Companion animal disease management method and apparatus for performing same

Abstract

The present invention relates to a companion animal disease management method and an apparatus for performing same. The companion animal disease management method may comprise the steps of: receiving, by a companion animal disease management apparatus, companion animal disease management data; generating, by the companion animal disease management apparatus, disease prediction data on the basis of the companion animal disease management data; and generating, by the companion animal disease management apparatus, a health report on the basis of the disease prediction data, wherein the companion animal disease management data includes genetic testing data, companion animal data, and health diary data.

Description

Methods for managing pet diseases and devices for performing such methods

[0001] The present invention relates to a method for managing companion animal diseases and a device for performing such a method. More specifically, the present invention relates to a method for managing companion animal diseases based on genetic testing data and a device for performing such a method.

[0002] Pet tech, a portmanteau of "pet" and "technology," refers to products and services that incorporate cutting-edge information and communication technology (ICT), such as big data and artificial intelligence (AI), into pet-related products to aid in pet care. The scope of pet tech is extremely broad and diverse, ranging from CCTV products that monitor pets left alone at home, to wearable devices that track their locations, to smart toilets that automatically clean cat waste, to services that automatically produce and deliver customized, natural pet food using robots, and even genetically-based pet health management services.

[0003] Digital healthcare for pets refers to pet tech products and services directly related to pet health management. Examples include wearable devices that not only track pet locations but also monitor body temperature, heart rate, respiration rate, and pH levels, as well as genetically-based health management services.

[0004] In particular, pet genetic testing services allow customers to conveniently apply and receive results from home. They can also predict genetic diseases in their pets early, enabling disease prevention through personalized care, including improved diet and exercise. Furthermore, based on the results of pet genetic testing, recommendations for products tailored to the needs of your pet can be made.

[0005] Related technology includes Korean Publication Patent No. 10-2021-0156671.

[0006] The purpose of the present invention is to solve all of the above-described problems.

[0007] In addition, the present invention aims to predict diseases that may occur in companion animals based on genetic test data, companion animal data, health diary data, etc., and to manage companion animals based on the predicted diseases.

[0008] In addition, the present invention aims to manage companion animals by improving the reliability of predictions of the possibility of disease in companion animals based on artificial intelligence through continuous accumulation of data, thereby performing more accurate disease predictions, and adaptively writing a health diary for companion animals in consideration of the predicted disease.

[0009] A representative configuration of the present invention to achieve the above purpose is as follows.

[0010] According to one embodiment of the present invention, a method for managing a pet disease includes a step in which a pet disease management device receives pet disease management data, a step in which the pet disease management device generates disease prediction data based on the pet disease management data, and a step in which the pet disease management device generates a health report based on the disease prediction data, wherein the pet disease management data may include genetic test data, pet data, and health diary data.

[0011] Meanwhile, the step of generating a health report may include a step of the pet disease management device receiving health diary data and a step of the pet disease management device analyzing the health diary data based on the disease prediction data to generate the health report.

[0012] In addition, the disease prediction data is generated based on a plurality of prediction modules, and the plurality of prediction modules include a first prediction module and a second prediction module, and the first prediction module generates the disease prediction data based on a non-learning-based, preset veterinary knowledge-based algorithm, and the second prediction module can generate the disease prediction data through learning-based artificial intelligence.

[0013] According to another embodiment of the present invention, a companion animal disease management device for managing companion animal diseases may include a data input unit configured to receive companion animal disease management data, a disease prediction unit configured to generate disease prediction data based on the companion animal disease management data, and a health report generation unit configured to generate a health report based on the disease prediction data, wherein the companion animal disease management data may include genetic test data, companion animal data, and health diary data.

[0014] Meanwhile, the companion animal disease management device is implemented to receive health diary data, and the companion animal disease management device can analyze the health diary data based on the disease prediction data to generate the health report.

[0015] In addition, the disease prediction data is generated based on a plurality of prediction modules, and the plurality of prediction modules include a first prediction module and a second prediction module, and the first prediction module generates the disease prediction data based on a non-learning-based, preset veterinary knowledge-based algorithm, and the second prediction module can generate the disease prediction data through learning-based artificial intelligence.

[0016] According to the present invention, diseases that may occur in companion animals can be predicted based on genetic test data, companion animal data, health diary data, etc., and companion animals can be managed based on the predicted diseases.

[0017] In addition, according to the present invention, the reliability of prediction of the possibility of disease in companion animals based on artificial intelligence is improved as data continues to accumulate, enabling more accurate disease prediction, and the companion animal's disease can be effectively managed by adaptively writing a health diary in consideration of the predicted disease in the companion animal.

[0018] Figure 1 is a conceptual diagram illustrating a companion animal disease management device according to an embodiment of the present invention.

[0019] Figure 2 is a conceptual diagram illustrating the operation of a disease prediction unit according to an embodiment of the present invention.

[0020] Figure 3 is a conceptual diagram illustrating the operation of a disease prediction model according to an embodiment of the present invention.

[0021] Figure 4 is a conceptual diagram showing the operation of a health diary analysis unit according to an embodiment of the present invention.

[0022] FIG. 5 is a conceptual diagram illustrating a specific method for generating a health diary report based on health diary analysis basic information according to an embodiment of the present invention.

[0023] FIG. 6 is a conceptual diagram illustrating a method for providing data for planning an insurance product for companion animals according to an embodiment of the present invention.

[0024] FIG. 7 is a conceptual diagram illustrating a symptom classification method based on a decision tree according to an embodiment of the present invention.

[0025] FIG. 8 is a conceptual diagram illustrating a user interface that adaptively changes according to the possibility of a pet's illness according to an embodiment of the present invention.

[0026] The following detailed description of the present invention refers to the accompanying drawings, which illustrate specific embodiments in which the present invention may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the present invention. It should be understood that the various embodiments of the present invention, while different from each other, are not necessarily mutually exclusive. For example, specific shapes, structures, and characteristics described herein may be modified and implemented from one embodiment to another without departing from the spirit and scope of the present invention. Furthermore, it should be understood that the positions or arrangements of individual components within each embodiment may also be modified without departing from the spirit and scope of the present invention. Accordingly, the following detailed description is not to be taken in a limiting sense, and the scope of the present invention is to be construed to encompass the scope of the claims and all equivalents thereof. Like reference numerals in the drawings represent the same or similar elements throughout the several aspects.

[0027] Hereinafter, various preferred embodiments of the present invention will be described in detail with reference to the attached drawings so that a person having ordinary skill in the art to which the present invention pertains can easily practice the present invention.

[0028] Hereinafter, the term “gene” is used for convenience of explanation, but it can be interpreted to mean including genetic mutations based on genes.

[0029]

[0030] Figure 1 is a conceptual diagram illustrating a companion animal disease management device according to an embodiment of the present invention.

[0031] In Fig. 1, a pet disease management device for managing a pet disease based on genetic test data is disclosed.

[0032] Referring to FIG. 1, the pet disease management device may include a data input unit (100), a disease prediction unit (110), a health diary analysis unit (120), a health report generation unit (130), an app setting unit (140), a processor (150), etc.

[0033] The data input unit (100) may be implemented to receive data for disease management of companion animals. The data input unit (100) may include genetic test data, companion animal data, health diary data, etc. Data for disease management of companion animals, such as genetic test data, companion animal data, and health diary data, may be expressed as "companion animal disease management data." The genetic test data may include genetic test results for the companion animal. For example, the genetic test results for the companion animal may be generated through genetic testing based on a genetic test kit and may include results regarding the possibility of genetically based diseases that the companion animal may have.

[0034] Pet data may include various information about your pet, such as pet type, pet age, and pet gender.

[0035] Health diary data can be information recorded about a pet's health. For example, health diary data can include information about a pet's urine and feces, dietary habits, activity levels, and medications taken.

[0036] A disease prediction unit (110) may be implemented to predict diseases. The disease prediction unit (110) may be implemented to predict diseases in companion animals based on companion animal disease management data (e.g., genetic testing data, companion animal data). The disease prediction unit (110) generates disease prediction data, and companion animal disease management data based on the disease prediction data may be transmitted.

[0037] The health diary analysis unit (120) may be implemented to analyze health diaries based on genetic testing data and pet data. Alternatively, the health diary analysis unit (120) may generate health diary analysis result data based on disease prediction data generated by the disease prediction unit.

[0038] A health report generation unit (130) may be implemented to generate a health report based on the analysis results of a health diary. The health report generation unit (130) may generate health diary analysis result data based on health diary analysis basic data and generate a health report based on this.

[0039] The app settings section (140) may be implemented to configure the app. The app settings section (140) may be implemented to change the user's app settings depending on the user's pet. For example, the app settings section (140) may change the app's UX / UI depending on the pet's illness. Alternatively, the app settings section (140) may be configured to separately request information necessary for writing a health diary when writing a health diary, depending on the pet's illness, and to separately request information to be included in the health report through the health diary.

[0040] The processor (150) can be implemented to control the operations of the data input unit (100), disease prediction unit (110), health diary analysis unit (120), health report generation unit (130), and app setting unit (140).

[0041] A method for managing a pet disease may include a step in which a pet disease management device receives pet disease management data, a step in which the pet disease management device generates disease prediction data based on the pet disease management data, and a step in which the pet disease management device generates a health report based on the disease prediction data. The method is characterized in that the pet disease management data includes genetic test data, pet data, and health diary data.

[0042] Additionally, the pet disease management method may include a step in which a pet disease management device receives health diary data and a step in which the pet disease management device analyzes the health diary data based on disease prediction data to generate the health report.

[0043]

[0044] Figure 2 is a conceptual diagram illustrating the operation of a disease prediction unit according to an embodiment of the present invention.

[0045] In Fig. 2, the operation of a disease prediction unit for generating predicted disease data based on genetic test data and companion animal data is disclosed.

[0046] Referring to FIG. 2, the disease prediction unit can receive genetic test data and companion animal data and generate disease prediction data based on a disease prediction model.

[0047] The disease prediction unit may include two prediction modules (a first prediction module (210) and a second prediction module (220)). The first prediction module (210) is a module for predicting diseases when learning data is insufficient to train an artificial intelligence model. The second prediction module (220) is a module for predicting diseases based on an artificial intelligence model when learning data is sufficient for training the artificial intelligence model. In other words, the first prediction module (210) may generate disease prediction data based on a preset veterinary knowledge-based algorithm based on a non-learning basis, and the second prediction module (220) may generate disease prediction data through learning-based artificial intelligence.

[0048] The disease prediction unit may generate disease prediction data based on the first prediction module (210) until the prediction performance of the second prediction module (220) becomes higher than that of the first prediction module (210). Conversely, when the prediction performance of the second prediction module (220) becomes higher than that of the first prediction module (210), disease prediction data may be generated based on the second prediction module (220) instead of the first prediction module (210).

[0049] The first prediction module (210) may be a module that predicts diseases of companion animals based on existing gene-based disease prediction algorithms. For example, the first prediction module (210) may have information on the probability of occurrence of diseases by age group of companion animals based on gene A, based on veterinary knowledge, if a companion animal of type x has gene A. Such disease prediction algorithms may be applied to the first prediction module (210).

[0050] The second prediction module (220) is an artificial intelligence-based module that can generate predicted disease data by learning about diseases that may occur based on gene A when a companion animal of type x has gene A.

[0051] The learning data for the second prediction module (220) can be generated in various ways. Examples of learning data include veterinarian diagnostic records, health diaries recorded by pet owners, and data collected based on a community of pets with the A gene.

[0052] In order to compare the performance of the first prediction module (210) and the second prediction module (220), a comparison between predicted disease data can be made. First, it can be determined whether the second predicted disease data generated by the second prediction module (220) is identical to the first predicted disease data generated through the first prediction module (210) by a threshold percentage or more. If the first predicted disease data and the second predicted disease data are identical by a threshold percentage or more, a second determination can be made as to which predicted disease data has higher accuracy between the first predicted disease data and the second predicted disease data for data in which there is a difference (hereinafter, difference data) between the first predicted disease data and the second predicted disease data.

[0053] Accuracy assessments for differential data can be based on data about actual diseases. For example, suppose a prediction of the onset time of disease x in a companion animal k with gene A is provided as predicted disease data.

[0054] In such cases, a prediction module that generates more accurate predicted disease data for the time of invention based on actual companion animal disease outbreak data may be judged to have higher accuracy.

[0055] In this manner, a comparison is continuously made between the first prediction module (210) and the second prediction module (220), and after a certain point in time, if the performance of the second prediction module (220) has a higher value than the performance of the first prediction module (210), the second prediction module (220) can replace the first prediction module (210).

[0056] Disease prediction models can be created for each disease, and the information about genes input into the disease prediction model can change based on changes in the correlation between genes and diseases. Furthermore, the correlation between genes and diseases can change based on changes in disease prediction probabilities based on various gene groups, and information about genes with high correlation with diseases can be input into the disease prediction model.

[0057]

[0058] Figure 3 is a conceptual diagram illustrating the operation of a disease prediction model according to an embodiment of the present invention.

[0059] Figure 3 is a conceptual diagram showing changes in data input to a disease prediction model and the creation of various artificial intelligence prediction models according to changes in the data.

[0060] Referring to FIG. 3, a plurality of candidate disease prediction models (320) are trained through a plurality of input data groups as input data to generate disease prediction data, and based on the prediction accuracy of the disease prediction data, the candidate disease prediction model (320) with the highest prediction accuracy can be used as a target disease prediction model (300) for current disease prediction.

[0061] Multiple different input data groups for training the candidate disease prediction model (320) may include combined genetic test data preprocessed and combined based on genetic test data, and combined companion animal data preprocessed and combined based on companion animal data. Furthermore, the input data group may include companion animal disease data containing information about diseases actually present in companion animals.

[0062] For example, if genetic testing data includes testing data for gene A, gene B, gene C, and gene D, various combinations of gene A, gene B, gene C, and gene D can generate combined genetic testing data.

[0063] If the pet data includes data on pet age, pet gender, pet breed, and pet lifestyle, various combinations of pet age, pet gender, pet breed, and pet lifestyle can be used to create composite pet data.

[0064] Predictions based on combined genetic testing data and combined pet data could enable predictions of various diseases based on various genetic combinations that have not previously been associated with specific diseases and pet characteristics that have not previously been associated with specific diseases.

[0065] Based on the disease prediction data output from each of the plurality of candidate disease prediction models (320) learned based on these various input data groups and the disease prediction data output from the target disease prediction model (300), the disease prediction performance between the candidate disease prediction model (320) and the target disease prediction model (320) can be compared.

[0066] In the present invention, the disease prediction model with the highest performance among multiple candidate disease prediction models (300) may be used for disease prediction as a target candidate disease prediction model (300), and the remaining disease prediction models may operate as candidate disease prediction models (320). If the performance of a specific candidate disease prediction model is later higher than that of the target disease prediction model (300), the specific candidate disease prediction model may operate as a new target disease prediction model (300).

[0067]

[0068] Figure 4 is a conceptual diagram showing the operation of a health diary analysis unit according to an embodiment of the present invention.

[0069] In Fig. 4, the operation of the health diary analysis unit for analyzing the health diary by considering the possibility of disease in the companion animal is initiated.

[0070] Referring to FIG. 4, the health diary analysis unit can receive genetic test data, pet data, and / or pet disease data.

[0071] The health diary analysis unit can determine target words (400) and target sentences (420) based on genetic test data, pet data, and / or pet disease data. The target words (400) and target sentences (420) may include words and sentences that serve as targets for performing health diary analysis on the pet.

[0072] For example, if a pet has a gene related to obesity, the target word (400) and target sentence (420) may be set as words and sentences that can extract information about dietary habits, amount of exercise, etc. As another example, if a pet has a gene related to patellar dislocation, the target word (400) and target sentence (420) may be set as words and sentences that can extract information about behavioral habits related to patellar dislocation.

[0073] Based on target words (400) and target sentences (420), health diary data can be analyzed to generate health diary analysis basic information (440). The health diary analysis basic information (440) can be the basic information for generating health diary analysis results. For example, based on target words (400) and target sentences (420) set for a pet with an obesity-related gene, target sentences related to obesity, such as "the amount of food eaten has increased significantly compared to before" and "the pet constantly acts as if it is hungry," can be extracted as health diary analysis basic information (440).

[0074] That is, by excluding words and sentences with low relevance in the health diary, information for analyzing the health of the pet in the health diary can be determined as basic information for health diary analysis (440).

[0075] A health diary analysis result (460) may be generated based on the health diary analysis basic information (440). The health diary analysis result (460) may be an analysis result that can be provided to a user based on the health diary analysis basic information (440). For example, analysis results based on various criteria, such as analysis data on the severity of a disease related to a specific gene or analysis data on the improvement of a pet's health condition, may be provided to the user as the health diary analysis result (460).

[0076]

[0077] FIG. 5 is a conceptual diagram illustrating a specific method for generating a health diary report based on health diary analysis basic information according to an embodiment of the present invention.

[0078] Referring to FIG. 5, a method for generating a health report (540) based on health diary analysis basic information (500) is disclosed. Different analysis basic information groups (520) can be set based on the health diary analysis basic information (500), and a health report (540) can be generated based on the different analysis basic information groups (520).

[0079] For example, different analysis baseline information groups can generate different health reports for different purposes. Based on analysis baseline information group 1, Health Report 1 can be generated for the pet owner. Based on analysis baseline information group 2, Health Report 2 can be generated for the veterinarian diagnosing the pet. Based on analysis baseline information group 3, Health Report 3 can be generated for the pet's insurance company.

[0080] In order to generate a health report (540), analysis can be performed based on health diary analysis basic information (500) generated over time.

[0081] The health diary analysis basic information (500) may include first type health diary analysis basic information (550) that requires time series analysis and second type health diary analysis basic information (560) that does not require time series analysis.

[0082] The first type health diary analysis basic information (550) may define an analysis time series for each piece of information. The first type health diary analysis basic information (550) may be included in an analysis basic information group according to the analysis time series, and may be utilized to generate a health report according to the analysis time series.

[0083] The second type health diary analysis basic information (560) does not have a separate time series defined, and the information closest to the time point for report generation is included in the analysis basic information group and can be utilized for health report generation.

[0084] The analysis time series of the first type health diary analysis basic information (550) may be defined as a default analysis time series (570) based on the period required for diagnosis. For example, if a pet has symptoms such as anorexia, the period required for veterinary analysis for anorexia may be defined as the default analysis time series (570). The default analysis time series (570) may be adjusted to an adjusted analysis time series (580) based on factors such as the user's input cycle of health diary analysis basic information, pet data, and whether the symptoms are mixed with other symptoms.

[0085] For example, the longer the cycle in which the user inputs the health diary analysis basic information (500), the longer the adjusted analysis time series (580) can be set to be compared to the default analysis time series (570). Based on the companion animal data, if the companion animal is relatively older or has other existing diseases based on the companion animal's type, age, sex, existing diseases, etc., the adjusted analysis time series can be set to be compared to the default analysis time series. In addition, if symptoms that can be analyzed as other diseases exist in a mixed manner by considering whether mixed symptoms with other symptoms exist, the adjusted analysis time series (580) can be set to be relatively longer than the default analysis time series (570).

[0086] The default analysis time series (570) and the adjusted analysis time series (580) may be set differently depending on the type of report. In the case of a health report 3 provided to provide coverage for an insurance product, the default analysis time series (570) and the adjusted analysis time series (580) may be set relatively long. In the case of a health report 1 delivered to a user who is the owner of a pet, the default analysis time series (570) and the adjusted analysis time series (580) may be set relatively short.

[0087]

[0088] FIG. 6 is a conceptual diagram illustrating a method for providing data for planning an insurance product for companion animals according to an embodiment of the present invention.

[0089] In FIG. 6, a method for providing data for an insurance company to develop an insurance product for pets is disclosed.

[0090] Referring to Figure 6, the companion animal disease management device can transmit statistical data on diseases suffered by multiple companion animals to the insurance company's server. This statistical data on diseases suffered by multiple companion animals can be referred to as "insurance product creation basic data."

[0091] The basic data for creating insurance products is transmitted to the insurance company server, and the insurance company server can create insurance products based on the basic data for creating insurance products.

[0092] To create basic data for insurance product creation, data on pets that have already developed a disease and data on pets that have not developed a disease but are predicted to develop a disease based on their genes can be utilized.

[0093] Data on pets that have already developed a disease can be expressed as the term "first type insurance product creation basic data (610)," and data on pets that have not developed a disease but are predicted to develop a disease based on genes can be expressed as the term "second type insurance product creation basic data (620).

[0094] The Type 1 insurance product creation basic data (610) may include pet data, genetic test data, disease onset time data, and disease type data. The Type 1 insurance product creation basic data may be grouped for insurance product creation and created as a Type 1 insurance product creation basic data group.

[0095] The first type insurance product creation basic data group can be divided into the first type insurance product creation basic data group 1 (620), which is generated without considering the correlation between genetic test data and a disease, and the first type insurance product creation basic data group 2 (630), which is generated considering the correlation between genetic test data and a disease. The data of the first type insurance product creation basic data group 2 (630) is the data that should be given the highest weight and considered when designing an insurance product. The data of the first type insurance product creation basic data group 1 (620) is data created to design an insurance product by exploring the correlation between unknown genetic test data and a specific disease when designing an insurance product.

[0096] (1) Group 1 (620) of basic data for creating Type 1 insurance products

[0097] The first type insurance product creation basic data (610) can be embedded into four vectors by vectorizing companion animal data, genetic test data, disease occurrence time data, and disease type data in individual dimensions. The first type insurance product creation basic data (610) changed into a four-dimensional vector {vector 1, vector 2, vector 3, vector 4} can be clustered on a four-dimensional plane and provided to the insurance company server as the first type insurance product creation basic data group 1 (620) as a cluster including data having a specific tendency. The first type insurance product creation basic data group 1 (620) can be a data group having identical / similar companion animal data characteristics, identical / similar genetic test data, identical / similar disease occurrence time, and identical / similar disease type.

[0098] (2) Group 2 (630) of basic data for creating Type 1 insurance products

[0099] According to an embodiment of the present invention, a method for generating a simplified Type 1 insurance product creation basic data group may be used for diseases for which the correlation between genetic test data and disease type data is already known. Genetic test data and disease type data are fixed, and based on the fixed genetic test data and disease type data, only companion animal data and disease onset time data are transformed into two-dimensional vectors, clustered, and provided to the insurance company server as Type 1 insurance product creation basic data group 2 (630).

[0100] (3) Type 2 insurance product creation basic data group (660)

[0101] The basic data (650) for creating a second type of insurance product may include pet data, genetic test data, disease prediction data, and disease-specific prediction reliability data.

[0102] The second type insurance product creation basic data (650) can be implemented to create an insurance product based on disease prediction data. The second type insurance product creation basic data (650) can be used to design an insurance product based on predicted disease data and information regarding the timing of predicted disease occurrence included in the disease prediction data.

[0103] Companion animal data, genetic test data, and disease prediction data can be embedded into a three-dimensional vector, and the three-dimensional vectors can be clustered to form a plurality of second type insurance product creation basic data groups (660). Each of the plurality of second type insurance product creation basic data groups (660) may be a data group for companion animals predicted to have the same / similar disease. Among the plurality of second type insurance product creation basic data groups (660), only some of the second type insurance product creation basic data groups (660) may be provided to the insurance company server in consideration of the reliability of disease prediction. Based on the disease-specific prediction reliability data, if the reliability of prediction using only genetic data for a specific disease is below a threshold value, the second type insurance product creation basic data group (660) corresponding to the disease may not be provided to the insurance company server.

[0104]

[0105] FIG. 7 is a conceptual diagram illustrating a symptom classification method based on a decision tree according to an embodiment of the present invention.

[0106] In Fig. 7, a method for creating and expanding a decision tree for judging symptoms in more detail for each disease is disclosed.

[0107]

[0108] Referring to Figure 7, a decision tree can be used to more specifically classify symptoms associated with genes. For example, even in the case of anorexia, a variety of anorexia symptoms can occur. Anorexia can be accompanied by a variety of symptoms, including simple anorexia, anorexia that restricts eating to a specific food, anorexia accompanied by lethargy, and anorexia accompanied by diarrhea and vomiting. By further specifying the symptoms of a companion animal, a decision tree can enable more specific reports on the symptoms of genetically related diseases, which can then be utilized to improve the predictive performance of genetically related diseases.

[0109] A decision tree can be created through a symptom-based level differentiation step and a genetic data-based symptom linkage step.

[0110] (1) Symptom-based level differentiation stage (S700)

[0111] The decision tree can be initially created at the first level, based on symptoms. Level 1 can be the most comprehensive symptom type. For example, Level 1 can be defined as the most comprehensive term for each symptom, such as "loss of appetite," "cough," or "movement disorder."

[0112] The n levels after Level 1 may be defined by the companion animal disease management device based on clinical data, or may be generated based on health diary data entered by users.

[0113] For example, if anorexia is the first level, it can be defined as simple anorexia, anorexia that does not eat only a specific food, anorexia that occurs with lethargy, anorexia that occurs with diarrhea and vomiting, etc. on the nth level based on veterinary clinical data. Alternatively, if a new symptom of anorexia is recorded by users at a threshold rate or higher based on the symptoms of anorexia recorded by users, it can be added to the nth level. The threshold rate can be set differently for each symptom, and the more common the symptom, the higher the threshold rate can be set.

[0114] In this way, a decision tree can be generated by segmenting it into n levels, and a specific level or final level of the decision tree can be used to determine the pet's symptoms. Symptoms located at a specific level can be referred to as "specific level symptoms" (e.g., "third level symptoms"), and symptoms located at the final level of the decision tree can be referred to as "final level symptoms."

[0115] (2) Genetic data-based symptom linkage step (S720)

[0116] The genetic data-based symptom linking step (S720) may be a step for linking genetic data with symptoms located in a decision tree divided into n levels. For example, if heart disease exists due to genetic factors, anorexia accompanied by lethargy due to heart disease may occur. Therefore, genetic data related to heart disease may be linked to anorexia accompanied by lethargy in the decision tree. In this manner, specific or final-level symptoms can be designated as genetically linked symptoms (750, 760).

[0117] Gene-linked symptoms (750, 760) can be determined based on veterinary clinical data and health diary data of companion animals with specific genes. Symptoms identified as being linked to specific genes based on veterinary clinical data can be determined as gene-linked symptoms (750, 760). In addition, if a specific symptom occurs at a threshold rate or higher based on genetic test data and health diary data of companion animals with specific genes, the symptom can also be determined as a gene-linked symptom (750, 760). The threshold rate for determining a gene-linked symptom can be set differently for each symptom and gene.

[0118] The decision tree generated in this manner can be reflected in a health diary, allowing users to enter symptoms without text input. For example, if the user selects the symptom of anorexia, the final level of symptoms can be presented as options, and the user can select the symptom most closely resembling their pet's symptoms, thereby creating a health diary. Furthermore, the health diary can be generated as a decision tree, and predictions can be made based on the decision tree.

[0119]

[0120] FIG. 8 is a conceptual diagram illustrating a user interface that adaptively changes according to the possibility of a pet's illness according to an embodiment of the present invention.

[0121] In Fig. 8, a method for managing the health of a pet through a pet health management app is disclosed based on the possibility of the pet having a disease.

[0122] Referring to FIG. 8, a pet health management service can be provided on the pet health management app based on the current disease (800) that the pet already has and the predicted disease (820) predicted based on the pet's genetic test data.

[0123] A user interface for managing the pet's current disease (800) and predicted disease (820) may be provided on the pet health management app.

[0124] On the user interface, priorities for the current disease (800) and the predicted disease (820) are set, and the user interface can be changed on the pet health management app so that the current disease (800) and the predicted disease (820) can be managed in different formats (e.g., size, font, location) according to the priorities. Hereinafter, in the embodiment of the present invention, for the convenience of explanation, a method for performing management of the current disease (800) and the predicted disease (820) through a listing order on the user interface is disclosed, but the user interface design for managing pet diseases according to such priorities can be implemented in various ways.

[0125] The current disease (800) may be set to have a higher priority than the predicted disease (820).

[0126] Additionally, among the current diseases, diseases with a relatively high severity, such as diseases that are relatively life-threatening, can be set to have a relatively high priority.

[0127] In the case of a predicted disease (820), the probability of occurrence and the time of occurrence of the predicted disease (820) may be considered, and the higher the probability of occurrence and the earliest time of occurrence as of the present time, the higher the priority may be set. Based on the probability of occurrence and the time of occurrence of the predicted disease (820), scoring of the predicted disease (820) may be performed to determine a disease prediction score. A predicted disease with a relatively high disease prediction score may be set to a relatively higher priority and positioned on the user interface. The higher the severity of the predicted disease (820), the higher the weight given to the probability of occurrence, and the priority may also be adjusted.

[0128] When a current disease (800) and a predicted disease (820) are determined, health diary information for managing the current disease (800) and the predicted disease (820) above a certain priority can be requested from the user. To request health diary information, a user interface corresponding to a specific level of symptom or a final level of symptom in the decision tree is adaptively generated and provided to the user, allowing the user to record more accurate symptom information in the health diary without separate text input.

[0129]

[0130] The embodiments of the present invention described above may be implemented in the form of program commands that can be executed through various computer components and recorded on a computer-readable recording medium. The computer-readable recording medium may include program commands, data files, data structures, etc., either singly or in combination. The program commands recorded on the computer-readable recording medium may be specially designed and configured for the present invention or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specifically configured to store and execute program commands, such as ROMs, RAMs, and flash memories. Examples of 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. Hardware devices may be changed into one or more software modules to perform processing according to the present invention, and vice versa.

[0131] Although the present invention has been described above with specific details such as specific components and limited examples and drawings, these are provided only to help a more general understanding of the present invention, and the present invention is not limited to the above examples, and those with ordinary knowledge in the technical field to which the present invention pertains can make various modifications and changes based on this description.

[0132] Therefore, the idea of ​​the present invention should not be limited to the embodiments described above, and not only the scope of the patent claims described below but also all scopes equivalent to or equivalently modified from the scope of the patent claims are considered to fall within the scope of the idea of ​​the present invention.

Claims

1. How to manage pet diseases: Steps for receiving pet disease management data by a pet disease management device The step of generating disease prediction data based on the pet disease management data by the companion animal disease management device; and The above pet disease management device comprises a step of generating a health report based on the above disease prediction data, A method characterized in that the companion animal disease management data includes genetic test data, companion animal data, and health diary data.

2. In the first paragraph, the step of generating the health report comprises: The step of the above pet disease management device receiving health diary data; and A method characterized in that the pet disease management device comprises a step of analyzing the health diary data based on the disease prediction data and generating the health report.

3. In paragraph 2, The above disease prediction data is generated based on multiple prediction modules, The above plurality of prediction modules include a first prediction module and a second prediction module, The above first prediction module generates the disease prediction data based on a non-learning-based, preset veterinary knowledge-based algorithm, A method characterized in that the second prediction module generates the disease prediction data through learning-based artificial intelligence.

4. The companion animal disease management device that performs companion animal disease management is: A data input unit implemented to receive companion animal disease management data; A disease prediction unit implemented to generate disease prediction data based on the above companion animal disease management data; and Including a health report generation unit implemented to generate a health report based on the above disease prediction data, A pet disease management device characterized in that the pet disease management data includes genetic test data, pet data, and health diary data.

5. In paragraph 4, The above companion animal disease management device is implemented to receive health diary data, A pet disease management device characterized in that the pet disease management device is implemented to generate the health report by analyzing the health diary data based on the disease prediction data.

6. In paragraph 5, The above disease prediction data is generated based on multiple prediction modules, The above plurality of prediction modules include a first prediction module and a second prediction module, The above first prediction module generates the disease prediction data based on a non-learning-based, preset veterinary knowledge-based algorithm, A companion animal disease management device characterized in that the second prediction module generates the disease prediction data through learning-based artificial intelligence.

Images