Multispectral infrared data processing method, system, and electronic device

Abstract

The present application relates to the field of multispectral infrared analysis, and discloses a multispectral infrared data processing method, system and electronic equipment. The method comprises the following steps: splitting a multispectral processing function into a plurality of multispectral processing sub-modules, compiling and encrypting the multispectral processing sub-modules to obtain an encrypted Wasm module; obtaining multispectral original data of a target object and converting the multispectral original data into binary data; screening and decrypting the encrypted Wasm module according to a scene trigger and a terminal performance detection result to obtain a decrypted module; and inputting the binary data into the decrypted module for processing to obtain a data processing result. The present application directly encapsulates a multispectral processing function algorithm through Wasm, and the execution efficiency is close to that of original code, so that real-time data processing is realized to meet the demand for on-site real-time analysis. The Wasm module can be uniformly run in different terminal environments, the development and maintenance cost is reduced, the Wasm module exists in the form of encrypted binary data and cannot be decompiled, and the core algorithm is protected.

Description

Technical Field

[0001] This invention relates to the field of multispectral infrared analysis technology, and in particular to a multispectral infrared data processing method, system and electronic device. Background Technology

[0002] The core of multispectral infrared analysis technology is to collect spectral response data of target objects in multiple bands such as near-infrared, mid-infrared, and far-infrared, and combine multi-band fusion, feature extraction, and pattern recognition algorithms to achieve functions such as component identification, content detection, and defect screening. Its key requirements are real-time performance, cross-platform compatibility, and data security.

[0003] Multispectral infrared processing technologies are mainly divided into three categories: local processing systems based on dedicated hardware, offline analysis systems based on desktop software, and simple web-based processing systems based on JavaScript. However, simple web-based processing systems rely on JavaScript, resulting in low execution efficiency and processing single samples in seconds, which cannot meet the needs of real-time on-site analysis. While dedicated hardware and desktop software meet performance standards, they suffer from poor portability and insufficient cross-platform compatibility, making them difficult to adapt to mobile detection scenarios. Summary of the Invention

[0004] The main objective of this invention is to provide a multispectral infrared data processing method, system, and electronic device, which aims to solve at least one of the aforementioned technical problems.

[0005] In a first aspect, embodiments of the present invention provide a multispectral infrared data processing method, comprising:

[0006] The multispectral processing function is broken down into multiple multispectral processing sub-modules, and the multispectral processing sub-modules are compiled and encrypted to obtain the encrypted Wasm module.

[0007] Acquire the raw multispectral data of the target object and convert the raw multispectral data into binary data;

[0008] The encrypted Wasm module is filtered and decrypted based on the scene trigger and terminal performance test results to obtain the decrypted module;

[0009] The binary data is input into the decrypted module for processing to obtain the data processing result.

[0010] In some embodiments, the step of splitting the multispectral processing function into multiple multispectral processing sub-modules, compiling and encrypting the multispectral processing sub-modules to obtain an encrypted Wasm module includes:

[0011] The multispectral processing function is broken down into multiple multispectral processing sub-modules;

[0012] The multispectral processing submodule is compiled to obtain the Wasm module and the JS glue script;

[0013] The Wasm module is encrypted to obtain an encrypted Wasm module, and the encryption key is bound to the hardware features of the terminal device.

[0014] Compile the decryption Wasm module corresponding to the encryption key.

[0015] In some embodiments, the step of filtering and decrypting the encrypted Wasm module based on scene triggering and terminal performance detection results to obtain the decrypted module includes:

[0016] In response to the target detection scenario, determine the multispectral processing submodule to be loaded corresponding to the target detection scenario;

[0017] The performance of the terminal device is tested, and the performance test results are obtained.

[0018] Based on the performance test results, the multispectral processing sub-modules to be loaded are screened to obtain the screened modules;

[0019] The filtered modules are preloaded and decrypted to obtain the decrypted modules.

[0020] In some embodiments, determining the multispectral processing submodule to be loaded corresponding to the target detection scene includes:

[0021] The target detection scenario is determined based on a preset mapping table to identify the corresponding multispectral processing sub-module to be loaded.

[0022] The method further includes: a multispectral processing module for acquiring different industry sub-scenarios;

[0023] Set the loading priority of the multispectral processing module for the same scene;

[0024] A preset mapping table of multispectral scenes and modules is constructed based on the multispectral processing module and the loading priority.

[0025] In some embodiments, the method further includes:

[0026] During operation, the data processing results are monitored in real time based on preset monitoring indicators to obtain quality monitoring results; wherein, the preset monitoring indicators include signal-to-noise ratio, baseline drift amplitude, and band synchronization deviation;

[0027] The remaining DDR memory of the device is monitored in real time during operation to obtain performance monitoring results;

[0028] If the quality monitoring results meet the reloading triggering conditions or a first switching request is received, then the reloading triggering decision is executed;

[0029] If the performance monitoring results meet the uninstallation triggering conditions or a second switching request is received, then the uninstallation triggering decision is executed.

[0030] In some embodiments, the step of executing a reloading trigger decision if the quality monitoring result meets the reloading trigger condition or a first switching request is received includes:

[0031] When the signal-to-noise ratio in the quality monitoring result is less than the preset signal-to-noise ratio threshold, the enhanced noise reduction submodule is triggered to reload.

[0032] When the baseline drift amplitude in the quality monitoring results exceeds the preset baseline drift threshold, the high-precision baseline correction submodule is triggered to reload.

[0033] When the band synchronization deviation in the quality monitoring results is greater than the preset band deviation threshold, the multi-band alignment submodule is triggered to reload.

[0034] When the first switching request is received, the high-precision matching submodule and the PLS quantitative submodule are triggered to reload; the first switching request is to switch from fast detection to high-precision detection.

[0035] In some embodiments, the step of executing an uninstallation trigger decision if the performance monitoring result meets the uninstallation trigger condition or a second switching request is received includes:

[0036] When the remaining DDR amount of the device in the performance monitoring results is less than a preset remaining threshold, the enhanced noise reduction submodule is triggered to unload.

[0037] When a second switching request is received, the high-precision matching submodule and the PLS quantitative submodule are unloaded; the second switching request is to switch from high-precision detection to fast detection.

[0038] In some embodiments, the method further includes:

[0039] The data processing results are stored in a non-display buffer pool;

[0040] The data in the non-display buffer pool is sent to the display buffer pool in a first-in-first-out (FIFO) queue manner for visualization.

[0041] Secondly, embodiments of the present invention provide a multispectral infrared data processing system, comprising:

[0042] The function splitting module is used to split the multispectral processing function into multiple multispectral processing sub-modules, and to compile and encrypt the multispectral processing sub-modules to obtain the encrypted Wasm module.

[0043] The data acquisition module is used to acquire the multispectral raw data of the target object and convert the multispectral raw data into binary data.

[0044] The detection and filtering module is used to filter and decrypt the encrypted Wasm module based on the scene trigger and terminal performance detection results, so as to obtain the decrypted module;

[0045] The data processing module is used to input the binary data into the decrypted module for processing to obtain the data processing result.

[0046] Thirdly, embodiments of the present invention provide an electronic device, including:

[0047] One or more processors;

[0048] Memory, used to store one or more programs;

[0049] When the one or more programs are executed by the one or more processors, the one or more processors implement any of the methods described above.

[0050] This invention provides a multispectral infrared data processing method, comprising: splitting the multispectral processing function into multiple multispectral processing sub-modules; compiling and encrypting the multispectral processing sub-modules to obtain an encrypted Wasm module; acquiring the collected raw multispectral data of the target object and converting the raw multispectral data into binary data; filtering and decrypting the encrypted Wasm module according to scene triggering and terminal performance detection results to obtain a decrypted module; and inputting the binary data into the decrypted module for processing to obtain the data processing result. This invention directly encapsulates the core algorithm of the multispectral processing function through Wasm, achieving execution efficiency close to native code, enabling real-time processing of multispectral data, and meeting the needs of real-time on-site analysis. The Wasm module can run uniformly in different terminal environments without the need to develop a dedicated version, greatly reducing development and maintenance costs. Furthermore, the Wasm module exists in encrypted binary form and cannot be decompiled, fundamentally protecting the core algorithm of the multispectral processing function. Attached Figure Description

[0051] Figure 1 A flowchart illustrating a multispectral infrared data processing method provided in an embodiment of the present invention;

[0052] Figure 2 This is a data flow architecture diagram of the multispectral infrared processing involved in the embodiments of the present invention;

[0053] Figure 3This is a schematic diagram of the multispectral data acquisition and preprocessing flow involved in the embodiments of the present invention;

[0054] Figure 4 A structural block diagram of a multispectral infrared data processing system provided in an embodiment of the present invention;

[0055] Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of the present invention.

[0056] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0057] To enable those skilled in the art to better understand the technical solutions of the present invention, exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0058] Where there is no conflict, the various embodiments of the present invention and the features thereof may be combined with each other.

[0059] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0060] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Terms such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0061] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and the invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0062] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information all comply with relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution follows relevant national laws and regulations (e.g., the "Information Security Technology - Personal Information Security Specification"). For example: appropriate measures are taken for personal information access control; restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; and explicit identity targeting is eliminated when using personal information to avoid precisely locating a specific individual.

[0063] The key terms involved in this invention are defined as follows:

[0064] WebAssembly (often abbreviated as Wasm): A new code format;

[0065] SIMD: Single Instruction, Multiple Data;

[0066] PLS: Partial Least Squares;

[0067] SNR: Signal-to-Noise Ratio;

[0068] VOCs: Volatile Organic Compounds;

[0069] AES: Advanced Encryption Standard, a symmetric encryption algorithm;

[0070] PC: Personal Computer, such as a desktop or laptop computer;

[0071] CPU: Central Processing Unit;

[0072] DDR: Double Data Rate SDRAM, or Double Data Rate Synchronous Dynamic Random Access Memory;

[0073] Buffer: A storage area used to temporarily store data.

[0074] In related technologies, WebAssembly (Wasm) is a low-level binary instruction format that can be used as a compilation target for high-level languages ​​such as C / C++ and Rust. It possesses near-native execution efficiency, cross-platform portability, and sandbox security isolation, primarily used to address performance bottlenecks in computationally intensive tasks on the web. However, no technology has yet directly combined it with the analysis and processing of multispectral infrared data. None of the relevant multispectral infrared processing technologies involve the direct integration of Wasm with multispectral infrared processing.

[0075] Multispectral infrared processing technology, which is not combined with Wasm's core advantages, suffers from the following insurmountable defects:

[0076] 1. Insufficient computational performance to meet the demands of real-time multi-band processing: Multispectral infrared data contains data from multiple bands (a single frame of multispectral data can reach tens to hundreds of MB), requiring computationally intensive operations such as multi-band alignment, noise removal, and feature matrix calculations. Related technologies rely on JavaScript for processing, resulting in low efficiency and processing single samples in seconds, failing to meet the needs of real-time on-site analysis. While dedicated hardware and desktop software meet performance requirements, their poor portability and lack of cross-platform compatibility make them unsuitable for mobile detection scenarios.

[0077] 2. Difficult cross-platform adaptation and high deployment costs: Multispectral infrared detection equipment comes in various forms (portable, fixed, vehicle-mounted), and the corresponding terminal devices include PCs, mobile devices, embedded devices, etc. The processing system in related technologies needs to be developed with dedicated versions for different terminals (such as Windows desktop version and Android mobile version), resulting in high development and maintenance costs; moreover, the data formats and processing logic between different devices are incompatible, making multi-scenario collaborative analysis difficult.

[0078] 3. Significant risks to core algorithms and data security: The core value of multispectral infrared analysis lies in proprietary algorithms, which are core intellectual property of enterprises. Algorithms in desktop software or web-based systems exist in source code or bytecode form, making them vulnerable to decompilation and theft. Simultaneously, multispectral data (such as medical and industrial core product data) faces the risk of leakage during transmission or processing due to the lack of secure isolation mechanisms.

[0079] 4. High module coupling and poor flexibility in scene adaptation: Different multispectral infrared application scenarios (such as industrial quality inspection and environmental monitoring) have different requirements for algorithm accuracy, processing speed and band range. In related technologies, the system adopts an integrated design with fixed algorithms and processing flow, which cannot dynamically switch core modules (such as high-precision analysis modules and rapid qualitative modules) according to the scene, resulting in resource waste or insufficient accuracy.

[0080] To address at least one of the technical problems existing in the aforementioned related technologies, the present invention provides a multispectral infrared data processing method. Figure 1 This is a flowchart illustrating a multispectral infrared data processing method provided in an embodiment of the present invention.

[0081] As an embodiment of the present invention, such as Figure 1 As shown, the multispectral infrared data processing method includes:

[0082] Step S1: Divide the multispectral processing function into multiple multispectral processing sub-modules, compile and encrypt the multispectral processing sub-modules to obtain the encrypted Wasm module;

[0083] Step S2: Acquire the collected multispectral raw data of the target object and convert the multispectral raw data into binary data;

[0084] Step S3: Based on the scene trigger and terminal performance detection results, the encrypted Wasm module is filtered and decrypted to obtain the decrypted module;

[0085] Step S4: Input the binary data into the decrypted module for processing to obtain the data processing result.

[0086] It should be noted that the execution subject in this embodiment can be an electronic device, which can be a computer device with data processing function, or other devices that can achieve the same or similar functions. This embodiment does not limit this. In this embodiment, a computer device is used as an example for explanation.

[0087] It is understood that the multispectral infrared data processing method in this embodiment focuses on the direct integration of WebAssembly (Wasm) and multispectral infrared data processing, and can cover all scenarios that require real-time, cross-platform, and high-security multispectral infrared analysis. Specific applications include: industrial multispectral quality inspection, environmental multispectral monitoring, medical multispectral diagnostics, and agricultural multispectral detection.

[0088] For example, in the field of industrial multispectral quality inspection: it is applicable to scenarios such as chemical raw material composition detection, semiconductor chip defect screening, and spectral characteristic analysis of new energy materials. After the industrial-grade multispectral infrared sensor collects data, no dedicated hardware or desktop software is required. The browser directly loads the Wasm processing module to complete multi-band data fusion, feature extraction, and quality judgment in real time, adapting to various terminals such as production line PCs and mobile devices. For example, in the field of environmental multispectral monitoring: it is used for quantitative analysis of multiple atmospheric components (CO2, VOCs, etc.), water pollutant identification, and soil heavy metal detection. After portable devices collect data, the mobile browser calls the Wasm module, and the device directly completes data noise reduction, band matching, and concentration calculation, without relying on cloud computing power, reducing transmission latency and the risk of data leakage.

[0089] For example, in the field of medical multispectral diagnostics: it is applied to scenarios such as infrared imaging analysis of human tissues and detection of body fluid (blood, urine) components. After the medical multispectral infrared device is connected to terminals such as tablets and PCs, the browser-side processes sensitive spectral data through the Wasm module. The core algorithm runs in binary form, balancing data privacy and analysis efficiency, and quickly outputs reports. For example, in the field of agricultural multispectral detection: it is suitable for early warning of crop diseases and pests, quantitative analysis of sugar and moisture content in agricultural products (fruits, grains), etc. After portable field devices collect data, the mobile terminal completes data standardization, feature matching, and result visualization through the Wasm module, supporting real-time decision-making in the field.

[0090] It should be noted that this embodiment aims to directly integrate WebAssembly with multispectral infrared analysis and processing technologies, providing a method for direct processing of multispectral infrared data based on Wasm. Leveraging Wasm's high performance, cross-platform compatibility, and sandbox security features, it addresses performance bottlenecks, difficulties in cross-platform adaptation, high security risks, and poor scenario flexibility associated with related technologies. This achieves real-time and efficient processing of multispectral infrared data, seamless cross-device adaptation, secure core technologies, and flexible adaptation to multiple scenarios. The core of this embodiment's implementation is to encapsulate the entire core logic of multispectral infrared processing into various Wasm sub-modules, realizing a direct fusion architecture between the end-user and web-based sides for multispectral data acquisition, direct Wasm module processing, and result output. The data flow architecture diagram is shown below. Figure 2 As shown in the diagram. The following explanation will follow specific steps.

[0091] In some embodiments, the raw multispectral data of the target object is acquired and then converted into binary data.

[0092] Specifically, S100: Multispectral data acquisition and preprocessing. The multispectral infrared sensor acquires multi-band raw data of the target object, including but not limited to spectral intensity values, wavelength ranges, and acquisition parameters for each band. The acquisition module converts the raw data into a binary stream (binary data) that can be directly parsed by the Wasm module to avoid data format conversion losses.

[0093] For example, such as Figure 3 As shown, S100 may include the following steps: S101 Sensor connection, the multispectral infrared sensor establishes a connection with the terminal (e.g., PC or mobile terminal) via USB / WIFI / Bluetooth interface; S102 Data acquisition, the sensor acquires multispectral data of the target based on its own physical and electrical characteristics; S103 Data preprocessing, the sensor's built-in microchip performs preprocessing on the data, such as outlier removal, timestamp acquisition, and encoding into a binary data stream.

[0094] In some embodiments, the multispectral processing function is divided into multiple multispectral processing sub-modules, and the multispectral processing sub-modules are compiled and encrypted to obtain an encrypted Wasm module, including: dividing the multispectral processing function into multiple multispectral processing sub-modules; compiling the multispectral processing sub-modules to obtain a Wasm module and a JS glue script; encrypting the Wasm module to obtain an encrypted Wasm module, and binding the encryption key to the hardware features of the terminal device; and compiling a decryption Wasm module corresponding to the encryption key.

[0095] Specifically, such as Figure 2 As shown, S200: Multispectral Wasm Module Management. Wasm module management is the core of the entire architecture and can include 12 sub-processes. (See diagram below.) Figure 2 As shown, S201, S202, and S203 belong to the pre-preparation stage; S204, S205, and S206 belong to the triggering and decision-making stage; S207, S208, and S209 belong to the loading and initialization stage; and S210, S211, and S212 belong to the runtime monitoring stage.

[0096] For example, such as Figure 2As shown, the S201 functional module is atomically decomposed. The multispectral core processing function includes three core modules: preprocessing module, feature extraction module, and spectral matching module. These three core modules can each contain independent sub-modules. For example, the preprocessing module may include a raw data verification sub-module, a multi-band noise removal sub-module, a baseline correction sub-module, a multi-band alignment sub-module, and a data standardization sub-module; the feature extraction module may include a general feature extraction sub-module, a scene-specific feature enhancement sub-module, a feature selection sub-module, and a feature fusion sub-module; and the spectral matching module may include a matching preprocessing sub-module, a standard spectral library management sub-module, a qualitative matching sub-module, and a quantitative calculation sub-module. Each sub-module unit size is ≤50KB.

[0097] In some embodiments, determining the multispectral processing submodule to be loaded corresponding to the target detection scene includes: determining the multispectral processing submodule to be loaded corresponding to the target detection scene based on a preset mapping table;

[0098] The method further includes: acquiring multispectral processing modules for different industry sub-scenarios; setting the loading priority of the multispectral processing modules for the same scenario; and constructing a preset mapping table of multispectral scenarios and modules based on the multispectral processing modules and loading priorities.

[0099] Specifically, such as Figure 2 As shown, S202 constructs a multispectral scene and module mapping table. Multispectral scene and module mapping tables (preset mapping tables) are established according to different industries and different sub-scenarios. For example, taking high-precision component detection of chemical raw materials in industrial multispectral quality inspection as an example, this scenario requires selecting multispectral processing sub-modules such as basic noise reduction, baseline correction, band alignment, industrial scene feature extraction, and PLS regression quantification. Furthermore, these modules also have different priorities in this type of scenario; for example, the basic noise reduction module has the highest priority and needs to be loaded first; band alignment is next; and industrial scene feature extraction is next. The table structure of the multispectral scene and module mapping table is shown in Table 1 below:

[0100] Table 1

[0101]

[0102] Specifically, such as Figure 2As shown, the S203 atomization function compiles and encrypts the WASM module. The code for the multispectral core submodules can be written in C / C++, for example, using the Emscripten tool (C / C++) to configure compilation parameters with SIMD instruction sets and memory optimization settings. The compilation tool compiles each multispectral processing submodule into a Wasm binary module (.wasm file), simultaneously generating a lightweight JS glue script (responsible only for Wasm module loading, instantiation, and simple interaction with the front end, excluding core algorithm logic). The Wasm binary module is then encrypted to obtain an encrypted Wasm module, for example, using the AES-256 encryption algorithm. The encryption key is bound to the terminal device's hardware characteristics to prevent unauthorized copying and use of the module. A decryption Wasm module with the same key is also compiled, which is the foundational module of this architecture. The encryption method used can be selected according to the actual situation, requiring the compilation of a corresponding decryption Wasm module; this embodiment does not impose any restrictions on this.

[0103] For example, specific algorithm functions (such as noise reduction and feature extraction) can be atomically written using C / C++. Atomization here means breaking down functions into fine, independent parts, facilitating flexible combination later. Emscripten, the compiler toolchain, is used, enabling the SIMD instruction set. SIMD (Single Instruction Multiple Data) allows the CPU to process multiple data points in parallel in a single operation. For scenarios involving a large number of numerical calculations, such as multispectral data, enabling SIMD in this embodiment can significantly improve computation speed. Memory optimization configuration parameters reduce memory usage and fragmentation, improving data read / write efficiency in memory. The Wasm binary module (.wasm) is a compiled output, small in size, fast loading, and running at near-native speed. A lightweight JS glue script (auxiliary code) is responsible for loading the Wasm module. The script does not contain the core algorithm logic; the algorithm logic is entirely encapsulated in the .wasm file, ensuring the encapsulation of core computations. The generated Wasm module is encrypted, resulting in an encrypted Wasm module. The encrypted Wasm module becomes a string of gibberish, which cannot be decrypted without the key. Since the algorithm is already in binary format, and with an additional layer of encryption, it is very difficult for attackers to decompile and recover the source code or algorithm logic.

[0104] Specifically, the encryption key is bound to the hardware characteristics of the terminal device, which typically include a unique device ID such as the CPU serial number and MAC address. If a user copies the software to another computer, the key will not match because the hardware characteristics have changed, decryption will fail, and the module will not run, thus achieving one-device-one-key software authorization protection.

[0105] For example, since the Wasm module is encrypted, the browser must decrypt it before it can run. A decryption mechanism is designed, requiring the compilation of a special Wasm module (the decryption Wasm module). Workflow: Upon system startup, the front-end reads the hardware characteristics of the current device and calls the decryption Wasm module. The decryption Wasm module uses a key matching the hardware characteristics to decrypt the encrypted core business Wasm module into executable code; the decrypted code is then loaded and executed to perform the specific infrared data processing tasks.

[0106] In this embodiment, a technical solution involving compilation optimization, encrypted encapsulation, hardware-bound authorization, and real-time decryption and execution is adopted to transform the core algorithm of multispectral infrared processing into a secure, efficient, and web-accessible module (Wasm). Encrypted compilation and hardware-bound decryption mechanisms are implemented. Wasm and SIMD optimizations address the issue of low web-end performance, while AES encryption and hardware-bound keys mitigate the risks of code theft and unauthorized copying.

[0107] In some embodiments, the encrypted Wasm module is filtered and decrypted based on scene triggering and terminal performance detection results to obtain a decrypted module, including: in response to a target detection scene, determining the multispectral processing submodule to be loaded corresponding to the target detection scene; performing performance detection on the terminal device to obtain performance detection results; filtering the multispectral processing submodule to be loaded based on the performance detection results to obtain a filtered module; and preloading and decrypting the filtered module to obtain a decrypted module.

[0108] Specifically, such as Figure 2 As shown, S204 Scene Trigger: The list of multispectral detection scenarios is made available to the user. After the user selects a multispectral detection scenario, the front-end (e.g., a browser) triggers a module loading request. S205 Terminal Performance Detection: The front-end (e.g., a browser) automatically detects the terminal's computing power and memory, queries the multispectral scene and module mapping table (preset mapping table), and outputs performance detection results, including CPU usage percentage, CPU operating frequency, DDR memory usage percentage, DRR bandwidth, and memory usage of each multispectral processing sub-module, among other data. S206 Intelligent Module Filtering: Based on the data obtained in S205 (performance detection results), the front-end (e.g., a browser) first performs basic filtering, i.e., retrieves the modules to be loaded from the multispectral data and module mapping table based on the scene identifier. Secondly, it performs performance estimation (computing power + memory) based on the performance detection results, eliminating unsuitable multispectral processing sub-modules to ensure basic functionality. Here, DDR represents the terminal device's running memory.

[0109] For example, based on the performance test results, the multispectral processing submodules to be loaded are screened to obtain the screened modules. The encrypted Wasm modules corresponding to the screened modules are then obtained, preloaded, and decrypted. Figure 2 As shown, S207 decrypts the Wasm module, and the front-end runs the corresponding decryption Wasm module to decrypt the pre-loaded encrypted Wasm module. S208 loads Wasm modules incrementally according to priority. For example, according to the "Required WASM Atomization Submodules" sequence number shown in Table 1, the earlier the sequence number, the higher the priority.

[0110] In some embodiments, the binary data is input into the decrypted module for processing to obtain the data processing result.

[0111] Specifically, such as Figure 2 As shown, the S209 module initializes, processes data, and displays the results. The required multispectral module runs within the browser kernel, eliminating the need for external data interaction and maximizing efficiency.

[0112] In some embodiments, the method further includes: real-time monitoring of the data processing results based on preset monitoring indicators during operation to obtain quality monitoring results; wherein the preset monitoring indicators include signal-to-noise ratio, baseline drift amplitude, and band synchronization deviation; real-time monitoring of the remaining DDR memory of the device during operation to obtain performance monitoring results; if the quality monitoring results meet the reloading trigger condition or a first switching request is received, then a reloading trigger decision is executed; if the performance monitoring results meet the unloading trigger condition or a second switching request is received, then an unloading trigger decision is executed.

[0113] Specifically, such as Figure 2 As shown, S210 multispectral data is monitored in real time, and the data processing results after S209 data processing are monitored in real time. 1. Monitoring indicators (preset monitoring indicators): signal-to-noise ratio (SNR), baseline drift amplitude, band synchronization deviation; 2. Threshold judgment: normal data: SNR ≥ 30dB, baseline drift amplitude ≤ 5%, band synchronization deviation ≤ 1ms; low quality data: SNR < 30dB (excessive noise) or baseline drift amplitude > 5% (instrument interference) or band synchronization deviation > 1ms; 3. Monitoring frequency: a quality assessment is triggered once every 100ms of processing 1 frame of multispectral data.

[0114] In some embodiments, if the quality monitoring result meets the reloading trigger condition or a first switching request is received, a reloading trigger decision is executed, including: triggering the reloading of the enhancement and noise reduction submodule when the signal-to-noise ratio in the quality monitoring result is less than a preset signal-to-noise ratio threshold; triggering the reloading of the high-precision baseline correction submodule when the baseline drift amplitude in the quality monitoring result is greater than a preset baseline drift threshold; triggering the reloading of the multi-band alignment submodule when the band synchronization deviation in the quality monitoring result is greater than a preset band deviation threshold; and triggering the reloading of the high-precision matching submodule and the PLS quantitative submodule when a first switching request is received; wherein, the first switching request is a switch from rapid detection to high-precision detection.

[0115] In some embodiments, if the performance monitoring result meets the unloading trigger condition or a second switching request is received, an unloading trigger decision is executed, including: when the remaining amount of device DDR in the performance monitoring result is less than a preset remaining amount threshold, triggering the unloading of the enhanced noise reduction submodule; when a second switching request is received, triggering the unloading of the high-precision matching submodule and the PLS quantitative submodule; wherein, the second switching request is a switch from high-precision detection to fast detection.

[0116] Specifically, such as Figure 2 As shown, S211 triggers loading and unloading decisions. Loading trigger conditions fall into two categories: 1. Data quality triggering. For example, if the signal-to-noise ratio (SNR) is less than a preset SNR threshold (e.g., 30dB), the "enhanced noise reduction submodule" is automatically loaded; if the baseline drift amplitude is greater than a preset baseline drift threshold (e.g., 5%), the "high-precision baseline correction submodule" is automatically loaded; if the band synchronization deviation is greater than a preset band deviation threshold (e.g., 1ms), the "multi-band alignment submodule" is automatically loaded. 2. User demand triggering. When a user switches from "fast detection" to "high-precision detection," the "high-precision matching submodule + PLS quantitative submodule" is loaded.

[0117] Specifically, the unloading trigger conditions include two categories: 1. Performance warning, for example, when the remaining amount of DDR is less than the preset remaining amount threshold, such as 10%, the "enhanced noise reduction submodule" is unloaded; 2. User demand trigger, when the user switches from "high-precision detection" to "fast detection", the "high-precision matching submodule + PLS quantitative submodule" is unloaded.

[0118] For example, high-precision detection represents a mode with high requirements for data quality and result accuracy. It can employ high-precision baseline correction submodules, high-precision matching submodules, PLS quantitative submodules, etc., and can output quantitative analysis results such as specific chemical concentration values. It has strong recognition capabilities for weak features and overlapping spectra, and a low false positive rate. High-precision detection has the largest computational load, consumes relatively more time, and has high CPU and memory resource consumption. Fast detection represents a standard mode that balances accuracy and speed. It can employ basic noise reduction submodules, baseline correction submodules, qualitative matching submodules, etc., to remove obvious noise, but does not excessively pursue smoothness of details and may not involve complex quantitative calculations. Fast detection can meet routine screening needs and provide qualitative judgments or approximate ranges of components, but may not provide extremely high-precision quantitative data.

[0119] In some embodiments, the method further includes: storing the data processing result in a non-display buffer pool; and sending the data in the non-display buffer pool to the display buffer pool in a first-in-first-out queue manner for visualization.

[0120] Specifically, such as Figure 2 As shown, S212 seamlessly connects data. This embodiment employs a two-level caching mechanism. After the multispectral raw data is processed by each multispectral processing submodule, it is not directly sent to the display buffer pool buffer1 (display buffer pool). Instead, the data is first sent to another buffer pool buffer2 (non-display buffer pool). This buffer pool buffer2 is a queue, and the queue size can be determined based on the loading and unloading time of the modules. For example, after saving 3 frames of data, the data that first enters buffer2 is sent to buffer1 for display according to the "first-in, first-out" queue method. At this time, if the data interruption time caused by the unloading or reloading of the multispectral processing submodule is less than 3 frames, buffer2 will still have data to be displayed, so that the user will not feel it on the interface, thereby enhancing the user experience.

[0121] In some embodiments, such as Figure 2 As shown, S300: Processing results are directly output and visualized.

[0122] Specifically, all Wasm modules run on a browser, requiring only one development effort for cross-platform compatibility, significantly reducing costs. Data acquired by the multispectral acquisition device can be directly transmitted to the browser in binary format via USB / Wi-Fi / Bluetooth or other transmission media. Upon receiving the binary data, the browser processes it directly through the loaded Wasm modules, eliminating the need for intermediate file storage and maximizing efficiency. The loaded Wasm modules can also visualize the processed data on demand within the browser, such as creating data reports, plotting curves, and marking defects.

[0123] It should be noted that the method in this embodiment directly encapsulates the core multispectral processing algorithm through Wasm, achieving execution efficiency close to native code and 5-10 times faster than JavaScript implementation. This meets the needs of real-time on-site analysis, overcomes performance bottlenecks, and enables real-time processing of multispectral data. The Wasm module can run uniformly in browsers, mobile WebViews, and embedded Web environments, eliminating the need to develop dedicated versions for different terminals. This reduces development and maintenance costs by more than 60%. The data format and processing logic are unified, supporting multi-device collaborative analysis and achieving seamless cross-platform adaptation, thus reducing deployment costs. The Wasm module exists in encrypted binary form, making it impossible to decompile and fundamentally protecting the core multispectral analysis algorithm. The sandbox environment isolates the core algorithm from the front-end environment, processing sensitive multispectral data in a closed environment with encrypted transmission, eliminating the risk of leakage and ensuring core technology and data security. Wasm sub-modules support dynamic loading and unloading, allowing selection of appropriate modules based on different scenarios such as high-precision analysis and rapid qualitative analysis, avoiding resource waste. Custom algorithm module compilation and integration are supported, adapting to new multispectral infrared application scenarios, achieving flexible scenario adaptation and efficient resource utilization. Multispectral data can be directly fed into the Wasm module for processing without intermediate format conversion or transfer, reducing data transmission and processing losses by 80%, ensuring the accuracy of analysis results, and making data processing direct, efficient, and less wasteful.

[0124] In this embodiment, a direct fusion architecture of Wasm and multispectral infrared processing is adopted. Multispectral data is directly input into the Wasm module for end-to-end processing without intermediate transfer. It boasts strong cross-platform capabilities, supporting diverse forms of multispectral infrared detection equipment (portable, fixed, vehicle-mounted), and corresponding terminal devices including PCs, mobile devices, and embedded devices. The processing system does not require developing dedicated versions for different terminals, such as Windows desktop versions and Android mobile versions, significantly reducing development and maintenance costs. A Wasm module management strategy is employed to centrally manage each Wasm submodule. Based on the current scenario and terminal performance, the most suitable Wasm submodule is intelligently loaded, while the quality of multispectral data is monitored in real time. By loading and unloading Wasm submodules, the system achieves sufficient performance and quality.

[0125] This embodiment provides a multispectral infrared data processing method, including: splitting the multispectral processing function into multiple multispectral processing sub-modules; compiling and encrypting the multispectral processing sub-modules to obtain an encrypted Wasm module; acquiring the collected raw multispectral data of the target object and converting the raw multispectral data into binary data; filtering and decrypting the encrypted Wasm module based on scene triggering and terminal performance detection results to obtain a decrypted module; and inputting the binary data into the decrypted module for processing to obtain the data processing result. In this embodiment, the core algorithm of the multispectral processing function is directly encapsulated in Wasm, achieving execution efficiency close to native code, enabling real-time processing of multispectral data, and meeting the needs of real-time on-site analysis. The Wasm module can run uniformly in different terminal environments without the need to develop a dedicated version, greatly reducing development and maintenance costs. Furthermore, the Wasm module exists in encrypted binary form and cannot be decompiled, fundamentally protecting the core algorithm of the multispectral processing function.

[0126] Reference Figure 4 , Figure 4 This is a structural block diagram of an embodiment of the multispectral infrared data processing system of the present invention. Figure 4 As shown, the multispectral infrared data processing system includes:

[0127] The function splitting module 10 is used to split the multispectral processing function into multiple multispectral processing sub-modules, compile and encrypt the multispectral processing sub-modules to obtain the encrypted Wasm module;

[0128] Data acquisition module 20 is used to acquire the multispectral raw data of the target object and convert the multispectral raw data into binary data;

[0129] The detection and filtering module 30 is used to filter and decrypt the encrypted Wasm module based on the scene trigger and terminal performance detection results to obtain the decrypted module;

[0130] The data processing module 40 is used to input the binary data into the decrypted module for processing to obtain the data processing result.

[0131] Specifically, this embodiment of the multispectral infrared data processing system directly integrates WebAssembly with multispectral infrared analysis and processing technology, providing a Wasm-based multispectral infrared data direct processing system. By leveraging Wasm's high performance, cross-platform compatibility, and sandbox security features, it solves problems such as performance bottlenecks, difficulties in cross-platform adaptation, high security risks, and poor scenario flexibility in related technologies, achieving real-time and efficient processing of multispectral infrared data, seamless cross-device adaptation, core technology security and confidentiality, and flexible adaptation to multiple scenarios.

[0132] The multispectral infrared data processing system provided in this embodiment directly encapsulates the core algorithms of multispectral processing functions through Wasm, achieving execution efficiency close to native code and enabling real-time processing of multispectral data to meet on-site real-time analysis needs. The Wasm module can run uniformly in different terminal environments without the need to develop a dedicated version, greatly reducing development and maintenance costs. Furthermore, the Wasm module exists in encrypted binary form, making it impossible to decompile, fundamentally protecting the core algorithms of the multispectral processing function.

[0133] It should be noted that technical details not described in detail in this embodiment of the multispectral infrared data processing system can be found in any embodiment of the present invention applied to the multispectral infrared data processing method described above, and will not be repeated here.

[0134] Based on the same inventive concept, embodiments of the present invention also provide an electronic device. Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Figure 5 As shown, an embodiment of the present invention provides an electronic device including: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, which, when executed by the one or more processors, cause the one or more processors to implement any of the multispectral infrared data processing methods described in the above embodiments; the one or more I / O interfaces 103 are connected between the processor and the memory, configured to enable information interaction between the processor and the memory.

[0135] The processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read / write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus).

[0136] In some embodiments, the processor 101, memory 102, and I / O interface 103 are interconnected via bus 104, and thus connected to other components of the computing device.

[0137] In some embodiments, the one or more processors 101 include a field-programmable gate array.

[0138] This invention also provides a computer-readable medium. The computer-readable medium stores a computer program, which, when executed by a processor, implements the steps of any of the multispectral infrared data processing methods described in the above embodiments. The computer-readable storage medium may be volatile or non-volatile.

[0139] This invention also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code is run in the processor of an electronic device, the processor in the electronic device executes the above-described multispectral infrared data processing method.

[0140] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0141] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0142] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0143] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via 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). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0144] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0145] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should 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-readable program instructions.

[0146] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0147] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0148] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0149] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of the invention as set forth in the appended claims.

Claims

1. A method for processing multispectral infrared data, characterized in that, include: The multispectral processing function is broken down into multiple multispectral processing sub-modules, and the multispectral processing sub-modules are compiled and encrypted to obtain the encrypted Wasm module. Acquire the raw multispectral data of the target object and convert the raw multispectral data into binary data; The encrypted Wasm module is filtered and decrypted based on the scene trigger and terminal performance test results to obtain the decrypted module; The binary data is input into the decrypted module for processing to obtain the data processing result.

2. The method as described in claim 1, characterized in that, The process involves breaking down the multispectral processing function into multiple multispectral processing sub-modules, compiling and encrypting these sub-modules to obtain an encrypted Wasm module, including: The multispectral processing function is broken down into multiple multispectral processing sub-modules; The multispectral processing submodule is compiled to obtain the Wasm module and the JS glue script; The Wasm module is encrypted to obtain an encrypted Wasm module, and the encryption key is bound to the hardware features of the terminal device. Compile the decryption Wasm module corresponding to the encryption key.

3. The method as described in claim 1, characterized in that, The process of filtering and decrypting the encrypted Wasm module based on scenario triggering and terminal performance detection results to obtain the decrypted module includes: In response to the target detection scenario, determine the multispectral processing submodule to be loaded corresponding to the target detection scenario; The performance of the terminal device is tested, and the performance test results are obtained. Based on the performance test results, the multispectral processing sub-modules to be loaded are screened to obtain the screened modules; The filtered modules are preloaded and decrypted to obtain the decrypted modules.

4. The method as described in claim 3, characterized in that, The step of determining the multispectral processing submodule to be loaded corresponding to the target detection scene includes: The target detection scenario is determined based on a preset mapping table to identify the corresponding multispectral processing sub-module to be loaded. The method further includes: a multispectral processing module for acquiring different industry sub-scenarios; Set the loading priority of the multispectral processing module for the same scene; A preset mapping table of multispectral scenes and modules is constructed based on the multispectral processing module and the loading priority.

5. The method as described in claim 1, characterized in that, The method further includes: During operation, the data processing results are monitored in real time based on preset monitoring indicators to obtain quality monitoring results; wherein, the preset monitoring indicators include signal-to-noise ratio, baseline drift amplitude, and band synchronization deviation; The remaining DDR memory of the device is monitored in real time during operation to obtain performance monitoring results; If the quality monitoring results meet the reloading triggering conditions or a first switching request is received, then the reloading triggering decision is executed; If the performance monitoring results meet the uninstallation triggering conditions or a second switching request is received, then the uninstallation triggering decision is executed.

6. The method as described in claim 5, characterized in that, If the quality monitoring result meets the reloading trigger condition or a first switching request is received, then the reloading trigger decision is executed, including: When the signal-to-noise ratio in the quality monitoring result is less than the preset signal-to-noise ratio threshold, the enhanced noise reduction submodule is triggered to reload. When the baseline drift amplitude in the quality monitoring results exceeds the preset baseline drift threshold, the high-precision baseline correction submodule is triggered to reload. When the band synchronization deviation in the quality monitoring results is greater than the preset band deviation threshold, the multi-band alignment submodule is triggered to reload. When the first switching request is received, the high-precision matching submodule and the PLS quantitative submodule are triggered to reload; the first switching request is to switch from fast detection to high-precision detection.

7. The method as described in claim 5, characterized in that, If the performance monitoring result meets the uninstallation trigger condition or a second switching request is received, then an uninstallation trigger decision is executed, including: When the remaining DDR amount of the device in the performance monitoring results is less than a preset remaining threshold, the enhanced noise reduction submodule is triggered to unload. When a second switching request is received, the high-precision matching submodule and the PLS quantitative submodule are unloaded; the second switching request is to switch from high-precision detection to fast detection.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: The data processing results are stored in a non-display buffer pool; The data in the non-display buffer pool is sent to the display buffer pool in a first-in-first-out (FIFO) queue manner for visualization.

9. A multispectral infrared data processing system, characterized in that, include: The function splitting module is used to split the multispectral processing function into multiple multispectral processing sub-modules, and to compile and encrypt the multispectral processing sub-modules to obtain the encrypted Wasm module. The data acquisition module is used to acquire the multispectral raw data of the target object and convert the multispectral raw data into binary data. The detection and filtering module is used to filter and decrypt the encrypted Wasm module based on the scene trigger and terminal performance detection results, so as to obtain the decrypted module; The data processing module is used to input the binary data into the decrypted module for processing to obtain the data processing result.

10. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 8.

Images