A lens parameter verification method and system, a computer device and a storage medium

Abstract

This invention discloses a lens parameter verification method, system, computer device, and storage medium. The method includes: acquiring a focimeter measurement image; wherein the focimeter measurement image contains measurement data related to spectacle lenses; extracting the focimeter measurement data from the focimeter measurement image using image recognition technology; validating the focimeter measurement data and filtering and outputting structured parameters based on the validity verification result; performing rule verification on the structured parameters using a rule engine to obtain the rule verification result; and displaying and storing the rule verification result. This invention, through automated image acquisition, data extraction, verification filtering, rule verification, and display and storage processes, can achieve intelligent and efficient lens parameter verification, thereby improving the verification efficiency and accuracy of lens parameters.

Description

Technical Field

[0001] This invention relates to the field of computer software technology, and in particular to a method, system, computer device, and storage medium for verifying lens parameters. Background Technology

[0002] With the continuous improvement of health awareness, the field of eye health management is undergoing a crucial paradigm shift from "correction-centered" to "health-centered." As the primary entry point for eye health services, optometry centers have expanded their functions far beyond the traditional single scope of optometry and glasses fitting, and are upgrading into comprehensive eye health management centers integrating basic eye disease screening, visual function assessment, myopia prevention and control, and chronic disease management. In this transformation process, fundus examination, with its unique advantage of directly reflecting the health status of core eye structures such as the retina and optic nerve, has become a core value-added service and risk management link for optometry centers. It is also a key means of assessing eye health and screening for eye complications of systemic diseases such as hypertension and diabetes.

[0003] However, the large-scale and standardized promotion of fundus examination services faces a core bottleneck: professional fundus image interpretation heavily relies on experienced ophthalmologists or optometrists, and such professional human resources are scarce and have a long training cycle, directly leading to low service efficiency, inconsistent quality, and insufficient accessibility, severely hindering the transformation of optometry centers towards high-value-added services. Existing related technical solutions have multiple shortcomings: traditional manual report interpretation is time-consuming and affected by physician experience and work status, making it difficult to standardize interpretation standards. In scenarios such as physical examinations and screenings, and high outpatient volume, it can easily lead to excessive burden on physicians and report delays; massive amounts of fundus image data are only used for single diagnoses, lacking systematic intelligent analysis, and cannot effectively identify long-term health trends, conduct population epidemiological analysis, or support scientific research; traditional reports are full of professional jargon, which is difficult for ordinary patients to understand, hindering doctor-patient communication and patient self-health management. Looking further, the existing technologies have significant limitations: basic computer-aided detection systems can only achieve simple marking of single lesions, lacking comprehensive assessment of the overall fundus condition and multi-lesion correlation analysis, and cannot generate structured text conclusions and recommendations; independent AI image analysis software is mostly an isolated application, disconnected from the business processes of the optometry management system and electronic health records, cumbersome to operate and requiring physicians to manually import and export data, making it difficult to achieve a one-click closed loop of "examination-analysis-report-archiving"; the general report templates of existing optometry management systems still require physicians to fill them out completely manually, and cannot automatically extract key information from images and complete the filling.

[0004] Meanwhile, in the core process of optometry and eyeglass fitting, the focimeter, as a key metrological instrument for measuring critical parameters such as vertex power, prism power, optical center, and axis of spectacle lenses (including contact lenses), directly affects the quality of the fitted eyeglasses and the wearer's visual health. Currently, the traceability of focimeter values ​​is mainly completed through periodic manual verification, carried out according to metrological verification procedures. However, there are many prominent pain points in practical applications: manual verification relies on the operation and visual interpretation of professional technicians, which is time-consuming, labor-intensive, and costly; indication errors or drifts caused by environmental changes, equipment aging, and misoperation during daily use are difficult to detect in a timely manner, usually only becoming apparent during the next periodic verification, resulting in a significant quality risk period; for the conformity assessment of critical values ​​or complex lenses, inconsistencies may arise due to differences in the experience of staff; traditional paper records or scattered electronic records make it difficult to effectively track and deeply analyze long-term performance changes of the instrument. In the existing technology, relevant research mainly focuses on the error sources of the focimeter itself, software and hardware calibration methods, and hardware optimization to improve measurement speed and accuracy, but has not solved the problem of continuous and intelligent data quality monitoring and verification during use.

[0005] In summary, both the large-scale promotion of fundus examination services and the precise management of focimeter measurement data face numerous constraints from existing technologies and service models. There is an urgent need for technical solutions that can be seamlessly integrated into vision management systems, achieve high-precision intelligent analysis, and automatically generate structured results in order to improve diagnostic and verification efficiency, ensure service quality, unlock data value, and optimize user experience. Summary of the Invention

[0006] This invention provides a lens parameter verification method, system, computer equipment, and storage medium, aiming to improve the verification efficiency and accuracy of lens parameters.

[0007] In a first aspect, embodiments of the present invention provide a lens parameter verification method, including: Acquire a focimeter measurement image; wherein the focimeter measurement image contains measurement data about the spectacle lens; Sofometer measurement data is extracted from the sofometer measurement images using image recognition technology; The validity of the focimeter measurement data is verified, and structured parameters are filtered and output based on the results of the validity verification. The structured parameters are validated using a rule engine to obtain the validation results. The results of the rule verification are displayed and stored.

[0008] Secondly, embodiments of the present invention provide a lens parameter verification system, comprising: An image acquisition unit is used to acquire a focimeter measurement image; wherein the focimeter measurement image contains measurement data about the spectacle lens; The data extraction unit is used to extract focimeter measurement data from the focimeter measurement image using image recognition technology; The verification and filtering unit is used to verify the validity of the focimeter measurement data and filter out structured parameters based on the results of the validity verification. The rule verification unit is used to perform rule verification on the structured parameters through the rule engine to obtain the rule verification result; The display storage unit is used to display and store the results of the rule verification.

[0009] Thirdly, embodiments of the present invention provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the lens parameter verification method as described in the first aspect.

[0010] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the lens parameter verification method as described in the first aspect.

[0011] This invention provides a lens parameter verification method, system, computer device, and storage medium. The method includes: acquiring a focimeter measurement image; wherein the focimeter measurement image contains measurement data related to spectacle lenses; extracting the focimeter measurement data from the focimeter measurement image using image recognition technology; validating the focimeter measurement data and filtering and outputting structured parameters based on the validity verification result; performing rule verification on the structured parameters using a rule engine to obtain the rule verification result; and displaying and storing the rule verification result. This invention, through automated image acquisition, data extraction, verification filtering, rule verification, and display and storage processes, can achieve intelligent and efficient lens parameter verification, thereby improving the verification efficiency and accuracy of lens parameters. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart illustrating a lens parameter verification method provided in an embodiment of the present invention. Figure 2 This is an overall architecture diagram of a lens parameter verification method provided in an embodiment of the present invention; Figure 3 This is a schematic block diagram of a lens parameter verification system provided in an embodiment of the present invention. Detailed Implementation

[0014] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0015] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0016] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0017] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0018] Please see below. Figure 1 This invention provides a lens parameter verification method, specifically including steps S101 to S105.

[0019] Step S101: Acquire a focimeter measurement image; wherein the focimeter measurement image contains measurement data about the spectacle lens; Step S102: Extract focimeter measurement data from the focimeter measurement image using image recognition technology; Step S103: Verify the validity of the focimeter measurement data, and filter and output structured parameters based on the results of the validity verification; Step S104: Perform rule validation on the structured parameters using the rule engine to obtain the rule validation result; Step S105: Display and store the results of the rule verification.

[0020] In this embodiment, firstly, a focimeter measurement image containing spectacle lens measurement data is acquired; then, image recognition technology is used to extract the focimeter measurement data (such as spherical, cylindrical, and axis parameters) from it; next, the extracted measurement data is validated for validity, and structured parameters are filtered and output based on the validation results; then, a rule engine is used to perform rule validation on the structured parameters to obtain the validation results; finally, the rule validation results are displayed and stored. This embodiment, through an automated process of image acquisition, data extraction, validation filtering, rule validation, and display and storage, can achieve intelligent and efficient lens parameter validation, thereby improving the validation efficiency and accuracy of lens parameters.

[0021] To address the shortcomings of existing technologies, this embodiment provides an artificial intelligence-based lens parameter verification method. Its core objective focuses on optimizing the lens parameter verification process and management efficiency from multiple dimensions: Firstly, it automatically acquires focimeter display data using image recognition technology to replace manual readings, and combines preset rules and algorithm models to achieve automated, real-time, and instantaneous data verification. Secondly, it utilizes historical data and a knowledge base to intelligently judge the rationality and trend anomalies of measurement data, establishing an intelligent anomaly detection and early warning mechanism. Simultaneously, it establishes a digital archive for each focimeter, including verification history, error curves, and maintenance records, significantly improving the standardization and traceability of metrological management and helping to advance metrological management towards a more refined level. Furthermore, it provides data-driven decision support for metrological verification personnel, effectively simplifying the verification process and further improving the objectivity and consistency of verification results.

[0022] In practical applications, a corresponding integrated intelligent verification platform system encompassing "acquisition-analysis-decision-traceability" can be built based on the lens parameter verification method provided in this embodiment. This system intelligently acquires lens measurement data, utilizes intelligent algorithms for multi-dimensional analysis and verification, achieves automated early warning, and stores the entire process data in a structured manner, forming a closed-loop metrological quality management system. Specifically, the system can include a hierarchical structure such as a sensing layer, a transmission layer, a platform vehicle, and an application layer. For example, the sensing layer can be used for automatic data acquisition: the system automatically acquires accurate measurement data in real time by parsing the native communication protocol of the focimeter data interface. The transmission layer can be used for reliable data transmission: using wired or wireless communication technology, the data acquired by the sensing layer is securely and stably transmitted to the platform layer. The platform layer can be used for in-depth data processing: cleaning, storing, analyzing, and mining the transmitted data, combining rule engines and algorithm models to achieve real-time data verification and anomaly detection, while simultaneously establishing a digital archive of the focimeter to record historical verification data and performance changes. The application layer can be used to provide diverse services: providing metrology and calibration personnel with an intuitive operating interface and decision support to facilitate calibration management and result viewing; providing optometry center managers with statistical reports and data analysis to assist in business decision-making and quality control; and providing ordinary users with concise and easy-to-understand calibration reports to improve user experience and satisfaction.

[0023] Through this hierarchical structure, the intelligent calibration platform system can automate and intelligently complete the entire process of lens parameter calibration, effectively solving many pain points of manual calibration in existing technologies, improving calibration efficiency and accuracy, and providing strong support for the metrological management and business development of optometry centers. In actual deployment, the system configuration and functions can be flexibly adjusted according to the scale and business needs of the optometry center, ensuring the system's adaptability and scalability. For example, for large optometry centers, server configuration and storage capacity can be increased to handle large amounts of measurement data and user requests; for small optometry centers, a lightweight deployment approach can be adopted to reduce system costs and maintenance difficulty. Furthermore, the system can be deeply integrated with the optometry management system to achieve data sharing and business process collaboration, further improving the overall operational efficiency and service quality of the optometry center.

[0024] In one embodiment, acquiring the focimeter measurement image includes: Establish a communication connection with the focimeter and send the pre-assembled instruction frame to the focimeter in the form of a binary data stream; Monitor the response data of the focimeter and determine whether the response data is received within a preset time. If it is determined that the response data is not received within the preset time, then an exception is handled according to the preset exception policy. If the response data is received within a preset time, the response data is set as the focimeter measurement image.

[0025] In this embodiment, when acquiring images measured by a focimeter, a communication connection (such as a specified COM serial port or TCP / IP connection) is first established and a command frame is sent to ensure effective data interaction with the focimeter. By sending the pre-assembled command frame in the form of a binary data stream, the system's measurement requirements can be accurately conveyed. When monitoring the focimeter's response data, the system strictly determines whether a response is received within a preset time. If a response is not received within the specified time, an exception is handled according to a preset exception strategy (such as recording an error log, triggering a retransmission mechanism, etc.). This ensures the stability and reliability of the system in the face of emergencies and avoids the inability to perform verification work normally due to missing or abnormal responses. When it is determined that response data has been received within the preset time, it is set as the focimeter measurement image, laying the foundation for subsequent image recognition and data extraction. This rigorous process design makes the entire data acquisition process more scientific and standardized, reduces interference from human factors, and further improves the accuracy and reliability of the data.

[0026] In one embodiment, extracting focimeter measurement data from the focimeter measurement image using image recognition technology includes: The focimeter measurement image is preprocessed; Based on the preprocessed focimeter measurement image, key lens parameter information is determined, and focimeter measurement data is set according to the key lens parameter information; wherein, the key lens parameter information includes the position, byte order, data format, and unit conversion relationship of the key lens parameter in the focimeter data segment.

[0027] In this embodiment, various image processing techniques, such as grayscale conversion, noise reduction filtering, and edge detection, can be employed during image preprocessing to improve image quality and clarity, preparing for the subsequent accurate extraction of key lens parameter information. Grayscale conversion converts a color image into a grayscale image, reducing data volume while highlighting image features; noise reduction filtering removes noise interference from the image, making it smoother; and edge detection helps determine the boundaries of key elements in the image, providing a basis for subsequent parameter localization.

[0028] After image preprocessing, key lens parameters are determined from the focimeter measurement images. This can be achieved by combining image recognition algorithms and deep learning models. These algorithms and models can be pre-trained with a large amount of sample data to accurately identify the location, byte order, data format, and unit conversion relationships of various key lens parameters in the focimeter images. For example, by analyzing the characteristics of numbers and symbols in the image, the specific values ​​of parameters such as spherical power, cylindrical power, and axis can be determined, and then converted into standard measurement units according to pre-defined unit conversion relationships.

[0029] In one embodiment, the step of validating the focimeter measurement data and filtering the output structured parameters based on the validity verification result includes: The validity of the focimeter measurement data is verified using a preset validity verification strategy to obtain validity verification results; wherein, the validity verification strategy includes combining parameter logic rationality verification; When the validity verification result of the focimeter measurement data is that the verification fails, the corresponding focimeter measurement data is deleted; When the validity verification result of the focimeter measurement data is passed, the corresponding focimeter measurement data is used as the structured parameter and output.

[0030] In this embodiment, when acquiring structured parameters, the measurement data is first validated using a preset valid verification strategy to determine the rationality of the parameter logic. For example, the cylindrical power (C value) is usually not negative; the sign combination of spherical power and cylindrical power should conform to optical principles. This verification method can not only identify errors in the data itself but also discover unreasonable logical relationships between data. For example, in optical parameters, there are certain logical relationships between spherical power and cylindrical power. This comprehensive verification can promptly capture data that does not conform to physical laws or industry standards. When the measurement data fails verification, the relevant data can be directly deleted, thus preventing erroneous data from entering subsequent analysis and processing stages and reducing verification errors and decision-making mistakes caused by erroneous data. For data that passes verification, it can be output as structured parameters, including spherical power (S), cylindrical power (C), axis (A), down-light (ADD), pupillary distance (PD), etc., along with a precise timestamp and device ID. The extracted parameters are converted into standardized data objects that are unified within the system in real time, so as to provide an accurate and reliable data foundation for subsequent data processing and business system calls, and to provide an accurate and reliable data foundation for subsequent verification and analysis.

[0031] This method of validating and filtering measurement data to output structured parameters further enhances the accuracy and reliability of the entire lens parameter calibration system, ensuring that the final calibration results accurately reflect the actual parameters of the lens. Simultaneously, it helps improve the system's automation level, reduces human intervention and errors, and makes the calibration process more efficient and intelligent.

[0032] For example, regarding the relationship between spherical and cylindrical power, the absolute value of the spherical power should be greater than the absolute value of the cylindrical power (|S| > |C|). If, during verification, the absolute value of the spherical power is found not to be greater than the absolute value of the cylindrical power, it indicates a problem with the logical validity of the parameter. Similarly, regarding the optical center and pupillary distance, the optical center distance calculated from the coordinates of the optical centers of the left and right lenses should be consistent with the pupillary distance (PD) value provided by the optometry provider within a reasonable range (e.g., a difference ≤ 2mm). If, during verification, the optical center distance is found not to be consistent with the pupillary distance (PD) value provided by the optometry provider within a reasonable range, it indicates a problem with the logical validity of the parameter. Furthermore, regarding the astigmatism axis and power, when the absolute value of the cylindrical power C is extremely low (e.g., <0.12D), a warning is triggered regarding the reliability of the axis A (but it is not forced to zero, see previous analysis), prompting a review.

[0033] In one embodiment, the step of performing rule validation on the structured parameters using a rule engine to obtain the rule validation result includes: The structured parameters are validated using a pre-defined rule base to obtain the validation results; wherein the rule base includes lens parameter quality control standards.

[0034] This embodiment uses rule-based validation of structured parameters, such as lens parameter quality control standards set in the rule base, to ensure that all lens parameters meet quality requirements, such as "cylindrical axis deviation must not exceed ±X°" and "spherical power repeatability measurement error must not exceed ±Y". The rules in the rule base are detailed and explicit, and the rule base stores all validation thresholds, logical rules, and associated model parameters related to the device, which can be synchronously updated from the cloud to the edge terminal. For example, regarding spherical power, its error range in different scenarios is precisely specified to ensure the lens's focusing function is accurate; for cylindrical power, the rules strictly limit the reasonable relationship between its absolute value and spherical power, as well as the standard for its positive and negative signs, to ensure that the lens can effectively correct astigmatism.

[0035] During rule validation, each parameter can be meticulously examined. If a parameter is found to be inconsistent with the standard in the rule base, it can be immediately flagged. For example, if the spherical power exceeds the error range, it will be quickly listed as abnormal data; if the sign of the cylindrical power does not conform to the rules, it will also be identified promptly. For flagged abnormal parameters, appropriate measures can be taken, such as generating an anomaly report. The report indicates the name of the abnormal parameter, its actual value, and the standard value in the rule base, and can also provide a possible cause analysis. In this way, users can clearly understand the problem and quickly take targeted solutions, whether adjusting the lens or re-measuring, providing a clear direction.

[0036] Furthermore, rule verification can be dynamically adjusted. For example, the rule base can be updated in a timely manner based on changes in lens parameter quality control standards, ensuring that rule verification always accurately reflects the latest quality requirements. This dynamic adjustment allows for adaptation to the parameter verification needs of different types of lenses at different times, providing a lasting guarantee for the stable improvement of lens quality.

[0037] In specific embodiments, verification rules and verification scenarios corresponding to different parameter categories are provided. Specifically, this includes: When the parameter category is spherical power (S), the verification rule names include repeatability error verification and spherical-cylindrical logic verification. The repeatability error verification rule logic and threshold can be: the range (maximum value - minimum value) of the spherical power in three consecutive automatic measurements of the same lens must not exceed ±0.06D; the spherical-cylindrical logic verification rule logic and threshold can be: when the cylindrical power C≠0, the absolute value of the spherical power S must be greater than the absolute value of the cylindrical power C. The purpose and scenario of repeatability error verification is to ensure the stability and consistency of measurements from a single device and to identify equipment fluctuations; the purpose and scenario of spherical-cylindrical logic verification is to prevent data contradictions based on optical principles (the absolute value of S should be greater than C).

[0038] When the parameter category is cylinder power (C), the verification rule names include cylinder axis correlation verification and cylinder symbol verification. The rule logic and threshold for cylinder axis correlation verification can be: when the absolute value of cylinder power C is ≤0.25D, its corresponding axis A should be automatically set to 0°; the rule logic and threshold for cylinder symbol verification can be: cylinder power C must be negative (negative cylinder form). If it is not negative, a warning or automatic conversion will be triggered. The purpose and scenario of cylinder axis correlation verification is to conform to the optical practice of axis insensitivity in low astigmatism and avoid meaningless data; the purpose and scenario of cylinder symbol verification is to standardize the internal prescription format and ensure data consistency.

[0039] When the parameter category is axis position (A), the verification rule names include axis position range verification and axis position deviation tolerance verification. The rule logic and threshold for axis position range verification can be: the value of axis position A must be within a closed interval of 1° to 180°; 0° is generally considered invalid. The rule logic and threshold for axis position deviation tolerance verification can be: compare the current measured axis position with the standard value or the previous measured value; the absolute value of the deviation must not exceed ±2°. The purpose and scenario of axis position range verification is to ensure that the data conforms to the basic validity defined by optics. The purpose and scenario of axis position deviation tolerance verification is to strictly control the processing accuracy in the astigmatic direction, which is the core of quality control.

[0040] When the parameter category is interpupillary distance (PD), the verification rule names include physiological range verification and binocular symmetry verification. The rule logic and threshold for physiological range verification can be: the monocular interpupillary distance should be between 23mm and 40mm; the total interpupillary distance should be between 50mm and 80mm. The rule logic and threshold for binocular symmetry verification can be: the difference between the left and right monocular interpupillary distances should not exceed 3mm under normal circumstances. If it exceeds this, a review is prompted. The purpose and scenario of physiological range verification is to filter out obviously impossible measurement errors or image recognition errors; the purpose and scenario of binocular symmetry verification is to identify possible measurement errors or special facial asymmetries.

[0041] When the parameter category is optical center, the verification rule names include optical center-pupillary distance correlation verification and vertical difference verification. The rule logic and threshold for optical center-pupillary distance correlation verification are as follows: the "optical center distance" calculated from the horizontal distance between the optical centers of the left and right eyes should differ from the measured "total pupillary distance" within ±2mm. The rule logic and threshold for vertical difference verification are as follows: the vertical height difference between the optical centers of the left and right eyes should generally not exceed ±1mm. The purpose and scenario of optical center-pupillary distance correlation verification is to ensure that the optical center positioning matches the patient's actual pupillary distance, which is crucial for accurate fitting. The purpose and scenario of vertical difference verification is to ensure that the line of sight passes through the lenses at the same horizontal height when both eyes are viewing objects, preventing eye strain caused by prismatic effects.

[0042] In one embodiment, displaying and storing the result of the rule validation includes: When the result of the rule verification is that all verification items pass, the result of the rule verification is displayed using the first display identifier; When the result of the rule verification is that at least one verification item fails, the result of the rule verification is displayed using a second display identifier, and the failed verification items are marked; wherein, the first display identifier is different from the second display identifier.

[0043] In this embodiment, different display indicators are used to distinguish the results of rule verification, allowing users to quickly and intuitively understand the verification status. When the first display indicator (e.g., green) is used, it indicates that the structured parameters of the lens fully comply with the quality control standards in the rule base, the lens quality is reliable, and it can proceed to the next stage or be used directly. When the second display indicator (e.g., red) is used, it means that at least one verification item has failed. In this case, it is particularly important to mark the failed verification item. The marked content can include detailed information such as the name of the abnormal parameter, the comparison between the measured value and the standard value, etc., to facilitate further analysis and problem handling by the user.

[0044] In another embodiment, displaying and storing the result of the rule verification further includes: The focimeter measurement images, focimeter measurement data, and rule verification results are summarized, and then encrypted before being uploaded to a preset storage. A digital archive is created for each focimeter, and the digital archive is updated and maintained by combining the focimeter measurement images, focimeter measurement data, and the results of rule verification.

[0045] In this embodiment, during storage operations, the focimeter measurement images, measurement data, and rule verification results are first aggregated and then encrypted to ensure data security and privacy. The encrypted data is then uploaded to a pre-configured storage device for centralized management and storage. This device can be a local server or cloud storage, allowing users to choose based on their needs and circumstances. Local server storage offers higher data security and controllability, making it suitable for enterprises with high data security requirements; while cloud storage provides flexibility and scalability, allowing for adjustments to storage capacity as needed based on business development.

[0046] Furthermore, this embodiment establishes a digital file for each focimeter and updates and maintains it in conjunction with relevant data, which helps users to comprehensively manage and monitor the equipment. Specifically, the digital file records detailed information about the focimeter, including basic equipment information (such as equipment model, serial number, user department, etc.), measurement data, and calibration results. By analyzing this data, users can promptly understand the equipment's operating status and performance, predict potential equipment failures, and perform maintenance and upkeep in advance, thereby reducing equipment repair costs and downtime. Simultaneously, the digital file also provides strong support for production management. Users can optimize and adjust the production process based on the focimeter's measurement data and calibration results, improving production efficiency and product quality. For example, if frequent anomalies are found in the measurement data of a particular focimeter, users can inspect and repair the equipment or adjust the production process to ensure that the produced lenses meet quality requirements. In addition, the digital file can provide a basis for product quality traceability. When product quality problems occur, users can quickly locate the root cause of the problem by querying the digital file, identify potentially problematic production processes and equipment, and take corresponding measures for improvement and correction, thereby improving product quality management and customer satisfaction.

[0047] Combination Figure 2 In practical applications, when a user needs to measure lenses, the data is first automatically collected at the perception layer, and then the focimeter analyzes the corresponding image or data stream. Next, the data is transmitted to the platform layer via wired or wireless network for core intelligent processing. This includes extracting structured parameters such as spherical power (S), cylindrical power (C), axis (A), pupillary distance (PD), and additional power (ADD) through an automatic recognition engine, and performing rule verification through intelligent verification and a rule engine. After rule verification, two results are generated: one is a pass (passing the verification results in a qualified result), and the other is an error (failing the verification results in an error and triggers an alert). The data then enters the application layer to generate an automated verification panel, and the relevant data is synchronously stored in the cloud or locally, with data traceability as the final endpoint. The entire process achieves intelligent closed-loop management of lens parameters from collection, processing, verification to storage.

[0048] In summary, this embodiment boasts multiple key innovations and significant advantages. Firstly, it automates the entire process from triggering measurement, acquiring data, parsing parameters, to performing verification, eliminating the need for manual reading, input, or judgment, thus significantly improving verification efficiency. Secondly, the system constructs a fully automated error-proofing mechanism across the entire data chain, from generation to acquisition and verification. When inconsistencies arise in data acquired through different methods, an automatic warning is triggered, fundamentally eliminating transmission errors, parsing errors, or human misinterpretation that may occur with a single data source, ensuring the highest level of data reliability. Simultaneously, the targeted design of the protocol parsing adapter and instruction set library ensures compatibility with focimeters of different brands, models, and interfaces, effectively protecting existing equipment investments. Finally, the decoupled architecture provides flexible deployment capabilities, allowing the system to be deployed on local servers or in the cloud according to enterprise needs, adapting to the IT environments of enterprises of different sizes.

[0049] Figure 3 This is a schematic block diagram of a lens parameter verification system 300 provided in an embodiment of the present invention. The lens parameter verification system 300 includes: Image acquisition unit 301 is used to acquire focimeter measurement images; wherein, the focimeter measurement images contain measurement data about the spectacle lenses; Data extraction unit 302 is used to extract focimeter measurement data from the focimeter measurement image using image recognition technology; The verification filtering unit 303 is used to verify the validity of the focimeter measurement data and filter out structured parameters based on the results of the validity verification. The rule verification unit 304 is used to perform rule verification on the structured parameters through the rule engine to obtain the rule verification result. The display storage unit 305 is used to display and store the results of the rule verification.

[0050] In one embodiment, the image acquisition unit 301 includes: The instruction sending unit is used to establish a communication connection with the focimeter and send the pre-assembled instruction frame to the focimeter in the form of a binary data stream; The response judgment unit is used to monitor the response data of the focimeter and determine whether the response data is received within a preset time. An exception handling unit is used to perform exception handling according to a preset exception strategy if it is determined that the response data has not been received within a preset time. The data setting unit is used to set the response data as the focimeter measurement image if it is determined that the response data is received within a preset time.

[0051] In one embodiment, the data extraction unit 302 includes: An image preprocessing unit is used to preprocess the focimeter measurement image; The information determination unit is used to determine key lens parameter information based on the preprocessed focimeter measurement image, and to set focimeter measurement data according to the key lens parameter information; wherein, the key lens parameter information includes the position, byte order, data format, and unit conversion relationship of the key lens parameters in the focimeter data segment.

[0052] In one embodiment, the verification filtering unit 303 includes: An effective verification unit is used to verify the validity of the focimeter measurement data using a preset effective verification strategy to obtain a validity verification result; wherein, the effective verification strategy includes combining parameter logic rationality verification; The data deletion unit is used to delete the corresponding focimeter measurement data when the validity verification result of the focimeter measurement data is that the verification fails. The data output unit is used to output the corresponding focimeter measurement data as the structured parameter when the validity verification result of the focimeter measurement data is passed.

[0053] In one embodiment, the rule verification unit 304 includes: A quality verification unit is used to perform rule verification on the structured parameters using a preset rule base to obtain the result of the rule verification; wherein, the rule base includes lens parameter quality control standards.

[0054] In one embodiment, the display storage unit 305 includes: The first display unit is used to display the result of the rule verification using a first display identifier when the result of the rule verification is that all verification items pass. The second display unit is used to display the result of the rule verification using a second display identifier and to mark the failed verification items when the result of the rule verification is that at least one verification item fails; wherein the first display identifier is different from the second display identifier.

[0055] In one embodiment, the display storage unit 305 further includes: The data upload unit is used to summarize the focimeter measurement images, focimeter measurement data and rule verification results, and upload the focimeter measurement images, focimeter measurement data and rule verification results to the preset storage after encryption. The update and maintenance unit is used to establish a digital file for each focimeter and update and maintain the digital file by combining the focimeter measurement images, focimeter measurement data and rule verification results.

[0056] Since the embodiments of the system part correspond to the embodiments of the method part, please refer to the description of the embodiments of the method part for the embodiments of the system part, and they will not be repeated here.

[0057] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed, can perform the steps provided in the above embodiments. The storage medium may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0058] This invention also provides a computer device, which may include a memory and a processor. The memory stores a computer program, and when the processor calls the computer program in the memory, it can implement the steps provided in the above embodiments. Of course, the computer device may also include various network interfaces, power supplies, and other components.

[0059] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0060] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for verifying lens parameters, characterized in that, include: Acquire a focimeter measurement image; wherein the focimeter measurement image contains measurement data about the spectacle lens; Sofometer measurement data is extracted from the sofometer measurement images using image recognition technology; The validity of the focimeter measurement data is verified, and structured parameters are filtered and output based on the results of the validity verification. The structured parameters are validated using a rule engine to obtain the validation results. The results of the rule verification are displayed and stored.

2. The lens parameter verification method according to claim 1, characterized in that, The acquisition of the focimeter measurement image includes: Establish a communication connection with the focimeter and send the pre-assembled instruction frame to the focimeter in the form of a binary data stream; Monitor the response data of the focimeter and determine whether the response data is received within a preset time. If it is determined that the response data is not received within the preset time, then an exception is handled according to the preset exception policy. If the response data is received within a preset time, the response data is set as the focimeter measurement image.

3. The lens parameter verification method according to claim 1, characterized in that, The step of extracting focimeter measurement data from the focimeter measurement image using image recognition technology includes: The focimeter measurement image is preprocessed; Based on the preprocessed focimeter measurement image, key lens parameter information is determined, and focimeter measurement data is set according to the key lens parameter information; wherein, the key lens parameter information includes the position, byte order, data format, and unit conversion relationship of the key lens parameter in the focimeter data segment.

4. The lens parameter verification method according to claim 1, characterized in that, The process of validating the focimeter measurement data and filtering the output structured parameters based on the validity verification results includes: The validity of the focimeter measurement data is verified using a preset validity verification strategy to obtain validity verification results; wherein, the validity verification strategy includes combining parameter logic rationality verification; When the validity verification result of the focimeter measurement data is that the verification fails, the corresponding focimeter measurement data is deleted; When the validity verification result of the focimeter measurement data is passed, the corresponding focimeter measurement data is used as the structured parameter and output.

5. The lens parameter verification method according to claim 1, characterized in that, The step of performing rule validation on the structured parameters through a rule engine to obtain the rule validation result includes: The structured parameters are validated using a pre-defined rule base to obtain the validation results; wherein the rule base includes lens parameter quality control standards.

6. The lens parameter verification method according to claim 1, characterized in that, The process of displaying and storing the results of the rule validation includes: When the result of the rule verification is that all verification items pass, the result of the rule verification is displayed using the first display identifier; When the result of the rule verification is that at least one verification item fails, the result of the rule verification is displayed using a second display identifier, and the failed verification items are marked; wherein, the first display identifier is different from the second display identifier.

7. The lens parameter verification method according to claim 1, characterized in that, The process of displaying and storing the results of the rule validation also includes: The focimeter measurement images, focimeter measurement data, and rule verification results are summarized, and then encrypted before being uploaded to a preset storage. A digital archive is created for each focimeter, and the digital archive is updated and maintained by combining the focimeter measurement images, focimeter measurement data, and the results of rule verification.

8. A lens parameter verification system, characterized in that, include: An image acquisition unit is used to acquire a focimeter measurement image; wherein the focimeter measurement image contains measurement data about the spectacle lens; The data extraction unit is used to extract focimeter measurement data from the focimeter measurement image using image recognition technology; The verification and filtering unit is used to verify the validity of the focimeter measurement data and filter out structured parameters based on the results of the validity verification. The rule verification unit is used to perform rule verification on the structured parameters through the rule engine to obtain the rule verification result; The display storage unit is used to display and store the results of the rule verification.

9. A computer device, characterized in that, The device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the lens parameter verification method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the lens parameter verification method as described in any one of claims 1 to 7.

Images