Pressure recognition method, data correction method, apparatus, and computer device

Abstract

A pressure recognition method, a data correction method, an apparatus, and a computer device. The pressure recognition method comprises: acquiring at least one type of data feature of analyte concentration data within a first time window; and on the basis of a comparison result between the at least one type of data feature and a preset feature threshold, determining whether an analyte sensor is subjected to pressure at a current moment, wherein the analyte concentration data within the first time window does not comprise data fed back by other sensors, and the other sensors do not comprise the analyte sensor.

Description

Pressure identification method, data correction method, device and computer equipment

[0001] Related applications

[0002] The present application claims priority to the Chinese patent application No. 202411029529.6, filed on July 29, 2024, entitled "Data correction method, device and computer equipment", the contents of which are hereby incorporated by reference in their entirety. TECHNICAL FIELD

[0003] The present application relates to the technical field of continuous analyte monitoring, in particular to a pressure identification method, a data correction method, a device and a computer equipment. BACKGROUND

[0004] Continuous glucose monitoring system (CGM) is a specific analyte monitoring system, which detects the interstitial fluid glucose concentration of a user by inserting a sensing electrode into the interstitial fluid of the user. Because there is a high correlation between interstitial fluid glucose concentration and blood glucose concentration (mainly due to capillary diffusion and glucose dynamic balance in blood), the dynamic blood glucose information of the user can be obtained.

[0005] In special cases, the glucose concentration data detected by CGM may fluctuate abnormally, such as when the action site of CGM is continuously compressed (typically, for example, when the user is sleeping). Due to local ischemia of human tissue, the interstitial fluid glucose concentration deviates from the blood glucose concentration, so that the data measured by the sensor cannot truly reflect the blood glucose level of the human body. Typically, when compressed, the sensor appears a large and deep concave in data performance. In the case of serious deviation, this kind of abnormal condition deviating from blood glucose expression may trigger false alarms such as hypoglycemia alarm, which seriously affects the accuracy of the sensor monitoring result.

[0006] The existing method for abnormal identification and correction of continuous glucose monitoring system performs abnormal analysis through the data stream provided by the additional physical sensor (typically, for example, pressure sensor, gyroscope, etc.) and switches the signal processing algorithm accordingly. Such method has the problems of large system power consumption and difficulty in integration on small volume devices. SUMMARY

[0007] The first aspect of the present application provides a pressure identification method, the method comprising:

[0008] obtaining at least one type of data feature of the first window length analyte concentration data;

[0009] determining whether the analyte sensor is under pressure at the current time based on the comparison result of the at least one type of data feature and the preset feature threshold.

[0010] The first window length analyte concentration data comprises raw analyte concentration data at the current time point;

[0011] The first window length analyte concentration data does not include data fed back by other sensors, which do not include analyte sensors.

[0012] In some embodiments, the at least one type of data feature comprises at least one of an amplitude of high frequency data, a principal component analysis residual, a data prediction error, and a high frequency data control chart.

[0013] In some embodiments, determining whether the analyte sensor is under pressure at the current time point based on the comparison result of the at least one type of data feature and the preset feature threshold comprises:

[0014] determining whether under pressure based on the size relationship between a single data feature and a preset feature threshold, or

[0015] setting a confidence level and / or a weight corresponding to each type of data feature based on the size relationship between each type of data feature and the corresponding preset feature threshold;

[0016] obtaining a joint calculation result based on the confidence level of each type of data feature and a preset weight value, and determining whether under pressure based on the comparison result of the joint calculation result and a preset fluctuation threshold.

[0017] In some embodiments, obtaining a joint calculation result based on the confidence level of each type of data feature and a preset weight value comprises: performing weighted summation on each type of data feature based on the confidence level of each type of data feature and a preset weight value.

[0018] In some embodiments, the preset feature threshold is obtained based on analyte concentration historical data of the current user.

[0019] In some embodiments, the first window length analyte concentration data comprises raw analyte concentration data at the current time point, comprising:

[0020] obtaining analyte concentration data corresponding to the current time point and a first time period to form first window length analyte concentration data; the first time period is a time length within a first preset time length before the current time point.

[0021] The second aspect of the present application provides a data correction method, comprising:

[0022] obtaining at least one type of data feature of the first window length analyte concentration data;

[0023] determining output analyte concentration data at the current time point based on the comparison result of the at least one type of data feature and a preset feature threshold.

[0024] The output analyte concentration data of the current time point is selected from the prediction data or the raw analyte concentration data corresponding to the current time point;

[0025] The first window length analyte concentration data comprises raw analyte concentration data of the current time point;

[0026] The first window length analyte concentration data does not include data fed back by other sensors, which do not include analyte sensors.

[0027] In some embodiments, the first window length analyte concentration data comprises raw analyte concentration data of the current time point, including:

[0028] Obtaining analyte concentration data corresponding to the current time point and a first time period, to form first window length analyte concentration data; the first time period is a time length within a first preset time length before the current time point.

[0029] In some embodiments, the at least one type of data feature includes at least one of the amplitude of high frequency data, principal component analysis residual error, data prediction error, and high frequency data control chart.

[0030] In some embodiments, second window length analyte concentration data is obtained based on analyte concentration data corresponding to a second time period, the second time period being a time length within a second preset time length before the current time point;

[0031] The prediction data is generated based on the second window length analyte concentration data.

[0032] In some embodiments, the second preset time length is the same as or different from the first preset time length.

[0033] In some embodiments, the second preset time length is greater than the first preset time length.

[0034] In some embodiments, the output analyte concentration data is used for display and / or data analysis.

[0035] In some embodiments, determining the output analyte concentration data of the current time point based on the comparison result of the at least one type of data feature and the preset feature threshold value includes:

[0036] Determining whether the analyte sensor at the current time point is under pressure based on the comparison result of the at least one type of data feature and the preset feature threshold value;

[0037] If under pressure, determining the output analyte concentration data of the current time point based on the trend feature of the first window length analyte concentration data;

[0038] If not, the original analyte concentration data corresponding to the current time is taken as the output analyte concentration data of the current time.

[0039] In some embodiments, the trend feature includes a spike up, a spike down.

[0040] In some embodiments, if the trend feature is a spike up, the predicted data is taken as the output analyte concentration data of the current time.

[0041] If the trend feature is a spike down, a difference between the original analyte concentration data and the predicted data is calculated; and the output analyte concentration data of the current time is determined based on the difference.

[0042] In some embodiments, the determination of the output analyte concentration data of the current time based on the difference includes:

[0043] When the difference is not less than a comparison threshold, the predicted data is taken as the output analyte concentration data of the current time.

[0044] When the difference is less than the comparison threshold, the original analyte concentration data is taken as the output analyte concentration data of the current time.

[0045] In some embodiments, the determination of whether the analyte sensor of the current time is under pressure based on the comparison result of the at least one type of data feature and the preset feature threshold includes:

[0046] determination of whether under pressure based on a size relationship between a single data feature and a preset feature threshold, or

[0047] setting a confidence level and / or a weight corresponding to each type of data feature based on a size relationship between each type of data feature and a corresponding preset feature threshold.

[0048] obtaining a joint calculation result based on the confidence levels of each type of data feature and preset weight values, and determining whether under pressure based on a comparison result of the joint calculation result and a preset fluctuation threshold.

[0049] In some embodiments, the obtaining of the joint calculation result based on the confidence levels of each type of data feature and preset weight values includes:

[0050] weighted summation of each type of data feature based on the confidence levels of each type of data feature and preset weight values.

[0051] In some embodiments, the preset feature threshold is obtained based on analyte concentration historical data of a current user.

[0052] In some embodiments, the determining the output analyte concentration data of the current time based on the comparison result of the at least one type of data feature and the preset feature threshold comprises:

[0053] determining the state type identifier of the current time based on the comparison result of the at least one type of data feature and the preset feature threshold;

[0054] determining the output analyte concentration data of the current time based on the state type identifier.

[0055] In some embodiments, the determining the state type identifier of the current time based on the comparison result of the at least one type of data feature and the preset feature threshold comprises:

[0056] determining whether the analyte sensor is under pressure at the current time based on the comparison result of the at least one type of data feature and the preset feature threshold; if not, marking the state type identifier of the current time as a reset state;

[0057] if yes, determining the state type identifier of the current time based on the trend feature of the first window length analyte concentration data; wherein,

[0058] if the trend feature is a spike upward, marking the state type identifier of the current time as a fluctuation start;

[0059] if the trend feature is a spike downward, marking the state type identifier of the current time as a fluctuation recovery.

[0060] In some embodiments, if the state type identifier of the current time is the reset state, taking the original analyte concentration data corresponding to the current time as the output analyte concentration data of the current time;

[0061] if the state type identifier of the current time is the fluctuation start, taking the predicted data as the output analyte concentration data of the current time;

[0062] if the state type identifier of the current time is the fluctuation recovery, calculating a difference between the original analyte concentration data and the predicted data;

[0063] when the difference is not less than a comparison threshold, taking the predicted data as the output analyte concentration data of the current time;

[0064] when the difference is less than the comparison threshold, taking the original analyte concentration data as the output analyte concentration data of the current time.

[0065] A third aspect of the present application provides a pressure recognition device, the device comprising:

[0066] An original data acquisition module is configured to acquire at least one type of data feature of the first window length analyte concentration data;

[0067] A pressure identification module is configured to determine whether the analyte sensor is under pressure based on a comparison result of the at least one type of data feature and a preset feature threshold value;

[0068] The first window length analyte concentration data includes original analyte concentration data at the current time point, and does not include data fed back by other sensors, which do not include the analyte sensor.

[0069] The fourth aspect of the present application provides a data correction device, which is characterized in that the device comprises:

[0070] An original data acquisition module is configured to acquire at least one type of data feature of the first window length analyte concentration data;

[0071] A data output module is configured to determine output analyte concentration data at the current time point based on a comparison result of the at least one type of data feature and a preset feature threshold value.

[0072] The fifth aspect of the present application provides a computer device, which comprises a memory and a processor, and is characterized in that the memory stores a computer program, and the processor is configured to run the computer program to perform steps of any one of the pressure detection methods.

[0073] The sixth aspect of the present application provides a computer device, which comprises a memory and a processor, and is characterized in that the memory stores a computer program, and the processor is configured to run the computer program to perform steps of any one of the data correction methods.

[0074] Compared with related technologies, the pressure identification method, the data correction method, the device and the computer device provided in the present embodiment, by acquiring analyte concentration data at the current time point and within a preset time length before the current time point, first window length data is formed; based on data features of the first window length data, it is determined whether original analyte concentration data corresponding to the current time point is to be corrected data; if the original analyte concentration data is to be corrected data, a state type of the current time point is set based on a trend feature of the first window length data; based on the state type, output analyte concentration data at the current time point is determined, which solves the problem of large system power consumption and difficulty in integration on a small volume device, realizes identification and correction of to-be-corrected data by using a single analyte sensor, and helps to reduce system integration difficulty and system power consumption.

[0075] The details of various embodiments of the application are described in the following drawings and description. Other features, problems and advantages of the application will be apparent from the description, drawings and claims. BRIEF DESCRIPTION OF DRAWINGS

[0076] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings required to be used in the embodiments or the prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of the disclosed drawings.

[0077] Fig. 1 is a hardware structure block diagram of a terminal of a data correction method in an embodiment.

[0078] Fig. 2 is a flowchart of a pressure recognition method in an embodiment.

[0079] Fig. 3 is a flowchart of a data correction method in an embodiment.

[0080] Fig. 4 is a flowchart of a data correction method in an embodiment.

[0081] Fig. 5 is a flowchart of a data correction method in an embodiment.

[0082] Fig. 6 is a flowchart of a data correction method in an embodiment.

[0083] Fig. 7 is a flowchart of a data correction method in an embodiment.

[0084] Fig. 8 is a raw signal collected by an analyte monitoring system in an embodiment.

[0085] Fig. 9 is a corrected signal obtained after identification and correction of the data to be corrected by an analyte monitoring system in an embodiment.

[0086] Fig. 10 is a comparison diagram of a measured curve and a predicted curve of an analyte concentration in an embodiment.

[0087] Fig. 11 is a marking diagram of a signal collected when an analyte sensor is under pressure in an embodiment.

[0088] Fig. 12 is a structure diagram of a pressure recognition device in an embodiment.

[0089] Fig. 13 is a structure diagram of a data correction device in an embodiment.

[0090] Fig. 14 is a structure diagram of a data correction device in an embodiment. DETAILED DESCRIPTION

[0091] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0092] Unless otherwise defined, technical terms or scientific terms used in the present application shall have the general meaning understood by those of ordinary skill in the art to which the present application belongs. In the present application, the terms "one", "a", "an", "the", "these", and the like similar words do not represent a quantitative limitation, but can be singular or plural. In the present application, the terms "include", "contain", "have" and any variants thereof are intended to cover non-exclusive inclusion; for example, a process, method and system, product or device containing a series of steps or modules (units) are not limited to the listed steps or modules (units), but can include steps or modules (units) not listed, or can include other steps or modules (units) inherent to the process, method, product or device. In the present application, the terms "connected", "connected", "coupled" and the like similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. In the present application, "multiple" means two or more. The association between the associated objects is described by the term "and / or", which means that there can be three relationships, for example, "A and / or B" can mean that A exists alone, A and B exist together, and B exists alone. In general, the character " / " represents an "or" relationship between the objects before and after it. In the present application, the terms "first", "second", "third" and the like are only used to distinguish similar objects, and do not represent a specific order of the objects.

[0093] The method embodiments provided in the present embodiment can be executed in a terminal, a computer or a similar computing device. For example, it is run on a terminal. FIG. 1 is a hardware structure block diagram of a terminal of the data correction method of the present embodiment. As shown in FIG. 1, the terminal can include one or more (only one is shown in FIG. 1) processors 102 and a memory 104 for storing data, wherein the processor 102 can include but not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above-mentioned terminal can also include a transmission device 106 for communication function and an input and output device 108. Those of ordinary skill in the art can understand that the structure shown in FIG. 1 is only schematic, which does not limit the structure of the above-mentioned terminal. For example, the terminal can include more or less components than those shown in FIG. 1, or have a different configuration from that shown in FIG. 1.

[0094] The memory 104 can be used to store computer programs, such as software programs of application software and modules, such as a computer program corresponding to the data correction method in the embodiment, and the processor 102 can execute various functional applications and data processing, i.e., implement the method described above, by running the computer program stored in the memory 104. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include a memory remotely arranged with respect to the processor 102, and the remote memory can be connected to the terminal through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0095] The transmission device 106 is configured to receive or send data via a network. The network includes a wireless network provided by a communication provider of the terminal. In an example, the transmission device 106 includes a network adapter (NIC) that can be connected to other network devices through a base station to communicate with the Internet. In an example, the transmission device 106 can be a radio frequency (RF) module configured to communicate with the Internet in a wireless manner.

[0096] In the embodiment, a data correction method is provided, which is applied to an analyte monitoring system. The analyte monitoring system is a system for collecting, processing, and analyzing an analyte (such as a chemical component in a gas, a liquid, or a solid) in a specific object. Specifically, the analyte monitoring system can be a biological sample monitoring system or an environmental monitoring system, for example, a wearable biological sample monitoring system, which can be a continuous glucose monitoring system (CGM). The analyte concentration data used by the data correction method can be glucose concentration data or blood glucose concentration data.

[0097] FIG. 2 is a flowchart of a pressure identification method according to an embodiment. As shown in FIG. 2, the flow includes the following steps:

[0098] In step S10, at least one type of data feature of the first window length analyte concentration data is obtained.

[0099] Specifically, the first window length analyte concentration data includes raw analyte concentration data at a current time, as shown in FIG. 7, the current time is time t, and the first preset time can be set according to the requirements of calculation accuracy, calculation data volume, etc. For example, the first preset time is set as T1-1, then the first time period is t-1 time to t-(T1-1) time, and thus the first window length analyte concentration data of T1 time length from t to t-(T1-1) can be obtained. The analyte concentration data is the gas concentration or liquid concentration in the target object, which can be glucose concentration data or blood glucose concentration data.

[0100] In step S20, whether the analyte sensor is pressed at the current time is determined based on a comparison result of the at least one type of data feature and a preset feature threshold.

[0101] The first window length analyte concentration data does not include data fed back by other sensors, and the other sensors do not include the analyte sensor.

[0102] Specifically, the at least one type of data feature includes at least one of the amplitude of high-frequency data, principal component analysis residual error, data prediction error, and high-frequency data control chart. When the analyte sensor is pressed, the data detected by the sensor can show a large and deep concave, and among other types of abnormalities, it can also be a convex phenomenon. The first window length analyte concentration data can be extracted and analyzed for data features to determine whether the analyte sensor is pressed.

[0103] In one embodiment, the step S20, the determination of whether the analyte sensor is pressed at the current time based on the comparison result of the at least one type of data feature and the preset threshold, specifically includes:

[0104] Based on the size relationship between a single data feature and a preset feature threshold, it is determined whether it is pressed.

[0105] In one embodiment, the step 20 further includes:

[0106] Based on the size relationship between each type of data feature and the corresponding preset feature threshold, the confidence and / or weight of each type of data feature is set;

[0107] Based on the confidence of each type of data feature and the preset weight value, a joint calculation result is obtained, and based on a comparison result of the joint calculation result and a preset fluctuation threshold, it is determined whether it is pressed.

[0108] Specifically, each type of feature has a corresponding set of confidence and weight values, and based on the confidence and weight values, the various types of data features are weighted and summed. If the calculation result exceeds the preset fluctuation threshold, it is determined that the current analyte sensor is under pressure. If the calculation result does not exceed the preset fluctuation threshold (for example, the fluctuation threshold is 0.5), it is determined that the current analyte sensor is not under pressure. The weight value is preset; the confidence is calculated based on the data features.

[0109] In one embodiment, the joint calculation result is obtained based on the confidence of each type of data feature and the preset weight value, including: weighted sum of each type of data feature based on the confidence of each type of data feature and the preset weight value. In one embodiment, the preset feature threshold is obtained based on the analyte concentration history data of the current user.

[0110] Specifically, the analyte concentration history data of the current user for N days is obtained, and the stable feature value of the analyte concentration of the user is calculated as the feature threshold of each type of feature.

[0111] FIG. 3 is a flowchart of a data correction method according to one embodiment. As shown in FIG. 3, the flow includes the following steps:

[0112] Step S1110, at least one type of data feature of the first window length analyte concentration data is obtained.

[0113] Specifically, the first window length analyte concentration data contains the original analyte concentration data at the current time, as shown in FIG. 7, the current time is t, and the first preset time can be set according to the requirements of calculation accuracy, calculation data amount, etc. For example, the first preset time is set to T1-1, then the first time period is t-1 to t-(T1-1), and thus the first window length analyte concentration data of T1 time length from t to t-(T1-1) can be obtained. The analyte concentration data is the gas concentration or liquid concentration in the target object, which can be glucose concentration data or blood glucose concentration data.

[0114] Step S1120, based on the comparison result of the at least one type of data feature and the preset feature threshold, the output analyte concentration data at the current time is determined.

[0115] Specifically, the data features include the amplitude of high-frequency data, principal component analysis residual error, data prediction error, and high-frequency data control chart, etc. At least two types of data features are extracted from the first window length analyte concentration data. In another embodiment, a type of data feature can also be extracted from the first window length analyte concentration data, and the analysis is based on this single type of data feature to improve the calculation speed. The extracted data features are subjected to threshold judgment to determine the output analyte concentration data at the current time.

[0116] In one of the embodiments, the output analyte concentration data at the current time is selected from the predicted data or the raw analyte concentration data corresponding to the current time.

[0117] In one of the embodiments, the second window length analyte concentration data is obtained based on the analyte concentration data corresponding to a second time period, the second time period being a time period within a second preset time length before the current time; and the predicted data is generated based on the second window length analyte concentration data.

[0118] Specifically, referring to FIG. 7, the current time is time t, the second preset time length can be set the same as the above-mentioned first preset time length, or can be set differently, and the second preset time length is optionally greater than the first preset time length. When the second preset time length is set as T2-1, the second time period is time t-1 to time t-(T2-1), and the analyte concentration data within the time window from t to t-(T2-1) forms the second window length analyte concentration data.

[0119] In one of the embodiments, the method for generating the predicted data includes but is not limited to autoregression, deep learning, machine learning, etc.

[0120] Specifically, the second window length analyte concentration data is used for dynamic prediction, and the predicted data is updated in real time following the current time, thereby improving the quality of the correction of the to-be-corrected data.

[0121] In one of the embodiments, the output analyte concentration data is used for display and / or data analysis.

[0122] FIG. 4 is a flowchart of a data correction method according to one of the embodiments, as shown in FIG. 4, the flowchart includes the following steps:

[0123] Step S2110: Obtain at least one type of data feature of the first window length analyte concentration data.

[0124] Specifically, the first window length analyte concentration data includes raw analyte concentration data at the current time, referring to FIG. 7, the current time is time t, and the first preset time can be set according to the requirements of calculation accuracy and calculation data amount, etc. For example, the first preset time is set as T1-1, then the first time period is time t-1 to time t-(T1-1), and thus the first window length analyte concentration data of T1 time length from t to t-(T1-1) can be obtained. The analyte concentration data is the gas concentration or liquid concentration in the target object, which is optionally glucose concentration data, or blood glucose concentration data.

[0125] Step S2120: Determine whether the analyte sensor at the current time is under pressure based on the comparison result of the at least one type of data feature and the preset feature threshold.

[0126] Specifically, the data features include the amplitude of high frequency data, principal component analysis residual, data prediction error, and high frequency data control chart, etc. At least two types of data features are extracted from the first window length analyte concentration data. Each type of feature has its corresponding set of confidence and weight values. Based on the confidence and weight values, the weighted sum of each type of data feature is calculated. If the calculation result exceeds the preset fluctuation threshold, it is determined that the current analyte sensor is under pressure. If the calculation result does not exceed the preset fluctuation threshold (for example, the fluctuation threshold is 0.5), it is determined that the current analyte sensor is not under pressure. Wherein, the weight value is preset; the confidence is calculated based on the data feature. In another embodiment, a type of data feature can also be extracted from the first window length analyte concentration data, and analysis is performed based on this single type of data feature to improve the calculation speed. The extracted data features are subjected to threshold judgment to determine whether the analyte sensor is under pressure at the current time.

[0127] Specifically, when the analyte sensor is under pressure, the data detected by the sensor may exhibit a large and deep concave, which may also be a convex phenomenon in other types of abnormalities. The first window length analyte concentration data can be extracted and analyzed to determine whether the analyte sensor is under pressure, so as to more accurately process the to-be-corrected data.

[0128] In one embodiment, step S2120 includes:

[0129] Based on the size relationship between the single data feature and the preset feature threshold, it is determined whether it is under pressure.

[0130] In one embodiment, the step 20 further includes:

[0131] Based on the size relationship between each type of data feature and the corresponding preset feature threshold, the confidence and / or weight of each type of data feature is set;

[0132] Based on the confidence of each type of data feature and the preset weight value, a joint calculation result is obtained, and based on the comparison result between the joint calculation result and the preset fluctuation threshold, it is determined whether it is under pressure.

[0133] In one embodiment, the step of obtaining a joint calculation result based on the confidence of each type of data feature and the preset weight value includes: based on the confidence of each type of data feature and the preset weight value, the weighted sum of each type of data feature is calculated.

[0134] Step S2130, if under pressure, the output analyte concentration data at the current time is determined based on the trend feature of the first window length analyte concentration data;

[0135] If not under pressure, the original analyte concentration data corresponding to the current time is taken as the output analyte concentration data of the current time.

[0136] Specifically, when the analyte sensor is under pressure, the data detected by the sensor can show a large and deep concave, which can also be a convex phenomenon among other kinds of abnormalities. The trend feature of the first window length analyte concentration data can be analyzed to determine the abnormal stage in which the current time is located, so as to more accurately process the to-be-corrected data.

[0137] The trend feature can be obtained by calculating the peak direction of the first window length analyte concentration data, for example, the peak is upward, and the slope of the subsequent data of the peak is negative, that is, the data shows a downward trend; or the peak is downward, and the slope of the subsequent data of the peak is positive, and the data shows an upward trend. When the trend feature is upward, the state type is set to fluctuation start, and when the trend feature is downward, the state type is set to fluctuation end; or, when the trend feature is downward, the state type is set to fluctuation start, and when the trend feature is upward, the state type is set to fluctuation end. For different fluctuation types, the correspondence between the trend feature and the state type can be set differently.

[0138] The processing method corresponding to different trends is as follows: if the trend feature is upward, the predicted data is taken as the output analyte concentration data; if the trend feature is downward, the difference between the predicted data and the original analyte concentration data is analyzed, if the difference is large, the predicted data is taken as the output analyte concentration data, if the difference is small, the original analyte concentration data is taken as the output analyte concentration data, wherein the difference being large or small can be judged by a threshold. FIGS. 8 and 9 show the comparison of the original signal and the corrected signal collected by the embodiment. In FIG. 8, the part of the signal circled is the to-be-corrected data identified, and after the to-be-corrected data is processed by the above method, the corrected data as shown in FIG. 9 is obtained, and it can be seen that the abnormal fluctuation is accurately eliminated.

[0139] FIG. 5 is a flowchart of the data correction method of one embodiment, as shown in FIG. 5, the flowchart includes the following steps:

[0140] In step S3110, at least one kind of data feature of the first window length analyte concentration data is obtained.

[0141] Specifically, the first window length analyte concentration data contains raw analyte concentration data at the current time, as shown in FIG. 7, the current time is t, and the first preset time can be set according to the requirements of calculation accuracy, calculation data volume, etc. For example, the first preset time is set as T1-1, then the first time period is t-1 to t-(T1-1), and thus the first window length analyte concentration data of T1 time length from t to t-(T1-1) can be obtained. The analyte concentration data is the gas concentration or liquid concentration in the target object, which can be glucose concentration data or blood glucose concentration data.

[0142] In step S3120, the state type identifier at the current time is determined based on the comparison result of the at least one type of data feature and the preset feature threshold.

[0143] In step S3130, the output analyte concentration data at the current time is determined based on the state type identifier.

[0144] Specifically, when no fluctuation is detected according to the data features of the first window length analyte concentration data, the current time remains in the default reset state. When fluctuation is detected according to the data features of the first window length analyte concentration data, the fluctuation is distinguished, and the reset state is replaced by the start of fluctuation or the end of fluctuation. The processing methods corresponding to different state types are as follows: if the current time corresponds to the reset state, the raw analyte concentration data is used as the output analyte concentration data; if the current time corresponds to the start of fluctuation, the predicted data is used as the output analyte concentration data; if the current time corresponds to the end of fluctuation, the difference between the predicted data and the raw analyte concentration data is analyzed, if the difference is large, the predicted data is used as the output analyte concentration data, if the difference is small, the state type is restored to the reset state, and the raw analyte concentration data is used as the output analyte concentration data, wherein the difference being large or small can be determined by a threshold. FIG. 8 and FIG. 9 show the comparison of the raw signal and the corrected signal collected by the embodiment. In FIG. 8, the circled part of the signal is the to-be-corrected data identified, and after the to-be-corrected data is processed by the above method, the corrected data shown in FIG. 9 is obtained, and it can be seen that the abnormal fluctuation is accurately eliminated.

[0145] Step S3130 can also only handle the situation where fluctuations have occurred, i.e., the state type only includes fluctuation start and fluctuation end. When step S3120 detects fluctuations, the corresponding current time is marked as the fluctuation start and the fluctuation end. If marked as the fluctuation start, the original analyte concentration data is replaced with the prediction data as the output analyte concentration data to complete the correction of the current time data. If marked as the fluctuation end, the difference between the prediction data and the original analyte concentration data is analyzed; if the difference is large, the original analyte concentration data is replaced with the prediction data as the output analyte concentration data; if the difference is small, the original analyte concentration data is not replaced, and the original analyte concentration data is used as the output analyte concentration data. For non-fluctuation situations, the original analyte concentration data can be directly used as the current time data after step S3130 detects, without the need to correct the original data.

[0146] FIG. 6 is a flowchart of a data correction method according to an embodiment. As shown in FIG. 6, the flow includes the following steps:

[0147] Step S210: Obtain analyte concentration data in a first time period and at a current time to form first window length data; the first time period is a time period before the current time by a first preset time length.

[0148] Specifically, referring to FIG. 7, the current time is time t, and the first preset time can be set according to the requirements of calculation accuracy, calculation data volume, etc. For example, the first preset time is set as T1-1, and then the first time period is time t-1 to time t-(T1-1), from which first window length data of a total T1 time length from time t to time t-(T1-1) can be obtained. The analyte concentration data is the gas concentration or liquid concentration in the target object, which can be selected as glucose concentration data or blood glucose concentration data.

[0149] Step S220: Determine whether the original analyte concentration data corresponding to the current time is to be corrected based on the data features of the first window length data.

[0150] Specifically, the data to be corrected includes abnormal data, and can also include redundant data, distorted data, etc. At least two types of data features are extracted from the first window length data, including the amplitude of high-frequency data, principal component analysis residual error, data prediction error, and high-frequency data control chart, etc. In another embodiment, a certain type of data feature can also be extracted from the first window length data, and the analysis is based on this single type of data feature to improve the calculation speed. The extracted data features are subjected to threshold value judgment, and the judgment result of the data features is used to analyze whether the original analyte concentration data corresponding to the current time is to be corrected.

[0151] Step S230, if the original analyte concentration data is to be corrected data, setting the state type of the current time based on the trend feature of the first window length data.

[0152] Specifically, when the to-be-corrected data occurs, the data detected by the sensor can show a large and deep concave, which can also be a convex phenomenon in other types of abnormalities. The trend feature of the current time can be analyzed to determine the abnormal stage of the current time, so as to more accurately process the to-be-corrected data.

[0153] The trend feature can be obtained by calculating the peak direction of the first window length data, for example, the peak is upward, and the slope of the subsequent data of the peak is negative, that is, the data shows a downward trend; or the peak is downward, and the slope of the subsequent data of the peak is positive, and the data shows an upward trend. When the trend feature is upward, the state type is set to fluctuation start, and when the trend feature is downward, the state type is set to fluctuation end; or, when the trend feature is downward, the state type is set to fluctuation start, and when the trend feature is upward, the state type is set to fluctuation end. For different fluctuation types, the correspondence between the trend feature and the state type can be set differently.

[0154] Step S240, determining the output analyte concentration data of the current time based on the state type.

[0155] Specifically, step S240 can process both abnormal and non-abnormal situations, that is, the state type includes fluctuation start, fluctuation end, and reset state of non-fluctuation. The reset state is the initial default state of all times. When step S220 does not detect fluctuation, the current time remains the default reset state. When step S220 detects fluctuation, the fluctuation is distinguished based on step S230, and the reset state is replaced by fluctuation start or fluctuation end. The processing methods corresponding to different state types are as follows: if the current time corresponds to the reset state, the original analyte concentration data is used as the output analyte concentration data; if the current time corresponds to the fluctuation start, the predicted data is used as the output analyte concentration data; if the current time corresponds to the fluctuation end, the difference between the predicted data and the original analyte concentration data is analyzed, if the difference is large, the predicted data is used as the output analyte concentration data, if the difference is small, the state type is restored to the reset state, and the original analyte concentration data is used as the output analyte concentration data, wherein the difference being large or small can be determined by a threshold. FIGS. 8 and 9 show the comparison of the original signal and the corrected signal collected by the embodiment. In FIG. 8, the part of the signal circled is the to-be-corrected data identified, and after the to-be-corrected data is processed by the above method, the corrected data as shown in FIG. 9 is obtained, and it can be seen that the abnormal fluctuation is accurately eliminated.

[0156] Step S240 can also only make processing for the case where fluctuation has occurred, i.e. the state type only includes fluctuation start and fluctuation end. When step S220 detects fluctuation, the corresponding current time is marked as fluctuation start and fluctuation end. If marked as fluctuation start, the original analyte concentration data is replaced with the prediction data as the output analyte concentration data to complete the correction of the current time data. If marked as fluctuation end, the difference between the prediction data and the original analyte concentration data is analyzed; if the difference is large, the original analyte concentration data is replaced with the prediction data as the output analyte concentration data; if the difference is small, the original analyte concentration data is not replaced, and the original analyte concentration data is used as the output analyte concentration data. For the case where there is no fluctuation, the original analyte concentration data can be directly used as the data of the current time after detection by step S220, without the need for correction of the original data.

[0157] The output analyte concentration data is used for output display and / or for use in other data analysis.

[0158] In the present application, the pressure recognition method and the data correction method are used to obtain analyte concentration data at the current time and within a preset time length before the current time to form first window length data; based on data features of the first window length data, it is determined whether the original analyte concentration data corresponding to the current time is to be corrected data; if the original analyte concentration data is to be corrected data, the state type of the current time is set based on the trend features of the first window length data; and the output analyte concentration data of the current time is determined based on the state type, thereby solving the problem of large system power consumption and difficulty in integration on small volume devices, and realizing the identification and correction of to-be-corrected data using a single analyte sensor, which helps to reduce system integration difficulty and reduce system power consumption.

[0159] In one embodiment, referring to FIG. 7, based on step S220, based on the data features of the first window length data, it is determined whether the original analyte concentration data corresponding to the current time is to be corrected data, which specifically includes the following steps:

[0160] Step S310, at least two types of data features are extracted from the first window length data.

[0161] Step S320, based on the confidence and weight value of each type of data feature, each type of data feature is jointly calculated.

[0162] Step S330, based on the joint calculation result, it is determined whether the original analyte concentration data corresponding to the current time is to be corrected data.

[0163] Specifically, each type of feature has a corresponding set of confidence and weight values, and the various types of data features are weighted and summed based on the confidence and weight values. If the calculation result exceeds the preset fluctuation threshold, the original analyte concentration data corresponding to the current time is judged as the data to be corrected. If the calculation result does not exceed the preset fluctuation threshold (for example, the fluctuation threshold is 0.5), the original analyte concentration data corresponding to the current time is not judged as the data to be corrected. Wherein, the weight value is preset; the confidence is calculated based on the data feature.

[0164] In the present embodiment, the joint calculation of multiple data features is used to make multi-dimensional judgment on the data to be corrected, thereby improving the accuracy of the judgment.

[0165] In one of the embodiments, referring to FIG. 7, based on the step S320, the joint calculation of various types of data features is performed based on the confidence and weight values of the various types of data features, including:

[0166] Step S321, calculating the feature threshold of each type of feature based on the analyte concentration historical data of the current user.

[0167] Specifically, the analyte concentration historical data of the current user for N days is obtained, and the stable feature value of the analyte concentration of the user is calculated as the feature threshold of each type of feature.

[0168] Step S322, setting the confidence of the data feature based on the size relationship between the feature threshold and the corresponding data feature.

[0169] Specifically, the data feature exceeding the feature threshold is recorded as 1, and the data feature not exceeding the feature threshold is recorded as 0.

[0170] Step S323, joint calculation of various types of data features based on the confidence of each type of data feature and the preset weight value; the weight value corresponds to each type of data feature.

[0171] In the present embodiment, the personalized feature threshold is set based on the historical data of the user, so that the judgment of the data to be corrected is more accurate on different individuals.

[0172] In one of the embodiments, based on the step S230, the state type of the current time is set based on the trend feature of the first window length data, including:

[0173] Step S231, calculating the trend feature of the first window length data.

[0174] Step S232, when the trend feature is a sharp peak upward, the state type of the current time is marked as fluctuation start.

[0175] Step S233, when the trend feature is a sharp peak downward, the state type of the current time is marked as fluctuation recovery.

[0176] Specifically, referring to FIG. 10, when the analyte sensor is pressed, the sensor shows a large and deep concave in the data expression. This kind of abnormal situation deviating from the normal analyte concentration expression may trigger a low value alarm or other error prompt when accumulated to be obvious enough. According to the trend characteristics, the phase of the abnormal fluctuation can be analyzed. Since the slope of the subsequent data after the peak upward is negative, that is, the data shows a downward trend, it can be indicated that the current time is in the beginning stage of being pressed. Since the slope of the subsequent data after the peak downward is positive, that is, the data shows an upward trend, it can be indicated that the current time is in the end stage of being pressed, so as to further divide and mark the fluctuation. In FIG. 10, the peak at point A is detected and the trend is downward, so point A is marked as the beginning of the fluctuation. The peak at point B is detected and the trend is upward, so point B is marked as the recovery of the fluctuation. Other similar situations generated by the fluctuation caused by being pressed can also be identified by the direction of the peak of the data.

[0177] In the embodiment, by analyzing the characteristics of two key nodes in the analyte concentration waveform during the fluctuation duration, the fluctuation phase at the current time is accurately marked, and the perception ability of the monitoring system to the data to be corrected is improved.

[0178] In one of the embodiments, based on the step S240, the output analyte concentration data at the current time is determined based on the state type, including:

[0179] In step S410, if the state type mark is marked as the beginning of the fluctuation, the predicted data is taken as the output analyte concentration data at the current time.

[0180] In step S420, if the state type mark is marked as the recovery of the fluctuation, the difference between the original analyte concentration data and the predicted data is calculated; and the output analyte concentration data at the current time is determined based on the difference.

[0181] Specifically, the predicted data can be calculated by dynamic prediction, or can be set in advance by a fixed predicted value.

[0182] Referring to FIG. 10, after the fluctuation begins, the current time is necessarily in the situation deviating from the normal data, so the predicted value is used to correct it. After the fluctuation recovers, the progress of the recovery cannot be judged by the current time, so by comparing the original analyte concentration data with the predicted data, it is judged whether the current time is in the situation deviating from the normal data.

[0183] In the embodiment, by classifying and discussing the beginning of the fluctuation and the recovery of the fluctuation, the corresponding correction scheme is given, so as to ensure the quality of the data to be corrected.

[0184] In one of the embodiments, based on the step S420, the output analyte concentration data at the current time is determined based on the difference, including:

[0185] In step S421, when the difference is less than the comparison threshold, the original analyte concentration data is taken as the output analyte concentration data at the current time.

[0186] In step S422, when the difference is not less than the comparison threshold, the prediction data is taken as the output analyte concentration data at the current time.

[0187] Referring to FIG. 10, when the difference is less than the comparison threshold, it indicates that the measurement curve is close enough to the prediction curve, and then the prediction can be stopped and the measurement curve is taken as the output; otherwise, the prediction curve is taken as the output.

[0188] In the embodiment, through the comparison of the difference, the data closer to the actual situation is taken as the output data during the fluctuation recovery, and the output accuracy during the fluctuation recovery is improved.

[0189] In one of the embodiments, before the step S410, it further includes:

[0190] In step S430, the second window length data is obtained based on the analyte concentration data corresponding to the second period, and the second period is a time length before the current time.

[0191] Specifically, referring to FIG. 7, the current time is t, and the second preset time can be set according to the requirements of calculation accuracy, calculation data volume, etc. The second preset time length can be set the same as the first preset time length or can be set differently. Optionally, the second preset time length is greater than the first preset time length. When the second preset time length is set as T2-1, the second period is from t-1 to t-(T2-1), and the analyte concentration data in the time window from t-1 to t-(T2-1) forms the second window length data.

[0192] In step S440, the prediction data is generated based on the second window length data.

[0193] Specifically, the data prediction method includes but is not limited to the prediction method based on autoregression, deep learning, machine learning, etc.

[0194] In the embodiment, the dynamic prediction is performed based on the second window length data, the prediction data is updated in real time following the current time, and the quality of the to-be-corrected data correction is improved.

[0195] In one of the embodiments, based on the step S240, the output analyte concentration data at the current time is determined based on the state type, and further includes:

[0196] If the original analyte concentration data is not the data to be corrected, the state type of the current time is reset state; in the reset state, the original analyte concentration data is taken as the output analyte concentration data of the current time.

[0197] Specifically, the default flag of the current time is 0, i.e. reset state; when it is identified and determined as fluctuation by step S220, the flag will be marked as +1, i.e. fluctuation start, or marked as -1, i.e. fluctuation recovery. When the analyte concentration data value of the current time is received, the state type thereof is judged based on the flag; if the flag is 0, no data correction processing is performed, i.e. the original analyte concentration data is taken as the output analyte concentration data of the current time.

[0198] The present application will be described and illustrated below through an embodiment.

[0199] FIG. 7 is a flowchart of data correction in an embodiment, as shown in FIG. 7, the method comprises the following processes:

[0200] I. Fluctuation detection

[0201] S1, receiving analyte concentration data Samplet of the current time t collected by a continuous glucose monitoring system (CGM), and combining analyte concentration data corresponding to a first time period to form a first window length data with a length of T1; the first time period is a time period within a first preset time length before the current time. Wherein, the analyte concentration data Samplet is glucose concentration data.

[0202] S2, extracting at least two types of data features from the first window length data; based on the confidence and weight value of each type of data feature, each type of data feature is calculated jointly; if the joint calculation result exceeds the fluctuation threshold, the original analyte concentration data Samplet is determined as data to be corrected; if the joint calculation result does not exceed the fluctuation threshold, the original analyte concentration data Samplet is determined as non-data to be corrected.

[0203] S3, when determined as non-data to be corrected, the current time t corresponding to the original analyte concentration data Samplet retains the reset state, i.e. the flag is 0. When determined as data to be corrected, the state type of the current time t is set based on the trend feature of the first window length data; if the trend feature is a peak upward, the state type of the current time t is switched from the reset state to the fluctuation start, i.e. the flag is +1; if the trend feature is a peak downward, the state type of the current time t is switched from the reset state to the fluctuation recovery, i.e. the flag is -1.

[0204] II. Fluctuation correction

[0205] S4. determining the output analyte concentration data of the current time t based on the flag bit:

[0206] S4.1, when the flag bit is in the reset state 0, the original analyte concentration data Samplet is displayed as the output analyte concentration data.

[0207] S4.2, when the flag bit is in the fluctuation start state +1, the analyte concentration data corresponding to the second time period is read to obtain the second window length data with a length of T2, and the second time period is the time within the second preset time length before the current time. The predicted data PredictedSamplet is generated based on the second window length data, and the predicted data PredictedSamplet is used as the output analyte concentration data of the current time t.

[0208] S4.3, when the flag bit is in the fluctuation recovery state -1, the analyte concentration data corresponding to the second time period is read to obtain the second window length data with a length of T2, and the second time period is the time within the second preset time length before the current time. The predicted data PredictedSamplet is generated based on the second window length data. By comparing the original analyte concentration data Samplet and the predicted data PredictedSamplet, when the deviation between the two is less than the threshold A, the actual data value Samplet is used as the output analyte concentration data for display; otherwise, the predicted data PredictedSamplet is continued to be used for display.

[0209] In this embodiment, the recognition and correction of fluctuation are realized only by relying on the current signal fed back by the analyte sensor in the CGM, without relying on the data stream provided by other physical sensors. Compared with the scheme that needs to rely on additional physical sensors, this method has the advantages of small system integration volume, no additional peripheral devices, and low system power consumption.

[0210] The present application is described and illustrated by an embodiment. When the fluctuation specifically corresponds to the pressure abnormality, the data processing process is as follows:

[0211] Based on the analyte concentration data Samplet at the current time, a first window length of 20 minutes is selected to generate the first window length data. Principal component analysis is selected as the first feature extraction method, and the first window length data after retaining 90% of the principal components is reorganized. After reorganization, the residual energy between the original data and the reorganized data is calculated. When the residual energy exceeds the threshold value, it is judged to be a compression anomaly, and the feature mark during compression is shown in FIG. 7. The residual energy threshold value can be determined by the chi-square distribution value of the historical data. When the feature is an upward sharp peak upward, it is judged to be the start of compression, and the compression start flag is set; when the feature is a downward sharp peak downward, it is judged to be a compression recovery, and the compression stop flag is set. After detecting the start of compression, the predicted data is used to replace the current data value Samplet; when the compression state is corrected to compression recovery, the deviation A between the real-time data value Samplet and the predicted data value PredictedSamplet is less than 20%, the real-time data value Samplet is used, otherwise, the predicted data value PredictedSamplet is continuously used.

[0212] In this embodiment, the recognition and correction of compression anomaly are realized only by relying on the current signal fed back by the analyte sensor in the CGM, without relying on the data stream provided by other physical sensors. Compared with the scheme that needs to rely on additional physical sensors, this method has the advantages of small system integration volume, no additional peripheral devices, and low system power consumption.

[0213] It should be noted that the steps shown in the above flow or the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0214] In this embodiment, a compression recognition device and a data correction device are also provided, the compression recognition device is used to implement the compression recognition method in the above embodiments and optional implementation manners, and the data correction device is used to identify the data correction method in the above embodiments and optional implementation manners, which has been described and will not be repeated. The terms "module", "unit", "sub-unit" and the like used below can be a combination of software and / or hardware that can implement a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware or a combination of software and hardware is also possible and is conceived.

[0215] FIG. 12 is a structural block diagram of a compression recognition device according to an embodiment. As shown in FIG. 12, the device includes an original data acquisition module 11 and a compression recognition module 12.

[0216] The original data acquisition module 11 is configured to acquire at least one type of data feature of the first window length analyte concentration data.

[0217] a pressure identification module 12 configured to determine whether the analyte sensor is under pressure based on a data feature of the first window length analyte concentration data;

[0218] wherein the first window length analyte concentration data comprises raw analyte concentration data at the current time point;

[0219] The first window length analyte concentration data does not include data fed back by other sensors, which do not include the analyte sensor.

[0220] In one embodiment, the pressure identification module 12 is further configured to determine whether the analyte sensor is under pressure based on a size relationship between the single data feature and a preset feature threshold, or

[0221] based on the size relationship between each type of data feature and the corresponding preset feature threshold, set the confidence and / or weight corresponding to each type of data feature;

[0222] based on the confidence of each type of data feature and the preset weight value, weighted sum each type of data feature, and based on a comparison result between the weighted sum result and a preset fluctuation threshold, determine whether the analyte sensor is under pressure.

[0223] In one embodiment, the pressure identification module 12 is further configured to obtain the feature threshold based on analyte concentration history data of the current user.

[0224] FIG. 13 is a structural block diagram of a data correction device according to one embodiment, as shown in FIG. 13, the device comprises: a raw data acquisition module 21, a data output module 22.

[0225] The raw data acquisition module 21 is configured to acquire at least one type of data feature of the first window length analyte concentration data;

[0226] The data output module 22 is configured to determine the output analyte concentration data at the current time point based on a comparison result between the at least one type of data feature and a preset feature threshold;

[0227] wherein the first window length analyte concentration data comprises raw analyte concentration data at the current time point;

[0228] The first window length analyte concentration data does not include data fed back by other sensors, which do not include the analyte sensor.

[0229] In some embodiments, the data output module 22 is further configured to determine whether the analyte sensor is under pressure based on a comparison result of the at least one type of data feature and a preset feature threshold; if under pressure, determine the output analyte concentration data at the current time based on a trend feature of the first window length analyte concentration data; wherein if the trend feature is a spike upward, the predicted data is taken as the output analyte concentration data at the current time;

[0230] if the trend feature is a spike downward, calculate a difference value between the original analyte concentration data and the predicted data; when the difference value is not less than a comparison threshold, the predicted data is taken as the output analyte concentration data at the current time;

[0231] when the difference value is less than the comparison threshold, the original analyte concentration data is taken as the output analyte concentration data at the current time;

[0232] if not under pressure, the original analyte concentration data corresponding to the current time is taken as the output analyte concentration data at the current time.

[0233] In some embodiments, the data output module 22 is further configured to determine whether under pressure based on a size relationship between a single data feature and a preset feature threshold, or set a confidence level and / or a weight corresponding to each type of data feature based on a size relationship between each type of data feature and a corresponding preset feature threshold; obtain a joint calculation result based on the confidence level of each type of data feature and a preset weight value, and determine whether under pressure based on a comparison result of the joint calculation result and a preset fluctuation threshold.

[0234] In some embodiments, the data output module 22 is further configured to determine a state type identifier at the current time based on a comparison result of the at least one type of data feature and a preset feature threshold; and determine the output analyte concentration data at the current time based on the state type identifier.

[0235] In some embodiments, the data output module 22 is further configured to determine whether the analyte sensor is under pressure based on a comparison result of the at least one type of data feature and a preset feature threshold; if not under pressure, mark the state type identifier at the current time as a reset state; if under pressure, determine the state type identifier at the current time based on a trend feature of the first window length analyte concentration data; wherein if the trend feature is a spike upward, mark the state type identifier at the current time as a fluctuation start; if the trend feature is a spike downward, mark the state type identifier at the current time as a fluctuation recovery.

[0236] In some embodiments, the data output module 22 is further configured to, if the state type of the current time point is identified as a reset state, output the raw analyte concentration data corresponding to the current time point as the output analyte concentration data of the current time point; if the state type of the current time point is identified as a fluctuation start, output the prediction data as the output analyte concentration data of the current time point; if the state type of the current time point is identified as a fluctuation recovery, calculate a difference between the raw analyte concentration data and the prediction data; when the difference is not less than a comparison threshold, output the prediction data as the output analyte concentration data of the current time point; and when the difference is less than the comparison threshold, output the raw analyte concentration data as the output analyte concentration data of the current time point.

[0237] FIG. 14 is a structural block diagram of a data correction device according to an embodiment. As shown in FIG. 14, the device further includes a raw data acquisition module 10, a data to be corrected judgment module 20, a state type marking module 30, and a data output module 40.

[0238] The raw data acquisition module 10 is configured to acquire analyte concentration data of a current time point and a first time period, to form first window length data.

[0239] The data to be corrected judgment module 20 is configured to judge whether the raw analyte concentration data corresponding to the current time point is data to be corrected based on data features of the first window length data.

[0240] The state type marking module 30 is configured to set a state type of the current time point based on a trend feature of the current time point of the first window length data if the raw analyte concentration data is data to be corrected.

[0241] The data output module 40 is configured to determine output analyte concentration data of the current time point based on the state type.

[0242] In one embodiment, the raw data acquisition module 10 is configured to acquire analyte concentration data corresponding to the current time point and a first time period, to form first window length data; and the first time period is a time point within a first preset time length before the current time point.

[0243] In one embodiment, the state type marking module 30 is configured to set a state type of the current time point based on a trend feature of the current time point if the raw analyte concentration data is data to be corrected.

[0244] In one embodiment, the data to be corrected judgment module 20 is further configured to extract at least two types of data features from the first window length data; perform joint calculation on the data features based on confidence and weight values of the data features; and judge whether the raw analyte concentration data corresponding to the current time point is data to be corrected based on a result of the joint calculation.

[0245] In one of the embodiments, the to-be-corrected data judging module 20 is further configured to calculate feature threshold values of various features based on the analyte concentration history data of the current user; set confidence levels of the data features based on the size relationship between the feature threshold values and the corresponding data features; and jointly calculate the various data features based on the confidence levels of the various data features and preset weight values, the weight values corresponding to the various data features.

[0246] In one of the embodiments, the state type marking module 30 is further configured to calculate a trend feature of the first window length data; mark the state type of the current time as fluctuation start when the trend feature is a peak upward; and mark the state type of the current time as fluctuation recovery when the trend feature is a peak downward.

[0247] In one of the embodiments, the data output module 40 is further configured to, if the state type is marked as fluctuation start, take the predicted data as the output analyte concentration data of the current time; if the state type is marked as fluctuation recovery, calculate a difference value between the original analyte concentration data and the predicted data; and determine the output analyte concentration data of the current time based on the difference value.

[0248] In one of the embodiments, the data output module 40 is further configured to, if the difference value is less than a comparison threshold value, take the original analyte concentration data as the output analyte concentration data of the current time; and if the difference value is not less than the comparison threshold value, take the predicted data as the output analyte concentration data of the current time.

[0249] In one of the embodiments, the data output module 40 is further configured to obtain second window length data based on the analyte concentration data corresponding to a second time period, the second time period being a time period within a second preset time length before the current time; and generate the predicted data based on the second window length data.

[0250] In one of the embodiments, the data output module 40 is further configured to, if the original analyte concentration data is not the to-be-corrected data, mark the state type of the current time as reset state; and in the reset state, take the original analyte concentration data as the output analyte concentration data of the current time.

[0251] It should be noted that each of the above modules can be a functional module or a program module, and can be implemented by software or hardware. For the modules implemented by hardware, each of the above modules can be located in the same processor; or each of the above modules can also be located in different processors in any combination.

[0252] In the embodiment, a computer device is also provided, including a memory and a processor, the memory stores a computer program, and the processor is configured to execute the computer program to perform the steps in any of the above method embodiments.

[0253] Optionally, the computer device can further include a transmission device connected with the processor and an input / output device connected with the processor.

[0254] It should be noted that the specific examples in the embodiment can refer to the examples described in the above embodiments and optional implementation manners, which will not be described herein.

[0255] In addition, in combination with the data correction method provided in the above embodiments, a storage medium can also be provided to implement the data correction method in the embodiment. The storage medium stores a computer program; the computer program is executed by a processor to implement any of the data correction methods in the above embodiments.

[0256] It should be understood that the specific embodiments described herein are only used to explain this application, but not to limit it. According to the embodiments provided in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor are within the scope of the present application.

[0257] Obviously, the drawings are only some examples or embodiments of the present application, and can be applied to other similar situations without creative labor for those of ordinary skill in the art. In addition, it can be understood that although the work done in the development process may be complex and long, some design, manufacture or production changes according to the technical content disclosed in the present application are only routine technical means for those of ordinary skill in the art, and should not be regarded as insufficient disclosure of the present application.

[0258] The technical features of the above embodiments can be combined arbitrarily. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist contradictory, it should be considered as the scope of the present disclosure.

[0259] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the patent scope of the application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, some modifications and improvements can be made, which are all within the scope of the present application. Therefore, the patent protection scope of the present application should be subject to the appended claims.

Claims

1. A pressure recognition method, characterized in that, The method, applied to an analyte monitoring system, includes: Acquire at least one type of data feature from the analyte concentration data of the first window length; Based on the comparison result of the at least one type of data feature and the preset feature threshold, it is determined whether the analyte sensor is under pressure at the current moment; The analyte concentration data for the first window length includes the raw analyte concentration data at the current moment; The analyte concentration data for the first window length does not include data fed back from other sensors, and the other sensors do not include analyte sensors.

2. The pressure recognition method according to claim 1, wherein: The at least one type of data feature includes at least one of the following: amplitude of high-frequency data, principal component analysis residual, data prediction error, and high-frequency data control chart.

3. The pressure recognition method according to any one of claims 1-2, wherein: Determining whether the analyte sensor is under pressure at the current moment based on the comparison result of the at least one type of data feature and a preset threshold includes: Based on the relationship between a single data feature and a preset feature threshold, it is determined whether the system is under pressure, or Based on the relationship between various data features and their corresponding preset feature thresholds, set the confidence level and / or weight of each data feature. The joint calculation result is obtained based on the confidence level of various data features and the preset weight value. Based on the comparison result of the joint calculation result and the preset fluctuation threshold, it is determined whether the data is under pressure.

4. The pressure recognition method according to claim 3, wherein: The process of obtaining the joint calculation result based on the confidence level and preset weight value of each type of data feature includes: Based on the confidence level and preset weight value of each type of data feature, the data features of each type are weighted and summed.

5. The pressure identification method according to any one of claims 1-4, wherein: The preset feature threshold is obtained based on the current user's historical analyte concentration data.

6. The pressure recognition method according to any one of claims 1-5, wherein, The first window length analyte concentration data includes the raw analyte concentration data at the current moment, including: The analyte concentration data corresponding to the current time and the first time period are obtained to form the analyte concentration data of the first window length; the first time period is the duration within a first preset time length before the current time.

7. A data correction method, characterized in that, The method, applied to an analyte monitoring system, includes: Acquire at least one type of data feature from the analyte concentration data of the first window length; Based on the comparison results of the at least one type of data feature and the preset feature threshold, the output analyte concentration data at the current moment is determined; The output analyte concentration data at the current moment is selected from the predicted data or the original analyte concentration data corresponding to the current moment; The analyte concentration data for the first window length includes the raw analyte concentration data at the current moment; The analyte concentration data for the first window length does not include data fed back from other sensors, and the other sensors do not include analyte sensors.

8. The data correction method according to claim 7, wherein, The first window length analyte concentration data includes the raw analyte concentration data at the current moment, including: The analyte concentration data corresponding to the current time and the first time period are obtained to form the analyte concentration data of the first window length; the first time period is the duration within a first preset time length before the current time.

9. The data correction method according to any one of claims 7-8, wherein, The at least one type of data feature includes at least one of the following: amplitude of high-frequency data, principal component analysis residual, data prediction error, and high-frequency data control chart.

10. The data correction method according to claim 7, wherein, The method includes: The second window length analyte concentration data is obtained based on the analyte concentration data corresponding to the second time period, where the second time period is the duration within a second preset time length before the current time. The predicted data is generated based on the analyte concentration data of the second window length.

11. The data correction method according to claim 10, wherein, The second preset time length may be the same as or different from the first preset time length.

12. The data correction method according to claim 10, wherein, The second preset time length is greater than the first preset time length.

13. The data correction method according to any one of claims 7-12, wherein, The output analyte concentration data is used for display and / or data analysis.

14. The data correction method according to any one of claims 7-13, wherein, The step of determining the output analyte concentration data at the current moment based on the comparison result of the at least one type of data feature and the preset feature threshold includes: Based on the comparison result of the at least one type of data feature and the preset feature threshold, it is determined whether the analyte sensor is under pressure at the current moment; If pressure is applied, the output analyte concentration data at the current moment is determined based on the trend characteristics of the analyte concentration data of the first window length. If there is no pressure, the original analyte concentration data at the current moment will be used as the output analyte concentration data at the current moment.

15. The data correction method according to claim 14, wherein, The trend characteristics include upward peaks and downward peaks.

16. The data correction method according to claim 15, wherein, If the trend characteristic is an upward peak, then the predicted data will be used as the output analyte concentration data at the current moment; If the trend characteristic is a downward peak, then calculate the difference between the original analyte concentration data and the predicted data; The output analyte concentration data at the current moment is determined based on the difference.

17. The data correction method according to claim 16, wherein, The step of determining the output analyte concentration data at the current moment based on the difference includes: When the difference is not less than the comparison threshold, the predicted data is used as the output analyte concentration data at the current moment; When the difference is less than the comparison threshold, the original analyte concentration data is used as the output analyte concentration data at the current moment.

18. The data correction method according to any one of claims 14-17, wherein: Determining whether the analyte sensor is under pressure at the current moment based on the comparison result of the at least one type of data feature and a preset feature threshold includes: Based on the relationship between a single data feature and a preset feature threshold, it is determined whether the system is under pressure, or Based on the relationship between various data features and their corresponding preset feature thresholds, set the confidence level and / or weight of each data feature. The joint calculation result is obtained based on the confidence level of various data features and the preset weight value. Based on the comparison result of the joint calculation result and the preset fluctuation threshold, it is determined whether the data is under pressure.

19. The data correction method according to claim 18, wherein: The process of obtaining the joint calculation result based on the confidence level and preset weight value of each type of data feature includes: Based on the confidence level and preset weight value of each type of data feature, the data features of each type are weighted and summed.

20. The data correction method according to any one of claims 7-19, wherein: The preset feature threshold is obtained based on the current user's historical analyte concentration data.

21. The data correction method according to any one of claims 7-20, wherein: The step of determining the output analyte concentration data at the current moment based on the comparison result of the at least one type of data feature and the preset feature threshold includes: Based on the comparison result between the at least one type of data feature and the preset feature threshold, the state type identifier at the current moment is determined; Based on the state type identifier, the current output analyte concentration data is determined.

22. The data correction method according to claim 21, wherein: The step of determining the state type identifier at the current moment based on the comparison result of the at least one type of data feature and a preset feature threshold includes: Based on the comparison result of the at least one type of data feature and the preset feature threshold, it is determined whether the analyte sensor is under pressure at the current moment; If there is no pressure, the current state type is marked as reset state; If under pressure, the current state type identifier is determined based on the trend characteristics of the analyte concentration data within the first window length; wherein, If the trend characteristic is an upward spike, mark the current state type as the start of a fluctuation; If the trend characteristic is a downward peak, the current state type is marked as fluctuation recovery.

23. The data correction method according to claim 22, wherein: If the current state type is identified as reset, the original analyte concentration data corresponding to the current state will be used as the output analyte concentration data for the current state. If the current state type is marked as the start of a fluctuation, then the predicted data will be used as the output analyte concentration data for the current moment. If the current state type is marked as fluctuation recovery, then calculate the difference between the original analyte concentration data and the predicted data; When the difference is not less than the comparison threshold, the predicted data is used as the output analyte concentration data at the current moment; When the difference is less than the comparison threshold, the original analyte concentration data is used as the output analyte concentration data at the current moment.

24. A pressure-sensitive identification device, characterized in that, The device includes: The raw data acquisition module is used to acquire at least one type of data feature of the analyte concentration data of the first window length; The pressure recognition module is used to determine whether the analyte sensor is under pressure at the current moment based on the comparison result of the at least one type of data feature and a preset feature threshold. The first window length analyte concentration data includes the original analyte concentration data at the current moment; The analyte concentration data for the first window length does not include data fed back from other sensors, and the other sensors do not include analyte sensors.

25. A data correction device, characterized in that, The device includes: The raw data acquisition module is used to acquire at least one type of data feature of the analyte concentration data of the first window length; The data output module is used to determine the output analyte concentration data at the current moment based on the comparison result between the at least one type of data feature and a preset feature threshold. The first window length analyte concentration data includes the original analyte concentration data at the current moment; The analyte concentration data for the first window length does not include data fed back from other sensors, and the other sensors do not include analyte sensors.

26. A computer device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the steps of the pressure detection method according to any one of claims 1-6.

27. A computer device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the steps of the data correction method according to any one of claims 7-23.

Images