Operation method of electronic device, computing device, and system

Abstract

To provide a technique for reflecting a state of a pet.SOLUTION: According to an aspect of the present disclosure, an operation method of an electronic device can be provided, the method including: operation of acquiring, by at least one processor included in the electronic device, input data including quantitative data according to a result of a PCR test and additional information related to health or disease of a pet; operation of invoking a first artificial intelligence model for calculating a health score; and operation of inputting the input data to the first artificial intelligence model and calculating a health score indicating a health state of the pet.SELECTED DRAWING: Figure 13

Description

[Technical field]

[0001] The present invention relates to an electronic device that includes an artificial intelligence model, and more particularly to an electronic device that uses an artificial intelligence model to predict the health and disease states of companion animals (pets) and recommend suitable foods depending on the pet's health and disease. [Background technology]

[0002] As the pet business grows rapidly, the size of the pet healthcare market is also expanding rapidly.

[0003] In particular, many of the illnesses that pets suffer from are caused by infectious diseases. Pet illnesses are caused by infection with pathogens (e.g., germs, bacteria, microorganisms, etc.). However, the biggest problem in treating illnesses in pets is that pets cannot complain about pain. In the end, the reality is that treatment for pet illnesses begins a long time after the onset of symptoms.

[0004] Recently, the cost of keeping pets has been increasing rapidly. A major factor is the cost of pet treatment, which accounts for more than half of the total cost of keeping pets. In this situation, there is a need for technology that can closely monitor the current condition of pets and predict infectious diseases in advance. Summary of the Invention [Problem to be solved by the invention]

[0005] An object of the present invention is to provide a technique for understanding the health condition, etc., of a pet.

[0006] On the other hand, the problems that the present invention aims to solve are not limited to the problems mentioned above, and problems not mentioned can be clearly understood by a person having ordinary skill in the art to which the inventions included in the present invention belong from this specification and the attached drawings. [Means for solving the problem]

[0007] The present invention focuses on the problem that disease prediction has been carried out in a very non-quantitative manner up until now.

[0008] Therefore, the present invention utilizes data obtained by qualitatively and quantitatively analyzing the genes of pathogens carried by pets to indirectly predict the current health condition and diseases of pets, and then uses preventive solutions for them.

[0009] One aspect of the invention is to analyze PCR test results to determine the disease status of pets.

[0010] Another aspect of the present invention is to accurately assess the health of a pet based on information about the pet.

[0011] A further aspect of the present invention is to recommend suitable foods reflective of the pet's health and disease state.

[0012] According to one embodiment of the present invention, a method for operating an electronic device can be provided, the method including the following operations: acquiring quantitative data including a plurality of quantitative values ​​corresponding to each of a plurality of pathogens in accordance with PCR test results by at least one processor included in the electronic device; determining at least one predicted target disease based on the plurality of quantitative values; preprocessing the quantitative data corresponding to the predicted target disease using a first preprocessing algorithm corresponding to the determined predicted target disease; and inputting the preprocessed quantitative data into a first artificial intelligence model corresponding to the determined predicted target disease, and outputting a disease occurrence probability corresponding to the predicted target disease.

[0013] In addition, according to another embodiment of the present invention, a method for operating an electronic device can be provided, the method including: acquiring, by at least one processor included in an electronic device, input data including quantitative data from PCR test results and additional information related to the pet's health or disease; loading a first artificial intelligence model for calculating a health score; and inputting the input data into the first artificial intelligence model to calculate a health score indicating the pet's health condition.

[0014] According to a further embodiment of the present invention, a method for operating an electronic device can be provided, the method including the steps of: acquiring, by at least one processor included in the electronic device, a first dataset indicating a health or disease state of the pet; acquiring improvement information of the pet based on the first dataset (the improvement information includes information on improved functions indicating functions requiring improvement, and information on improved nutrients indicating nutrients corresponding to the functions requiring improvement); acquiring food information from a food database (the food information includes nutrient content information); comparing the improvement information and the food information to determine at least one food that matches the improvement information; selecting at least one recommended food based on the determined at least one food; and providing the at least one recommended food through a user interface.

[0015] The solutions to the problems according to the various embodiments are not limited to the solutions described above, and solutions not mentioned can be clearly understood by a person having ordinary skill in the art to which the present invention pertains from this specification and the accompanying drawings. Effect of the Invention

[0016] It is possible to obtain technology that can grasp the health condition of a pet.

[0017] The effects of the embodiments included in the present invention are not limited to the effects described above, and unmentioned solutions can be clearly understood by a person having ordinary skill in the art to which the present invention pertains from this specification and the accompanying drawings. [Brief description of the drawings]

[0018] [Figure 1] FIG. 1 illustrates a pet diagnostic system according to various embodiments. [Diagram 2] 1A to 1C are diagrams illustrating configurations of electronic devices according to various embodiments. [Diagram 3] FIG. 1 is a diagram illustrating an electronic device including an artificial intelligence model trained based on training data related to a pet, according to various embodiments. [Figure 4] FIG. 1 shows an example of PCR quantitative data. [Diagram 5] FIG. 1 illustrates how an electronic device may use an artificial intelligence model to obtain output data based on input data, according to various embodiments. [Figure 6] FIG. 1 illustrates how an electronic device according to various embodiments predicts a pet's likelihood of developing a disease based on PCR data. [Figure 7] FIG. 1 shows the correlation between pathogenic microorganisms and diseases. [Figure 8] 1 is a flow chart illustrating an embodiment in which an electronic device obtains a disease score in accordance with various embodiments. [Figure 9] FIG. 1 illustrates a specific method by which an electronic device determines a predicted target disease according to various embodiments. [Figure 10] 10 is a flow chart illustrating another embodiment in which an electronic device obtains a disease score in accordance with various embodiments. [Figure 11] 10 is a flow chart illustrating yet another embodiment in which an electronic device obtains a disease score in accordance with various embodiments. [Figure 12] FIG. 1 illustrates how an electronic device calculates a health score according to various embodiments. [Figure 13]1 is a flow chart illustrating a method for an electronic device to obtain a health score according to various embodiments. [Figure 14] FIG. 1 illustrates an embodiment of adjusting weights of an artificial intelligence model based on input data according to various embodiments. [Figure 15] 1 is a flow chart illustrating an embodiment of incrementally training an artificial intelligence model based on input data in accordance with various embodiments. [Figure 16] 1 is a flowchart illustrating an example of an operation for providing customized food recommendations to a pet, according to various embodiments. [Figure 17] 1A to 1C are diagrams for explaining examples of improvement information and food information according to various embodiments. [Figure 18] 10 is a flowchart illustrating an example of an operation for obtaining improvement information according to various embodiments. [Figure 19] 11 is a flowchart illustrating yet another example of an operation for obtaining improvement information in accordance with various embodiments. [Figure 20] 1 is a flowchart illustrating an example of operations for determining at least one food item according to various embodiments. [Figure 21] 11 is a flowchart illustrating yet another example of operations for determining at least one food item in accordance with various embodiments. [Figure 22] 11 is a flowchart illustrating yet another example of operations for determining at least one food item in accordance with various embodiments. [Figure 23] FIG. 2 is a diagram illustrating an example of a user interface according to various embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0019] The examples described in this specification are intended to clearly explain the concept of the present invention to those having ordinary skill in the art to which the present invention pertains, and the present invention is not limited to the examples described in this specification. The scope of the present invention should be construed as including modifications or variations that do not deviate from the concept of the present invention.

[0020] The terms used in this specification are selected as general terms that are currently widely used as much as possible, taking into consideration the functions in the present invention, but this may vary depending on the intention of a person with ordinary skill in the art to which the present invention belongs, precedent cases, the emergence of new technology, etc. However, apart from this, when a specific term is used with a definition of an arbitrary meaning, the meaning of the term will be described separately. Therefore, the terms used in this specification should be interpreted based on the substantial meaning of the term and the entire content of this specification, rather than simply the name of the term.

[0021] The drawings attached to this specification are intended to easily explain the present invention, and the shapes shown in the drawings may be exaggerated as necessary to facilitate understanding of the present invention, and therefore the present invention is not limited by the drawings.

[0022] In this specification, each of the statements such as "A or B," "at least one of A and B," "at least one of A or B," "A, B or C," "at least one of A, B and C," and "at least one of A, B, or C" can include any one of the items listed in the statement or all possible combinations thereof.

[0023] In this specification, if it is determined that a specific description of a known configuration or function according to the present invention may obscure the gist of the present invention, the detailed description thereof will be omitted as necessary. In addition, numbers (e.g., 1st, 2nd, etc.) used in the description of this specification are merely identification symbols for distinguishing one component from another.

[0024] In addition, the suffixes "part" and "section" for components used in the following description are given or used interchangeably in consideration of making the specification easier to draft, and do not have distinct meanings or roles by themselves.

[0025] That is, the embodiments of the present invention are provided so that the present invention will be complete and will familiarize those skilled in the art with the scope of the present invention, and the present invention is defined only by the scope of the claims. Like reference numerals refer to like elements throughout the specification.

[0026] Terms such as "first" and / or "second" may be used to describe various components, but the components should not be limited by the terms. The terms are used only to distinguish one component from another, e.g., a first component may be referred to as a second component, and similarly, a second component may be referred to as a first component, without departing from the scope of the inventive concept.

[0027] When an element is referred to as being "coupled" or "connected" to another element, it should be understood that it may be directly coupled or connected to the other element, but that there may be other elements in between. On the other hand, when an element is referred to as being "directly coupled" or "directly connected" to another element, it should be understood that there are no other elements in between. Other expressions describing the relationship between elements, such as "between" and "immediately between," or "adjacent to" and "directly adjacent to," should be interpreted similarly.

[0028] In the figures, each block of the process flow chart and combinations of the flow charts may be performed by computer program instructions. These computer program instructions may be loaded onto a processor of a general purpose computer, a special purpose computer, or other programmable data processing device, such that the instructions executed through the processor of the computer or other programmable data processing device generate means for performing the functions described in the flow chart blocks. These computer program instructions may also be stored in a computer usable or computer readable memory that can direct a computer or other programmable data processing device to perform a function in a particular manner, such that the instructions stored in the computer usable or computer readable memory may produce an article of manufacture that includes instruction means for performing the functions described in the flow chart blocks. The computer program instructions may also be loaded onto a computer or other programmable data processing device, such that a sequence of operational steps are executed on the computer or other programmable data processing device to create a computer-implemented process, and the instructions executing the computer or other programmable data processing device may provide steps for performing the functions described in the flow chart blocks.

[0029] The machine-readable storage medium may also be provided in the form of a non-transitory storage medium. Here, "non-transitory" simply means that the storage medium is a tangible device and does not include a signal (e.g., electromagnetic waves), and this term does not distinguish between data being stored semi-permanently on the storage medium and data being stored temporarily.

[0030] Moreover, each block may represent a module, segment, or portion of code that includes one or more executable instructions for performing a particular logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may be performed out of order. For example, two blocks shown in succession may in fact be performed substantially simultaneously, or the blocks may sometimes be performed in reverse order according to their corresponding functions. For example, the operations performed by a module, program, or other component may be performed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be performed in a different order, omitted, or one or more other operations may be added.

[0031] The term "unit" as used herein means a software or hardware component such as a Field Programmable Gate Array (FPGA) or an Application Specific Integrated Circuit (ASIC). A "unit" is intended to perform a specific function, but is not limited to software or hardware. A "unit" may be configured to reside on an addressable storage medium and to implement one or more processors. Thus, in some embodiments, a "unit" includes components such as software components, object-oriented software components, class components, and task class components, as well as processes, functions, attributes, procedures, subroutines, program code segments, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The components and functions provided within the "units" may be further separated into components and units that are combined or added in fewer components and units. Moreover, the components and units may be implemented to implement one or more CPUs of a device or a security multimedia card. Furthermore, in various embodiments of the present invention, a "unit" may include one or more processors.

[0032] The operation principle of the present invention will be described in detail below with reference to the accompanying drawings. In the following, when it is determined that a detailed description of related known functions or configurations may unnecessarily obscure the gist of the present invention, the detailed description will be omitted. The terms described below are defined in consideration of the functions of the present invention, and may vary depending on the intention or practice of a user or operator. Therefore, the definitions must be based on the entire contents of this specification.

[0033] According to one embodiment of the present invention, there is provided an optimization method for an artificial intelligence (AI) model reflecting a pet's condition, a disease prediction method, and an operating method of an electronic device, a computing device, and a system in which such a method is implemented. According to one embodiment of the present invention, a method for operating an electronic device can be provided, the method including the steps of: acquiring, by at least one processor included in the electronic device, input data including quantitative data from the results of a PCR (Polymerase Chain Reaction) test and additional information related to the pet's health or disease; invoking a first artificial intelligence model for calculating a health score; and inputting the input data into the first artificial intelligence model to calculate a health score indicating the pet's health condition. In the above, quantitative data is obtained from the results of a PCR test. However, the test for obtaining quantitative data is not limited to a PCR test, and may be, for example, a blood test, as long as it is a test that can obtain information on the physical condition of a pet, including the health condition of the pet. In the following, a PCR test will be described as an example of a test for obtaining quantitative data.

[0034] The additional information may be obtained by receiving it from at least one of a user input or a pre-stored database.

[0035] The first artificial intelligence model may be implemented to include at least one weight for extracting at least one feature value corresponding to said input data.

[0036] The operation of calculating a health score may include an operation of applying at least one weighting based on the input data through at least one layer of the first artificial intelligence model, and an operation of outputting a health score through at least one layer of the first artificial intelligence model.

[0037] A method of operating an electronic device may be provided, further comprising the act of pre-processing input data to adjust at least one weight of said first artificial intelligence model.

[0038] A method for operating an electronic device may be provided, further comprising the steps of: calculating a first risk level associated with disease occurrence based on quantitative data; calculating a second risk level associated with health based on the additional information; and adjusting at least one weight of the first artificial intelligence model based on the first risk level and the second risk level.

[0039] The electronic device can calculate a first degree of risk posed by a pathogenic microorganism by analyzing the pathogen-specific quantitative values ​​contained in the quantitative data.

[0040] A method for operating an electronic device may be provided, further comprising the operation of additionally training the first artificial intelligence model based on input data and the health score.

[0041] An electronic device according to an embodiment of the present invention can analyze PCR test results to analyze a pet's disease status.

[0042] An electronic device according to another embodiment of the present invention can accurately determine the health of a pet based on information about the pet.

[0043] According to another embodiment of the present invention, the electronic device can recommend suitable foods reflecting the health and disease state of the pet.

[0044] The following describes an electronic device or a system including an electronic device that provides a solution for analyzing pet diseases and health based on diagnostic information about the pet.

[0045] FIG. 1 is a diagram illustrating a pet diagnostic system according to various embodiments.

[0046] The pet diagnostic system according to the present invention can determine the health condition of a companion animal (pet) and recommend food (e.g., pet food) suitable for promoting the pet's health. A PCR diagnostic test can be performed to predict the pet's disease. The system can also detect quantitative values ​​for multiple pathogens based on the diagnostic kit for which the PCR test was performed. The system can also train an artificial intelligence model based on the multiple quantitative values ​​from the PCR results and the clinical data set for the pet. In this case, the system can train an artificial intelligence model to calculate the probability of disease occurrence based on data related to the pet (e.g., PCR data, age data, etc.).

[0047] The system can use artificial intelligence models to accurately predict the probability of a pet developing a disease, and based on this, can determine the pet's health condition.

[0048] The system can also recommend suitable foods based on the pet's health condition. Specifically, the system can select at least one food suitable for the pet's health condition from a database of pre-stored pet foods and recommend it to the user.

[0049] Referring to FIG. 1, a pet diagnostic system according to the present invention may include an electronic device 100 for analyzing a pet's diagnostic results and a user device 110 that is provided with the pet's diagnostic results.

[0050] The electronic device 100 may receive diagnostic test results for the pet from a user. In this case, the diagnostic test results may refer to a test kit in which a sample from the pet is collected to perform a PCR test on the pet. The electronic device may analyze the received test results. The electronic device may analyze the received test results in a predetermined manner to determine the health condition of the pet. The electronic device may calculate a quantitative value of at least one pathogen contained in the sample from the pet based on the test results, and may determine the health condition of the pet based on the calculated value.

[0051] In addition, the electronic device 100 can provide the judgment result to at least one user device 110. The electronic device can provide, but is not limited to, pet health information, disease information, or food recommendation information through the interface of the user device.

[0052] FIG. 2 is a diagram illustrating the configuration of an electronic device according to various embodiments.

[0053] 2, the electronic device may include, but is not limited to, a processor 210, a memory 220, and a communication circuit 230, and may further include a configuration of an electronic device that is obvious to a person skilled in the art. In this case, the electronic device may include, but is not limited to, a server device.

[0054] The processor 210 may include at least one processor, at least some of which are implemented to provide different functions. For example, it may execute software (e.g., a program) to control at least one other component (e.g., a hardware or software component) of the electronic device connected to the processor 210, and perform various data processing or calculations. According to an embodiment, as at least a part of the data processing or calculation, the processor 210 may store instructions or data received from other components in the memory 220 (e.g., a volatile memory), process the instructions or data stored in the volatile memory, and store the result data in the non-volatile memory. According to an embodiment, the processor 210 may include a main processor (e.g., a central processing unit or an application processor) or an auxiliary processor (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor. For example, if the electronic device includes a main processor and an auxiliary processor, the auxiliary processor may be configured to use less power than the main processor or to be specialized for a designated function. The auxiliary processor may be implemented separately from or as part of the main processor. The auxiliary processor may, for example, control at least a portion of the functionality or state associated with at least one of the components of the electronic device (e.g., the communication circuitry 230) on behalf of the main processor while the main processor is in an inactive (e.g., sleep) state, or together with the main processor while the main processor is in an active (e.g., application execution) state. According to one embodiment, the auxiliary processor (e.g., an image signal processor or a communication processor) may be implemented as part of another component (e.g., the communication circuitry 230) with which it is functionally associated.According to an embodiment, the auxiliary processor (e.g., a neural network processing device) may include a hardware structure specialized for processing the artificial intelligence model. The artificial intelligence model may be generated through machine learning. Such learning may be performed, for example, within the electronic device on which the artificial intelligence model is executed, or through a separate server. The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the above examples. The artificial intelligence model may include multiple artificial neural network layers. The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRRDNN), a deep Q-networks, or a combination of two or more thereof, but is not limited to the above examples. The artificial intelligence model may additionally or alternatively include a software structure in addition to the hardware structure, while the operation of the electronic device (or computing device) described below may be understood as the operation of the processor 210.

[0055] The processor 210 included in the electronic device 200 according to the present invention can provide multiple functions for pets. Specifically, the processor 210 can perform a disease prediction function for predicting the probability of disease occurrence by analyzing the diagnostic test results of the pet, a health score calculation function for scoring the health condition of the pet based on clinical data, or a food recommendation function for recommending food suitable for the pet's health condition, etc. For example, the processor 210 can include, but is not limited to, a disease prediction unit 211, a health score calculation unit 212, and a food recommendation unit 213.

[0056] In the present invention, the processor is described as being divided into a number of units (e.g., "parts") based on their functions, but this is merely for the convenience of explanation, and each unit is not necessarily realized by separate hardware. In other words, the multiple units included in the processor may be realized by separate hardware, or may be realized by a single piece of hardware.

[0057] The disease prediction unit 211 can calculate the probability of disease occurrence by analyzing the diagnostic test results of the pet (e.g., quantitative data of pathogens from PCR results) using at least one artificial intelligence model. Details of the method for predicting diseases in pets using the disease prediction unit 211 will be described in Figures 7 to 11.

[0058] The health score calculation unit 212 can use at least one artificial intelligence model to analyze the disease state and / or health state of the pet based on the clinical data to calculate the overall health score of the pet. Details of the method for calculating the pet's health score using the health score calculation unit 212 will be described in Figures 12 to 15.

[0059] The food recommendation unit 213 can provide at least one recommended food by determining a food suitable for the health condition of the pet using a pre-stored food database. Details of the food recommendation method using the food recommendation unit 213 will be described with reference to Figs. 16 to 18.

[0060] The memory 220 can store various data output by at least one component of the electronic device (e.g., the processor 210). The data can include, for example, input data or output data for software (e.g., programs) and associated instructions therefor. The memory 220 can include volatile or non-volatile memory. The memory 220 can be implemented to store an operating system, middleware or applications, and / or artificial intelligence models as described above.

[0061] Furthermore, the memory 220 included in the electronic device 200 according to the present invention may include at least one database constructed for a specific purpose. Specifically, the electronic device 200 may include at least one database constructed to predict the health and / or disease state of a pet and recommend a suitable food. For example, the memory 220 may include, but is not limited to, a clinical DB 221 that stores information on a doctor's diagnosis results regarding the pet's health, a PCR DB 222 that stores information on the pet's PCR test results, a food DB 223 that stores information on a plurality of pet foods, or a health record DB 224 that stores information on the pet's health history (e.g., the presence or absence of a past medical history, the presence or absence of a disease, etc.).

[0062] The electronic device 200 may also be implemented to store at least one of the databases described above using the memory 220, but is not limited to this, and may also be implemented to receive data (e.g., medical data regarding a pet) that has been pre-stored on an external device (e.g., a hospital server).

[0063] The communication circuitry 230 can support the establishment of a direct (e.g., wired) or wireless communication channel between the electronic device and an external electronic device (e.g., a user device) and the execution of communication over the established communication channel. The communication circuitry 230 can include one or more communication processors (e.g., communication chips) that operate independently of the processor 210 (e.g., a program processor) and support the direct (e.g., wired) or wireless communication. According to an embodiment, the communication circuitry 230 can include a wireless communication module (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (e.g., a mobile device, a wearable device, or a server device) through a first network (e.g., a short-range communication network such as Bluetooth, WiFi (wireless fidelity) direct, or IrDA (infrared data association)) or a second network (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). Such various types of communication modules may be integrated in one component (e.g., a single chip) or may be realized in multiple components (e.g., multiple chips) that are separate from each other. The wireless communication module can identify or authenticate the M electronic device in a communication network such as the first network or the second network using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identity module. The wireless communication module can support 5G networks after 4G networks and next-generation communication technologies such as NR access technology.NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module can support, for example, a high frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module can support various technologies to ensure performance in the high frequency band, such as beamforming, massive MIMO (multiple-input and multiple-output), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. According to one embodiment, the wireless communication module can support a peak data rate (e.g., 20 Gbps or more) for implementing eMBB, loss coverage (e.g., 164 dB or less) for implementing mMTC, or U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less round trip) for implementing URLLC.

[0064] FIG. 3 is a diagram illustrating an electronic device including an artificial intelligence model trained based on training data related to a pet, according to various embodiments.

[0065] FIG. 4 is a diagram showing an example of PCR quantitative data.

[0066] 3, the electronic device can build a database (DB) for model learning based on data related to the pet. Here, the term database (DB) can refer to a collection of data built according to a predetermined structure, but is not limited thereto, and can also refer to a collection of data grouped according to a specific purpose (e.g., learning an artificial intelligence model).

[0067] For example, the electronic device may include health data related to the pet's health and disease data related to the pet's disease.

[0068] In the present invention, the "health data" may be any grouping of at least one data related to the health condition of a pet. For example, the health data may include, but is not limited to, basic data related to basic information of a pet, such as the pet's age, species, and sex, BCS (Body Condition Score) data related to the pet's obesity state, and questionnaire data related to a questionnaire on the pet's health.

[0069] Furthermore, in the present invention, "disease data" may be any grouping of at least one data related to a pet's disease. For example, the disease data may include, but is not limited to, interview data related to the results of an interview regarding the pet's disease, disease history data related to the pet's past and current medical history, or disease score data related to the pet's probability of developing a disease.

[0070] In addition, without being limited thereto, the electronic device may further include additional information related to PCR quantitative data based on PCR test results, health score data based on scoring results for the pet's health condition, medical data related to the pet's medical records, or further information about the pet.

[0071] For example, the PCR quantitative data can be displayed as formatted data as shown in Figure 4, and can be displayed as data arranged for each test item. Specifically, the PCR quantitative data can include multiple quantitative values ​​indicating the detection levels of multiple pathogens.

[0072] The electronic device can also train an artificial intelligence model based on a training data set constructed based on the above-mentioned data.

[0073] In this case, the electronic device can build an artificial intelligence model suitable for predicting diseases of pets based on a predetermined formula.

[0074] For example, the electronic device can train multiple artificial intelligence models based on samples related to a pet's disease and select one artificial intelligence model based on the disease prediction accuracy of the trained models.

[0075] As a specific example, the electronic device can identify oral bacteria associated with periodontal disease, train five machine learning models (logistic regression, random forest, support vector machine, decision tree, K-nearest neighbor), and then select the machine learning model that can most accurately predict the progression of periodontal disease. Furthermore, the electronic device can input microbial quantitative data from a newly obtained saliva sample to the selected machine learning model to identify the accuracy, specificity, and sensitivity of predicting the progression of periodontal disease.

[0076] The electronic device can collect information on the pet's health and illnesses, as well as doctors' medical records, to construct a clinical database (clinical DB), and can derive information on the pet's health and illnesses by training an artificial intelligence model based on the constructed clinical database.

[0077] [Pet disease and health prediction] FIG. 5 illustrates how an electronic device may use an artificial intelligence model to obtain output data based on input data, according to various embodiments.

[0078] Referring to FIG. 5, the electronic device can input input data (Input) to the artificial intelligence model. For example, the input data can include, but is not limited to, PCR data, physical information (e.g., age), medical interview / health information, etc. In addition, the electronic device can preprocess the input data based on a preprocessing algorithm and input the preprocessed data to the artificial intelligence model. A database stores a plurality of pieces of information, such as data that affect the pet's health or disease. In preprocessing by the preprocessing algorithm, a weight is assigned to the input data based on at least one factor of the plurality of pieces of information stored in the database. In the artificial intelligence model, a weight is set for each of the plurality of pieces of information, and the weight is adjusted by learning. That is, in the artificial intelligence model, for example, data that affects the pet's health or disease is updated by learning at any time, and the weight is updated and set at any time according to the magnitude of the influence on the pet's health or disease. Data updated by learning at any time includes, but is not limited to, health data, disease data, PCR quantitative data, health score data, medical data, and additional information, as shown in FIG. 3. In addition, data that is updated through learning from time to time may include, but is not limited to, information regarding a doctor's diagnosis of a pet's health as stored in a clinical DB221, information regarding a pet's PCR test results as stored in a PCR DB222, information regarding a number of pet foods as stored in a food DB223, and information regarding a pet's health history as stored in a health record DB224, as shown in FIG. 2.

[0079] The electronic device can obtain output data by processing input data using an artificial intelligence model. For example, the output data can include, but is not limited to, a disease score indicating the probability of disease occurrence in the pet, or a health score indicating the health condition of the pet. The electronic device can also obtain output data using an artificial intelligence model trained based on a pre-stored database (DB, e.g., clinical data). Specifically, the electronic device can obtain an artificial intelligence model in which at least one weight is set based on a plurality of pieces of information stored in the database, and can obtain output data by processing input data using the artificial intelligence model. That is, the electronic device updates various data from time to time through learning using the artificial intelligence model, and processes input data based on the learned various data to obtain output data. For example, the electronic device obtains output data by extracting information useful for improving the pet's health or disease, etc. by collating input data with various data learned from time to time using the artificial intelligence model. By learning various data from time to time, optimal output data updated from time to time for improving the pet's health or disease, etc. can be obtained. As a specific example, but not limited to, each database is associated with a health condition as a criterion. For example, the pet's past and current medical history, PCR quantitative data based on PCR test results, etc. are associated with medical data related to the pet's medical records such as the pet's disease, and this association is learned and updated by the artificial intelligence model as needed. Thus, the electronic device can obtain information on the pet's disease in a state updated as output data by inputting input data (Input) such as PCR quantitative data into the artificial intelligence model. Also, but not limited to, the pet's past and current medical history, PCR quantitative data based on PCR test results, medical data related to the pet's medical records such as the pet's disease, etc. are associated with pet food according to the pet's health condition, and this association is learned and updated as needed by the artificial intelligence model. Thus, the electronic device can obtain information on recommended pet food in a state updated as output data by inputting input data (Input) such as PCR quantitative data into the artificial intelligence model.

[0080] A weight can be assigned to at least one factor affecting the pet's health or disease, and the electronic device can learn the influence of the at least one factor by learning at least one weight of the artificial intelligence model based on learning data reflecting the at least one factor.

[0081] FIG. 6 illustrates how an electronic device can predict a pet's likelihood of developing a disease based on PCR data, according to various embodiments.

[0082] FIG. 7 is a diagram showing the correlation between pathogenic microorganisms and diseases.

[0083] 6, the electronic device can obtain quantitative data including a plurality of quantitative values ​​based on the PCR test result. In this case, the quantitative data can include a plurality of quantitative values ​​corresponding to the detection levels of a plurality of pathogens. For example, the quantitative data can include, but is not limited to, a first quantitative value corresponding to the detection level of a first pathogen, a second quantitative value corresponding to the detection level of a second pathogen, and a third quantitative value corresponding to the detection level of a third pathogen.

[0084] The electronic device may also process the quantitative data with an artificial intelligence model to obtain a disease score indicative of the pet's probability of developing a disease. Specifically, the electronic device may process the quantitative data based on at least one pre-processing algorithm and at least one disease prediction model to obtain the disease score.

[0085] The electronic device may include a pre-processing algorithm and a disease prediction model corresponding to a disease to be predicted. Specifically, the electronic device may include a plurality of artificial intelligence models optimized for a plurality of pet diseases, and may use the artificial intelligence model corresponding to the disease to be predicted.

[0086] For example, the electronic device may include, but is not limited to, a first pre-processing algorithm and a first disease prediction model for predicting a first disease, a second pre-processing algorithm and a second disease prediction model for predicting a second disease, and a third pre-processing algorithm and a third disease prediction model for predicting a third disease, etc.

[0087] The electronic device can input at least one quantitative value corresponding to the predicted target disease based on the PCR quantitative data into the artificial intelligence model.

[0088] Pathogens detected in pets are correlated with at least one disease (or illness). For example, referring to FIG. 7, diseases associated with nine pathogenic microorganisms (Tannerella forsythia, Treponema denticola, Prevotella intermedia, Fusobacterium nucleatum, Prevotella nigrescenes, Camphylobacter rectus, Eubacterium nodatum, Parvimonas micra, Eikenella) are shown.

[0089] For example, Tannerella forsythia is associated with type 2 diabetes, rheumatoid arthritis, myocardial infarction, atherosclerosis, premature birth, coronary artery disease, chronic obstructive pulmonary disease, chronic kidney disease, and Alzheimer's disease; Treponema denticola is associated with acute myocardial infarction, type 2 diabetes, atherosclerosis, gastric cancer, chronic obstructive pulmonary disease, chronic kidney disease, Alzheimer's disease, and gestational hypertension; Prevotella intermedia is associated with myocardial infarction, premature birth, cardiovascular disease, hypertension, coronary artery disease, acute bronchitis, and Alzheimer's disease; Fusobacterium nucleatum is associated with type 2 diabetes, atherosclerosis, premature birth, gastric cancer, stillbirth, colon cancer, osteomyelitis, cavernous sinus thrombosis, acute bronchitis, Alzheimer's disease, colon cancer, myocarditis, myopericarditis, and acute encephalopathy; Prevotella nigrescenes is associated with stroke, diabetes, premature birth, and coronary artery disease; Camphylobacter rectus is associated with osteomyelitis, thoracic empyema, sacroiliac joint inflammation, sepsis, and coronary artery disease; Eubacterium nodatum is associated with Alzheimer's disease and type 1 diabetes; Parvimonas micra is associated with endocarditis, septic arthritis, and infectious arthritis; and Eikenella corrodens is associated with osteomyelitis, arthritis, liver abscess, endocarditis, parapneumonic pleural effusion, empyema, diabetes, lung infection, abdominal infection, skin infection, skeletal infection, endocarditis, malignancy, coronary artery disease, and pancreatic abscess.

[0090] The electronic device may store a matching table reflecting the above-mentioned pathogen-to-disease correlations, and may utilize the matching table to identify correlations between pathogens and diseases.

[0091] As an example, the electronic device can predict the probability of a pet developing a disease by determining a predicted target disease based on PCR quantitative data and a matching table.

[0092] FIG. 8 is a flow chart illustrating one embodiment in which an electronic device obtains a disease score, according to various embodiments.

[0093] FIG. 9 illustrates a specific method for an electronic device to determine a predicted target disease, according to various embodiments.

[0094] 8, the electronic device (or at least one processor included in the electronic device) may perform an operation of obtaining quantitative data including a plurality of quantitative values ​​corresponding to each of a plurality of pathogens according to a PCR test result, in accordance with an operation S801. In this case, the electronic device may obtain quantitative data including a plurality of quantitative values ​​corresponding to the detection levels of the plurality of pathogens through a multiplex PCR analysis for the plurality of pathogens.

[0095] The electronic device may also perform an operation of determining at least one predicted target disease based on the multiple quantitative values, via operation S803, where the electronic device may determine the predicted target disease based on a pre-stored matching table reflecting correlations between pathogens and diseases.

[0096] Specifically, referring to FIG. 9, the electronic device can identify at least one quantitative value having a value equal to or greater than a predetermined standard value among a plurality of quantitative values ​​by operation S901. At this time, the predetermined standard value can be determined clinically. Specifically, the predetermined standard value can be a reference point set based on an inflammation value (two or more levels of the standard inflammation value) that requires treatment. That is, the electronic device can identify at least one pathogen having a level of amount that requires treatment, and identify at least one quantitative value corresponding to the pathogen.

[0097] Further, the electronic device can identify at least one pathogen corresponding to the identified quantitative value by operation S903. Further, the electronic device can determine at least one predicted target disease corresponding to the identified at least one pathogen based on a pre-stored matching table by step S905. Specifically, the electronic device can determine at least one predicted target disease by identifying a pathogen having a value equal to or greater than a predetermined standard value and identifying at least one disease corresponding to the identified pathogen.

[0098] In this case, the matching table may further include information regarding at least one disease that the pathogen affects, and information regarding the level to which the pathogen affects each pathogen.

[0099] The electronic device may determine the predicted target disease by selecting at least one disease with a high level of impact from the pathogen based on the matching table.

[0100] For example, the electronic device can determine the predicted target disease by selecting at least one disease in which the pathogen has an influence level equal to or greater than a predetermined threshold value. Further, for example, the electronic device can determine the predicted target disease by selecting the disease in which the pathogen has an influence level that is the highest.

[0101] Furthermore, when multiple pathogens are identified by operation S903, the electronic device can determine a prediction target disease based on the frequency of diseases corresponding to the multiple pathogens. Specifically, the electronic device can determine at least one disease commonly corresponding to the multiple pathogens as a prediction target disease.

[0102] The electronic device can also determine the predicted target disease based on the amount of pathogenic microorganisms determined by the multiple quantitative values ​​and the presence or absence of a disease caused by the pathogenic microorganisms. Specifically, the electronic device can determine the predicted target disease by setting a weight according to the amount of pathogenic microorganisms determined by the multiple quantitative values ​​and the presence or absence of a disease caused by the pathogenic microorganisms.

[0103] 8 again, the electronic device may execute an operation of selecting a pre-processing algorithm and an artificial intelligence model based on the determined prediction target disease by operation S805. Specifically, the electronic device may select a pre-processing algorithm and an artificial intelligence model suitable for the prediction target disease from among a plurality of pre-processing algorithms and a plurality of artificial intelligence models. At this time, the selected artificial intelligence model may be a model trained to calculate the occurrence probability of the prediction target disease.

[0104] In addition, the electronic device may perform an operation of pre-processing the quantitative data corresponding to the prediction target disease by the selected pre-processing algorithm in step S807. Specifically, the electronic device may pre-process the input data to adjust at least one weight.

[0105] In addition, the electronic device can execute an operation of inputting the preprocessed data to the selected artificial intelligence model and outputting a disease score indicating a disease occurrence probability corresponding to the prediction target disease by operation S809. At this time, the electronic device can obtain a plurality of disease scores corresponding to each of the plurality of prediction target diseases for the plurality of prediction target diseases.

[0106] The electronic device can improve the accuracy of disease prediction by selecting an optimal artificial intelligence model based on input data and outputting a result value. In addition, the electronic device can reduce calculation costs by performing calculations using the selected artificial intelligence model, since unnecessary calculations are not performed.

[0107] In another embodiment, the electronic device can predict the probability of a pet developing a disease by analyzing the PCR quantitative data based on the determined predicted target disease.

[0108] FIG. 10 is a flow chart illustrating another embodiment in which an electronic device obtains a disease score, according to various embodiments.

[0109] 10, the electronic device can determine the prediction target disease as the first disease by operation S1001. At this time, the electronic device can determine the prediction target disease as the first disease based on the user's input. Also, the electronic device can determine the prediction target disease as the first disease by inputting input data (e.g., PCR quantitative data) into a first pre-processing algorithm corresponding to the first disease.

[0110] The electronic device may also select at least one pathogen associated with the first disease based on a pre-stored matching table, via operation S1003.

[0111] Furthermore, the electronic device can input at least one quantitative value corresponding to at least one pathogen to the first model by operation S1005. In this case, the first model can learn to calculate the occurrence probability of the first disease based on the quantitative data. For example, the quantitative data includes multiple quantitative values ​​corresponding to the detection levels of multiple pathogens, and the first model learns a correlation between the quantitative data and the occurrence probability of the first disease, and calculates the occurrence probability of the first disease based on the quantitative data.

[0112] Furthermore, the electronic device may, by operation S1007, calculate a first disease score indicating the probability of occurrence of the first disease using at least one layer included in the first model.

[0113] FIG. 11 is a flow chart illustrating yet another embodiment in which an electronic device obtains a disease score, according to various embodiments.

[0114] Referring to FIG. 11, the electronic device may perform an operation to obtain quantitative data according to a PCR test result, by an operation S1101.

[0115] In addition, the electronic device may perform an operation of acquiring additional information (e.g., physical / medical history / health / disease information) related to the pet based on the user's input through operation S1103. At this time, the additional information may include data related to the pet's health or disease. Specifically, the additional information may include basic information including the pet's age information, gender information, species information, etc. In addition, the additional information may include questionnaire data related to the pet's health and medical history data related to the pet's disease. Furthermore, the additional information may include disease history information related to the pet's disease history.

[0116] Furthermore, the electronic device may obtain additional information corresponding to the disease to be predicted. Specifically, the electronic device may store additional information necessary for predicting a specific disease in advance and use it to predict the specific disease. In this case, the additional information may include medical information that is medically confirmed as necessary for predicting the specific disease.

[0117] For example, the electronic device can use dental images (e.g., dental X-rays, etc.) as additional information to predict periodontal disease. Also, for example, the electronic device can use endoscopic examination information, parasite examination information, stool examination information, etc. as additional information to predict digestive disease. Also, for example, the electronic device can use dementia interview information as additional information to predict dementia.

[0118] The electronic device may also execute an operation of calculating a disease score corresponding to at least one disease based on the quantitative data and the additional information by operation S1105. The electronic device may calculate a disease score indicating a probability of disease occurrence based on the disease occurrence risk according to the PCR quantitative data and the disease occurrence risk according to the additional information.

[0119] The electronic device can optimize the artificial intelligence model using various information related to the disease to be predicted, and can output highly accurate results using the artificial intelligence model that has learned the influence of quantitative data from PCR results, pet health, and various data related to the disease.

[0120] The electronic device according to the present invention can calculate an overall health score of a pet, reflecting the pet's health condition and disease scores for multiple diseases.

[0121] FIG. 12 illustrates how an electronic device calculates a health score, according to various embodiments.

[0122] Referring to FIG. 12, the electronic device may obtain a health score indicating the overall health of the pet based on data related to the pet's health or disease.

[0123] Specifically, the electronic device may use a health score calculation model (artificial intelligence model) to calculate a health score based on input data related to the pet.

[0124] In this case, the input data may include PCR quantitative data according to the PCR diagnostic test result. The PCR quantitative data may include a plurality of quantitative values ​​corresponding to the degree of detection of a plurality of pathogens. The quantitative data has been described above in detail and will not be described here.

[0125] Additionally, the input data may include health data related to the pet's health or disease data related to the pet's disease.

[0126] For example, the electronic device may obtain the health or disease data based on a questionnaire about the pet's health or a medical interview about the pet, or by receiving information about the pet from a medical database.

[0127] Health or disease data may include, but is not limited to, basic data such as the pet's age, BCS data, disease history data, and the like.

[0128] The electronic device can train a health score calculation model based on a pre-stored clinical database (DB). In this case, the clinical database can store pet health data / disease data and corresponding health scores. Specifically, the electronic device can train an artificial intelligence model to calculate a health score based on the pet health data and disease data.

[0129] The electronic device can also adjust the weights of the health score calculation unit based on the acquired health or disease data, and calculate the health score by assigning the adjusted weights to the input data (or feature values ​​extracted based on the input data).

[0130] In addition, the electronic device can update the clinical database and additionally train the health score calculation model based on the updated data set. Specifically, the database can be updated by acquiring information on the pet's health data / disease data and the corresponding health scores, thereby additionally training the health score calculation model.

[0131] This allows for an optimized artificial intelligence model to be obtained that can calculate a health score reflecting the pet's health based on pet data in various environments and corresponding medical findings.

[0132] As a specific example, the electronic device can obtain a health score calculation model with adjusted weights based on input data including PCR quantitative data, basic data, BCS data, and disease history data, and obtain a health score through at least one output layer included in the health score calculation model. The electronic device can also re-learn the health score calculation model based on the input data and the output health score.

[0133] FIG. 13 is a flow chart illustrating a method for an electronic device to obtain a health score according to various embodiments.

[0134] 13, the electronic device can execute an operation of acquiring quantitative data based on a PCR test result in operation S1301. Details of operation S1301 have been described above and will not be repeated here.

[0135] The electronic device may also perform an operation of obtaining additional information related to the pet based on the user's input, via operation S1303. In this case, the additional information may include health data related to the pet's health and disease data related to the pet's disease. For example, the electronic device may obtain the pet's age data, BCS data, or disease history data, etc.

[0136] Additionally, without being limited thereto, the electronic device may retrieve additional information related to the pet from at least one database stored in the memory.

[0137] The electronic device may also execute an operation of calling a first artificial intelligence model for calculating a health score by operation S1305. At this time, the first artificial intelligence model may be an artificial intelligence model trained to output a health score based on the pet's health / disease data. Specifically, the first artificial intelligence model may include parameters including a plurality of weights corresponding to data included in the training data. The first artificial intelligence model may include at least one weight for extracting at least one feature value corresponding to the input data.

[0138] In addition, the electronic device may input the input data to the first artificial intelligence model to calculate a health score indicating the health status of the pet, via operation S1307. Specifically, the electronic device may apply at least one weighting based on the input data through at least one layer of the artificial intelligence model, and may output a health score through at least one layer of the artificial intelligence model.

[0139] At this time, the electronic device can adjust the weights based on the input data. For example, the electronic device can adjust weights corresponding to the amount of pathogens determined by PCR quantitative data included in the input data, the presence or absence of diseases caused by pathogens, age, BCS, disease history, etc.

[0140] FIG. 14 illustrates an embodiment of adjusting weights of an artificial intelligence model based on input data, according to various embodiments.

[0141] 14, the electronic device can obtain a health score indicating the health of the pet by processing the input data using an artificial intelligence model 1400. In this case, the health score may be a score evaluated based on a doctor's diagnosis score, with 100 points set as the healthiest standard, but is not limited thereto, and may be at least one index for relatively indicating the health of the pet.

[0142] The electronic device can calculate a first risk level associated with the occurrence of a disease based on the PCR quantitative data. Specifically, the electronic device can perform a regression analysis of the quantitative values ​​for each pathogen included in the PCR quantitative data to calculate the first risk level caused by the pathogenic microorganism. For example, the electronic device can calculate the first risk level caused by the pathogenic microorganism by comparing the quantitative value with a disease standard amount of the microorganism (a value determined by clinical practice, a reference point of an inflammation value that requires treatment), but is not limited thereto.

[0143] Further, the electronic device can calculate a second risk level related to the pet's health based on additional information related to the pet's health and disease. Specifically, the electronic device can calculate the second risk level by analyzing the pet's health and disease related information (e.g., age, BCS, disease history, etc.) and scoring the influence of each of the additional information. For example, but not limited to, the electronic device can calculate an age risk score based on the pet's age, a BCS risk score based on the pet's BCS, and a disease history based on the pet's disease history.

[0144] Further, the electronic device can adjust at least one weight of the artificial intelligence model 1400 based on the calculated risk level, and the electronic device can obtain a health score reflecting the health status of the pet by assigning the adjusted weight.

[0145] 13, the electronic device may store the input data and the health score in a database, per operation S1309. Additionally, the electronic device may re-train the first artificial intelligence model based on the data stored in the database to adjust at least one weight, per operation S1311.

[0146] Through this, the electronic device can train an artificial intelligence model so that even if the quantitative values ​​of pathogenic microorganisms are similar, the higher the risk based on the pet's health data and disease data, the higher the probability of disease occurrence will be output.

[0147] FIG. 15 is a flow chart illustrating an embodiment of incrementally training an artificial intelligence model based on input data, according to various embodiments.

[0148] 15, the electronic device may perform an operation of obtaining quantitative data corresponding to a PCR test result in operation S1501. Also, the electronic device may perform an operation of obtaining additional information related to the pet based on a user's input in operation S1503.

[0149] The electronic device may also use the artificial intelligence model to calculate a first risk level indicating the probability of occurrence of the first disease based on the quantitative data, by operation S1505. The electronic device may also use the artificial intelligence model to calculate a second risk level indicating the probability of occurrence of the first disease based on the additional information, by operation S1507.

[0150] Also, the electronic device can obtain, by operation S1509, a health score related to the pet's health condition based on the first risk level and the second risk level using the artificial intelligence model. Furthermore, the electronic device can adjust at least one weight related to the quantitative data and the additional information based on the input value and the output value of the artificial intelligence model by operation S1511. That is, the artificial intelligence model included in the electronic device can learn the influence of the obtained data related to the pet's health and disease on the probability of disease occurrence and the associated health score.

[0151] This allows electronic devices to improve the accuracy of their artificial intelligence models as they accumulate databases.

[0152] [Food Recommendations] For the health of pets, it is important that they consume foods appropriate for their health or disease state.

[0153] An electronic device according to an embodiment of the present invention may provide a function of recommending foods suitable for improving the health of a pet in consideration of the pet's health and disease state. In this case, the electronic device may pre-store information on various foods, select at least one food suitable for improving the pet's health from a pre-stored database, and provide the selected recommended food to a user device.

[0154] The pet food recommendation function of the electronic device will now be described in detail.

[0155] 16 is a flow chart illustrating an example of operations for providing customized food recommendations to a pet according to various embodiments. Operations may be performed out of the order of the operations shown and / or described, and more and / or fewer operations may be performed.

[0156] 16, in operation S2101, the electronic device can obtain a first data set based on a pet's health or disease state. For example, the first data set can include the pet's health or disease data described above.

[0157] According to various embodiments, in operation S2103, the electronic device can obtain improvement information of the pet based on the first data set. In the present invention, "improvement information" can be used as a term to mean information about the part (e.g., function, nutrients) that needs to be improved for the health of the pet. More details regarding the operation of obtaining improvement information will be described in the description of Figures 17 to 19.

[0158] FIG. 17 is a diagram for explaining an example of improvement information and food information according to various embodiments.

[0159] For example, referring to FIG. 17, the improvement information may include at least one of information on an improved function and information on an improved nutrient. In the present invention, the term "improved function" may be used as a term meaning a health function of a pet that needs to be improved (for example, at least a part of a function of the pet's body, etc.), and may be replaced with terms such as "function to be improved" and "function requiring improvement" depending on the case. For example, the information on an improved function may include information on at least one improved function. Here, examples of the improved function may include, but are not limited to, oral health, intestinal health, skin and hair health, eye health, diet, bone health, immune health, blood circulation health, and joint health. In the present invention, the term "improved nutrient" means a nutrient related to the improvement of a pet's health or disease, and may include nutrients that need to be taken in for functional improvement and nutrients whose intake is limited for functional improvement. For example, the information on an improved nutrient may include information on at least one improved nutrient. Here, examples of nutrients may include, but are not limited to, crude protein, crude fat, crude fiber, crude ash, calcium, phosphorus, vitamin A, vitamin D, zinc, omega 6, omega 3, metabolic energy, etc. For example, the information on improved nutrients may include information on limiting nutrients and information on necessary nutrients. In the present invention, the term "limiting nutrients" can be used as a term meaning nutrients whose intake is limited for functional improvement. In the present invention, the term "necessary nutrients" can be used as a term meaning nutrients whose intake is required for functional improvement. For example, examples of limiting nutrients and necessary nutrients are as shown in below.

[0160] [Table 1]

[0161] For example, when the function to be improved is the urinary system, vitamin A, vitamin B2, vitamin C, vitamin E, saponin, etc. may be the necessary nutrients that need to be taken to improve urinary system function. However, sodium, phosphate, excess protein, etc. may be the limiting nutrients that need to be taken to improve urinary system function.

[0162] According to various embodiments, the information on the improved function may include information on a plurality of improved functions, and the information on the improved nutrients may include comprehensive nutrient information based on information on the nutrients corresponding to each of the plurality of improved functions. For example, if the improved functions are the urinary and respiratory systems, vitamin C, vitamin E, etc. may be comprehensive necessary nutrients that need to be taken to improve the urinary and respiratory functions. However, sodium may be a comprehensive restricted nutrient whose intake is restricted to improve the urinary and respiratory functions.

[0163] According to various embodiments, the electronic device may include a food database (DB) that stores information about various foods. Alternatively, according to various embodiments, the electronic device may receive information from an externally constructed food database (DB). For example, the food database may be configured in the form of Table 2 below.

[0164] [Table 2]

[0165] The food database may include food information regarding a plurality of foods (a first food, a second food, ...). For example, the food information may include nutrient content information for each of the plurality of foods. The nutrient content information may include information such as nutritional components, component content, and calories. According to various embodiments, the food information may further include labeling information indicating a function to be improved. According to various embodiments, the food information may further include information such as a brand name providing the food, a product name by which the food can be identified, and a product image.

[0166] By storing various food information in the food database, the electronic device can use the pre-stored food information to determine recommended foods that meet the user's needs, which has the effect of reducing the amount of calculations required by the processor. Also, since a database of foods that are actually sold is created, the user can actually purchase and use the recommended foods that have been determined.

[0167] 18 is a flow chart illustrating an example of an operation S2103 of obtaining remediation information according to various embodiments. Operations may be performed out of the order of the operations shown and / or described, and more operations and / or fewer operations may be performed.

[0168] According to various embodiments, referring to FIG. 18, in operation S2301, the electronic device can determine the vulnerable function of the pet based on the first data set. In operation S2303, the electronic device can obtain information of the improved function based on the determined vulnerable function. In the present invention, the term "vulnerable function" can be used to mean a vulnerable health function of the pet (e.g., at least a part of the function of the pet's body). For example, the electronic device can determine one or more vulnerable functions based on the first data set. Thereby, the obtained information of the improved function can include information on one or more improved functions. For example, when the information on the improved functions is included, the electronic device can determine the priority among the multiple improved functions. Here, the electronic device can determine the priority based on the risk of the improved function and the probability of disease occurrence. By determining the priority among the improved functions in this manner, the improved function to be prioritized for the user's pet can be determined, which can provide the user with efficient recommended food.

[0169] According to various embodiments, in operation S2305, the electronic device can determine the limiting nutrients and the required nutrients corresponding to any one of the improvement functions according to the information of the improvement function. For example, the limiting nutrients and the required nutrients corresponding to any one of the improvement functions can be determined as a single nutrient or multiple nutrients, respectively.

[0170] According to various embodiments, when the restricted nutrients and / or required nutrients are determined as a plurality of nutrients, in operation S2307, the electronic device can determine the priority order among the plurality of nutrients for each of the restricted nutrients and / or required nutrients. For example, when the restricted nutrients corresponding to any one of the improvement functions are determined as nutrients A, B, and C, the priority order among the nutrients A to C can be determined. For example, when the required nutrients corresponding to any one of the improvement functions are determined as nutrients D, E, and F, the priority order among the nutrients D to F can be determined. For example, the electronic device can determine the priority order based on the influence of each of the plurality of nutrients on the improvement function. For example, a nutrient having a large influence on the improvement function may have a high priority order. By determining the priority order among the plurality of nutrients for each of the restricted nutrients and required nutrients in this way, the improvement nutrients prioritized for the user's pet can be determined, which makes it possible to provide the user with efficient recommended foods.

[0171] According to various embodiments, in operation S2309, the electronic device can obtain information on improved nutrients based on the determined limiting nutrients and necessary nutrients. According to various embodiments, in operation S2311, the electronic device can obtain improvement information including information on the improved function and information on improved nutrients. The improvement information can be used to determine the recommended foods when the electronic device, which will be described later, provides recommended foods divided into recommended foods by function. By obtaining information on improved nutrients based on limiting nutrients and necessary nutrients in this way, information on nutrients corresponding to a specific improved function can be provided to the user's pet, which has the effect of providing recommended foods by function and providing recommended foods for improving a specific function.

[0172] 19 is a flowchart illustrating a further example of an operation of obtaining remediation information (S2103) according to various embodiments. The operations may be performed out of the order of the operations shown and / or described, and more and / or fewer operations may be performed.

[0173] According to various embodiments, referring to FIG. 19, in operation S2401, the electronic device can determine a vulnerable function of the pet based on a first data set. In operation S2403, the electronic device can obtain information of a plurality of improved functions based on the determined vulnerable function. For example, the electronic device can determine a plurality of vulnerable functions based on a first data set. Thereby, the obtained information of the improved function can include information on a plurality of improved functions. For example, the electronic device can determine a priority order among the plurality of improved functions. Otherwise, the operations S2401 and S2403 can be performed similarly to the above-mentioned operations S2301 and S2303, and therefore, a duplicated description will be omitted.

[0174] According to various embodiments, in operation S2404, the electronic device can obtain information of a first improved nutrient based on a first limited nutrient and a first required nutrient corresponding to a first improvement function, and can obtain information of a second improved nutrient based on a second limited nutrient and a second required nutrient corresponding to a second improvement function. The operation S2404 can be performed in the same manner as S2305 and S2307 above, and therefore a duplicated description will be omitted. According to various embodiments, the operation S2404 can further obtain information of an nth improved nutrient based on an nth limited nutrient and an nth required nutrient corresponding to an nth improvement function (wherein n is a natural number equal to or greater than 3).

[0175] According to various embodiments, in operation S2405, the electronic device can determine the overall restricted nutrients and required nutrients based on the information of the improvement function, the information of the first improved nutrients, and the information of the second improved nutrients. The "overall restricted nutrients" and "overall required nutrients" in the present invention can be used as terms that mean the corresponding restricted nutrients and required nutrients by considering all of the multiple improved functions included in the information of the improvement function, rather than corresponding to only one of the improved functions of the pet. For example, the electronic device can determine the overall restricted nutrients and the overall required nutrients based on the priority between the multiple improved functions. Here, the higher the priority of the improved function, the more the restricted nutrients and the required nutrients corresponding to the function can be determined as the overall restricted nutrients and the overall required nutrients. For example, the electronic device can determine the overall restricted nutrients and the overall required nutrients based on the restricted nutrients and the required nutrients frequencies corresponding to the multiple improved functions. Here, the restricted nutrients and the required nutrients corresponding to the multiple improved functions may be common, but the higher the corresponding frequency of the restricted nutrients and the required nutrients, the more the restricted nutrients and the required nutrients can be determined as the overall restricted nutrients and the overall required nutrients. For example, the total limiting nutrient and the total required nutrient can be determined as one or more nutrients, respectively. According to various embodiments, the operation S2405 can determine the total limiting nutrient and the total required nutrient based on the information of the improvement function, the information of a first improved nutrient, the information of a second improved nutrient, ..., and n (where n is a natural number of 3 or more) improved nutrients.

[0176] According to various embodiments, when the limiting nutrients and / or the necessary nutrients are determined as a plurality of nutrients, in operation S2407, the electronic device may determine a priority among the plurality of nutrients for each of the limiting nutrients and the necessary nutrients. For example, when the comprehensive limiting nutrients are determined as nutrients A, B, and C, the priority among the nutrients A to F may be determined. For example, when the comprehensive necessary nutrients are determined as nutrients D, E, and F, the priority among the nutrients D to F may be determined. For example, the electronic device may determine a priority based on the influence of each of the plurality of nutrients on the improvement function. For example, a nutrient having a large influence on the improvement function may have a high priority. For example, the electronic device may determine a priority based on the frequency with which each of the plurality of nutrients corresponds to a plurality of improvement functions. For example, a nutrient having a high frequency with which it corresponds to a plurality of improvement functions may have a high priority. In this way, by determining a priority among the plurality of nutrients for each of the comprehensive limiting nutrients and the comprehensive necessary nutrients, an improvement nutrient prioritized for the user's pet may be determined, which allows the user to provide efficient recommended food.

[0177] According to various embodiments, in operation S2409, the electronic device may obtain information on improved nutrients based on the determined overall limiting nutrients and overall required nutrients. According to various embodiments, in operation S2411, the electronic device may obtain improvement information including information on improved nutrients. The improvement information can be used to determine the recommended foods when the electronic device classifies and provides recommended foods according to nutrients, which will be described later. By obtaining information on improved nutrients based on the overall limiting nutrients and overall required nutrients, the nutrients that need to be improved for the user's pet can be provided not simply as nutrients corresponding to a specific improvement function, but by considering all of the various improvement functions of the user's pet, and information on the corresponding nutrients can be provided, which has the effect of providing recommended foods according to nutrients and providing recommended foods for more comprehensive pet health rather than specific function improvement.

[0178] In various embodiments, referring again to FIG. 16, in operation S2105, the electronic device can obtain labeling information indicating the function to be improved for each of the multiple foods included in the food database. For this purpose, a labeling operation indicating the function to be improved for each of the multiple foods included in the food database may be required. The above operation is for matching food information with information on the improvement function in operation S2109 for determining foods to be matched, which will be described later. This has the effect of reducing the amount of calculation, since matching with food information is possible without obtaining information on improved nutrients corresponding to the information on the improvement function. Specific contents of the above operation will be described later with reference to FIG. 20.

[0179] According to various embodiments, in operation S2107, the electronic device may obtain food information from a food database. Here, the food database may include information on foods to be recommended. The food database has been described with reference to FIG. 17, and detailed description thereof will be omitted. According to various embodiments, the food database may be input with information from a producer who produces the food. For example, the food database may be input by an operator who operates the electronic device of the present invention directly collecting and inputting information on foods. For example, the food database may be input in conjunction with information known as food labels, etc.

[0180] According to various embodiments, in operation S2109, the electronic device can compare the improvement information and the food information to determine at least one food that matches the improvement information. Referring again to FIG. 17, the electronic device can compare the pet improvement information 2220 and the food database 2210 to determine at least one recommended food.

[0181] Specifically, the electronic device can determine at least one recommended food by comparing the information on the improvement function among the improvement information of the pet and the labeled improvement target function among the food information in the food database. For example, the electronic device can determine, as a recommended food, a food labeled with an improvement target function corresponding to at least one improvement function included in the information on the improvement function. For example, the information on the improvement function may be the information acquired in S2309 described above.

[0182] The electronic device can also compare the improved nutrient information from the pet's improvement information with the contained nutrient information from the food information in the food database to determine at least one recommended food. For example, the electronic device can determine, as a recommended food, a food that contains at least one nutrient included in the required nutrient information from among a plurality of foods included in the food database. According to various embodiments, by comparing the contained nutrient information, the electronic device can recommend an optimal food in consideration of the restricted nutrients and required nutrients from the pet's improvement information. For example, the improved nutrient information can be the information acquired in S2309. For example, the improved nutrient information can be the information acquired in S2409.

[0183] A specific embodiment of determining recommended foods based on functions and nutrients will be further described below through the description of Figs. 20 to 22.

[0184] 20 is a flow chart illustrating an example of an operation S2109 of determining at least one food item, according to various embodiments. The operations may be performed out of the order of the operations shown and / or described, and more and / or fewer operations may be performed.

[0185] According to various embodiments, in operation S2501, the electronic device can obtain labeling information for a plurality of foods included in the food database, the labeling information indicating the function to be improved for each of the plurality of foods. The operation S2501 can be performed in the same manner as the above-mentioned operation S2105, and therefore a duplicated description will be omitted.

[0186] According to various embodiments, in operation S2503, the electronic device may select any one of the improvement functions included in the improvement function information. According to various embodiments, in operation S2505, the electronic device may compare the selected improvement function and labeling information to determine at least one food. For example, in operation S2501, the electronic device may obtain labeling information in which the improvement target function is "eye function" for a food containing carrot in the food database. Thereafter, if the electronic device selects "eye function" as one of the functions that needs to be improved according to the improvement function information in operation S2503, the improvement function information and food information are matched in operation S2505, and the food containing carrot may be determined as a recommended food. According to various embodiments, in operation S2113 described below, the electronic device may classify the recommended foods into recommended foods by function and provide them.

[0187] 21 is a flow chart illustrating another example of an operation S2109 of determining at least one food item, according to various embodiments. The operations may be performed out of the order of the operations shown and / or described, and more and / or fewer operations may be performed.

[0188] According to various embodiments, in operation S2601, the electronic device may select one of the improvement functions included in the information of the improvement functions. The operation S2601 may be performed in the same manner as the above-mentioned operation S2503, and therefore a duplicated description will be omitted.

[0189] According to various embodiments, in operation S2603, the electronic device can obtain information of improved nutrients corresponding to the selected improvement function. For example, the electronic device can perform the same as the above-mentioned operations S2305 and S2309. Specifically, the electronic device can determine limit nutrients and required nutrients corresponding to any one of the selected improvement functions. Then, based on the determined limit nutrients and required nutrients, information of improved nutrients can be obtained.

[0190] According to various embodiments, in operation S2605, the electronic device can assign a score to a food containing a necessary nutrient included in the information of the improved nutrient based on the priority and content of the necessary nutrient. Here, the priority of the necessary nutrient may be determined in the above-mentioned operation S2307. For example, if any one of the necessary nutrients has a high priority determined in the above-mentioned operation S2307, the electronic device can assign a high score to the food containing the necessary nutrient. For example, if the content of the necessary nutrient included in any one of the foods is high, the electronic device can assign a high score to the food.

[0191] According to various embodiments, in operation S2607, the electronic device can exclude foods that contain a certain amount or more of the limiting nutrients included in the information on the improving nutrients. For example, the certain amount can be set based on an amount that is limited in intake with respect to the improving function. For example, the certain amount can mean an effective amount that has a negative effect on the improving function.

[0192] According to various embodiments, in operation S2609, the electronic device may assign a score to foods that have been assigned a score equal to or greater than a certain value based on a predetermined criterion. For example, foods that have been assigned a score equal to or greater than a certain value may be foods that effectively have a positive effect on the improvement function due to the necessary nutrients contained in the foods. For example, the predetermined criterion may be determined based on the popularity of the food, the calories of the food, the pet's preferences (e.g., texture, dosage form, size, etc.), whether or not allergenic ingredients are contained, and the like. For example, if any one of the foods is popular, the electronic device may assign a high score to the food. For example, based on the calories of any one of the foods and the improvement information of the pet, the electronic device may assign a score to the food. For example, if the improvement information of the pet is related to obesity, the electronic device may assign a high score to a low-calorie food. For example, if any one of the foods matches the pet's preferences (e.g., texture, dosage form, size, etc.), the electronic device may assign a high score to the food. For example, if any one of the foods contains an allergenic ingredient of the pet, the electronic device may exclude the food. This has the effect of providing recommended foods according to not only improved function information or improved nutrient information but also various other criteria, thereby providing recommended foods that meet the needs of the user.

[0193] According to various embodiments, in operation S2611, the electronic device may determine a ranking of foods based on the assigned scores. According to various embodiments, in operation S2613, the electronic device may determine at least one food as a recommended food based on the determined ranking. According to various embodiments, in operation S2113 described below, the electronic device may provide the recommended foods by classifying them into recommended foods by function.

[0194] 22 is a flow chart illustrating another example of an operation S2109 of determining at least one food item, according to various embodiments. The operations may be performed out of the order of the operations shown and / or described, and more and / or fewer operations may be performed.

[0195] According to various embodiments, in operation S2701, the electronic device can select any one of the comprehensive required nutrients included in the information of improved nutrients.

[0196] According to various embodiments, in act S2703, the electronic device can sort foods that contain the selected necessary nutrients. According to various embodiments, in act S2705, the electronic device can assign scores to the sorted foods based on the content of the necessary nutrients. For example, if a food has a high content of a necessary nutrient, the electronic device can assign a high score to the food.

[0197] According to various embodiments, in operation S2707, the electronic device can exclude foods that contain a certain value or more of the comprehensive limiting nutrients included in the information on the improving nutrients. For example, the certain value can be set based on an amount that is limited in intake with respect to the improving function. For example, the certain value can mean an effective amount that has a negative effect on the improving function.

[0198] According to various embodiments, in operation S2709, the electronic device may assign a score based on a predetermined criterion to foods that have been assigned a score above a certain value. Since operation S2709 may be performed in the same manner as operation S2609 described above, a duplicate description will be omitted.

[0199] According to various embodiments, in operation S2711, the electronic device may determine a ranking of foods based on the assigned scores. According to various embodiments, in operation S2713, the electronic device may determine at least one food as a recommended food based on the determined ranking. According to various embodiments, in operation S2113 described below, the electronic device may provide the recommended foods by classifying them into recommended foods by nutrients. The operations S2711 and S2713 may be performed in the same manner as S2611 and S2613 described above, and therefore repeated explanations will be omitted.

[0200] According to various embodiments, referring again to FIG. 16, in operation S2111, the electronic device may select at least one recommended food based on the determined at least one food. According to various embodiments, in operation S2113, the at least one recommended food may be provided to the user through a user interface. For example, the electronic device may provide the at least one recommended food as a recommended food by function or a recommended food by nutrient. For example, the electronic device may provide the at least one recommended food determined in the above-mentioned operation S2505 as a recommended food by function. For example, the electronic device may provide the at least one recommended food determined in the above-mentioned operation S2613 as a recommended food by function. For example, the electronic device may provide the at least one recommended food determined in the above-mentioned operation S2713 as a recommended food by nutrient. In this way, the electronic device may provide the recommended food by classifying it into a recommended food by function or a recommended food by nutrient, thereby providing a recommended food customized according to the user's demand, thereby satisfying the user and providing an efficient service.

[0201] An electronic device according to an embodiment of the present invention may provide information through a display device of a user device. In particular, the electronic device may provide an interface including information related to a food recommendation function.

[0202] 23 is a diagram for explaining an example of a user interface according to various embodiments. For example, the interface may include at least one of a first interface 2801 showing improvement information, a second interface 2802 showing at least one recommended food, and a third interface 2803 showing the improvement effect of the recommended food.

[0203] For example, the improvement information shown on the first interface 2801 may include information on an improvement function or information on an improvement nutrient. The information on the improvement function may be information on an improvement function obtained by the above-mentioned operation S2309. The information on the improvement nutrients may be information on an improvement nutrient including information on comprehensive required nutrients obtained by the above-mentioned operation S2409. This has the effect that the electronic device provides the user with the information obtained by the above-mentioned operation, so that the user can not only receive recommended foods but also obtain improvement information of the pet, thereby obtaining more accurate and specific information about the pet's health.

[0204] For example, the recommended food shown in the second interface 2802 may be the recommended food determined in the above-mentioned operations S2505, S2613, and S2713. For example, the second interface may further show information regarding a product image of the recommended food, a product name by which the food can be identified, a brand name providing the food, etc. This has the effect of allowing the electronic device to further provide various information regarding the recommended food, thereby making it easier for the user to understand the information of the provided recommended food and helping the user to actually purchase it.

[0205] For example, the improvement effect of the recommended food shown in the third interface 2803 may include information about the expected health improvement effect when the recommended food is ingested. This has the effect that the electronic device provides information about the health improvement effect, which allows the user to easily understand the health improvement effect of the recommended food and allows the user to more clearly recognize the effect of improving the health of the pet.

[0206] Although the embodiments have been described above by way of limited embodiments and drawings, those having ordinary skill in the art may make various modifications and variations from the above description. For example, the described techniques may be performed in an order different from that described, and / or the components of the described systems, structures, devices, circuits, etc. may be combined or combined in a manner different from that described, or may be replaced by other components or equivalents, and still achieve suitable results.

[0207] Therefore, other embodiments, examples, and equivalents of the claims are also within the scope of the following claims. [Explanation of symbols]

[0208] 100: Electronic Devices 210: Processor 220: Memory 230: Communication circuit

Claims

1. by at least one processor included in the electronic device, obtaining input data including quantitative data resulting from testing, including PCR testing, and additional information related to the pet's health or disease; Invoking a first artificial intelligence model to calculate a health score; and inputting the input data into the first artificial intelligence model and calculating a health score indicating the health status of the pet.

2. The method of claim 1 , wherein the additional information is obtained by receiving it from at least one of a user input or a pre-stored database.

3. The method of claim 1 , wherein the first artificial intelligence model is implemented to include at least one weight for extracting at least one feature value corresponding to the input data.

4. The operation of calculating the health score includes: applying at least one weight based on the input data through at least one layer of the first artificial intelligence model; and outputting a health score through at least one layer of a first artificial intelligence model.

5. The method of claim 1 , further comprising the act of pre-processing the input data to adjust at least one weight of the first artificial intelligence model.

6. calculating a first risk associated with disease occurrence based on the quantitative data; calculating a second health-related risk based on the additional information; The method of claim 1 , further comprising: adjusting at least one weight of the first artificial intelligence model based on the first risk level and the second risk level.

7. The method of claim 6 , further comprising the step of: calculating a first risk level posed by a pathogenic microorganism by analyzing quantitative values ​​for each pathogen included in the quantitative data.

8. The method of claim 1 , further comprising: additionally training the first artificial intelligence model based on the input data and the health score.

9. Memory and at least one processor electronically connected to the memory; The at least one processor Obtain input data including quantitative data from testing, including PCR testing, and additional information related to the pet's health or disease; Invoking a first artificial intelligence model for calculating a health score; A computing device configured to input the input data into the first artificial intelligence model and calculate a health score indicative of the pet's health status.

10. A server comprising the computing device of claim 9; and at least one user device that obtains pet health or disease information based on a communication connection with the server.

Images