A shared oxygen concentrator operation management method and system

Abstract

The present invention relates to the technical field of data management, and proposes a shared oxygen concentrator operation management method and system, including: collecting operating data of multiple dimensions of the oxygen concentrator; obtaining the initial change degree of each dimensional combination at each time point according to the change in the correlation of the operating data of two dimensions in the dimensional combination under the change of time point; obtaining the comprehensive change degree of each time point; dividing the time axis into several time periods based on the comprehensive change degree of the time point; obtaining the correlation distance between any two time periods according to the correlation of the change of the operating data of two dimensions in each dimensional combination in different time periods; clustering the time periods to obtain several time period clusters; composing slices of the operating data of multiple dimensions under each time period cluster; compressing and storing several operating data under each dimension in each time period in each slice. The present invention aims to solve the problem that direct storage of a large amount of multi-dimensional data of the oxygen concentrator will affect data access speed and management efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of data management, and in particular to a method and system for operating and managing a shared oxygen concentrator. Background Art

[0002] The application of Internet of Things (IoT) in the medical field is becoming more and more mature, so as to provide better medical services for patients. As a kind of medical equipment, oxygen concentrator can be managed and used more intelligently and efficiently through the application of IoT technology; however, there are some problems with the traditional management methods of oxygen concentrators, such as low equipment utilization and difficulty in real-time monitoring of equipment status. IoT technology connects oxygen concentrators to the Internet to realize data interaction and real-time monitoring between devices; this makes it possible to manage oxygen concentrators intelligently, for example, sensors can be used to monitor oxygen concentration, equipment working status and other information in real time, and transmit these data to the cloud for analysis and storage.

[0003] However, when the oxygen concentrator transmits and stores multidimensional data through the Internet of Things, the amount of data generated by the multidimensional data is too large. Direct compression and storage will seriously affect the access speed and occupy a large storage space, which will lead to low efficiency in the analysis and management of the multidimensional data of the oxygen concentrator. It is difficult to achieve rapid adjustment of the oxygen concentration of the oxygen concentrator and stable operation of the equipment. Therefore, it is necessary to use a distributed storage system to perform distributed compression storage on the large amount of multidimensional data generated by the oxygen concentrator. Summary of the invention

[0004] The present invention provides a shared oxygen concentrator operation management method and system to solve the problem that the direct storage of a large amount of multi-dimensional data of the existing oxygen concentrator will affect the data access speed and management efficiency. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present invention provides a method for operating and managing a shared oxygen concentrator, the method comprising the following steps:

[0006] Collecting operation data of multiple dimensions of the oxygen concentrator, wherein the operation data of the multiple dimensions correspond to the same time axis, and the time axis includes a plurality of time points;

[0007] Take any two dimensions as a dimension combination, and obtain the initial change degree of each dimension combination at each time point according to the change in the correlation between the operating data of the two dimensions in the dimension combination at the time point; obtain the comprehensive change degree at each time point according to the initial change degree and the correlation between the operating data of the two dimensions in the dimension combination;

[0008] The time axis is divided into several time periods based on the comprehensive change degree of the time points; the correlation distance between any two time periods is obtained based on the correlation of the operation data changes of two dimensions in the combination of dimensions in different time periods; the time periods are clustered according to the correlation distance to obtain several time period clusters; the operation data of multiple dimensions under each time period cluster are sliced;

[0009] Several running data in each dimension of each time period in each slice are compressed and stored.

[0010] Preferably, the initial change degree of each dimension combination at each time point is obtained by:

[0011] According to the change of the correlation of the running data of the two dimensions in the dimension combination at the time point, the correlation of each dimension combination at each time point is obtained; Dimensions and The dimension combination corresponding to the dimension is taken as the target dimension combination. The initial change degree of the target dimension combination at each time point The calculation method is:

[0012]

[0013] in, Indicates The order value of a time point, Indicates The order value of a time point, Indicates The initial change degree of the target dimension combination at a time point, Indicates The correlation of the target dimension combination at each time point, Indicates The correlation of the target dimension combination at each time point, It means to find the absolute value. Represents an exponential function with a natural constant as its base.

[0014] Preferably, the correlation of each dimension combination at each time point is obtained by:

[0015] Get the The sequence of running data of the first two time points of the dimension, and the The Pearson correlation coefficient of the two sequences is calculated from the running data of the first two time points of each dimension, and the result is recorded as the correlation of the target dimension combination at the second time point.

[0016] A sequence consisting of the operating data of the first three time points of each of the two dimensions is obtained, and the Pearson correlation coefficient of the sequence is calculated as the correlation of the target dimension combination at the third time point; the calculation method of the correlation of the target dimension combination at the first time point is: obtain the absolute value of the difference between the operating data of the two dimensions in the target dimension combination at the first time point, and use the difference obtained by subtracting the absolute value of the difference from 1 as the correlation of the target dimension combination at the first time point.

[0017] Preferably, the method of obtaining the comprehensive degree of change at each time point includes:

[0018] Get all time points The mean of the correlation of the combination of dimensions is recorded as the first mean; the first mean is combined with the At the next time point The product of the initial change degree of the combination of dimensions is recorded as At the next time point The first product of the combination of dimensions; The mean of the first product of all dimension combinations at the time point is taken as the The overall degree of change at a certain point in time.

[0019] Preferably, the time axis is divided into several time periods based on the comprehensive change degree of the time points, including the specific method of:

[0020] The time points when the comprehensive change degree is greater than the change threshold are taken as segmentation points, and the first time point is taken as a segmentation point. The time axis composed of all time points is divided into several time periods through the segmentation points, where each segmentation point is taken as the first time point in the corresponding time period.

[0021] Preferably, the method of obtaining the correlation distance between any two time periods includes:

[0022] According to the correlation of the operating data of two dimensions in the dimension combination in any two time periods, several associated dimension combinations of each dimension in any two time periods and the time period difference fluctuation coefficient of each associated dimension combination are obtained;

[0023] No. The time period and The correlation distance of the time period The calculation method is:

[0024]

[0025] in, represents the number of dimensions, Indicates The dimension in The time period and The number of associated dimension combinations in a time period, Indicates The dimension in The time period and The first The time period difference volatility coefficient of the combination of related dimensions, Indicates The dimension in The time period and The first The first of the associated dimension combinations The correlation factor for each time period, Indicates The dimension in The time period and The first The first of the associated dimension combinations The correlation factor for each time period, It means to find the absolute value. Represents an exponential function with a natural constant as its base.

[0026] Preferably, the specific method for obtaining the combinations of several associated dimensions of each dimension in any two time periods and the time period difference fluctuation coefficient of each associated dimension combination is as follows:

[0027] For Dimensions and The time period and time period, obtain the In each dimension combination of dimensions, the The Pearson correlation coefficient of the running data of the two dimensions in the time period, and the The Pearson correlation coefficients of the running data of the two dimensions in the time period are respectively recorded as In each dimension combination of The correlation factors of the time period and Correlation factors for each time period;

[0028] Preset a relevant threshold and The correlation factors of the time period and The dimension combination whose correlation factors in each time period are greater than the correlation threshold is recorded as The dimension in The time period and Combination of related dimensions under different time periods;

[0029] For any associated dimension combination, obtain the The DTW distance between the sequences composed of the running data of another dimension in any two time periods in addition to the dimension, and the variance of all the obtained DTW distances is recorded as the time period difference fluctuation coefficient of the associated dimension combination.

[0030] Preferably, the method of obtaining a plurality of time period clusters includes:

[0031] DBSCAN clustering is performed on all time periods, and the distance measurement uses the correlation distance between time periods to obtain several clusters, which are recorded as several time period clusters.

[0032] Preferably, the operation data of multiple dimensions under each time period cluster is sliced, and the specific method includes:

[0033] For any time period cluster, a number of running data of each dimension in all time periods in the time period cluster constitute the slice corresponding to the time period cluster.

[0034] In a second aspect, another embodiment of the present invention provides a shared oxygen concentrator operation and management system, the system comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0035] The beneficial effects of the present invention are as follows: the present invention collects the operation data of multiple dimensions of the oxygen concentrator, divides the time period corresponding to the same time axis in different dimensions, and quantifies the correlation distance of the time period according to the correlation of the operation data changes in each dimension in each time period, thereby realizing the clustering of the time period and obtaining slices, and compressing and distributing the slices to reduce the storage space occupied by a large amount of operation data of the oxygen concentrator, and at the same time, the operation data can be quickly called based on the distributed storage system. Among them, the initial change degree of the time point is obtained by the correlation of the operation data changes at the same time point in different dimensions, and the comprehensive change degree of the time point is obtained by combining the correlation of the operation data changes in the dimension combination, and the time period is divided based on the comprehensive change degree, so that the overall changes of the operation data of the same dimension in the same time period are similar; then clustering is performed according to the correlation distance, so that the time periods with the same or similar distribution in the operation data of each dimension are clustered into the same time period cluster, so that the same slice reflects more operation data of multiple dimensions of the oxygen concentrator under the same working state, greatly improving the efficiency of compression and storage of slices, and finally completing the management of the operation data of the oxygen concentrator based on slices. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0037] Figure 1 A schematic flow chart of a shared oxygen generator operation management method provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0038] 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.

[0039] See also Figure 1 , which shows a flow chart of a shared oxygen concentrator operation management method provided by an embodiment of the present invention, the method comprising the following steps:

[0040] Step S001: Collect operating data of multiple dimensions of the oxygen concentrator.

[0041] The purpose of this embodiment is to perform distributed storage on the operating data of multiple dimensions generated during the operation of the oxygen concentrator. Therefore, it is necessary to arrange several different types of sensors on the oxygen concentrator to collect the operating data. This embodiment collects data of eight dimensions, including the concentration, flow rate and pressure of the oxygen production parameters of the oxygen concentrator, the air compressor parameters, pressure dew point and dew temperature during the operation of the oxygen concentrator, and the temperature and humidity in the environment where the oxygen concentrator is located.

[0042] Specifically, in this embodiment, the oxygen concentrator oxygen production parameters, such as concentration, flow rate and pressure, as well as the air compressor parameters, pressure dew point and dew temperature during the operation of the oxygen concentrator, a total of six dimensions of data are directly acquired through the oxygen concentrator equipment; the temperature and humidity in the environment are collected through the temperature sensor and the humidity sensor respectively, and the sampling time interval of the data in each dimension is 1 second. Data collection starts after the oxygen concentrator starts to run. After the data in each dimension is collected, the data in each dimension is numerically processed respectively, and the numerically processed data is recorded as the operating data of each dimension. Then, each operating data in each dimension corresponds to a time point, and the overall time axis corresponding to all operating data in different dimensions is the same, and the operating data in all dimensions are constrained by numerical processing. Within the range.

[0043] So far, a number of operating data of the oxygen concentrator in multiple dimensions have been collected.

[0044] It should be noted that in the storage process of oxygen concentrator operating data in different dimensions, in order to ensure that the oxygen concentration can be quickly adjusted and the oxygen concentrator equipment can operate stably according to the changes in the operating data in different dimensions, it is necessary to compress and store the oxygen concentrator operating data of different dimensions with large data volume; data slicing is to divide the data set into smaller parts, called "shards" or "slices", so that each slice can be easier to manage and process. In a distributed storage system, each slice can be stored on a different server, thereby improving storage capacity and access speed.

[0045] Step S002: according to the changes of the operating data at the same time point in different dimensions, obtain the comprehensive change degree of each time point; divide the time axis into several time periods based on the comprehensive change degree of the time point; according to the correlation of the changes of the operating data in different dimensions in different time periods, obtain the correlation distance between any two time periods; cluster the time periods according to the correlation distance to obtain several time period clusters; slice the operating data of multiple dimensions under each time period cluster.

[0046] Preferably, in one embodiment of the present invention, the comprehensive change degree at each time point is obtained according to the change of the running data at the same time point in different dimensions, and the specific method includes:

[0047] Combining any two different dimensions into a dimension combination will result in several dimension combinations. Dimensions and The dimension combination corresponding to the dimensions is taken as the target dimension combination, where ; Get the first The sequence of running data of the first two time points of the dimension, and the The Pearson correlation coefficient of the two sequences is calculated for the sequence consisting of the operating data of the first two time points of each dimension, and the result is recorded as the correlation of the target dimension combination at the second time point; similarly, the sequence consisting of the operating data of the first three time points of each dimension is obtained, and the Pearson correlation coefficient of the sequence is calculated as the correlation of the target dimension combination at the third time point; the correlation of the target dimension combination at each time point is obtained according to the above method. It is particularly noted that the calculation method of the correlation of the target dimension combination at the first time point is: obtain the absolute value of the difference between the operating data of the two dimensions in the target dimension combination at the first time point, and use the difference obtained by subtracting the absolute value of the difference from 1 as the correlation of the target dimension combination at the first time point; then The initial change degree of the target dimension combination at each time point The calculation method is:

[0048]

[0049] in, Indicates The order value of the time point, that is, The length of the two sequences corresponding to the correlation obtained at each time point; Indicates The order value of the time point, that is, The length of the two sequences corresponding to the correlation obtained at each time point; Indicates The initial change degree of the target dimension combination at a time point, Indicates The correlation of the target dimension combination at each time point, Indicates The correlation of the target dimension combination at each time point, It means to find the absolute value. represents an exponential function with a natural constant as the base. In this embodiment, Model to present inverse proportional relationship and normalization processing, As the input of the model, the implementer can set the inverse proportional function and the normalization function according to the actual situation; the initial change degree of the target dimension combination at each time point is obtained according to the above method; it is particularly noted that the initial change degree is not calculated at the first time point, and the initial change degree of the target dimension combination at the second time point is the correlation of the target dimension combination at the second time point.

[0050] It should be noted that the correlation change of adjacent time points is used as the reference value of the initial change degree, and the initial change degree of each time point calculated iteratively and the sequence length corresponding to the correlation are used as weights to adjust the reference of the correlation change of adjacent time points. If the initial change degree of a time point is large and the sequence length corresponding to the correlation is short, the smaller the reference of the correlation change between the time point and the previous time point, the lower the reference of the correlation change between the time point and the previous time point. The correlation changes of adjacent time points before the time point are obtained. The initial change at a time point.

[0051] Furthermore, according to the above method, the initial change degree of each time point in each dimension combination is obtained except the first time point, then The overall change degree at each time point The calculation method is:

[0052]

[0053] in, represents the number of dimension combinations, Indicates all time points The mean of the correlations of the dimension combinations, Indicates At the next time point The initial change degree of the combination of dimensions; the comprehensive change degree of each time point except the first time point is obtained according to the above method.

[0054] It should be noted that the comprehensive degree of change is obtained by weighted average of the initial change degrees of different dimensional combinations at the same time point, and the mean correlation of each dimensional combination is used as the weight. The larger the mean correlation, the more there is an overall response relationship between the corresponding dimensional combinations, and the greater the reference value of the corresponding initial change degree.

[0055] It should be noted that the operating data of different dimensions of the oxygen concentrator have different impacts on the monitoring of the oxygen concentrator, and there is a certain response relationship between the operating data of different dimensions during the operation of the oxygen concentrator. For example, certain parameters or indicators of the oxygen concentrator may respond to changes in the external environment or operating conditions. When the ambient temperature rises, the oxygen production efficiency of the oxygen concentrator may decrease; when the oxygen demand increases, the oxygen concentrator may automatically increase the oxygen production flow rate. Therefore, there is a certain relationship between the operating data of different dimensions of the oxygen concentrator. If the difference between the change in the operating data for a certain period of time and the above relationship is large, the data difference in this time period is large, and the corresponding data needs to be sliced ​​according to the difference.

[0056] Optionally, in other embodiments, for any dimension, the slope of the operating data at each time point in the dimension is obtained, and the difference between the slope of each time point and the adjacent previous time point is used as the initial change degree at each time point in the dimension; by averaging the initial change degrees of each time point in different dimensions, the comprehensive change degree of each time point is obtained, wherein the initial change degree and comprehensive change degree are not calculated for the first time point.

[0057] Preferably, in one embodiment of the present invention, the time axis is divided into several time periods based on the comprehensive change degree of the time points, including the specific method of:

[0058] A change threshold is preset. In this embodiment, the change threshold is described as 0.58. The time point when the comprehensive change degree is greater than the change threshold is used as the segmentation point. The time axis composed of all time points is divided into several time periods through the segmentation points, where each segmentation point is used as the first time point in the corresponding time period, and the first time point is also used as a segmentation point, that is, the first time point in the first time period.

[0059] It should be noted that at a time point with a greater degree of comprehensive change, the operating data of each dimension changes greatly at that time point, and segmentation is required to ensure that the changes between the operating data of the same dimension within the time period are small, and then subsequent slice acquisition is performed.

[0060] Preferably, in one embodiment of the present invention, the correlation distance between any two time periods is obtained according to the correlation of the operation data changes in different dimensions in different time periods, and the specific method includes:

[0061] For Dimensions and The time period and time periods (including ), get the value including the first In each dimension combination of dimensions, the The Pearson correlation coefficient of the running data of the two dimensions in the time period, and the The Pearson correlation coefficients of the running data of the two dimensions in the time period are respectively recorded as In each dimension combination of The correlation factors of the time period and The Pearson correlation coefficient is calculated based on the two sequences of the operation data of the two dimensions in the corresponding time period according to the time series; a correlation threshold is preset, and the correlation threshold in this embodiment is described as 0.65. The correlation factors of the time period and The dimension combination whose correlation factors in each time period are greater than the correlation threshold is recorded as The dimension in The time period and time periods; for any associated dimension combination, obtain the associated dimension combination except the The DTW distance between the sequences of the running data of another dimension in any two time periods in addition to the dimension is recorded as the variance of all the DTW distances obtained as the time period difference fluctuation coefficient of the associated dimension combination; according to the above method, the variance of all the DTW distances obtained in the first time period is recorded as the variance of all the DTW distances obtained in the first time period. The time period and The associated dimension combinations under different time periods, as well as the time period difference fluctuation coefficient of each associated dimension combination.

[0062] Further, The time period and The correlation distance of the time period The calculation method is:

[0063]

[0064] in, represents the number of dimensions, Indicates The dimension in The time period and The number of associated dimension combinations in a time period, Indicates The dimension in The time period and The first The time period difference volatility coefficient of the combination of related dimensions, Indicates The dimension in The time period and The first The first of the associated dimension combinations The correlation factor for each time period, Indicates The dimension in The time period and The first The first of the associated dimension combinations The correlation factor for each time period, It means to find the absolute value. represents an exponential function with a natural constant as the base. In this embodiment, Model to present inverse proportional relationship and normalization processing, As the input of the model, the implementer can set the inverse proportional function and the normalization function according to the actual situation; the correlation distance between any two time periods can be obtained according to the above method.

[0065] It should be noted that through The correlation benchmark value is constructed by the difference in the correlation factors of the first dimension in the two periods of the correlation dimension combination. The smaller the difference in the correlation factor, the The greater the correlation (relevance) between the two time periods in the first dimension in the association combination, the greater the correlation benchmark value; at the same time, the inverse proportional value of the time period difference fluctuation coefficient of the association dimension combination is used as the weight. The larger the time period difference fluctuation coefficient, the more likely the corresponding association dimension combination is. In another dimension of each dimension, the greater the change in correlation between time periods, the more chaotic the distribution, the smaller the confidence of the corresponding dimension and the associated dimension combination, and the smaller the corresponding weight; by weighted averaging the correlation benchmark values ​​of each dimension and each associated dimension combination, and then averaging the obtained means of each dimension, the correlation between the two time periods is obtained. The greater the correlation, the smaller the correlation distance. Therefore, the correlation distance is obtained by subtracting the correlation from 1.

[0066] Optionally, in other embodiments, The time period and Take the time period as an example, and get the The DTW distance between the sequences of the running data in the two time periods is recorded as The dimension in The time period and The time period distance of each time period; get the time period distance of each dimension in the The time period and The time period distance of each time period is taken as the average of all time period distances. The time period and The correlation distance of a time period.

[0067] It should be noted that after dividing the multi-dimensional operating data of the oxygen generator into time periods, it is necessary to obtain the relationship between dimensions in time periods with the same or similar distribution, and determine the similarity between time periods by analyzing the changing relationship between the time periods and the relationship between the obtained dimensions, and then slice them according to the similarity; the slicing process is based on cluster analysis, and the oxygen generator is a cyclic process during operation, including compression, filtration, separation, desorption and emission to ensure stable oxygen output, and other types of data such as the environment have different response relationships to different processes. Therefore, in order to obtain accurate response relationships, different time periods need to be clustered.

[0068] Preferably, in one embodiment of the present invention, the time periods are clustered according to the correlation distance to obtain a number of time period clusters; and the operation data of multiple dimensions under each time period cluster are sliced, including the specific method of:

[0069] In this embodiment, DBSCAN clustering is performed on all time periods, and the distance measurement adopts the correlation distance between time periods, thereby obtaining a number of clusters, which are recorded as a number of time period clusters; for any time period cluster, a number of operating data of each dimension in all time periods in the time period cluster together constitute a slice corresponding to the time period cluster, thereby obtaining a slice corresponding to each time period cluster; it should be noted that the slice contains a sequence composed of all operating data of each dimension in each time period under the time period cluster corresponding to the slice, that is, the slice is composed of a number of operating data sequences, and the time periods corresponding to the operating data sequences all belong to the time period cluster corresponding to the slice.

[0070] Optionally, in other embodiments, other clustering methods, such as K-means clustering, are used to cluster the time periods and obtain slices, wherein the distance metric uses the correlation distance between the time periods, and the specific clustering process is not described in detail in this embodiment.

[0071] At this point, by analyzing the changes in the correlation of operating data of different dimensions in time series, the comprehensive degree of change at the time point is obtained and the time period is divided; through the correlation of the operating data of each dimension between the time periods, the correlation distance between the time periods is quantified and clustered, and finally the multi-dimensional operating data of the oxygen concentrator is sliced ​​and obtained according to the time period.

[0072] Step S003: compress and store a number of operation data in each dimension in each time period in each slice.

[0073] Preferably, in one embodiment of the present invention, after the slices are obtained, revolving door compression is directly performed on a number of operating data in each dimension in each time period in each slice, and the tolerance parameter is implemented using a preset tolerance hyperparameter, i.e., 0.4, to obtain the compressed operating data of each time period, and distributed storage is completed based on the slice corresponding to the time cluster to which the time period belongs.

[0074] At this point, by analyzing the time series changes of the multi-dimensional operation data of the oxygen concentrator and slicing it, and performing revolving door compression on the data in the slices, distributed storage of the multi-dimensional operation data of the oxygen concentrator is achieved, thereby improving the adjustment, operation and management efficiency of the oxygen concentrator.

[0075] Another embodiment of the present invention provides a shared oxygen concentrator operation and management system, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, steps S001 to S003 of the above method are implemented.

[0076] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A shared oxygen concentrator operation management method, characterized in that: The method comprises the following steps: Collecting operation data of multiple dimensions of the oxygen concentrator, wherein the operation data of the multiple dimensions correspond to the same time axis, and the time axis includes a plurality of time points; Take any two dimensions as a dimension combination, and obtain the initial change degree of each dimension combination at each time point according to the change in the correlation between the operating data of the two dimensions in the dimension combination at the time point; obtain the comprehensive change degree at each time point according to the initial change degree and the correlation between the operating data of the two dimensions in the dimension combination; The time axis is divided into several time periods based on the comprehensive change degree of the time points; the correlation distance between any two time periods is obtained based on the correlation of the operation data changes of two dimensions in the combination of dimensions in different time periods; the time periods are clustered according to the correlation distance to obtain several time period clusters; the operation data of multiple dimensions under each time period cluster are sliced; Compress and store a number of running data in each dimension in each time period in each slice; The specific method of obtaining the correlation distance between any two time periods is as follows: According to the correlation of the operating data of two dimensions in the dimension combination in any two time periods, obtain several associated dimension combinations of each dimension in any two time periods and the time period difference fluctuation coefficient of each associated dimension combination, as well as the correlation factor of each time period; No. The time period and The correlation distance of the time period The calculation method is: in, represents the number of dimensions, Indicates The dimension in The time period and The number of associated dimension combinations in a time period, Indicates The dimension in The time period and The first The time period difference volatility coefficient of the combination of related dimensions, Indicates The dimension in The time period and The first The first of the associated dimension combinations The correlation factor for each time period, Indicates The dimension in The time period and The first The first of the associated dimension combinations The correlation factor for each time period, It means to find the absolute value. represents an exponential function with a natural constant as base; The specific acquisition method of the several associated dimension combinations of each dimension in any two time periods and the time period difference fluctuation coefficient of each associated dimension combination, as well as the correlation factor of each time period, is as follows: For Dimensions and The time period and time period, obtain the In each dimension combination of dimensions, the The Pearson correlation coefficient of the running data of the two dimensions in the time period, and the The Pearson correlation coefficients of the running data of the two dimensions in the time period are respectively recorded as In each dimension combination of The correlation factors of the time period and Correlation factors for each time period; Preset a relevant threshold and The correlation factors of the time period and The dimension combination whose correlation factors in each time period are greater than the correlation threshold is recorded as The dimension in The time period and Combination of related dimensions under different time periods; For any associated dimension combination, obtain the The DTW distance between the sequences composed of the running data of another dimension in any two time periods in addition to the dimension, and the variance of all the obtained DTW distances is recorded as the time period difference fluctuation coefficient of the associated dimension combination.

2. A shared oxygen concentrator operation management method according to claim 1, characterized in that: The initial change degree of each dimension combination at each time point is obtained by: According to the change of the correlation of the running data of the two dimensions in the dimension combination at the time point, the correlation of each dimension combination at each time point is obtained; Dimensions and The dimension combination corresponding to the dimension is taken as the target dimension combination. The initial change degree of the target dimension combination at each time point The calculation method is: in, Indicates The order value of a time point, Indicates The order value of a time point, Indicates The initial change degree of the target dimension combination at a time point, Indicates The correlation of the target dimension combination at each time point, Indicates The correlation of the target dimension combination at each time point, It means to find the absolute value. Represents an exponential function with a natural constant as its base.

3. A shared oxygen concentrator operation management method according to claim 2, characterized in that: The specific method for obtaining the correlation of each dimension combination at each time point is as follows: Get the The sequence of running data of the first two time points of the dimension, and the The Pearson correlation coefficient of the two sequences is calculated from the running data of the first two time points of each dimension, and the result is recorded as the correlation of the target dimension combination at the second time point. A sequence consisting of the operating data of the first three time points of each of the two dimensions is obtained, and the Pearson correlation coefficient of the sequence is calculated as the correlation of the target dimension combination at the third time point; the calculation method of the correlation of the target dimension combination at the first time point is: obtain the absolute value of the difference between the operating data of the two dimensions in the target dimension combination at the first time point, and use the difference obtained by subtracting the absolute value of the difference from 1 as the correlation of the target dimension combination at the first time point.

4. A shared oxygen concentrator operation management method according to claim 3, characterized in that: The specific method of obtaining the comprehensive change degree at each time point includes: Get all time points The mean of the correlation of the combination of dimensions is recorded as the first mean; the first mean is combined with the At the next time point The product of the initial change degree of the combination of dimensions is recorded as At the next time point The first product of the combination of dimensions; The mean of the first product of all dimension combinations at the time point is taken as the The overall degree of change at a certain point in time.

5. A shared oxygen concentrator operation management method according to claim 1, characterized in that: The specific method of dividing the time axis into several time periods based on the comprehensive change degree of the time points includes: The time points when the comprehensive change degree is greater than the change threshold are taken as segmentation points, and the first time point is taken as a segmentation point. The time axis composed of all time points is divided into several time periods through the segmentation points, where each segmentation point is taken as the first time point in the corresponding time period.

6. A shared oxygen concentrator operation management method according to claim 1, characterized in that: The specific method of obtaining a plurality of time period clusters includes: DBSCAN clustering is performed on all time periods, and the distance measurement uses the correlation distance between time periods to obtain several clusters, which are recorded as several time period clusters.

7. A shared oxygen concentrator operation management method according to claim 1, characterized in that: The specific method of slicing the operation data of multiple dimensions under each time period cluster includes: For any time period cluster, a number of running data of each dimension in all time periods in the time period cluster constitute the slice corresponding to the time period cluster.

8. A shared oxygen concentrator operation management system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the shared oxygen generator operation management method as described in any one of claims 1 to 7 are implemented.

Images