Dual verification method, system, and media based on type recognition and result calibration

Abstract

The application provides a double verification method, system and medium based on type identification and result calibration, first, the first optical curve of the test paper is acquired, the curve is matched with the preset standard curve to determine the first identification type; then, the multi-dimensional feature threshold is dynamically loaded, and the multi-dimensional feature information is parsed from the optical curve based on the feature extraction rule; secondly, the chain threshold judgment process is executed, whether the reaction area change rate is higher than the starting threshold is verified first, whether the fluctuation amplitude is lower than the stable threshold is confirmed, and whether the peak-to-peak value is within the type threshold range is determined, and the second identification type is generated if all the above are passed; finally, the test paper type is confirmed by comparing the consistency of the first and second identification types, and the final result is output if consistent, and the abnormal processing is triggered if inconsistent. The double guarantee mechanism of optical feature matching and parameterized threshold verification is used to improve the accuracy and reliability of the test paper type interpretation.

Description

Technical Field

[0001] This invention relates to the field of medical test strip identification and verification, and more specifically, to a dual verification method, system, and medium based on type identification and result calibration. Background Technology

[0002] In the field of medical testing equipment technology, especially in automated test strip interpretation systems based on optical principles, achieving accurate identification of test strip types and reliable calibration of test results has always been a significant technical challenge. First, traditional devices mostly rely on users manually selecting the test strip type. This human intervention mode is highly susceptible to operational errors leading to incorrect type selection, thus causing systemic deviations in the entire testing process. Second, traditional systems mostly employ fixed optical interpretation thresholds and uniform signal processing algorithms, which cannot adapt to the inherent differences in reaction kinetics and optical response characteristics of different types of test strips (such as HCG and LH), resulting in limited interpretation accuracy. Third, existing technologies lack effective multi-verification mechanisms; interpretation results obtained through a single identification path are unreliable, especially with a significantly increased false positive rate when signal quality is poor or environmental interference exists. Finally, traditional systems do not comprehensively monitor the test strip reaction process, often neglecting precise judgment of the reaction initiation timing and signal stability, and lacking intelligent handling capabilities for abnormal situations, thus affecting the accuracy and consistency of the final results.

[0003] Therefore, there is an urgent need for a dual verification technology based on type recognition and result calibration to improve the accuracy of test strip type identification. Summary of the Invention

[0004] In view of the above problems, the purpose of this invention is to provide a dual verification method, system, and medium based on type recognition and result calibration. By establishing a dual recognition path of optical curve matching and feature parameter verification, it achieves cross-verification of test strip types and automatic interception of anomalies, fundamentally improving the robustness of the recognition system. First, by establishing a type-adaptive dynamic parameter loading mechanism, the optimal threshold configuration for different test strip characteristics is achieved, enhancing adaptability and interpretation accuracy. At the same time, by comprehensively extracting multi-dimensional features in the time and frequency domains, a comprehensive analysis of the optical features of the test strip is achieved, providing a rich data foundation for accurate interpretation. Second, by introducing a preprocessing process for optical curves and a confidence threshold mechanism, the quality of raw data is optimized and low-quality data is intelligently filtered, improving the accuracy of type matching. Then, by implementing continuous monitoring of reaction initiation and multi-cycle verification of signal stability, refined control of the test strip reaction process is achieved, ensuring the scientific nature of data collection timing. Finally, by constructing a type consistency comparison and hierarchical anomaly handling process, early diagnosis and intelligent recovery of system faults are achieved, effectively ensuring the continuity and reliability of the detection process.

[0005] The first aspect of this invention provides a dual verification method based on type recognition and result calibration, the method comprising:

[0006] Based on the preset optical acquisition mode, the first optical curve of the test strip is obtained;

[0007] The first optical curve is matched with a preset standard curve, and the first recognition type is obtained based on the similarity.

[0008] Based on the first identification type, dynamically load multi-dimensional feature thresholds, including at least the initiation threshold, the stability threshold, and the type threshold range;

[0009] Based on the preset feature extraction rules, multidimensional feature information is obtained according to the first optical curve, including at least the reaction zone change rate, fluctuation amplitude, and reaction zone peak-to-peak value.

[0010] Determine whether the rate of change in the reaction zone is higher than the start-up threshold;

[0011] If so, determine whether the fluctuation amplitude is lower than the stability threshold;

[0012] If so, determine whether the peak value of the reaction zone is within the range of the type threshold.

[0013] If so, then the second identification type is obtained;

[0014] Determine whether the first identification type and the second identification type are the same;

[0015] If so, then the test strip type is obtained;

[0016] If not, an exception command will be output.

[0017] In this scheme, the step of matching the first optical curve with a preset standard curve and obtaining the first recognition type based on similarity specifically includes:

[0018] The first optical curve of the test strip reaction area is obtained based on the reflected light data collected by the optical sensor.

[0019] The first optical curve is preprocessed, including baseline calibration and noise filtering;

[0020] The similarity of the preprocessed first optical curve with the preset HCG standard curve and LH standard curve is calculated respectively.

[0021] Based on the similarity calculation results, the test strip type corresponding to the standard curve with the highest similarity is selected as the first identification type;

[0022] When the highest similarity is lower than the preset confidence threshold, an abnormal signal for type identification is output.

[0023] This solution includes start signal detection and optical stabilization verification, specifically:

[0024] Based on the first optical curve, the signal change rate of adjacent sampling points is calculated to obtain the change rate of the reaction zone;

[0025] The rate of change in the reaction zone is compared with the start-up threshold of dynamic loading to obtain the number of sampling periods in which the rate of change in the reaction zone is continuously higher than the start-up threshold.

[0026] If the number of sampling periods exceeds the preset number of periods threshold, the reaction is determined to have started normally;

[0027] After the reaction is initiated, the signal fluctuation amplitude within a preset time window is calculated based on the first optical curve;

[0028] When the fluctuation amplitude is below the stability threshold for two consecutive sampling periods, the signal is considered to have reached a stable state.

[0029] In this scheme, the step of dynamically loading multi-dimensional feature thresholds according to the first recognition type specifically includes:

[0030] Based on the first identification type, access the non-volatile memory that stores different types of test strip parameter sets;

[0031] If the first identification type is HCG, then the first parameter group is loaded, and the first parameter group includes at least the initiation threshold, stability threshold and type threshold range applicable to the reaction kinetics characteristics of HCG test strip;

[0032] If the first identification type is LH, then the second parameter set is loaded. The second parameter set includes at least the initiation threshold, stability threshold and type threshold range applicable to the reaction kinetics of LH test strips.

[0033] The loaded parameter set is set as the effective threshold of the current reading cycle, forming a multi-dimensional feature threshold set.

[0034] In this scheme, the step of obtaining multi-dimensional feature information based on the preset feature extraction rules and the first optical curve specifically includes:

[0035] Temporal features, including the rate of change and fluctuation amplitude of the signal in the reaction region, are extracted from the first optical curve.

[0036] Frequency domain features, including main frequency components and spectral energy distribution, are extracted from the first optical curve.

[0037] Calculate the characteristic parameters of the optical signal in the reaction zone, including peak position, valley position, and peak-to-peak value;

[0038] The extracted multidimensional feature information is classified and stored.

[0039] This solution includes type validation and exception handling, and also includes:

[0040] Perform a consistency comparison between the first identification type and the second identification type;

[0041] When both match, confirm the final test strip type and output the calibrated test results;

[0042] When the two are inconsistent, the exception handling process is initiated, including re-collecting optical data and prompting the user to confirm the test strip type;

[0043] If multiple consecutive verifications are inconsistent, a self-test procedure will be executed and a device maintenance prompt message will be output.

[0044] A second aspect of the present invention provides a dual verification system based on type recognition and result calibration, comprising a dual verification method program based on type recognition and result calibration, wherein the dual verification method program based on type recognition and result calibration, when executed by the processor, implements the following steps:

[0045] Based on the preset optical acquisition mode, the first optical curve of the test strip is obtained;

[0046] The first optical curve is matched with a preset standard curve, and the first recognition type is obtained based on the similarity.

[0047] Based on the first identification type, dynamically load multi-dimensional feature thresholds, including at least the initiation threshold, the stability threshold, and the type threshold range;

[0048] Based on the preset feature extraction rules, multidimensional feature information is obtained according to the first optical curve, including at least the reaction zone change rate, fluctuation amplitude, and reaction zone peak-to-peak value.

[0049] Determine whether the rate of change in the reaction zone is higher than the start-up threshold;

[0050] If so, determine whether the fluctuation amplitude is lower than the stability threshold;

[0051] If so, determine whether the peak value of the reaction zone is within the range of the type threshold.

[0052] If so, then the second identification type is obtained;

[0053] Determine whether the first identification type and the second identification type are the same;

[0054] If so, then the test strip type is obtained;

[0055] If not, an exception command will be output.

[0056] In this scheme, the step of matching the first optical curve with a preset standard curve and obtaining the first recognition type based on similarity specifically includes:

[0057] The first optical curve of the test strip reaction area is obtained based on the reflected light data collected by the optical sensor.

[0058] The first optical curve is preprocessed, including baseline calibration and noise filtering;

[0059] The similarity of the preprocessed first optical curve with the preset HCG standard curve and LH standard curve is calculated respectively.

[0060] Based on the similarity calculation results, the test strip type corresponding to the standard curve with the highest similarity is selected as the first identification type;

[0061] When the highest similarity is lower than the preset confidence threshold, an abnormal signal for type identification is output.

[0062] This solution includes start signal detection and optical stabilization verification, specifically:

[0063] Based on the first optical curve, the signal change rate of adjacent sampling points is calculated to obtain the change rate of the reaction zone;

[0064] The rate of change in the reaction zone is compared with the start-up threshold of dynamic loading to obtain the number of sampling periods in which the rate of change in the reaction zone is continuously higher than the start-up threshold.

[0065] If the number of sampling periods exceeds the preset number of periods threshold, the reaction is determined to have started normally;

[0066] After the reaction is initiated, the signal fluctuation amplitude within a preset time window is calculated based on the first optical curve;

[0067] When the fluctuation amplitude is below the stability threshold for two consecutive sampling periods, the signal is considered to have reached a stable state.

[0068] A third aspect of the present invention provides a computer-readable storage medium comprising a dual verification method program based on type recognition and result calibration, wherein when the dual verification method program based on type recognition and result calibration is executed by a processor, it implements the steps of the dual verification method based on type recognition and result calibration as described in any of the preceding claims.

[0069] This invention provides a dual verification method, system, and medium based on type recognition and result calibration. First, the first optical curve of the test strip is acquired, and this curve is matched with a preset standard curve to determine the first identification type. Then, multi-dimensional feature thresholds are dynamically loaded, and multi-dimensional feature information is parsed from the optical curve based on feature extraction rules. Next, a series of threshold judgment processes are executed: first, it is verified whether the rate of change in the reaction zone is higher than the activation threshold; then, it is confirmed whether the fluctuation amplitude is lower than the stability threshold; finally, it is determined whether the peak-to-peak value is within the type threshold range. If all pass, a second identification type is generated. Finally, the test strip type is confirmed by comparing the consistency between the first and second identification types. If they match, the final result is output; if they do not match, an anomaly handling is triggered. This invention improves the accuracy and reliability of test strip type interpretation through a dual guarantee mechanism of optical feature matching and parameterized threshold verification. Attached Figure Description

[0070] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope.

[0071] Figure 1 A flowchart of a dual verification method based on type recognition and result calibration according to the present invention is shown;

[0072] Figure 2 A flowchart illustrating an optical curve matching method provided by an embodiment of the present invention is shown;

[0073] Figure 3 This diagram illustrates a flowchart of a start signal detection and optical stabilization verification method provided by an embodiment of the present invention.

[0074] Figure 4 A block diagram of a dual verification system based on type recognition and result calibration according to the present invention is shown. Detailed Implementation

[0075] 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 embodiments of the present invention, and not all embodiments. 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.

[0076] Unless otherwise defined, all terms (including technical and scientific terms) used in embodiments of this invention shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in a common dictionary shall be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and not as being interpreted in an idealized or highly formalized sense, unless expressly defined in this embodiment of the invention.

[0077] The terms "first," "second," and similar words used in the embodiments of this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "an," "a," or "the" do not indicate a quantity limitation, but rather indicate the presence of at least one. Similarly, terms such as "including" or "comprising" mean that the element or object preceding the word encompasses the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The steps preceding or following the steps in the method of the embodiments of this invention are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0078] In addition, the functional modules in the various embodiments of the present invention can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0079] Figure 1 A flowchart of a dual verification method based on type recognition and result calibration according to the present invention is shown.

[0080] like Figure 1 As shown, the first aspect of this invention discloses a dual verification method based on type recognition and result calibration, the method comprising:

[0081] S102, based on the preset optical acquisition mode, obtain the first optical curve of the test strip;

[0082] S104, Match the first optical curve with the preset standard curve, and obtain the first recognition type based on the similarity;

[0083] S106, based on the first identification type, dynamically load multi-dimensional feature thresholds, including at least a start threshold, a stability threshold, and a type threshold range;

[0084] S108, based on the preset feature extraction rules, obtains multi-dimensional feature information according to the first optical curve, including at least the reaction zone change rate, fluctuation amplitude, and reaction zone peak-to-peak value.

[0085] S110, determine whether the rate of change of the reaction zone is higher than the start-up threshold;

[0086] S112, if so, determine whether the fluctuation amplitude is lower than the stability threshold;

[0087] S114, if so, determine whether the peak value of the reaction zone is within the range of the type threshold;

[0088] S116, if so, then the second identification type is obtained;

[0089] S118, determine whether the first identification type and the second identification type are the same;

[0090] S120, if yes, then the test strip type is obtained;

[0091] S122, if not, output an exception instruction.

[0092] It should be noted that the first identification type is a preliminary type identification result based on the optical curve of the test strip; the second identification type is a preliminary type interpretation result based on the optical features of the test strip. In this embodiment, firstly, the first optical curve of the test strip is acquired through a preset optical acquisition mode; wherein, the first optical curve contains optical feature information of the test strip reaction area. Next, the obtained first optical curve is compared with a pre-stored standard curve for similarity matching calculation, and the first identification type is determined based on the matching result. Subsequently, according to the determined first identification type, the corresponding multi-dimensional feature threshold parameter group is dynamically loaded; wherein, the parameter group includes at least a start-up threshold for determining the start of the reaction, a stability threshold for determining signal stability, and a type threshold range for type verification. After obtaining these basic parameters, multi-dimensional feature information is extracted from the first optical curve based on preset feature extraction rules; wherein, at least, key feature parameters such as the reaction area change rate, fluctuation amplitude, and reaction area peak-to-peak value are extracted. Then, a chain judgment process is executed: first, it is determined whether the reaction area change rate is higher than the start-up threshold; if so, it is further determined whether the fluctuation amplitude is lower than the stability threshold; if so, it is further determined whether the reaction area peak-to-peak value is within the type threshold range; if so, the second identification type is obtained. Finally, the consistency between the first and second identification types is verified; if they are the same, the final test strip type is confirmed; if they are different, an error command is output. This embodiment effectively improves the accuracy and reliability of test strip type identification through a dual mechanism of optical curve matching and feature parameter verification.

[0093] Figure 2A flowchart of an optical curve matching method provided by an embodiment of the present invention is shown.

[0094] According to embodiments of the present invention, such as Figure 2 As shown, the step of matching the first optical curve with a preset standard curve and obtaining the first recognition type based on similarity specifically includes:

[0095] S202, based on the reflected light data collected by the optical sensor, the first optical curve of the test strip reaction area is obtained;

[0096] S204, preprocess the first optical curve, including baseline calibration and noise filtering;

[0097] S206, calculate the similarity between the preprocessed first optical curve and the preset HCG standard curve and LH standard curve respectively;

[0098] S208. Based on the similarity calculation results, the test strip type corresponding to the standard curve with the highest similarity is selected as the first identification type.

[0099] S210, when the highest similarity is lower than the preset confidence threshold, output a type identification abnormality signal.

[0100] It should be noted that in this embodiment, firstly, a first optical curve of the test strip reaction area is constructed based on the reflected light data collected by the optical sensor. To improve data quality, the original optical curve is preprocessed; this includes baseline calibration to eliminate background interference and noise filtering to improve the signal-to-noise ratio. The preprocessed optical curve is then compared with preset HCG and LH standard curves for similarity calculation. A specific similarity algorithm is used to evaluate the matching degree of curve morphology and feature points. Based on the similarity calculation results, the test strip type corresponding to the standard curve with the highest similarity is selected as the first identification type. To ensure the reliability of the identification results, a confidence threshold mechanism is also set. When the highest similarity is lower than the preset confidence threshold, an abnormal type identification signal is output to avoid misidentification caused by low-quality matching. This embodiment provides an accurate and reliable preliminary identification foundation for subsequent verification processes through multi-level curve processing and rigorous similarity evaluation.

[0101] Figure 3 A flowchart of a start signal detection and optical stability verification method provided by an embodiment of the present invention is shown.

[0102] According to embodiments of the present invention, such as Figure 3 As shown, this includes start signal detection and optical stabilization verification, specifically:

[0103] S302, calculate the signal change rate of adjacent sampling points based on the first optical curve to obtain the change rate of the reaction zone;

[0104] S304, compare the rate of change of the reaction zone with the start-up threshold of dynamic loading to obtain the number of sampling periods in which the rate of change of the reaction zone is continuously higher than the start-up threshold;

[0105] S306, if the number of sampling cycles exceeds the preset number of cycles threshold, the reaction is determined to have started normally;

[0106] S308, after the reaction is started, calculate the signal fluctuation amplitude within a preset time window based on the first optical curve;

[0107] S310: When the fluctuation amplitude is lower than the stability threshold for two consecutive sampling periods, the signal is determined to have reached a stable state.

[0108] It should be noted that in this embodiment, the reaction zone change rate parameter is obtained by calculating the signal change rate of adjacent sampling points based on the obtained first optical curve. The calculated reaction zone change rate is continuously compared with the dynamically loaded start-up threshold, and the number of sampling periods in which the reaction zone change rate is continuously higher than the start-up threshold is counted. Only when the number of sampling periods exceeds a preset number of periods threshold is the reaction considered to have started normally. This embodiment effectively avoids false triggering caused by instantaneous interference through a continuous monitoring mechanism. After confirming the start of the reaction, the optical stabilization monitoring stage is entered, and the signal fluctuation amplitude within a preset time window is calculated based on the first optical curve. By continuously monitoring the comparison results of the fluctuation amplitude and the stabilization threshold, the signal is considered to have reached a stable state when the fluctuation amplitude is lower than the stabilization threshold for two consecutive sampling periods. This embodiment ensures that subsequent analysis is only performed under the condition that the reaction has started normally and the signal is stable through a dual verification mechanism, significantly improving the accuracy of the detection results.

[0109] According to an embodiment of the present invention, the step of dynamically loading multi-dimensional feature thresholds based on a first identification type specifically includes:

[0110] Based on the first identification type, access the non-volatile memory that stores different types of test strip parameter sets;

[0111] If the first identification type is HCG, then the first parameter group is loaded, and the first parameter group includes at least the initiation threshold, stability threshold and type threshold range applicable to the reaction kinetics characteristics of HCG test strip;

[0112] If the first identification type is LH, then the second parameter set is loaded. The second parameter set includes at least the initiation threshold, stability threshold and type threshold range applicable to the reaction kinetics of LH test strips.

[0113] The loaded parameter set is set as the effective threshold of the current reading cycle, forming a multi-dimensional feature threshold set.

[0114] It should be noted that, in this embodiment, based on the determined first identification type, a database of different types of test strip parameters stored in non-volatile memory is accessed. When the first identification type is HCG, a first parameter set optimized specifically for the reaction kinetics of HCG test strips is loaded; wherein, the first parameter set includes at least the activation threshold, stability threshold, and type threshold range applicable to HCG test strips. When the first identification type is LH, a second parameter set optimized specifically for the reaction kinetics of LH test strips is loaded; the second parameter set includes at least the activation threshold, stability threshold, and type threshold range applicable to LH test strips. After loading, the selected parameter set is set as the effective threshold for the current interpretation cycle, forming a complete set of multi-dimensional feature thresholds. This embodiment, through a type-adaptive parameter configuration mechanism, enables the system to adopt the most optimized interpretation criteria for the characteristics of different test strips, improving the accuracy and adaptability of detection.

[0115] According to an embodiment of the present invention, the step of obtaining multi-dimensional feature information based on a preset feature extraction rule and a first optical curve specifically includes:

[0116] Temporal features, including the rate of change and fluctuation amplitude of the signal in the reaction region, are extracted from the first optical curve.

[0117] Frequency domain features, including main frequency components and spectral energy distribution, are extracted from the first optical curve.

[0118] Calculate the characteristic parameters of the optical signal in the reaction zone, including peak position, valley position, and peak-to-peak value;

[0119] The extracted multidimensional feature information is classified and stored.

[0120] It should be noted that in this embodiment, time-domain features are extracted from the first optical curve, including calculating the signal change rate in the reaction zone by calculating the slope of the signal change, and obtaining key parameters such as the fluctuation amplitude by analyzing the signal fluctuation. Simultaneously, frequency-domain features are also extracted from the first optical curve, including the analysis of the main frequency components and the spectral energy distribution characteristics obtained after frequency domain transformation of the optical signal. Furthermore, multiple characteristic parameters of the optical signal in the reaction zone are calculated, including identifying the peak and valley positions by recognizing the extreme points of the curve, and obtaining the peak-to-peak value by calculating the difference between the peak and valley values. After all feature extraction is completed, the extracted multi-dimensional feature information is classified and stored according to feature categories to establish a structured feature dataset. This embodiment, through comprehensive multi-dimensional feature analysis in both the time and frequency domains, can fully capture the optical feature changes of the test strip reaction, providing rich and accurate feature data support for subsequent type verification and result interpretation, thereby improving the ability to analyze complex optical signals and the completeness of feature recognition.

[0121] According to embodiments of the present invention, the method includes type validation and exception handling, and further includes:

[0122] Perform a consistency comparison between the first identification type and the second identification type;

[0123] When both match, confirm the final test strip type and output the calibrated test results;

[0124] When the two are inconsistent, the exception handling process is initiated, including re-collecting optical data and prompting the user to confirm the test strip type;

[0125] If multiple consecutive verifications are inconsistent, a self-test procedure will be executed and a device maintenance prompt message will be output.

[0126] It should be noted that in this embodiment, a detailed consistency comparison is first performed between the first identification type obtained based on optical curve matching and the second identification type obtained based on feature parameter analysis. A specific comparison algorithm is used to evaluate the correlation between the two identification results. When the two identification types are completely consistent, the final test strip type is confirmed and a calibrated test result is output to ensure the reliability of the result. When the identification types are inconsistent, an anomaly handling process is immediately initiated, including re-acquiring optical data to obtain a more accurate signal, and simultaneously prompting the user to confirm the test strip type through the user interface to avoid identification deviations caused by operational errors. In the special case of multiple consecutive inconsistent verifications, a thorough self-test procedure is executed, comprehensively testing the optical sensor, signal processing module, etc., and outputting detailed equipment maintenance prompts. This embodiment, by establishing a multi-layered verification and anomaly handling mechanism, ensures stability and reliability in complex usage environments and reduces the risk of misjudgment.

[0127] It is worth mentioning that it also includes:

[0128] Acquire ambient light intensity information and establish a model relating ambient light intensity to baseline noise of optical sensors;

[0129] Based on the ambient light intensity information, the baseline compensation value is obtained;

[0130] The baseline compensation value is applied to the preprocessing of the first optical curve to perform signal denoising and baseline calibration algorithms.

[0131] Outputs a standardized optical curve after ambient light compensation.

[0132] It should be noted that in this embodiment, the ambient light intensity information of the current environment is acquired in real time through an ambient light sensor, and a correspondence model between ambient light intensity and the baseline noise of the optical sensor is established to quantify the interference degree of ambient light on the detection system. Based on the established ambient light interference model, a precise baseline compensation value is calculated, which can effectively offset the basic signal deviation caused by ambient light. In the optical curve processing stage, the calculated baseline compensation value is applied to the preprocessing of the first optical curve, and signal denoising and baseline calibration algorithms are executed to eliminate the system errors introduced by ambient light. After complete compensation processing, a standardized optical curve after ambient light compensation is output; the compensated curve has a higher signal-to-noise ratio and a more accurate baseline level. This embodiment improves the adaptability and detection consistency under different lighting conditions through advanced ambient light compensation technology, ensuring stable and reliable detection results in various operating environments.

[0133] It's worth mentioning that after obtaining the test strip type, the following information is also included:

[0134] Obtain the production batch number information and parse it to obtain the production date and shelf life parameters;

[0135] Calculate the number of valid days based on the current system date information;

[0136] Determine whether the number of valid days is lower than the preset time limit;

[0137] If so, then generate a time-limited warning flag;

[0138] The time-limit warning flag is associated with the final test strip type result in the output.

[0139] It should be noted that in this embodiment, after determining the test strip type, the production batch number information of the test strip is automatically obtained. The precise production date and shelf-life parameters are obtained by parsing the batch number coding rules. Combined with the current system date information obtained from the system clock, the remaining valid days of the test strip are calculated to accurately assess its effective usage period. Then, the calculated remaining valid days are compared with a preset expiration threshold; when the expiration date is below the threshold, an expiration warning is automatically generated, indicating the potential risk of test strip failure. Finally, the expiration warning is correlated with the final test strip type result, ensuring that the user can simultaneously obtain test strip type information and expiration status. This embodiment, through an automated expiration monitoring mechanism, prevents detection errors caused by expired test strips, improving the reliability of test results and the safety of user use.

[0140] It's worth noting that before outputting the final test strip type result, the following is also included:

[0141] The optical sensor is controlled to simultaneously acquire optical signals from multiple detection channels within the reaction zone of the test strip, resulting in multiple corresponding optical curves;

[0142] For each detection channel, a feature extraction and threshold judgment process is performed separately to obtain preliminary judgment results for multiple channels;

[0143] Compare the consistency of the interpretation results of each channel, and when the number of consistent channels reaches the preset confidence level, the interpretation result is adopted;

[0144] If there are discrepancies in the results of each channel, a weighted voting algorithm is executed, assigning different weights to each channel based on its signal quality, and calculating the weighted interpretation result.

[0145] It should be noted that in this embodiment, the optical sensor simultaneously acquires optical signals from multiple detection channels within the test strip reaction area, obtaining independent optical curves corresponding to multiple detection areas and establishing a multi-dimensional signal acquisition system. A complete feature extraction and threshold judgment process is performed on the optical curve acquired by each detection channel, resulting in multiple preliminary interpretations based on data from different channels, ensuring that each channel can independently complete the analysis process. Then, the consistency level of the interpretations from each channel is compared. When a preset number of consistent channels is reached, the interpretation result is adopted as the final conclusion. In special cases where there are discrepancies in the results from different channels, an intelligent weighted voting algorithm is executed, assigning different weight coefficients based on the signal quality indicators of each channel, and obtaining the most reliable interpretation result through weighted calculation. This embodiment improves anti-interference capability and result accuracy through multi-channel independent verification and intelligent fusion decision-making mechanisms, exhibiting superior reliability, especially in edge cases or when signal quality is uneven.

[0146] Figure 4 A block diagram of a dual verification system based on type recognition and result calibration according to the present invention is shown.

[0147] like Figure 4 As shown, the second aspect of the present invention discloses a dual verification system 4 based on type recognition and result calibration, including a memory 41 and a processor 42. The memory includes a dual verification method program based on type recognition and result calibration. When the dual verification method program based on type recognition and result calibration is executed by the processor, it performs the following steps:

[0148] Based on the preset optical acquisition mode, the first optical curve of the test strip is obtained;

[0149] The first optical curve is matched with a preset standard curve, and the first recognition type is obtained based on the similarity.

[0150] Based on the first identification type, dynamically load multi-dimensional feature thresholds, including at least the initiation threshold, the stability threshold, and the type threshold range;

[0151] Based on the preset feature extraction rules, multidimensional feature information is obtained according to the first optical curve, including at least the reaction zone change rate, fluctuation amplitude, and reaction zone peak-to-peak value.

[0152] Determine whether the rate of change in the reaction zone is higher than the start-up threshold;

[0153] If so, determine whether the fluctuation amplitude is lower than the stability threshold;

[0154] If so, determine whether the peak value of the reaction zone is within the range of the type threshold.

[0155] If so, then the second identification type is obtained;

[0156] Determine whether the first identification type and the second identification type are the same;

[0157] If so, then the test strip type is obtained;

[0158] If not, an exception command will be output.

[0159] It should be noted that the first identification type is a preliminary type identification result based on the optical curve of the test strip; the second identification type is a preliminary type interpretation result based on the optical features of the test strip. In this embodiment, firstly, the first optical curve of the test strip is acquired through a preset optical acquisition mode; wherein, the first optical curve contains optical feature information of the test strip reaction area. Next, the obtained first optical curve is compared with a pre-stored standard curve for similarity matching calculation, and the first identification type is determined based on the matching result. Subsequently, according to the determined first identification type, the corresponding multi-dimensional feature threshold parameter group is dynamically loaded; wherein, the parameter group includes at least a start-up threshold for determining the start of the reaction, a stability threshold for determining signal stability, and a type threshold range for type verification. After obtaining these basic parameters, multi-dimensional feature information is extracted from the first optical curve based on preset feature extraction rules; wherein, at least, key feature parameters such as the reaction area change rate, fluctuation amplitude, and reaction area peak-to-peak value are extracted. Then, a chain judgment process is executed: first, it is determined whether the reaction area change rate is higher than the start-up threshold; if so, it is further determined whether the fluctuation amplitude is lower than the stability threshold; if so, it is further determined whether the reaction area peak-to-peak value is within the type threshold range; if so, the second identification type is obtained. Finally, the consistency between the first and second identification types is verified; if they are the same, the final test strip type is confirmed; if they are different, an error command is output. This embodiment effectively improves the accuracy and reliability of test strip type identification through a dual mechanism of optical curve matching and feature parameter verification.

[0160] According to an embodiment of the present invention, the step of matching the first optical curve with a preset standard curve and obtaining a first recognition type based on similarity specifically includes:

[0161] The first optical curve of the test strip reaction area is obtained based on the reflected light data collected by the optical sensor.

[0162] The first optical curve is preprocessed, including baseline calibration and noise filtering;

[0163] The similarity of the preprocessed first optical curve with the preset HCG standard curve and LH standard curve is calculated respectively.

[0164] Based on the similarity calculation results, the test strip type corresponding to the standard curve with the highest similarity is selected as the first identification type;

[0165] When the highest similarity is lower than the preset confidence threshold, an abnormal signal for type identification is output.

[0166] It should be noted that in this embodiment, firstly, a first optical curve of the test strip reaction area is constructed based on the reflected light data collected by the optical sensor. To improve data quality, the original optical curve is preprocessed; this includes baseline calibration to eliminate background interference and noise filtering to improve the signal-to-noise ratio. The preprocessed optical curve is then compared with preset HCG and LH standard curves for similarity calculation. A specific similarity algorithm is used to evaluate the matching degree of curve morphology and feature points. Based on the similarity calculation results, the test strip type corresponding to the standard curve with the highest similarity is selected as the first identification type. To ensure the reliability of the identification results, a confidence threshold mechanism is also set. When the highest similarity is lower than the preset confidence threshold, an abnormal type identification signal is output to avoid misidentification caused by low-quality matching. This embodiment provides an accurate and reliable preliminary identification foundation for subsequent verification processes through multi-level curve processing and rigorous similarity evaluation.

[0167] According to an embodiment of the present invention, the method includes start signal detection and optical stabilization verification, specifically:

[0168] Based on the first optical curve, the signal change rate of adjacent sampling points is calculated to obtain the change rate of the reaction zone;

[0169] The rate of change in the reaction zone is compared with the start-up threshold of dynamic loading to obtain the number of sampling periods in which the rate of change in the reaction zone is continuously higher than the start-up threshold.

[0170] If the number of sampling periods exceeds the preset number of periods threshold, the reaction is determined to have started normally;

[0171] After the reaction is initiated, the signal fluctuation amplitude within a preset time window is calculated based on the first optical curve;

[0172] When the fluctuation amplitude is below the stability threshold for two consecutive sampling periods, the signal is considered to have reached a stable state.

[0173] It should be noted that in this embodiment, the reaction zone change rate parameter is obtained by calculating the signal change rate of adjacent sampling points based on the obtained first optical curve. The calculated reaction zone change rate is continuously compared with the dynamically loaded start-up threshold, and the number of sampling periods in which the reaction zone change rate is continuously higher than the start-up threshold is counted. Only when the number of sampling periods exceeds a preset number of periods threshold is the reaction considered to have started normally. This embodiment effectively avoids false triggering caused by instantaneous interference through a continuous monitoring mechanism. After confirming the start of the reaction, the optical stabilization monitoring stage is entered, and the signal fluctuation amplitude within a preset time window is calculated based on the first optical curve. By continuously monitoring the comparison results of the fluctuation amplitude and the stabilization threshold, the signal is considered to have reached a stable state when the fluctuation amplitude is lower than the stabilization threshold for two consecutive sampling periods. This embodiment ensures that subsequent analysis is only performed under the condition that the reaction has started normally and the signal is stable through a dual verification mechanism, significantly improving the accuracy of the detection results.

[0174] A third aspect of the present invention provides a computer-readable storage medium comprising a dual verification method program based on type recognition and result calibration, wherein when the dual verification method program based on type recognition and result calibration is executed by a processor, it implements the steps of the dual verification method based on type recognition and result calibration as described in any of the preceding claims.

[0175] In summary, this invention provides a dual verification method, system, and medium based on type recognition and result calibration. First, the first optical curve of the test strip is acquired, and this curve is matched with a preset standard curve to determine the first identification type. Then, multi-dimensional feature thresholds are dynamically loaded, and multi-dimensional feature information is parsed from the optical curve based on feature extraction rules. Next, a series of threshold judgment processes are executed: first, it is verified whether the rate of change in the reaction zone is higher than the activation threshold; then, it is confirmed whether the fluctuation amplitude is lower than the stability threshold; finally, it is determined whether the peak-to-peak value is within the type threshold range. If all conditions are met, a second identification type is generated. Finally, the test strip type is confirmed by comparing the consistency between the first and second identification types. If they are consistent, the final result is output; if they are inconsistent, anomaly handling is triggered. This invention improves the accuracy and reliability of test strip type interpretation through a dual guarantee mechanism of optical feature matching and parameterized threshold verification.

[0176] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the 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 to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0177] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A dual verification method based on type recognition and result calibration, characterized in that, The method includes: Based on the preset optical acquisition mode, the first optical curve of the test strip is obtained; The first optical curve is matched with a preset standard curve, and the first recognition type is obtained based on the similarity. Based on the first identification type, dynamically load multi-dimensional feature thresholds, including at least the initiation threshold, the stability threshold, and the type threshold range; Based on the preset feature extraction rules, multidimensional feature information is obtained according to the first optical curve, including at least the reaction zone change rate, fluctuation amplitude, and reaction zone peak-to-peak value. Based on the first optical curve, the signal change rate of adjacent sampling points is calculated to obtain the change rate of the reaction zone; The rate of change in the reaction zone is compared with the start-up threshold of dynamic loading to obtain the number of sampling periods in which the rate of change in the reaction zone is continuously higher than the start-up threshold. If the number of sampling periods exceeds the preset number of periods threshold, the reaction is determined to have started normally; After the reaction is initiated, the signal fluctuation amplitude within a preset time window is calculated based on the first optical curve; When the fluctuation amplitude is below the stability threshold for two consecutive sampling periods, the signal is determined to have reached a stable state. After reaching a stable state, determine whether the peak value of the reaction zone is within the range of the type threshold. If so, then the second identification type is obtained; Determine whether the first identification type and the second identification type are the same; If so, then the test strip type is obtained; If not, output an exception command; Before outputting the final test strip type result, the following is also included: The optical sensor is controlled to simultaneously acquire optical signals from multiple detection channels within the reaction zone of the test strip, resulting in multiple corresponding optical curves; For each detection channel, a feature extraction and threshold judgment process is performed separately to obtain preliminary judgment results for multiple channels; Compare the consistency of the interpretation results of each channel, and when the number of consistent channels reaches the preset confidence level, the interpretation result is adopted; If there are discrepancies in the results of each channel, a weighted voting algorithm is executed, assigning different weights to each channel based on its signal quality, and calculating the weighted interpretation result.

2. The dual verification method based on type recognition and result calibration according to claim 1, characterized in that, The step of matching the first optical curve with a preset standard curve and obtaining a first recognition type based on similarity specifically includes: The first optical curve of the test strip reaction area is obtained based on the reflected light data collected by the optical sensor. The first optical curve is preprocessed, including baseline calibration and noise filtering; The similarity of the preprocessed first optical curve with the preset HCG standard curve and LH standard curve is calculated respectively. Based on the similarity calculation results, the test strip type corresponding to the standard curve with the highest similarity is selected as the first identification type; When the highest similarity is lower than the preset confidence threshold, an abnormal signal for type identification is output.

3. The dual verification method based on type recognition and result calibration according to claim 1, characterized in that, The step of dynamically loading multi-dimensional feature thresholds according to the first identification type specifically includes: Based on the first identification type, access the non-volatile memory that stores different types of test strip parameter sets; If the first identification type is HCG, then the first parameter group is loaded, and the first parameter group includes at least the initiation threshold, stability threshold and type threshold range applicable to the reaction kinetics characteristics of HCG test strip; If the first identification type is LH, then the second parameter set is loaded. The second parameter set includes at least the initiation threshold, stability threshold and type threshold range applicable to the reaction kinetics of LH test strip. The loaded parameter set is set as the effective threshold of the current reading cycle, forming a multi-dimensional feature threshold set.

4. The dual verification method based on type recognition and result calibration according to claim 1, characterized in that, The multi-dimensional feature information obtained based on the preset feature extraction rules and the first optical curve specifically includes: Temporal features, including the rate of change and fluctuation amplitude of the signal in the reaction region, are extracted from the first optical curve. Frequency domain features, including main frequency components and spectral energy distribution, are extracted from the first optical curve. Calculate the characteristic parameters of the optical signal in the reaction zone, including peak position, valley position, and peak-to-peak value; The extracted multidimensional feature information is classified and stored.

5. The dual verification method based on type recognition and result calibration according to claim 1, characterized in that, Including type validation and exception handling, it also includes: Perform a consistency comparison between the first identification type and the second identification type; When both match, confirm the final test strip type and output the calibrated test results; When the two are inconsistent, the exception handling process is initiated, including re-collecting optical data and prompting the user to confirm the test strip type; If multiple consecutive verifications are inconsistent, a self-test procedure will be executed and a device maintenance prompt message will be output.

6. A dual verification system based on type recognition and result calibration, characterized in that, The system includes a memory and a processor. The memory includes a dual verification method program based on type recognition and result calibration. When the processor executes the dual verification method program based on type recognition and result calibration, it performs the following steps: Based on the preset optical acquisition mode, the first optical curve of the test strip is obtained; The first optical curve is matched with a preset standard curve, and the first recognition type is obtained based on the similarity. Based on the first identification type, dynamically load multi-dimensional feature thresholds, including at least the initiation threshold, the stability threshold, and the type threshold range; Based on the preset feature extraction rules, multidimensional feature information is obtained according to the first optical curve, including at least the reaction zone change rate, fluctuation amplitude, and reaction zone peak-to-peak value. Based on the first optical curve, the signal change rate of adjacent sampling points is calculated to obtain the change rate of the reaction zone; The rate of change in the reaction zone is compared with the start-up threshold of dynamic loading to obtain the number of sampling periods in which the rate of change in the reaction zone is continuously higher than the start-up threshold. If the number of sampling periods exceeds the preset number of periods threshold, the reaction is determined to have started normally; After the reaction is initiated, the signal fluctuation amplitude within a preset time window is calculated based on the first optical curve; When the fluctuation amplitude is below the stability threshold for two consecutive sampling periods, the signal is determined to have reached a stable state. After reaching a stable state, determine whether the peak value of the reaction zone is within the range of the type threshold. If so, then the second identification type is obtained; Determine whether the first identification type and the second identification type are the same; If so, then the test strip type is obtained; If not, output an exception command; Before outputting the final test strip type result, the following is also included: The optical sensor is controlled to simultaneously acquire optical signals from multiple detection channels within the reaction zone of the test strip, resulting in multiple corresponding optical curves; For each detection channel, a feature extraction and threshold judgment process is performed separately to obtain preliminary judgment results for multiple channels; Compare the consistency of the interpretation results of each channel, and when the number of consistent channels reaches the preset confidence level, the interpretation result is adopted; If there are discrepancies in the results of each channel, a weighted voting algorithm is executed, assigning different weights to each channel based on its signal quality, and calculating the weighted interpretation result.

7. The dual verification system based on type recognition and result calibration according to claim 6, characterized in that, The step of matching the first optical curve with a preset standard curve and obtaining a first recognition type based on similarity specifically includes: The first optical curve of the test strip reaction area is obtained based on the reflected light data collected by the optical sensor. The first optical curve is preprocessed, including baseline calibration and noise filtering; The similarity of the preprocessed first optical curve with the preset HCG standard curve and LH standard curve is calculated respectively. Based on the similarity calculation results, the test strip type corresponding to the standard curve with the highest similarity is selected as the first identification type; When the highest similarity is lower than the preset confidence threshold, an abnormal signal for type identification is output.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer-readable storage medium includes a dual verification method program based on type recognition and result calibration. When the dual verification method program based on type recognition and result calibration is executed by a processor, it implements the steps of the dual verification method based on type recognition and result calibration as described in any one of claims 1 to 5.

Images