Spectral data analysis method, device and system, storage medium and program product

Abstract

The invention discloses a spectral data analysis method, device and system, a storage medium and a program product, and relates to the technical field of data processing.The spectral data analysis method comprises the steps that spectral data reflected by a target skin area of a user is obtained, and the spectral data comprises signal parameters of multiple optical signals reflected by the target skin area; performing principal component analysis on the spectral data, and extracting each spectral feature in the spectral data; utilizing a partial least squares regression algorithm to determine the relevancy between each spectral feature and the to-be-analyzed index of the user; according to each correlation degree, screening from each spectral feature to obtain a selected spectral feature; and obtaining a spectral analysis result according to the selected spectral characteristics. According to the method, blood glucose detection can be carried out without invasive data acquisition on the user, the technical problem of how to carry out spectral data analysis when non-invasive blood glucose detection is realized is solved, and the user experience is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a spectral data analysis method, device, system, storage medium and program product. Background Art

[0002] In the related technologies, the blood sugar detection of users is mainly based on invasive blood sample collection and analysis, which makes it very inconvenient for users to perform blood sugar detection and the user experience is poor. Therefore, in order to improve the user experience, non-invasive blood sugar detection technology based on spectral data analysis has received widespread attention, which leads to the problem of how to perform spectral data analysis when implementing non-invasive blood sugar detection. Summary of the invention

[0003] The main purpose of this application is to provide a spectral data analysis method, device, system, storage medium and program product, aiming to solve the technical problem of how to perform spectral data analysis when realizing non-invasive blood glucose testing.

[0004] To achieve the above purpose, the present application proposes a spectral data analysis method, which includes:

[0005] Acquiring spectral data of a plurality of light signals reflected from a target skin area of ​​a user;

[0006] Perform principal component analysis on the spectral data to extract multiple spectral features from the spectral data;

[0007] The partial least squares regression algorithm is used to determine the correlation between each spectral feature and the index to be analyzed;

[0008] According to each correlation degree, a selected spectral feature is screened from each spectral feature;

[0009] According to the selected spectral features, the spectral analysis results are obtained.

[0010] In one embodiment, before the step of obtaining the spectrum analysis result according to the selected spectrum feature, the method further comprises:

[0011] Obtain environmental data of the user's environment;

[0012] Compensating and correcting the selected spectral features according to the environmental data to obtain the target spectral features;

[0013] The steps of obtaining the spectrum analysis result according to the selected spectrum characteristics include:

[0014] According to the target spectral characteristics, the spectral analysis results are obtained.

[0015] In one embodiment, the step of obtaining the spectrum analysis result according to the selected spectrum feature includes:

[0016] The selected spectral features are input into a prediction model to obtain a spectral analysis result, wherein the prediction model is pre-trained using a spectral data sample set, and each spectral data sample in the spectral data sample set includes a corresponding analysis result tag.

[0017] In one embodiment, before the step of inputting the selected spectral features into the prediction model to obtain the spectral analysis results, the spectral data analysis method further includes:

[0018] Determine selected time information of the selected spectral feature according to the acquisition time of the spectral data;

[0019] The steps of inputting the selected spectral features into the prediction model to obtain the spectral analysis results include:

[0020] The selected spectral features and the selected time information are input into the prediction model to obtain the spectral analysis result, wherein each spectral data sample in the spectral data sample set includes a corresponding analysis result tag and a time information tag.

[0021] In one embodiment, after the step of inputting the spectral features into the prediction model to obtain the spectral analysis results, the spectral data analysis method further comprises:

[0022] According to a preset period, periodically obtain a plurality of historical spectral data and corresponding historical spectral analysis results to construct a historical spectral data set;

[0023] The prediction model is trained using the historical spectral dataset and the model parameters of the prediction model are updated.

[0024] In one embodiment, the step of obtaining spectral data reflected by the user's skin includes:

[0025] Acquire raw spectral data of multiple light signals reflected by a target skin area of ​​a user;

[0026] The original spectral data are subjected to denoising, baseline correction and normalization to obtain spectral data.

[0027] In addition, to achieve the above objectives, the present application also proposes a spectral data analysis device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the spectral data analysis method as described above.

[0028] In addition, to achieve the above purpose, the present application also proposes a spectral data analysis system, the spectral data analysis system comprising:

[0029] A plurality of light sources, used to emit a plurality of light source signals to a target skin area of ​​a user;

[0030] A photodiode, used to collect multiple light signals reflected from the target skin area and obtain corresponding multiple electrical signals;

[0031] Spectral data analysis equipment as above.

[0032] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the spectral data analysis method as described above are implemented.

[0033] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps of the spectral data analysis method as described above are implemented.

[0034] One or more technical solutions proposed in this application have at least the following technical effects:

[0035] The present application provides a spectral data analysis method, device, system, storage medium and program product, which extract features from spectral data of multiple light signals reflected from a target skin area of ​​a user, and screen out selected spectral features based on the correlation between each extracted spectral feature and an indicator to be analyzed to obtain a spectral analysis result, which can be applied to blood glucose testing. The spectral analysis result is obtained by extracting selected spectral features related to blood glucose indicators, and the blood glucose test result of the user can be determined based on the spectral analysis result, so that blood glucose testing can be performed without invasive data collection for the user, thereby solving the technical problem of how to perform spectral data analysis when implementing non-invasive blood glucose testing and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 This is a schematic diagram of the process of the first embodiment of the spectrum data analysis method of the present application;

[0039] Figure 2 Schematic diagram of the device structure of the hardware operating environment involved in the spectral data analysis method in the embodiment of the present application.

[0040] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0041] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0042] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0043] The main solution of the embodiment of the present application is: obtaining spectral data of multiple light signals reflected by the user's target skin area; performing principal component analysis on the spectral data to extract multiple spectral features in the spectral data; using a partial least squares regression algorithm to determine the correlation between each spectral feature and the indicator to be analyzed; based on each correlation, selecting a selected spectral feature from each spectral feature; and obtaining a spectral analysis result based on the selected spectral feature.

[0044] The present application provides a solution, which extracts features from spectral data of multiple light signals reflected from a target skin area of ​​a user, and selects spectral features based on the correlation between each extracted spectral feature and the index to be analyzed to obtain a spectral analysis result, which can be applied to blood glucose testing. The spectral analysis result is obtained by extracting selected spectral features related to blood glucose indexes, so that the blood glucose test result of the user can be determined based on the spectral analysis result, thereby performing blood glucose testing without invasive data collection on the user. This solves the technical problem of how to perform spectral data analysis when implementing non-invasive blood glucose testing, and improves the user experience.

[0045] It should be noted that the execution subject of this embodiment can be a computing service device with spectral data analysis, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a spectral data analysis device, etc. The following takes the spectral data analysis device as an example to illustrate this embodiment and the following embodiments.

[0046] First, an embodiment of the present application provides a spectral data analysis system, which may include:

[0047] A plurality of light sources, used to emit a plurality of light source signals to a target skin area of ​​a user;

[0048] A photodiode, used to collect multiple light signals reflected from the target skin area and obtain corresponding multiple electrical signals;

[0049] Spectral data analysis equipment as follows.

[0050] It should be noted that multiple light sources can emit light source signals of different wavelengths to the target skin area of ​​the user. The photodiode is a highly sensitive photodiode that can capture the light signals reflected by the target skin area from different light source signals and convert each light signal into a corresponding electrical signal, so that the spectral data analysis device can perform signal processing on the multiple electrical signals to obtain corresponding spectral data.

[0051] The light source may be an LED light source, and multiple light sources and photodiodes may be provided on a wearable device. For example, the wearable device may be a device worn on a user's upper arm or abdomen. The wearable device may send multiple electrical signals to the spectral data analysis device in a wired or wireless manner.

[0052] Based on this, the present application embodiment provides a spectral data analysis method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the spectrum data analysis method of the present application.

[0053] In this embodiment, the spectral data analysis method may include steps S100 to S500:

[0054] Step S100, obtaining spectral data of multiple light signals reflected by a target skin area of ​​a user.

[0055] It should be noted that the spectral data includes signal parameters of multiple light signals, and the signal parameters may include parameters such as the intensity and wavelength of the light signals. After the user wears the wearable device on the target skin area, the wearable device can transmit a light source signal to the target skin area upon receiving a trigger signal, and collect the light signal reflected by the target skin area to obtain a corresponding electrical signal, or periodically transmit a light source signal to the target skin area, and collect the light signal reflected by the target skin area to obtain a corresponding electrical signal; when the spectral data analysis device receives multiple electrical signals sent by the wearable device, it can perform signal processing on the multiple electrical signals, extract the signal parameters of the multiple light signals, and thus obtain the corresponding spectral data.

[0056] In a feasible implementation, step S100 may include: acquiring original spectral data of multiple light signals reflected by the target skin area of ​​the user; and performing denoising, baseline correction and normalization on the original spectral data to obtain spectral data.

[0057] It should be noted that before analyzing the original spectral data, the original spectral data can be preprocessed to reduce impurity data, erroneous data and invalid data in the original spectral data to obtain spectral data, thereby improving the accuracy of spectral data analysis by analyzing the spectral data obtained by preprocessing.

[0058] In a specific implementation, the denoising process may include using a filter or wavelet transform to remove high-frequency noise in the original spectral data. The baseline correction may include correcting the baseline drift of the original spectral data by polynomial fitting or derivative method. The normalization process may include eliminating the influence of the spectral intensity change in the original spectral data on the spectral analysis results by standardizing or normalizing the data.

[0059] Step S200, performing principal component analysis on the spectral data to extract the spectral features in the spectral data.

[0060] It should be noted that principal component analysis (PCA) can perform dimensionality reduction processing on spectral data, calculate the score value of each principal component in the spectral data, and extract multiple main spectral features in the spectral data based on the score value to retain the main variation information of the spectral data.

[0061] Step S300, using a partial least squares regression algorithm to determine the correlation between each spectral feature and the index to be analyzed.

[0062] It should be noted that the index to be analyzed may be a blood sugar index, a body temperature index, a lactic acid index, an alcohol index, a drug abuse index, etc. Taking the blood sugar index as an example, a PLSR model can be constructed based on different spectral feature samples and different blood sugar concentrations using a partial least squares regression (PLSR) algorithm, and the correlation between each spectral feature and the user's blood sugar concentration can be predicted using the PLSR model.

[0063] Step S400 , selecting a selected spectral feature from each spectral feature according to each correlation.

[0064] Step S500, obtaining spectrum analysis results according to the selected spectrum characteristics.

[0065] It should be noted that the selected spectral feature may include at least one spectral feature with a high correlation with the indicator to be analyzed. The spectral analysis result may include a normal result and an abnormal result. Taking blood glucose testing as an example, a normal result is a normal blood glucose concentration, and an abnormal result includes a low blood glucose concentration and a high blood glucose concentration.

[0066] It is understandable that by comparing the selected spectral features with the corresponding standard spectral features, a corresponding comparison result can be obtained, and the spectral analysis result can be obtained by combining the comparison results. Among them, the standard spectral features can be determined according to the standard data corresponding to the index to be analyzed.

[0067] In this embodiment, a genetic algorithm or a recursive feature elimination algorithm may be used to select a selected spectral feature from various spectral features according to various correlations.

[0068] Therefore, this embodiment provides a spectral data analysis method, which extracts features from spectral data of multiple light signals reflected by the target skin area of ​​the user, and screens out selected spectral features based on the correlation between each extracted spectral feature and the indicator to be analyzed to obtain a spectral analysis result, which can be applied to blood glucose testing. The spectral analysis result is obtained by extracting selected spectral features related to the blood glucose indicator, and the blood glucose test result of the user can be determined based on the spectral analysis result, so that blood glucose testing can be performed without invasive data collection on the user. This solves the technical problem of how to perform spectral data analysis when implementing non-invasive blood glucose testing, and improves the user experience.

[0069] In a feasible implementation, after step S400, the spectral data analysis method may further include: acquiring environmental data of the user's environment; and compensating and correcting the selected spectral features according to the environmental data to obtain target spectral features.

[0070] Correspondingly, step S500 may include: obtaining a spectrum analysis result according to the target spectrum characteristics.

[0071] It is understandable that when testing the blood sugar of a user, the influence of environmental factors (such as ambient temperature, ambient humidity, etc.) can also be considered to compensate and correct the selected spectral features, thereby optimizing the selected spectral features, obtaining target spectral features, and improving the accuracy of the spectral features. The environmental data may include an ambient temperature value and / or an ambient temperature value.

[0072] In this embodiment, the spectral feature deviation under different preset environmental data compared with the standard environmental data can be determined in advance based on experimental data. After obtaining the environmental data, the selected spectral feature is compensated and corrected according to the corresponding spectral feature deviation to optimize the selected spectral feature and obtain the target spectral feature.

[0073] Therefore, this embodiment provides a spectral data analysis method. After obtaining the selected spectral features, the selected spectral features are compensated and corrected in combination with the actual environment of the user, thereby improving the accuracy of the target spectral features, thereby obtaining more accurate spectral analysis results, and improving the accuracy of blood glucose testing.

[0074] In a feasible implementation, step S500 may include: inputting the selected spectral features into a prediction model to obtain spectral analysis results.

[0075] The prediction model is pre-trained using a spectral data sample set, and each spectral data sample in the spectral data sample set includes a corresponding analysis result tag.

[0076] It should be noted that the prediction model can be a large language multimodal model, for example, a Flan T-5 model. The spectral data sample set can include multiple groups of experimental spectral data of clinical records, and the analysis results are marked as experimental analysis result marks corresponding to each experimental spectral data. Thus, the prediction model can be used to predict the selected spectral features and obtain the corresponding spectral analysis results.

[0077] In a feasible implementation manner, before “inputting the selected spectral feature into the prediction model to obtain the spectral analysis result”, the spectral data analysis method may further include: determining the selected time information of the selected spectral feature according to the acquisition time of the spectral data;

[0078] Correspondingly, “inputting the selected spectral features into the prediction model to obtain the spectral analysis results” may include: inputting the selected spectral features and the selected time information into the prediction model to obtain the spectral analysis results.

[0079] Each spectral data sample in the spectral data sample set includes a corresponding analysis result tag and a time information tag.

[0080] It is understandable that the value range of the index to be analyzed may be different in different time periods. Therefore, the spectral analysis results may be predicted by combining the acquisition time of the spectral data and the selected spectral features.

[0081] Taking blood glucose testing as an example, fasting blood glucose (FBG): normal blood glucose concentration is between 3.9 and 6.1 mmol / L; low blood glucose concentration is below 3.9 mmol / L, but in diabetic patients, the definition of hypoglycemia may be different, usually below 3.5 mmol / L; high blood glucose concentration is above 6.1 mmol / L, but does not meet the criteria for diagnosis of diabetes.

[0082] Postprandial Blood Glucose: Normal blood glucose concentration means the blood glucose level 2 hours after a meal should be lower than 7.8mmol / L; excessive blood glucose concentration means the blood glucose level 2 hours after a meal exceeds 11.1mmol / L.

[0083] Glycated hemoglobin (HbA1c): Normal blood sugar concentration is a glycated hemoglobin level between 4% and 6%; high blood sugar concentration is a glycated hemoglobin level above 6.5%, which usually indicates that the patient may have diabetes.

[0084] Random blood sugar: Random blood sugar refers to the blood sugar level measured at any time. A high blood sugar concentration of more than 11.1mmol / L may indicate hyperglycemia.

[0085] Therefore, in a specific implementation, each spectral data sample can be classified according to the sample collection time of the spectral data sample, the time information of the spectral data sample can be obtained, the spectral data sample can be marked, and a prediction model can be constructed by training the spectral data sample set. This allows the prediction model to predict the spectral analysis result according to the input selected spectral features and selected time information. Among them, the time information can be the classification label of the classification where the collection time belongs.

[0086] In a feasible implementation, after "inputting the spectral features into the prediction model to obtain the spectral analysis results", the spectral data analysis method may also include: periodically acquiring multiple historical spectral data and corresponding historical spectral analysis results according to a preset period to construct a historical spectral data set; using the historical spectral data set to train the prediction model and update the model parameters of the prediction model.

[0087] It should be noted that the historical spectrum data set may include historical spectrum data and corresponding historical spectrum analysis results within a preset period. The preset period may be adjusted according to actual indicators to be analyzed and actual use environment.

[0088] It is understandable that the present embodiment can set a preset update time or a preset period to periodically retrain and calibrate the prediction model based on historical spectral data and corresponding historical spectral analysis results, so that the prediction model better matches the actual use environment and users.

[0089] In addition, in this embodiment, after obtaining the spectral analysis results, different spectral analysis results can be visualized by different colors, so as to use color changes to help users quickly understand the changing state of the indicators to be analyzed. In a specific implementation, the spectral analysis results output by the prediction model can be mapped to different colors through a color mapping algorithm to present a visualization effect. For example, for blood sugar test results, a color gradient from blue (hypoglycemia) to red (hyperglycemia) can be used for visualization.

[0090] Therefore, this embodiment provides a spectral data analysis method, which trains a large language multimodal model through experimental spectral data, and the obtained prediction model can learn the relationship between spectral data and the indicators to be analyzed, thereby providing accurate prediction of spectral analysis results. In addition, by periodically retraining the prediction model, the prediction model can be further optimized according to different environmental conditions and user conditions to improve the accuracy of the prediction model. In addition, the spectral analysis results are displayed in a color visualization manner, so that users can understand and manage the indicators to be analyzed at a glance, further improving the user experience.

[0091] The present application provides a spectral data analysis device, which includes: at least one processor; and a memory that is communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the spectral data analysis method in the above-mentioned embodiment one.

[0092] Reference below Figure 2 , which shows a schematic diagram of the structure of a spectral data analysis device suitable for implementing the embodiment of the present application. The spectral data analysis device in the embodiment of the present application may include but is not limited to mobile terminals such as laptop computers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions: tablet computers), etc., and fixed terminals such as desktop computers, etc. Figure 2 The spectral data analysis device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0093] like Figure 2As shown, the spectral data analysis device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the spectral data analysis device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the spectral data analysis device to communicate with other devices wirelessly or by wire to exchange data. Although the spectral data analysis device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0094] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0095] The spectral data analysis device provided by the present application adopts the spectral data analysis method in the above embodiment, which can solve the technical problem of how to perform spectral data analysis when realizing non-invasive blood glucose detection. Compared with the related art, the beneficial effects of the spectral data analysis device provided by the present application are the same as the beneficial effects of the spectral data analysis method provided by the above embodiment, and the other technical features in the spectral data analysis device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0096] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0097] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0098] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the spectral data analysis method in the above-mentioned embodiment.

[0099] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0100] The computer-readable storage medium may be included in the spectral data analysis device; or may exist independently without being assembled into the spectral data analysis device.

[0101] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the spectral data analysis device, the spectral data analysis device: obtains spectral data of multiple light signals reflected by the target skin area of ​​the user; performs principal component analysis on the spectral data to extract multiple spectral features in the spectral data; uses a partial least squares regression algorithm to determine the correlation between each spectral feature and the indicator to be analyzed; based on each correlation, selects a spectral feature from each spectral feature; and obtains a spectral analysis result based on the selected spectral feature.

[0102] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0103] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0104] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0105] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned spectral data analysis method, and can solve the technical problem of how to perform spectral data analysis when implementing non-invasive blood glucose detection. Compared with the related art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the spectral data analysis method provided in the above-mentioned embodiment, and will not be repeated here.

[0106] The present application also provides a computer program product, comprising a computer program, which implements the steps of the above-mentioned spectral data analysis method when executed by a processor.

[0107] The computer program product provided by the present application can solve the technical problem of how to perform spectral data analysis when implementing non-invasive blood glucose testing. Compared with the related art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the spectral data analysis method provided by the above embodiment, which will not be repeated here.

[0108] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A spectral data analysis method, characterized in that: The spectral data analysis method comprises: Acquiring spectral data of a plurality of light signals reflected from a target skin area of ​​a user; Performing principal component analysis on the spectral data to extract multiple spectral features from the spectral data; Determine the correlation between each of the spectral features and the index to be analyzed by using a partial least squares regression algorithm; According to the correlations, a selected spectral feature is obtained by screening from the spectral features; According to the selected spectral features, a spectral analysis result is obtained.

2. The spectral data analysis method according to claim 1, characterized in that: Before the step of obtaining a spectral analysis result according to the selected spectral feature, the method further comprises: Acquire environmental data of the environment where the user is located; Compensating and correcting the selected spectral feature according to the environmental data to obtain a target spectral feature; The step of obtaining a spectrum analysis result according to the selected spectrum feature comprises: According to the target spectral characteristics, a spectral analysis result is obtained.

3. The spectral data analysis method according to claim 1, characterized in that: The step of obtaining a spectrum analysis result according to the selected spectrum feature comprises: The selected spectral features are input into a prediction model to obtain a spectral analysis result, wherein the prediction model is pre-trained using a spectral data sample set, and each spectral data sample in the spectral data sample set includes a corresponding analysis result tag.

4. The spectral data analysis method according to claim 3, characterized in that: Before the step of inputting the selected spectral features into a prediction model to obtain spectral analysis results, the spectral data analysis method further comprises: Determining selected time information of the selected spectral feature according to the acquisition time of the spectral data; The step of inputting the selected spectral features into a prediction model to obtain spectral analysis results comprises: The selected spectral features and the selected time information are input into a prediction model to obtain a spectral analysis result, wherein each spectral data sample in the spectral data sample set includes a corresponding analysis result tag and a time information tag.

5. The spectral data analysis method according to claim 3, characterized in that: After the step of inputting the spectral features into a prediction model to obtain a spectral analysis result, the spectral data analysis method further comprises: According to a preset period, periodically obtain a plurality of historical spectral data and corresponding historical spectral analysis results to construct a historical spectral data set; The prediction model is trained using the historical spectral data set, and model parameters of the prediction model are updated.

6. The spectral data analysis method according to any one of claims 1 to 5, characterized in that: The step of obtaining the spectral data reflected by the user's skin comprises: Acquire raw spectral data of multiple light signals reflected by a target skin area of ​​a user; The original spectral data is subjected to denoising, baseline correction and normalization processing to obtain spectral data.

7. A spectral data analysis device, characterized in that: The spectral data analysis device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the spectral data analysis method according to any one of claims 1 to 6.

8. A spectral data analysis system, characterized in that: The spectral data analysis system comprises: A plurality of light sources, used to emit a plurality of light source signals to a target skin area of ​​a user; A photodiode, used to collect a plurality of light signals reflected by the target skin area and obtain a corresponding plurality of electrical signals; The spectral data analysis device as claimed in claim 7.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the spectral data analysis method according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the spectral data analysis method according to any one of claims 1 to 6 are implemented.

Images