Cross-system data co-processing method and system based on image recognition and chip storage

Abstract

The invention relates to a cross-system data cooperative processing method and system based on image recognition and chip storage, and the method comprises the following steps: obtaining an electronic image of physical medium data through an image collection device or a virtual printer, and carrying out the preprocessing of the electronic image, performing data positioning and extraction on the preprocessed image by using an image recognition algorithm; writing the extracted data into a specified sector of the embedded chip, and verifying the data consistency through CRC32 verification and a read-back comparison mechanism; according to coding requirements of a target system, context-aware format adaptation is carried out on chip data through a dynamic format conversion model, and cross-system automatic data transmission is carried out by adopting an API interface and a SendKeys method; a whole-process operation log is generated, the operation log comprises a timestamp, a chip serial number, a data hash value and a block chain tamper-proof storage identifier, and anomaly backtracking and auditing are supported.

Description

Technical Field

[0001] This application relates to the field of data management and automation technologies, and more specifically, to a cross-system data collaborative processing method and system based on image recognition and chip storage. Background Art

[0002] The current cross-system data collaborative processing solutions generally have the following technical bottlenecks: First, the digitization of physical medium data (such as paper documents, barcode labels) relies on traditional image processing technologies. Existing methods (such as fixed-parameter Gaussian filtering, standard Otsu segmentation) have poor adaptability to distorted and low-contrast images, resulting in a high error rate of text localization. Second, the data storage verification mechanism is single. Most solutions only use CRC or MD5 verification, which cannot detect physical bit flip errors of storage media and lack the cross-verification logic between image features and chip data. Third, format conversion during cross-system transmission relies on manual configuration templates and is difficult to dynamically adapt to the encoding differences of heterogeneous systems. Operation logs are mostly stored in a centralized database, which has the risk of tampering. Existing blockchain solutions have a storage delay of more than 500 ms in high-concurrency scenarios due to the fixed block capacity design. These problems seriously restrict the requirements for high-precision and real-time data collaboration in fields such as healthcare and logistics.

[0003] The prior art, such as the Chinese patent application with the publication number "CN112100149A", discloses a log automation analysis system. This invention is achieved through the following technical solutions: The log preprocessing module sends the cleaned working day log file to the text analysis slicing module for semantic analysis, calculates the Simhash fingerprints of adjacent texts in the log, and performs similarity calculation and judgment to form the smallest non-repeating text blocks; the parameter name and value extraction module constructs a regular expression matching pattern according to the smallest non-repeating text blocks in the text or according to a pre-written log template, and selects the read-in log for parameter name and value extraction processing; the data IO module saves the extracted text key information, parameter names, and values to the hard disk for subsequent reading and writing; the statistical plotting and report generation module statistically analyzes the values extracted from the hard disk by category, draws visualization graphs according to the data statistical values, and generates an analysis report.

[0004] The problems of the above prior art are that this method only supports text log analysis and cannot process physical medium data such as images and chip storage; it relies on conventional storage (such as CSV / database) and lacks the ability to verify physical medium data; format conversion depends on predefined templates and cannot dynamically adapt to heterogeneous systems; log storage depends on traditional databases and has the risk of tampering. Summary of the Invention

[0005] To solve the above technical problems, the present invention proposes a cross-system data collaborative processing method and system based on image recognition and chip storage.

[0006] The technical solution of the present invention is as follows:

[0007] The present invention proposes a cross-system data collaborative processing method based on image recognition and chip storage, including the following steps:

[0008] Obtain the electronic image of the physical medium data through an image acquisition device or a virtual printer, preprocess the electronic image, and use an image recognition algorithm to perform data positioning and extraction on the preprocessed image;

[0009] Write the extracted data into the specified sector of the embedded chip, and verify the data consistency through the CRC32 checksum and read-back comparison mechanism;

[0010] According to the encoding requirements of the target system, perform context-aware format adaptation on the chip data through a dynamic format conversion model, and use the API interface and the SendKeys method to perform cross-system automated data transfer;

[0011] Generate a full-process operation log, which includes a timestamp, a chip serial number, a data hash value, and a blockchain anti-tampering storage identifier, and supports exception backtracking and auditing.

[0012] As a preferred embodiment, the preprocessing of the electronic image specifically includes noise reduction filtering, geometric correction, and adaptive threshold segmentation based on improved Otsu, where: the noise reduction filtering uses an adaptive bilateral filter, and the filter weight function is:

[0013]

[0014] The filtered pixel calculation is:

[0015]

[0016] In the formula: W(x,y,i,j) is the joint weight of the central pixel (x,y) and the neighborhood (i,j); (x,y) is the central coordinate of the pixel to be filtered; (i,j) is the coordinate of any pixel in the neighborhood; σ d is the standard deviation of the spatial domain; σ r is the standard deviation of the intensity domain; σ n is the noise variance; α is the noise sensitivity coefficient; I(i,j) is the original pixel value at the coordinate (i,j); I(x,y) is the original pixel value at the coordinate (x,y); Ω is the filtering window centered on (x,y).

[0017] As a preferred embodiment, the preprocessing of the electronic image specifically includes noise reduction filtering, geometric correction, and adaptive threshold segmentation based on improved Otsu, where: the geometric correction uses a perspective transformation matrix; specifically:

[0018]

[0019] Among them:

[0020]

[0021] In the formula: (x, y) is the original center coordinate; (x ′ , y ′ ) is the coordinate of the corresponding point of (x, y) in the transformed image; M is the sub-homogeneous transformation matrix.

[0022] As a preferred embodiment, the electronic image is preprocessed, specifically including noise reduction filtering, geometric correction, and adaptive threshold segmentation based on improved Otsu. Among them, the specific steps of the adaptive threshold segmentation based on improved Otsu are as follows:

[0023] Gradient magnitude calculation:

[0024]

[0025] Among them:

[0026]

[0027] In the formula: G(x, y) is the gradient magnitude of the pixel (x, y); I is the input grayscale image matrix; S x is the Sobel horizontal direction operator; S y is the Sobel vertical direction operator; * is the convolution operator;

[0028] Construct a weighted histogram:

[0029]

[0030] In the formula: p(t) is the grayscale weighted histogram; γ is the gradient threshold; δ() is the Dirac function; t is the candidate segmentation threshold;

[0031] Introduce the regional contrast weight and improve the between-class variance function:

[0032]

[0033] In the formula: is the improved between-class variance; ω0(t) and ω1(t) are the foreground and background pixel ratios respectively; μ1(t) and μ2(t) are the foreground and background grayscale averages respectively; μ global is the global grayscale average;

[0034] Optimal threshold calculation:

[0035]

[0036] In the formula: t* is the optimal segmentation threshold; L is the total number of gray levels.

[0037] As a preferred embodiment, the image recognition algorithm is used to perform data positioning and extraction on the preprocessed image. The image recognition algorithm includes the integrated application of Canny edge detection, morphological operations, and multi-code system decoding engines.

[0038] As a preferred embodiment, the data consistency is verified through the CRC32 checksum and read-back comparison mechanism. The data consistency verification adopts multi-modal fusion verification. The specific steps are as follows: extract the SIFT feature descriptors of the image and generate a hash value; read the chip data to generate a hash value; compare the hash value of the image feature descriptors with the hash value of the chip data. If it is greater than the pre-audit threshold, trigger manual review.

[0039] As a preferred embodiment, the blockchain anti-tampering storage satisfies:

[0040] The Merkle root hash of at least 10 operation records is included in each block;

[0041] The prev_hash field in the block header matches the SHA-256 value of the previous block;

[0042] The asymmetric encryption signature adopts the ECDSA algorithm, and the private key is shard-stored in multiple physical nodes.

[0043] On the other hand, the present invention also provides a cross-system data collaborative processing system based on image recognition and chip storage, including:

[0044] An image acquisition and data extraction module, which obtains the electronic image of the physical medium data through an image acquisition device or a virtual printer, preprocesses the electronic image, and performs data positioning and extraction on the preprocessed image by using an image recognition algorithm;

[0045] A chip interaction module, which writes the extracted data into the specified sector of the embedded chip and verifies the data consistency through the CRC32 checksum and read-back comparison mechanism;

[0046] A cross-system dynamic adaptation transmission module, which performs context-aware format adaptation on the chip data through a dynamic format conversion model according to the encoding requirements of the target system, and performs cross-system automated data transfer by using an API interface and the SendKeys method;

[0047] A log traceability module, which generates an operation log for the entire process. The operation log includes a timestamp, a chip serial number, a data hash value, and a blockchain anti-tampering storage identifier, and supports exception backtracking and auditing.

[0048] In another aspect, the present invention also provides an electronic device, on which a computer program is stored, and when the computer program is executed by a processor, it implements the cross-system data collaborative processing method based on image recognition and chip storage as described in any embodiment of the present invention.

[0049] In another aspect, the present invention also provides a computer-readable medium for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the cross-system data collaborative processing method based on image recognition and chip storage as described in any embodiment of the present invention.

[0050] The present invention has the following beneficial effects:

[0051] 1. By integrating adaptive bilateral filtering, perspective transformation correction, and improved Otsu segmentation, the image quality of distorted and noisy documents is significantly improved, and the text localization accuracy rate is increased by more than 40%;

[0052] 2. Based on the context-aware dynamic format conversion model, it supports the hybrid transmission mode of API interfaces and SendKeys simulation input, and can adapt to more than 90% of heterogeneous systems;

[0053] 3. The multi-modal verification mechanism of CRC32 verification and SIFT feature hashing comparison reduces the missed detection rate to less than 0.01%; combined with blockchain storage and private key sharding technology, anti-tampering audit tracking is realized;

[0054] 4. The operation logs integrate timestamps, chip serial numbers, and data hash values, and are bound to the blockchain through a Merkle tree, supporting second-level exception localization and improving audit efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0056] Figure 1 It is a schematic flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0058] It should be understood that the step numbers used in the text are only for convenient description and do not limit the execution order of the steps.

[0059] It should be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0060] The terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0061] The term " / and" refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0062] Embodiment 1:

[0063] To make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments of the present application and with reference to the attached Figure 1 , and the technical solutions of the present invention will be clearly and completely described.

[0064] To solve the problems of the prior art, the present invention provides a cross-system data collaborative processing method based on image recognition and chip storage, including the following steps:

[0065] Obtain an electronic image of physical medium data through an image acquisition device or a virtual printer, preprocess the electronic image, and use an image recognition algorithm to perform data positioning and extraction on the preprocessed image; the data for positioning and extraction includes text regions, one-dimensional barcodes, two-dimensional matrix codes, geometric figures, and biometric features.

[0066] The preprocessing of the electronic image specifically includes noise reduction filtering, geometric correction, and adaptive threshold segmentation based on improved Otsu,

[0067] wherein: the noise reduction filtering adopts an adaptive bilateral filter, and the filter weight function is:

[0068]

[0069] The filtered pixel is calculated as follows:

[0070]

[0071] Where: W(x,y,i,j) is the combined weight of the central pixel (x,y) and the neighborhood (i,j); (x,y) is the central coordinate of the pixel to be filtered; (i,j) is the coordinate of any pixel within the neighborhood; σ d is the standard deviation in the spatial domain (default is 1.5 for a 3×3 neighborhood); σ r is the standard deviation in the intensity domain (taking 5% of the dynamic range of the image); σ n is the noise variance; α is the noise sensitivity coefficient, with a value range of 0.2 to 0.5; I(i,j) is the original pixel value at coordinate (i,j); I(x,y) is the original pixel value at coordinate (x,y); Ω is the filtering window centered at (x,y).

[0072] Among them: Geometric correction uses a perspective transformation matrix; specifically:

[0073]

[0074] Among them:

[0075]

[0076] Where: (x,y) is the original central coordinate; (x ′ ,y ′ ) is the corresponding point coordinate of (x,y) in the transformed image; M is the sub - homogeneous transformation matrix.

[0077] Among them: Based on the improved Otsu's adaptive threshold segmentation, the specific steps are as follows:

[0078] Gradient magnitude calculation:

[0079]

[0080] Among them:

[0081]

[0082] Where: G(x,y) is the gradient magnitude of the pixel (x,y); I is the input grayscale image matrix; S x is the Sobel horizontal direction operator; S y is the Sobel vertical direction operator; * is the convolution operator;

[0083] Construct a weighted histogram:

[0084]

[0085] where: p(t) is the grayscale weighted histogram; γ is the gradient threshold, taking the 75th percentile of the gradient distribution; δ() is the Dirac function, used to count the grayscale frequency; t is the candidate segmentation threshold;

[0086] Introduce the regional contrast weight to improve the between-class variance function:

[0087]

[0088] where: is the improved between-class variance; ω0(t) and ω1(t) are the foreground and background pixel ratios respectively; μ1(t) and μ2(t) are the foreground and background grayscale averages respectively; μ global is the global grayscale average;

[0089] Optimal threshold calculation:

[0090]

[0091] where: t * is the optimal segmentation threshold; L is the total number of gray levels.

[0092] The above-mentioned uses an image recognition algorithm to perform data positioning and extraction on the preprocessed image. The image recognition algorithm includes the fusion application of Canny edge detection, morphological operations, and multi-code system decoding engines.

[0093] Write the extracted data into the specified sector of the embedded chip, and verify the data consistency through the CRC32 checksum and read-back comparison mechanism;

[0094] The above-mentioned verifies the data consistency through the CRC32 checksum and read-back comparison mechanism. The data consistency verification adopts multi-modal fusion verification. The specific steps are: extract the SIFT feature descriptor of the image and generate a hash value; read the chip data to generate a hash value; compare the hash value of the image feature descriptor with the hash value of the chip data. If it is greater than the pre-audit threshold, in this embodiment, the threshold is set to 5, and manual review is triggered.

[0095] According to the encoding requirements of the target system, perform context-aware format adaptation on the chip data through a dynamic format conversion model, and use API interfaces (such as SwitchToThisWindow) and the SendKeys method for cross-system automated data transfer;

[0096] Generate a full-process operation log. The operation log includes a timestamp, chip serial number, data hash value, and blockchain anti-tampering storage identifier, supporting exception backtracking and auditing.

[0097] The above-mentioned blockchain anti-tampering storage satisfies:

[0098] Each block contains the Merkle root hash of at least 10 operation records;

[0099] The prev_hash field in the block header matches the SHA-256 value of the previous block;

[0100] The asymmetric encryption signature uses the ECDSA algorithm, and the private key is shard-stored on multiple physical nodes.

[0101] Example Two:

[0102] The image acquisition and data extraction module obtains the electronic image of the physical medium data through an image acquisition device or a virtual printer, preprocesses the electronic image, and uses an image recognition algorithm to perform data positioning and extraction on the preprocessed image;

[0103] The chip interaction module writes the extracted data into the specified sector of the embedded chip, and verifies the data consistency through the CRC32 checksum and read-back comparison mechanism;

[0104] The cross-system dynamic adaptation and transmission module performs context-aware format adaptation on the chip data through a dynamic format conversion model according to the encoding requirements of the target system, and performs cross-system automated data transfer using the API interface and the SendKeys method;

[0105] The log traceability module generates an operation log for the entire process. The operation log includes a timestamp, a chip serial number, a data hash value, and a blockchain anti-tampering storage identifier, and supports exception backtracking and auditing.

[0106] Example Three:

[0107] This example provides an electronic device with a computer program stored thereon. When the computer program is executed by a processor, it implements the cross-system data collaborative processing method based on image recognition and chip storage as described in any embodiment of the present invention.

[0108] Example Four:

[0109] This example provides a computer-readable medium for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the cross-system data collaborative processing method based on image recognition and chip storage as described in any embodiment of the present invention.

[0110] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent the situations of A existing alone, A and B existing simultaneously, and B existing alone. Where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0111] Those of ordinary skill in the art can realize that the various units and algorithm steps described in the embodiments disclosed herein can be implemented by a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0112] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0113] In several embodiments provided by the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (hereinafter referred to as ROM), random access memories (hereinafter referred to as RAM), magnetic disks, or optical discs that can store program codes.

[0114] The above are only the embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A cross-system data collaborative processing method based on image recognition and chip storage, characterized in that: The following steps are involved: The electronic image of the physical medium data is obtained through an image acquisition device or a virtual printer, and the electronic image is preprocessed, and the data of the preprocessed image is located and extracted using an image recognition algorithm; Write the extracted data to the specified sector of the embedded chip and verify the data consistency through CRC32 check and readback comparison mechanism; According to the encoding requirements of the target system, the chip data is adapted to the format of the context-awareness through the dynamic format conversion model, and the API interface and SendKeys method are used to automatically transfer data across systems; Generates a full-process operation log, which includes timestamp, chip serial number, data hash value and blockchain tamper-proof storage identifier, and supports exception backtracking and auditing.

2. The cross-system data collaborative processing method based on image recognition and chip storage according to claim 1 is characterized in that: The electronic image is preprocessed, specifically including noise reduction filtering, geometric correction and adaptive threshold segmentation based on improved Otsu, wherein: the noise reduction filtering adopts an adaptive bilateral filter, and the filter weight function is: The pixel after filtering is calculated as: Where: W(x,y,i,j) is the joint weight of the central pixel (x,y) and the neighborhood (i,j); (x,y) is the center coordinate of the pixel to be filtered; (i,j) is the coordinate of any pixel in the neighborhood; σ d is the standard deviation in the spatial domain; σ r is the intensity domain standard deviation; σ n is the noise variance; α is the noise sensitivity coefficient; I(i,j) is the original pixel value at the coordinate (i,j); I(x,y) is the original pixel value at the coordinate (x,y); Ω is the filter window centered at (x,y).

3. The cross-system data collaborative processing method based on image recognition and chip storage according to claim 1 is characterized in that: The electronic image is preprocessed, specifically including noise reduction filtering, geometric correction and adaptive threshold segmentation based on improved Otsu, wherein: the geometric correction uses a perspective transformation matrix; specifically: in: Where: (x, y) is the original center coordinate; (x ′ ,y ′ ) is the coordinate of the corresponding point (x, y) in the transformed image; M is the subhomogeneous transformation matrix.

4. The cross-system data collaborative processing method based on image recognition and chip storage according to claim 1 is characterized in that: The electronic image is preprocessed, specifically including noise reduction filtering, geometric correction and adaptive threshold segmentation based on improved Otsu, wherein: the adaptive threshold segmentation based on improved Otsu, the specific steps are: Gradient amplitude calculation: in: Where: G(x,y) is the gradient amplitude of pixel (x,y); I is the input grayscale image matrix; S x is the Sobel horizontal operator; S y is the Sobel vertical operator; * is the convolution operator; Construct a weighted histogram: Where: p(t) is the grayscale weighted histogram; γ is the gradient threshold; δ() is the Dirac function; t is the candidate segmentation threshold; Introduce regional contrast weights to improve the inter-class variance function: Where: is the improved inter-class variance; ω0(t) and ω1(t) are the ratios of foreground and background pixels, respectively; μ1(t) and μ2(t) are the average grayscale values ​​of foreground and background, respectively; μ global is the global grayscale average; Optimal threshold calculation: Where: t * is the optimal segmentation threshold; L is the total number of gray levels.

5. The cross-system data collaborative processing system based on image recognition and chip storage according to claim 1, characterized in that: The image recognition algorithm is used to locate and extract data from the preprocessed image. The image recognition algorithm includes the fusion application of Canny edge detection, morphological operation and multi-code decoding engine.

6. The cross-system data collaborative processing method based on image recognition and chip storage according to claim 1 is characterized in that: The data consistency is verified through CRC32 verification and readback comparison mechanism. The data consistency verification adopts multimodal fusion verification. The specific steps are: extracting the image SIFT feature descriptor and generating a hash value; reading the chip data to generate a hash value; comparing the image feature descriptor hash value with the chip data hash value. If it is greater than the pre-examination threshold, manual review is triggered.

7. The cross-system data collaborative processing method based on image recognition and chip storage according to claim 1 is characterized in that: The blockchain tamper-proof storage satisfies: Each block contains the Merkle tree root hash of at least 10 operation records; The prev_hash field in the block header matches the SHA-256 value of the previous block; Asymmetric encryption signature uses the ECDSA algorithm, and the private key is stored in multiple physical nodes.

8. A cross-system data collaborative processing system based on image recognition and chip storage, characterized in that: include: The image acquisition and data extraction module obtains the electronic image of the physical medium data through the image acquisition device or the virtual printer, pre-processes the electronic image, and uses the image recognition algorithm to locate and extract data from the pre-processed image; The chip interaction module writes the extracted data into the specified sector of the embedded chip and verifies the data consistency through CRC32 checksum and readback comparison mechanism; The cross-system dynamic adaptation transmission module performs context-aware format adaptation of chip data through a dynamic format conversion model according to the encoding requirements of the target system, and uses the API interface and SendKeys method to perform automated data transmission across systems; The log tracing module generates a full-process operation log, which contains timestamp, chip serial number, data hash value and blockchain tamper-proof storage identifier, and supports exception backtracking and auditing.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the cross-system data collaborative processing method based on image recognition and chip storage is implemented as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the cross-system data collaborative processing method based on image recognition and chip storage as described in any one of claims 1 to 7 is implemented.

Images