Waveform data processing method, device, terminal equipment and medium

Abstract

The present invention discloses a waveform data processing method, device, terminal equipment and medium. The method comprises: acquiring collected waveform data, performing real-time and / or quasi-real-time analysis on the collected waveform data to obtain analysis results. If the analysis result is that waveform data corresponding to a positive indication does not exist in the collected waveform data, then sampling and retaining the collected waveform data; if the analysis result is that waveform data corresponding to a positive indication exists in the collected waveform data, then retaining the collected waveform data, thereby solving the problem of insufficient storage of waveform data corresponding to a positive indication due to insufficient storage space when storing waveform data.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a waveform data processing method, device, terminal equipment and medium. Background Art

[0002] Waveform data is widely used in life to monitor periodic activities, such as electrocardiogram, respiratory rhythm, sleep data, etc. Doctors can analyze waveform data and determine the corresponding indications for patients from the waveform data of positive indications.

[0003] Usually, this type of waveform data is continuous time data and needs to be collected for a long time. The corresponding collection will take up a lot of storage space. When the storage space is insufficient, all previous waveform data will be deleted to store the current waveform data, or a period of observation time will be selected to store the waveform data corresponding to that period of time for analysis.

[0004] If the previous waveform data is deleted, when it is needed for analysis later, it may be found that the required waveform data has been deleted and the corresponding analysis cannot be performed. If only one section of waveform data is analyzed, on the one hand, the number of positive waveforms is limited due to the limited storage space, and not all data in this section of waveform data is useful for analysis. For example, in the electrocardiogram waveform data, most of the waveforms are waveforms corresponding to negative indications, and there may be only one or two waveforms corresponding to positive indications for analysis. On the other hand, it is impossible to compare the waveform data corresponding to the positive indications of the patient in other time periods, resulting in insufficient diagnosis and possible errors in the corresponding disease judgment. Summary of the invention

[0005] The main purpose of the present invention is to provide a waveform data processing method, aiming to solve the technical problem that when storing waveform data, the waveform data corresponding to the positive indication is insufficiently stored due to insufficient storage space.

[0006] To achieve the above object, the present invention provides a waveform data processing method, which comprises the following steps:

[0007] Get the collected waveform data;

[0008] Perform real-time and / or quasi-real-time analysis on the collected waveform data to obtain analysis results:

[0009] If the analysis result is that there is no waveform data corresponding to a positive indication in the collected waveform data, sampling and retaining the collected waveform data;

[0010] If the analysis result is that waveform data corresponding to a positive indication exists in the collected waveform data, the collected waveform data is retained.

[0011] Optionally, the step of acquiring the collected waveform data includes:

[0012] Acquiring collected waveform data at a preset frequency, wherein the preset frequency includes at least one frequency;

[0013] The collected waveform data is pre-analyzed. If the result of the pre-analysis is that the percentage value corresponding to the positive indication in the collected waveform data reaches a preset threshold, the preset frequency is increased to improve the accuracy of the collected samples.

[0014] Optionally, the step of performing real-time and / or quasi-real-time analysis on the collected waveform data to obtain an analysis result comprises:

[0015] Acquiring characteristic information of the collected waveform data;

[0016] According to the characteristic information, the collected waveform data is analyzed in real time and / or quasi real time for a preset target event to obtain an analysis result.

[0017] Optionally, if the analysis result is that waveform data corresponding to a positive indication exists in the collected waveform data, the step of retaining the collected waveform data includes:

[0018] If waveform data corresponding to a positive indication exists in the collected waveform data, the waveform data corresponding to the positive indication is retained as intermediate data, the waveform data within a preset range.

[0019] Optionally, if there is waveform data corresponding to a positive indication in the collected waveform data, then retaining the waveform data corresponding to the positive indication as intermediate data, the step of retaining the waveform data within a preset range further includes:

[0020] Recording the corresponding characteristic values ​​in the waveform data within the preset range;

[0021] The position information corresponding to the characteristic value is recorded.

[0022] Optionally, if the analysis result is that there is no waveform data corresponding to a positive indication in the collected waveform data, then after the step of sampling and retaining the collected waveform data, the step further includes:

[0023] Calculate the error data MSE corresponding to the sampled and retained waveform data according to the sampled and retained waveform data;

[0024] A quality level is identified for the sampled retained waveform data based on the MSE.

[0025] Optionally, after the step of identifying the quality level of the sampled and retained waveform data according to the MSE, the step further includes:

[0026] If the amount of waveform data retained by the sampling reaches a preset threshold, the waveform data with a quality level lower than the preset level is deleted.

[0027] In addition, to achieve the above-mentioned purpose, the present invention also provides a waveform data processing device, the waveform data processing device comprising:

[0028] An acquisition module, used for acquiring collected waveform data;

[0029] An analysis module, used for performing real-time and / or quasi-real-time analysis on the collected waveform data to obtain analysis results;

[0030] A sampling and retaining module, used for sampling and retaining the collected waveform data if the analysis result is that there is no waveform data corresponding to a positive indication in the collected waveform data;

[0031] A retaining module is used to retain the collected waveform data if the analysis result is that the collected waveform data contains waveform data corresponding to a positive indication.

[0032] In addition, to achieve the above-mentioned purpose, the present invention also provides a terminal device, which includes a memory, a processor, and a waveform data processing program stored in the memory and executable on the processor, and the waveform data processing program implements the steps of the waveform data processing method described above when executed by the processor.

[0033] In addition, to achieve the above-mentioned purpose, the present invention also provides a computer-readable storage medium, on which a waveform data processing program is stored, and when the waveform data processing is executed by a processor, the steps of the waveform data processing method as described above are implemented.

[0034] The present invention provides a waveform data processing method, device, terminal equipment and medium. The collected waveform data is acquired, and the collected waveform data is analyzed in real time and / or quasi-real time to obtain an analysis result. If the analysis result is that the waveform data corresponding to the positive indication does not exist in the collected waveform data, the collected waveform data is sampled and retained. If the analysis result is that the waveform data corresponding to the positive indication exists in the collected waveform data, the collected waveform data is retained. By retaining all the valid waveform data, the waveform data corresponding to multiple positive indications can be retained for subsequent analysis and processing, thereby improving the reliability of the analysis and processing. At the same time, since most of the waveform data corresponding to the negative indication is repeated and has low diagnostic value, by sampling and retaining it, that is, only partially retaining it periodically, a large amount of storage space is saved compared to retaining all of it, thereby improving the utilization rate of storage space resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a schematic diagram of the functional modules of the terminal device to which the waveform data processing device of the present application belongs;

[0036] Figure 2 This is a flow chart of an exemplary embodiment of a waveform data processing method of the present application;

[0037] Figure 3 This is an example diagram of an electrocardiogram involved in the waveform data processing method of this application;

[0038] Figure 4 A flowchart of another exemplary embodiment of the waveform data processing method of the present application;

[0039] Figure 5 A flowchart of another exemplary embodiment of the waveform data processing method of the present application;

[0040] Figure 6 A flowchart of another exemplary embodiment of the waveform data processing method of the present application;

[0041] Figure 7 This is a flowchart of another exemplary embodiment of the waveform data processing method of the present application.

[0042] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0043] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0044] The main solution of the embodiment of the present invention is: by acquiring the collected waveform data, performing real-time and / or quasi-real-time analysis on the collected waveform data to obtain an analysis result; if the analysis result is that there is no waveform data corresponding to a positive indication in the collected waveform data, then the collected waveform data is sampled and retained; if the analysis result is that there is waveform data corresponding to a positive indication in the collected waveform data, then the collected waveform data is retained. From the perspective that when waveform data is usually saved, the storage space resource utilization rate is not high and only a small amount of waveform data corresponding to positive indications can be stored, combined with the characteristic that not all data in the waveform data are valid data, a waveform data storage method is provided. Through this method, more valid data can be stored under the same storage space, thereby improving the reliability of subsequent corresponding analysis based on the valid data. At the same time, when storing the same amount of valid data, the requirements for storage space resources are reduced.

[0045] Related background knowledge involved in the embodiments of this application

[0046] Reference Figure 3 , Figure 3 The electrocardiogram is an exemplary electrocardiogram. Specifically, after the electrode end of the electrocardiogram machine is connected to the corresponding limb lead, the electrode monitors that when the cell is excited under stimulation, the sodium channel opens, and Na + The process of rapidly converting the negative potential inside the membrane to a positive potential from the outside of the membrane along the concentration gradient, and displaying the process on the electrocardiogram. In the figure, the horizontal axis represents time, each large grid is divided into 5 small grids, representing 0.2s, and each small grid represents 0.04s. The vertical axis represents voltage, each large grid is divided into 5 small grids, representing 0.5mV, and each small grid represents 0.1mV; the P wave represents the atrial depolarization process, the first half of the P wave is the right atrium, and the second half is the left atrium, so the abnormal P wave reflects the problem of the atrium. QRS wave: represents the depolarization process of the ventricle, and the wide and deformed QRS wave group reflects the problem of the ventricle. ST-T segment: represents the whole process of ventricular repolarization, and its abnormality is often seen in ventricular problems. QT interval: represents the activity process of the entire ventricle, and the clinical judgment mainly depends on the corrected QT period.

[0047] Specifically, refer to Figure 1 , Figure 1 This is a functional module diagram of the terminal device to which the device corresponding to this application belongs. The waveform data processing device can be a device independent of the terminal device, capable of acquiring collected waveform data, analyzing the collected waveform data, and retaining the waveform data according to the analysis results, and can be carried on the terminal device in the form of hardware or software. The terminal device can be a smart mobile terminal with data processing function such as a mobile phone or a tablet computer, and can also be a fixed terminal device or server with data processing function.

[0048] In this embodiment, the terminal device to which the waveform data processing apparatus belongs includes at least an output module 110 , a processor 120 , a memory 130 and a communication module 140 .

[0049] The memory 130 stores an operating system and a waveform data processing program. The waveform data processing device can store information such as the collected waveform data, analysis results, waveform data corresponding to positive indications, and waveform data retained by sampling in the memory 130. The output module 110 can be a display screen, etc. The communication module 140 can include a WIFI module, a mobile communication module, and a Bluetooth module, etc., and communicates with an external device or server through the communication module 140.

[0050] When the dust removal reminder program in the memory 130 is executed by the processor, the following steps are implemented:

[0051] Get the collected waveform data;

[0052] Perform real-time and / or quasi-real-time analysis on the collected waveform data to obtain analysis results:

[0053] If the analysis result is that there is no waveform data corresponding to a positive indication in the collected waveform data, sampling and retaining the collected waveform data;

[0054] If the analysis result is that waveform data corresponding to a positive indication exists in the collected waveform data, the collected waveform data is retained.

[0055] Furthermore, before the dust removal reminder program in the memory 130 is executed by the processor, the following steps are also implemented:

[0056] Acquiring collected waveform data at a preset frequency, wherein the preset frequency includes at least one frequency;

[0057] The collected waveform data is pre-analyzed. If the result of the pre-analysis is that the percentage value corresponding to the positive indication in the collected waveform data reaches a preset threshold, the preset frequency is adjusted to improve the accuracy of the collected samples.

[0058] Furthermore, before the dust removal reminder program in the memory 130 is executed by the processor, the following steps are also implemented:

[0059] Acquiring characteristic information of the collected waveform data;

[0060] According to the characteristic information, the collected waveform data is analyzed in real time and / or quasi real time for a preset target event to obtain an analysis result.

[0061] Furthermore, before the dust removal reminder program in the memory 130 is executed by the processor, the following steps are also implemented:

[0062] If waveform data corresponding to a positive indication exists in the collected waveform data, the waveform data corresponding to the positive indication is retained as intermediate data, the waveform data within a preset range.

[0063] Furthermore, before the dust removal reminder program in the memory 130 is executed by the processor, the following steps are also implemented:

[0064] Recording the corresponding characteristic values ​​in the waveform data within the preset range;

[0065] The position information corresponding to the characteristic value is recorded.

[0066] Furthermore, before the dust removal reminder program in the memory 130 is executed by the processor, the following steps are also implemented:

[0067] Calculate the error data MSE corresponding to the sampled and retained waveform data according to the sampled and retained waveform data;

[0068] A quality level is identified for the sampled retained waveform data based on the MSE.

[0069] Furthermore, before the dust removal reminder program in the memory 130 is executed by the processor, the following steps are also implemented:

[0070] If the amount of waveform data retained by the sampling reaches a preset threshold, the waveform data with a quality level lower than the preset level is deleted.

[0071] The present invention provides a waveform data processing method, device, terminal equipment and medium. The collected waveform data is acquired, and the collected waveform data is analyzed in real time and / or quasi-real time to obtain an analysis result. If the analysis result is that the waveform data corresponding to the positive indication does not exist in the collected waveform data, the collected waveform data is sampled and retained. If the analysis result is that the waveform data corresponding to the positive indication exists in the collected waveform data, the collected waveform data is retained. By retaining all the waveform data corresponding to the positive indication, multiple valid waveform data can be retained for subsequent analysis and processing, thereby improving the reliability of the analysis and processing. At the same time, by sampling and retaining the ineffective waveform data, the storage space requirement is reduced when the waveform data is stored, thereby improving the utilization rate of the storage space resources.

[0072] Based on the above terminal device architecture but not limited to the above architecture, an embodiment of the method of the present application is proposed.

[0073] Reference Figure 2 , Figure 2 This is a flow chart of an exemplary embodiment of a waveform data processing method of the present application. The waveform data processing method comprises:

[0074] Step S1001, obtaining collected waveform data;

[0075] The solution of this embodiment is applied to electrocardiogram waveform data, and takes into account the validity and practicality of the stored data when storing the electrocardiogram waveform data. The solution of this application can be widely used in all storage methods of continuous waveform data.

[0076] Specifically, when a storage instruction is received, the ECG data collected by the electrocardiogram is acquired at a preset period, wherein the preset period is for acquiring and analyzing the ECG data in real time and sequentially within a reasonable time period. For example, ECG data with a preset period of 3 minutes is acquired for subsequent analysis, retention and deletion steps. After the subsequent steps of the current ECG data are completed, the next three minutes of ECG data are acquired. Compared with the method of acquiring after the entire acquisition is completed, the method of acquiring at a preset period improves the efficiency of waveform data acquisition, thereby improving the efficiency of waveform data processing.

[0077] Step S1002, performing real-time and / or quasi-real-time analysis on the collected waveform data to obtain analysis results;

[0078] Specifically, real-time analysis means that the waveform data acquired is analyzed while the waveform data is acquired. It is applicable to waveform data with a shorter cycle time, and the analysis results can be given in real time to improve the analysis efficiency. For example, the waveform data of the heartbeat usually has a cycle of 1-2 minutes. Through real-time analysis, the measured heart rate can be given at the end of the measurement. Quasi-real-time analysis means that the waveform data acquired before the current time is analyzed at regular intervals. It is applicable to waveform data with a longer cycle time, such as the waveform data of sleep, which usually has a cycle of 8 hours. Every half an hour, the sleep waveform data of the previous half an hour is analyzed, that is, 16 analysis results are obtained. By comparing the 16 analysis results, the time period with better sleep quality can be obtained, which improves the accuracy of the analysis. Simultaneously using real-time and / or quasi-real-time analysis means analyzing the same type of waveform data of different time periods to obtain more comprehensive analysis results, such as firstly analyzing the heartbeat waveform data before and after a person's running in real time, and then comparing and analyzing the heartbeat waveform data before and after running when necessary, more information can be obtained, such as the amplitude and trend of the increase in the heartbeat frequency during exercise compared to that during non-exercise.

[0079] The parameter basis for determining whether there is target data in the real-time and / or quasi-real-time analysis of waveform data is determined according to the preset target event corresponding to the waveform data, that is, different target events correspond to the parameters used in the analysis one by one. For example, for heartbeat activity, the normal heartbeat activity frequency is 60-100 beats / minute. By comparing the actual number of heartbeats contained in a preset cycle of 1 minute with the normal number of heartbeats, when the actual number of heartbeats is less than 60 or greater than 120, the electrocardiogram waveform data corresponding to the activity cycle is the waveform data corresponding to the positive indication, also known as the target data; when the actual number of heartbeats is in the closed interval of 60 to 120, the waveform data corresponding to the heartbeat activity cycle, and the corresponding preset cycle electrocardiogram data do not have waveform data corresponding to the positive indication, that is, there is no target data.

[0080] Example 1, refer to Figure 3 ,when Figure 3 When expressed as a heartbeat cycle, since the heartbeat cycle occupies 24 small grids in the horizontal axis, that is, the time of a heartbeat is 0.96 seconds, therefore, the heart rate = 60 / 0.96 = 62.5 beats / minute. Usually the normal heart rate is 60-100 beats / minute. Figure 3 The heart rate of the heartbeat represented is normal, and there is no target data in the preset period corresponding to the heartbeat.

[0081] Step S1003: if the analysis result is that there is no waveform data corresponding to a positive indication in the collected waveform data, then sample and retain the collected waveform data; if the analysis result is that there is waveform data corresponding to a positive indication in the collected waveform data, then retain the collected waveform data.

[0082] Specifically, after comparing and analyzing the waveform data of the preset period through step S1002, it is determined whether there is waveform data corresponding to a positive indication, that is, target data, in the waveform data. If there is target data in the waveform data, all the electrocardiogram data corresponding to the preset period are retained, that is, all the electrocardiogram data within 1 minute of the preset period are retained.

[0083] If the target data does not exist in the waveform data, the ECG data within the preset period of 1 minute is sampled and retained at a preset ratio. For example, if the preset period of 1 minute contains 60 heartbeats and the heart rate is within the normal range, the ECG data corresponding to the preset period is retained at a preset ratio of 10%, that is, the ECG data corresponding to 6 heartbeats are sampled and retained, wherein the sampling method can be random sampling, and the ECG data corresponding to 6 heartbeats are randomly retained.

[0084] Furthermore, the sampling and retention method can also be to retain the electrocardiogram data corresponding to the 1st, 2nd, 29th, 30th, 59th, and 60th heartbeats respectively. By retaining the average, the retained electrocardiogram data is made more representative, thereby improving the reliability of sampling and retention.

[0085] This embodiment adopts the above scheme, specifically by acquiring collected waveform data, performing real-time and / or quasi-real-time analysis on the collected waveform data to obtain analysis results. If the analysis result is that there is no waveform data corresponding to a positive indication in the collected waveform data, then the collected waveform data is sampled and retained. If the analysis result is that there is waveform data corresponding to a positive indication in the collected waveform data, then the collected waveform data is retained. A waveform data storage method is provided, and the storage method analyzes the waveform data and then classifies it, and retains waveform data of different classifications in different ways, thereby improving the utilization rate of storage space resources. At the same time, because a large amount of waveform data corresponding to positive indications is retained in the storage space, doctors can make diagnoses based on the positive waveform data of the same patient in different time periods, thereby improving the reliability of diagnosis.

[0086] Reference Figure 4 , Figure 4 The flowchart of another exemplary embodiment of the waveform data processing method of the present application is as follows. Step S1002, performing real-time and / or quasi-real-time analysis on the collected waveform data, and obtaining the analysis result comprises:

[0087] Step S100, obtaining characteristic information of the collected waveform data;

[0088] Specifically, refer to Figure 3 , obtain waveform data collected by the electrocardiogram, the waveform data including frequency and amplitude information corresponding to the P wave, R wave, QRS complex, ST wave, T wave and U wave, that is, characteristic information, for comparison and analysis of the characteristic information in step S200.

[0089] Step S200: performing real-time and / or quasi-real-time analysis on the collected waveform data according to the characteristic information to obtain an analysis result.

[0090] Specifically, the characteristic information includes the frequency information of the R wave, and the frequency information of the R wave is analyzed in real time and / or quasi real time. Referring to the example in step S1002, based on Figure 3 The number of grids occupied by adjacent RR intervals and the scale of the grids can be used to calculate the frequency of heartbeats, that is, the heart rate. When the heart rate is lower than 60 beats / minute, the arrhythmia symptom corresponding to the positive indication is sinus bradycardia. When the heart rate is higher than 120 beats / minute, the arrhythmia symptom corresponding to the positive indication is sinus tachycardia. The waveform data corresponding to the positive indication is the target data, and all waveform data of the preset period containing the target data are retained.

[0091] In addition, the P wave can reflect abnormal symptoms of the atrium. More specifically, the first half of the P wave, that is, the rising part, is the potential change during the depolarization of the right atrium, and the second half, that is, the falling part, is the potential change during the depolarization of the left atrium. Usually, the duration of the P wave is less than 0.12s, and the amplitude of the P wave is less than 0.25mV when the electrocardiogram is connected to the limb leads, and less than 0.2mV when it is connected to the chest leads. By obtaining the time, amplitude and trend of the P wave, it can be analyzed through comparative analysis whether the P wave is abnormal. If the P wave is abnormal, the waveform data corresponding to the period of the P wave is the target data, and all the waveform data of the preset period corresponding to the target data are retained for retrieval analysis required for subsequent diagnosis. If the P wave is normal, since the period of a single P wave is less than the preset period, that is, the preset period contains several normal P waves, it is sufficient to sample and retain several normal P waves at a preset ratio.

[0092] Example 1: If the preset cycle contains 9 normal P waves within 1 minute, the waveform data corresponding to 3 normal P waves are randomly saved, and the waveform data corresponding to the remaining 6 P waves are deleted;

[0093] Furthermore, normal P wave data are retained on average, that is, the 1st, 5th, and 9th P wave data are retained, and the waveform data corresponding to the remaining 6 P waves are deleted. Since they are all normal P waves, only part of them needs to be saved for subsequent diagnostic analysis, which ultimately saves storage space to store waveform data corresponding to abnormal P wave data, which has relatively greater reference value for diagnosis.

[0094] In addition, the QRS complex reflects the potential changes of ventricular muscle depolarization. Usually, the time range is between 0.06-0.10s, the shape is rS type in chest lead, and the amplitude is less than 1.0mV. By comparing and analyzing the time, shape and amplitude information of the QRS complex, it is possible to determine whether the waveform data corresponding to the QRS is the target data, that is, to obtain the analysis result, and then perform the same operation as in Example 1 above based on the analysis result, and finally achieve full retention of the waveform data corresponding to the target data and sampling retention of the waveform data corresponding to the non-target data.

[0095] Furthermore, the acquired QRS waveform data can be checked through a QRS wave algorithm. Specifically, by calculating adjacent RR intervals and real-time heart rate, a judgment result of whether the acquired QRS waveform data is the target data can be obtained. After obtaining the judgment result, the same operation as in the above example 1 is performed, and finally all waveform data corresponding to the target data are retained, and waveform data corresponding to the non-target data are sampled and retained.

[0096] This embodiment adopts the above scheme, specifically by acquiring the characteristic information of the collected waveform data, and performing real-time and / or quasi-real-time analysis on the collected waveform data according to the characteristic information to obtain analysis results, and judging whether the waveform data corresponding to the period is the target data according to the analysis results, and effectively analyzing and classifying the waveform data for subsequent execution of corresponding steps according to the results of the analysis and classification, thereby providing effective reference information and improving the reliability of the analysis.

[0097] Reference Figure 5 , Figure 5 The flowchart of another exemplary embodiment of the waveform data processing method of the present application is shown in step S1003. If the analysis result is that the collected waveform data contains waveform data corresponding to a positive indication, the step of retaining the collected waveform data includes:

[0098] Step A100, if there is waveform data corresponding to a positive indication in the collected waveform data, the waveform data corresponding to the positive indication is retained as intermediate data, the waveform data within a preset range;

[0099] Specifically, referring to the above embodiment, the waveform data corresponding to the positive indication refers to the data corresponding to the indicators in the electrocardiogram that exceed the normal range, which has diagnostic significance. When the waveform data corresponding to the positive indication, that is, the target data, is identified through the comparative analysis in the above example, the target data is used as the middle value and several cycles are appropriately added to the left and right to increase the interval range of the target data to prevent the time period data corresponding to the target data from being deleted prematurely before it occurs.

[0100] There are waveform data corresponding to several cycles within a preset cycle. If the target data, that is, the waveform data corresponding to the positive indication, occurs at the first position of the preset cycle, or occurs at the last position of the preset cycle, the waveform data corresponding to the adjacent cycle before or after it also has certain diagnostic value and can be used to observe the formation or end of the positive indication. Therefore, it is necessary to retain the waveform data corresponding to the positive indication before and / or after the positive indication.

[0101] Example 1: There are 10 cycles within the preset cycle of 1 minute, and each cycle is 10s, which correspond to the waveform data of each cycle activity one by one. After comparative analysis, the waveform data corresponding to the first cycle is judged to be a positive indication, that is, the target data. Since the previous sampling and retention method includes average retention, that is, the waveform data of the first, last, and middle corresponding frequencies are retained, the interval of the target data is increased, and the corresponding first and / or last waveform data is added to the target data, which effectively avoids the distortion or fragmentation of the target data caused by cutting in a standard length.

[0102] Step A200, recording the corresponding characteristic values ​​in the waveform data within the preset range;

[0103] Specifically, after increasing the target data interval in step A100, the current target data interval is obtained. Since the values ​​in the current target data interval have a greater diagnostic value, the characteristic data corresponding to the various indicators of the waveform data in the current interval are recorded for subsequent analysis with the ECG. Figure 1 It also shows that the analysis efficiency is improved by eliminating the process of reading and calculating during analysis.

[0104] For example, the duration, amplitude, peak time, and absolute value of the maximum peak value of each indicator waveform are usually recorded and displayed together with the electrocardiogram, and the corresponding ones are intuitively marked.

[0105] Furthermore, a corresponding thumbnail may be generated for waveform data that is significantly different from waveform data corresponding to other activity periods within a preset period, for subsequent diagnosis.

[0106] Step A300, recording the position information corresponding to the characteristic value.

[0107] Furthermore, after recording each characteristic value through step A200, the position information corresponding to each characteristic value in the waveform data is recorded so that the doctor can quickly locate the corresponding position based on the recorded position information for reference, thereby effectively improving the doctor's diagnosis efficiency.

[0108] This embodiment adopts the above scheme, specifically, if there is waveform data corresponding to a positive indication in the collected waveform data, then the waveform data corresponding to the positive indication is retained as intermediate data and the waveform data within a preset range, and the corresponding feature values ​​in the waveform data within the preset range are recorded, and the position information corresponding to the feature values ​​is recorded. By recording and displaying the corresponding feature values, the diagnostic efficiency is improved, and by recording the position information corresponding to the feature information, that is, adding an index, the efficiency of retrieval and analysis is improved, and ultimately the diagnostic efficiency is improved.

[0109] Reference Figure 6 , Figure 6 The flowchart of another exemplary embodiment of the waveform data processing method of the present application is shown in step S1003. If the analysis result is that there is no waveform data corresponding to a positive indication in the collected waveform data, then after the step of sampling and retaining the collected waveform data, the following steps are further included:

[0110] Step B100, calculating the error data MSE corresponding to the sampled and retained waveform data according to the sampled and retained waveform data;

[0111] Specifically, the waveform data after sampling and retention refers to the waveform data after sampling and retention of the waveform data of the preset period without the target data at a preset ratio. By comparing the mean square error value MSE between each activity cycle after sampling and retention, the activity cycle in which the waveform data change is more different from the waveform data of other activity cycles within the preset period can be obtained, that is, by calculating the MSE of the potential value with the same corresponding position in the waveform data corresponding to each activity cycle, the activity cycle corresponding to the waveform with the most abnormal waveform can be found, and the waveform data corresponding to each activity cycle can be scored according to the MSE to identify the quality level. Since in the electrocardiogram, usually within a preset period, the waveform data shapes corresponding to different activity cycles tend to be the same, if the trend of the waveform data of an individual activity cycle and the adjacent activity cycle are greatly different, it may be caused by instrument damage. Therefore, the higher the MSE value calculated above, the more different the shape of the waveform corresponding to the activity cycle is from the shape corresponding to other activity cycles, and the difference may be caused by other interference, and a lower quality level is identified for the activity cycle. By identifying the quality level according to the MSE, the activity cycles in the waveform data after sampling and retention can be classified. In the subsequent retrieval and analysis, the waveform data corresponding to the activity cycle with a higher display quality level is preferentially retrieved as non-target data, that is, the waveform data corresponding to the negative indication, thereby improving the efficiency of the retrieval and analysis.

[0112] Step B200: Identify the quality level of the sampled and retained waveform data according to the MSE.

[0113] Specifically, in step B100, the quality level is identified by comparing the shapes corresponding to other activity cycles, and a lower quality level is identified for the waveform data corresponding to the activity cycle with a larger shape difference, and a higher quality level is identified for the waveform data corresponding to the activity cycle with a smaller shape difference.

[0114] Step B300: If the amount of waveform data retained by the sampling reaches a preset threshold, the waveform data with a quality level lower than the preset level is deleted.

[0115] Furthermore, when the total amount of sampled and retained waveform data reaches a preset threshold, that is, when the retained amount of waveform data corresponding to negative indications reaches a preset threshold, or when storage space is insufficient, waveform data corresponding to activity cycles with lower quality levels are preferentially deleted to free up storage space and store more waveform data corresponding to positive indications with greater diagnostic value.

[0116] Specifically, the preset threshold can be ten times the amount of data retained in the first sampling. For example, when negative waveform data is retained in the first sampling, the preset ratio of sampling retention is 10%. After sampling and retaining for a preset period corresponding to 10 negative indications, the amount of data corresponding to the negative indications retained is ten times the amount of data retained in the first sampling. In this case, the negative data retained in the first sampling must be sampled and deleted to free up storage space to store waveform data corresponding to positive indications with greater diagnostic value.

[0117] Among them, the sampling deletion method can be, first, according to the potential values ​​corresponding to each second of all activity cycles within the preset period, the standard activity cycle composed of the average potential values ​​per second is obtained by averaging. Then, each activity cycle within the preset period and the standard activity cycle are subjected to mean square error MSE calculation to obtain a corresponding mean square error value set, and the mean square error value set corresponds to the similarity between the waveform shape corresponding to each activity cycle and the waveform shape corresponding to the standard activity cycle. Usually, the waveform shapes corresponding to the activity cycles within the preset period are not much different and have similarity. If the waveforms differ greatly, it may be a monitoring abnormality caused by hardware failure. Therefore, the diagnostic value of the waveform data corresponding to the activity cycle with a large difference in waveform shape is low and suitable for priority deletion.

[0118] More specifically, the quality level of the waveform data corresponding to the activity cycle is identified according to the specific value of MSE. Exemplarily, there are three groups of activity cycles corresponding to the negative indications after sampling and retention, namely a, b, and c. The standard activity cycle d is obtained by averaging the potential values ​​corresponding to each second in a, b, and c, and then the mean square error is calculated for the potential values ​​corresponding to each second of a, b, c, and d, respectively, to obtain the corresponding three mean square error values. According to the preset mean square error threshold, the mean square error values ​​are classified. For example, if the waveform data of the activity cycle corresponding to a is level 1, the waveform data of the activity cycle corresponding to b is level 2, and the waveform data of the activity cycle corresponding to c is level 3, then when the amount of waveform data retained by sampling reaches the preset threshold, the waveform data with a quality level lower than the preset level is deleted, that is, the waveform data corresponding to a is deleted.

[0119] This embodiment adopts the above scheme, specifically by calculating the error data MSE corresponding to the sampled and retained waveform data based on the sampled and retained waveform data, and then identifying the quality level of the sampled and retained waveform data based on the MSE. When the data amount of the sampled and retained waveform data reaches a preset threshold, the waveform data with a quality level lower than the preset level is deleted. By identifying the quality level of the active periods within the preset period, the waveform data corresponding to the active periods with higher display quality levels are preferentially retrieved, thereby improving the efficiency of retrieval and analysis. By preferentially deleting the waveform data corresponding to the active periods with lower quality levels, the utilization rate of storage space resources is improved.

[0120] Reference Figure 7 , Figure 7 This is a flow chart of another exemplary embodiment of the waveform data processing method of the present application. Step S1001, the step of obtaining the collected waveform data includes:

[0121] Step C100, acquiring collected waveform data at a preset frequency, wherein the preset frequency includes at least one frequency;

[0122] Specifically, the preset frequency refers to the frequency of acquiring waveform data from a device that collects waveform data. For example, the electrocardiogram collects waveform data in real time and acquires the waveform data of the previous 3 minutes every 3 minutes, that is, at the 4th minute, where 3 minutes is the preset frequency. The preset frequency can be changed according to actual needs to meet the need to obtain waveform data corresponding to positive indications multiple times, thereby improving the accuracy of sample collection.

[0123] Step C200, pre-analyze the collected waveform data. If the result of the pre-analysis is that the percentage value corresponding to the positive indication in the collected waveform data reaches a preset threshold, adjust the preset frequency to improve the accuracy of the collected samples.

[0124] Specifically, after acquiring the collected waveform data, the waveform data is pre-analyzed, that is, analyzing whether there is waveform data corresponding to a positive indication in the waveform data. If so, the acquisition interval is reduced to collect samples multiple times, where the collected samples are waveform data corresponding to the positive indication.

[0125] Exemplarily, the preset threshold is 50% and the preset frequency is 3 minutes / time. In the 4th minute, the waveform data of the first 3 minutes is pre-analyzed. When it is found that the waveform data corresponding to the positive indication in the first 3 minutes occupies 1.5 minutes, that is, the proportion of the waveform data corresponding to the positive indication reaches the preset threshold of 50%, the preset frequency is increased to 2 minutes / time to improve the accuracy of sample collection.

[0126] This embodiment adopts the above scheme, specifically by obtaining the collected waveform data at a preset frequency, wherein the preset frequency includes at least one frequency, and pre-analyzing the collected waveform data. If the result of the pre-analysis is that the proportion value corresponding to the positive indication in the collected waveform data reaches a preset threshold, the preset frequency is adjusted to improve the accuracy of the collected samples, and the waveform data corresponding to the positive indication can be obtained multiple times, avoiding the data of the time period when the positive indication has not occurred from being deleted prematurely, thereby improving the accuracy of the collected samples.

[0127] In addition, an embodiment of the present application further provides a waveform data processing device, the waveform data processing device comprising:

[0128] An acquisition module, used for acquiring collected waveform data;

[0129] An analysis module, used for performing real-time and / or quasi-real-time analysis on the collected waveform data to obtain analysis results;

[0130] A sampling and retaining module, used for sampling and retaining the collected waveform data if the analysis result is that there is no waveform data corresponding to a positive indication in the collected waveform data;

[0131] A retaining module is used to retain the collected waveform data if the analysis result is that the collected waveform data contains waveform data corresponding to a positive indication.

[0132] For the principle and implementation process of implementing data flow detection in this embodiment, please refer to the above embodiments and will not be repeated here.

[0133] In addition, an embodiment of the present application also proposes a terminal device, which includes a memory, a processor, and a waveform data processing program stored in the memory and executable on the processor, and the waveform data processing, when executed by the processor, implements the steps of waveform data processing as described above.

[0134] Since the waveform data processing program adopts all the technical solutions of all the aforementioned embodiments when executed by the processor, it has at least all the beneficial effects brought by all the technical solutions of all the aforementioned embodiments, which will not be described one by one here.

[0135] In addition, an embodiment of the present application further proposes a computer-readable storage medium, on which a waveform data processing program is stored. When the waveform data processing program is executed by a processor, the steps of waveform data processing as described above are implemented.

[0136] Since the waveform data processing program adopts all the technical solutions of all the aforementioned embodiments when executed by the processor, it has at least all the beneficial effects brought by all the technical solutions of all the aforementioned embodiments, which will not be described one by one here.

[0137] Compared with the prior art, the waveform data processing method, apparatus, terminal device and storage medium proposed in the embodiments of the present application obtain collected waveform data, perform real-time and / or quasi-real-time analysis on the collected waveform data, and obtain analysis results. If the analysis result is that there is no waveform data corresponding to a positive indication in the collected waveform data, the collected waveform data is sampled and retained; if the analysis result is that there is waveform data corresponding to a positive indication in the collected waveform data, the collected waveform data is retained. This solves the contradiction between the large amount of storage space required for continuous storage and the limited storage space when storing waveform data. By sampling and retaining waveform data where no target data exists and retaining all waveform data where target data exists, storage space resources are reasonably allocated, storage costs are reduced, and the utilization rate of storage space resources is improved. At the same time, the storage of multiple valid data is conducive to subsequent analysis, thereby improving the reliability of the analysis results.

[0138] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0139] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0140] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as above, and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, a controlled terminal, or a network device, etc.) to execute the method of each embodiment of the present application.

[0141] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A waveform data processing method, characterized in that: The waveform data processing method comprises the following steps: Get the collected waveform data; The step of obtaining the collected waveform data comprises: Acquiring the collected waveform data at a preset frequency, wherein the preset frequency includes at least one frequency; Pre-analyzing the collected waveform data, and if a result of the pre-analysis is that a percentage value corresponding to a positive indication in the collected waveform data reaches a preset threshold, increasing the preset frequency; Perform real-time and / or quasi-real-time analysis on the collected waveform data to obtain analysis results: If the analysis result is that there is no waveform data corresponding to a positive indication in the collected waveform data, sampling and retaining the collected waveform data; If the analysis result is that the collected waveform data contains waveform data corresponding to a positive indication, retaining the collected waveform data; If the analysis result is that the collected waveform data contains waveform data corresponding to a positive indication, the step of retaining the collected waveform data includes: If there is waveform data corresponding to a positive indication in the collected waveform data, the waveform data corresponding to the positive indication is retained as intermediate data and the waveform data within a preset range; When the intermediate data is identified, taking the intermediate data as the core, appropriately adding a number of cycles to the left and right to increase the interval range of the target data; When the first position and / or the last position of the preset cycle is set, the waveform data corresponding to the adjacent cycle before and / or after the waveform data corresponding to the positive indication is retained to observe the formation and / or end of the positive indication.

2. The waveform data processing method according to claim 1, characterized in that: The step of performing real-time and / or quasi-real-time analysis on the collected waveform data to obtain analysis results comprises: Acquiring characteristic information of the collected waveform data; According to the characteristic information, the collected waveform data is analyzed in real time and / or quasi real time for a preset target event to obtain an analysis result.

3. The waveform data processing method according to claim 1, characterized in that: If there is waveform data corresponding to a positive indication in the collected waveform data, the waveform data corresponding to the positive indication is retained as intermediate data, and the step of obtaining waveform data within a preset range further includes: Recording the corresponding characteristic values ​​in the waveform data within the preset range; The position information corresponding to the characteristic value is recorded.

4. The waveform data processing method according to claim 1, characterized in that: If the analysis result is that there is no waveform data corresponding to a positive indication in the collected waveform data, then after the step of sampling and retaining the collected waveform data, the method further includes: Calculate the error data MSE corresponding to the sampled and retained waveform data according to the sampled and retained waveform data; A quality level is identified for the sampled retained waveform data based on the MSE.

5. The waveform data processing method according to claim 4, characterized in that: After the step of identifying the quality level of the sampled and retained waveform data according to the MSE, the following step further comprises: If the amount of waveform data retained by the sampling reaches a preset threshold, the waveform data with a quality level lower than the preset level is deleted.

6. A waveform data processing device, characterized in that: The waveform data processing device comprises: An acquisition module is used to acquire collected waveform data, wherein the step of acquiring the collected waveform data comprises: acquiring the collected waveform data at a preset frequency, wherein the preset frequency includes at least one frequency; performing a pre-analysis on the collected waveform data, and if the result of the pre-analysis is that the percentage value corresponding to the positive indication in the collected waveform data reaches a preset threshold, then increasing the preset frequency; An analysis module, used for performing real-time and / or quasi-real-time analysis on the collected waveform data to obtain analysis results; A sampling and retaining module, used for sampling and retaining the collected waveform data if the analysis result is that there is no waveform data corresponding to a positive indication in the collected waveform data; A retention module is used to retain the collected waveform data if the analysis result is that the collected waveform data contains waveform data corresponding to a positive indication. Specifically, if the collected waveform data contains waveform data corresponding to a positive indication, the waveform data corresponding to the positive indication is retained as intermediate data and within a preset range; when the intermediate data is identified, a number of cycles are appropriately added to the left and right with the intermediate data as the core to increase the interval range of the target data; when the first position and / or the last position of the preset cycle is reached, the waveform data corresponding to the adjacent cycles before and / or after the waveform data corresponding to the positive indication is retained to observe the formation and / or end of the positive indication.

7. A terminal device, characterized in that: The terminal device includes a memory, a processor, and a waveform data processing program stored in the memory and executable on the processor. When the waveform data processing program is executed by the processor, the steps of the waveform data processing method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a waveform data processing program, and when the waveform data processing program is executed by a processor, the steps of the waveform data processing method according to any one of claims 1 to 5 are implemented.

Images