Method for predicting urinary tract infection by using urine

Abstract

A method for predicting urinary tract infection, of the present invention, may comprise the steps of: acquiring first measurement data, which is obtained by capturing a test sheet at a first point, and second measurement data, which is obtained by capturing the test sheet at a second point; extracting a first change area of the first measurement data and a second change area of the second measurement data on the basis of sample data; calculating an average color value on the basis of the color value of the first change area and the color value of the second change area; calculating an average HSL value on the basis of the average color value; correcting the average HSL value; and predicting the urinary tract infection by using an artificial intelligence model on the basis of the sample data, the average color value, and the corrected average HSL value.

Description

A method for predicting urinary tract infections using urine

[0001] The present invention relates to a method for predicting urinary tract infection, and more specifically, to a method for predicting urinary tract infection based on various color parameters of data obtained by photographing a test paper.

[0002] Recently, diagnostic kits that can be conveniently administered at home have become increasingly popular. These kits offer the advantages of enabling early detection and intervention, preventing infection, and saving time and money by eliminating the need for a visit to a medical institution.

[0003] Among the diseases that can be detected with diagnostic kits, urinary tract infections (UTIs) are easily detected using biological samples (such as urine). These kits can detect UTIs not only in humans but also in pets. However, interpreting the test strips and assessing the severity of UTIs with the naked eye is not easy. Therefore, a diagnostic kit-based disease prediction technology that analyzes the test strip results and assesses the severity of UTIs is needed.

[0004] One object of the present invention is to provide a method for predicting urinary tract infection based on various color parameters of data obtained by photographing a test strip.

[0005] According to one embodiment of the present invention, a method for predicting urinary tract infection based on various color parameters of data obtained by photographing a test paper can be provided.

[0006] Figure 1 is an environmental diagram of a system that provides a method for predicting urinary tract infection according to one embodiment.

[0007] Figure 2 is a flowchart of a method for predicting urinary tract infection according to one embodiment.

[0008] Figure 3 is a flowchart of a method for extracting color values ​​according to one embodiment.

[0009] Figure 4 is a flowchart of a method for correcting HSL values ​​according to one embodiment.

[0010] Figure 5 is a flowchart of a method for calculating the degree of urinary tract infection according to one embodiment.

[0011] Figure 6 is a graph to explain the relationship between the degree of urinary tract infection and gray scale values.

[0012] Figure 7 is an example drawing for explaining multiple measurement data.

[0013] Figure 8 is an example drawing for explaining the average color value.

[0014] Figure 9 is an example drawing to explain the degree of urinary tract infection.

[0015] Figures 10 and 11 are example drawings for explaining an interface implemented on an application.

[0016] In one embodiment, a method for predicting urinary tract infection is provided, which is performed by at least one processor, the method comprising: acquiring first measurement data photographed at a first time point and second measurement data photographed at a second time point of a test strip; extracting a first change area of ​​the first measurement data and a second change area of ​​the second measurement data based on sample data; calculating an average color value based on a color value of the first change area and a color value of the second change area; calculating an average HSL value based on the average color value; correcting the average HSL value; and predicting urinary tract infection using an artificial intelligence model based on the sample data, the average color value, and the corrected average HSL value.

[0017] Here, the step of calculating the average color value may include the step of extracting an overlapping area of ​​the first change area and the second change area for the test paper; the step of extracting a first color value for the first measurement data and a second color value for the second measurement data in the overlapping area; and the step of calculating an average color value of the overlapping area based on the first color value and the second color value.

[0018] Here, the step of correcting the HSL value may include a step of checking whether the first measurement data and the second measurement data are data shot outdoors or data shot indoors; a step of applying an outdoor correction factor to the HSL value if the data is shot outdoors; and a step of applying an indoor correction factor to the HSL value if the data is shot indoors.

[0019] Here, the outdoor correction coefficient and the indoor correction coefficient can be set based on at least one of the HSL value of the first measurement data and the second measurement data, shooting location information, shooting time information, and HSL information of the sample data.

[0020] Here, the step of determining whether the data is shot outdoors or indoors may include a step of transmitting a question related to indoor / outdoor shooting; or a step of determining shooting location information of the first measurement data and the second measurement data.

[0021] Here, the step of predicting the urinary tract infection includes the step of calculating a gray scale value based on the average color value; the step of inputting the gray scale value into the artificial intelligence model; and the step of calculating a degree of urinary tract infection including a score or grade through the artificial intelligence model, wherein the degree of urinary tract infection may increase as the gray scale value decreases.

[0022] Here, the step of providing a guideline based on the degree of the urinary tract infection is further included, wherein the guideline may include at least one of a measurement cycle, hospital information, and diet information.

[0023] Here, the sample data may be data obtained by photographing the test paper at a time point prior to the first time point, or may be data obtained by correcting a pre-stored test paper image based on the HSL values ​​of the first measurement data and the second measurement data.

[0024] Here, a non-transitory computer-readable recording medium having recorded thereon a program for executing the above urinary tract infection prediction method may be provided.

[0025] Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the contents described in the attached drawings. However, the present invention is not limited or restricted by the exemplary embodiments. Unless otherwise defined, all terms (including technical and scientific terms) used in this specification shall be used with meanings that can be commonly understood by those of ordinary skill in the technical field to which this disclosure pertains. However, this may vary depending on the intentions of those skilled in the art, precedents, the emergence of new technologies, etc.

[0026] Additionally, terms defined in commonly used dictionaries should not be interpreted ideally or excessively unless explicitly and specifically defined otherwise. In certain cases, terms may be arbitrarily selected by the applicant, in which case their meanings will be described in detail in the relevant description. Therefore, the terms used in this disclosure should be defined based on their meaning and the overall content of this disclosure, rather than simply their names.

[0027] Throughout this specification, when a part is said to "include" a certain component, this does not mean that other components may be included, but rather that other components may be excluded, unless specifically stated otherwise. Furthermore, the singular forms used herein also include plural forms unless specifically stated otherwise. Furthermore, the expression "at least one of a, b, and / or c" used throughout this specification can encompass "a alone," "b alone," "c alone," "a and b," "a and c," "b and c," or "all of a, b, and c."

[0028] Meanwhile, terms such as "first and / or second" used in this specification may be used to describe various components, but are only used to distinguish one component from another and are not intended to be limited to the components referred to by those terms. For example, without departing from the scope of the present invention, the first component may be referred to as the second component, and the second component may also be referred to as the first component.

[0029] In addition, terms such as “unit”, “module”, etc. described in this specification mean a unit that processes at least one function or operation, which may be implemented by hardware or software, or a combination of hardware and software. In addition, embodiments of the present disclosure in this specification may be represented by functional block configurations and various processing steps. These functional blocks may be implemented by various numbers of hardware or / and software configurations that execute specific functions. For example, embodiments of the present disclosure may employ direct circuit configurations such as memory, processing, logic, look-up tables, etc. that may execute various functions under the control of one or more microprocessors or other control devices.

[0030] In embodiments according to the present disclosure, functions related to artificial intelligence may be implemented through a processor and memory. In this case, the processor may be any one of a general-purpose processor such as a CPU (Center Processing Unit), an AP (Application Processor), a DSP (Digital Signal Processor), a graphics-only processor such as a GPU (Graphics Processing Unit), a VPU (Vision Processing Unit), and an AI-only processor such as an NPU (Neural Network Processing Unit). The processor may process input data according to predefined operation rules or AI models stored in the memory. Alternatively, if the processor is an AI-only processor, the AI-only processor may be designed with a hardware structure specialized for processing a specific AI model. In some embodiments according to the present disclosure, functions related to artificial intelligence may be implemented through a plurality of processors.

[0031] In embodiments of the present disclosure, predefined operating rules or artificial intelligence models may be configured to perform machine learning. Here, "configured to perform machine learning" means that the predefined operating rules or artificial intelligence models are trained using a learning algorithm and a plurality of learning data sets to perform a desired characteristic (or purpose). This learning may be performed within the device itself implementing the artificial intelligence according to the present disclosure, or may be performed through a separate server and / or system.

[0032] Artificial intelligence models can be implemented as neural networks (or artificial neural networks) and operate based on statistical learning algorithms that mimic biological neurons in machine learning and cognitive science. A neural network can refer to a general model in which artificial neurons (nodes) form a network by combining synapses, and through learning, the strength of the synaptic connections changes, thereby achieving problem-solving capabilities. A neural network can be composed of multiple neural network layers. For example, a neural network can include an input layer, a hidden layer, and an output layer. Each of the multiple neural network layers can include at least one node and at least one weight, and can perform neural network operations through operations between the computational results of the previous (precious) layer and the weights. At least one weight of the multiple neural network layers can be optimized based on the learning results of the artificial intelligence model. For example, at least one weight can be updated during the learning process to reduce or minimize the loss or cost values ​​obtained from the artificial intelligence model. Neural networks can infer the desired outcome from arbitrary input.

[0033] The learning methods of artificial intelligence models can be categorized into supervised learning, where input and output data are provided as training data, and the correct answer (output data) corresponding to the problem (input data) is determined, unsupervised learning, where only input data is provided without output data, and the correct answer (output data) corresponding to the problem (input data) is not determined, and reinforcement learning, where a reward is given whenever an action is taken in the current state, and learning progresses in the direction of maximizing this reward. Alternatively, they can be categorized according to the architecture, which is the structure of the learning model.

[0034] In an embodiment of the present disclosure, the artificial intelligence model is a CNN (Convolution Neural Network) such as GoogleNet, AlexNet, VGG Network, etc., R-CNN (Region with Convolution Neural Network), RPN (Region Proposal Network), RNN (Recurrent Neural Network), S-DNN (Stacking-based deep Neural Network), S-SDNN (State-Space Dynamic Neural Network), Deconvolution Network, DBN (Deep Belief Network), RBM (Restrcted Boltzman Machine), Fully Convolutional Network, LSTM (Long Short-Term Memory) Network, Classification Network, Generative Modeling, eXplainable AI, Continual AI, Representation Learning, AI for Material Design, BERT for natural language processing, SP-BERT, MRC / QA, Text Analysis, Dialog System, GPT-3, GPT-4, Visual Analytics for vision processing, Visual Understanding, Video Synthesis, ResNet for data intelligence, Anomaly Detection, Prediction, Time-Series Forecasting, Optimization, At least one of various artificial intelligence structures and algorithms, such as Recommendation, Data Creation, etc., may be used, and the above-described examples are merely listing examples of artificial intelligence structures and algorithms used according to embodiments of the present disclosure, and do not limit the artificial intelligence structures and algorithms used according to embodiments of the present disclosure.

[0035] Hereinafter, various embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In describing the embodiments, descriptions of technical details that are well known in the technical field to which the present invention pertains and are not directly related to the present invention will be omitted. This is to convey the gist of the present invention more clearly without obscuring unnecessary explanation. For the same reason, some components in the accompanying drawings are exaggerated, omitted, or schematically depicted. Furthermore, the size of each component does not entirely reflect the actual size. Throughout this specification, the same reference numerals may refer to the same or corresponding components.

[0036]

[0037] Figure 1 is an environmental diagram of a system that provides a method for predicting urinary tract infection according to one embodiment.

[0038] Referring to FIG. 1, a system (hereinafter, "system") providing a method for predicting urinary tract infections according to one embodiment may include a server (1000) and a user terminal (2000). While FIG. 1 illustrates two components included in the system, the system is not limited thereto, and the system may include additional components. Furthermore, while FIG. 1 illustrates one user terminal (2000) communicating with the server (1000), the system is not limited thereto, and the server (1000) may communicate with multiple user terminals and multiple other servers.

[0039] The server (1000) may be a computing device and may be the overall subject of a urinary tract infection prediction service. The server (1000) may be a computing device including at least one processor. Specifically, the server (1000) may include, but is not limited to, a control processor, an operation processor, a communication module / processor, a storage module / processor, and the like. The server (1000) may be an artificial intelligence server capable of automatically performing tasks through data learning. The server (1000) may provide the urinary tract infection prediction service through a mobile application or website.

[0040] Alternatively, the server (1000) may be a program implemented in a programming language included within the user terminal (2000). Alternatively, the server (1000) may be an edge computing device, an intermediate server between the main server and the terminal.

[0041] The server (1000) can communicate with the user terminal (2000) to transmit and receive data. Specifically, the server (1000) can receive measurement data from the user terminal (2000). In addition, the server (1000) can transmit the results of analyzing the measurement data to the user terminal (2000).

[0042] The user terminal (2000) may be a device of a user using a urinary tract infection prediction service. Specifically, the user terminal (2000) may be a user's mobile device or a server of the user's computer.

[0043] A user can utilize the services provided by the server (1000) via a user terminal (2000). Specifically, the user can take a picture of a test paper via the user terminal (2000) and transmit the taken image to the server (1000). In addition, the user can obtain the degree of urinary tract infection analyzed by the server (1000) and corresponding guidelines based on the taken image.

[0044] Although the system for providing prediction of urinary tract infection according to one embodiment of the present invention has been briefly described above, the connection relationship between each component may be modified and implemented.

[0045] For example, a user can receive a urinary tract infection prediction service by having multiple servers and a user terminal (2000) receiving data from multiple servers. While FIG. 1 illustrates a single server (1000), this is not limited to this, and multiple processors within the server (1000) may exist as multiple servers, each with its own role.

[0046]

[0047] Figure 2 is a flowchart of a method for predicting urinary tract infection according to one embodiment.

[0048] Referring to FIG. 2, a method for predicting urinary tract infection according to one embodiment may include a step of acquiring first measurement data and second measurement data (S100), a step of extracting a first change area and a second change area (S200), a step of extracting an average color value (S300), a step of calculating an average HSL value (S400), a step of correcting the average HSL value (S500), a step of predicting urinary tract infection (S600), and a step of providing a guideline (S700). Although FIG. 2 illustrates that steps S100 to S700 are performed sequentially, the present invention is not limited thereto, and new steps may be added or some steps may be merged and performed simultaneously.

[0049] The step (S100) of acquiring first measurement data and second measurement data may be a step in which the server (1000) receives an image of a test paper taken from a user terminal (2000). Specifically, the server (1000) may acquire first measurement data taken of the test paper at a first point in time and second measurement data taken of the test paper at a second point in time. At this time, the first measurement data and the second measurement data may be data taken of the same test paper stained with a body fluid (e.g., a biological sample, urine, etc.) at different points in time.

[0050] To reduce errors in captured images, the server (1000) may obtain data obtained by photographing the same test paper multiple times from the user terminal (2000). For example, the server (1000) may obtain data obtained by photographing the same test paper approximately five times from the user terminal (2000) (first to fifth measurement data). By obtaining multiple measurement data and calculating an average value thereof, the server (1000) may reduce errors in the shooting environment, camera parameters, etc.

[0051] Step (S200) of extracting the first change area and the second change area may be a step in which the server (1000) extracts the first change area of ​​the first measurement data acquired in step S100 and the second change area of ​​the second measurement data. The server (1000) may extract the first change area and the second change area based on sample data. In this case, the sample data may be an image of a test paper that is not contaminated with bodily fluid.

[0052] Specifically, the sample data may be data acquired through the user terminal (2000) as an image captured at a time point prior to the time points (the first time point and the second time point) at which the first measurement data and the second measurement data were captured. Alternatively, the sample data may be data in which the test paper image is corrected by applying a pre-stored test paper image to the shooting environment (color, brightness, HSL value, etc.) of the first measurement data and the second measurement data.

[0053] The server (1000) can extract the first change area by comparing the sample data and the first measurement data. Specifically, the server (1000) can compare the area corresponding to the test paper of the sample data with the area corresponding to the test paper of the first measurement data. The server (1000) can extract the first change area by comparing the area corresponding to the test paper and extracting pixels whose color has changed in the corresponding area.

[0054] At this time, the server (1000) can determine whether the color of the pixel has changed based on the first reference value. For example, if the color value of the first pixel in the area corresponding to the test paper has changed by more than the first reference value (percentage or numerical value), the server (1000) can determine that the first pixel is included in the first change area. However, if the color value of the first pixel in the area corresponding to the test paper has changed by less than the first reference value, the server (1000) can determine that the first pixel is not included in the first change area. At this time, the first reference value can be set based on the shooting environment (color, brightness, HSL value, etc.) of the first measurement data or the second measurement data.

[0055] Similarly, the server (1000) can extract the second change area by comparing the sample data and the second measurement data. Specifically, the server (1000) can compare the area corresponding to the test paper of the sample data with the area corresponding to the test paper of the second measurement data. The server (1000) can extract the second change area by comparing the area corresponding to the test paper and extracting pixels whose color has changed in the area.

[0056] The step (S300) of extracting the average color value may be a step in which the server (1000) calculates the average color value of the overlap area based on the color value of the first change area and the color value of the second change area. The server (1000) may set pixels included in both the first change area and the second change area as the overlap area. The server (1000) may calculate the average color value based on the color value of the first measurement data and the color value of the second measurement data of the pixels included in the overlap area. This will be described in detail with reference to FIG. 3.

[0057] The step (S400) of calculating the average HSL value may be a step in which the server (1000) calculates the average HSL value based on the average color value calculated in step S300. The server (1000) may calculate the HSL value, which is a color parameter related to color, saturation, and brightness, based on the average color value. The server (1000) may use the calculated average HSL value to determine the degree of urinary tract infection.

[0058] The step (S500) of correcting the average HSL value may be a step in which the server (1000) corrects the average HSL value to suit the shooting environment, depending on whether the first measurement data and the second measurement data were shot indoors or outdoors. This will be described in detail with reference to FIG. 4.

[0059] The step (S600) of predicting urinary tract infection may be a step in which the server (1000) predicts the degree of urinary tract infection through bodily fluids applied to a test strip using various color parameters such as an average color value and a corrected HSL value. This will be described in detail with reference to FIG. 5.

[0060] Step (S700) of providing guidelines may be a step in which the server (1000) transmits a response plan to the user terminal (2000) based on the degree of urinary tract infection predicted in step S600. For example, if the degree of urinary tract infection is divided into grades, the server (1000) may transmit a guideline corresponding to the grade to the user terminal (2000). Also, for example, if the degree of urinary tract infection is calculated as a score, the server (1000) may transmit a guideline corresponding to the score to the user terminal (2000).

[0061] Specifically, the guidelines may include at least one of measurement cycle, hospital information, and dietary information. For example, if the urinary tract infection risk level is level 2 (suspected), the server (1000) may transmit a message recommending weekly diagnosis with a kit and information on foods to avoid to the user terminal (2000). Furthermore, if the urinary tract infection risk level is level 3 (requiring medical treatment), the server (1000) may transmit information on nearby hospitals to the user terminal (2000) based on the location information of the user terminal (2000).

[0062]

[0063] Figure 3 is a flowchart of a method for extracting color values ​​according to one embodiment.

[0064] Referring to FIG. 3, a method for extracting color values ​​according to one embodiment may include a step of extracting an overlapping area (S310), a step of extracting a first color value and a second color value (S320), and a step of calculating an average color value (S330). FIG. 3 illustrates that steps S310 to S330 are performed sequentially, but this is not limited to the sequential execution of steps, and new steps may be added or some steps may be merged and performed simultaneously.

[0065] The step of extracting an overlap area (S310) may be a step in which the server (1000) extracts pixels included in both the first change area and the second change area. Although the first measurement data and the second measurement data are both data obtained by photographing a test paper stained with the same sample, they may include different image results depending on the photographing environment, etc. Accordingly, the server (1000) may extract an overlap area in consideration of pixels included in both the first change area of ​​the first measurement data and the second change area of ​​the second measurement data in order to reduce errors due to the photographing environment, etc.

[0066] The step (S320) of extracting the first color value and the second color value may be a step in which the server (1000) extracts the first color value from the first measurement data of the pixel included in the overlap area and the second color value from the second measurement data. For example, the server (1000) may extract the first color value from the first measurement data of the first pixel included in the overlap area and the second color value from the second measurement data. In addition, the server (1000) may extract the third color value from the first measurement data of the second pixel included in the overlap area and the fourth color value from the second measurement data. The server (1000) may calculate the average of the color values ​​of the pixels of the first overlap area using the average values ​​of the first pixels and the second pixels.

[0067] The step (S330) of calculating an average color value may be a step in which the server (1000) averages the first color value and the second color value extracted in step S320. The server (1000) can reduce errors due to the shooting environment, etc. by averaging the first color value based on the first measurement data and the second color value based on the second measurement data.

[0068]

[0069] Figure 4 is a flowchart of a method for correcting HSL values ​​according to one embodiment.

[0070] Referring to FIG. 4, a method for correcting an HSL value according to one embodiment may include a step (S510) of checking whether measurement data was taken outdoors, a step (S520) of applying an outdoor correction factor if the result of step S510 is positive, and a step (S530) of applying an indoor correction factor if the result of step S510 is negative.

[0071] The step (S510) of confirming whether the measurement data was taken outdoors may include a step in which the server (1000) transmits a question related to indoor / outdoor shooting to the user terminal (2000). For example, the server (1000) may provide the user with a message or interface via the user terminal (2000) to confirm whether the measurement location is indoor or outdoor. The user may provide indoor / outdoor shooting information to the server (1000) by clicking on whether indoor / outdoor shooting was performed or entering information into an input field via the user terminal (2000).

[0072] Alternatively, the step (S510) of determining whether the measurement data was captured outdoors may include a step of determining the shooting location information of the first measurement data and the second measurement data. Specifically, the first measurement data and the second measurement data may include information on the shooting time and shooting location as well as the captured image of the test paper. Accordingly, the server (1000) can determine whether the shooting was performed indoors or outdoors by checking the shooting location information (GPS location information) included in the first measurement data and the second measurement data.

[0073] If the result of step S510 is positive (if the first measurement data and the second measurement data were shot outdoors), the step of applying the outdoor correction factor (S520) may be a step in which the server (1000) adds the outdoor correction factor to the average HSL value. In addition, if the result of step S510 is negative (if the first measurement data and the second measurement data were shot indoors), the step of applying the indoor correction factor (S530) may be a step in which the server (1000) adds the indoor correction factor to the average HSL value.

[0074] The outdoor correction factor and the indoor correction factor may be set based on at least one of the HSL values ​​of the first measurement data and the second measurement data, the shooting location information, the shooting time information, and the HSL information of the sample data. For example, when the shooting time is within 12 o'clock to 16 o'clock, the outdoor correction factor may be -a%, -b%, -c% applied to H, S, and L, respectively. In addition, for example, when the HSL value of the measurement data is less than or equal to a threshold value, the outdoor correction factor or the indoor correction factor may be -d%, -e%, -f% applied to H, S, and L, respectively. At this time, the indoor correction factor and the outdoor correction factor may have the same value and opposite signs, but are not limited thereto.

[0075]

[0076] Figure 5 is a flowchart of a method for calculating the degree of urinary tract infection according to one embodiment.

[0077] Referring to FIG. 5, a method for calculating the degree of urinary tract infection according to one embodiment may include a step of calculating a grayscale value (S610), a step of inputting the grayscale value into an artificial intelligence model (S620), and a step of calculating the degree of urinary tract infection (S630). FIG. 5 illustrates that steps S610 to S630 are performed sequentially, but this is not limited to the sequential execution of steps, and new steps may be added or some steps may be merged and performed simultaneously.

[0078] The step (S610) of calculating a gray scale value may be a step in which the server (1000) calculates a gray scale value, which is one of the color parameters, based on an average color value. Specifically, the server (1000) may calculate a gray scale value by adding values ​​obtained by multiplying the R, G, and B values ​​by 0.299, 0.587, and 0.114, respectively.

[0079] The step (S620) of inputting grayscale values ​​into an artificial intelligence model may be a step in which the server (1000) inputs the grayscale values ​​calculated in step S610 into an artificial intelligence model trained to predict urinary tract infection. Specifically, the artificial intelligence model can calculate the degree of urinary tract infection by determining the nitrite concentration based on the input image or color parameters.

[0080] The step (S630) of calculating the degree of urinary tract infection may be a step in which the server (1000) uses an artificial intelligence model to calculate the degree of urinary tract infection of the body fluid stained on the test paper of the first measurement data and the second measurement data as a score or grade. At this time, the smaller the gray scale value calculated in step S610, the higher the degree (score or grade) of urinary tract infection. For example, the smaller the gray scale value, the higher the score or risk grade related to urinary tract infection.

[0081]

[0082] Figure 6 is a graph illustrating the relationship between the degree of urinary tract infection and gray scale values. The X-axis value of the graph in Figure 6 is proportional to the concentration of nitrite, and the Y-axis value represents the gray scale value. Figure 6 shows the results of multiple experiments on the relationship between the concentration of nitrite and the gray scale value.

[0083] Referring to Figure 6, it can be seen that overall, as the concentration of nitrite increases, the gray scale value decreases. Accordingly, it can be seen that the lower the gray scale value, the higher the severity of urinary tract infection.

[0084]

[0085] Figure 7 is an example drawing for explaining multiple measurement data.

[0086] Referring to FIG. 7, it can be seen that the server (1000) acquires multiple measurement data from the user terminal (2000) and acquires various color parameters based on the measurement data. For example, the server (1000) can acquire five (1st to 5th) measurement data taken at different times from the user terminal (2000). The server (1000) can extract hexadecimal codes, RGB values, grayscale values, etc. from each of the first to fifth measurement data.

[0087]

[0088] Figure 8 is an example drawing for explaining the average color value.

[0089] Referring to FIG. 8, the server (1000) can average the RGB values ​​of the first to fifth measurement data. By averaging the color values ​​of measurement data captured at different times, the server (1000) can reduce errors caused by the shooting environment, etc.

[0090]

[0091] Figure 9 is an example drawing to explain the degree of urinary tract infection.

[0092] Referring to FIG. 9, the server (1000) can set the values ​​of various color parameters that serve as criteria for determining the level of urinary tract infection through learning of an artificial intelligence model. For example, the closer the hexadecimal code is to b39b8f, the closer the RGB values ​​are to 179, 155, and 143, respectively, and the closer the grayscale value is to 160.808, the more the artificial intelligence model can determine the level of urinary tract infection to be level 1. The server (1000) can transmit a guideline corresponding to level 1 urinary tract infection to the user terminal (2000).

[0093] Also, for example, the closer the hexadecimal code is to 54041a, the closer the RGB values ​​are to 84, 4, and 26, respectively, and the closer the grayscale value is to 30.428, the more the artificial intelligence model can determine the degree of urinary tract infection to be level 2. The server (1000) can transmit a guideline corresponding to level 2 urinary tract infection to the user terminal (2000).

[0094] Also, for example, the closer the hexadecimal code is to a31261, the closer the RGB values ​​are to 163, 18, and 97, respectively, and the closer the grayscale value is to 70.361, the more the artificial intelligence model can determine the degree of urinary tract infection as level 3. The server (1000) can transmit a guideline corresponding to the degree of urinary tract infection level 3 to the user terminal (2000).

[0095]

[0096] Figures 10 and 11 are example drawings for explaining an interface implemented on an application.

[0097] Referring to FIG. 10, the server (1000) can transmit an interface including colors that serve as criteria for grades 1, 2, and 3 of urinary tract infection to the user terminal (2000) so that the user can visually check the level before taking a picture of the test paper.

[0098] Referring to FIG. 11, the server (1000) can store data related to previous prediction services so that the user can check the history of using the urinary tract infection prediction service, and can transmit an interface for checking the history to the user terminal (2000).

[0099]

[0100] The method according to the embodiment may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., alone or in combination. The program commands recorded on the medium may be those specially designed and configured for the embodiment or may be those known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands, such as ROMs, RAMs, and flash memories. Examples of the program commands include not only machine language codes generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiment, and vice versa.

[0101] Although the embodiments described above have been described by way of limited examples and drawings, those skilled in the art will appreciate that various modifications and variations can be made based on the above description. For example, appropriate results can still be achieved even if the described techniques are performed in a different order than described, and / or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents.

[0102] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims described below.

Claims

1. A method for predicting urinary tract infection performed by at least one processor, A step of acquiring first measurement data photographed at a first point in time and second measurement data photographed at a second point in time; A step of extracting a first change area of ​​the first measurement data and a second change area of ​​the second measurement data based on sample data; A step of calculating an average color value based on the color value of the first change area and the color value of the second change area; A step of calculating an average HSL value based on the above average color value; a step of correcting the above average HSL value; and A step of predicting urinary tract infection using an artificial intelligence model based on the sample data, the average color value, and the corrected average HSL value. How to predict urinary tract infections.

2. In paragraph 1, The step of calculating the above average color value is: A step of extracting an overlapping area of ​​the first change area and the second change area for the test paper; A step of extracting a first color value for the first measurement data of the overlapping area and a second color value for the second measurement data; and A step of calculating an average color value of the overlapping area based on the first color value and the second color value. How to predict urinary tract infections.

3. In paragraph 2, The step of correcting the above HSL value is: A step of confirming whether the first measurement data and the second measurement data are data taken outdoors or data taken indoors; If the data is shot outdoors, a step of applying an outdoor correction factor to the HSL value; and In case of data shot indoors, a step of applying an indoor correction factor to the HSL value is included. How to predict urinary tract infections.

4. In paragraph 3, The outdoor correction coefficient and the indoor correction coefficient are set based on at least one of the HSL value of the first measurement data and the second measurement data, shooting location information, shooting time information, and HSL information of the sample data. How to predict urinary tract infections.

5. In paragraph 3, The step of checking whether the data was shot outdoors or indoors is as follows: Steps to send questions related to indoor and outdoor shooting; or A step of confirming the shooting location information of the first measurement data and the second measurement data is included. How to predict urinary tract infections.

6. In paragraph 1, The steps for predicting the above urinary tract infection are: A step of calculating a gray scale value based on the above average color value; a step of inputting the grayscale value into the artificial intelligence model; and A step of calculating the degree of urinary tract infection including a score or grade through the above artificial intelligence model is included, The degree of the above urinary tract infection increases as the gray scale value decreases. How to predict urinary tract infections.

7. In paragraph 6, Further comprising a step of providing guidelines based on the degree of the urinary tract infection; The above guidelines include at least one of measurement cycle, hospital information, and dietary information. How to predict urinary tract infections.

8. In paragraph 1, The sample data is data obtained by photographing the test paper at a time point prior to the first time point, or data obtained by correcting a pre-stored test paper image based on the HSL values ​​of the first measurement data and the second measurement data. How to predict urinary tract infections.

9. A non-transitory computer-readable recording medium having recorded thereon a program for executing the urinary tract infection prediction method described in paragraph 1.

Images