Peritoneal dialysis solution detection data intelligent analysis method based on visual identification

Abstract

The invention provides a peritoneal dialysis solution detection data intelligent analysis method based on visual identification, and the method comprises the steps: obtaining a to-be-identified test paper image, carrying out the test paper region segmentation and color correction of the test paper image, and carrying out the brightness equalization processing of a test paper detection region, and obtaining a processed test paper detection region; obtaining a standardized color feature vector of a test paper color development area from the test paper detection area; carrying out mapping matching on the standardized color feature vector and a standard colorimetric database to obtain a colorimetric matching value, carrying out color abnormality identification according to the colorimetric matching value, comparing the color abnormality with a preset abnormal value to obtain a test paper colorimetric analysis result, and carrying out self-adaptive correction on the test paper colorimetric analysis result with abnormality; and constructing a personalized colorimetric model according to the colorimetric matching value in combination with a historical colorimetric matching value, and performing health trend analysis and early warning.

Description

Technical Field

[0001] The present invention belongs to the field of visual recognition, and particularly relates to an intelligent analysis method for peritoneal dialysis fluid detection data based on visual recognition. Background Art

[0002] Peritoneal dialysis is a long-term treatment method for patients with end-stage renal disease, relying on the component changes of peritoneal dialysis fluid to evaluate the dialysis effect and the patient's health status. Peritoneal dialysis-related peritonitis is the most common and serious complication of end-stage renal disease, and early diagnosis is crucial for reducing hospitalization rates and the risk of complications. Existing peritoneal dialysis fluid detection methods mainly include two methods: laboratory detection and test strip detection. Laboratory detection methods, such as white blood cell count, Gram stain smear, culture analysis, etc., rely on professional equipment and medical staff, have a long detection cycle, and are not suitable for home self-examination. To improve convenience, test strip-based detection methods have emerged on the market. Patients can evaluate key indicators in peritoneal dialysis fluid (such as white blood cells, pH, protein, glucose, etc.) by comparing the colors of test strips. However, this method still has significant deficiencies, affecting the accuracy and practicality of detection.

[0003] First of all, test strip detection relies on visual color comparison or mobile phone photo comparison, which is severely affected by environmental factors. Visual color comparison is easily affected by subjective judgment and has a large error; although mobile phone photo color comparison can reduce subjective errors, the existing color analysis methods (such as colorimetric analysis based on the RGB color space) are sensitive to changes in light, angle, and device hardware, resulting in inconsistent color recognition of the same test strip under different conditions. In addition, the colorimetric standards of different brands of test strips may vary, and the existing detection methods usually use fixed colorimetric cards for comparison, making it difficult to ensure cross-brand consistency, thus affecting the comparability of long-term detection data.

[0004] Secondly, existing methods are difficult to accurately identify small changes in the color of test strips. Many early lesions of peritonitis only show slight leukocytosis or abnormal pH values, and the existing colorimetric methods are not sensitive enough to these small color changes, easily leading to false detection or missed detection of early lesions. In addition, peritoneal dialysis fluid turbidity is an important judgment index for peritonitis, but its causes are relatively complex, including infectious and non-infectious factors (such as chyluria, hemorrhage, protein precipitation, etc.). Currently, color-based detection methods cannot effectively distinguish different types of turbidity, resulting in a high risk of misdiagnosis.

[0005] In addition, existing technologies lack the ability for long-term health monitoring and trend analysis. The current detection methods are mainly based on single measurements, unable to conduct dynamic evaluations by combining historical data, and difficult to predict the risk of peritonitis. For long-term dialysis patients, the lack of continuous health data analysis will reduce the guiding value of home detection, leading to the neglect of many potential health risks.

[0006] In summary, the existing peritoneal dialysis fluid test strip detection methods have obvious deficiencies in aspects such as environmental adaptability, colorimetric accuracy, early disease identification, cross-brand consistency, and long-term health monitoring. There is an urgent need for a more accurate, stable, and intelligent detection method to improve the reliability of home detection and provide a more clinically valuable health assessment ability. Summary of the Invention

[0007] The object of the present invention is to propose an intelligent analysis method for peritoneal dialysis fluid detection data based on visual recognition, which provides a new detection method by improving colorimetric accuracy, reducing environmental interference, enhancing early disease detection ability, and supporting long-term health monitoring.

[0008] To achieve the above object, the present invention provides an intelligent analysis method for peritoneal dialysis fluid detection data based on visual recognition, and the method includes the following steps:

[0009] S1. Obtain a test strip image to be recognized, perform test strip area segmentation, color correction, and brightness equalization processing on the test strip detection area of the test strip image to obtain a processed test strip detection area;

[0010] S2. Obtain a standardized color feature vector of the test strip color development area from the test strip detection area;

[0011] S3. Map and match the standardized color feature vector with a standard colorimetric database to obtain a colorimetric matching value, perform color abnormality recognition based on the colorimetric matching value, compare the color abnormality with a preset abnormal value to obtain a test strip colorimetric analysis result, and perform adaptive correction on the test strip colorimetric analysis result with abnormalities;

[0012] S4. Construct a personalized colorimetric model based on the colorimetric matching value and historical colorimetric matching values, and perform health trend analysis and early warning.

[0013] Further, the test strip area segmentation adaptively determines a threshold according to the image gray value to generate a binary image, and at the same time removes the noise of the binary image through opening operation, and retains the largest connected area as the test strip detection area;

[0014] The color correction uses the color mean value of the test strip background area as a reference, calculates a color correction coefficient, corrects the color of the test strip detection area according to the color correction coefficient, and introduces a regularization term to compensate for illumination changes and test strip brand differences; the regularization term is based on the ratio of the color variance to the mean value of the test strip detection area;

[0015] The brightness equalization processing of the test strip detection area is realized through guided filtering, wherein the guided image is the test strip background area, and the adjustment factor is adaptively determined according to the background brightness.

[0016] Further, the S2 specifically includes:

[0017] Convert the color data of the test strip color development area from the RGB color space to the HSV color space;

[0018] Normalize the color data of the test strip detection area to compensate for color offset;

[0019] Perform weighted adjustment on the color features to generate a standardized color feature vector.

[0020] Furthermore, the mapping and matching of the standardized color feature vector with the standard color comparison database is specifically as follows:

[0021] Construct a standard color comparison database; the standard color comparison database contains multiple standard color comparison vectors and their corresponding health status labels;

[0022] The mapping and matching establish a mapping relationship between the color feature vector and the standard color comparison database through weighted minimization of color difference calculation.

[0023] Furthermore, the degree of abnormality is calculated as follows:

[0024]

[0025] where δ c is the color abnormality; Var(C std ) calculates the variance of the color of the test strip color development area to measure color stability; C b,avg is the mean color vector in the standard color comparison database B; Std(C b ) is the color standard deviation of the standard color comparison database B, representing the color distribution range of the standard color comparison; λ is the abnormal detection adjustment coefficient to ensure adaptive adjustment of the color abnormality calculation for different test strip brands; ∈ is a decimal to prevent division by zero;

[0026] Based on the comparison of the color abnormality with a preset abnormal value, make a final determination of the detection result and perform adaptive correction on the abnormal situation.

[0027] Furthermore, the S4 specifically includes:

[0028] Use historical detection data to establish a personalized color comparison model to calibrate the health significance of individual color changes;

[0029] Use time series modeling methods to predict the change trend of the health status and provide risk warnings in the early stage of the disease;

[0030] Provide a personalized feedback mechanism so that when an abnormal situation occurs, the patient can record relevant information and optimize the color comparison calibration model in combination with the doctor's diagnosis result.

[0031] Furthermore, the personalized colorimetric model is updated by minimizing the individual colorimetric deviation:

[0032]

[0033] Among them, M p is the output of the personalized colorimetric calibration model, C b is the most matching color vector in the standard colorimetric database B, used to provide a colorimetric benchmark under an ideal healthy state; ω t is the time decay factor, ensuring that the most recent test results contribute more to the model update; N is the total time; the colorimetric results of the past N tests are The corresponding color feature vector is in, Limit the short-term and drastic changes in the colorimetric results, ensure the smoothness of the colorimetric model update, and improve the adaptability of the colorimetric model to changes in individual health status.

[0034] Furthermore, the predicted changing trend of the health status is combined with historical health scores, colorimetric results, and personalized colorimetric models to perform trend prediction; if the predicted value is lower than the set threshold for multiple consecutive times, a health warning is triggered, prompting the user that peritonitis or other health abnormalities may exist.

[0035] The beneficial technical effects of the present invention are at least as follows:

[0036] It can adapt to different lighting conditions and shooting environments more stably, reduce the colorimetric error caused by ambient light interference, and improve the stability of color recognition.

[0037] Secondly, the present invention optimizes the test paper colorimetric analysis method, which can improve the system's ability to recognize slight color changes, reduce false detection or missed detection due to colorimetric errors, and enhance the system's adaptability to test papers of different brands, thereby ensuring the comparability and consistency of test results.

[0038] In addition, the present invention enhances the intelligent analysis capability of test data, enabling the system to combine the user's historical test data, build personalized colorimetric calibration standards, and conduct long-term health trend analysis to provide users with disease risk warnings and improve the early detection capability of peritonitis.

[0039] The invention can significantly improve the accuracy and stability of peritoneal dialysis fluid test strip detection, while enhancing the clinical guidance value of home testing, and providing peritoneal dialysis patients with a more convenient and reliable intelligent health management solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The present invention will be further described with reference to the accompanying drawings. However, the embodiments shown in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on the following drawings without creative efforts.

[0041] Figure 1 It is a flowchart of an intelligent analysis method for peritoneal dialysis solution detection data based on visual recognition disclosed in an embodiment of the present invention. Detailed implementation manners

[0042] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and are only used to explain the present invention, and should not be construed as a limitation to the present invention.

[0043] As Figure 1 shown, the intelligent analysis method for peritoneal dialysis solution detection data based on visual recognition provided by the embodiment of the present invention includes the following steps:

[0044] S1. Obtain the test strip image to be recognized, and perform test strip area segmentation, color correction, and brightness equalization processing on the test strip detection area of the test strip image to obtain the processed test strip detection area.

[0045] Specifically, obtain the standardized test strip image I std , and perform the following steps:

[0046] Test strip area segmentation: Use the edge detection algorithm to obtain the contour of the test strip area, and remove the background interference through morphological operations to extract the test strip detection area R t .

[0047] Let the gray value of the original image be I g , and use the threshold segmentation method to obtain the binary image B t :

[0048]

[0049] where T b is a dynamically calculated threshold, which is adaptively adjusted according to the brightness of the test strip background to ensure stable segmentation under different lighting conditions.

[0050] Use the improved morphological opening operation to remove small noise points, and combine the connected region analysis to retain the test strip area with the largest area as R t , ensuring the integrity of the test strip area.

[0051] Reference area extraction and color reference correction: Use the uncolored area on the test strip as a reference to calculate the color offset to ensure color consistency.

[0052] Let R r be the background area of the test strip, and its color mean is (R r , G r , B r ), which is used as the color reference.

[0053] Calculate the color correction coefficient α c , and add an innovative regularization term λ to enhance color stability:

[0054]

[0055] where, Var(R t ) is the color variance of the test strip color development area, which measures the stability of the color distribution. Mean(R t ) is the color mean of the test strip color development area. λ is an adaptive regularization coefficient, which enables color compensation to adapt to different lighting environments and avoid color distortion caused by overcorrection.

[0056] According to α c , normalize R t :

[0057]

[0058] This normalization method can further eliminate color deviation caused by test strip brand differences and lighting changes compared with traditional color normalization methods, and improve the stability and cross-brand consistency of colorimetric detection.

[0059] Brightness equalization of the test strip detection area: To reduce color abnormalities caused by local uneven lighting, a method based on guided filtering is used to smooth the brightness of the test strip detection area R t ′.

[0060] Let the input of the guided filter be R t ′, the guidance image be the test strip background area R r , and the filtered output be R t ″, then:

[0061] R t ″ = R t ′ - γ·(R r - Mean(R r )) (4)

[0062] where, γ is the brightness adjustment factor, which can be adaptively adjusted according to the test strip background brightness to ensure that the brightness of the test strip color development area remains stable in different environments.

[0063] Compared with the traditional histogram equalization method, this method can enhance the contrast while maintaining the color information of the test strip without distortion, improving the accuracy of colorimetric analysis.

[0064] Output the test strip detection area R after color correction and brightness equalization t ″, as the input for subsequent color feature extraction, ensuring the comparability of color information under different lighting environments and reducing the colorimetric deviation caused by differences in test strip brands.

[0065] S2. Obtain the standardized color feature vector of the test strip color development area from the test strip detection area.

[0066] Among them, the key to test strip colorimetric detection lies in accurately identifying the color information of different detection areas on the test strip. Therefore, it is necessary to extract pixel-level color values from R t ″ and convert them into a more stable color feature vector.

[0067] Specifically, the color data C of the test strip color development area raw consists of (R, G, B). However, since the RGB color space is easily affected by light, we first convert it to the HSV color space:

[0068] C h = (H, S, V) = f c (R, G, B) (5)

[0069] Among them, f c is a color conversion function that converts RGB color to HSV. Since the HSV hue component H is more robust to light changes.

[0070] Adaptive color normalization of the test strip detection area: The color of the test strip is affected by the chemical reaction of the reagent, and its color development characteristics vary depending on the detection item. Therefore, we need to adaptively adjust through color distribution to improve the color stability under different test strip brands and detection areas.

[0071] Let the mean value of the color distribution of the test strip reference area (background area) be C r = (H r , S r , V r ), used to compare with the color C of the test strip detection area h , and calculate the normalization coefficient α c :

[0072]

[0073] Among them, λ is a dynamic adjustment factor, enabling color normalization to adapt to the color development characteristics of different test strip brands. Mean(C h ) calculates the mean value of the overall color of the detection area to prevent color normalization from overly affecting the colorimetric result.

[0074] Normalized color vector:

[0075] C n = C h ·α c (7)

[0076] This normalization method can compensate for color shifts caused by differences in test strip brands and improve cross-brand consistency in colorimetric analysis.

[0077] Adaptive enhancement of color weights: The color of the test strip detection area may be affected by factors such as uneven local illumination and uneven chemical reactions on the test strip. Therefore, we perform weighted adjustment on the color features to highlight key color information.

[0078] Calculate the color enhancement weight ω c :

[0079]

[0080] where β is the color enhancement coefficient, used to control the adjustment amplitude of the color weights. Var(C n ) calculates the variance of the normalized color distribution and identifies the non-uniformity of the color development area. This weight term ensures that the high-variation parts of the color development area are enhanced, improving the sensitivity of colorimetric analysis.

[0081] Construct the final standardized color feature vector: Combine the color enhancement weight ω c , to obtain the final test strip color feature:

[0082] C std = ω c ·C n (9)

[0083] This color feature vector C std has a more stable color representation, ensuring the comparability of color information under different test strip brands and environments, and providing input for subsequent intelligent colorimetric analysis.

[0084] Output the standardized color feature vector C std , for subsequent colorimetric analysis, ensuring that the color information of the test strip detection area remains consistent under cross-environment and cross-device conditions, and improving the accuracy and robustness of colorimetric analysis.

[0085] S3. Map and match the standardized color feature vector with the standard colorimetric database to obtain a colorimetric match value, identify color abnormality based on the colorimetric match value, compare the color abnormality with a preset abnormal value to obtain the test strip colorimetric analysis result, and perform adaptive correction on the test strip colorimetric analysis result with abnormalities.

[0086] Among them, the input standardized color feature vector is C std .

[0087] Specifically, a test strip color matching mapping is constructed: the color change of the test strip corresponds to the chemical composition change in the peritoneal dialysis fluid. Therefore, we need to establish a mapping relationship between the color feature vector C std and the standard color comparison database B for precise color comparison.

[0088] Suppose the standard color comparison database B contains multiple standard color comparison vectors C b and their corresponding health status labels L b , then the color comparison matching function M b is calculated as follows by weighted minimizing the color difference:

[0089]

[0090] Among them, C b,i represents the i-th standard color vector in the color comparison database. w i is a dynamic weighting factor, which is adaptively adjusted by factors such as test strip brand, chemical reaction time, and lighting environment to optimize color comparison matching under different test strip conditions.

[0091] This optimization method ensures the stability of the color comparison calculation results and is not affected by environmental lighting and test strip brand.

[0092] Calculate the color abnormality: The peritoneal dialysis fluid test strip may have abnormal color development due to factors such as test strip quality, user operation, and environmental lighting. Therefore, we need to calculate the abnormality degree of the test strip color to reduce misjudgment and missed detection. The color abnormality δ c is calculated as follows:

[0093]

[0094] Among them, Var(C std ) calculates the variance of the color in the color development area of the test strip to measure color stability. C b,avg is the mean color vector in the standard color comparison database B. Std(C b ) is the color standard deviation of the standard color comparison database B, indicating the color distribution range of the standard color comparison. λ is an abnormal detection adjustment coefficient to ensure adaptive adjustment of the color abnormality calculation for different test strip brands. ∈ is a decimal to prevent division by zero problems.

[0095] This color abnormality detection method can eliminate color comparison errors caused by factors such as uneven chemical reactions of the test strip and abnormal lighting, and improve the robustness of test strip color comparison.

[0096] Preferably, after color comparison calculation and color abnormality detection, we need to make a final determination of the detection result and perform adaptive correction on abnormal situations.

[0097] Let the final detection category of the test strip be L c It is determined by the following decision function:

[0098]

[0099] where τ c is the abnormal determination threshold, which is adaptively adjusted by historical data to ensure the sensitivity and stability of abnormal detection. If δ c > τ c , the system enters the adaptive abnormal correction mode, recalculates the colorimetric matching function M b , and combines the user's historical colorimetric data for self-update of the colorimetric model to optimize future detection accuracy.

[0100] Output the colorimetric analysis result L of the test strip c , including the test strip detection category and the color abnormality degree δ c , and this result will be used for subsequent health trend analysis and personalized colorimetric optimization to ensure the long-term stability and accuracy of the colorimetric analysis result.

[0101] S4. Construct a personalized colorimetric model based on the colorimetric matching value and the historical colorimetric matching value, and conduct health trend analysis and early warning.

[0102] Specifically, construct a personalized colorimetric calibration model:

[0103] Since there are individual differences in the components of peritoneal dialysis fluid among different patients, the standard value of the test strip color development needs to be fine-tuned for individuals. We use historical detection data to establish a personalized colorimetric model M p , calibrate the health significance of individual color changes, so that colorimetric analysis is not only applicable to the health assessment in the sense of population statistics, but also adapts to individual health characteristics.

[0104] Let the colorimetric results of the past N detections be and their corresponding color feature vectors be Then the personalized colorimetric calibration model M p is updated by minimizing the individual colorimetric deviation:

[0105]

[0106] where C b is the most matching color vector in the standard colorimetric database B, which is used to provide a colorimetric benchmark in the ideal health state. ω t is the time decay factor, which ensures that the most recent detection results contribute more to the model update:

[0107] ω t = e -λ(N-t ) (14)

[0108] λ is the time decay parameter, which controls the influence range of historical data on model update. The innovation regularization term restricts the short-term drastic changes in the colorimetric results, ensures the smoothness of the colorimetric model update, and improves the adaptability of the colorimetric model to changes in individual health status.

[0109] Preferably, since the early symptoms of peritonitis may be manifested as slow changes in the colorimetric results of the test strip rather than single mutations, we use time series modeling methods to predict the change trend of the health status and provide risk warnings in the early stage of the disease.

[0110] Let H(t) represent the health score of the test data at time t, which is defined as follows:

[0111]

[0112] Among them, f(·) is the health trend modeling function, which combines historical health scores, the latest colorimetric results, and the personalized calibration model for trend prediction. To enhance the stability of trend modeling, a dynamic change constraint term is introduced:

[0113]

[0114] Among them, α, β, γ are model weights, which control the dynamic changes of the health score. Restricts the large fluctuations in the health score within a short time and improves the reliability of abnormal change detection.

[0115] If H(t) is lower than the set threshold τ h for multiple consecutive times, then a health warning W is triggered, indicating that the user may have peritonitis or other health abnormalities:

[0116]

[0117] Among them, τ h is dynamically adjusted through individual historical data to ensure the accuracy of the warning.

[0118] Preferably, since factors such as the patient's living habits, diet, and drug use may affect the colorimetric results of the peritoneal dialysis fluid, we provide a personalized feedback mechanism so that when an abnormal situation occurs, the patient can record relevant information and optimize the colorimetric calibration model M p .

[0119] In the next colorimetric analysis, the system will adjust the colorimetric calibration parameters according to the personalized feedback data, optimize the calculation of the health score H(t), and make the model more suitable for the actual changes in the individual health status.

[0120] Output personalized health trend H(t) and intelligent warning signal W for long-term health monitoring and feedback them to the personalized colorimetric calibration model M p , forming a closed-loop optimization to improve the accuracy and individual adaptability of colorimetric analysis.

[0121] The above describes specific embodiments of this specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve the desired results. Additionally, the processes depicted in the figures do not necessarily have to be in the specific order or sequential order shown to achieve the desired results. In certain implementations, multitasking and parallel processing are also possible or may be advantageous.

[0122] The systems, devices, modules, or units illustrated in the above embodiments can be specifically implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or any combination of these devices.

[0123] For convenience of description, when describing the above devices, they are described as various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0124] Those skilled in the art should understand that the embodiments of this specification can be provided as a method, a system, or a computer program product. Therefore, the embodiments of this specification can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] This specification is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of this specification. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate for implementing the processes Figure 1One or more processes and / or blocks Figure 1 means for the functions specified in one or more blocks.

[0126] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction means that implements the functions in the process Figure 1 One or more processes and / or blocks Figure 1 specified in one or more blocks.

[0127] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions in the process Figure 1 One or more processes and / or blocks Figure 1 specified in one or more blocks.

[0128] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0129] Memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory such as read only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

[0130] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storing information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technologies, compact disc read only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0131] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising said element.

[0132] This specification can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0133] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and reference can be made to the corresponding parts of the method embodiments for the relevant content.

[0134] Finally, it should be noted that what is disclosed in an embodiment of a lithium battery pack chip equalization control platform of the present invention is only a preferred embodiment of the present invention, and is only used to illustrate the technical solution of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacement on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent analysis method for peritoneal dialysis fluid detection data based on visual recognition, characterized in that The method includes the following steps: S1. Obtain the test strip image to be recognized, perform test strip area segmentation, color correction, and brightness equalization processing on the test strip detection area of the test strip image to obtain the processed test strip detection area; S2. Obtain the standardized color feature vector of the test strip color development area from the test strip detection area; S3. Map and match the standardized color feature vector with the standard color comparison database to obtain a color comparison match value, perform color abnormality recognition based on the color comparison match value, obtain the test strip color comparison analysis result by comparing the color abnormality with a preset abnormal value, and perform adaptive correction on the test strip color comparison analysis result with abnormalities; S4. Construct a personalized color comparison model based on the color comparison match value and historical color comparison match values, and perform health trend analysis and early warning.

2. The intelligent analysis method for peritoneal dialysis fluid detection data based on visual recognition according to claim 1, wherein The test strip area segmentation adaptively determines a threshold according to the image gray value to generate a binary image, and at the same time removes the noise of the binary image through opening operation, and retains the largest connected area as the test strip detection area; The color correction uses the color mean value of the test strip background area as a reference, calculates the color correction coefficient, corrects the color of the test strip detection area according to the color correction coefficient, and introduces a regularization term to compensate for illumination changes and test strip brand differences; the regularization term is based on the ratio of the color variance to the mean value of the test strip detection area; The brightness equalization processing of the test strip detection area is realized through guided filtering, where the guiding image is the test strip background area, and the adjustment factor is adaptively determined according to the background brightness.

3. The intelligent analysis method for peritoneal dialysis fluid detection data based on visual recognition according to claim 1, wherein The S2 specifically includes: Convert the color data of the test strip color development area from the RGB color space to the HSV color space; Normalize the color data of the test strip detection area to compensate for color offset; Perform weighted adjustment on the color features to generate a standardized color feature vector.

4. The intelligent analysis method for peritoneal dialysis fluid detection data based on visual recognition according to claim 1, characterized in that, The mapping and matching of the standardized color feature vector with the standard color comparison database is specifically: Construct a standard color comparison database; the standard color comparison database contains multiple standard color comparison vectors and their corresponding health status labels; The mapping and matching calculates the weighted minimum color difference to establish a mapping relationship between the color feature vector and the standard color comparison database.

5. The intelligent analysis method for peritoneal dialysis fluid detection data based on visual recognition according to claim 4, characterized in that, The calculation of the degree of abnormality is as follows: Among them, δ c is the color abnormality; Var(C std ) calculates the variance of the color in the color development area of the test strip to measure the color stability; C b,avg is the mean color vector in the standard color comparison database B; Std(C b ) is the color standard deviation of the standard color comparison database B, representing the color distribution range of the standard color comparison; λ is the anomaly detection adjustment coefficient to ensure the adaptive adjustment of the color abnormality calculation for different test strip brands; ∈ is a decimal to prevent division by zero problem; Compare the color abnormality with a preset abnormal value to make a final determination of the test result, and perform adaptive correction on the abnormal situation.

6. The intelligent analysis method for peritoneal dialysis fluid detection data based on visual recognition according to claim 1, wherein The S4 specifically includes: Use historical detection data to establish a personalized color comparison model to calibrate the health significance of individual color changes; Use time series modeling methods to predict the change trend of the health status and provide risk warnings in the early stage of the disease; Provide a personalized feedback mechanism so that when an abnormal situation occurs, the patient records relevant information and optimizes the color comparison calibration model in combination with the doctor's diagnosis result.

7. The intelligent analysis method for peritoneal dialysis solution detection data based on visual recognition according to claim 6, wherein The personalized color comparison model is updated by minimizing the individual color comparison deviation: Among them, M p is the output of the personalized colorimetric calibration model, C b is the most matching color vector in the standard colorimetric database B, which is used to provide a colorimetric benchmark under the ideal health state; ω t is the time decay factor, which ensures that the most recent detection results contribute more to the model update; N is the total time duration; the colorimetric results of the past N detections are and their corresponding color feature vectors are where limits the rapid short-term changes in the colorimetric results, ensures the smoothness of the colorimetric model update, and improves the adaptability of the colorimetric model to changes in the individual's health state.

8. The intelligent analysis method for peritoneal dialysis fluid detection data based on visual recognition according to claim 6, wherein, The prediction of the change trend of the health status combines historical health scores, color comparison results, and personalized color comparison models for trend prediction; If the predicted value is lower than the set threshold for multiple consecutive times, a health warning is triggered to prompt the user that there may be peritonitis or other health abnormalities.

Images