Spectrometer, integrated system based on artificial intelligence and sample parameter analysis method

Abstract

The invention provides a spectrograph, an integrated system based on artificial intelligence and a sample parameter analysis method.The integrated system based on artificial intelligence comprises the spectrograph and one or more servers, and each server is provided with an artificial intelligence module. Namely, the Internet of Things technology, the compact spectrum analysis technology, the intelligent terminal and artificial intelligence are organically integrated, so that the target sample can be accurately identified and represented. Further, a micro spectrometer that can be applied to smartphones or other portable electronics is designed that uses non-spherical surfaces, toric mirrors and cylindrical lenses, providing a good balance between resolution and luminous flux, and providing improved stray light interference suppression. In this way, rapid, accurate and real-time analysis can be provided, a user can obtain clear information and personalized suggestions about a target sample, and the method is particularly suitable for medical and chemical samples in the field of high performance liquid chromatography.

Description

Technical Field

[0001] This application belongs to the field of spectral analysis technology, and in particular relates to a spectrometer, an artificial intelligence-based integrated system, and a sample parameter analysis method. Background Technology

[0002] A spectrometer is an instrument that decomposes incident polychromatic light into spectral components and measures the intensity distribution of each wavelength after passing through a sample. In its optical system design, several key performance parameters need to be comprehensively optimized and balanced within a general architecture, including: spectral resolution, luminous flux, stray light suppression level, structural complexity, system configurability, and overall size.

[0003] Spectrometers are widely used in the fields of material identification and characterization. By detecting the spectral information emitted, transmitted, or reflected by a sample, various physical properties can be inferred, such as refractive index, concentration, luminescence characteristics, and chemical composition.

[0004] Currently, most commercial spectrometers employ dispersive optical structures, which use transmission or reflection diffraction gratings to spread the incident light beam according to wavelength. The system typically also includes one or more aspherical reflecting or transmitting optical elements (such as aspherical mirrors or lenses) to collimate the dispersed light and image it onto a detector (such as a photodiode array). The system's optical geometry determines the size and shape of the imaging spot on the detector, ensuring that light of different wavelengths is distributed longitudinally along the detector.

[0005] Traditional spectrometer optical systems typically include components for collimation, dispersion, and focusing to form a spectral image. The entrance interface is usually a slit structure, and can be equipped with input optics to guide the diverging beam into the system. The dispersed light signal is received by a linear array sensor, typically located on the spectral image plane, and converted into an electrical signal, thus enabling rapid full-spectrum acquisition without moving parts. However, such systems generally suffer from large size, complex mechanical structure, and overall bulkiness. Furthermore, they have inherent limitations in optical performance, such as astigmatism, chromatic aberration, and spectral field curvature on the detector plane. Even compact designs using a single concave grating struggle to achieve true miniaturization.

[0006] In contrast, waveguide-based spectrometers offer significant advantages in terms of size. Traditional spectrometers rely on large optical components and three-dimensional optical paths, while waveguide spectrometers use thin, monolithic glass substrates to confine light waves within a waveguide layer on the order of hundreds of micrometers, thus approximating a two-dimensional optical path and greatly reducing system thickness. Therefore, waveguide technology is considered an important development direction for realizing ultracompact spectrometers. However, these devices still face a series of challenges in practical applications, such as high propagation loss, stray light caused by scattering at waveguide boundaries, and limited optical coupling efficiency.

[0007] Currently, how to effectively overcome the problems of high propagation loss, boundary scattering stray light, and insufficient coupling efficiency caused by the aforementioned waveguide structures while meeting the miniaturization requirements remains a technical challenge that has not yet been properly resolved in the industry. Summary of the Invention

[0008] The purpose of this application is to provide a spectrometer, an artificial intelligence-based integrated system, and a sample parameter analysis method that can achieve a balance between resolution and luminous flux, and can achieve the technical effect of reducing stray light interference and minimizing optical aberrations.

[0009] This application provides a spectrometer, an artificial intelligence-based integrated system, and a sample parameter analysis method, which are implemented as follows: A spectrometer, comprising: The outer casing is provided with an entrance slit for receiving light from a light source; Dispersive elements are used to disperse light from a light source. A complex concave element is used to focus the light dispersed by the dispersive element onto the detector, so that the light is dispersed along the length of the detector. Cylindrical lenses are used to form a linear image on the detector by focusing light that is not focused by the complex concave element in the direction perpendicular to the length of the detector. A wireless transmission module is used to transmit the collected data to a target terminal, wherein the target terminal includes at least one of the following: an Internet of Things terminal, a smartphone device, or a cloud system.

[0010] In one embodiment, the optical cavity of the spectrometer is provided with: a first toric mirror, a grating, a second toric mirror, a detector, and one or more light traps.

[0011] In one embodiment, the housing is provided with an entrance slit that guides light from a light source to a first toric mirror in the optical cavity, the first toric mirror guiding the light beam to a grating in the optical cavity, the grating guiding the light beam to a second toric mirror in the optical cavity, the second toric mirror guiding the light to a detector in the optical cavity, and the one or more light traps absorbing stray light from the grating.

[0012] In one embodiment, the optical cavity is coated with a light-absorbing coating.

[0013] In one embodiment, the entrance slit is at least one of the following: at least one core of a single-mode fiber, at least one core of a multimode fiber, at least one pinhole with a diameter approximately equal to the diameter of the single-mode fiber, at least one pinhole with a diameter approximately equal to the diameter of the multimode fiber, a slit with a width approximately equal to the diameter of the single-mode fiber, and a slit with a width approximately equal to the diameter of the multimode fiber.

[0014] In one embodiment, the dispersive element is reflective.

[0015] In one embodiment, the concave torus element is one of the following: a concave torus lens having at least one of a spherical and / or a non-spherical cross section, or a positive torus lens having at least one of a plano-convex, spherical and / or a non-spherical cross section; the cylindrical lens is one of the following: a convex cylindrical lens having a rectangular cross section, or a positive cylindrical lens having at least one of a plano-convex, spherical and / or a non-spherical cross section.

[0016] In one embodiment, the cylindrical lens is used to collimate the light beam, the dispersive element is used to separate the collimated light into different wavelengths, and the cylindrical lens is used to receive the dispersed light and focus it onto the detector along a horizontal line.

[0017] An integrated system based on artificial intelligence includes: the aforementioned spectrometer, one or more servers, wherein the servers are equipped with an artificial intelligence module, wherein: The one or more servers are used to receive multidimensional training data from a spectrometer or chemical analysis equipment; The artificial intelligence module is used to generate feature spectra for multiple molecules or groups of molecules based on the training data; The one or more servers are also used to receive experimental data from the spectrometer; The artificial intelligence module is also used to compare the experimental data with the feature spectrum and automatically generate a report on the molecules present in the identified sample.

[0018] In one implementation, the one or more servers are cloud servers.

[0019] In one embodiment, the one or more servers are further configured to receive multidimensional training data from the spectrometer or chemical analysis device, wherein the multidimensional training data includes: public datasets and / or additional third-party datasets.

[0020] In one implementation, the report carries a deterministic value associated with each identified molecule.

[0021] A method for analyzing sample characteristic parameters based on the above-mentioned integrated system includes: The target sample is subjected to absorption, emission, and reflectance spectra measurements in multiple wavelength ranges using a multi-wavelength spectrometer, or one or more regions of interest of the target sample are scanned. One or more features of the target sample are extracted using computer vision; Identify one or more regions of interest within one or more features of a target object using computer vision; Measure the spectrophotometric value of each of the plurality of wavelengths to generate the spectrum of each region of interest in the target sample; The artificial intelligence module analyzes one or more characteristic parameters of the target sample by analyzing the spectrum of each region of interest in the target sample, one or more features of the target sample, and one or more regions of interest within one or more features of the target object.

[0022] In one implementation, one or more features of the target sample are extracted using computer vision, including: Data is analyzed and curve resolution is enhanced by performing convolution operations within the encoder network; A set of feature curves is generated based on global and local features and test results.

[0023] In one embodiment, the target sample is subjected to absorption, emission, and reflectance spectra measurements within multiple wavelength ranges using a multi-wavelength spectrometer, or one or more regions of interest of the target sample are scanned, including: One or more regions of interest in a target sample are captured by an array sensor to detect light in the wavelength range of 185 nm to 1100 nm.

[0024] In one embodiment, before analyzing one or more characteristic parameters of the target sample by using an artificial intelligence module to analyze the spectrum of each region of interest in the target sample, one or more features of the target sample, and one or more regions of interest within one or more features of the target object, the method further includes: Perform wavelength calibration using a reference source; The spectral peaks are matched with known molecular characteristic spectra to verify the accuracy of the artificial intelligence module in detecting elemental emission, and nonlinear distortion is corrected by fitting a fifth-order polynomial model that maps pixel positions to wavelengths.

[0025] The spectrometer provided in this application includes: a housing with an entrance slit for receiving light from a light source; a dispersive element for dispersing the light from the light source; a toric concave element for focusing the dispersed light onto a detector, thus dispersing the light along the length of the detector; and a cylindrical lens for forming a line image on the detector from light that is not focused by the toric concave element along the length of the detector. In this example, by employing an aspherical surface, a toric mirror, and a cylindrical lens, a balance can be achieved between resolution and luminous flux, and the technical effects of reducing stray light interference and minimizing optical aberrations can be achieved. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a schematic diagram of the artificial intelligence-based recognition system provided in this application; Figure 2 This is a perspective view of a mirror spectrometer provided in this application; Figure 3 This is a perspective view of a non-spherical surface spectrometer provided in this application; Figure 4 This is a schematic diagram of a toric surface reflector provided in this application; Figure 5 This is a schematic diagram of a cylindrical lens provided in this application focusing scattered light from a diffraction grating into a linear image; Figure 6 This is a schematic diagram of an optical system including a cylindrical lens provided in this application, in which the lens is configured to focus an incident beam into a linear image. Figure 7 This is a schematic diagram of the spectral data of the characteristic emission spectrum of the mercury lamp provided in this application; Figure 8 This is a schematic diagram of the calibrated intensity wavelength provided in this application; Figure 9 This is a schematic diagram of the spectral resolution evaluation of the five characteristic peaks of benzene based on the AI-based spectral system provided in this application; Figure 10 This is a flowchart of one embodiment of the method for analyzing sample characteristic parameters based on an integrated system provided in this application. Detailed Implementation

[0028] To enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this application.

[0029] Addressing the limitations of existing spectrometers, this paper proposes an adaptive artificial intelligence system built using the Internet of Things (IoT). Combining computer vision and spectroscopy, a method for material analysis is developed through cross-checking of multidimensional data. The use of AI allows the model to optimize and improve as the dataset grows. This approach expands the application scope of existing spectroscopic techniques and provides users with fast, reliable, and user-friendly information.

[0030] Specifically, a portable method and system for material analysis is provided, integrating three core components: an Internet of Things (IoT) or smartphone device, compact spectroscopy, and artificial intelligence to improve the quality and accessibility of material analysis. In one embodiment, a miniature spectrometer applicable to smartphones and other portable electronic devices is provided, designed to use aspherical surfaces to correct optical aberrations and to minimize size and volume through unilateral optics. This spectrometer utilizes aspherical surfaces, toric mirrors, and cylindrical lenses to provide a good balance between resolution and throughput, and offers improved stray light interference suppression. This approach provides rapid, accurate, and real-time analysis, enabling users to obtain clear information (e.g., spectral data) and personalized recommendations about the target sample, particularly suitable for medical and chemical samples in the field of high-performance liquid chromatography (HPLC).

[0031] This example provides an artificial intelligence (AI)-based system for automatically identifying chemical molecules in fluid samples. The system includes one or more cloud servers configured to receive training data from one or more spectrometers or chemical analysis devices. An AI module deployed on the cloud servers automatically develops characteristic spectra for multiple molecules or ensembles of molecules based on this training data, which is supplemented by public datasets and / or additional third-party datasets. The aforementioned one or more cloud servers also receive experimental data of medical fluid samples from a test spectrometer. The AI ​​module then automatically compares the experimental data with the characteristic spectra and generates a report indicating the identified molecules present in the sample.

[0032] To allow independent manipulation of the beam's propagation characteristics in the tangential or sagittal plane at any point of intersection between the beam and the optical elements within the spectrometer, this is achieved in this example by employing a cylindrical or toric optical element with a dominant optical power in only one direction. Specifically, this optical element can include: all types of cylindrical lenses, all types of toric lenses, and one-dimensional transmission or reflection gratings located on a plane, concave, convex, cylindrical, toric, or spherical substrate. Here, "all types" can refer to elements with positive or negative optical power and that may have a spherical or non-spherical cross-section.

[0033] This example also provides a spectrometer including: a dispersive element for dispersing light from a light source; and a toric concave element configured to focus the light dispersed by the dispersive element onto a detector, such that the light is dispersed along the length of the detector. The light is not completely focused onto the detector by the toric concave element in a direction perpendicular to the length of the detector, and a cylindrical lens is provided to form a line image on the detector.

[0034] Furthermore, a small entrance aperture can be provided at the entrance slit of the spectrometer. Specifically, this small entrance aperture can be: the core of a single-mode or multimode fiber, a pinhole matching the diameter of the fiber core, or a slit of similar width and less than a few millimeters in height. The optical output obtained through this aperture can be: a symmetrical or asymmetrical cone with a three-dimensional propagation path.

[0035] The aforementioned spectrometer may specifically include: an entrance aperture, a collimation device, a dispersion-focusing device, a focusing device, and a detector. The dispersion-focusing device may include the following transmission subsystems: a cylindrical or toric mirror for collimation only in the sagittal plane; a transmission grating for dispersion only in the sagittal plane; and a cylindrical or toric mirror for focusing only in the sagittal plane. The collimation device collimates only in the tangential plane, and the focusing device focuses only in the tangential plane. In this way, the size of all optical elements within the spectrometer can be reduced, thereby significantly reducing the overall instrument volume and effectively correcting optical aberrations such as astigmatism and spectral image curvature.

[0036] This compact spectrometer system can be integrated into an Internet of Things (IoT) platform or attached to a smartphone device employing AI-driven analysis. It features onboard data storage and signal processing capabilities, enabling real-time spectral measurements in field applications. Measurement results can be wirelessly transmitted to a remote station for immediate analysis and sharing. The spectrometer can incorporate non-spherical optical surfaces, including parabolic, toric, and cylindrical geometries, allowing for simultaneous spectral analysis of multiple light sources within a compact structure. This approach enables precise alignment of scattered light with the detector and minimizes crosstalk, significantly reducing the overall size of the spectrometer housing and achieving a balance between resolution and flux. Stray light interference can be reduced using light traps and light-absorbing coatings, further enhancing performance. Numerical comparisons of computer simulations and experimental results of the optical system when illuminated by parallel-propagating planar light show good consistency in the chosen parameters.

[0037] like Figure 1The diagram shown illustrates the recognition system described in this example, including a built-in spectrometer, data streams, and infrastructure deployment, demonstrating how a cloud-based AI model can process local requests by integrating computer vision image input and spectral data acquired from sensors built into a portable device.

[0038] refer to Figure 2 A mirror spectrometer 200 is shown in ray tracing form. The optics of the spectrometer 200 include: an entrance aperture 202 for the core of an optical fiber 201 for input signal transmission; a collimating mirror 204; a reflection diffraction grating 206; and a focusing toric mirror 208. For the spectrometer 200, input light 203 is emitted from the entrance aperture 202 and diverges towards the collimating mirror 204, which collimates the diverging light 203 into collimated light 205. The collimated light 205 propagates and then incident on the grating 206, which disperses the light 203 into dispersive collimated light 205 by reflection. Then, the focusing toric mirror 208 focuses the light 205 into converging light 207, thereby forming a spectral image 210 on a detector 211. Figure 2 As shown, the propagation paths of the diverging light 203, collimating light 205, dispersive light, and converging light 207 are all in three-dimensional coordinates. The spectrometer 200 includes three key optical elements: a collimating mirror 204, a grating 206, and a focusing toric mirror 208. These three optical elements have a large finite working aperture to receive and manipulate the diverging light 203, dispersive collimating light 205, and converging light 207 without cutting them off at any point. To correct this astigmatism, a toric mirror 208 is incorporated into the spectrometer to compensate for astigmatism and focus the light onto the detector. Furthermore, cylindrical lenses can also be used to simultaneously reduce the light onto the detector array, thereby focusing the light onto an image narrower than the detector height.

[0039] like Figure 3 As shown, another lens spectrometer 300 is illustrated in ray tracing form. The optics of this spectrometer 300 include: an entrance aperture 302 serving as the core of an optical fiber 301 for input signal transmission; a series of diverging beams passing through a sample cell 304; a collimating lens 306; a transmission diffraction grating 308; and a focusing lens 310. For the spectrometer 300, input light 303 is emitted from the entrance aperture 302 and diverges towards the collimating cylindrical lens 306, which collimates the diverging light 305 into collimated light 307. The collimated light 307 propagates and is incident on the grating 308, which disperses the light 308 into dispersive collimated light 309. The focusing cylindrical lens 310 then focuses the dispersive collimated light 309 into converging light 311, thereby forming a spectral image on the detector 312. Figure 3As shown, the propagation paths of the diverging light 305, collimating light 307, dispersive light 309, and converging light 311 are all three-dimensional. The three key optical elements within the spectrometer 300—the collimating lens 307, the grating 308, and the focusing cylindrical lens 310—need to have sufficiently large finite working apertures to receive and manipulate the diverging light 305, collimating light 307, dispersive collimating light 309, and converging light 311 without truncating them at any point. Therefore, the overall volume required to construct the spectrometer 300 is three-dimensional.

[0040] Furthermore, such as Figure 4 As shown, the mirror surface 411 can be a toric mirror, which allows the tangential and sagittal focal lines to converge to a single focal plane. This configuration enhances focusing and image quality over a wide range of incident angles, making it particularly advantageous in spectrometer applications and CCD-based optical systems. Figure 4 A toric mirror 411 is shown because its focal length is constant, whereas known optical systems using focusing lenses always exhibit chromatic aberration due to their refractive index being wavelength-dependent, thus their focal length is wavelength-dependent. Using a toric mirror avoids the spherical aberration produced by spherical mirrors. In this embodiment, the use of a mirror causes a significant bending of the optical path from the light source to the grating, rather than keeping the light source and grating essentially in a straight line. The toric mirror is manufactured as an aspherical element with two orthogonal curvatures (meridian and sagittal) that are different from each other. The toric mirror 411, applied to a spectrometer, simultaneously focuses and disperses the beam in both the vertical (meridian) and horizontal (sagittal) directions. Its meridional radius, controlling horizontal focusing, is adjustable and can be set to a plane as needed. The two fixed sagittal radii and flat portion of the mirror provide horizontal focusing. This toric surface design allows for precise correction of astigmatism and field curvature, enabling clear imaging of spectral lines on a flat detector plane. Therefore, the use of toric mirrors improves resolution and reduces optical aberrations, eliminating the need for additional correction optics, thus simplifying the system and minimizing its size, weight, and alignment complexity.

[0041] exist Figure 4This document defines several optical parameters associated with the torus mirror for ray tracing and curvature analysis. The torus mirror 411 has two distinct radii of curvature: one in the horizontal (tangential) plane and one in the vertical (sagittal) plane, enabling it to correct astigmatism in off-axis imaging systems. In this example, the angle of incidence is denoted as θ, which is equal to half the angle between the incident and reflected rays; the tangential radius is denoted as R_t, also known as the basis curve, which is the radius of curvature in the horizontal plane; and the sagittal radius is denoted as R_s, or the secondary curve, which defines the curvature in the vertical plane. In typical torus geometry, R_s is generally smaller than R_t. The object distance (P) is the distance from the object to the center of the mirror, specifically where the horizontal and vertical axes of the mirror aperture intersect, also known as the object conjugate distance. The image distance (q) is the distance from the center of the mirror to the image, expressed in analytical calculations as S_t in the tangential (meridian) plane and S_s in the sagittal (secondary) plane. The dual-radius structure of the toric mirror enables precise focusing across two planes, making it particularly suitable for applications requiring reduced astigmatism and improved image quality. In this example, the focusing toric mirror is designed according to the following formula:

[0042] When using a spherical mirror to focus light from a point source, astigmatism is typically produced due to the mirror's uniform curvature. In contrast, toric mirrors, by combining two different radii of curvature (one in the tangential plane and one in the sagittal plane), can significantly reduce this astigmatism, thus enabling the formation of a compact, elliptical focal spot. Therefore, toric mirrors can be used in focusing and aberration correction systems, such as… Figure 4 The toric mirror used in this example is shown in ray tracing form.

[0043] like Figure 5 As shown, the cylindrical lens 413 is used to focus the spectrally dispersed parallel beam 412 from the diffraction grating located upstream of the lens into a line image. The dispersed light components 414 intersect and converge, forming a line focal point at the sensor focal plane 415. However, this line focal point only occurs along the Y-axis; there is no corresponding line focal point along the X-axis or parallel to the X-axis. Therefore, when the image light is focused onto the image plane, the focusing cylindrical lens 413 ensures precise focusing in the tangential plane, thereby improving resolution. Thus, the beam 414 forms rays corresponding to each wavelength on the detector 415, rather than forming a light spot. However, if the height of the light exceeds the height of the sensor pixel, excess light is lost, leading to a decrease in the sensitivity of the spectrometer.

[0044] like Figure 6 As shown, the dot plot indicates that all light spots within the field of view (FOV) remain compact, indicating high imaging accuracy. The spectral diffusers from the grating intersect and are focused by the cylindrical lens to form a linear image, as shown... Figure 5 As shown in the dot plot, the RMS radius of the root mean square (RMS) spot is approximately 13 mm, and the field of view ranges from... The wavelength range is from 400 nm to 632.8 nm. The proposed optical system utilizes dot plot analysis tools to evaluate the quality of the focal line and verifies its performance based on diffraction theory.

[0045] The spectrometer presented in this example incorporates aberration corrections (e.g., using aspherical or toric focusing mirrors) and various types of aspherical surfaces for spectroscopic applications. The overall size and weight are reduced by incorporating toric mirrors and cylindrical lenses, while eliminating optical aberrations, particularly astigmatism and field curvature. In this example, the spectrometer design achieves a good balance between resolution and flux through the use of aspherical surfaces, toric mirrors, and cylindrical lenses, while also suppressing stray light.

[0046] The exact dimensions of the aforementioned spectrometer configuration can be obtained from the spectrometer developed by ZEMAX Development Corporation. It is confirmed that the synchronous optical system provided by cylindrical lenses and toric mirrors allows for the use of smaller CCDs while maintaining imaging capabilities, thus significantly reducing costs. In this example, it can also be used with multiple light sources emitting light in-plane and perpendicular to the plane.

[0047] In another embodiment, this example provides an artificial intelligence (AI)-based system for automatically identifying biomolecules in fluid samples. This system may include one or more cloud servers configured to receive training data from spectrometers and / or chemical analysis equipment. An AI module residing on the cloud server automatically generates characteristic molecular spectra for multiple individual molecules or ensembles of molecules based on this training data. The training data may be augmented using public and / or third-party datasets to improve accuracy and robustness. The system may also receive experimental data from a test spectrometer analyzing medical fluid samples. The AI ​​module compares this experimental data with the previously generated molecular spectra and automatically generates a report indicating the identified molecules present in the sample.

[0048] In one embodiment, a computing device (e.g., computer, smartphone, tablet, smartwatch, etc.) equipped with a processor and memory is also provided, configured to receive and analyze spectral test data from at least one spectral analysis instrument (particularly a spectrophotometric analysis instrument). In one embodiment, the system includes at least one server that communicates with the spectral analysis instrument directly or through an intermediary device (e.g., computer, tablet, or smartphone) via a network. This configuration supports remote data analysis, thereby utilizing greater computing resources than a local device might have. In a further embodiment, the server may include at least one quantum processor designed to assist in advanced analysis of the spectral test data.

[0049] Specifically, Internet of Things (IoT)-enabled systems can include smart devices equipped with computer vision capabilities (e.g., computers, smartphones, tablets, smartwatches, cameras, etc.). These devices have processors and memory and are configured to receive and analyze spectral test data from at least one spectral analysis instrument (particularly a spectrophotometric analysis instrument). In one embodiment, the system includes at least one server that communicates with the spectral analysis instrument directly or through an intermediary device (e.g., a computer, tablet, or smartphone) via a network. This architecture supports remote data processing, enabling access to enhanced computing resources typically unavailable to local devices. In another embodiment, the server includes at least one quantum processor to assist in advanced analysis of the spectral test data.

[0050] The aforementioned system can generate predictive models using methods including, but not limited to, machine learning (ML), artificial intelligence (AI), neural networks (NNs), deep learning, historical data analysis, and data mining. Preferably, the system can obtain predictive data based on historical data, external data sources, machine learning models, artificial intelligence algorithms, neural networks, and other intelligent learning methods, and can employ heuristic algorithms, particle swarm optimization, molecular structure analysis, technical analysis indicators, combinatorial optimization, quantum optimization strategies, iterative methods, deep learning techniques, and feature selection methods.

[0051] like Figure 7 The illustration shows an example of spectral data used to facilitate the recognition of specific molecules, demonstrating the effectiveness of such spectra in distinguishing the presence and concentration of target molecule compounds. In this case, the spectral data corresponds to the characteristic emission spectrum of a mercury lamp, implemented as described in this invention. Figure 2 and Figure 3 As shown. Figure 7The test results presented show several distinct emission peaks corresponding to known mercury spectral lines. Significant peaks were observed at approximately 253.6 nm, 302.4 nm, 312.8 nm, 333.7 nm, 365.1 nm, 404.3 nm, and 435.6 nm, which are consistent with standard reference values ​​for mercury discharge spectra. These emission lines were captured using a spectrometer system connected to the cloud-based smart platform described in this invention.

[0052] like Figure 8 The image shown is a modified intensity-wavelength graph, representing test results transmitted to an intelligent system hosted on a cloud platform. This system processes the characteristic emission spectrum of a mercury lamp; the relevant system components and processes are as follows... Figure 1 , Figure 2 and Figure 3 As shown.

[0053] refer to Figure 8 The system processes raw intensity data, employs a wavelength calibration model, and matches observed peaks with known molecular characteristic spectra. This verifies the system's ability to accurately detect and analyze elemental emission, confirming the precision of spectral acquisition and the robustness of the fundamental wavelength calibration process. In this process, the system receives input data, including the number of pixels (X) recorded by a detector (such as a CCD or photodiode array) and the corresponding reference wavelength (λ) obtained from a calibration light source (such as a neon or mercury lamp). This data is transmitted to an intelligent system hosted on a cloud-based platform, enabling scalable processing, centralized data access, and integration with additional calibration datasets from multiple sources. The intelligent system processes this data using curve fitting techniques, generating a fifth-order polynomial model, as follows: .

[0054] In the above model, the coefficients arrive The relationship between pixel position and wavelength is defined. Specifically, Indicates the intercept. This represents a linear term, approximately representing a direct mapping from pixel to wavelength. arrive These are higher-order terms used to explain the inherent spectral curvature and nonlinear distortion in optical systems. Once the coefficients are determined, the system can accurately estimate the wavelength corresponding to any given pixel. Furthermore, it explains the rationale for using higher-order polynomials: correcting for the inherent nonlinearity between pixel position and wavelength, and how each coefficient contributes to reconstructing the true spectrum while minimizing instrument-induced errors. This calibration process significantly improves the reliability and accuracy of spectral analysis.

[0055] like Figure 9As shown, in one embodiment, the present invention provides an artificial intelligence (AI)-based system for automating spectral analysis. The system performs spectral performance testing by setting the light source to a deuterium lamp, performing a spectral scan to record wavelength accuracy, and then inserting cuvettes with the same optical path length to scan blank and benzene samples, thereby observing five characteristic peaks of benzene to evaluate spectral resolution. The AI ​​module is designed to automatically develop characteristic spectra for multiple molecules or ensembles of molecules using multidimensional training data. One or more servers receive experimental data from a test spectrometer analyzing fluid samples, and the AI ​​module generates a report identifying the presence of molecules by comparing the experimental data with the characteristic spectra. Data generated by spectrometers or other chemical analysis devices associated with the present invention can be aggregated into a single cloud environment, optionally including additional public or third-party datasets to enhance and strengthen the model. This integration supports the development of one of the most powerful spectral data analysis models known to date. In one embodiment, the report may include not only the identification of the presence of molecules but also an indication of their concentration and / or a probability value associated with each identification, indicating the degree of certainty with which the model identified the reported molecule.

[0056] The example above involves spectroscopic technology and the use of artificial intelligence for multi-element detection in bioanalytes. When applied to medical and chemical samples in high-performance liquid chromatography (HPLC), it can automatically interpret spectral test data to identify the chemical composition of the sample fluid, thereby improving the speed and accuracy of the results.

[0057] Specifically, in this example, a spectrometer is provided, which may include: 1) The outer casing is provided with an entrance slit for receiving light from the light source; 2) Dispersive element, used to disperse light from a light source; 3) Concave surface element, used to focus the light dispersed by the dispersive element onto the detector, so that the light is dispersed along the length of the detector; 4) Cylindrical lens, used to form a linear image on the detector by focusing light that is not focused by the toric concave element in the direction perpendicular to the length of the detector; 5) A wireless transmission module for transmitting the collected data to a target terminal, wherein the target terminal includes at least one of the following: an Internet of Things terminal, a smartphone device, or a cloud system.

[0058] The optical cavity of the aforementioned spectrometer may contain: a first toric mirror, a grating, a second toric mirror, a detector, and one or more light traps. Correspondingly, an entrance slit is provided in the outer casing. The entrance slit guides light from the light source to the first toric mirror in the optical cavity. The first toric mirror guides the light beam to the grating in the optical cavity. The grating guides the light beam to the second toric mirror in the optical cavity. The second toric mirror guides the light to the detector in the optical cavity. The one or more light traps absorb stray light from the grating.

[0059] That is, by using aspherical surfaces, toric mirrors and cylindrical lenses, a balance can be achieved between resolution and light flux, and the technical effect of reducing stray light interference and minimizing optical aberrations can be achieved.

[0060] The interior of the aforementioned optical cavity may be coated with a light-absorbing coating. The aforementioned entrance slit may be at least one of the following: at least one core of a single-mode fiber, at least one core of a multimode fiber, at least one pinhole with a diameter approximately equal to the diameter of a single-mode fiber, at least one pinhole with a diameter approximately equal to the diameter of a multimode fiber, a slit with a width approximately equal to the diameter of a single-mode fiber, or a slit with a width approximately equal to the diameter of a multimode fiber.

[0061] In implementation, the dispersive element described above can be reflective. The concave toric element described above can be one of the following: a concave toric mirror having at least one of a spherical and / or aspherical cross-section, or a positive toric lens having at least one of a plano-convex, spherical and / or aspherical cross-section; the cylindrical lens described above can be one of the following: a convex cylindrical mirror having a rectangular cross-section, or a positive cylindrical lens having at least one of a plano-convex, spherical and / or aspherical cross-section.

[0062] Specifically, the cylindrical lens can be used to collimate the beam, the dispersive element can be used to separate the collimated light into different wavelengths, and the cylindrical lens can be used to receive the dispersed light and focus it onto the detector along a horizontal line.

[0063] This example also provides an integrated system based on artificial intelligence, which may include the aforementioned spectrometer and one or more servers, wherein the servers are equipped with an artificial intelligence module, wherein: The one or more servers are used to receive multidimensional training data from a spectrometer or chemical analysis equipment; The artificial intelligence module is used to generate feature spectra for multiple molecules or groups of molecules based on the training data; The one or more servers are also used to receive experimental data from the spectrometer; The artificial intelligence module is also used to compare the experimental data with the feature spectrum and automatically generate a report on the molecules present in the identified sample.

[0064] Specifically, the aforementioned one or more servers can be cloud servers. These servers can also be used to receive multidimensional training data from the spectrometer or chemical analysis equipment, wherein the multidimensional training data may include, but is not limited to, public datasets and / or additional third-party datasets.

[0065] The report may include a deterministic value associated with each identified molecule.

[0066] Figure 10 This is a flowchart illustrating one embodiment of the method for analyzing sample characteristic parameters based on an integrated system provided in this application. While this application provides method operation steps or apparatus structures as shown in the following embodiments or figures, more or fewer operation steps or module units may be included in the method or apparatus based on conventional or non-inventive effort. In steps or structures where there is no logically necessary causal relationship, the execution order of these steps or the module structure of the apparatus is not limited to the execution order or module structure described in the embodiments and figures of this application. When the method or module structure is applied in actual devices or terminal products, it can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed processing environment) according to the method or module structure shown in the embodiments or figures.

[0067] Specifically, such as Figure 10 As shown, the above-mentioned method for analyzing sample characteristic parameters based on an integrated system may include the following steps: Step 1001: Use a multi-wavelength spectrometer to measure the absorption spectrum, emission spectrum, and reflectance spectrum of the target sample in multiple wavelength ranges, or scan one or more regions of interest of the target sample; Specifically, one or more regions of interest of a target sample can be captured by an array sensor to detect light in the wavelength range of 185 nm to 1100 nm.

[0068] Step 1002: Extract one or more features of the target sample using computer vision; Step 1003: Identify one or more regions of interest within one or more features of the target object using computer vision; Specifically, data can be analyzed and curve resolution enhanced by performing convolution operations within the encoder network; and a set of feature curves can be generated based on global and local features and test results.

[0069] Step 1004: Measure the spectrophotometric value of each of the plurality of wavelengths to generate the spectrum of each region of interest in the target sample; Step 1005: Analyze one or more characteristic parameters of the target sample by using the artificial intelligence module to obtain the spectrum of each region of interest in the target sample, one or more features of the target sample, and one or more regions of interest within one or more features of the target object.

[0070] To achieve more accurate characteristic parameter analysis, wavelength calibration can be performed using a reference source before analyzing one or more characteristic parameters of the target sample; the spectral peaks are matched with known molecular characteristic spectra to verify the accuracy of the artificial intelligence module in detecting elemental emission; and nonlinear distortion is corrected by fitting a fifth-order polynomial model that maps pixel positions to wavelengths.

[0071] When performing characteristic parameter analysis, predictive models can be generated using methods including, but not limited to, machine learning (ML), artificial intelligence (AI), neural networks (NNs), deep learning, historical data analysis, and data mining. Preferably, the system can obtain predictive data based on historical data, external data sources, machine learning models, artificial intelligence algorithms, neural networks, and other intelligent learning methods, and can employ heuristic algorithms, particle swarm optimization, molecular structure analysis, technical analysis indicators, combinatorial optimization, quantum optimization strategies, iterative methods, deep learning techniques, and feature selection methods.

[0072] This application also provides a specific implementation of an electronic device capable of implementing all steps of the method for analyzing sample characteristic parameters based on an integrated system as described in the above embodiments. The electronic device specifically includes: a processor, a memory, a communication interface, and a bus; wherein the processor, memory, and communication interface communicate with each other via the bus; the processor is used to call a computer program in the memory, and when the processor executes the computer program, it implements all steps of the method for analyzing sample characteristic parameters based on an integrated system as described in the above embodiments. For example, when the processor executes the computer program, it implements the following steps: Step 1: Use a multi-wavelength spectrometer to measure the absorption spectrum, emission spectrum, and reflectance spectrum of the target sample in multiple wavelength ranges, or scan one or more regions of interest of the target sample; Step 2: Extract one or more features of the target sample using computer vision; Step 3: Identify one or more regions of interest within one or more features of the target object using computer vision; Step 4: Measure the spectrophotometric value of each of the multiple wavelengths to generate the spectrum of each region of interest in the target sample; Step 5: Analyze one or more characteristic parameters of the target sample by using the artificial intelligence module to analyze the spectrum of each region of interest in the target sample, one or more features of the target sample, and one or more regions of interest within one or more features of the target object.

[0073] Embodiments of this application also provide a computer-readable storage medium capable of implementing all steps of the method for analyzing sample characteristic parameters based on an integrated system as described in the above embodiments. The computer-readable storage medium stores a computer program that, when executed by a processor, implements all steps of the method for analyzing sample characteristic parameters based on an integrated system as described in the above embodiments. For example, when the processor executes the computer program, it implements the following steps: Step 1: Use a multi-wavelength spectrometer to measure the absorption spectrum, emission spectrum, and reflectance spectrum of the target sample in multiple wavelength ranges, or scan one or more regions of interest of the target sample; Step 2: Extract one or more features of the target sample using computer vision; Step 3: Identify one or more regions of interest within one or more features of the target object using computer vision; Step 4: Measure the spectrophotometric value of each of the multiple wavelengths to generate the spectrum of each region of interest in the target sample; Step 5: Analyze one or more characteristic parameters of the target sample by using the artificial intelligence module to analyze the spectrum of each region of interest in the target sample, one or more features of the target sample, and one or more regions of interest within one or more features of the target object.

[0074] It should be noted that in the embodiments of this application, certain software, components, models and other existing solutions in the industry may be mentioned. These should be regarded as exemplary and are only intended to illustrate the feasibility of implementing the technical solution of this application. However, it does not mean that the applicant has used or necessarily used the solution.

[0075] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, hardware + program embodiments are relatively simple in description because they are fundamentally similar to method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0076] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0077] While this application provides the method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or client product execution, the methods shown in the embodiments or drawings can be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment).

[0078] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, a laptop computer, an in-vehicle human-machine interaction device, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0079] While this specification provides method operation steps as described in the embodiments or flowcharts, more or fewer operation steps may be included based on conventional or non-inventive means. The order of steps listed in the embodiments is merely one possible execution order among many and does not represent the only execution order. In actual device or end product execution, the methods shown in the embodiments or drawings may be executed sequentially or in parallel (e.g., in a parallel processor or multi-threaded processing environment, or even a distributed data processing environment). The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitations, the presence of other identical or equivalent elements in the process, method, product, or apparatus that includes said elements is not excluded.

[0080] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, in implementing the embodiments of this specification, the functions of each module can be implemented in one or more software and / or hardware components, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0081] Those skilled in the art will also know that, besides implementing the controller using purely computer-readable program code, the same functions can be achieved by logically programming the method steps, making the controller function as logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices within it used to implement various functions can also be considered structures within that hardware component. Alternatively, the devices used to implement various functions can be considered as both software modules implementing the method and structures within a hardware component.

[0082] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0083] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0084] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0085] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0086] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0087] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0088] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of entirely hardware embodiments, entirely software embodiments, or embodiments combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of computer program products implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0089] The embodiments described in this specification can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. The embodiments of this specification can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0090] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, system embodiments are basically similar to method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments. In the description of this specification, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments in this specification. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0091] The above description is merely an embodiment of the present specification and is not intended to limit the embodiments of the present specification. For those skilled in the art, various modifications and variations can be made to the embodiments of the present specification. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of the embodiments of the present specification should be included within the scope of the claims of the embodiments of the present specification.

Claims

1. A spectrometer, characterized in that, include: The outer casing is provided with an entrance slit for receiving light from a light source; Dispersive elements are used to disperse light from a light source. A complex concave element is used to focus the light dispersed by the dispersive element onto the detector, so that the light is dispersed along the length of the detector. Cylindrical lenses are used to form a linear image on the detector by focusing light that is not focused by the complex concave element in the direction perpendicular to the length of the detector. A wireless transmission module is used to transmit the collected data to a target terminal, wherein the target terminal includes at least one of the following: an Internet of Things terminal, a smartphone device, or a cloud system.

2. The spectrometer according to claim 1, characterized in that, The optical cavity of the spectrometer is provided with: a first toric mirror, a grating, a second toric mirror, a detector, and one or more light traps.

3. The spectrometer according to claim 2, characterized in that, The housing is provided with an entrance slit that guides light from the light source to a first toric mirror in the optical cavity. The first toric mirror guides the light beam to a grating in the optical cavity. The grating guides the light beam to a second toric mirror in the optical cavity. The second toric mirror guides the light to a detector in the optical cavity. The one or more light traps absorb stray light from the grating.

4. The spectrometer according to claim 2, characterized in that, The optical cavity is coated with a light-absorbing coating.

5. The spectrometer according to claim 3, characterized in that, The entrance slit is at least one of the following: at least one core of a single-mode fiber, at least one core of a multimode fiber, at least one pinhole with a diameter approximately equal to the diameter of a single-mode fiber, at least one pinhole with a diameter approximately equal to the diameter of a multimode fiber, a slit with a width approximately equal to the diameter of a single-mode fiber, or a slit with a width approximately equal to the diameter of a multimode fiber.

6. The spectrometer according to claim 1, characterized in that, The dispersive element is reflective.

7. The spectrometer according to claim 1, characterized in that, The concave torus element is one of the following: a concave torus lens having at least one of a spherical and / or a non-spherical cross section, or a positive torus lens having at least one of a plano-convex, spherical and / or a non-spherical cross section; the cylindrical lens is one of the following: a convex cylindrical lens having a rectangular cross section, or a positive cylindrical lens having at least one of a plano-convex, spherical and / or a non-spherical cross section.

8. The spectrometer according to any one of claims 1 to 7, characterized in that, The cylindrical lens is used to collimate the light beam, the dispersive element is used to separate the collimated light into different wavelengths, and the cylindrical lens is used to receive the dispersed light and focus it onto the detector along a horizontal line.

9. An integrated system based on artificial intelligence, characterized in that, include: The spectrometer and one or more servers according to any one of claims 1 to 8, wherein the servers are equipped with an artificial intelligence module, wherein: The one or more servers are used to receive multidimensional training data from a spectrometer or chemical analysis equipment; The artificial intelligence module is used to generate feature spectra for multiple molecules or groups of molecules based on the training data; The one or more servers are also used to receive experimental data from the spectrometer; The artificial intelligence module is also used to compare the experimental data with the feature spectrum and automatically generate a report on the molecules present in the identified sample.

10. The integrated system according to claim 9, characterized in that, The one or more servers mentioned are cloud servers.

11. The integrated system according to claim 9, characterized in that, The one or more servers are also configured to receive multidimensional training data from the spectrometer or chemical analysis equipment, wherein the multidimensional training data includes: public datasets and / or additional third-party datasets.

12. The integrated system according to claim 9, characterized in that, The report contains a deterministic value associated with each identified molecule.

13. A method for analyzing sample parameters based on the integrated system according to any one of claims 9 to 12, characterized in that, include: The target sample is subjected to absorption, emission, and reflectance spectra measurements in multiple wavelength ranges using a multi-wavelength spectrometer, or one or more regions of interest of the target sample are scanned. One or more features of the target sample are extracted using computer vision; Identify one or more regions of interest within one or more features of a target object using computer vision; Measure the spectrophotometric value of each of the plurality of wavelengths to generate the spectrum of each region of interest in the target sample; The artificial intelligence module analyzes one or more characteristic parameters of the target sample by analyzing the spectrum of each region of interest in the target sample, one or more features of the target sample, and one or more regions of interest within one or more features of the target object.

14. The method according to claim 13, characterized in that, Extracting one or more features of the target sample using computer vision, including: Data is analyzed and curve resolution is enhanced by performing convolution operations within the encoder network; A set of feature curves is generated based on global and local features and test results.

15. The method according to claim 13, characterized in that, Using a multi-wavelength spectrometer to perform absorption, emission, and reflectance spectra measurements on a target sample across multiple wavelength ranges, or to scan one or more regions of interest on the target sample, including: One or more regions of interest in a target sample are captured by an array sensor to detect light in the wavelength range of 185 nm to 1100 nm.

16. The method according to claim 13, characterized in that, Before analyzing one or more characteristic parameters of the target sample using the artificial intelligence module by combining the spectrum of each region of interest in the target sample, one or more features of the target sample, and one or more regions of interest within one or more features of the target object, the process further includes: Wavelength calibration is performed using a reference source; The spectral peaks are matched with known molecular characteristic spectra to verify the accuracy of the artificial intelligence module in detecting elemental emission, and nonlinear distortion is corrected by fitting a fifth-order polynomial model that maps pixel positions to wavelengths.

Images