096] Step S302.4, starting from n=1 and i=1, calculate |P n -T i |, mark the calculation result as S(n,i), where (n,i) is the serial number of S, and determine whether i is equal to max(i). If not, set i+1 and calculate S(n,i) again. If not, set n+1 and reset i to 1, and recalculate S(n,i);

[0097] Step S302.5, obtain several S(n,i) by calculation, start from n=1, find the minimum value in S(n,i), mark i as h, and set P n Incorporate R h , where R h R represents i=h i ; Determine whether n is equal to max(n). If so, stop searching. If not, add n+1 and search and group again.

[0098] Step S302.6, calculate max(i) / 2, mark the result as f, and set R i Mark as important data of physical signs, and set R i Labeled as secondary data of signs;

[0099] In the specific implementation, in this embodiment, P1 is 0.0738, T1 is 0.1024, and S(1,1)=0.0286 is obtained by calculation. For P1, S(1,1), S(1,2), S(1,3), S(1,4), S(1,5) and S(1,6) are calculated. By comparison, S(1,1) is the smallest. At this time, i=1, that is, h=1, P1 is included in R1, that is, P1 is included in the first cluster grouping, and the physical sign data corresponding to P1 is growth hormone, that is, the physical sign data "growth hormone" is summarized as the first cluster grouping, and so on, P2 to P are analyzed. 88 Clustering grouping; calculate max(i) / 2=f=3, mark the vital sign data in R3, R4, R5 and R6 as important vital sign data, and mark the vital sign data in R1 and R2 as secondary vital sign data; when monitoring the health status of patients, medical staff focus on monitoring the important vital sign data.

[0100] Embodiment 2, this embodiment provides an electronic device, which may include: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus. The memory stores computer-readable instructions, and the processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps in the data weight clustering labeling method based on a large data set are executed to achieve the following functions: based on the large data set, the weight set of the vital sign data is counted; the weight set is analyzed by a clustering algorithm to obtain the weight clustering points of the vital sign data; the clustering value of the vital sign data is calculated based on the weight clustering points, and then the vital sign data is clustered and labeled according to the different clustering values ​​of the vital sign data.

[0101] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0102] Embodiment 3. The present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the data weight clustering labeling method based on a large data set provided by the above methods, and the method includes: based on the large data set, counting the weight set of vital sign data; analyzing the weight set through a clustering algorithm to obtain weight clustering points of the vital sign data; calculating the clustering value of the vital sign data based on the weight clustering points, and then clustering and labeling the vital sign data according to different clustering values ​​of the vital sign data.

[0103] Embodiment 4, the present application also provides a computer-readable storage medium, and the present application provides a storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the data weight clustering labeling method based on a large data set are executed to achieve the following functions: based on the large data set, a weight set of vital sign data is counted; the weight set is analyzed by a clustering algorithm to obtain weight clustering points of the vital sign data; the clustering value of the vital sign data is calculated based on the weight clustering points, and then the vital sign data is clustered and labeled according to different clustering values ​​of the vital sign data.

[0104] Through the description of the above implementation methods, the embodiments of the present invention can be provided as methods, systems or computer program products. Based on such an understanding, the above technical solutions can be essentially or partly contributed to the prior art in the form of software products, which can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and include several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0105] In the embodiments provided in the present application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of systems, modules and units can be electrical, mechanical or other forms.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application 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. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A data weight clustering labeling method based on a large data set, characterized in that: The steps include: Based on large data sets, statistical weight sets of vital signs data; The weight set is analyzed by clustering algorithm to obtain weight clustering points of vital sign data; The clustering value of the vital sign data is calculated based on the weighted clustering points, and then the vital sign data is clustered and marked according to the clustering values ​​of different vital sign data.

2. The data weight clustering labeling method based on a large data set according to claim 1 is characterized in that: Based on the large data set, the weight set of statistical vital sign data includes the following sub-steps: Based on the large data set, a vital sign data record database is established to store each data record; A weight set of statistical vital sign data is analyzed based on the vital sign data record database.

3. The data weight clustering labeling method based on a large data set according to claim 2 is characterized in that: Based on the large data set, establishing a vital sign data record database to store each data record includes the following sub-steps: For any physical sign data, a physical sign data recording database is established, and each physical sign data has a corresponding physical sign data recording database; The data records stored in the physical sign data record database include data numbers, data weights, data values ​​and evaluation values; The data number is the sorting number of the data record in the vital sign data record database; the data weight is the weight corresponding to the vital sign data in the field to which this data record applies; the data value is the value of the vital sign data of the patient monitored by this data record; and the evaluation value is the final calculated result of the health evaluation calculation of the patient involved in the data record.

4. The data weight clustering labeling method based on a large data set according to claim 3 is characterized in that: The weight set of analyzing statistical vital sign data based on the vital sign data record database includes the following sub-steps: Calculate the data value and divide it by the evaluation value, and mark the result as the data ratio; Mark the data weight and data proportion in a data record as a set of sign weight groups; Count all the weight groups of physical signs in the same physical sign data record database and integrate them into a weight set; Each of the vital sign data has a corresponding weight set.

5. The data weight clustering labeling method based on a large data set according to claim 4 is characterized in that: Analyzing the weight set through the clustering algorithm to obtain the weight clustering points of the vital sign data includes the following sub-steps: A plane rectangular coordinate system including only the first quadrant is established with the physical sign weight as the X-axis and the data proportion as the Y-axis, which is named as a data weight distribution diagram. Each weight set is constructed with an independent data weight distribution diagram; All the weight groups of the physical signs in the same weight set are entered into the data weight distribution map, and the coordinate points therein are named as data weight points. A circle is constructed with any data weight point as the center and the first correlation distance as the radius, and is named as the correlation circle. It is then found whether there is a data weight point in the correlation circle. If so, a data correlation signal is output, and if not, a data non-correlation signal is output; If a data association signal is output, the data weight in the association circle is marked as an association point, and then an association circle is constructed with the association point as the center and the first association distance as the radius, and the judgment is made again; When the data association signal is no longer output, the data weight point as the center of the circle and the associated points are all marked as cluster coordinate points. At the same time, the cluster coordinate points obtained in this analysis are summarized into a cluster group, and they will no longer be used as data weight points for subsequent cluster coordinate point analysis; Reconstruct the cluster group for correlation circle analysis until all data weight points are converted into cluster coordinate points and then stop the analysis. At this time, several cluster groups are obtained. The number of cluster coordinate points in the cluster group is marked as the number of clusters. It is determined whether the number of clusters is less than or equal to the first error number. If so, a cluster error signal is output, and if not, a cluster correct signal is output; If a clustering error signal is output, the cluster group is dissolved, and the cluster coordinate points in it are marked as free coordinate points. Each cluster group is analyzed to obtain a number of free coordinate points. The remaining cluster groups are analyzed using the mean shift clustering algorithm, and the center points obtained from the analysis are marked as weighted cluster points.

6. The data weight clustering labeling method based on a large data set according to claim 5 is characterized in that: Calculating the clustering value of the vital sign data based on the weighted clustering points, and then clustering and marking the vital sign data according to the clustering values ​​of different vital sign data includes the following sub-steps: The clustering values ​​of the vital sign data are calculated based on the weighted clustering points, and then the clustering values ​​of different vital sign data are sorted and numbered to obtain a clustering queue; The vital sign data were clustered and labeled based on the cluster cohort.

7. The data weight clustering labeling method based on a large data set according to claim 6 is characterized in that: The clustering values ​​of the vital sign data are calculated based on the weighted clustering points, and the clustering values ​​of different vital sign data are sorted and numbered to obtain the clustering queue, which includes the following sub-steps: For any physical sign data, the average value of the weighted clustering points of the physical sign data is calculated, and the calculation result is marked as the clustering value; In order from small to large, the cluster values ​​of all physical sign data are sorted and numbered, and the symbol P is used to represent the cluster values. n Indicates, where n is a non-zero natural number and n is the serial number of P, the maximum value of n is marked as max(n), and the cluster queue is obtained after sorting and numbering.

8. The data weight clustering labeling method based on a large data set according to claim 6 is characterized in that: Clustering and labeling of vital sign data based on clustering cohorts includes the following sub-steps: In the cluster queue, P n With n as the horizontal axis and the cluster value as the vertical axis, a rectangular coordinate system containing only the first quadrant is established, named the classification labeling diagram; The classification mark graph is analyzed by the mean shift clustering algorithm, and the center point obtained by the analysis is marked as the classification mark point, and a number of classification mark points are obtained through the analysis; Sort and number the classification mark points in ascending order, using the symbol T i Indicates, where i is a non-zero natural number and i is the serial number of T, the maximum value of i is marked as max(i), and max(i) cluster groups are established, each named as the i-th group, and the symbol R i express; Starting from n=1 and i=1, calculate |P n -T i |, mark the calculation result as S(n,i), where (n,i) is the serial number of S, and determine whether i is equal to max(i). If not, set i+1 and calculate S(n,i) again. If not, set n+1 and reset i to 1, and recalculate S(n,i); By calculating, we get several S(n,i), start from n=1, find the minimum value in S(n,i), mark i as h, and set P n Incorporate R h , where R h R represents i=h i ; Determine whether n is equal to max(n). If so, stop searching. If not, add n+1 and search and group again. Calculate max(i) / 2, mark the result as f, and replace R with i≥f i Mark as important data of physical signs, and set R i Labelled as secondary data.

9. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the method according to any one of claims 1 to 8 are executed.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are executed.

Images